drm/i915/gt: Ignore TLB invalidations on idle engines

Check if the device is powered down prior to any engine activity,
as, on such cases, all the TLBs were already invalidated, so an
explicit TLB invalidation is not needed, thus reducing the
performance regression impact due to it.

This becomes more significant with GuC, as it can only do so when
the connection to the GuC is awake.

Cc: stable@vger.kernel.org
Fixes: 7938d61 ("drm/i915: Flush TLBs before releasing backing store")
Signed-off-by: Chris Wilson <chris.p.wilson@intel.com>
Cc: Fei Yang <fei.yang@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Acked-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Acked-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/278a57a672edac75683f0818b292e95da583a5fe.1658924372.git.mchehab@kernel.org

drivers/gpu/drm/i915/gem/i915_gem_pages.c

@@ -6,14 +6,15 @@
 
 #include <drm/drm_cache.h>
 
+#include "gt/intel_gt.h"
+#include "gt/intel_gt_pm.h"
+
 #include "i915_drv.h"
 #include "i915_gem_object.h"
 #include "i915_scatterlist.h"
 #include "i915_gem_lmem.h"
 #include "i915_gem_mman.h"
 
-#include "gt/intel_gt.h"
-
 void __i915_gem_object_set_pages(struct drm_i915_gem_object *obj,
 				 struct sg_table *pages,
 				 unsigned int sg_page_sizes)
@@ -217,10 +218,11 @@ __i915_gem_object_unset_pages(struct drm_i915_gem_object *obj)
 
 	if (test_and_clear_bit(I915_BO_WAS_BOUND_BIT, &obj->flags)) {
 		struct drm_i915_private *i915 = to_i915(obj->base.dev);
+		struct intel_gt *gt = to_gt(i915);
 		intel_wakeref_t wakeref;
 
-		with_intel_runtime_pm_if_active(&i915->runtime_pm, wakeref)
-			intel_gt_invalidate_tlbs(to_gt(i915));
+		with_intel_gt_pm_if_awake(gt, wakeref)
+			intel_gt_invalidate_tlbs(gt);
 	}
 
 	return pages;

drivers/gpu/drm/i915/gt/intel_gt.c

@@ -12,6 +12,7 @@
 
 #include "i915_drv.h"
 #include "intel_context.h"
+#include "intel_engine_pm.h"
 #include "intel_engine_regs.h"
 #include "intel_ggtt_gmch.h"
 #include "intel_gt.h"
@@ -924,6 +925,7 @@ void intel_gt_invalidate_tlbs(struct intel_gt *gt)
 	struct drm_i915_private *i915 = gt->i915;
 	struct intel_uncore *uncore = gt->uncore;
 	struct intel_engine_cs *engine;
+	intel_engine_mask_t awake, tmp;
 	enum intel_engine_id id;
 	const i915_reg_t *regs;
 	unsigned int num = 0;
@@ -947,39 +949,40 @@ void intel_gt_invalidate_tlbs(struct intel_gt *gt)
 
 	GEM_TRACE("\n");
 
-	assert_rpm_wakelock_held(&i915->runtime_pm);
-
 	mutex_lock(&gt->tlb_invalidate_lock);
 	intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL);
 
 	spin_lock_irq(&uncore->lock); /* serialise invalidate with GT reset */
 
+	awake = 0;
 	for_each_engine(engine, gt, id) {
 		struct reg_and_bit rb;
 
+		if (!intel_engine_pm_is_awake(engine))
+			continue;
+
 		rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num);
 		if (!i915_mmio_reg_offset(rb.reg))
 			continue;
 
 		intel_uncore_write_fw(uncore, rb.reg, rb.bit);
+		awake |= engine->mask;
 	}
 
 	spin_unlock_irq(&uncore->lock);
 
-	for_each_engine(engine, gt, id) {
+	for_each_engine_masked(engine, gt, awake, tmp) {
+		struct reg_and_bit rb;
+
 		/*
 		 * HW architecture suggest typical invalidation time at 40us,
 		 * with pessimistic cases up to 100us and a recommendation to
 		 * cap at 1ms. We go a bit higher just in case.
 		 */
 		const unsigned int timeout_us = 100;
 		const unsigned int timeout_ms = 4;
-		struct reg_and_bit rb;
 
 		rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num);
-		if (!i915_mmio_reg_offset(rb.reg))
-			continue;
-
 		if (__intel_wait_for_register_fw(uncore,
 						 rb.reg, rb.bit, 0,
 						 timeout_us, timeout_ms,

drivers/gpu/drm/i915/gt/intel_gt_pm.h

@@ -55,6 +55,9 @@ static inline void intel_gt_pm_might_put(struct intel_gt *gt)
 	for (tmp = 1, intel_gt_pm_get(gt); tmp; \
 	     intel_gt_pm_put(gt), tmp = 0)
 
+#define with_intel_gt_pm_if_awake(gt, wf) \
+	for (wf = intel_gt_pm_get_if_awake(gt); wf; intel_gt_pm_put_async(gt), wf = 0)
+
 static inline int intel_gt_pm_wait_for_idle(struct intel_gt *gt)
 {
 	return intel_wakeref_wait_for_idle(&gt->wakeref);