From: Francisco Jerez <currojerez@riseup.net> To: linux-pm@vger.kernel.org, intel-gfx@lists.freedesktop.org Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>, "Pandruvada, Srinivas" <srinivas.pandruvada@intel.com>, "Vivi, Rodrigo" <rodrigo.vivi@intel.com>, Peter Zijlstra <peterz@infradead.org> Subject: [PATCH 07/10] cpufreq: intel_pstate: Implement VLP controller for HWP parts. Date: Tue, 10 Mar 2020 14:42:00 -0700 [thread overview] Message-ID: <20200310214203.26459-8-currojerez@riseup.net> (raw) In-Reply-To: <20200310214203.26459-1-currojerez@riseup.net> This implements a simple variably low-pass-filtering governor in control of the HWP MIN/MAX PERF range based on the previously introduced get_vlp_target_range(). See "cpufreq: intel_pstate: Implement VLP controller target P-state range estimation." for the rationale. Signed-off-by: Francisco Jerez <currojerez@riseup.net> --- drivers/cpufreq/intel_pstate.c | 79 +++++++++++++++++++++++++++++++++- 1 file changed, 77 insertions(+), 2 deletions(-) diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index cecadfec8bc1..a01eed40d897 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -1905,6 +1905,20 @@ static void intel_pstate_reset_vlp(struct cpudata *cpu) vlp->gain = max(1, div_fp(1000, vlp_params.setpoint_0_pml)); vlp->target.p_base = 0; vlp->stats.last_response_frequency_hz = vlp_params.avg_hz; + + if (hwp_active) { + const uint32_t p0 = max(cpu->pstate.min_pstate, + cpu->min_perf_ratio); + const uint32_t p1 = max_t(uint32_t, p0, cpu->max_perf_ratio); + const uint64_t hwp_req = (READ_ONCE(cpu->hwp_req_cached) & + ~(HWP_MAX_PERF(~0L) | + HWP_MIN_PERF(~0L) | + HWP_DESIRED_PERF(~0L))) | + HWP_MIN_PERF(p0) | HWP_MAX_PERF(p1); + + wrmsrl_on_cpu(cpu->cpu, MSR_HWP_REQUEST, hwp_req); + cpu->hwp_req_cached = hwp_req; + } } /** @@ -2222,6 +2236,46 @@ static void intel_pstate_adjust_pstate(struct cpudata *cpu) fp_toint(cpu->iowait_boost * 100)); } +static void intel_pstate_adjust_pstate_range(struct cpudata *cpu, + const unsigned int range[]) +{ + const int from = cpu->hwp_req_cached; + unsigned int p0, p1, p_min, p_max; + struct sample *sample; + uint64_t hwp_req; + + update_turbo_state(); + + p0 = max(cpu->pstate.min_pstate, cpu->min_perf_ratio); + p1 = max_t(unsigned int, p0, cpu->max_perf_ratio); + p_min = clamp_t(unsigned int, range[0], p0, p1); + p_max = clamp_t(unsigned int, range[1], p0, p1); + + trace_cpu_frequency(p_max * cpu->pstate.scaling, cpu->cpu); + + hwp_req = (READ_ONCE(cpu->hwp_req_cached) & + ~(HWP_MAX_PERF(~0L) | HWP_MIN_PERF(~0L) | + HWP_DESIRED_PERF(~0L))) | + HWP_MIN_PERF(vlp_params.debug & 2 ? p0 : p_min) | + HWP_MAX_PERF(vlp_params.debug & 4 ? p1 : p_max); + + if (hwp_req != cpu->hwp_req_cached) { + wrmsrl(MSR_HWP_REQUEST, hwp_req); + cpu->hwp_req_cached = hwp_req; + } + + sample = &cpu->sample; + trace_pstate_sample(mul_ext_fp(100, sample->core_avg_perf), + fp_toint(sample->busy_scaled), + from, + hwp_req, + sample->mperf, + sample->aperf, + sample->tsc, + get_avg_frequency(cpu), + fp_toint(cpu->iowait_boost * 100)); +} + static void intel_pstate_update_util(struct update_util_data *data, u64 time, unsigned int flags) { @@ -2260,6 +2314,22 @@ static void intel_pstate_update_util(struct update_util_data *data, u64 time, intel_pstate_adjust_pstate(cpu); } +/** + * Implementation of the cpufreq update_util hook based on the VLP + * controller (see get_vlp_target_range()). + */ +static void intel_pstate_update_util_hwp_vlp(struct update_util_data *data, + u64 time, unsigned int flags) +{ + struct cpudata *cpu = container_of(data, struct cpudata, update_util); + + if (update_vlp_sample(cpu, time, flags)) { + const struct vlp_target_range *target = + get_vlp_target_range(cpu); + intel_pstate_adjust_pstate_range(cpu, target->value); + } +} + static struct pstate_funcs core_funcs = { .get_max = core_get_max_pstate, .get_max_physical = core_get_max_pstate_physical, @@ -2389,6 +2459,9 @@ static int intel_pstate_init_cpu(unsigned int cpunum) intel_pstate_get_cpu_pstates(cpu); + if (pstate_funcs.update_util == intel_pstate_update_util_hwp_vlp) + intel_pstate_reset_vlp(cpu); + pr_debug("controlling: cpu %d\n", cpunum); return 0; @@ -2398,7 +2471,8 @@ static void intel_pstate_set_update_util_hook(unsigned int cpu_num) { struct cpudata *cpu = all_cpu_data[cpu_num]; - if (hwp_active && !hwp_boost) + if (hwp_active && !hwp_boost && + pstate_funcs.update_util != intel_pstate_update_util_hwp_vlp) return; if (cpu->update_util_set) @@ -2526,7 +2600,8 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy) * was turned off, in that case we need to clear the * update util hook. */ - if (!hwp_boost) + if (!hwp_boost && pstate_funcs.update_util != + intel_pstate_update_util_hwp_vlp) intel_pstate_clear_update_util_hook(policy->cpu); intel_pstate_hwp_set(policy->cpu); } -- 2.22.1
WARNING: multiple messages have this Message-ID (diff)
From: Francisco Jerez <currojerez@riseup.net> To: linux-pm@vger.kernel.org, intel-gfx@lists.freedesktop.org Cc: Peter Zijlstra <peterz@infradead.org>, "Rafael J. Wysocki" <rjw@rjwysocki.net>, "Pandruvada, Srinivas" <srinivas.pandruvada@intel.com> Subject: [Intel-gfx] [PATCH 07/10] cpufreq: intel_pstate: Implement VLP controller for HWP parts. Date: Tue, 10 Mar 2020 14:42:00 -0700 [thread overview] Message-ID: <20200310214203.26459-8-currojerez@riseup.net> (raw) In-Reply-To: <20200310214203.26459-1-currojerez@riseup.net> This implements a simple variably low-pass-filtering governor in control of the HWP MIN/MAX PERF range based on the previously introduced get_vlp_target_range(). See "cpufreq: intel_pstate: Implement VLP controller target P-state range estimation." for the rationale. Signed-off-by: Francisco Jerez <currojerez@riseup.net> --- drivers/cpufreq/intel_pstate.c | 79 +++++++++++++++++++++++++++++++++- 1 file changed, 77 insertions(+), 2 deletions(-) diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index cecadfec8bc1..a01eed40d897 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -1905,6 +1905,20 @@ static void intel_pstate_reset_vlp(struct cpudata *cpu) vlp->gain = max(1, div_fp(1000, vlp_params.setpoint_0_pml)); vlp->target.p_base = 0; vlp->stats.last_response_frequency_hz = vlp_params.avg_hz; + + if (hwp_active) { + const uint32_t p0 = max(cpu->pstate.min_pstate, + cpu->min_perf_ratio); + const uint32_t p1 = max_t(uint32_t, p0, cpu->max_perf_ratio); + const uint64_t hwp_req = (READ_ONCE(cpu->hwp_req_cached) & + ~(HWP_MAX_PERF(~0L) | + HWP_MIN_PERF(~0L) | + HWP_DESIRED_PERF(~0L))) | + HWP_MIN_PERF(p0) | HWP_MAX_PERF(p1); + + wrmsrl_on_cpu(cpu->cpu, MSR_HWP_REQUEST, hwp_req); + cpu->hwp_req_cached = hwp_req; + } } /** @@ -2222,6 +2236,46 @@ static void intel_pstate_adjust_pstate(struct cpudata *cpu) fp_toint(cpu->iowait_boost * 100)); } +static void intel_pstate_adjust_pstate_range(struct cpudata *cpu, + const unsigned int range[]) +{ + const int from = cpu->hwp_req_cached; + unsigned int p0, p1, p_min, p_max; + struct sample *sample; + uint64_t hwp_req; + + update_turbo_state(); + + p0 = max(cpu->pstate.min_pstate, cpu->min_perf_ratio); + p1 = max_t(unsigned int, p0, cpu->max_perf_ratio); + p_min = clamp_t(unsigned int, range[0], p0, p1); + p_max = clamp_t(unsigned int, range[1], p0, p1); + + trace_cpu_frequency(p_max * cpu->pstate.scaling, cpu->cpu); + + hwp_req = (READ_ONCE(cpu->hwp_req_cached) & + ~(HWP_MAX_PERF(~0L) | HWP_MIN_PERF(~0L) | + HWP_DESIRED_PERF(~0L))) | + HWP_MIN_PERF(vlp_params.debug & 2 ? p0 : p_min) | + HWP_MAX_PERF(vlp_params.debug & 4 ? p1 : p_max); + + if (hwp_req != cpu->hwp_req_cached) { + wrmsrl(MSR_HWP_REQUEST, hwp_req); + cpu->hwp_req_cached = hwp_req; + } + + sample = &cpu->sample; + trace_pstate_sample(mul_ext_fp(100, sample->core_avg_perf), + fp_toint(sample->busy_scaled), + from, + hwp_req, + sample->mperf, + sample->aperf, + sample->tsc, + get_avg_frequency(cpu), + fp_toint(cpu->iowait_boost * 100)); +} + static void intel_pstate_update_util(struct update_util_data *data, u64 time, unsigned int flags) { @@ -2260,6 +2314,22 @@ static void intel_pstate_update_util(struct update_util_data *data, u64 time, intel_pstate_adjust_pstate(cpu); } +/** + * Implementation of the cpufreq update_util hook based on the VLP + * controller (see get_vlp_target_range()). + */ +static void intel_pstate_update_util_hwp_vlp(struct update_util_data *data, + u64 time, unsigned int flags) +{ + struct cpudata *cpu = container_of(data, struct cpudata, update_util); + + if (update_vlp_sample(cpu, time, flags)) { + const struct vlp_target_range *target = + get_vlp_target_range(cpu); + intel_pstate_adjust_pstate_range(cpu, target->value); + } +} + static struct pstate_funcs core_funcs = { .get_max = core_get_max_pstate, .get_max_physical = core_get_max_pstate_physical, @@ -2389,6 +2459,9 @@ static int intel_pstate_init_cpu(unsigned int cpunum) intel_pstate_get_cpu_pstates(cpu); + if (pstate_funcs.update_util == intel_pstate_update_util_hwp_vlp) + intel_pstate_reset_vlp(cpu); + pr_debug("controlling: cpu %d\n", cpunum); return 