drm/i915/perf: Allow non-privileged access when OA buffer is not sampled
Subsystems (2)
PATCH 1/2 drm/i915/perf: Allow non-privileged access when OA buffer is not sampled
SAMPLE_OA_REPORT enables sampling of OA reports from the OA buffer. Since reports from OA buffer had system wide visibility, collecting samples from the OA buffer was a privileged operation on previous platforms. Prior to TGL, it was also necessary to sample the OA buffer to normalize reports from MI REPORT PERF COUNT.
TGL has a dedicated OAR unit to sample perf reports for a specific render context. This removes the necessity to sample OA buffer.
- If not sampling the OA buffer, allow non-privileged access. An earlier patch allows the non-privilege access:
https://patchwork.freedesktop.org/patch/337716/?series=68582&rev=1
- Clear up the path for non-privileged access in this patch
--- drivers/gpu/drm/i915/i915_perf.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)
drivers/gpu/drm/i915/i915_perf.c +3 -2
@@ -2718,7 +2718,8 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,return -EINVAL ; } -if (!(props->sample_flags &SAMPLE_OA_REPORT )) { +if (!(props->sample_flags &SAMPLE_OA_REPORT ) && + (INTEL_GEN (perf->i915) <12 || !stream->ctx)) {DRM_DEBUG ("Only OA report sampling supported\n" );return -EINVAL ; }
@@ -2750,7 +2751,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, format_size = perf->oa_formats[props->oa_format].size; - stream->sample_flags |=SAMPLE_OA_REPORT ; + stream->sample_flags = props->sample_flags; stream->sample_size += format_size; stream->oa_buffer.format_size = format_size;
Signature · 6 lines
2.20.1 _______________________________________________ Intel-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/intel-gfx
PATCH 2/2 drm/i915/perf: Configure OAR for specific context
Gen12 supports saving/restoring render counters per context. Apply OAR configuration only for the context that is passed in to perf.
v2:
- Fix OACTXCONTROL value to only stop/resume counters.
- Remove gen12_update_reg_state_unlocked as power state is already applied by the caller.
--- drivers/gpu/drm/i915/i915_perf.c | 193 +++++++++++++++++-------------- 1 file changed, 108 insertions(+), 85 deletions(-)
drivers/gpu/drm/i915/i915_perf.c +108 -85
@@ -2078,20 +2078,12 @@ gen8_update_reg_state_unlocked(const struct intel_context *ce,u32 *reg_state = ce->lrc_reg_state;int i; -if (IS_GEN (stream->perf->i915,12 )) { -u32 format = stream->oa_buffer.format; + reg_state[ctx_oactxctrl +1 ] = + (stream->period_exponent <<GEN8_OA_TIMER_PERIOD_SHIFT ) | + (stream->periodic ?GEN8_OA_TIMER_ENABLE :0 ) | +GEN8_OA_COUNTER_RESUME ; - reg_state[ctx_oactxctrl +1 ] = - (format <<GEN12_OAR_OACONTROL_COUNTER_FORMAT_SHIFT ) | - (stream->oa_config ?GEN12_OAR_OACONTROL_COUNTER_ENABLE :0 ); - }else { - reg_state[ctx_oactxctrl +1 ] = - (stream->period_exponent <<GEN8_OA_TIMER_PERIOD_SHIFT ) | - (stream->periodic ?GEN8_OA_TIMER_ENABLE :0 ) | -GEN8_OA_COUNTER_RESUME ; - } - -for (i =0 ; !!ctx_flexeu0 && i <ARRAY_SIZE (flex_regs); i++) +for (i =0 ; i <ARRAY_SIZE (flex_regs); i++) reg_state[ctx_flexeu0 + i *2 +1 ] =oa_config_flex_reg (stream->oa_config, flex_regs[i]);
@@ -2224,34 +2216,49 @@ static int gen8_configure_context(struct i915_gem_context *ctx,return err; } -static int gen12_emit_oar_config (struct intel_context *ce,bool enable) +static int gen12_configure_oar_context (struct i915_perf_stream *stream,bool enable) { -struct i915_request *rq; -u32 *cs; -int err =0 ; - - rq =i915_request_create (ce); -if (IS_ERR (rq)) -return PTR_ERR (rq); +int err; +struct intel_context *ce = stream->pinned_ctx; +struct flex regs_context[] = { + { +GEN8_OACTXCONTROL , + stream->perf->ctx_oactxctrl_offset +1 , + enable ?GEN8_OA_COUNTER_RESUME :0 , + }, + }; +struct flex regs_lri[] = { + { +GEN12_OAR_OACONTROL , + }, + { +RING_CONTEXT_CONTROL (ce->engine->mmio_base), + }, + }; +u32 format = stream->oa_buffer.format; - cs =intel_ring_begin (rq,4 ); -if (IS_ERR (cs)) { - err =PTR_ERR (cs); - goto out; - } + regs_lri[0 ].value = + (format <<GEN12_OAR_OACONTROL_COUNTER_FORMAT_SHIFT ) | + (enable ?GEN12_OAR_OACONTROL_COUNTER_ENABLE :0 ); - *cs++ =MI_LOAD_REGISTER_IMM (1 ); - *cs++ =i915_mmio_reg_offset (RING_CONTEXT_CONTROL (ce->engine->mmio_base)); - *cs++ =_MASKED_FIELD (GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE , - enable ?GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE :0 ); - *cs++ =MI_NOOP ; + regs_lri[1 ].value = +_MASKED_FIELD (GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE , + enable ? +GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE : +0 ); -intel_ring_advance (rq, cs); +/* Modify the context image of pinned context with regs_context*/ + err =intel_context_lock_pinned (ce); +if (err) +return err; -out: -i915_request_add (rq); + err =gen8_modify_context (ce, regs_context,ARRAY_SIZE (regs_context)); +intel_context_unlock_pinned (ce); +if (err) +return err; -return err; +/* Apply regs_lri using LRI with pinned context */ +return gen8_modify_self (ce, regs_lri,ARRAY_SIZE (regs_lri)); }/*
