[Mesa-dev] [PATCH v3 3/5] i965: perf: read slice/unslice frequencies from OA reports

[Lionel Landwerlin]

v2: Add comment breaking down where the frequency values come from (Ken)

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin at intel.com>
---
 .../drivers/dri/i965/brw_performance_query.c  | 49 +++++++++++++++++++
 .../drivers/dri/i965/brw_performance_query.h  | 12 +++++
 2 files changed, 61 insertions(+)

diff --git a/src/mesa/drivers/dri/i965/brw_performance_query.c b/src/mesa/drivers/dri/i965/brw_performance_query.c
index 32cf96a333d..03ba4942070 100644
--- a/src/mesa/drivers/dri/i965/brw_performance_query.c
+++ b/src/mesa/drivers/dri/i965/brw_performance_query.c
@@ -1341,6 +1341,54 @@ brw_is_perf_query_ready(struct gl_context *ctx,
    return false;
 }
 
+static void
+gen8_read_report_clock_ratios(const uint32_t *report,
+                              uint64_t *slice_freq_hz,
+                              uint64_t *unslice_freq_hz)
+{
+   /* The lower 16bits of the RPT_ID field of the OA reports contains a
+    * snapshot of the bits coming from the RP_FREQ_NORMAL register and is
+    * divided this way :
+    *
+    * RPT_ID[31:25]: RP_FREQ_NORMAL[20:14] (low squashed_slice_clock_frequency)
+    * RPT_ID[10:9]:  RP_FREQ_NORMAL[22:21] (high squashed_slice_clock_frequency)
+    * RPT_ID[8:0]:   RP_FREQ_NORMAL[31:23] (squashed_unslice_clock_frequency)
+    *
+    * Slice/Unslice frequency values from the RP_FREQ_NORMAL register are
+    * multiples of 16.66MHz.
+    */
+
+   uint32_t unslice_freq = report[0] & 0x1ff;
+   uint32_t slice_freq_low = (report[0] >> 25) & 0x7f;
+   uint32_t slice_freq_high = (report[0] >> 9) & 0x3;
+   uint32_t slice_freq = slice_freq_low | (slice_freq_high << 7);
+
+   *slice_freq_hz = slice_freq * 16666000ULL;
+   *unslice_freq_hz = unslice_freq * 16666000ULL;
+}
+
+static void
+read_slice_unslice_frequencies(struct brw_context *brw,
+                               struct brw_perf_query_object *obj)
+{
+   const struct gen_device_info *devinfo = &brw->screen->devinfo;
+   uint32_t *begin_report, *end_report;
+
+   /* No data available before gen8. */
+   if (devinfo->gen < 8)
+      return;
+
+   begin_report = obj->oa.map;
+   end_report = obj->oa.map + MI_RPC_BO_END_OFFSET_BYTES;
+
+   gen8_read_report_clock_ratios(begin_report,
+                                 &obj->oa.slice_frequency[0],
+                                 &obj->oa.unslice_frequency[0]);
+   gen8_read_report_clock_ratios(end_report,
+                                 &obj->oa.slice_frequency[1],
+                                 &obj->oa.unslice_frequency[1]);
+}
+
 static void
 read_gt_frequency(struct brw_context *brw,
                   struct brw_perf_query_object *obj)
@@ -1382,6 +1430,7 @@ get_oa_counter_data(struct brw_context *brw,
 
    if (!obj->oa.results_accumulated) {
       read_gt_frequency(brw, obj);
+      read_slice_unslice_frequencies(brw, obj);
       accumulate_oa_reports(brw, obj);
       assert(obj->oa.results_accumulated);
 
diff --git a/src/mesa/drivers/dri/i965/brw_performance_query.h b/src/mesa/drivers/dri/i965/brw_performance_query.h
index f8732738b4e..6d3ecf0be3a 100644
--- a/src/mesa/drivers/dri/i965/brw_performance_query.h
+++ b/src/mesa/drivers/dri/i965/brw_performance_query.h
@@ -118,6 +118,18 @@ struct brw_perf_query_object
           * Frequency of the GT at begin and end of the query.
           */
          uint64_t gt_frequency[2];
+
+         /**
+          * Frequency in the the slices of the GT at the begin and end of the
+          * query.
+          */
+         uint64_t slice_frequency[2];
+
+         /**
+          * Frequency in the the unslice of the GT at the begin and end of the
+          * query.
+          */
+         uint64_t unslice_frequency[2];
       } oa;
 
       struct {
-- 
2.17.0