1 files changed, 39 insertions, 12 deletions

diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 125b6ca25a75..824a34ec0b83 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1846,8 +1846,7 @@ static u32 *save_restore_register(struct i915_perf_stream *stream, u32 *cs,
 	for (d = 0; d < dword_count; d++) {
 		*cs++ = cmd;
 		*cs++ = i915_mmio_reg_offset(reg) + 4 * d;
-		*cs++ = intel_gt_scratch_offset(stream->engine->gt,
-						offset) + 4 * d;
+		*cs++ = i915_ggtt_offset(stream->noa_wait) + offset + 4 * d;
 		*cs++ = 0;
 	}
 
@@ -1880,7 +1879,13 @@ static int alloc_noa_wait(struct i915_perf_stream *stream)
 					  MI_PREDICATE_RESULT_2_ENGINE(base) :
 					  MI_PREDICATE_RESULT_1(RENDER_RING_BASE);
 
-	bo = i915_gem_object_create_internal(i915, 4096);
+	/*
+	 * gt->scratch was being used to save/restore the GPR registers, but on
+	 * MTL the scratch uses stolen lmem. An MI_SRM to this memory region
+	 * causes an engine hang. Instead allocate an additional page here to
+	 * save/restore GPR registers
+	 */
+	bo = i915_gem_object_create_internal(i915, 8192);
 	if (IS_ERR(bo)) {
 		drm_err(&i915->drm,
 			"Failed to allocate NOA wait batchbuffer\n");
@@ -1914,14 +1919,19 @@ retry:
 		goto err_unpin;
 	}
 
+	stream->noa_wait = vma;
+
+#define GPR_SAVE_OFFSET 4096
+#define PREDICATE_SAVE_OFFSET 4160
+
 	/* Save registers. */
 	for (i = 0; i < N_CS_GPR; i++)
 		cs = save_restore_register(
 			stream, cs, true /* save */, CS_GPR(i),
-			INTEL_GT_SCRATCH_FIELD_PERF_CS_GPR + 8 * i, 2);
+			GPR_SAVE_OFFSET + 8 * i, 2);
 	cs = save_restore_register(
 		stream, cs, true /* save */, mi_predicate_result,
-		INTEL_GT_SCRATCH_FIELD_PERF_PREDICATE_RESULT_1, 1);
+		PREDICATE_SAVE_OFFSET, 1);
 
 	/* First timestamp snapshot location. */
 	ts0 = cs;
@@ -2037,10 +2047,10 @@ retry:
 	for (i = 0; i < N_CS_GPR; i++)
 		cs = save_restore_register(
 			stream, cs, false /* restore */, CS_GPR(i),
-			INTEL_GT_SCRATCH_FIELD_PERF_CS_GPR + 8 * i, 2);
+			GPR_SAVE_OFFSET + 8 * i, 2);
 	cs = save_restore_register(
 		stream, cs, false /* restore */, mi_predicate_result,
-		INTEL_GT_SCRATCH_FIELD_PERF_PREDICATE_RESULT_1, 1);
+		PREDICATE_SAVE_OFFSET, 1);
 
 	/* And return to the ring. */
 	*cs++ = MI_BATCH_BUFFER_END;
@@ -2050,7 +2060,6 @@ retry:
 	i915_gem_object_flush_map(bo);
 	__i915_gem_object_release_map(bo);
 
-	stream->noa_wait = vma;
 	goto out_ww;
 
 err_unpin:
@@ -2263,7 +2272,7 @@ retry:
 		goto err_add_request;
 
 	err = rq->engine->emit_bb_start(rq,
-					vma->node.start, 0,
+					i915_vma_offset(vma), 0,
 					I915_DISPATCH_SECURE);
 	if (err)
 		goto err_add_request;
@@ -3131,8 +3140,11 @@ get_sseu_config(struct intel_sseu *out_sseu,
  */
 u32 i915_perf_oa_timestamp_frequency(struct drm_i915_private *i915)
 {
-	/* Wa_18013179988:dg2 */
-	if (IS_DG2(i915)) {
+	/*
+	 * Wa_18013179988:dg2
+	 * Wa_14015846243:mtl
+	 */
+	if (IS_DG2(i915) || IS_METEORLAKE(i915)) {
 		intel_wakeref_t wakeref;
 		u32 reg, shift;
 
@@ -4310,6 +4322,17 @@ static const struct i915_range gen12_oa_mux_regs[] = {
 	{}
 };
 
+/*
+ * Ref: 14010536224:
+ * 0x20cc is repurposed on MTL, so use a separate array for MTL.
+ */
+static const struct i915_range mtl_oa_mux_regs[] = {
+	{ .start = 0x0d00, .end = 0x0d04 },	/* RPM_CONFIG[0-1] */
+	{ .start = 0x0d0c, .end = 0x0d2c },	/* NOA_CONFIG[0-8] */
+	{ .start = 0x9840, .end = 0x9840 },	/* GDT_CHICKEN_BITS */
+	{ .start = 0x9884, .end = 0x9888 },	/* NOA_WRITE */
+};
+
 static bool gen7_is_valid_b_counter_addr(struct i915_perf *perf, u32 addr)
 {
 	return reg_in_range_table(addr, gen7_oa_b_counters);
@@ -4353,7 +4376,10 @@ static bool xehp_is_valid_b_counter_addr(struct i915_perf *perf, u32 addr)
 
 static bool gen12_is_valid_mux_addr(struct i915_perf *perf, u32 addr)
 {
-	return reg_in_range_table(addr, gen12_oa_mux_regs);
+	if (IS_METEORLAKE(perf->i915))
+		return reg_in_range_table(addr, mtl_oa_mux_regs);
+	else
+		return reg_in_range_table(addr, gen12_oa_mux_regs);
 }
 
 static u32 mask_reg_value(u32 reg, u32 val)
@@ -4750,6 +4776,7 @@ static void oa_init_supported_formats(struct i915_perf *perf)
 		break;
 
 	case INTEL_DG2:
+	case INTEL_METEORLAKE:
 		oa_format_add(perf, I915_OAR_FORMAT_A32u40_A4u32_B8_C8);
 		oa_format_add(perf, I915_OA_FORMAT_A24u40_A14u32_B8_C8);
 		break;