drm/i915: Consolidate TLB invalidation flow

As the logic for selecting the register and corresponsing values grew, the
code become a bit unsightly. Consolidate by storing the required values at
engine init time in the engine itself, and by doing so minimise the amount
of invariant platform and engine checks during each and every TLB
invalidation.

v2:
 * Fail engine probe if TLB invlidations registers are unknown.

v3:
 * Rebase.

v4:
 * Fix handling of GEN8_M2TCR. (Andrzej)

v5:
 * Tidy checkpatch warnings.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Andrzej Hajda <andrzej.hajda@intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Andrzej Hajda <andrzej.hajda@intel.com> # v1
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230216092123.159085-1-tvrtko.ursulin@linux.intel.com

1 files changed, 22 insertions, 116 deletions

diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index 001a7ec5b861..f7f271708fc7 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -982,35 +982,6 @@ void intel_gt_info_print(const struct intel_gt_info *info,
 	intel_sseu_dump(&info->sseu, p);
 }
 
-struct reg_and_bit {
-	union {
-		i915_reg_t reg;
-		i915_mcr_reg_t mcr_reg;
-	};
-	u32 bit;
-};
-
-static struct reg_and_bit
-get_reg_and_bit(const struct intel_engine_cs *engine, const bool gen8,
-		const i915_reg_t *regs, const unsigned int num)
-{
-	const unsigned int class = engine->class;
-	struct reg_and_bit rb = { };
-
-	if (gt_WARN_ON_ONCE(engine->gt, class >= num || !regs[class].reg))
-		return rb;
-
-	rb.reg = regs[class];
-	if (gen8 && class == VIDEO_DECODE_CLASS)
-		rb.reg.reg += 4 * engine->instance; /* GEN8_M2TCR */
-	else
-		rb.bit = engine->instance;
-
-	rb.bit = BIT(rb.bit);
-
-	return rb;
-}
-
 /*
  * HW architecture suggest typical invalidation time at 40us,
  * with pessimistic cases up to 100us and a recommendation to
@@ -1024,14 +995,20 @@ get_reg_and_bit(const struct intel_engine_cs *engine, const bool gen8,
  * but are now considered MCR registers.  Since they exist within a GAM range,
  * the primary instance of the register rolls up the status from each unit.
  */
-static int wait_for_invalidate(struct intel_gt *gt, struct reg_and_bit rb)
+static int wait_for_invalidate(struct intel_engine_cs *engine)
 {
-	if (GRAPHICS_VER_FULL(gt->i915) >= IP_VER(12, 50))
-		return intel_gt_mcr_wait_for_reg(gt, rb.mcr_reg, rb.bit, 0,
+	if (engine->tlb_inv.mcr)
+		return intel_gt_mcr_wait_for_reg(engine->gt,
+						 engine->tlb_inv.reg.mcr_reg,
+						 engine->tlb_inv.done,
+						 0,
 						 TLB_INVAL_TIMEOUT_US,
 						 TLB_INVAL_TIMEOUT_MS);
 	else
-		return __intel_wait_for_register_fw(gt->uncore, rb.reg, rb.bit, 0,
+		return __intel_wait_for_register_fw(engine->gt->uncore,
+						    engine->tlb_inv.reg.reg,
+						    engine->tlb_inv.done,
+						    0,
 						    TLB_INVAL_TIMEOUT_US,
 						    TLB_INVAL_TIMEOUT_MS,
 						    NULL);
@@ -1039,62 +1016,14 @@ static int wait_for_invalidate(struct intel_gt *gt, struct reg_and_bit rb)
 
 static void mmio_invalidate_full(struct intel_gt *gt)
 {
-	static const i915_reg_t gen8_regs[] = {
-		[RENDER_CLASS]			= GEN8_RTCR,
-		[VIDEO_DECODE_CLASS]		= GEN8_M1TCR, /* , GEN8_M2TCR */
-		[VIDEO_ENHANCEMENT_CLASS]	= GEN8_VTCR,
-		[COPY_ENGINE_CLASS]		= GEN8_BTCR,
-	};
-	static const i915_reg_t gen12_regs[] = {
-		[RENDER_CLASS]			= GEN12_GFX_TLB_INV_CR,
-		[VIDEO_DECODE_CLASS]		= GEN12_VD_TLB_INV_CR,
-		[VIDEO_ENHANCEMENT_CLASS]	= GEN12_VE_TLB_INV_CR,
-		[COPY_ENGINE_CLASS]		= GEN12_BLT_TLB_INV_CR,
-		[COMPUTE_CLASS]			= GEN12_COMPCTX_TLB_INV_CR,
-	};
-	static const i915_mcr_reg_t xehp_regs[] = {
-		[RENDER_CLASS]			= XEHP_GFX_TLB_INV_CR,
-		[VIDEO_DECODE_CLASS]		= XEHP_VD_TLB_INV_CR,
-		[VIDEO_ENHANCEMENT_CLASS]	= XEHP_VE_TLB_INV_CR,
-		[COPY_ENGINE_CLASS]		= XEHP_BLT_TLB_INV_CR,
-		[COMPUTE_CLASS]			= XEHP_COMPCTX_TLB_INV_CR,
-	};
 	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;
 	unsigned long flags;
 