@@ -2277,53 +2284,16 @@ static int gen12_emit_oar_config(struct intel_context *ce, bool enable)* per-context OA state. * * Note: it's only the RCS/Render context that has any OA state. +* Note: the first flex register passed must always be R_PWR_CLK_STATE */ -static int lrc_configure_all_contexts (struct i915_perf_stream *stream, -const struct i915_oa_config *oa_config) +static int oa_configure_all_contexts (struct i915_perf_stream *stream, +struct flex *regs, +size_t num_regs) {struct drm_i915_private *i915 = stream->perf->i915; -/* The MMIO offsets for Flex EU registers aren't contiguous */ -const u32 ctx_flexeu0 = stream->perf->ctx_flexeu0_offset; -#define ctx_flexeuN (N ) (ctx_flexeu0 + 2 * (N) + 1) -struct flex regs[] = { - { -GEN8_R_PWR_CLK_STATE , -CTX_R_PWR_CLK_STATE , - }, - { -IS_GEN (i915,12 ) ? -GEN12_OAR_OACONTROL :GEN8_OACTXCONTROL , - stream->perf->ctx_oactxctrl_offset +1 , - }, - {EU_PERF_CNTL0 ,ctx_flexeuN (0 ) }, - {EU_PERF_CNTL1 ,ctx_flexeuN (1 ) }, - {EU_PERF_CNTL2 ,ctx_flexeuN (2 ) }, - {EU_PERF_CNTL3 ,ctx_flexeuN (3 ) }, - {EU_PERF_CNTL4 ,ctx_flexeuN (4 ) }, - {EU_PERF_CNTL5 ,ctx_flexeuN (5 ) }, - {EU_PERF_CNTL6 ,ctx_flexeuN (6 ) }, - }; -#undef ctx_flexeuNstruct intel_engine_cs *engine;struct i915_gem_context *ctx, *cn; -size_t array_size =IS_GEN (i915,12 ) ?2 :ARRAY_SIZE (regs); -int i, err; - -if (IS_GEN (i915,12 )) { -u32 format = stream->oa_buffer.format; - - regs[1 ].value = - (format <<GEN12_OAR_OACONTROL_COUNTER_FORMAT_SHIFT ) | - (oa_config ?GEN12_OAR_OACONTROL_COUNTER_ENABLE :0 ); - }else { - regs[1 ].value = - (stream->period_exponent <<GEN8_OA_TIMER_PERIOD_SHIFT ) | - (stream->periodic ?GEN8_OA_TIMER_ENABLE :0 ) | -GEN8_OA_COUNTER_RESUME ; - } - -for (i =2 ; !!ctx_flexeu0 && i < array_size; i++) - regs[i].value =oa_config_flex_reg (oa_config, regs[i].reg); +int err;lockdep_assert_held (&stream->perf->lock);
@@ -2353,7 +2323,7 @@ static int lrc_configure_all_contexts(struct i915_perf_stream *stream,spin_unlock (&i915->gem.contexts.lock); - err =gen8_configure_context (ctx, regs, array_size); + err =gen8_configure_context (ctx, regs, num_regs);if (err) {i915_gem_context_put (ctx);return err;
@@ -2378,7 +2348,7 @@ static int lrc_configure_all_contexts(struct i915_perf_stream *stream, regs[0 ].value =intel_sseu_make_rpcs (i915, &ce->sseu); - err =gen8_modify_self (ce, regs, array_size); + err =gen8_modify_self (ce, regs, num_regs);if (err)return err; }
@@ -2386,6 +2356,56 @@ static int lrc_configure_all_contexts(struct i915_perf_stream *stream,return 0 ; } +static int gen12_configure_all_contexts (struct i915_perf_stream *stream, +const struct i915_oa_config *oa_config) +{ +struct flex regs[] = { + { +GEN8_R_PWR_CLK_STATE , +CTX_R_PWR_CLK_STATE , + }, + }; + +return oa_configure_all_contexts (stream, regs,ARRAY_SIZE (regs)); +} + +static int lrc_configure_all_contexts (struct i915_perf_stream *stream, +const struct i915_oa_config *oa_config) +{ +/* The MMIO offsets for Flex EU registers aren't contiguous */ +const u32 ctx_flexeu0 = stream->perf->ctx_flexeu0_offset; +#define ctx_flexeuN (N ) (ctx_flexeu0 + 2 * (N) + 1) +struct flex regs[] = { + { +GEN8_R_PWR_CLK_STATE , +CTX_R_PWR_CLK_STATE , + }, + { +GEN8_OACTXCONTROL , + stream->perf->ctx_oactxctrl_offset +1 , + }, + {EU_PERF_CNTL0 ,ctx_flexeuN (0 ) }, + {EU_PERF_CNTL1 ,ctx_flexeuN (1 ) }, + {EU_PERF_CNTL2 ,ctx_flexeuN (2 ) }, + {EU_PERF_CNTL3 ,ctx_flexeuN (3 ) }, + {EU_PERF_CNTL4 ,ctx_flexeuN (4 ) }, + {EU_PERF_CNTL5 ,ctx_flexeuN (5 ) }, + {EU_PERF_CNTL6 ,ctx_flexeuN (6 ) }, + }; +#undef ctx_flexeuN +int i; + + regs[1 ].value = + (stream->period_exponent <<GEN8_OA_TIMER_PERIOD_SHIFT ) | + (stream->periodic ?GEN8_OA_TIMER_ENABLE :0 ) | +GEN8_OA_COUNTER_RESUME ; + +for (i =2 ; i <ARRAY_SIZE (regs); i++) + regs[i].value =oa_config_flex_reg (oa_config, regs[i].reg); + +return oa_configure_all_contexts (stream, regs,ARRAY_SIZE (regs)); +} +static int gen8_enable_metric_set (struct i915_perf_stream *stream) {struct intel_uncore *uncore = stream->uncore;
@@ -2469,7 +2489,7 @@ static int gen12_enable_metric_set(struct i915_perf_stream *stream)* to make sure all slices/subslices are ON before writing to NOA * registers. */ - ret =lrc_configure_all_contexts (stream, oa_config); + ret =gen12_configure_all_contexts (stream, oa_config);if (ret)return ret;
@@ -2479,8 +2499,7 @@ static int gen12_enable_metric_set(struct i915_perf_stream *stream)* requested this. */ if (stream->ctx) { - ret =gen12_emit_oar_config (stream->pinned_ctx, - oa_config !=NULL ); + ret =gen12_configure_oar_context (stream, oa_config !=NULL );if (ret)return ret; }
@@ -2514,11 +2533,11 @@ static void gen12_disable_metric_set(struct i915_perf_stream *stream)struct intel_uncore *uncore = stream->uncore;/* Reset all contexts' slices/subslices configurations. */ -lrc_configure_all_contexts (stream,NULL ); +gen12_configure_all_contexts (stream,NULL );/* disable the context save/restore or OAR counters */ if (stream->ctx) -gen12_emit_oar_config (stream->pinned_ctx, false); +gen12_configure_oar_context (stream, false);/* Make sure we disable noa to save power. */ intel_uncore_rmw (uncore,RPM_CONFIG1 ,GEN10_GT_NOA_ENABLE ,0 );
@@ -2860,7 +2879,11 @@ void i915_oa_init_reg_state(const struct intel_context *ce,return ; stream = engine->i915->perf.exclusive_stream; -if (stream) +/* +* For gen12, only CTX_R_PWR_CLK_STATE needs update, but the caller +* is already doing that, so nothing to be done for gen12 here. +*/ +if (stream &&INTEL_GEN (stream->perf->i915) <12 )gen8_update_reg_state_unlocked (ce, stream); }
Signature · 6 lines
2.20.1 _______________________________________________ Intel-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Re: [PATCH 2/2] drm/i915/perf: Configure OAR for specific context
Quoted 9 lines · Umesh Nerlige Ramappa
Gen12 supports saving/restoring render counters per context. Apply OAR configuration only for the context that is passed in to perf.
v2:
- Fix OACTXCONTROL value to only stop/resume counters.
