1 files changed, 26 insertions, 93 deletions

diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 8f4a25d2c..2d695818f 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -206,6 +206,7 @@
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_clock_utils.h"
 #include "gt/intel_gt_mcr.h"
+#include "gt/intel_gt_print.h"
 #include "gt/intel_gt_regs.h"
 #include "gt/intel_lrc.h"
 #include "gt/intel_lrc_reg.h"
@@ -542,10 +543,9 @@ static bool oa_buffer_check_unlocked(struct i915_perf_stream *stream)
 {
 	u32 gtt_offset = i915_ggtt_offset(stream->oa_buffer.vma);
 	int report_size = stream->oa_buffer.format->size;
-	u32 head, tail, read_tail;
+	u32 tail, hw_tail;
 	unsigned long flags;
 	bool pollin;
-	u32 hw_tail;
 	u32 partial_report_size;
 
 	/* We have to consider the (unlikely) possibility that read() errors
@@ -555,6 +555,7 @@ static bool oa_buffer_check_unlocked(struct i915_perf_stream *stream)
 	spin_lock_irqsave(&stream->oa_buffer.ptr_lock, flags);
 
 	hw_tail = stream->perf->ops.oa_hw_tail_read(stream);
+	hw_tail -= gtt_offset;
 
 	/* The tail pointer increases in 64 byte increments, not in report_size
 	 * steps. Also the report size may not be a power of 2. Compute
@@ -566,13 +567,6 @@ static bool oa_buffer_check_unlocked(struct i915_perf_stream *stream)
 	/* Subtract partial amount off the tail */
 	hw_tail = OA_TAKEN(hw_tail, partial_report_size);
 
-	/* NB: The head we observe here might effectively be a little
-	 * out of date. If a read() is in progress, the head could be
-	 * anywhere between this head and stream->oa_buffer.tail.
-	 */
-	head = stream->oa_buffer.head - gtt_offset;
-	read_tail = stream->oa_buffer.tail - gtt_offset;
-
 	tail = hw_tail;
 
 	/* Walk the stream backward until we find a report with report
@@ -586,7 +580,7 @@ static bool oa_buffer_check_unlocked(struct i915_perf_stream *stream)
 	 * memory in the order they were written to.
 	 * If not : (╯°□°）╯︵ ┻━┻
 	 */
-	while (OA_TAKEN(tail, read_tail) >= report_size) {
+	while (OA_TAKEN(tail, stream->oa_buffer.tail) >= report_size) {
 		void *report = stream->oa_buffer.vaddr + tail;
 
 		if (oa_report_id(stream, report) ||
@@ -600,9 +594,9 @@ static bool oa_buffer_check_unlocked(struct i915_perf_stream *stream)
 	    __ratelimit(&stream->perf->tail_pointer_race))
 		drm_notice(&stream->uncore->i915->drm,
 			   "unlanded report(s) head=0x%x tail=0x%x hw_tail=0x%x\n",
-		 head, tail, hw_tail);
+		 stream->oa_buffer.head, tail, hw_tail);
 
-	stream->oa_buffer.tail = gtt_offset + tail;
+	stream->oa_buffer.tail = tail;
 
 	pollin = OA_TAKEN(stream->oa_buffer.tail,
 			  stream->oa_buffer.head) >= report_size;
@@ -753,13 +747,6 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
 	spin_unlock_irqrestore(&stream->oa_buffer.ptr_lock, flags);
 