-	/*
-	 * New platforms should not be added with catch-all-newer (>=)
-	 * condition so that any later platform added triggers the below warning
-	 * and in turn mandates a human cross-check of whether the invalidation
-	 * flows have compatible semantics.
-	 *
-	 * For instance with the 11.00 -> 12.00 transition three out of five
-	 * respective engine registers were moved to masked type. Then after the
-	 * 12.00 -> 12.50 transition multi cast handling is required too.
-	 */
-
-	if (GRAPHICS_VER_FULL(i915) == IP_VER(12, 50) ||
-	    GRAPHICS_VER_FULL(i915) == IP_VER(12, 55)) {
-		regs = NULL;
-		num = ARRAY_SIZE(xehp_regs);
-	} else if (GRAPHICS_VER_FULL(i915) == IP_VER(12, 0) ||
-		   GRAPHICS_VER_FULL(i915) == IP_VER(12, 10)) {
-		regs = gen12_regs;
-		num = ARRAY_SIZE(gen12_regs);
-	} else if (GRAPHICS_VER(i915) >= 8 && GRAPHICS_VER(i915) <= 11) {
-		regs = gen8_regs;
-		num = ARRAY_SIZE(gen8_regs);
-	} else if (GRAPHICS_VER(i915) < 8) {
-		return;
-	}
-
-	if (gt_WARN_ONCE(gt, !num, "Platform does not implement TLB invalidation!"))
+	if (GRAPHICS_VER(i915) < 8)
 		return;
 
 	intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL);
@@ -1104,33 +1033,18 @@ static void mmio_invalidate_full(struct intel_gt *gt)
 
 	awake = 0;
 	for_each_engine(engine, gt, id) {
-		struct reg_and_bit rb;
-
 		if (!intel_engine_pm_is_awake(engine))
 			continue;
 
-		if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) {
-			u32 val = BIT(engine->instance);
-
-			if (engine->class == VIDEO_DECODE_CLASS ||
-			    engine->class == VIDEO_ENHANCEMENT_CLASS ||
-			    engine->class == COMPUTE_CLASS)
-				val = _MASKED_BIT_ENABLE(val);
+		if (engine->tlb_inv.mcr)
 			intel_gt_mcr_multicast_write_fw(gt,
-							xehp_regs[engine->class],
-							val);
-		} else {
-			rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num);
-			if (!i915_mmio_reg_offset(rb.reg))
-				continue;
-
-			if (GRAPHICS_VER(i915) == 12 && (engine->class == VIDEO_DECODE_CLASS ||
-			    engine->class == VIDEO_ENHANCEMENT_CLASS ||
-			    engine->class == COMPUTE_CLASS))
-				rb.bit = _MASKED_BIT_ENABLE(rb.bit);
-
-			intel_uncore_write_fw(uncore, rb.reg, rb.bit);
-		}
+							engine->tlb_inv.reg.mcr_reg,
+							engine->tlb_inv.request);
+		else
+			intel_uncore_write_fw(uncore,
+					      engine->tlb_inv.reg.reg,
+					      engine->tlb_inv.request);
+
 		awake |= engine->mask;
 	}
 
@@ -1149,17 +1063,9 @@ static void mmio_invalidate_full(struct intel_gt *gt)
 	intel_gt_mcr_unlock(gt, flags);
 
 	for_each_engine_masked(engine, gt, awake, tmp) {
-		struct reg_and_bit rb;
-
-		if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) {
-			rb.mcr_reg = xehp_regs[engine->class];
-			rb.bit = BIT(engine->instance);
-		} else {
-			rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num);
-		}
-
-		if (wait_for_invalidate(gt, rb))
-			gt_err_ratelimited(gt, "%s TLB invalidation did not complete in %ums!\n",
+		if (wait_for_invalidate(engine))
+			gt_err_ratelimited(gt,
+					   "%s TLB invalidation did not complete in %ums!\n",
 					   engine->name, TLB_INVAL_TIMEOUT_MS);
 	}