gpu: nvgpu: hal for timestamps correlation

In order to perform timestamps correlation for FECS
traces, we need to collect GPU / GPU timestamps
samples. In virtualization case, it is possible for
a guest to get GPU timestamps by using read_ptimer.
However, if the CPU timestamp is read on guest side,
and the GPU timestamp is read on vm-server side,
then it introduces some latency that will create an
artificial offset for GPU timestamps (~2 us in
average). For better CPU / GPU timestamps correlation,
Added a command to collect all timestamps on vm-server
side.

Bug 1900475

Change-Id: Idfdc6ae4c16c501dc5e00053a5b75932c55148d6
Signed-off-by: Thomas Fleury <tfleury@nvidia.com>
Reviewed-on: http://git-master/r/1472447
(cherry picked from commit 56f56b5cd9d2e75cf7d2613b5e115bfebdbee0ce)
Reviewed-on: http://git-master/r/1489183
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>

1 files changed, 4 insertions, 0 deletions

diff --git a/drivers/gpu/nvgpu/gk20a/gk20a.h b/drivers/gpu/nvgpu/gk20a/gk20a.h
index 34f89fc8..d1a55104 100644
--- a/drivers/gpu/nvgpu/gk20a/gk20a.h
+++ b/drivers/gpu/nvgpu/gk20a/gk20a.h
@@ -63,6 +63,7 @@ struct nvgpu_nvhost_dev;
 #include "priv_ring_gk20a.h"
 #include "therm_gk20a.h"
 #include "gm20b/acr_gm20b.h"
+#include "gk20a/bus_gk20a.h"
 #include "cde_gk20a.h"
 #include "sched_gk20a.h"
 #ifdef CONFIG_ARCH_TEGRA_18x_SOC
@@ -905,6 +906,9 @@ struct gpu_ops {
                 void (*init_hw)(struct gk20a *g);
                 void (*isr)(struct gk20a *g);
                 int (*read_ptimer)(struct gk20a *g, u64 *value);
+                int (*get_timestamps_zipper)(struct gk20a *g,
+                        u32 source_id, u32 count,
+                        struct nvgpu_cpu_time_correlation_sample *);
                 int (*bar1_bind)(struct gk20a *g, struct nvgpu_mem *bar1_inst);
         } bus;