On Wed, April 23, 2025 1:19 PM Cavitt, Jonathan wrote:
> Add support for userspace to request a list of observed faults from a
> specified
> VM.
>
> v2:
> - Only allow querying of failed pagefaults (Matt Brost)
>
> v3:
> - Remove unnecessary size parameter from helper function, as it
> is a property of the arguments. (jcavitt)
> - Remove unnecessary copy_from_user (Jainxun)
> - Set address_precision to 1 (Jainxun)
> - Report max size instead of dynamic size for memory allocation
> purposes. Total memory usage is reported separately.
>
> v4:
> - Return int from xe_vm_get_property_size (Shuicheng)
> - Fix memory leak (Shuicheng)
> - Remove unnecessary size variable (jcavitt)
>
> v5:
> - Rename ioctl to xe_vm_get_faults_ioctl (jcavitt)
> - Update fill_property_pfs to eliminate need for kzalloc (Jianxun)
>
> v6:
> - Repair and move fill_faults break condition (Dan Carpenter)
> - Free vm after use (jcavitt)
> - Combine assertions (jcavitt)
> - Expand size check in xe_vm_get_faults_ioctl (jcavitt)
> - Remove return mask from fill_faults, as return is already -EFAULT or 0
> (jcavitt)
>
> v7:
> - Revert back to using xe_vm_get_property_ioctl
> - Apply better copy_to_user logic (jcavitt)
>
> v8:
> - Fix and clean up error value handling in ioctl (jcavitt)
> - Reapply return mask for fill_faults (jcavitt)
>
> v9:
> - Future-proof size logic for zero-size properties (jcavitt)
> - Add access and fault types (Jianxun)
> - Remove address type (Jianxun)
>
> v10:
> - Remove unnecessary switch case logic (Raag)
> - Compress size get, size validation, and property fill functions into a
> single helper function (jcavitt)
> - Assert valid size (jcavitt)
>
> v11:
> - Remove unnecessary else condition
> - Correct backwards helper function size logic (jcavitt)
>
> v12:
> - Use size_t instead of int (Raag)
>
> v13:
> - Remove engine class and instance (Ivan)
>
> v14:
> - Map access type, fault type, and fault level to user macros (Matt
> Brost, Ivan)
>
> v15:
> - Remove unnecessary size assertion (jcavitt)
>
> Signed-off-by: Jonathan Cavitt <jonathan.cav...@intel.com>
> Suggested-by: Matthew Brost <matthew.br...@intel.com>
> Cc: Jainxun Zhang <jianxun.zh...@intel.com>
> Cc: Shuicheng Lin <shuicheng....@intel.com>
> Cc: Raag Jadav <raag.ja...@intel.com>
> Cc: Ivan Briano <ivan.bri...@intel.com>
LGTM.
Reviewed-by: Shuicheng Lin <shuicheng....@intel.com>
> ---
> drivers/gpu/drm/xe/xe_device.c | 3 +
> drivers/gpu/drm/xe/xe_vm.c | 107
> +++++++++++++++++++++++++++++++++
> drivers/gpu/drm/xe/xe_vm.h | 2 +
> 3 files changed, 112 insertions(+)
>
> diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
> index 75e753e0a682..6816dc3a428c 100644
> --- a/drivers/gpu/drm/xe/xe_device.c
> +++ b/drivers/gpu/drm/xe/xe_device.c
> @@ -196,6 +196,9 @@ static const struct drm_ioctl_desc xe_ioctls[] = {
> DRM_IOCTL_DEF_DRV(XE_WAIT_USER_FENCE,
> xe_wait_user_fence_ioctl,
> DRM_RENDER_ALLOW),
> DRM_IOCTL_DEF_DRV(XE_OBSERVATION, xe_observation_ioctl,
> DRM_RENDER_ALLOW),
> + DRM_IOCTL_DEF_DRV(XE_VM_GET_PROPERTY,
> xe_vm_get_property_ioctl,
> + DRM_RENDER_ALLOW),
> +
> };
>
> static long xe_drm_ioctl(struct file *file, unsigned int cmd, unsigned long
> arg)
> diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index
> 107e397b4987..c20ac51d8573 100644
> --- a/drivers/gpu/drm/xe/xe_vm.c
> +++ b/drivers/gpu/drm/xe/xe_vm.c
> @@ -3600,6 +3600,113 @@ int xe_vm_bind_ioctl(struct drm_device *dev,
> void *data, struct drm_file *file)
> return err;
> }
>
> +/*
> + * Map access type, fault type, and fault level from current bspec
> + * specification to user spec abstraction. The current mapping is
> + * 1-to-1, but if there is ever a hardware change, we will need
> + * this abstraction layer to maintain API stability through the
> + * hardware change.
