diff options
author | Anton Vorontsov <avorontsov@nvidia.com> | 2015-08-19 17:27:51 -0400 |
---|---|---|
committer | Terje Bergstrom <tbergstrom@nvidia.com> | 2016-03-23 10:48:47 -0400 |
commit | 1c40d09c4c9c011c1318c328c0b4b6b17d1f537e (patch) | |
tree | 8b93fcd00739f9ada9302f06175278c9cb1d6785 /drivers/gpu/nvgpu/vgpu/vgpu.c | |
parent | 82da6ed595a87c8a3038eecd75880ab21dd4c5de (diff) |
gpu: nvgpu: Add support for FECS ctxsw tracing
bug 1648908
This commit adds support for FECS ctxsw tracing. Code is compiled
conditionnaly under CONFIG_GK20_CTXSW_TRACE.
This feature requires an updated FECS ucode that writes one record to a ring
buffer on each context switch. On RM/Kernel side, the GPU driver reads records
from the master ring buffer and generates trace entries into a user-facing
VM ring buffer. For each record in the master ring buffer, RM/Kernel has
to retrieve the vmid+pid of the user process that submitted related work.
Features currently implemented:
- master ring buffer allocation
- debugfs to dump master ring buffer
- FECS record per context switch (with both current and new contexts)
- dedicated device for ctxsw tracing (access to VM ring buffer)
- SOF generation (and access to PTIMER)
- VM ring buffer allocation, and reconfiguration
- enable/disable tracing at user level
- event-based trace filtering
- context_ptr to vmid+pid mapping
- read system call for ctxsw dev
- mmap system call for ctxsw dev (direct access to VM ring buffer)
- poll system call for ctxsw dev
- save/restore register on ELPG/CG6
- separate user ring from FECS ring handling
Features requiring ucode changes:
- enable/disable tracing at FECS level
- actual busy time on engine (bug 1642354)
- master ring buffer threshold interrupt (P1)
- API for GPU to CPU timestamp conversion (P1)
- vmid/pid/uid based filtering (P1)
Change-Id: I8e39c648221ee0fa09d5df8524b03dca83fe24f3
Signed-off-by: Thomas Fleury <tfleury@nvidia.com>
Reviewed-on: http://git-master/r/1022737
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Diffstat (limited to 'drivers/gpu/nvgpu/vgpu/vgpu.c')
-rw-r--r-- | drivers/gpu/nvgpu/vgpu/vgpu.c | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/drivers/gpu/nvgpu/vgpu/vgpu.c b/drivers/gpu/nvgpu/vgpu/vgpu.c index 4cc61cb1..57f510ca 100644 --- a/drivers/gpu/nvgpu/vgpu/vgpu.c +++ b/drivers/gpu/nvgpu/vgpu/vgpu.c | |||
@@ -18,6 +18,7 @@ | |||
18 | #include <linux/dma-mapping.h> | 18 | #include <linux/dma-mapping.h> |
19 | #include <linux/pm_runtime.h> | 19 | #include <linux/pm_runtime.h> |
20 | #include "vgpu/vgpu.h" | 20 | #include "vgpu/vgpu.h" |
21 | #include "vgpu/fecs_trace_vgpu.h" | ||
21 | #include "gk20a/debug_gk20a.h" | 22 | #include "gk20a/debug_gk20a.h" |
22 | #include "gk20a/hal_gk20a.h" | 23 | #include "gk20a/hal_gk20a.h" |
23 | #include "gk20a/hw_mc_gk20a.h" | 24 | #include "gk20a/hw_mc_gk20a.h" |
@@ -259,6 +260,7 @@ void vgpu_init_hal_common(struct gk20a *g) | |||
259 | vgpu_init_ltc_ops(gops); | 260 | vgpu_init_ltc_ops(gops); |
260 | vgpu_init_mm_ops(gops); | 261 | vgpu_init_mm_ops(gops); |
261 | vgpu_init_debug_ops(gops); | 262 | vgpu_init_debug_ops(gops); |
263 | vgpu_init_fecs_trace_ops(gops); | ||
262 | } | 264 | } |
263 | 265 | ||
264 | static int vgpu_init_hal(struct gk20a *g) | 266 | static int vgpu_init_hal(struct gk20a *g) |