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, 97 insertions, 0 deletions

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index d4e29da74612..f3a91e7f85f7 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -9,6 +9,7 @@
 
 #include "gem/i915_gem_context.h"
 #include "gem/i915_gem_internal.h"
+#include "gt/intel_gt_print.h"
 #include "gt/intel_gt_regs.h"
 
 #include "i915_cmd_parser.h"
@@ -1143,12 +1144,108 @@ err_put:
 	return ret;
 }
 
+static int intel_engine_init_tlb_invalidation(struct intel_engine_cs *engine)
+{
+	static const union intel_engine_tlb_inv_reg gen8_regs[] = {
+		[RENDER_CLASS].reg		= GEN8_RTCR,
+		[VIDEO_DECODE_CLASS].reg	= GEN8_M1TCR, /* , GEN8_M2TCR */
+		[VIDEO_ENHANCEMENT_CLASS].reg	= GEN8_VTCR,
+		[COPY_ENGINE_CLASS].reg		= GEN8_BTCR,
+	};
+	static const union intel_engine_tlb_inv_reg gen12_regs[] = {
+		[RENDER_CLASS].reg		= GEN12_GFX_TLB_INV_CR,
+		[VIDEO_DECODE_CLASS].reg	= GEN12_VD_TLB_INV_CR,
+		[VIDEO_ENHANCEMENT_CLASS].reg	= GEN12_VE_TLB_INV_CR,
+		[COPY_ENGINE_CLASS].reg		= GEN12_BLT_TLB_INV_CR,
+		[COMPUTE_CLASS].reg		= GEN12_COMPCTX_TLB_INV_CR,
+	};
+	static const union intel_engine_tlb_inv_reg xehp_regs[] = {
+		[RENDER_CLASS].mcr_reg		  = XEHP_GFX_TLB_INV_CR,
+		[VIDEO_DECODE_CLASS].mcr_reg	  = XEHP_VD_TLB_INV_CR,
+		[VIDEO_ENHANCEMENT_CLASS].mcr_reg = XEHP_VE_TLB_INV_CR,
+		[COPY_ENGINE_CLASS].mcr_reg	  = XEHP_BLT_TLB_INV_CR,
+		[COMPUTE_CLASS].mcr_reg		  = XEHP_COMPCTX_TLB_INV_CR,
+	};
+	struct drm_i915_private *i915 = engine->i915;
+	const unsigned int instance = engine->instance;
+	const unsigned int class = engine->class;
+	const union intel_engine_tlb_inv_reg *regs;
+	union intel_engine_tlb_inv_reg reg;
+	unsigned int num = 0;
+	u32 val;
+
+	/*
+	 * 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 = xehp_regs;
+		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 0;
+	}
+
+	if (gt_WARN_ONCE(engine->gt, !num,
+			 "Platform does not implement TLB invalidation!"))
+		return -ENODEV;
+
+	if (gt_WARN_ON_ONCE(engine->gt,
+			    class >= num ||
+			    (!regs[class].reg.reg &&
+			     !regs[class].mcr_reg.reg)))
+		return -ERANGE;
+
+	reg = regs[class];
+
+	if (regs == gen8_regs && class == VIDEO_DECODE_CLASS && instance == 1) {
+		reg.reg = GEN8_M2TCR;
+		val = 0;
+	} else {
+		val = instance;
+	}
+
+	val = BIT(val);
+
+	engine->tlb_inv.mcr = regs == xehp_regs;
+	engine->tlb_inv.reg = reg;
+	engine->tlb_inv.done = val;
+
+	if (GRAPHICS_VER(i915) >= 12 &&
+	    (engine->class == VIDEO_DECODE_CLASS ||
+	     engine->class == VIDEO_ENHANCEMENT_CLASS ||
+	     engine->class == COMPUTE_CLASS))
+		engine->tlb_inv.request = _MASKED_BIT_ENABLE(val);
+	else
+		engine->tlb_inv.request = val;
+
+	return 0;
+}
+
 static int engine_setup_common(struct intel_engine_cs *engine)
 {
 	int err;
 
 	init_llist_head(&engine->barrier_tasks);
 
+	err = intel_engine_init_tlb_invalidation(engine);
+	if (err)
+		return err;
+
 	err = init_status_page(engine);
 	if (err)
 		return err;