0; @@ -2398,7 +2471,8 @@ static void intel_pstate_set_update_util_hook(unsigned int cpu_num) { struct cpudata *cpu = all_cpu_data[cpu_num]; - if (hwp_active && !hwp_boost) + if (hwp_active && !hwp_boost && + pstate_funcs.update_util != intel_pstate_update_util_hwp_vlp) return; if (cpu->update_util_set) @@ -2526,7 +2600,8 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy) * was turned off, in that case we need to clear the * update util hook. */ - if (!hwp_boost) + if (!hwp_boost && pstate_funcs.update_util != + intel_pstate_update_util_hwp_vlp) intel_pstate_clear_update_util_hook(policy->cpu); intel_pstate_hwp_set(policy->cpu); } -- 2.22.1 _______________________________________________ Intel-gfx mailing list Intel-gfx@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/intel-gfx
next prev parent reply other threads:[~2020-03-10 21:46 UTC|newest] Thread overview: 85+ messages / expand[flat|nested] mbox.gz Atom feed top 2020-03-10 21:41 [RFC] GPU-bound energy efficiency improvements for the intel_pstate driver (v2) Francisco Jerez 2020-03-10 21:41 ` [Intel-gfx] " Francisco Jerez 2020-03-10 21:41 ` [PATCH 01/10] PM: QoS: Add CPU_RESPONSE_FREQUENCY global PM QoS limit Francisco Jerez 2020-03-10 21:41 ` [Intel-gfx] " Francisco Jerez 2020-03-11 12:42 ` Peter Zijlstra 2020-03-11 12:42 ` [Intel-gfx] " Peter Zijlstra 2020-03-11 19:23 ` Francisco Jerez 2020-03-11 19:23 ` [Intel-gfx] " Francisco Jerez 2020-03-11 19:23 ` [PATCHv2 " Francisco Jerez 2020-03-11 19:23 ` [Intel-gfx] " Francisco Jerez 2020-03-19 10:25 ` Rafael J. Wysocki 2020-03-19 10:25 ` [Intel-gfx] " Rafael J. Wysocki 2020-03-10 21:41 ` [PATCH 02/10] drm/i915: Adjust PM QoS response frequency based on GPU load Francisco Jerez 2020-03-10 21:41 ` [Intel-gfx] " Francisco Jerez 2020-03-10 22:26 ` Chris Wilson 2020-03-10 22:26 ` Chris Wilson 2020-03-11 0:34 ` Francisco Jerez 2020-03-11 0:34 ` Francisco Jerez 2020-03-18 19:42 ` Francisco Jerez 2020-03-18 19:42 ` Francisco Jerez 2020-03-20 2:46 ` Francisco Jerez 2020-03-20 2:46 ` Francisco Jerez 2020-03-20 10:06 ` Chris Wilson 2020-03-20 10:06 ` Chris Wilson 2020-03-11 10:00 ` Tvrtko Ursulin 2020-03-11 10:00 ` Tvrtko Ursulin 2020-03-11 10:21 ` Chris Wilson 2020-03-11 10:21 ` Chris Wilson 2020-03-11 19:54 ` Francisco Jerez 2020-03-11 19:54 ` Francisco Jerez 2020-03-12 11:52 ` Tvrtko Ursulin 2020-03-12 11:52 ` Tvrtko Ursulin 2020-03-13 7:39 ` Francisco Jerez 2020-03-13 7:39 ` Francisco Jerez 2020-03-16 20:54 ` Francisco Jerez 2020-03-16 20:54 ` Francisco Jerez 2020-03-10 21:41 ` [PATCH 03/10] OPTIONAL: drm/i915: Expose PM QoS control parameters via debugfs Francisco Jerez 2020-03-10 21:41 ` [Intel-gfx] " Francisco Jerez 2020-03-10 21:41 ` [PATCH 04/10] Revert "cpufreq: intel_pstate: Drop ->update_util from pstate_funcs" Francisco Jerez 2020-03-10 21:41 ` [Intel-gfx] " Francisco Jerez 2020-03-19 10:45 ` Rafael J. Wysocki 2020-03-19 10:45 ` [Intel-gfx] " Rafael J. Wysocki 2020-03-10 21:41 ` [PATCH 05/10] cpufreq: intel_pstate: Implement VLP controller