[PATCH Kernel v22 8/8] vfio: Selective dirty page tracking if IOMMU backed device pins pages
Added a check such that only singleton IOMMU groups can pin pages.
>From the point when vendor driver pins any pages, consider IOMMU group
dirty page scope to be limited to pinned pages.
To optimize to avoid walking list often, added flag
pinned_page_dirty_scope to indicate if all of the vfio_groups for each
vfio_domain in the domain_list dirty page scope is limited to pinned
pages. This flag is updated on first pinned pages request for that IOMMU
group and on attaching/detaching group.
Signed-off-by: Kirti Wankhede
Reviewed-by: Neo Jia
---
drivers/vfio/vfio.c | 13 +++--
drivers/vfio/vfio_iommu_type1.c | 103 +---
include/linux/vfio.h| 4 +-
3 files changed, 109 insertions(+), 11 deletions(-)
diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index 765e0e5d83ed..580099afeaff 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -85,6 +85,7 @@ struct vfio_group {
atomic_topened;
wait_queue_head_t container_q;
boolnoiommu;
+ unsigned intdev_counter;
struct kvm *kvm;
struct blocking_notifier_head notifier;
};
@@ -555,6 +556,7 @@ struct vfio_device *vfio_group_create_device(struct
vfio_group *group,
mutex_lock(&group->device_lock);
list_add(&device->group_next, &group->device_list);
+ group->dev_counter++;
mutex_unlock(&group->device_lock);
return device;
@@ -567,6 +569,7 @@ static void vfio_device_release(struct kref *kref)
struct vfio_group *group = device->group;
list_del(&device->group_next);
+ group->dev_counter--;
mutex_unlock(&group->device_lock);
dev_set_drvdata(device->dev, NULL);
@@ -1945,6 +1948,9 @@ int vfio_pin_pages(struct device *dev, unsigned long
*user_pfn, int npage,
if (!group)
return -ENODEV;
+ if (group->dev_counter > 1)
+ return -EINVAL;
+
ret = vfio_group_add_container_user(group);
if (ret)
goto err_pin_pages;
@@ -1952,7 +1958,8 @@ int vfio_pin_pages(struct device *dev, unsigned long
*user_pfn, int npage,
container = group->container;
driver = container->iommu_driver;
if (likely(driver && driver->ops->pin_pages))
- ret = driver->ops->pin_pages(container->iommu_data, user_pfn,
+ ret = driver->ops->pin_pages(container->iommu_data,
+group->iommu_group, user_pfn,
npage, prot, phys_pfn);
else
ret = -ENOTTY;
@@ -2050,8 +2057,8 @@ int vfio_group_pin_pages(struct vfio_group *group,
driver = container->iommu_driver;
if (likely(driver && driver->ops->pin_pages))
ret = driver->ops->pin_pages(container->iommu_data,
-user_iova_pfn, npage,
-prot, phys_pfn);
+group->iommu_group, user_iova_pfn,
+npage, prot, phys_pfn);
else
ret = -ENOTTY;
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index d74b76919cbb..f5b79a71e9f7 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -73,6 +73,7 @@ struct vfio_iommu {
boolv2;
boolnesting;
booldirty_page_tracking;
+ boolpinned_page_dirty_scope;
};
struct vfio_domain {
@@ -100,6 +101,7 @@ struct vfio_group {
struct iommu_group *iommu_group;
struct list_headnext;
boolmdev_group; /* An mdev group */
+ boolpinned_page_dirty_scope;
};
struct vfio_iova {
@@ -143,6 +145,10 @@ struct vfio_regions {
static int put_pfn(unsigned long pfn, int prot);
+static struct vfio_group *vfio_iommu_find_iommu_group(struct vfio_iommu *iommu,
+ struct iommu_group *iommu_group);
+
+static void update_pinned_page_dirty_scope(struct vfio_iommu *iommu);
/*
* This code handles mapping and unmapping of user data buffers
* into DMA'ble space using the IOMMU
@@ -592,11 +598,13 @@ static int vfio_unpin_page_external(struct vfio_dma *dma,
dma_addr_t iova,
}
static int vfio_iommu_type1_pin_pages(void *iommu_data,
+ struct iommu_group *iommu_group,
unsigned long *user_pfn,
int npage, int prot,
unsigned long *phys_pfn)
{
struct vfio_iommu *iommu = iommu_data;
+ struct vfio_group *group;
int i, j, ret;
unsigned long rem
[PATCH Kernel v22 8/8] vfio: Selective dirty page tracking if IOMMU backed device pins pages
Added a check such that only singleton IOMMU groups can pin pages.
>From the point when vendor driver pins any pages, consider IOMMU group
dirty page scope to be limited to pinned pages.
To optimize to avoid walking list often, added flag
pinned_page_dirty_scope to indicate if all of the vfio_groups for each
vfio_domain in the domain_list dirty page scope is limited to pinned
pages. This flag is updated on first pinned pages request for that IOMMU
group and on attaching/detaching group.
Signed-off-by: Kirti Wankhede
Reviewed-by: Neo Jia
---
drivers/vfio/vfio.c | 13 +++--
drivers/vfio/vfio_iommu_type1.c | 103 +---
include/linux/vfio.h| 4 +-
3 files changed, 109 insertions(+), 11 deletions(-)
diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index 765e0e5d83ed..580099afeaff 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -85,6 +85,7 @@ struct vfio_group {
atomic_topened;
wait_queue_head_t container_q;
boolnoiommu;
+ unsigned intdev_counter;
struct kvm *kvm;
struct blocking_notifier_head notifier;
};
@@ -555,6 +556,7 @@ struct vfio_device *vfio_group_create_device(struct
vfio_group *group,
mutex_lock(&group->device_lock);
list_add(&device->group_next, &group->device_list);
+ group->dev_counter++;
mutex_unlock(&group->device_lock);
return device;
@@ -567,6 +569,7 @@ static void vfio_device_release(struct kref *kref)
struct vfio_group *group = device->group;
list_del(&device->group_next);
+ group->dev_counter--;
mutex_unlock(&group->device_lock);
dev_set_drvdata(device->dev, NULL);
@@ -1945,6 +1948,9 @@ int vfio_pin_pages(struct device *dev, unsigned long
*user_pfn, int npage,
if (!group)
return -ENODEV;
+ if (group->dev_counter > 1)
+ return -EINVAL;
+
ret = vfio_group_add_container_user(group);
if (ret)
goto err_pin_pages;
@@ -1952,7 +1958,8 @@ int vfio_pin_pages(struct device *dev, unsigned long
*user_pfn, int npage,
container = group->container;
driver = container->iommu_driver;
if (likely(driver && driver->ops->pin_pages))
- ret = driver->ops->pin_pages(container->iommu_data, user_pfn,
+ ret = driver->ops->pin_pages(container->iommu_data,
+group->iommu_group, user_pfn,
npage, prot, phys_pfn);
else
ret = -ENOTTY;
@@ -2050,8 +2057,8 @@ int vfio_group_pin_pages(struct vfio_group *group,
driver = container->iommu_driver;
if (likely(driver && driver->ops->pin_pages))
ret = driver->ops->pin_pages(container->iommu_data,
-user_iova_pfn, npage,
-prot, phys_pfn);
+group->iommu_group, user_iova_pfn,
+npage, prot, phys_pfn);
else
ret = -ENOTTY;
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 5c3dc5863893..a6b9e13ef57c 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -73,6 +73,7 @@ struct vfio_iommu {
boolv2;
boolnesting;
booldirty_page_tracking;
+ boolpinned_page_dirty_scope;
};
struct vfio_domain {
@@ -100,6 +101,7 @@ struct vfio_group {
struct iommu_group *iommu_group;
struct list_headnext;
boolmdev_group; /* An mdev group */
+ boolpinned_page_dirty_scope;
};
struct vfio_iova {
@@ -143,6 +145,10 @@ struct vfio_regions {
static int put_pfn(unsigned long pfn, int prot);
+static struct vfio_group *vfio_iommu_find_iommu_group(struct vfio_iommu *iommu,
+ struct iommu_group *iommu_group);
+
+static void update_pinned_page_dirty_scope(struct vfio_iommu *iommu);
/*
* This code handles mapping and unmapping of user data buffers
* into DMA'ble space using the IOMMU
@@ -590,11 +596,13 @@ static int vfio_unpin_page_external(struct vfio_dma *dma,
dma_addr_t iova,
}
static int vfio_iommu_type1_pin_pages(void *iommu_data,
+ struct iommu_group *iommu_group,
unsigned long *user_pfn,
int npage, int prot,
unsigned long *phys_pfn)
{
struct vfio_iommu *iommu = iommu_data;
+ struct vfio_group *group;
int i, j, ret;
unsigned long rem
