[Intel-xe] [PATCH 00/21] Add OA functionality to Xe
Lionel Landwerlin
lionel.g.landwerlin at intel.com
Fri Oct 20 07:44:13 UTC 2023
On 19/09/2023 19:10, Ashutosh Dixit wrote:
> This patchset is the initial port of i915 perf/OA functionality to the XE
> driver. The following features in i915 have not been ported and will be
> added (as new patches) if/as they are needed:
>
> * Inline batch submission on stream exec_queue/hw_engine
If you give us a syncobj to wait on for the NOA reconfiguration this
won't be necessary
> * NOA wait
This is kind of required, otherwise we start reading reports from the OA
buffer and the values are garbage
> * GuC ctx id (guc_sw_ctx_id)
This is probably fine. On Gfx8 we always consider using OA a privileged
operation, if we keep it like that then it's okay.
> * CTX_R_PWR_CLK_STATE/GEN8_R_PWR_CLK_STATE
I think if we never care about Gfx11 that's fine.
> * hold_preemption (DRM_XE_OA_PROP_HOLD_PREEMPTION)
Without this, we can't implement perf queries in userspace.
Maybe that's okay?
> * sseu_config (DRM_XE_OA_PROP_GLOBAL_SSEU)
Without Gfx11 probably fine.
> * MTL bios_c6_setup
> * ratelimits
> * compat ioctl
>
> I am providing the following additional HAX patch (not part of this series)
> to help review these patches:
>
> https://patchwork.freedesktop.org/patch/551683/?series=120100&rev=4
>
> The commit message in the above patch explains how it can be useful for
> reviewing this series.
>
> This series is also available at:
> https://gitlab.freedesktop.org/adixit/kernel/-/tree/xe-oa
>
> The series has been tested against this IGT series:
> https://gitlab.freedesktop.org/adixit/igt-gpu-tools/-/tree/xe-oa
>
> v2: Fix build
> v3: Rebase, due to s/xe_engine/xe_exec_queue/
> v4: Re-run for testing
> v5: Address review comments, new patches 11 through 17
> v6: New patches 18 through 21
>
> Ashutosh Dixit (21):
> drm/xe/uapi: Introduce OA (observability architecture) uapi
> drm/xe/oa: Add OA types
> drm/xe/oa: Add registers and GPU commands used by OA
> drm/xe/oa: Module init/exit and probe/remove
> drm/xe/oa: Add/remove config ioctl's
> drm/xe/oa: Start implementing OA stream open ioctl
> drm/xe/oa: OA stream initialization
> drm/xe/oa: Expose OA stream fd
> drm/xe/oa: Read file_operation
> drm/xe/oa: Implement queries
> drm/xe/oa: Override GuC RC with OA on PVC
> drm/xe/uapi: "Perf" layer to support multiple perf counter stream
> types
> drm/xe/uapi: Multiplex PERF ops through a single PERF ioctl
> drm/xe/uapi: Simplify OA configs in uapi
> drm/xe/uapi: Remove OA format names from OA uapi
> drm/xe/oa: Make xe_oa_timestamp_frequency per gt
> drm/xe/oa: Remove filtering reports on context id
> drm/xe/uapi: More OA uapi fixes/additions
> drm/xe/uapi: Drop OA_IOCTL_VERSION
> drm/xe/uapi: Use OA unit id to identify OA unit
> drm/xe/uapi: Convert OA property key/value pairs to a struct
>
> drivers/gpu/drm/xe/Makefile | 2 +
> drivers/gpu/drm/xe/regs/xe_engine_regs.h | 2 +
> drivers/gpu/drm/xe/regs/xe_gpu_commands.h | 13 +
> drivers/gpu/drm/xe/regs/xe_oa_regs.h | 173 ++
> drivers/gpu/drm/xe/xe_device.c | 13 +
> drivers/gpu/drm/xe/xe_device_types.h | 4 +
> drivers/gpu/drm/xe/xe_gt_types.h | 4 +
> drivers/gpu/drm/xe/xe_guc_pc.c | 60 +
> drivers/gpu/drm/xe/xe_guc_pc.h | 3 +
> drivers/gpu/drm/xe/xe_hw_engine_types.h | 2 +
> drivers/gpu/drm/xe/xe_module.c | 5 +
> drivers/gpu/drm/xe/xe_oa.c | 2314 +++++++++++++++++++++
> drivers/gpu/drm/xe/xe_oa.h | 27 +
> drivers/gpu/drm/xe/xe_oa_types.h | 307 +++
> drivers/gpu/drm/xe/xe_perf.c | 36 +
> drivers/gpu/drm/xe/xe_perf.h | 16 +
> drivers/gpu/drm/xe/xe_query.c | 5 +-
> include/uapi/drm/xe_drm.h | 288 ++-
> 18 files changed, 3272 insertions(+), 2 deletions(-)
> create mode 100644 drivers/gpu/drm/xe/regs/xe_oa_regs.h
> create mode 100644 drivers/gpu/drm/xe/xe_oa.c
> create mode 100644 drivers/gpu/drm/xe/xe_oa.h
> create mode 100644 drivers/gpu/drm/xe/xe_oa_types.h
> create mode 100644 drivers/gpu/drm/xe/xe_perf.c
> create mode 100644 drivers/gpu/drm/xe/xe_perf.h
>
More information about the Intel-xe
mailing list