| Message ID | 20241205-topic-sm8x50-gpu-bw-vote-v4-2-9650d15dd435@linaro.org (mailing list archive) |
|---|---|
| State | Superseded |
| Headers | show |
| Series | drm/msm: adreno: add support for DDR bandwidth scaling via GMU | expand |
On 12/5/2024 8:31 PM, Neil Armstrong wrote: > The Adreno GPU Management Unit (GMU) can also scale DDR Bandwidth along > the Frequency and Power Domain level, but by default we leave the > OPP core scale the interconnect ddr path. > > While scaling via the interconnect path was sufficient, newer GPUs > like the A750 requires specific vote paremeters and bandwidth to > achieve full functionality. > > In order to calculate vote values used by the GPU Management > Unit (GMU), we need to parse all the possible OPP Bandwidths and > create a vote value to be sent to the appropriate Bus Control > Modules (BCMs) declared in the GPU info struct. > > This vote value is called IB, while on the other side 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 vote will be calculated later when setting the frequency. > > The vote array will then be used to dynamically generate the GMU > bw_table sent during the GMU power-up. > > Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org> Reviewed-by: Akhil P Oommen <quic_akhilpo@quicinc.com> -Akhil > --- > drivers/gpu/drm/msm/adreno/a6xx_gmu.c | 144 ++++++++++++++++++++++++++++++++++ > drivers/gpu/drm/msm/adreno/a6xx_gmu.h | 13 +++ > drivers/gpu/drm/msm/adreno/a6xx_gpu.h | 1 + > 3 files changed, 158 insertions(+) > > diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c > index 14db7376c712d19446b38152e480bd5a1e0a5198..36696d372a42a27b26a018b19e73bc6d8a4a5235 100644 > --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c > +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c > @@ -9,6 +9,7 @@ > #include <linux/pm_domain.h> > #include <linux/pm_opp.h> > #include <soc/qcom/cmd-db.h> > +#include <soc/qcom/tcs.h> > #include <drm/drm_gem.h> > > #include "a6xx_gpu.h" > @@ -1287,6 +1288,101 @@ static int a6xx_gmu_memory_probe(struct a6xx_gmu *gmu) > return 0; > } > > +/** > + * struct bcm_db - Auxiliary data pertaining to each Bus Clock Manager (BCM) > + * @unit: divisor used to convert bytes/sec bw value to an RPMh msg > + * @width: multiplier used to convert bytes/sec bw value to an RPMh msg > + * @vcd: virtual clock domain that this bcm belongs to > + * @reserved: reserved field > + */ > +struct bcm_db { > + __le32 unit; > + __le16 width; > + u8 vcd; > + u8 reserved; > +}; > + > +static int a6xx_gmu_rpmh_bw_votes_init(const struct a6xx_info *info, > + struct a6xx_gmu *gmu) > +{ > + const struct bcm_db *bcm_data[GMU_MAX_BCMS] = { 0 }; > + unsigned int bcm_index, bw_index, bcm_count = 0; > + > + if (!info->bcms) > + return 0; > + > + /* Retrieve BCM data from cmd-db */ > + for (bcm_index = 0; bcm_index < GMU_MAX_BCMS; bcm_index++) { > + size_t count; > + > + /* Stop at first unconfigured bcm */ > + if (!info->bcms[bcm_index].name) > + break; > + > + bcm_data[bcm_index] = cmd_db_read_aux_data( > + info->bcms[bcm_index].name, > + &count); > + if (IS_ERR(bcm_data[bcm_index])) > + return PTR_ERR(bcm_data[bcm_index]); > + > + if (!count) > + return -EINVAL; > + > + ++bcm_count; > + } > + > + /* Generate BCM votes values for each bandwidth & BCM */ > + for (bw_index = 0; bw_index < gmu->nr_gpu_bws; bw_index++) { > + u32 *data = gmu->gpu_ib_votes[bw_index]; > + u32 bw = gmu->gpu_bw_table[bw_index]; > + > + /* Calculations loosely copied from bcm_aggregate() & tcs_cmd_gen() */ > + for (bcm_index = 0; bcm_index < bcm_count; bcm_index++) { > + bool commit = false; > + u64 peak; > + u32 vote; > + > + /* Skip unconfigured BCM */ > + if (!bcm_data[bcm_index]) > + continue; > + > + if (bcm_index == bcm_count - 1 || > + (bcm_data[bcm_index + 1] && > + bcm_data[bcm_index]->vcd != bcm_data[bcm_index + 1]->vcd)) > + commit = true; > + > + if (!bw) { > + data[bcm_index] = BCM_TCS_CMD(commit, false, 0, 0); > + continue; > + } > + > + if (info->bcms[bcm_index].fixed) { > + u32 perfmode = 0; > + > + if (bw >= info->bcms[bcm_index].perfmode_bw) > + perfmode = info->bcms[bcm_index].perfmode; > + > + data[bcm_index] = BCM_TCS_CMD(commit, true, 0, perfmode); > + continue; > + } > + > + /* Multiply the bandwidth by the width of the connection */ > + peak = (u64)bw * le16_to_cpu(bcm_data[bcm_index]->width); > + do_div(peak, info->bcms[bcm_index].buswidth); > + > + /* Input bandwidth value is in KBps, scale the value to BCM unit */ > + peak *= 1000ULL; > + do_div(peak, le32_to_cpu(bcm_data[bcm_index]->unit)); > + > + vote = clamp(peak, 1, BCM_TCS_CMD_VOTE_MASK); > + > + data[bcm_index] = BCM_TCS_CMD(commit, true, vote, vote); > + } > + } > + > + return 0; > +} > + > /* Return the 'arc-level' for the given frequency */ > static unsigned int a6xx_gmu_get_arc_level(struct device *dev, > unsigned long freq) > @@ -1390,12 +1486,15 @@ static int a6xx_gmu_rpmh_arc_votes_init(struct device *dev, u32 *votes, > * The GMU votes with the RPMh for itself and on behalf of the GPU but we need > * to construct the list of votes on the CPU and send it over. Query the RPMh > * voltage levels and build the votes > + * The GMU can also vote for DDR interconnects, use the OPP bandwidth entries > + * and BCM parameters to build the votes. > */ > > static int a6xx_gmu_rpmh_votes_init(struct a6xx_gmu *gmu) > { > struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu); > struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; > + const struct a6xx_info *info = adreno_gpu->info->a6xx; > struct msm_gpu *gpu = &adreno_gpu->base; > int ret; > > @@ -1407,6 +1506,10 @@ static int a6xx_gmu_rpmh_votes_init(struct a6xx_gmu *gmu) > ret |= a6xx_gmu_rpmh_arc_votes_init(gmu->dev, gmu->cx_arc_votes, > gmu->gmu_freqs, gmu->nr_gmu_freqs, "cx.lvl"); > > + /* Build the interconnect votes */ > + if (info->bcms && gmu->nr_gpu_bws > 1) > + ret |= a6xx_gmu_rpmh_bw_votes_init(info, gmu); > + > return ret; > } > > @@ -1442,10 +1545,43 @@ static int a6xx_gmu_build_freq_table(struct device *dev, unsigned long *freqs, > return index; > } > > +static int a6xx_gmu_build_bw_table(struct device *dev, unsigned long *bandwidths, > + u32 size) > +{ > + int count = dev_pm_opp_get_opp_count(dev); > + struct dev_pm_opp *opp; > + int i, index = 0; > + unsigned int bandwidth = 1; > + > + /* > + * The OPP table doesn't contain the "off" bandwidth level so we need to > + * add 1 to the table size to account for it > + */ > + > + if (WARN(count + 1 > size, > + "The GMU bandwidth table is being truncated\n")) > + count = size - 1; > + > + /* Set the "off" bandwidth */ > + bandwidths[index++] = 0; > + > + for (i = 0; i < count; i++) { > + opp = dev_pm_opp_find_bw_ceil(dev, &bandwidth, 0); > + if (IS_ERR(opp)) > + break; > + > + dev_pm_opp_put(opp); > + bandwidths[index++] = bandwidth++; > + } > + > + return index; > +} > + > static