 	/*
-	 * NB: oa_buffer.head/tail include the gtt_offset which we don't want
-	 * while indexing relative to oa_buf_base.
-	 */
-	head -= gtt_offset;
-	tail -= gtt_offset;
-
-	/*
 	 * An out of bounds or misaligned head or tail pointer implies a driver
 	 * bug since we validate + align the tail pointers we read from the
 	 * hardware and we are in full control of the head pointer which should
@@ -923,9 +910,8 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
 		 * We removed the gtt_offset for the copy loop above, indexing
 		 * relative to oa_buf_base so put back here...
 		 */
-		head += gtt_offset;
 		intel_uncore_write(uncore, oaheadptr,
-				   head & GEN12_OAG_OAHEADPTR_MASK);
+				   (head + gtt_offset) & GEN12_OAG_OAHEADPTR_MASK);
 		stream->oa_buffer.head = head;
 
 		spin_unlock_irqrestore(&stream->oa_buffer.ptr_lock, flags);
@@ -1070,12 +1056,6 @@ static int gen7_append_oa_reports(struct i915_perf_stream *stream,
 
 	spin_unlock_irqrestore(&stream->oa_buffer.ptr_lock, flags);
 
-	/* NB: oa_buffer.head/tail include the gtt_offset which we don't want
-	 * while indexing relative to oa_buf_base.
-	 */
-	head -= gtt_offset;
-	tail -= gtt_offset;
-
 	/* An out of bounds or misaligned head or tail pointer implies a driver
 	 * bug since we validate + align the tail pointers we read from the
 	 * hardware and we are in full control of the head pointer which should
@@ -1138,13 +1118,8 @@ static int gen7_append_oa_reports(struct i915_perf_stream *stream,
 	if (start_offset != *offset) {
 		spin_lock_irqsave(&stream->oa_buffer.ptr_lock, flags);
 
-		/* We removed the gtt_offset for the copy loop above, indexing
-		 * relative to oa_buf_base so put back here...
-		 */
-		head += gtt_offset;
-
 		intel_uncore_write(uncore, GEN7_OASTATUS2,
-				   (head & GEN7_OASTATUS2_HEAD_MASK) |
+				   ((head + gtt_offset) & GEN7_OASTATUS2_HEAD_MASK) |
 				   GEN7_OASTATUS2_MEM_SELECT_GGTT);
 		stream->oa_buffer.head = head;
 
@@ -1703,13 +1678,6 @@ static void i915_oa_stream_destroy(struct i915_perf_stream *stream)
 
 	free_oa_buffer(stream);
 
-	/*
-	 * Wa_16011777198:dg2: Unset the override of GUCRC mode to enable rc6.
-	 */
-	if (stream->override_gucrc)
-		drm_WARN_ON(&gt->i915->drm,
-			    intel_guc_slpc_unset_gucrc_mode(&gt->uc.guc.slpc));
-
 	intel_uncore_forcewake_put(stream->uncore, FORCEWAKE_ALL);
 	intel_engine_pm_put(stream->engine);
 
@@ -1720,9 +1688,8 @@ static void i915_oa_stream_destroy(struct i915_perf_stream *stream)
 	free_noa_wait(stream);
 
 	if (perf->spurious_report_rs.missed) {
-		drm_notice(&gt->i915->drm,
-			   "%d spurious OA report notices suppressed due to ratelimiting\n",
-			   perf->spurious_report_rs.missed);
+		gt_notice(gt, "%d spurious OA report notices suppressed due to ratelimiting\n",
+			  perf->spurious_report_rs.missed);
 	}
 }
 
@@ -1739,7 +1706,7 @@ static void gen7_init_oa_buffer(struct i915_perf_stream *stream)
 	 */
 	intel_uncore_write(uncore, GEN7_OASTATUS2, /* head */
 			   gtt_offset | GEN7_OASTATUS2_MEM_SELECT_GGTT);
-	stream->oa_buffer.head = gtt_offset;
+	stream->oa_buffer.head = 0;
 
 	intel_uncore_write(uncore, GEN7_OABUFFER, gtt_offset);
 
@@ -1747,7 +1714,7 @@ static void gen7_init_oa_buffer(struct i915_perf_stream *stream)
 			   gtt_offset | OABUFFER_SIZE_16M);
 
