[Intel-gfx] [PATCH v5 2/5] drm/i915/display: handle migration for dpt
Ville Syrjälä
ville.syrjala at linux.intel.com
Tue Oct 4 13:31:07 UTC 2022
On Tue, Oct 04, 2022 at 02:19:13PM +0100, Matthew Auld wrote:
> On platforms like DG2, it looks like the dpt path here is missing the
> migrate-to-lmem step on discrete platforms.
>
> v2:
> - Move the vma_pin() under the for_i915_gem_ww(), otherwise the
> object can be moved after dropping the lock and then doing the pin.
>
> Fixes: 33e7a975103c ("drm/i915/xelpd: First stab at DPT support")
> Signed-off-by: Matthew Auld <matthew.auld at intel.com>
> Cc: Jianshui Yu <jianshui.yu at intel.com>
> Cc: Ville Syrjälä <ville.syrjala at linux.intel.com>
> Cc: Nirmoy Das <nirmoy.das at intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala at linux.intel.com>
> ---
> drivers/gpu/drm/i915/display/intel_fb_pin.c | 51 +++++++++++++--------
> 1 file changed, 33 insertions(+), 18 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/display/intel_fb_pin.c b/drivers/gpu/drm/i915/display/intel_fb_pin.c
> index 0cd9e8cb078b..5031ee5695dd 100644
> --- a/drivers/gpu/drm/i915/display/intel_fb_pin.c
> +++ b/drivers/gpu/drm/i915/display/intel_fb_pin.c
> @@ -26,10 +26,17 @@ intel_pin_fb_obj_dpt(struct drm_framebuffer *fb,
> struct drm_device *dev = fb->dev;
> struct drm_i915_private *dev_priv = to_i915(dev);
> struct drm_i915_gem_object *obj = intel_fb_obj(fb);
> + struct i915_gem_ww_ctx ww;
> struct i915_vma *vma;
> u32 alignment;
> int ret;
>
> + /*
> + * We are not syncing against the binding (and potential migrations)
> + * below, so this vm must never be async.
> + */
> + GEM_WARN_ON(vm->bind_async_flags);
> +
> if (WARN_ON(!i915_gem_object_is_framebuffer(obj)))
> return ERR_PTR(-EINVAL);
>
> @@ -37,29 +44,37 @@ intel_pin_fb_obj_dpt(struct drm_framebuffer *fb,
>
> atomic_inc(&dev_priv->gpu_error.pending_fb_pin);
>
> - ret = i915_gem_object_lock_interruptible(obj, NULL);
> - if (!ret) {
> + for_i915_gem_ww(&ww, ret, true) {
> + ret = i915_gem_object_lock(obj, &ww);
> + if (ret)
> + continue;
> +
> + if (HAS_LMEM(dev_priv)) {
> + ret = i915_gem_object_migrate(obj, &ww, INTEL_REGION_LMEM_0);
> + if (ret)
> + continue;
> + }
> +
> ret = i915_gem_object_set_cache_level(obj, I915_CACHE_NONE);
> - i915_gem_object_unlock(obj);
> - }
> - if (ret) {
> - vma = ERR_PTR(ret);
> - goto err;
> - }
> + if (ret)
> + continue;
>
> - vma = i915_vma_instance(obj, vm, view);
> - if (IS_ERR(vma))
> - goto err;
> + vma = i915_vma_instance(obj, vm, view);
> + if (IS_ERR(vma)) {
> + ret = PTR_ERR(vma);
> + continue;
> + }
>
> - if (i915_vma_misplaced(vma, 0, alignment, 0)) {
> - ret = i915_vma_unbind_unlocked(vma);
> - if (ret) {
> - vma = ERR_PTR(ret);
> - goto err;
> + if (i915_vma_misplaced(vma, 0, alignment, 0)) {
> + ret = i915_vma_unbind(vma);
> + if (ret)
> + continue;
> }
> - }
>
> - ret = i915_vma_pin(vma, 0, alignment, PIN_GLOBAL);
> + ret = i915_vma_pin_ww(vma, &ww, 0, alignment, PIN_GLOBAL);
> + if (ret)
> + continue;
> + }
> if (ret) {
> vma = ERR_PTR(ret);
> goto err;
> --
> 2.37.3
--
Ville Syrjälä
Intel
More information about the Intel-gfx
mailing list