drm/i915/gt: Batch TLB invalidations

Invalidate TLB in batches, in order to reduce performance regressions.

Currently, every caller performs a full barrier around a TLB
invalidation, ignoring all other invalidations that may have already
removed their PTEs from the cache. As this is a synchronous operation
and can be quite slow, we cause multiple threads to contend on the TLB
invalidate mutex blocking userspace.

We only need to invalidate the TLB once after replacing our PTE to
ensure that there is no possible continued access to the physical
address before releasing our pages. By tracking a seqno for each full
TLB invalidate we can quickly determine if one has been performed since
rewriting the PTE, and only if necessary trigger one for ourselves.

That helps to reduce the performance regression introduced by TLB
invalidate logic.

[mchehab: rebased to not require moving the code to a separate file]

Cc: stable@vger.kernel.org
Fixes: 7938d61591d3 ("drm/i915: Flush TLBs before releasing backing store")
Suggested-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Signed-off-by: Chris Wilson <chris.p.wilson@intel.com>
Cc: Fei Yang <fei.yang@intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>
Acked-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/4e97ef5deb6739cadaaf40aa45620547e9c4ec06.1658924372.git.mchehab@kernel.org
(cherry picked from commit 5d36acb7198b0e5eb88e6b701f9ad7b9448f8df9)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>

1 files changed, 40 insertions, 13 deletions

diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index 5c55a90672f4..f435e06125aa 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -38,8 +38,6 @@ static void __intel_gt_init_early(struct intel_gt *gt)
 {
 	spin_lock_init(&gt->irq_lock);
 
-	mutex_init(&gt->tlb_invalidate_lock);
-
 	INIT_LIST_HEAD(&gt->closed_vma);
 	spin_lock_init(&gt->closed_lock);
 
@@ -50,6 +48,8 @@ static void __intel_gt_init_early(struct intel_gt *gt)
 	intel_gt_init_reset(gt);
 	intel_gt_init_requests(gt);
 	intel_gt_init_timelines(gt);
+	mutex_init(&gt->tlb.invalidate_lock);
+	seqcount_mutex_init(&gt->tlb.seqno, &gt->tlb.invalidate_lock);
 	intel_gt_pm_init_early(gt);
 
 	intel_uc_init_early(&gt->uc);
@@ -770,6 +770,7 @@ void intel_gt_driver_late_release_all(struct drm_i915_private *i915)
 		intel_gt_fini_requests(gt);
 		intel_gt_fini_reset(gt);
 		intel_gt_fini_timelines(gt);
+		mutex_destroy(&gt->tlb.invalidate_lock);
 		intel_engines_free(gt);
 	}
 }
@@ -908,7 +909,7 @@ get_reg_and_bit(const struct intel_engine_cs *engine, const bool gen8,
 	return rb;
 }
 
-void intel_gt_invalidate_tlbs(struct intel_gt *gt)
+static void mmio_invalidate_full(struct intel_gt *gt)
 {
 	static const i915_reg_t gen8_regs[] = {
 		[RENDER_CLASS]			= GEN8_RTCR,
@@ -931,12 +932,6 @@ void intel_gt_invalidate_tlbs(struct intel_gt *gt)
 	const i915_reg_t *regs;
 	unsigned int num = 0;
 
-	if (I915_SELFTEST_ONLY(gt->awake == -ENODEV))
-		return;
-
-	if (intel_gt_is_wedged(gt))
-		return;
-
 	if (GRAPHICS_VER(i915) == 12) {
 		regs = gen12_regs;
 		num = ARRAY_SIZE(gen12_regs);
@@ -951,9 +946,6 @@ void intel_gt_invalidate_tlbs(struct intel_gt *gt)
 			  "Platform does not implement TLB invalidation!"))
 		return;
 
-	GEM_TRACE("\n");
-
-	mutex_lock(&gt->tlb_invalidate_lock);
 	intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL);
 
 	spin_lock_irq(&uncore->lock); /* serialise invalidate with GT reset */
@@ -973,6 +965,8 @@ void intel_gt_invalidate_tlbs(struct intel_gt *gt)
 		awake |= engine->mask;
 	}
 
+	GT_TRACE(gt, "invalidated engines %08x\n", awake);
+
 	/* Wa_2207587034:tgl,dg1,rkl,adl-s,adl-p */
 	if (awake &&
 	    (IS_TIGERLAKE(i915) ||
@@ -1012,5 +1006,38 @@ void intel_gt_invalidate_tlbs(struct intel_gt *gt)
 	 * transitions.
 	 */
 	intel_uncore_forcewake_put_delayed(uncore, FORCEWAKE_ALL);
-	mutex_unlock(&gt->tlb_invalidate_lock);
+}
+
+static bool tlb_seqno_passed(const struct intel_gt *gt, u32 seqno)
+{
+	u32 cur = intel_gt_tlb_seqno(gt);
+
+	/* Only skip if a *full* TLB invalidate barrier has passed */
+	return (s32)(cur - ALIGN(seqno, 2)) > 0;
+}
+
+void intel_gt_invalidate_tlb(struct intel_gt *gt, u32 seqno)
+{
+	intel_wakeref_t wakeref;
+
+	if (I915_SELFTEST_ONLY(gt->awake == -ENODEV))
+		return;
+
+	if (intel_gt_is_wedged(gt))
+		return;
+
+	if (tlb_seqno_passed(gt, seqno))
+		return;
+
+	with_intel_gt_pm_if_awake(gt, wakeref) {
+		mutex_lock(&gt->tlb.invalidate_lock);
+		if (tlb_seqno_passed(gt, seqno))
+			goto unlock;
+
+		mmio_invalidate_full(gt);
+
+		write_seqcount_invalidate(&gt->tlb.seqno);
+unlock:
+		mutex_unlock(&gt->tlb.invalidate_lock);
+	}
 }