drm/i915: Forgo last_fence active request tracking

We were using the last_fence to track the last request that used this
vma that might be interpreted by a fence register and forced ourselves
to wait for this request before modifying any fence register that
overlapped our vma. Due to requirement that we need to track any XY_BLT
command, linear or tiled, this in effect meant that we have to track the
vma for its active lifespan anyway, so we can forgo the explicit
last_fence tracking and just use the whole vma->active.

Another solution would be to pipeline the register updates, and would
help resolve some long running stalls for gen3 (but only gen 2 and 3!)

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190812174804.26180-1-chris@chris-wilson.co.uk

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index b616ba0..2c64098 100644 (file)
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -212,9 +212,7 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
                        }
                }
                if (vma->fence)
-                       seq_printf(m, " , fence: %d%s",
-                                  vma->fence->id,
-                                  i915_active_request_isset(&vma->last_fence) ? "*" : "");
+                       seq_printf(m, " , fence: %d", vma->fence->id);
                seq_puts(m, ")");
 
                spin_lock(&obj->vma.lock);

diff --git a/drivers/gpu/drm/i915/i915_gem_fence_reg.c b/drivers/gpu/drm/i915/i915_gem_fence_reg.c
index bcac359..c9654f1 100644 (file)
--- a/drivers/gpu/drm/i915/i915_gem_fence_reg.c
+++ b/drivers/gpu/drm/i915/i915_gem_fence_reg.c
@@ -230,16 +230,14 @@ static int fence_update(struct i915_fence_reg *fence,
                         i915_gem_object_get_tiling(vma->obj)))
                        return -EINVAL;
 
-               ret = i915_active_request_retire(&vma->last_fence,
-                                            &vma->obj->base.dev->struct_mutex);
+               ret = i915_active_wait(&vma->active);
                if (ret)
                        return ret;
        }
 
        old = xchg(&fence->vma, NULL);
        if (old) {
-               ret = i915_active_request_retire(&old->last_fence,
-                                            &old->obj->base.dev->struct_mutex);
+               ret = i915_active_wait(&old->active);
                if (ret) {
                        fence->vma = old;
                        return ret;

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 72a227c..e07c1ae 100644 (file)
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1867,7 +1867,6 @@ static struct i915_vma *pd_vma_create(struct gen6_ppgtt *ppgtt, int size)
                return ERR_PTR(-ENOMEM);
 
        i915_active_init(i915, &vma->active, NULL, NULL);
-       INIT_ACTIVE_REQUEST(&vma->last_fence);
 
        vma->vm = &ggtt->vm;
        vma->ops = &pd_vma_ops;

diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 4183b0e..8be1bbe 100644 (file)
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -120,7 +120,6 @@ vma_create(struct drm_i915_gem_object *obj,
 
        i915_active_init(vm->i915, &vma->active,
                         __i915_vma_active, __i915_vma_retire);
-       INIT_ACTIVE_REQUEST(&vma->last_fence);
 
        /* Declare ourselves safe for use inside shrinkers */
        if (IS_ENABLED(CONFIG_LOCKDEP)) {
@@ -802,8 +801,6 @@ static void __i915_vma_destroy(struct i915_vma *vma)
        GEM_BUG_ON(vma->node.allocated);
        GEM_BUG_ON(vma->fence);
 
-       GEM_BUG_ON(i915_active_request_isset(&vma->last_fence));
-
        mutex_lock(&vma->vm->mutex);
        list_del(&vma->vm_link);
        mutex_unlock(&vma->vm->mutex);
@@ -928,9 +925,6 @@ int i915_vma_move_to_active(struct i915_vma *vma,
        obj->read_domains |= I915_GEM_GPU_DOMAINS;
        obj->mm.dirty = true;
 
-       if (flags & EXEC_OBJECT_NEEDS_FENCE)
-               __i915_active_request_set(&vma->last_fence, rq);
-
        GEM_BUG_ON(!i915_vma_is_active(vma));
        return 0;
 }
@@ -961,14 +955,7 @@ int i915_vma_unbind(struct i915_vma *vma)
                 * before we are finished).
                 */
                __i915_vma_pin(vma);
-
                ret = i915_active_wait(&vma->active);
-               if (ret)
-                       goto unpin;
-
-               ret = i915_active_request_retire(&vma->last_fence,
-                                             &vma->vm->i915->drm.struct_mutex);
-unpin:
                __i915_vma_unpin(vma);
                if (ret)
                        return ret;

diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h
index 5c42247..b3d2121 100644 (file)
--- a/drivers/gpu/drm/i915/i915_vma.h
+++ b/drivers/gpu/drm/i915/i915_vma.h
@@ -111,7 +111,6 @@ struct i915_vma {
 #define I915_VMA_GGTT_WRITE    BIT(14)
 
        struct i915_active active;
-       struct i915_active_request last_fence;
 
        /**
         * Support different GGTT views into the same object.