- Removegen12_update_reg_state_unlockedas power state is already applied by the caller.Signed-off-by Umesh Nerlige Ramappa <[email protected]>
IGT Tests in this series:
https://patchwork.freedesktop.org/series/69322/
gen12-mi-rpc
gen12-unprivileged-single-ctx-counters
Thanks,
Umesh
Quoted 293 lines
---
drivers/gpu/drm/i915/i915_perf.c| 193 +++++++++++++++++--------------1 file changed, 108 insertions(+), 85 deletions(-)drivers/gpu/drm/i915/i915_perf.c +108
-85@@ -2078,20 +2078,12 @@ gen8_update_reg_state_unlocked(const struct intel_context *ce,u32 *reg_state = ce->lrc_reg_state;int i; -if (IS_GEN (stream->perf->i915,12 )) { -u32 format = stream->oa_buffer.format; + reg_state[ctx_oactxctrl +1 ] = + (stream->period_exponent <<GEN8_OA_TIMER_PERIOD_SHIFT ) | + (stream->periodic ?GEN8_OA_TIMER_ENABLE :0 ) | +GEN8_OA_COUNTER_RESUME ; - reg_state[ctx_oactxctrl +1 ] = - (format <<GEN12_OAR_OACONTROL_COUNTER_FORMAT_SHIFT ) | - (stream->oa_config ?GEN12_OAR_OACONTROL_COUNTER_ENABLE :0 ); - }else { - reg_state[ctx_oactxctrl +1 ] = - (stream->period_exponent <<GEN8_OA_TIMER_PERIOD_SHIFT ) | - (stream->periodic ?GEN8_OA_TIMER_ENABLE :0 ) | -GEN8_OA_COUNTER_RESUME ; - } - -for (i =0 ; !!ctx_flexeu0 && i <ARRAY_SIZE (flex_regs); i++) +for (i =0 ; i <ARRAY_SIZE (flex_regs); i++) reg_state[ctx_flexeu0 + i *2 +1 ] =oa_config_flex_reg (stream->oa_config, flex_regs[i]);@@ -2224,34 +2216,49 @@ static int gen8_configure_context(struct i915_gem_context *ctx,return err; } -static int gen12_emit_oar_config (struct intel_context *ce,bool enable) +static int gen12_configure_oar_context (struct i915_perf_stream *stream,bool enable) { -struct i915_request *rq; -u32 *cs; -int err =0 ; - - rq =i915_request_create (ce); -if (IS_ERR (rq)) -return PTR_ERR (rq); +int err; +struct intel_context *ce = stream->pinned_ctx; +struct flex regs_context[] = { + { +GEN8_OACTXCONTROL , + stream->perf->ctx_oactxctrl_offset +1 , + enable ?GEN8_OA_COUNTER_RESUME :0 , + }, + }; +struct flex regs_lri[] = { + { +GEN12_OAR_OACONTROL , + }, + { +RING_CONTEXT_CONTROL (ce->engine->mmio_base), + }, + }; +u32 format = stream->oa_buffer.format; - cs =intel_ring_begin (rq,4 ); -if (IS_ERR (cs)) { - err =PTR_ERR (cs); - goto out; - } + regs_lri[0 ].value = + (format <<GEN12_OAR_OACONTROL_COUNTER_FORMAT_SHIFT ) | + (enable ?GEN12_OAR_OACONTROL_COUNTER_ENABLE :0 ); - *cs++ =MI_LOAD_REGISTER_IMM (1 ); - *cs++ =i915_mmio_reg_offset (RING_CONTEXT_CONTROL (ce->engine->mmio_base)); - *cs++ =_MASKED_FIELD (GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE , - enable ?GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE :0 ); - *cs++ =MI_NOOP ; + regs_lri[1 ].value = +_MASKED_FIELD (GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE , + enable ? +GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE : +0 ); -intel_ring_advance (rq, cs); +/* Modify the context image of pinned context with regs_context*/ + err =intel_context_lock_pinned (ce); +if (err) +return err; -out: -i915_request_add (rq); + err =gen8_modify_context (ce, regs_context,ARRAY_SIZE (regs_context)); +intel_context_unlock_pinned (ce); +if (err) +return err; -return err; +/* Apply regs_lri using LRI with pinned context */ +return gen8_modify_self (ce, regs_lri,ARRAY_SIZE (regs_lri)); }/* @@ -2277,53 +2284,16 @@ static int gen12_emit_oar_config(struct intel_context *ce, bool enable)* per-context OA state. * * Note: it's only the RCS/Render context that has any OA state. +* Note: the first flex register passed must always be R_PWR_CLK_STATE */ -static int lrc_configure_all_contexts (struct i915_perf_stream *stream, -const struct i915_oa_config *oa_config) +static int oa_configure_all_contexts (struct i915_perf_stream *stream, +struct flex *regs, +size_t num_regs) {struct drm_i915_private *i915 = stream->perf->i915; -/* The MMIO offsets for Flex EU registers aren't contiguous */ -const u32 ctx_flexeu0 = stream->perf->ctx_flexeu0_offset; -#define ctx_flexeuN (N ) (ctx_flexeu0 + 2 * (N) + 1) -struct flex regs[] = { - { -GEN8_R_PWR_CLK_STATE , -CTX_R_PWR_CLK_STATE , - }, - { -IS_GEN (i915,12 ) ? -GEN12_OAR_OACONTROL :GEN8_OACTXCONTROL , - stream->perf->ctx_oactxctrl_offset +1 , - }, - {EU_PERF_CNTL0 ,ctx_flexeuN (0 ) }, - {EU_PERF_CNTL1 ,ctx_flexeuN (1 ) }, - {EU_PERF_CNTL2 ,ctx_flexeuN (2 ) }, - {EU_PERF_CNTL3 ,ctx_flexeuN (3 ) }, - {EU_PERF_CNTL4 ,ctx_flexeuN (4 ) }, - {EU_PERF_CNTL5 ,ctx_flexeuN (5 ) }, - {EU_PERF_CNTL6 ,ctx_flexeuN (6 ) }, - }; -#undef ctx_flexeuNstruct intel_engine_cs *engine;struct i915_gem_context *ctx, *cn; -size_t array_size =IS_GEN (i915,12 ) ?2 :ARRAY_SIZE (regs); -int i, err; - -if (IS_GEN (i915,12 )) { -u32 format = stream->oa_buffer.format; - - regs[1 ].value = - (format <<GEN12_OAR_OACONTROL_COUNTER_FORMAT_SHIFT ) | - (oa_config ?GEN12_OAR_OACONTROL_COUNTER_ENABLE :0 ); - }else { - regs[1 ].value = - (stream->period_exponent <<GEN8_OA_TIMER_PERIOD_SHIFT ) | - (stream->periodic ?GEN8_OA_TIMER_ENABLE :0 ) | -GEN8_OA_COUNTER_RESUME ; - } - -for (i =2 ; !!ctx_flexeu0 && i < array_size; i++) - regs[i].value =oa_config_flex_reg (oa_config, regs[i].reg); +int err;lockdep_assert_held (&stream->perf->lock);@@ -2353,7 +2323,7 @@ static int lrc_configure_all_contexts(struct i915_perf_stream *stream,spin_unlock (&i915->gem.contexts.lock); - err =gen8_configure_context (ctx, regs, array_size); + err =gen8_configure_context (ctx, regs, num_regs);if (err) {i915_gem_context_put (ctx);return err;@@ -2378,7 +2348,7 @@ static int lrc_configure_all_contexts(struct i915_perf_stream *stream, regs[0 ].value =intel_sseu_make_rpcs (i915, &ce->sseu); - err =gen8_modify_self (ce, regs, array_size); + err =gen8_modify_self (ce, regs, num_regs);if (err)return err; }@@ -2386,6 +2356,56 @@ static int lrc_configure_all_contexts(struct i915_perf_stream *stream,return 0 ; } +static int gen12_configure_all_contexts (struct i915_perf_stream *stream, +const struct i915_oa_config *oa_config) +{ +struct flex regs[] = { + { +GEN8_R_PWR_CLK_STATE , +CTX_R_PWR_CLK_STATE , + }, + }; + +return oa_configure_all_contexts (stream, regs,ARRAY_SIZE (regs)); +} + +static int lrc_configure_all_contexts (struct i915_perf_stream *stream, +const struct i915_oa_config *oa_config) +{ +/* The MMIO offsets for Flex EU registers aren't contiguous */ +const u32 ctx_flexeu0 = stream->perf->ctx_flexeu0_offset; +#define ctx_flexeuN (N ) (ctx_flexeu0 + 2 * (N) + 1) +struct flex regs[] = { + { +GEN8_R_PWR_CLK_STATE , +CTX_R_PWR_CLK_STATE , + }, + { +GEN8_OACTXCONTROL , + stream->perf->ctx_oactxctrl_offset +1 , + }, + {EU_PERF_CNTL0 ,ctx_flexeuN (0 ) }, + {EU_PERF_CNTL1 ,ctx_flexeuN (1 ) }, + {EU_PERF_CNTL2 ,ctx_flexeuN (2 ) }, + {EU_PERF_CNTL3 ,ctx_flexeuN (3 ) }, + {EU_PERF_CNTL4 ,ctx_flexeuN (4 ) }, + {EU_PERF_CNTL5 ,ctx_flexeuN (5 ) }, + {EU_PERF_CNTL6 ,ctx_flexeuN (6 ) }, + }; +#undef ctx_flexeuN +int i; + + regs[1 ].value = + (stream->period_exponent <<GEN8_OA_TIMER_PERIOD_SHIFT ) | + (stream->periodic ?GEN8_OA_TIMER_ENABLE :0 ) | +GEN8_OA_COUNTER_RESUME ; + +for (i =2 ; i <ARRAY_SIZE (regs); i++) + regs[i].value =oa_config_flex_reg (oa_config, regs[i].reg); + +return oa_configure_all_contexts (stream, regs,ARRAY_SIZE (regs)); +} +static int gen8_enable_metric_set (struct i915_perf_stream *stream) {struct intel_uncore *uncore = stream->uncore;@@ -2469,7 +2489,7 @@ static int gen12_enable_metric_set(struct i915_perf_stream *stream)* to make sure all slices/subslices are ON before writing to NOA * registers. */ - ret =lrc_configure_all_contexts (stream, oa_config); + ret =gen12_configure_all_contexts (stream, oa_config);if (ret)return ret;@@ -2479,8 +2499,7 @@ static int gen12_enable_metric_set(struct i915_perf_stream *stream)* requested this. */ if (stream->ctx) { - ret =gen12_emit_oar_config (stream->pinned_ctx, - oa_config !=NULL ); + ret =gen12_configure_oar_context (stream, oa_config !=NULL );if (ret)return ret; }@@ -2514,11 +2533,11 @@ static void gen12_disable_metric_set(struct i915_perf_stream *stream)struct intel_uncore *uncore = stream->uncore;/* Reset all contexts' slices/subslices configurations. */ -lrc_configure_all_contexts (stream,NULL ); +gen12_configure_all_contexts (stream,NULL );/* disable the context save/restore or OAR counters */ if (stream->ctx) -gen12_emit_oar_config (stream->pinned_ctx, false); +gen12_configure_oar_context (stream, false);/* Make sure we disable noa to save power. */ intel_uncore_rmw (uncore,RPM_CONFIG1 ,GEN10_GT_NOA_ENABLE ,0 );@@ -2860,7 +2879,11 @@ void i915_oa_init_reg_state(const struct intel_context *ce,return ; stream = engine->i915->perf.exclusive_stream; -if (stream) +/* +* For gen12, only CTX_R_PWR_CLK_STATE needs update, but the caller +* is already doing that, so nothing to be done for gen12 here. +*/ +if (stream &&INTEL_GEN (stream->perf->i915) <12 )gen8_update_reg_state_unlocked (ce, stream); }Signature · 6 lines
2.20.1 _______________________________________________ Intel-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/intel-gfx
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Re: [PATCH 2/2] drm/i915/perf: Configure OAR for specific context
In reply to Umesh Nerlige RamappaQuoted 56 lines · Umesh Nerlige Ramappa
Gen12 supports saving/restoring render counters per context. Apply OAR configuration only for the context that is passed in to perf.
v2:
- Fix OACTXCONTROL value to only stop/resume counters.
- Removegen12_update_reg_state_unlockedas power state is already applied by the caller.Signed-off-by Umesh Nerlige Ramappa <[email protected]>--- drivers/gpu/drm/i915/i915_perf.c | 193 +++++++++++++++++-------------- 1 file changed, 108 insertions(+), 85 deletions(-)drivers/gpu/drm/i915/i915_perf.c +6
-20@@ -2078,20 +2078,12 @@ gen8_update_reg_state_unlocked(const struct intel_context *ce,u32 *reg_state = ce->lrc_reg_state;int i; -if (IS_GEN (stream->perf->i915,12 )) { -u32 format = stream->oa_buffer.format; + reg_state[ctx_oactxctrl +1 ] = + (stream->period_exponent <<GEN8_OA_TIMER_PERIOD_SHIFT ) | + (stream->periodic ?GEN8_OA_TIMER_ENABLE :0 ) | +GEN8_OA_COUNTER_RESUME ; - reg_state[ctx_oactxctrl +1 ] = - (format <<GEN12_OAR_OACONTROL_COUNTER_FORMAT_SHIFT ) | - (stream->oa_config ?GEN12_OAR_OACONTROL_COUNTER_ENABLE :0 ); - }else { - reg_state[ctx_oactxctrl +1 ] = - (stream->period_exponent <<GEN8_OA_TIMER_PERIOD_SHIFT ) | - (stream->periodic ?GEN8_OA_TIMER_ENABLE :0 ) | -GEN8_OA_COUNTER_RESUME ; - } - -for (i =0 ; !!ctx_flexeu0 && i <ARRAY_SIZE (flex_regs); i++) +for (i =0 ; i <ARRAY_SIZE (flex_regs); i++) reg_state[ctx_flexeu0 + i *2 +1 ] =oa_config_flex_reg (stream->oa_config, flex_regs[i]);@@ -2224,34 +2216,49 @@ static int gen8_configure_context(struct i915_gem_context *ctx,return err; } -static int gen12_emit_oar_config (struct intel_context *ce,bool enable) +static int gen12_configure_oar_context (struct i915_perf_stream *stream,bool enable) { -struct i915_request *rq; -u32 *cs; -int err =0 ; - - rq =i915_request_create (ce); -if (IS_ERR (rq))
drivers/gpu/drm/i915/i915_perf.c static int gen8_configure_context(struct i915_gem_context *ctx, · line 2229
Quoted 10 lines
drivers/gpu/drm/i915/i915_perf.c +9
-1-return PTR_ERR (rq); +int err; +struct intel_context *ce = stream->pinned_ctx; +struct flex regs_context[] = { + { +GEN8_OACTXCONTROL , + stream->perf->ctx_oactxctrl_offset +1 , + enable ?GEN8_OA_COUNTER_RESUME :0 , + }, + };
When do we configure the Flex registers?
