| Message ID | 20241211-topic-sm8x50-gpu-bw-vote-v5-4-6112f9f785ec@linaro.org |
|---|---|
| State | New |
| Headers | show |
| Series | [v5,1/7] drm/msm: adreno: add defines for gpu & gmu frequency table sizes | expand |
On 11.12.2024 9:29 AM, Neil Armstrong wrote: > The Adreno GPU Management Unit (GMU) can also scale the DDR Bandwidth > along the Frequency and Power Domain level, until now we left the OPP > core scale the OPP bandwidth via the interconnect path. > > In order to enable bandwidth voting via the GPU Management > Unit (GMU), when an opp is set by devfreq we also look for > the corresponding bandwidth index in the previously generated > bw_table and pass this value along the frequency index to the GMU. > > The GMU also takes another vote called AB which is a 16bit quantized > value of the floor bandwidth against the maximum supported bandwidth. > > The AB is calculated with a default 25% of the bandwidth like the > downstream implementation too inform the GMU firmware the minimal > quantity of bandwidth we require for this OPP. > > Since we now vote for all resources via the GMU, setting the OPP > is no more needed, so we can completely skip calling > dev_pm_opp_set_opp() in this situation. > > Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org> > Reviewed-by: Akhil P Oommen <quic_akhilpo@quicinc.com> > Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org> > --- > drivers/gpu/drm/msm/adreno/a6xx_gmu.c | 39 +++++++++++++++++++++++++++++++++-- > drivers/gpu/drm/msm/adreno/a6xx_gmu.h | 2 +- > drivers/gpu/drm/msm/adreno/a6xx_hfi.c | 6 +++--- > drivers/gpu/drm/msm/adreno/a6xx_hfi.h | 5 +++++ > 4 files changed, 46 insertions(+), 6 deletions(-) > > diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c > index 36696d372a42a27b26a018b19e73bc6d8a4a5235..46ae0ec7a16a41d55755ce04fb32404cdba087be 100644 > --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c > +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c > @@ -110,9 +110,11 @@ void a6xx_gmu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp, > bool suspended) > { > struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); > + const struct a6xx_info *info = adreno_gpu->info->a6xx; > struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); > struct a6xx_gmu *gmu = &a6xx_gpu->gmu; > u32 perf_index; > + u32 bw_index = 0; > unsigned long gpu_freq; > int ret = 0; > > @@ -125,6 +127,37 @@ void a6xx_gmu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp, > if (gpu_freq == gmu->gpu_freqs[perf_index]) > break; > > + /* If enabled, find the corresponding DDR bandwidth index */ > + if (info->bcms && gmu->nr_gpu_bws > 1) { if (gmu->nr_gpu_bws) > + unsigned int bw = dev_pm_opp_get_bw(opp, true, 0); > + > + for (bw_index = 0; bw_index < gmu->nr_gpu_bws - 1; bw_index++) { > + if (bw == gmu->gpu_bw_table[bw_index]) > + break; > + } > + > + /* Vote AB as a fraction of the max bandwidth */ > + if (bw) { This seems to only be introduced with certain a7xx too.. you should ping the GMU with HFI_VALUE_GMU_AB_VOTE to check if it's supported > + u64 tmp; > + > + /* For now, vote for 25% of the bandwidth */ > + tmp = bw * 25; > + do_div(tmp, 100); > + > + /* > + * The AB vote consists of a 16 bit wide quantized level > + * against the maximum supported bandwidth. > + * Quantization can be calculated as below: > + * vote = (bandwidth * 2^16) / max bandwidth > + */ > + tmp *= MAX_AB_VOTE; > + do_div(tmp, gmu->gpu_bw_table[gmu->nr_gpu_bws - 1]); > + > + bw_index |= AB_VOTE(clamp(tmp, 1, MAX_AB_VOTE)); > + bw_index |= AB_VOTE_ENABLE; > + } > + } BTW, did you dump the values we send to the GMU here and in the RPMh builder part & validate against downstream? Konrad
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c index 36696d372a42a27b26a018b19e73bc6d8a4a5235..46ae0ec7a16a41d55755ce04fb32404cdba087be 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c @@ -110,9 +110,11 @@ void a6xx_gmu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp, bool suspended) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + const struct a6xx_info *info = adreno_gpu->info->a6xx; struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); struct a6xx_gmu *gmu = &a6xx_gpu->gmu; u32 perf_index; + u32 bw_index = 0; unsigned long gpu_freq; int ret = 0; @@ -125,6 +127,37 @@ void a6xx_gmu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp, if (gpu_freq == gmu->gpu_freqs[perf_index]) break; + /* If enabled, find the corresponding DDR bandwidth index */ + if (info->bcms && gmu->nr_gpu_bws > 1) { + unsigned int bw = dev_pm_opp_get_bw(opp, true, 0); + + for (bw_index = 0; bw_index < gmu->nr_gpu_bws - 1; bw_index++) { + if (bw == gmu->gpu_bw_table[bw_index]) + break; + } + + /* Vote AB as a fraction of the max bandwidth */ + if (bw) { + u64 tmp; + + /* For now, vote for 25% of the bandwidth */ + tmp = bw * 25; + do_div(tmp, 100); + + /* + * The AB vote consists of a 16 bit wide quantized level + * against the maximum supported bandwidth. + * Quantization can be calculated as below: + * vote = (bandwidth * 2^16) / max bandwidth + */ + tmp *= MAX_AB_VOTE; + do_div(tmp, gmu->gpu_bw_table[gmu->nr_gpu_bws - 1]); + + bw_index |= AB_VOTE(clamp(tmp, 1, MAX_AB_VOTE)); + bw_index |= AB_VOTE_ENABLE; + } + } + gmu->current_perf_index = perf_index; gmu->freq = gmu->gpu_freqs[perf_index]; @@ -140,8 +173,10 @@ void a6xx_gmu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp, return; if (!gmu->legacy) { - a6xx_hfi_set_freq(gmu, perf_index); - dev_pm_opp_set_opp(&gpu->pdev->dev, opp); + a6xx_hfi_set_freq(gmu, perf_index, bw_index); + /* With Bandwidth voting, we now vote for all resources, so skip OPP set */ + if (!bw_index) + dev_pm_opp_set_opp(&gpu->pdev->dev, opp); return; } diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h index 2062a2be224768c1937d7768f7b8439920e9e127..0c888b326cfb485400118f3601fa5f1949b03374 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h @@ -209,7 +209,7 @@ void a6xx_hfi_init(struct a6xx_gmu *gmu); int a6xx_hfi_start(struct a6xx_gmu *gmu, int boot_state); void a6xx_hfi_stop(struct a6xx_gmu *gmu); int a6xx_hfi_send_prep_slumber(struct a6xx_gmu *gmu); -int a6xx_hfi_set_freq(struct a6xx_gmu *gmu, int index); +int a6xx_hfi_set_freq(struct a6xx_gmu *gmu, u32 perf_index, u32 bw_index); bool a6xx_gmu_gx_is_on(struct a6xx_gmu *gmu); bool a6xx_gmu_sptprac_is_on(struct a6xx_gmu *gmu); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c index 995526620d678cd05020315f771213e4a6943bec..0989aee3dd2cf9bc3405c3b25a595c22e6f06387 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c @@ -772,13 +772,13 @@ static int a6xx_hfi_send_core_fw_start(struct a6xx_gmu *gmu) sizeof(msg), NULL, 0); } -int a6xx_hfi_set_freq(struct a6xx_gmu *gmu, int index) +int a6xx_hfi_set_freq(struct a6xx_gmu *gmu, u32 freq_index, u32 bw_index) { struct a6xx_hfi_gx_bw_perf_vote_cmd msg = { 0 }; msg.ack_type = 1; /* blocking */ - msg.freq = index; - msg.bw = 0; /* TODO: bus scaling */ + msg.freq = freq_index; + msg.bw = bw_index; return a6xx_hfi_send_msg(gmu, HFI_H2F_MSG_GX_BW_PERF_VOTE, &msg, sizeof(msg), NULL, 0); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_hfi.h b/drivers/gpu/drm/msm/adreno/a6xx_hfi.h index 528110169398f69f16443a29a1594d19c36fb595..52ba4a07d7b9a709289acd244a751ace9bdaab5d 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_hfi.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_hfi.h @@ -173,6 +173,11 @@ struct a6xx_hfi_gx_bw_perf_vote_cmd { u32 bw; }; +#define AB_VOTE_MASK GENMASK(31, 16) +#define MAX_AB_VOTE (FIELD_MAX(AB_VOTE_MASK) - 1) +#define AB_VOTE(vote) FIELD_PREP(AB_VOTE_MASK, (vote)) +#define AB_VOTE_ENABLE BIT(8) + #define HFI_H2F_MSG_PREPARE_SLUMBER 33 struct a6xx_hfi_prep_slumber_cmd {