drm/i915/execlists: Skip forcewake for ELSP submission

Now that we can read the CSB from the HWSP, we may avoid having to
perform mmio reads entirely and so forgo the rigmarole of the forcewake
dance.

v2: Include forcewake hint for GEM_TRACE readback of mmio. If we don't
hold fw ourselves, the reads may return garbage.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180122100714.15137-1-chris@chris-wilson.co.uk

diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 51e61b04a5554ea6b88d3bda2e8ef92adb2e2f3a..22d471a4228d0029227762f1e54268fd901a64c2 100644 (file)
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -778,6 +778,7 @@ static void execlists_submission_tasklet(unsigned long data)
        struct intel_engine_execlists * const execlists = &engine->execlists;
        struct execlist_port * const port = execlists->port;
        struct drm_i915_private *dev_priv = engine->i915;
+       bool fw = false;
 
        /* We can skip acquiring intel_runtime_pm_get() here as it was taken
         * on our behalf by the request (see i915_gem_mark_busy()) and it will
@@ -788,8 +789,6 @@ static void execlists_submission_tasklet(unsigned long data)
         */
        GEM_BUG_ON(!dev_priv->gt.awake);
 
-       intel_uncore_forcewake_get(dev_priv, execlists->fw_domains);
-
        /* Prefer doing test_and_clear_bit() as a two stage operation to avoid
         * imposing the cost of a locked atomic transaction when submitting a
         * new request (outside of the context-switch interrupt).
@@ -818,6 +817,12 @@ static void execlists_submission_tasklet(unsigned long data)
                 */
                __clear_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted);
                if (unlikely(execlists->csb_head == -1)) { /* following a reset */
+                       if (!fw) {
+                               intel_uncore_forcewake_get(dev_priv,
+                                                          execlists->fw_domains);
+                               fw = true;
+                       }
+
                        head = readl(dev_priv->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)));
                        tail = GEN8_CSB_WRITE_PTR(head);
                        head = GEN8_CSB_READ_PTR(head);
@@ -830,10 +835,10 @@ static void execlists_submission_tasklet(unsigned long data)
                        head = execlists->csb_head;
                        tail = READ_ONCE(buf[write_idx]);
                }
-               GEM_TRACE("%s cs-irq head=%d [%d], tail=%d [%d]\n",
+               GEM_TRACE("%s cs-irq head=%d [%d%s], tail=%d [%d%s]\n",
                          engine->name,
-                         head, GEN8_CSB_READ_PTR(readl(dev_priv->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)))),
-                         tail, GEN8_CSB_WRITE_PTR(readl(dev_priv->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)))));
+                         head, GEN8_CSB_READ_PTR(readl(dev_priv->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)))), fw ? "" : "?",
+                         tail, GEN8_CSB_WRITE_PTR(readl(dev_priv->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)))), fw ? "" : "?");
 
                while (head != tail) {
                        struct drm_i915_gem_request *rq;
@@ -943,7 +948,8 @@ static void execlists_submission_tasklet(unsigned long data)
        if (!execlists_is_active(execlists, EXECLISTS_ACTIVE_PREEMPT))
                execlists_dequeue(engine);
 
-       intel_uncore_forcewake_put(dev_priv, execlists->fw_domains);
+       if (fw)
+               intel_uncore_forcewake_put(dev_priv, execlists->fw_domains);
 }
 
 static void insert_request(struct intel_engine_cs *engine,