Quoted 19 lines
drivers/gpu/drm/i915/i915_perf.c +12
-5+struct flex regs_lri[] = { + { +GEN12_OAR_OACONTROL , + }, + { +RING_CONTEXT_CONTROL (ce->engine->mmio_base), + }, + }; +u32 format = stream->oa_buffer.format; - cs =intel_ring_begin (rq,4 ); -if (IS_ERR (cs)) { - err =PTR_ERR (cs); - goto out; - } + regs_lri[0 ].value = + (format <<GEN12_OAR_OACONTROL_COUNTER_FORMAT_SHIFT ) | + (enable ?GEN12_OAR_OACONTROL_COUNTER_ENABLE :0 );
drivers/gpu/drm/i915/i915_perf.c static int gen8_configure_context(struct i915_gem_context *ctx, · line 2248
Quoted 10 lines
drivers/gpu/drm/i915/i915_perf.c +5
-5- *cs++ =MI_LOAD_REGISTER_IMM (1 ); - *cs++ =i915_mmio_reg_offset (RING_CONTEXT_CONTROL (ce->engine->mmio_base)); - *cs++ =_MASKED_FIELD (GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE , - enable ?GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE :0 ); - *cs++ =MI_NOOP ; + regs_lri[1 ].value = +_MASKED_FIELD (GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE , + enable ? +GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE : +0 );
Can't we put those values in the array above?
Quoted 164 lines
drivers/gpu/drm/i915/i915_perf.c +68
-49-intel_ring_advance (rq, cs); +/* Modify the context image of pinned context with regs_context*/ + err =intel_context_lock_pinned (ce); +if (err) +return err; -out: -i915_request_add (rq); + err =gen8_modify_context (ce, regs_context,ARRAY_SIZE (regs_context)); +intel_context_unlock_pinned (ce); +if (err) +return err; -return err; +/* Apply regs_lri using LRI with pinned context */ +return gen8_modify_self (ce, regs_lri,ARRAY_SIZE (regs_lri)); }/* @@ -2277,53 +2284,16 @@ static int gen12_emit_oar_config(struct intel_context *ce, bool enable)* per-context OA state. * * Note: it's only the RCS/Render context that has any OA state. +* Note: the first flex register passed must always be R_PWR_CLK_STATE */ -static int lrc_configure_all_contexts (struct i915_perf_stream *stream, -const struct i915_oa_config *oa_config) +static int oa_configure_all_contexts (struct i915_perf_stream *stream, +struct flex *regs, +size_t num_regs) {struct drm_i915_private *i915 = stream->perf->i915; -/* The MMIO offsets for Flex EU registers aren't contiguous */ -const u32 ctx_flexeu0 = stream->perf->ctx_flexeu0_offset; -#define ctx_flexeuN (N ) (ctx_flexeu0 + 2 * (N) + 1) -struct flex regs[] = { - { -GEN8_R_PWR_CLK_STATE , -CTX_R_PWR_CLK_STATE , - }, - { -IS_GEN (i915,12 ) ? -GEN12_OAR_OACONTROL :GEN8_OACTXCONTROL , - stream->perf->ctx_oactxctrl_offset +1 , - }, - {EU_PERF_CNTL0 ,ctx_flexeuN (0 ) }, - {EU_PERF_CNTL1 ,ctx_flexeuN (1 ) }, - {EU_PERF_CNTL2 ,ctx_flexeuN (2 ) }, - {EU_PERF_CNTL3 ,ctx_flexeuN (3 ) }, - {EU_PERF_CNTL4 ,ctx_flexeuN (4 ) }, - {EU_PERF_CNTL5 ,ctx_flexeuN (5 ) }, - {EU_PERF_CNTL6 ,ctx_flexeuN (6 ) }, - }; -#undef ctx_flexeuNstruct intel_engine_cs *engine;struct i915_gem_context *ctx, *cn; -size_t array_size =IS_GEN (i915,12 ) ?2 :ARRAY_SIZE (regs); -int i, err; - -if (IS_GEN (i915,12 )) { -u32 format = stream->oa_buffer.format; - - regs[1 ].value = - (format <<GEN12_OAR_OACONTROL_COUNTER_FORMAT_SHIFT ) | - (oa_config ?GEN12_OAR_OACONTROL_COUNTER_ENABLE :0 ); - }else { - regs[1 ].value = - (stream->period_exponent <<GEN8_OA_TIMER_PERIOD_SHIFT ) | - (stream->periodic ?GEN8_OA_TIMER_ENABLE :0 ) | -GEN8_OA_COUNTER_RESUME ; - } - -for (i =2 ; !!ctx_flexeu0 && i < array_size; i++) - regs[i].value =oa_config_flex_reg (oa_config, regs[i].reg); +int err;lockdep_assert_held (&stream->perf->lock);@@ -2353,7 +2323,7 @@ static int lrc_configure_all_contexts(struct i915_perf_stream *stream,spin_unlock (&i915->gem.contexts.lock); - err =gen8_configure_context (ctx, regs, array_size); + err =gen8_configure_context (ctx, regs, num_regs);if (err) {i915_gem_context_put (ctx);return err;@@ -2378,7 +2348,7 @@ static int lrc_configure_all_contexts(struct i915_perf_stream *stream, regs[0 ].value =intel_sseu_make_rpcs (i915, &ce->sseu); - err =gen8_modify_self (ce, regs, array_size); + err =gen8_modify_self (ce, regs, num_regs);if (err)return err; }@@ -2386,6 +2356,56 @@ static int lrc_configure_all_contexts(struct i915_perf_stream *stream,return 0 ; } +static int gen12_configure_all_contexts (struct i915_perf_stream *stream, +const struct i915_oa_config *oa_config) +{ +struct flex regs[] = { + { +GEN8_R_PWR_CLK_STATE , +CTX_R_PWR_CLK_STATE , + }, + }; + +return oa_configure_all_contexts (stream, regs,ARRAY_SIZE (regs)); +} + +static int lrc_configure_all_contexts (struct i915_perf_stream *stream, +const struct i915_oa_config *oa_config) +{ +/* The MMIO offsets for Flex EU registers aren't contiguous */ +const u32 ctx_flexeu0 = stream->perf->ctx_flexeu0_offset; +#define ctx_flexeuN (N ) (ctx_flexeu0 + 2 * (N) + 1) +struct flex regs[] = { + { +GEN8_R_PWR_CLK_STATE , +CTX_R_PWR_CLK_STATE , + }, + { +GEN8_OACTXCONTROL , + stream->perf->ctx_oactxctrl_offset +1 , + }, + {EU_PERF_CNTL0 ,ctx_flexeuN (0 ) }, + {EU_PERF_CNTL1 ,ctx_flexeuN (1 ) }, + {EU_PERF_CNTL2 ,ctx_flexeuN (2 ) }, + {EU_PERF_CNTL3 ,ctx_flexeuN (3 ) }, + {EU_PERF_CNTL4 ,ctx_flexeuN (4 ) }, + {EU_PERF_CNTL5 ,ctx_flexeuN (5 ) }, + {EU_PERF_CNTL6 ,ctx_flexeuN (6 ) }, + }; +#undef ctx_flexeuN +int i; + + regs[1 ].value = + (stream->period_exponent <<GEN8_OA_TIMER_PERIOD_SHIFT ) | + (stream->periodic ?GEN8_OA_TIMER_ENABLE :0 ) | +GEN8_OA_COUNTER_RESUME ; + +for (i =2 ; i <ARRAY_SIZE (regs); i++) + regs[i].value =oa_config_flex_reg (oa_config, regs[i].reg); + +return oa_configure_all_contexts (stream, regs,ARRAY_SIZE (regs)); +} +static int gen8_enable_metric_set (struct i915_perf_stream *stream) {struct intel_uncore *uncore = stream->uncore;@@ -2469,7 +2489,7 @@ static int gen12_enable_metric_set(struct i915_perf_stream *stream)* to make sure all slices/subslices are ON before writing to NOA * registers. */ - ret =lrc_configure_all_contexts (stream, oa_config); + ret =gen12_configure_all_contexts (stream, oa_config);if (ret)return ret;
drivers/gpu/drm/i915/i915_perf.c static int gen12_enable_metric_set(struct i915_perf_stream *stream) · line 2502
Quoted 6 lines
drivers/gpu/drm/i915/i915_perf.c +1
-2@@ -2479,8 +2499,7 @@ static int gen12_enable_metric_set(struct i915_perf_stream *stream)* requested this. */ if (stream->ctx) { - ret =gen12_emit_oar_config (stream->pinned_ctx, - oa_config !=NULL ); + ret =gen12_configure_oar_context (stream, oa_config !=NULL );
I think you can assume oa_config is going to be != NULL in the enable_metric_set vfunc.
