From: Oscar Mateo <oscar.ma...@intel.com> Or with a spinlock grabbed, because it might sleep, which is not a nice thing to do. Instead, do the runtime_pm get/put together with the create/destroy request, and handle the forcewake get/put directly.
Signed-off-by: Oscar Mateo <oscar.ma...@intel.com> --- drivers/gpu/drm/i915/intel_lrc.c | 26 +++++++++++++++++++++----- 1 file changed, 21 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index d33e622..ea4b358 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -159,6 +159,7 @@ static void execlists_elsp_write(struct intel_engine_cs *ring, struct drm_i915_private *dev_priv = ring->dev->dev_private; uint64_t temp = 0; uint32_t desc[4]; + unsigned long flags; /* XXX: You must always write both descriptors in the order below. */ if (ctx_obj1) @@ -172,9 +173,17 @@ static void execlists_elsp_write(struct intel_engine_cs *ring, desc[3] = (u32)(temp >> 32); desc[2] = (u32)temp; - /* Set Force Wakeup bit to prevent GT from entering C6 while - * ELSP writes are in progress */ - gen6_gt_force_wake_get(dev_priv, FORCEWAKE_ALL); + /* Set Force Wakeup bit to prevent GT from entering C6 while ELSP writes + * are in progress. + * + * The other problem is that we can't just call gen6_gt_force_wake_get() + * because that function calls intel_runtime_pm_get(), which might sleep. + * Instead, we do the runtime_pm_get/put when creating/destroying requests. + */ + spin_lock_irqsave(&dev_priv->uncore.lock, flags); + if (dev_priv->uncore.forcewake_count++ == 0) + dev_priv->uncore.funcs.force_wake_get(dev_priv, FORCEWAKE_ALL); + spin_unlock_irqrestore(&dev_priv->uncore.lock, flags); I915_WRITE(RING_ELSP(ring), desc[1]); I915_WRITE(RING_ELSP(ring), desc[0]); @@ -185,8 +194,11 @@ static void execlists_elsp_write(struct intel_engine_cs *ring, /* ELSP is a write only register, so this serves as a posting read */ POSTING_READ(RING_EXECLIST_STATUS(ring)); - /* Release Force Wakeup */ - gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL); + /* Release Force Wakeup (see the big comment above). */ + spin_lock_irqsave(&dev_priv->uncore.lock, flags); + if (--dev_priv->uncore.forcewake_count == 0) + dev_priv->uncore.funcs.force_wake_put(dev_priv, FORCEWAKE_ALL); + spin_unlock_irqrestore(&dev_priv->uncore.lock, flags); } static int execlists_ctx_write_tail(struct drm_i915_gem_object *ctx_obj, u32 tail) @@ -353,6 +365,9 @@ static void execlists_free_request_task(struct work_struct *work) struct intel_ctx_submit_request *req = container_of(work, struct intel_ctx_submit_request, work); struct drm_device *dev = req->ring->dev; + struct drm_i915_private *dev_priv = dev->dev_private; + + intel_runtime_pm_put(dev_priv); mutex_lock(&dev->struct_mutex); i915_gem_context_unreference(req->ctx); @@ -378,6 +393,7 @@ static int execlists_context_queue(struct intel_engine_cs *ring, req->ring = ring; req->tail = tail; INIT_WORK(&req->work, execlists_free_request_task); + intel_runtime_pm_get(dev_priv); spin_lock_irqsave(&ring->execlist_lock, flags); -- 1.9.0 _______________________________________________ Intel-gfx mailing list Intel-gfx@lists.freedesktop.org http://lists.freedesktop.org/mailman/listinfo/intel-gfx