int a6xx_gmu_pwrlevels_probe(struct a6xx_gmu *gmu) > { > struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu); > struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; > + const struct a6xx_info *info = adreno_gpu->info->a6xx; > struct msm_gpu *gpu = &adreno_gpu->base; > > int ret = 0; > @@ -1472,6 +1608,14 @@ static int a6xx_gmu_pwrlevels_probe(struct a6xx_gmu *gmu) > > gmu->current_perf_index = gmu->nr_gpu_freqs - 1; > > + /* > + * The GMU also handles GPU Interconnect Votes so build a list > + * of DDR bandwidths from the GPU OPP table > + */ > + if (info->bcms) > + gmu->nr_gpu_bws = a6xx_gmu_build_bw_table(&gpu->pdev->dev, > + gmu->gpu_bw_table, ARRAY_SIZE(gmu->gpu_bw_table)); > + > /* Build the list of RPMh votes that we'll send to the GMU */ > return a6xx_gmu_rpmh_votes_init(gmu); > } > diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h > index 88f18ea6a38a08b5b171709e5020010947a5d347..2062a2be224768c1937d7768f7b8439920e9e127 100644 > --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h > +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h > @@ -21,6 +21,15 @@ struct a6xx_gmu_bo { > > #define GMU_MAX_GX_FREQS 16 > #define GMU_MAX_CX_FREQS 4 > +#define GMU_MAX_BCMS 3 > + > +struct a6xx_bcm { > + char *name; > + unsigned int buswidth; > + bool fixed; > + unsigned int perfmode; > + unsigned int perfmode_bw; > +}; > > /* > * These define the different GMU wake up options - these define how both the > @@ -85,6 +94,10 @@ struct a6xx_gmu { > unsigned long gpu_freqs[GMU_MAX_GX_FREQS]; > u32 gx_arc_votes[GMU_MAX_GX_FREQS]; > > + int nr_gpu_bws; > + unsigned long gpu_bw_table[GMU_MAX_GX_FREQS]; > + u32 gpu_ib_votes[GMU_MAX_GX_FREQS][GMU_MAX_BCMS]; > + > int nr_gmu_freqs; > unsigned long gmu_freqs[GMU_MAX_CX_FREQS]; > u32 cx_arc_votes[GMU_MAX_CX_FREQS]; > diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h > index 4aceffb6aae89c781facc2a6e4a82b20b341b6cb..9201a53dd341bf432923ffb44947e015208a3d02 100644 > --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h > +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h > @@ -44,6 +44,7 @@ struct a6xx_info { > u32 gmu_chipid; > u32 gmu_cgc_mode; > u32 prim_fifo_threshold; > + const struct a6xx_bcm *bcms; > }; > > struct a6xx_gpu { >
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c index 14db7376c712d19446b38152e480bd5a1e0a5198..36696d372a42a27b26a018b19e73bc6d8a4a5235 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c @@ -9,6 +9,7 @@ #include <linux/pm_domain.h> #include <linux/pm_opp.h> #include <soc/qcom/cmd-db.h> +#include <soc/qcom/tcs.h> #include <drm/drm_gem.h> #include "a6xx_gpu.h" @@ -1287,6 +1288,101 @@ static int a6xx_gmu_memory_probe(struct a6xx_gmu *gmu) return 0; } +/** + * struct bcm_db - Auxiliary data pertaining to each Bus Clock Manager (BCM) + * @unit: divisor used to convert bytes/sec bw value to an RPMh msg + * @width: multiplier used to convert bytes/sec bw value to an RPMh msg + * @vcd: virtual clock domain that this bcm belongs to + * @reserved: reserved field + */ +struct bcm_db { + __le32 unit; + __le16 width; + u8 vcd; + u8 reserved; +}; + +static int a6xx_gmu_rpmh_bw_votes_init(const struct a6xx_info *info, + struct a6xx_gmu *gmu) +{ + const struct bcm_db *bcm_data[GMU_MAX_BCMS] = { 0 }; + unsigned int bcm_index, bw_index, bcm_count = 0; + + if (!info->bcms) + return 0; + + /* Retrieve BCM data from cmd-db */ + for (bcm_index = 0; bcm_index < GMU_MAX_BCMS; bcm_index++) { + size_t count; + + /* Stop at first unconfigured bcm */ + if (!info->bcms[bcm_index].name) + break; + + bcm_data[bcm_index] = cmd_db_read_aux_data( + info->bcms[bcm_index].name, + &count); + if (IS_ERR(bcm_data[bcm_index])) + return PTR_ERR(bcm_data[bcm_index]); + + if (!count) + return -EINVAL; + + ++bcm_count; + } + + /* Generate BCM votes values for each bandwidth & BCM */ + for (bw_index = 0; bw_index < gmu->nr_gpu_bws; bw_index++) { + u32 *data = gmu->gpu_ib_votes[bw_index]; + u32 bw = gmu->gpu_bw_table[bw_index]; + + /* Calculations loosely copied from bcm_aggregate() & tcs_cmd_gen() */ + for (bcm_index = 0; bcm_index < bcm_count; bcm_index++) { + bool commit = false; + u64 peak; + u32 vote; + + /* Skip unconfigured BCM */ + if (!bcm_data[bcm_index]) + continue; + + if (bcm_index == bcm_count - 1 || + (bcm_data[bcm_index + 1] && + bcm_data[bcm_index]->vcd != bcm_data[bcm_index + 1]->vcd)) + commit = true; + + if (!bw) { + data[bcm_index] = BCM_TCS_CMD(commit, false, 0, 0); + continue; + } + + if (info->bcms[bcm_index].fixed) { + u32 perfmode = 0; + + if (bw >= info->bcms[bcm_index].perfmode_bw) + perfmode = info->bcms[bcm_index].perfmode; + + data[bcm_index] = BCM_TCS_CMD(commit, true, 0, perfmode); + continue; + } + + /* Multiply the bandwidth by the width of the connection */ + peak = (u64)bw * le16_to_cpu(bcm_data[bcm_index]->width); + do_div(peak, info->bcms[bcm_index].buswidth); + + /* Input bandwidth value is in KBps, scale the value to BCM unit */ + peak *= 1000ULL; + do_div(peak, le32_to_cpu(bcm_data[bcm_index]->unit)); + + vote = clamp(peak, 1, BCM_TCS_CMD_VOTE_MASK); + + data[bcm_index] = BCM_TCS_CMD(commit, true, vote, vote); + } + } + + return 0; +} + /* Return the 'arc-level' for the given frequency */ static unsigned int a6xx_gmu_get_arc_level(struct device *dev, unsigned long freq) @@ -1390,12 +1486,15 @@ static int a6xx_gmu_rpmh_arc_votes_init(struct device *dev, u32 *votes, * The GMU votes with the RPMh for itself and on behalf of the GPU but we need * to construct the list of votes on the CPU and send it over. Query the RPMh * voltage levels and build the votes + * The GMU can also vote for DDR interconnects, use the OPP bandwidth entries + * and BCM parameters to build the votes. */ static int a6xx_gmu_rpmh_votes_init(struct a6xx_gmu *gmu) { struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu); struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; + const struct a6xx_info *info = adreno_gpu->info->a6xx; struct msm_gpu *gpu = &adreno_gpu->base; int ret; @@ -1407,6 +1506,10 @@ static int a6xx_gmu_rpmh_votes_init(struct a6xx_gmu *gmu) ret |= a6xx_gmu_rpmh_arc_votes_init(gmu->dev, gmu->cx_arc_votes, gmu->gmu_freqs, gmu->nr_gmu_freqs, "cx.lvl"); + /* Build the interconnect votes */ + if (info->bcms && gmu->nr_gpu_bws > 1) + ret |= a6xx_gmu_rpmh_bw_votes_init(info, gmu); + return ret; } @@ -1442,10 +1545,43 @@ static int a6xx_gmu_build_freq_table(struct device *dev, unsigned long *freqs, return index; } +static int a6xx_gmu_build_bw_table(struct device *dev, unsigned long *bandwidths, + u32 size) +{ + int count = dev_pm_opp_get_opp_count(dev); + struct dev_pm_opp *opp; + int i, index = 0; + unsigned int bandwidth = 1; + + /* + * The OPP table doesn't contain the "off" bandwidth level so we need to + * add 1 to the table size to account for it + */ + + if (WARN(count + 1 > size, + "The GMU bandwidth table is being truncated\n")) + count = size - 1; + + /* Set the "off" bandwidth */ + bandwidths[index++] = 0; + + for (i = 0; i < count; i++) { + opp = dev_pm_opp_find_bw_ceil(dev, &bandwidth, 0); + if (IS_ERR(opp)) + break; + + dev_pm_opp_put(opp); + bandwidths[index++] = bandwidth++; + } + + return index; +} + static int a6xx_gmu_pwrlevels_probe(struct a6xx_gmu *gmu) { struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu); struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; + const struct a6xx_info *info = adreno_gpu->info->a6xx; struct msm_gpu *gpu = &adreno_gpu->base; int ret = 0; @@ -1472,6 +1608,14 @@ static int a6xx_gmu_pwrlevels_probe(struct a6xx_gmu *gmu) gmu->current_perf_index = gmu->nr_gpu_freqs - 1; + /* + * The GMU also handles GPU Interconnect Votes so build a list + * of DDR bandwidths from the GPU OPP table + */ + if (info->bcms) + gmu->nr_gpu_bws = a6xx_gmu_build_bw_table(&gpu->pdev->dev, + gmu->gpu_bw_table, ARRAY_SIZE(gmu->gpu_bw_table)); + /* Build the list of RPMh votes that we'll send to the GMU */ return a6xx_gmu_rpmh_votes_init(gmu); } diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h index 88f18ea6a38a08b5b171709e5020010947a5d347..2062a2be224768c1937d7768f7b8439920e9e127 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h @@ -21,6 +21,15 @@ struct a6xx_gmu_bo { #define GMU_MAX_GX_FREQS 16 #define GMU_MAX_CX_FREQS 4 +#define GMU_MAX_BCMS 3 + +struct a6xx_bcm { + char *name; + unsigned int buswidth; + bool fixed; + unsigned int perfmode; + unsigned int perfmode_bw; +}; /* * These define the different GMU wake up options - these define how both the @@ -85,6 +94,10 @@ struct a6xx_gmu { unsigned long gpu_freqs[GMU_MAX_GX_FREQS]; u32 gx_arc_votes[GMU_MAX_GX_FREQS]; + int nr_gpu_bws; + unsigned long gpu_bw_table[GMU_MAX_GX_FREQS]; + u32 gpu_ib_votes[GMU_MAX_GX_FREQS][GMU_MAX_BCMS]; + int nr_gmu_freqs; unsigned long gmu_freqs[GMU_MAX_CX_FREQS]; u32 cx_arc_votes[GMU_MAX_CX_FREQS]; diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h index 4aceffb6aae89c781facc2a6e4a82b20b341b6cb..9201a53dd341bf432923ffb44947e015208a3d02 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h @@ -44,6 +44,7 @@ struct a6xx_info { u32 gmu_chipid; u32 gmu_cgc_mode; u32 prim_fifo_threshold; + const struct a6xx_bcm *bcms; }; struct a6xx_gpu {
The Adreno GPU Management Unit (GMU) can also scale DDR Bandwidth along the Frequency and Power Domain level, but by default we leave the OPP core scale the interconnect ddr path. While scaling via the interconnect path was sufficient, newer GPUs like the A750 requires specific vote paremeters and bandwidth to achieve full functionality. In order to calculate vote values used by the GPU Management Unit (GMU), we need to parse all the possible OPP Bandwidths and create a vote value to be sent to the appropriate Bus Control Modules (BCMs) declared in the GPU info struct. This vote value is called IB, while on the other side 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 vote will be calculated later when setting the frequency. The vote array will then be used to dynamically generate the GMU bw_table sent during the GMU power-up. Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org> --- drivers/gpu/drm/msm/adreno/a6xx_gmu.c | 144 ++++++++++++++++++++++++++++++++++ drivers/gpu/drm/msm/adreno/a6xx_gmu.h | 13 +++ drivers/gpu/drm/msm/adreno/a6xx_gpu.h | 1 + 3 files changed, 158 insertions(+)