Quoted 20 lines
drivers/gpu/drm/i915/i915_perf.c +2
-2if (ret)return ret; }@@ -2514,11 +2533,11 @@ static void gen12_disable_metric_set(struct i915_perf_stream *stream)struct intel_uncore *uncore = stream->uncore;/* Reset all contexts' slices/subslices configurations. */ -lrc_configure_all_contexts (stream,NULL ); +gen12_configure_all_contexts (stream,NULL );/* disable the context save/restore or OAR counters */ if (stream->ctx) -gen12_emit_oar_config (stream->pinned_ctx, false); +gen12_configure_oar_context (stream, false);/* Make sure we disable noa to save power. */ intel_uncore_rmw (uncore,RPM_CONFIG1 ,GEN10_GT_NOA_ENABLE ,0 );@@ -2860,7 +2879,11 @@ void i915_oa_init_reg_state(const struct intel_context *ce,return ;
drivers/gpu/drm/i915/i915_perf.c void i915_oa_init_reg_state(const struct intel_context *ce, · line 2889
Quoted 10 lines
drivers/gpu/drm/i915/i915_perf.c +5
-1stream = engine->i915->perf.exclusive_stream; -if (stream) +/* +* For gen12, only CTX_R_PWR_CLK_STATE needs update, but the caller +* is already doing that, so nothing to be done for gen12 here. +*/ +if (stream &&INTEL_GEN (stream->perf->i915) <12 )gen8_update_reg_state_unlocked (ce, stream); }
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Re: [PATCH 2/2] drm/i915/perf: Configure OAR for specific context
Quoted 58 lines · Lionel Landwerlin
Quoted 57 lines · Umesh Nerlige Ramappa
Gen12 supports saving/restoring render counters per context. Apply OAR configuration only for the context that is passed in to perf.
v2:
- Fix OACTXCONTROL value to only stop/resume counters.
- Removegen12_update_reg_state_unlockedas power state is already applied by the caller.Signed-off-by Umesh Nerlige Ramappa <[email protected]>--- drivers/gpu/drm/i915/i915_perf.c | 193 +++++++++++++++++-------------- 1 file changed, 108 insertions(+), 85 deletions(-)drivers/gpu/drm/i915/i915_perf.c +10
-21@@ -2078,20 +2078,12 @@ gen8_update_reg_state_unlocked(const struct intel_context *ce,u32 *reg_state = ce->lrc_reg_state;int i; -if (IS_GEN (stream->perf->i915,12 )) { -u32 format = stream->oa_buffer.format; + reg_state[ctx_oactxctrl +1 ] = + (stream->period_exponent <<GEN8_OA_TIMER_PERIOD_SHIFT ) | + (stream->periodic ?GEN8_OA_TIMER_ENABLE :0 ) | +GEN8_OA_COUNTER_RESUME ; - reg_state[ctx_oactxctrl +1 ] = - (format <<GEN12_OAR_OACONTROL_COUNTER_FORMAT_SHIFT ) | - (stream->oa_config ?GEN12_OAR_OACONTROL_COUNTER_ENABLE :0 ); - }else { - reg_state[ctx_oactxctrl +1 ] = - (stream->period_exponent <<GEN8_OA_TIMER_PERIOD_SHIFT ) | - (stream->periodic ?GEN8_OA_TIMER_ENABLE :0 ) | -GEN8_OA_COUNTER_RESUME ; - } - -for (i =0 ; !!ctx_flexeu0 && i <ARRAY_SIZE (flex_regs); i++) +for (i =0 ; i <ARRAY_SIZE (flex_regs); i++) reg_state[ctx_flexeu0 + i *2 +1 ] =oa_config_flex_reg (stream->oa_config, flex_regs[i]);@@ -2224,34 +2216,49 @@ static int gen8_configure_context(struct i915_gem_context *ctx,return err; } -static int gen12_emit_oar_config (struct intel_context *ce,bool enable) +static int gen12_configure_oar_context (struct i915_perf_stream *stream,bool enable) { -struct i915_request *rq; -u32 *cs; -int err =0 ; - - rq =i915_request_create (ce); -if (IS_ERR (rq)) -return PTR_ERR (rq); +int err; +struct intel_context *ce = stream->pinned_ctx; +struct flex regs_context[] = { + {
Quoted 8 lines
drivers/gpu/drm/i915/i915_perf.c static int gen8_configure_context(struct i915_gem_context *ctx, · line 2229
Quoted 5 lines
drivers/gpu/drm/i915/i915_perf.c +5
-0+ GEN8_OACTXCONTROL, + stream->perf->ctx_oactxctrl_offset + 1, + enable ? GEN8_OA_COUNTER_RESUME : 0, + }, + };When do we configure the Flex registers?
I don't see flex registers in the context image dump or in the spec, so I guess we would only configure them if they are part of the metric set.
Will post a new version with below comments.
Thanks,
Umesh
Quoted 214 lines
Quoted 19 lines
drivers/gpu/drm/i915/i915_perf.c +12
-5+struct flex regs_lri[] = { + { +GEN12_OAR_OACONTROL , + }, + { +RING_CONTEXT_CONTROL (ce->engine->mmio_base), + }, + }; +u32 format = stream->oa_buffer.format; - cs =intel_ring_begin (rq,4 ); -if (IS_ERR (cs)) { - err =PTR_ERR (cs); - goto out; - } + regs_lri[0 ].value = + (format <<GEN12_OAR_OACONTROL_COUNTER_FORMAT_SHIFT ) | + (enable ?GEN12_OAR_OACONTROL_COUNTER_ENABLE :0 );drivers/gpu/drm/i915/i915_perf.c static int gen8_configure_context(struct i915_gem_context *ctx, · line 2248
Quoted 10 lines
drivers/gpu/drm/i915/i915_perf.c +5
-5- *cs++ =MI_LOAD_REGISTER_IMM (1 ); - *cs++ =i915_mmio_reg_offset (RING_CONTEXT_CONTROL (ce->engine->mmio_base)); - *cs++ =_MASKED_FIELD (GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE , - enable ?GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE :0 ); - *cs++ =MI_NOOP ; + regs_lri[1 ].value = +_MASKED_FIELD (GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE , + enable ? +GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE : +0 );Can't we put those values in the array above?
