From fd604ae6c261c5a56bb977ae99f875bbd7264a3f Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Thu, 2 Jan 2025 08:12:04 -0600 Subject: [PATCH 1/2] cpufreq/amd-pstate: Fix prefcore rankings commit 50a062a76200 ("cpufreq/amd-pstate: Store the boost numerator as highest perf again") updated the value stored for highest perf to no longer store the highest perf value but instead the boost numerator. This is a fixed value for systems with preferred cores and not appropriate for use ITMT rankings. Update the value used for ITMT rankings to be the preferred core ranking. Reported-and-tested-by: Sebastian Closes: https://bugzilla.kernel.org/show_bug.cgi?id=219640 Fixes: 50a062a76200 ("cpufreq/amd-pstate: Store the boost numerator as highest perf again") Reviewed-by: Dhananjay Ugwekar Link: https://lore.kernel.org/r/20250102141204.3413202-1-superm1@kernel.org Signed-off-by: Mario Limonciello --- drivers/cpufreq/amd-pstate.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index d7b1de97727a1..2330903a8b457 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -815,7 +815,7 @@ static void amd_pstate_init_prefcore(struct amd_cpudata *cpudata) * sched_set_itmt_support(true) has been called and it is valid to * update them at any time after it has been called. */ - sched_set_itmt_core_prio((int)READ_ONCE(cpudata->highest_perf), cpudata->cpu); + sched_set_itmt_core_prio((int)READ_ONCE(cpudata->prefcore_ranking), cpudata->cpu); schedule_work(&sched_prefcore_work); } From 857a61c2ce74e30fc3b10bc89d68ddd8d05b188c Mon Sep 17 00:00:00 2001 From: Naresh Solanki Date: Fri, 20 Dec 2024 01:48:32 +0530 Subject: [PATCH 2/2] cpufreq/amd-pstate: Refactor max frequency calculation The previous approach introduced roundoff errors during division when calculating the boost ratio. This, in turn, affected the maximum frequency calculation, often resulting in reporting lower frequency values. For example, on the Glinda SoC based board with the following parameters: max_perf = 208 nominal_perf = 100 nominal_freq = 2600 MHz The Linux kernel previously calculated the frequency as: freq = ((max_perf * 1024 / nominal_perf) * nominal_freq) / 1024 freq = 5405 MHz // Integer arithmetic. With the updated formula: freq = (max_perf * nominal_freq) / nominal_perf freq = 5408 MHz This change ensures more accurate frequency calculations by eliminating unnecessary shifts and divisions, thereby improving precision. Signed-off-by: Naresh Solanki [ML: trim the changelog from commit message] Reviewed-by: Mario Limonciello Link: https://lore.kernel.org/r/20241219201833.2750998-1-naresh.solanki@9elements.com Signed-off-by: Mario Limonciello --- drivers/cpufreq/amd-pstate.c | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index 2330903a8b457..dd9b8d6993d69 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -908,9 +908,8 @@ static int amd_pstate_init_freq(struct amd_cpudata *cpudata) { int ret; u32 min_freq, max_freq; - u32 nominal_perf, nominal_freq; + u32 highest_perf, nominal_perf, nominal_freq; u32 lowest_nonlinear_perf, lowest_nonlinear_freq; - u32 boost_ratio, lowest_nonlinear_ratio; struct cppc_perf_caps cppc_perf; ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf); @@ -927,16 +926,12 @@ static int amd_pstate_init_freq(struct amd_cpudata *cpudata) else nominal_freq = cppc_perf.nominal_freq; + highest_perf = READ_ONCE(cpudata->highest_perf); nominal_perf = READ_ONCE(cpudata->nominal_perf); - - boost_ratio = div_u64(cpudata->highest_perf << SCHED_CAPACITY_SHIFT, nominal_perf); - max_freq = (nominal_freq * boost_ratio >> SCHED_CAPACITY_SHIFT); + max_freq = div_u64((u64)highest_perf * nominal_freq, nominal_perf); lowest_nonlinear_perf = READ_ONCE(cpudata->lowest_nonlinear_perf); - lowest_nonlinear_ratio = div_u64(lowest_nonlinear_perf << SCHED_CAPACITY_SHIFT, - nominal_perf); - lowest_nonlinear_freq = (nominal_freq * lowest_nonlinear_ratio >> SCHED_CAPACITY_SHIFT); - + lowest_nonlinear_freq = div_u64((u64)nominal_freq * lowest_nonlinear_perf, nominal_perf); WRITE_ONCE(cpudata->min_freq, min_freq * 1000); WRITE_ONCE(cpudata->lowest_nonlinear_freq, lowest_nonlinear_freq * 1000); WRITE_ONCE(cpudata->nominal_freq, nominal_freq * 1000);