statistics and status calculation Francisco Jerez 2020-03-10 21:41 ` [Intel-gfx] " Francisco Jerez 2020-03-19 11:06 ` Rafael J. Wysocki 2020-03-19 11:06 ` [Intel-gfx] " Rafael J. Wysocki 2020-03-10 21:41 ` [PATCH 06/10] cpufreq: intel_pstate: Implement VLP controller target P-state range estimation Francisco Jerez 2020-03-10 21:41 ` [Intel-gfx] " Francisco Jerez 2020-03-19 11:12 ` Rafael J. Wysocki 2020-03-19 11:12 ` [Intel-gfx] " Rafael J. Wysocki 2020-03-10 21:42 ` Francisco Jerez [this message] 2020-03-10 21:42 ` [Intel-gfx] [PATCH 07/10] cpufreq: intel_pstate: Implement VLP controller for HWP parts Francisco Jerez 2020-03-17 23:59 ` Pandruvada, Srinivas 2020-03-17 23:59 ` [Intel-gfx] " Pandruvada, Srinivas 2020-03-18 19:51 ` Francisco Jerez 2020-03-18 19:51 ` [Intel-gfx] " Francisco Jerez 2020-03-18 20:10 ` Pandruvada, Srinivas 2020-03-18 20:10 ` [Intel-gfx] " Pandruvada, Srinivas 2020-03-18 20:22 ` Francisco Jerez 2020-03-18 20:22 ` [Intel-gfx] " Francisco Jerez 2020-03-23 20:13 ` Pandruvada, Srinivas 2020-03-23 20:13 ` [Intel-gfx] " Pandruvada, Srinivas 2020-03-10 21:42 ` [PATCH 08/10] cpufreq: intel_pstate: Enable VLP controller based on ACPI FADT profile and CPUID Francisco Jerez 2020-03-10 21:42 ` [Intel-gfx] " Francisco Jerez 2020-03-19 11:20 ` Rafael J. Wysocki 2020-03-19 11:20 ` [Intel-gfx] " Rafael J. Wysocki 2020-03-10 21:42 ` [PATCH 09/10] OPTIONAL: cpufreq: intel_pstate: Add tracing of VLP controller status Francisco Jerez 2020-03-10 21:42 ` [Intel-gfx] " Francisco Jerez 2020-03-10 21:42 ` [PATCH 10/10] OPTIONAL: cpufreq: intel_pstate: Expose VLP controller parameters via debugfs Francisco Jerez 2020-03-10 21:42 ` [Intel-gfx] " Francisco Jerez 2020-03-11 2:35 ` [RFC] GPU-bound energy efficiency improvements for the intel_pstate driver (v2) Pandruvada, Srinivas 2020-03-11 2:35 ` [Intel-gfx] " Pandruvada, Srinivas 2020-03-11 3:55 ` Francisco Jerez 2020-03-11 3:55 ` [Intel-gfx] " Francisco Jerez 2020-03-11 4:25 ` [Intel-gfx] ✗ Fi.CI.BUILD: failure for " Patchwork 2020-03-12 2:31 ` [Intel-gfx] ✗ Fi.CI.BUILD: failure for GPU-bound energy efficiency improvements for the intel_pstate driver (v2). (rev2) Patchwork 2020-03-12 2:32 ` Patchwork 2020-03-23 23:29 ` [RFC] GPU-bound energy efficiency improvements for the intel_pstate driver (v2) Pandruvada, Srinivas 2020-03-23 23:29 ` [Intel-gfx] " Pandruvada, Srinivas 2020-03-24 0:23 ` Francisco Jerez 2020-03-24 0:23 ` [Intel-gfx] " Francisco Jerez 2020-03-24 19:16 ` Francisco Jerez 2020-03-24 19:16 ` [Intel-gfx] " Francisco Jerez 2020-03-24 20:03 ` Pandruvada, Srinivas 2020-03-24 20:03 ` [Intel-gfx] " Pandruvada, Srinivas
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=20200310214203.26459-8-currojerez@riseup.net \ --to=currojerez@riseup.net \ --cc=intel-gfx@lists.freedesktop.org \ --cc=linux-pm@vger.kernel.org \ --cc=peterz@infradead.org \ --cc=rjw@rjwysocki.net \ --cc=rodrigo.vivi@intel.com \ --cc=srinivas.pandruvada@intel.com \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.