> + */
> +static u8 xe_to_user_access_type(u8 access_type) {
> + return access_type;
> +}
> +
> +static u8 xe_to_user_fault_type(u8 fault_type) {
> + return fault_type;
> +}
> +
> +static u8 xe_to_user_fault_level(u8 fault_level) {
> + return fault_level;
> +}
> +
> +static int fill_faults(struct xe_vm *vm,
> + struct drm_xe_vm_get_property *args) {
> + struct xe_vm_fault __user *usr_ptr = u64_to_user_ptr(args->data);
> + struct xe_vm_fault store = { 0 };
> + struct xe_vm_fault_entry *entry;
> + int ret = 0, i = 0, count, entry_size;
> +
> + entry_size = sizeof(struct xe_vm_fault);
> + count = args->size / entry_size;
> +
> + spin_lock(&vm->faults.lock);
> + list_for_each_entry(entry, &vm->faults.list, list) {
> + if (i++ == count)
> + break;
> +
> + memset(&store, 0, entry_size);
> +
> + store.address = entry->address;
> + store.address_precision = entry->address_precision;
> +
> + store.access_type = xe_to_user_access_type(entry-
> >access_type);
> + store.fault_type = xe_to_user_fault_type(entry->fault_type);
> + store.fault_level = xe_to_user_fault_level(entry->fault_level);
> +
> + ret = copy_to_user(usr_ptr, &store, entry_size);
> + if (ret)
> + break;
> +
> + usr_ptr++;
> + }
> + spin_unlock(&vm->faults.lock);
> +
> + return ret ? -EFAULT : 0;
> +}
> +
> +static int xe_vm_get_property_helper(struct xe_vm *vm,
> + struct drm_xe_vm_get_property *args) {
> + size_t size;
> +
> + switch (args->property) {
> + case DRM_XE_VM_GET_PROPERTY_FAULTS:
> + spin_lock(&vm->faults.lock);
> + size = size_mul(sizeof(struct xe_vm_fault), vm->faults.len);
> + spin_unlock(&vm->faults.lock);
> +
> + if (args->size)
> + /*
> + * Number of faults may increase between calls to
> + * xe_vm_get_property_ioctl, so just report the
> + * number of faults the user requests if it's less
> + * than or equal to the number of faults in the VM
> + * fault array.
> + */
> + return args->size <= size ? fill_faults(vm, args) : -
> EINVAL;
> +
> + args->size = size;
> + return 0;
> + }
> + return -EINVAL;
> +}
> +
> +int xe_vm_get_property_ioctl(struct drm_device *drm, void *data,
> + struct drm_file *file)
> +{
> + struct xe_device *xe = to_xe_device(drm);
> + struct xe_file *xef = to_xe_file(file);
> + struct drm_xe_vm_get_property *args = data;
> + struct xe_vm *vm;
> + int ret = 0;
> +
> + if (XE_IOCTL_DBG(xe, args->reserved[0] || args->reserved[1]))
> + return -EINVAL;
> +
> + vm = xe_vm_lookup(xef, args->vm_id);
> + if (XE_IOCTL_DBG(xe, !vm))
> + return -ENOENT;
> +
> + ret = xe_vm_get_property_helper(vm, args);
> +
> + xe_vm_put(vm);
> + return ret;
> +}
> +
> /**
> * xe_vm_bind_kernel_bo - bind a kernel BO to a VM
> * @vm: VM to bind the BO to
> diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h index
> 9bd7e93824da..63ec22458e04 100644
> --- a/drivers/gpu/drm/xe/xe_vm.h
> +++ b/drivers/gpu/drm/xe/xe_vm.h
> @@ -196,6 +196,8 @@ int xe_vm_destroy_ioctl(struct drm_device *dev, void
> *data,
> struct drm_file *file);
> int xe_vm_bind_ioctl(struct drm_device *dev, void *data,
> struct drm_file *file);
> +int xe_vm_get_property_ioctl(struct drm_device *dev, void *data,
> + struct drm_file *file);
>
> void xe_vm_close_and_put(struct xe_vm *vm);
>
> --
> 2.43.0
