diff options
author | Lionel Landwerlin <[email protected]> | 2018-06-02 12:29:46 +0100 |
---|---|---|
committer | Lionel Landwerlin <[email protected]> | 2018-06-04 18:16:08 +0100 |
commit | 61d5676b5561d61e3fdd9e88fc2b549b9b4df08f (patch) | |
tree | e6ea7d93c2c290311a2a6f26e8104b6bab424b18 /tools/perf/scripts/python/syscall-counts-by-pid.py | |
parent | 218b5000982b7c5e7433b86819be92f95984a1ae (diff) |
drm/i915/perf: fix ctx_id read with GuC & ICL
One thing we didn't really understand about the OA report is that the
ContextID field (dword 2) is copy of the context descriptor (dword 1).
On Gen8->10 and without using GuC we didn't notice the issue because
we only checked the 21bits of the ContextID field in the OA reports
which matches exactly the hw_id stored into the context descriptor.
When using GuC submission we have an issue of a non matching hw_id
because GuC uses bit 20 of the hw_id to signal proxy submission. This
change introduces a mask to compare only the relevant bits.
On ICL the context descriptor format has changed and we failed to
address this. On top of using a mask we also need to shift the bits
properly.
v2: Reuse lrc_desc rather than recomputing part of it (Chris/Michel)
v3: Always pin the context we're filtering with (Chris)
Signed-off-by: Lionel Landwerlin <[email protected]>
Fixes: 1de401c08fa805 ("drm/i915/perf: enable perf support on ICL")
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=104252
BSpec: 1237
Testcase: igt/perf/gen8-unprivileged-single-ctx-counters
Acked-by: Chris Wilson <[email protected]>
Reviewed-by: Michel Thierry <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
Cc: Lionel Landwerlin <[email protected]>
Cc: Matthew Auld <[email protected]>
Cc: Jani Nikula <[email protected]>
Cc: Joonas Lahtinen <[email protected]>
Cc: Rodrigo Vivi <[email protected]>
Cc: [email protected]
Diffstat (limited to 'tools/perf/scripts/python/syscall-counts-by-pid.py')
0 files changed, 0 insertions, 0 deletions