Quoted 152 lines
drivers/gpu/drm/i915/i915_perf.c +68
-49-intel_ring_advance (rq, cs); +/* Modify the context image of pinned context with regs_context*/ + err =intel_context_lock_pinned (ce); +if (err) +return err; -out: -i915_request_add (rq); + err =gen8_modify_context (ce, regs_context,ARRAY_SIZE (regs_context)); +intel_context_unlock_pinned (ce); +if (err) +return err; -return err; +/* Apply regs_lri using LRI with pinned context */ +return gen8_modify_self (ce, regs_lri,ARRAY_SIZE (regs_lri)); }/* @@ -2277,53 +2284,16 @@ static int gen12_emit_oar_config(struct intel_context *ce, bool enable)* per-context OA state. * * Note: it's only the RCS/Render context that has any OA state. +* Note: the first flex register passed must always be R_PWR_CLK_STATE */ -static int lrc_configure_all_contexts (struct i915_perf_stream *stream, -const struct i915_oa_config *oa_config) +static int oa_configure_all_contexts (struct i915_perf_stream *stream, +struct flex *regs, +size_t num_regs) {struct drm_i915_private *i915 = stream->perf->i915; -/* The MMIO offsets for Flex EU registers aren't contiguous */ -const u32 ctx_flexeu0 = stream->perf->ctx_flexeu0_offset; -#define ctx_flexeuN (N ) (ctx_flexeu0 + 2 * (N) + 1) -struct flex regs[] = { - { -GEN8_R_PWR_CLK_STATE , -CTX_R_PWR_CLK_STATE , - }, - { -IS_GEN (i915,12 ) ? -GEN12_OAR_OACONTROL :GEN8_OACTXCONTROL , - stream->perf->ctx_oactxctrl_offset +1 , - }, - {EU_PERF_CNTL0 ,ctx_flexeuN (0 ) }, - {EU_PERF_CNTL1 ,ctx_flexeuN (1 ) }, - {EU_PERF_CNTL2 ,ctx_flexeuN (2 ) }, - {EU_PERF_CNTL3 ,ctx_flexeuN (3 ) }, - {EU_PERF_CNTL4 ,ctx_flexeuN (4 ) }, - {EU_PERF_CNTL5 ,ctx_flexeuN (5 ) }, - {EU_PERF_CNTL6 ,ctx_flexeuN (6 ) }, - }; -#undef ctx_flexeuNstruct intel_engine_cs *engine;struct i915_gem_context *ctx, *cn; -size_t array_size =IS_GEN (i915,12 ) ?2 :ARRAY_SIZE (regs); -int i, err; - -if (IS_GEN (i915,12 )) { -u32 format = stream->oa_buffer.format; - - regs[1 ].value = - (format <<GEN12_OAR_OACONTROL_COUNTER_FORMAT_SHIFT ) | - (oa_config ?GEN12_OAR_OACONTROL_COUNTER_ENABLE :0 ); - }else { - regs[1 ].value = - (stream->period_exponent <<GEN8_OA_TIMER_PERIOD_SHIFT ) | - (stream->periodic ?GEN8_OA_TIMER_ENABLE :0 ) | -GEN8_OA_COUNTER_RESUME ; - } - -for (i =2 ; !!ctx_flexeu0 && i < array_size; i++) - regs[i].value =oa_config_flex_reg (oa_config, regs[i].reg); +int err;lockdep_assert_held (&stream->perf->lock);@@ -2353,7 +2323,7 @@ static int lrc_configure_all_contexts(struct i915_perf_stream *stream,spin_unlock (&i915->gem.contexts.lock); - err =gen8_configure_context (ctx, regs, array_size); + err =gen8_configure_context (ctx, regs, num_regs);if (err) {i915_gem_context_put (ctx);return err;@@ -2378,7 +2348,7 @@ static int lrc_configure_all_contexts(struct i915_perf_stream *stream, regs[0 ].value =intel_sseu_make_rpcs (i915, &ce->sseu); - err =gen8_modify_self (ce, regs, array_size); + err =gen8_modify_self (ce, regs, num_regs);if (err)return err; }@@ -2386,6 +2356,56 @@ static int lrc_configure_all_contexts(struct i915_perf_stream *stream,return 0 ; } +static int gen12_configure_all_contexts (struct i915_perf_stream *stream, +const struct i915_oa_config *oa_config) +{ +struct flex regs[] = { + { +GEN8_R_PWR_CLK_STATE , +CTX_R_PWR_CLK_STATE , + }, + }; + +return oa_configure_all_contexts (stream, regs,ARRAY_SIZE (regs)); +} + +static int lrc_configure_all_contexts (struct i915_perf_stream *stream, +const struct i915_oa_config *oa_config) +{ +/* The MMIO offsets for Flex EU registers aren't contiguous */ +const u32 ctx_flexeu0 = stream->perf->ctx_flexeu0_offset; +#define ctx_flexeuN (N ) (ctx_flexeu0 + 2 * (N) + 1) +struct flex regs[] = { + { +GEN8_R_PWR_CLK_STATE , +CTX_R_PWR_CLK_STATE , + }, + { +GEN8_OACTXCONTROL , + stream->perf->ctx_oactxctrl_offset +1 , + }, + {EU_PERF_CNTL0 ,ctx_flexeuN (0 ) }, + {EU_PERF_CNTL1 ,ctx_flexeuN (1 ) }, + {EU_PERF_CNTL2 ,ctx_flexeuN (2 ) }, + {EU_PERF_CNTL3 ,ctx_flexeuN (3 ) }, + {EU_PERF_CNTL4 ,ctx_flexeuN (4 ) }, + {EU_PERF_CNTL5 ,ctx_flexeuN (5 ) }, + {EU_PERF_CNTL6 ,ctx_flexeuN (6 ) }, + }; +#undef ctx_flexeuN +int i; + + regs[1 ].value = + (stream->period_exponent <<GEN8_OA_TIMER_PERIOD_SHIFT ) | + (stream->periodic ?GEN8_OA_TIMER_ENABLE :0 ) | +GEN8_OA_COUNTER_RESUME ; + +for (i =2 ; i <ARRAY_SIZE (regs); i++) + regs[i].value =oa_config_flex_reg (oa_config, regs[i].reg); + +return oa_configure_all_contexts (stream, regs,ARRAY_SIZE (regs)); +} +static int gen8_enable_metric_set (struct i915_perf_stream *stream) {struct intel_uncore *uncore = stream->uncore;@@ -2469,7 +2489,7 @@ static int gen12_enable_metric_set(struct i915_perf_stream *stream)* to make sure all slices/subslices are ON before writing to NOA * registers. */ - ret =lrc_configure_all_contexts (stream, oa_config); + ret =gen12_configure_all_contexts (stream, oa_config);if (ret)return ret;drivers/gpu/drm/i915/i915_perf.c static int gen12_enable_metric_set(struct i915_perf_stream *stream) · line 2502
Quoted 6 lines
drivers/gpu/drm/i915/i915_perf.c +1
-2@@ -2479,8 +2499,7 @@ static int gen12_enable_metric_set(struct i915_perf_stream *stream)* requested this. */ if (stream->ctx) { - ret =gen12_emit_oar_config (stream->pinned_ctx, - oa_config !=NULL ); + ret =gen12_configure_oar_context (stream, oa_config !=NULL );I think you can assume
oa_configis going to be != NULL in theenable_metric_setvfunc.Quoted 17 lines
drivers/gpu/drm/i915/i915_perf.c +2
-2if (ret)return ret; }@@ -2514,11 +2533,11 @@ static void gen12_disable_metric_set(struct i915_perf_stream *stream)struct intel_uncore *uncore = stream->uncore;/* Reset all contexts' slices/subslices configurations. */ -lrc_configure_all_contexts (stream,NULL ); +gen12_configure_all_contexts (stream,NULL );/* disable the context save/restore or OAR counters */ if (stream->ctx) -gen12_emit_oar_config (stream->pinned_ctx, false); +gen12_configure_oar_context (stream, false);/* Make sure we disable noa to save power. */ intel_uncore_rmw (uncore,RPM_CONFIG1 ,GEN10_GT_NOA_ENABLE ,0 );@@ -2860,7 +2879,11 @@ void i915_oa_init_reg_state(const struct intel_context *ce,return ; stream = engine->i915->perf.exclusive_stream;
