i965: Allow a per gen timebase scale factor

Prior to Skylake the Gen HW timestamps were driven by a 12.5MHz clock
with the convenient property of being able to scale by an integer (80)
to nanosecond units.

For Skylake the frequency is 12MHz or a scale factor of 83.333333

This updates gen_device_info to track a floating point timebase_scale
factor and makes corresponding _queryobj.c changes to no longer assume a
scale factor of 80 works across all gens.

Although the gen6_ code could have been been left alone, the changes
keep the code more comparable, and it now shares a few utility functions
for scaling raw timestamps and calculating deltas. The utility for
calculating deltas takes into account 32 or 36bit overflow depending on
the current kernel version.

Note: this leaves the timestamp handling of ARB_query_buffer_object
untouched, which continues to use an incorrect scale of 80 on Skylake
for now. This is more awkward to solve since the scaling is currently
done using a very limited uint64 ALU available to the command parser
that doesn't support multiply or divide where it's already taking a
large number of instructions just to effectively multiple by 80.

This fixes piglit arb_timer_query-timestamp-get on Skylake

v2: (Ken) Update timebase_scale for platforms past Skylake/Broxton too.

Signed-off-by: Robert Bragg <[email protected]>
Reviewed-by: Matt Turner <[email protected]>
Reviewed-by: Kenneth Graunke <[email protected]>

1 files changed, 24 insertions, 0 deletions

diff --git a/src/intel/common/gen_device_info.h b/src/intel/common/gen_device_info.h
index f0e8750d0ea..80676d0e003 100644
--- a/src/intel/common/gen_device_info.h
+++ b/src/intel/common/gen_device_info.h
@@ -147,6 +147,30 @@ struct gen_device_info
        */
       unsigned max_entries[4];
    } urb;
+
+   /**
+    * For the longest time the timestamp frequency for Gen's timestamp counter
+    * could be assumed to be 12.5MHz, where the least significant bit neatly
+    * corresponded to 80 nanoseconds.
+    *
+    * Since Gen9 the numbers aren't so round, with a a frequency of 12MHz for
+    * SKL (or scale factor of 83.33333333) and a frequency of 19200123Hz for
+    * BXT.
+    *
+    * For simplicty to fit with the current code scaling by a single constant
+    * to map from raw timestamps to nanoseconds we now do the conversion in
+    * floating point instead of integer arithmetic.
+    *
+    * In general it's probably worth noting that the documented constants we
+    * have for the per-platform timestamp frequencies aren't perfect and
+    * shouldn't be trusted for scaling and comparing timestamps with a large
+    * delta.
+    *
+    * E.g. with crude testing on my system using the 'correct' scale factor I'm
+    * seeing a drift of ~2 milliseconds per second.
+    */
+   double timebase_scale;
+
    /** @} */
 };