 	/* Mark that we need updated tail pointers to read from... */
-	stream->oa_buffer.tail = gtt_offset;
+	stream->oa_buffer.tail = 0;
 
 	spin_unlock_irqrestore(&stream->oa_buffer.ptr_lock, flags);
 
@@ -1781,7 +1748,7 @@ static void gen8_init_oa_buffer(struct i915_perf_stream *stream)
 
 	intel_uncore_write(uncore, GEN8_OASTATUS, 0);
 	intel_uncore_write(uncore, GEN8_OAHEADPTR, gtt_offset);
-	stream->oa_buffer.head = gtt_offset;
+	stream->oa_buffer.head = 0;
 
 	intel_uncore_write(uncore, GEN8_OABUFFER_UDW, 0);
 
@@ -1798,7 +1765,7 @@ static void gen8_init_oa_buffer(struct i915_perf_stream *stream)
 	intel_uncore_write(uncore, GEN8_OATAILPTR, gtt_offset & GEN8_OATAILPTR_MASK);
 
 	/* Mark that we need updated tail pointers to read from... */
-	stream->oa_buffer.tail = gtt_offset;
+	stream->oa_buffer.tail = 0;
 
 	/*
 	 * Reset state used to recognise context switches, affecting which
@@ -1835,7 +1802,7 @@ static void gen12_init_oa_buffer(struct i915_perf_stream *stream)
 	intel_uncore_write(uncore, __oa_regs(stream)->oa_status, 0);
 	intel_uncore_write(uncore, __oa_regs(stream)->oa_head_ptr,
 			   gtt_offset & GEN12_OAG_OAHEADPTR_MASK);
-	stream->oa_buffer.head = gtt_offset;
+	stream->oa_buffer.head = 0;
 
 	/*
 	 * PRM says:
@@ -1851,7 +1818,7 @@ static void gen12_init_oa_buffer(struct i915_perf_stream *stream)
 			   gtt_offset & GEN12_OAG_OATAILPTR_MASK);
 
 	/* Mark that we need updated tail pointers to read from... */
-	stream->oa_buffer.tail = gtt_offset;
+	stream->oa_buffer.tail = 0;
 
 	/*
 	 * Reset state used to recognise context switches, affecting which
@@ -1913,7 +1880,7 @@ static int alloc_oa_buffer(struct i915_perf_stream *stream)
 	 */
 	ret = i915_vma_pin(vma, 0, SZ_16M, PIN_GLOBAL | PIN_HIGH);
 	if (ret) {
-		drm_err(&gt->i915->drm, "Failed to pin OA buffer %d\n", ret);
+		gt_err(gt, "Failed to pin OA buffer %d\n", ret);
 		goto err_unref;
 	}
 
@@ -3255,11 +3222,10 @@ get_sseu_config(struct intel_sseu *out_sseu,
  */
 u32 i915_perf_oa_timestamp_frequency(struct drm_i915_private *i915)
 {
-	/*
-	 * Wa_18013179988:dg2
-	 * Wa_14015846243:mtl
-	 */
-	if (IS_DG2(i915) || IS_METEORLAKE(i915)) {
+	struct intel_gt *gt = to_gt(i915);
+
+	/* Wa_18013179988 */
+	if (IS_DG2(i915) || IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 71))) {
 		intel_wakeref_t wakeref;
 		u32 reg, shift;
 
@@ -3300,7 +3266,6 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 	struct drm_i915_private *i915 = stream->perf->i915;
 	struct i915_perf *perf = stream->perf;
 	struct i915_perf_group *g;
-	struct intel_gt *gt;
 	int ret;
 
 	if (!props->engine) {
@@ -3308,7 +3273,6 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 			"OA engine not specified\n");
 		return -EINVAL;
 	}
-	gt = props->engine->gt;
 	g = props->engine->oa_group;
 
 	/*
@@ -3409,25 +3373,6 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 	intel_engine_pm_get(stream->engine);
 	intel_uncore_forcewake_get(stream->uncore, FORCEWAKE_ALL);
 
-	/*
-	 * Wa_16011777198:dg2: GuC resets render as part of the Wa. This causes
-	 * OA to lose the configuration state. Prevent this by overriding GUCRC
-	 * mode.
-	 */
-	if (intel_uc_uses_guc_rc(&gt->uc) &&
-	    (IS_DG2_GRAPHICS_STEP(gt->i915, G10, STEP_A0, STEP_C0) ||
-	     IS_DG2_GRAPHICS_STEP(gt->i915, G11, STEP_A0, STEP_B0))) {
-		ret = intel_guc_slpc_override_gucrc_mode(&gt->uc.guc.slpc,
-							 SLPC_GUCRC_MODE_GUCRC_NO_RC6);
-		if (ret) {
-			drm_dbg(&stream->perf->i915->drm,
-				"Unable to override gucrc mode\n");
-			goto err_gucrc;
-		}
-
-		stream->override_gucrc = true;
-	}
-
 	ret = alloc_oa_buffer(stream);
 	if (ret)
 		goto err_oa_buf_alloc;
@@ -3464,10 +3409,6 @@ err_enable:
 	free_oa_buffer(stream);
 
 err_oa_buf_alloc:
-	if (stream->override_gucrc)
-		intel_guc_slpc_unset_gucrc_mode(&gt->uc.guc.slpc);
-
-err_gucrc:
 	intel_uncore_forcewake_put(stream->uncore, FORCEWAKE_ALL);
 	intel_engine_pm_put(stream->engine);
 
@@ -4251,7 +4192,7 @@ static int read_properties_unlocked(struct i915_perf *perf,
 	 * C6 disable in BIOS. Fail if Media C6 is enabled on steppings where OAM
 	 * does not work as expected.
 	 */
-	if (IS_MTL_MEDIA_STEP(props->engine->i915, STEP_A0, STEP_C0) &&
+	if (IS_MEDIA_GT_IP_STEP(props->engine->gt, IP_VER(13, 0), STEP_A0, STEP_C0) &&
 	    props->engine->oa_group->type == TYPE_OAM &&
 	    intel_check_bios_c6_setup(&props->engine->gt->rc6)) {
 		drm_dbg(&perf->i915->drm,
@@ -4564,7 +4505,7 @@ 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)
 {
-	if (IS_METEORLAKE(perf->i915))
+	if (GRAPHICS_VER_FULL(perf->i915) >= IP_VER(12, 70))
 		return reg_in_range_table(addr, mtl_oa_mux_regs);
 	else
 		return reg_in_range_table(addr, gen12_oa_mux_regs);
@@ -4915,7 +4856,6 @@ static struct ctl_table oa_table[] = {
 	 .extra1 = SYSCTL_ZERO,
 	 .extra2 = &oa_sample_rate_hard_limit,
 	 },
-	{}
 };
 
 static u32 num_perf_groups_per_gt(struct intel_gt *gt)
@@ -5352,16 +5292,9 @@ int i915_perf_ioctl_version(struct drm_i915_private *i915)
 	 * C6 disable in BIOS. If Media C6 is enabled in BIOS, return version 6
 	 * to indicate that OA media is not supported.
 	 */
-	if (IS_MTL_MEDIA_STEP(i915, STEP_A0, STEP_C0)) {
-		struct intel_gt *gt;
-		int i;
-
-		for_each_gt(gt, i915, i) {
-			if (gt->type == GT_MEDIA &&
-			    intel_check_bios_c6_setup(&gt->rc6))
-				return 6;
-		}
-	}
+	if (IS_MEDIA_GT_IP_STEP(i915->media_gt, IP_VER(13, 0), STEP_A0, STEP_C0) &&
+	    intel_check_bios_c6_setup(&i915->media_gt->rc6))
+		return 6;
 
 	return 7;
 }