Quoted 10 lines
drivers/gpu/drm/i915/i915_perf.c void i915_oa_init_reg_state(const struct intel_context *ce, · line 2888
Quoted 8 lines
drivers/gpu/drm/i915/i915_perf.c +5
-1-if (stream) +/* +* For gen12, only CTX_R_PWR_CLK_STATE needs update, but the caller +* is already doing that, so nothing to be done for gen12 here. +*/ +if (stream &&INTEL_GEN (stream->perf->i915) <12 )gen8_update_reg_state_unlocked (ce, stream); }
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Patchwork
CI✗ Fi.CI.CHECKPATCH: warning for series starting with [1/2] drm/i915/perf: Allow non-privileged access when OA buffer is not sampled
In reply to Umesh Nerlige Ramappa== Series Details ==
== Series Details ==
Series: series starting with [1/2] drm/i915/perf: Allow non-privileged access when OA buffer is not sampled
URL : https://patchwork.freedesktop.org/series/69491/
State : warning
== Summary ==
$ dim checkpatch origin/drm-tip 61f9bbf85888 drm/i915/perf: Allow non-privileged access when OA buffer is not sampled e58eb681f814 drm/i915/perf: Configure OAR for specific context -:267: CHECK:COMPARISON_TO_NULL: Comparison to NULL could be written "oa_config" #267: FILE: drivers/gpu/drm/i915/i915_perf.c:2502: + ret = gen12_configure_oar_context(stream, oa_config != NULL);
total: 0 errors, 0 warnings, 1 checks, 268 lines checked
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Patchwork
CI✗ Fi.CI.BAT: failure for series starting with [1/2] drm/i915/perf: Allow non-privileged access when OA buffer is not sampled
In reply to Umesh Nerlige Ramappa== Series Details ==
== Series Details ==
Series: series starting with [1/2] drm/i915/perf: Allow non-privileged access when OA buffer is not sampled
URL : https://patchwork.freedesktop.org/series/69491/
State : failure
== Summary ==
CI Bug Log - changes from CI_DRM_7346 -> Patchwork_15267
====================================================
Summary
-------
**FAILURE**
Serious unknown changes coming with Patchwork_15267 absolutely need to be verified manually.
If you think the reported changes have nothing to do with the changes introduced in Patchwork_15267, please notify your bug team to allow them to document this new failure mode, which will reduce false positives in CI.
External URL: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_15267/index.html
Possible new issues
-------------------
Here are the unknown changes that may have been introduced in Patchwork_15267:
### IGT changes ###
#### Possible regressions ####
* igt@i915_selftest@live_sanitycheck:
- fi-skl-lmem: NOTRUN -> [DMESG-WARN][1]
[1]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_15267/fi-skl-lmem/igt@i915_selftest@live_sanitycheck.html
Known issues
------------
Here are the changes found in Patchwork_15267 that come from known issues:
### IGT changes ###
#### Issues hit ####
* igt@gem_exec_suspend@basic-s3:
- fi-icl-dsi: [PASS][2] -> [INCOMPLETE][3] ([fdo#107713])
[2]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7346/fi-icl-dsi/igt@[email protected]
[3]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_15267/fi-icl-dsi/igt@[email protected]
#### Possible fixes ####
* igt@i915_module_load@reload-with-fault-injection:
- {fi-kbl-7560u}: [INCOMPLETE][4] ([fdo#109964] / [fdo#110343]) -> [PASS][5]
[4]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7346/fi-kbl-7560u/igt@[email protected]
[5]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_15267/fi-kbl-7560u/igt@[email protected]
* igt@i915_pm_rpm@module-reload:
- fi-skl-lmem: [DMESG-WARN][6] ([fdo#112261]) -> [PASS][7]
[6]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7346/fi-skl-lmem/igt@[email protected]
[7]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_15267/fi-skl-lmem/igt@[email protected]
* igt@i915_selftest@live_gem_contexts:
- fi-bsw-n3050: [INCOMPLETE][8] ([fdo# 111542]) -> [PASS][9]
[8]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7346/fi-bsw-n3050/igt@i915_selftest@live_gem_contexts.html
[9]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_15267/fi-bsw-n3050/igt@i915_selftest@live_gem_contexts.html
* igt@kms_chamelium@hdmi-edid-read:
- fi-kbl-7500u: [FAIL][10] ([fdo#109483]) -> [PASS][11]
[10]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7346/fi-kbl-7500u/igt@[email protected]
[11]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_15267/fi-kbl-7500u/igt@[email protected]
{name}: This element is suppressed. This means it is ignored when computing
the status of the difference (SUCCESS, WARNING, or FAILURE).
[fdo# 111542]: https://bugs.freedesktop.org/show_bug.cgi?id= 111542 [fdo#107713]: https://bugs.freedesktop.org/show_bug.cgi?id=107713
[fdo#109483]: https://bugs.freedesktop.org/show_bug.cgi?id=109483
[fdo#109964]: https://bugs.freedesktop.org/show_bug.cgi?id=109964
[fdo#110343]: https://bugs.freedesktop.org/show_bug.cgi?id=110343
[fdo#112261]: https://bugs.freedesktop.org/show_bug.cgi?id=112261
Participating hosts (49 -> 45)
------------------------------
Missing (4): fi-byt-clapper fi-byt-squawks fi-bsw-cyan fi-hsw-4200u
Build changes
-------------
* CI: CI-20190529 -> None
* Linux: CI_DRM_7346 -> Patchwork_15267
CI-20190529: 20190529
CI_DRM_7346: 78fd2497a0a373d6a68c047d759851e0a895f112 @ git://anongit.freedesktop.org/gfx-ci/linux
IGT_5284: b28d801e4c010942d05821fada6dd9d2d67d6e4d @ git://anongit.freedesktop.org/xorg/app/intel-gpu-tools
Patchwork_15267: e58eb681f814760556613c83fae52e3f1bd27e26 @ git://anongit.freedesktop.org/gfx-ci/linux
== Linux commits ==
e58eb681f814 drm/i915/perf: Configure OAR for specific context 61f9bbf85888 drm/i915/perf: Allow non-privileged access when OA buffer is not sampled
== Logs ==
For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_15267/index.html
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx