[PATCH v3 1/6] drm/xe: Add LRC ctx timestamp support functions

[Matthew Brost]

On Mon, Jun 10, 2024 at 08:49:57AM -0500, Lucas De Marchi wrote:
> On Fri, Jun 07, 2024 at 05:20:58PM GMT, Matthew Brost wrote:
> > LRC ctx timestamp support functions are used to determine how long a job
> > has run on the hardware.
> > 
> > v2:
> > - Don't use static inlines (Jani)
> > - Kernel doc
> > - s/ctx_timestamp_job/ctx_job_timestamp
> > 
> > Signed-off-by: Matthew Brost <matthew.brost at intel.com>
> > ---
> > drivers/gpu/drm/xe/xe_lrc.c | 66 +++++++++++++++++++++++++++++++++++++
> > drivers/gpu/drm/xe/xe_lrc.h |  5 +++
> > 2 files changed, 71 insertions(+)
> > 
> > diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c
> > index c1bb85d2e243..0fef354c6489 100644
> > --- a/drivers/gpu/drm/xe/xe_lrc.c
> > +++ b/drivers/gpu/drm/xe/xe_lrc.c
> > @@ -652,6 +652,7 @@ u32 xe_lrc_pphwsp_offset(struct xe_lrc *lrc)
> > 
> > #define LRC_SEQNO_PPHWSP_OFFSET 512
> > #define LRC_START_SEQNO_PPHWSP_OFFSET (LRC_SEQNO_PPHWSP_OFFSET + 8)
> > +#define LRC_CTX_JOB_TIMESTAMP_OFFSET (LRC_START_SEQNO_PPHWSP_OFFSET + 8)
> > #define LRC_PARALLEL_PPHWSP_OFFSET 2048
> > #define LRC_PPHWSP_SIZE SZ_4K
> > 
> > @@ -680,6 +681,12 @@ static inline u32 __xe_lrc_start_seqno_offset(struct xe_lrc *lrc)
> > 	return xe_lrc_pphwsp_offset(lrc) + LRC_START_SEQNO_PPHWSP_OFFSET;
> > }
> > 
> > +static u32 __xe_lrc_ctx_job_timestamp_offset(struct xe_lrc *lrc)
> > +{
> > +	/* The start seqno is stored in the driver-defined portion of PPHWSP */
> > +	return xe_lrc_pphwsp_offset(lrc) + LRC_CTX_JOB_TIMESTAMP_OFFSET;
> > +}
> > +
> > static inline u32 __xe_lrc_parallel_offset(struct xe_lrc *lrc)
> > {
> > 	/* The parallel is stored in the driver-defined portion of PPHWSP */
> > @@ -691,6 +698,11 @@ static inline u32 __xe_lrc_regs_offset(struct xe_lrc *lrc)
> > 	return xe_lrc_pphwsp_offset(lrc) + LRC_PPHWSP_SIZE;
> > }
> > 
> > +static u32 __xe_lrc_ctx_timestamp_offset(struct xe_lrc *lrc)
> > +{
> > +	return __xe_lrc_regs_offset(lrc) + CTX_TIMESTAMP * sizeof(u32);
> > +}
> > +
> > static inline u32 __xe_lrc_indirect_ring_offset(struct xe_lrc *lrc)
> > {
> > 	/* Indirect ring state page is at the very end of LRC */
> > @@ -716,11 +728,65 @@ DECL_MAP_ADDR_HELPERS(pphwsp)
> > DECL_MAP_ADDR_HELPERS(seqno)
> > DECL_MAP_ADDR_HELPERS(regs)
> > DECL_MAP_ADDR_HELPERS(start_seqno)
> > +DECL_MAP_ADDR_HELPERS(ctx_job_timestamp)
> > +DECL_MAP_ADDR_HELPERS(ctx_timestamp)
> > DECL_MAP_ADDR_HELPERS(parallel)
> > DECL_MAP_ADDR_HELPERS(indirect_ring)
> > 
> > #undef DECL_MAP_ADDR_HELPERS
> > 
> > +/**
> > + * xe_lrc_ctx_timestamp_ggtt_addr() - Get ctx timestamp GGTT address
> > + * @lrc: Pointer to the lrc.
> > + *
> > + * Returns: ctx timestamp GGTT address
> > + */
> > +u32 xe_lrc_ctx_timestamp_ggtt_addr(struct xe_lrc *lrc)
> > +{
> > +	return __xe_lrc_ctx_timestamp_ggtt_addr(lrc);
> > +}
> > +
> > +/**
> > + * xe_lrc_ctx_timestamp_addr() - Read ctx timestamp value
> > + * @lrc: Pointer to the lrc.
> > + *
> > + * Returns: ctx timestamp value
> > + */
> > +u32 xe_lrc_ctx_timestamp(struct xe_lrc *lrc)
> > +{
> > +	struct xe_device *xe = lrc_to_xe(lrc);
> > +	struct iosys_map map;
> > +
> > +	map = __xe_lrc_ctx_timestamp_map(lrc);
> > +	return xe_map_read32(xe, &map);
> > +}
> > +
> > +/**
> > + * xe_lrc_ctx_job_timestamp_ggtt_addr() - Get ctx job timestamp GGTT address
> > + * @lrc: Pointer to the lrc.
> > + *
> > + * Returns: ctx timestamp job GGTT address
> > + */
> > +u32 xe_lrc_ctx_job_timestamp_ggtt_addr(struct xe_lrc *lrc)
> > +{
> > +	return __xe_lrc_ctx_job_timestamp_ggtt_addr(lrc);
> > +}
> > +
> > +/**
> > + * xe_lrc_ctx_job_timestamp_addr() - Read ctx job timestamp value
> > + * @lrc: Pointer to the lrc.
> > + *
> > + * Returns: ctx timestamp job value
> > + */
> > +u32 xe_lrc_ctx_job_timestamp(struct xe_lrc *lrc)
> > +{
> > +	struct xe_device *xe = lrc_to_xe(lrc);
> > +	struct iosys_map map;
> > +
> > +	map = __xe_lrc_ctx_job_timestamp_map(lrc);
> > +	return xe_map_read32(xe, &map);
> > +}
> > +
> > u32 xe_lrc_ggtt_addr(struct xe_lrc *lrc)
> > {
> > 	return __xe_lrc_pphwsp_ggtt_addr(lrc);
> > diff --git a/drivers/gpu/drm/xe/xe_lrc.h b/drivers/gpu/drm/xe/xe_lrc.h
> > index 882c3437ba5c..001af6c79454 100644
> > --- a/drivers/gpu/drm/xe/xe_lrc.h
> > +++ b/drivers/gpu/drm/xe/xe_lrc.h
> > @@ -94,6 +94,11 @@ void xe_lrc_snapshot_capture_delayed(struct xe_lrc_snapshot *snapshot);
> > void xe_lrc_snapshot_print(struct xe_lrc_snapshot *snapshot, struct drm_printer *p);
> > void xe_lrc_snapshot_free(struct xe_lrc_snapshot *snapshot);
> > 
> > +u32 xe_lrc_ctx_timestamp_ggtt_addr(struct xe_lrc *lrc);
> > +u32 xe_lrc_ctx_timestamp(struct xe_lrc *lrc);
> 

Bad timing, just sent v4 at the same time.

> I  think we have some clash here. See the function below where we
> read the timestamp and cache it in the LRC. That one does something
> slightly different, but apparently the same thing. Why are these
> functions not using similar approch with xe_lrc_read_ctx_reg() rather
> than defining new helper functions? And why would we return the address
> and then having another function to read the value?

xe_lrc_read_ctx_reg(lrc, CTX_TIMESTAMP); is the same as: xe_lrc_ctx_timestamp(lrc);

I used 'DECL_MAP_ADDR_HELPERS' to implement the 4 exported functions
mainly as I need the GGTT address and that macro spits out a helper
with the GGTT address.

fwiw, also xe_lrc_read_ctx_reg is implemented with one of these
functions from DECL_MAP_ADDR_HELPERS - __xe_lrc_regs_map.

I'd vote, leave patch mainly as is but replace existing
xe_lrc_read_ctx_reg(lrc, CTX_TIMESTAMP); with
xe_lrc_ctx_timestamp(lrc);. 

If you want to cleanup the file itself and drop these macros, that seems
to be an orthogonal issue to my series.

Matt

> 
> Lucas De Marchi
> 
> > +u32 xe_lrc_ctx_job_timestamp_ggtt_addr(struct xe_lrc *lrc);
> > +u32 xe_lrc_ctx_job_timestamp(struct xe_lrc *lrc);
> > +
> > /**
> >  * xe_lrc_update_timestamp - readout LRC timestamp and update cached value
> >  * @lrc: logical ring context for this exec queue
> > -- 
> > 2.34.1
> >