From: Peter Zijlstra peterz@infradead.org
[ Upstream commit a23314e9d88d89d49e69db08f60b7caa470f04e1 ]
Vincent Wang reported that get_next_freq() has a mult overflow bug on 32-bit platforms in the IOWAIT boost case, since in that case {util,max} are in freq units instead of capacity units.
Solve this by moving the IOWAIT boost to capacity units. And since this means @max is constant; simplify the code.
Reported-by: Vincent Wang vincent.wang@unisoc.com Tested-by: Vincent Wang vincent.wang@unisoc.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Acked-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Cc: Andy Lutomirski luto@kernel.org Cc: Borislav Petkov bp@alien8.de Cc: Chunyan Zhang zhang.lyra@gmail.com Cc: Dave Hansen dave.hansen@linux.intel.com Cc: H. Peter Anvin hpa@zytor.com Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Peter Zijlstra peterz@infradead.org Cc: Quentin Perret quentin.perret@arm.com Cc: Rafael J. Wysocki rjw@rjwysocki.net Cc: Rik van Riel riel@surriel.com Cc: Thomas Gleixner tglx@linutronix.de Link: https://lkml.kernel.org/r/20190305083202.GU32494@hirez.programming.kicks-ass... Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/sched/cpufreq_schedutil.c | 59 ++++++++++++++------------------ 1 file changed, 25 insertions(+), 34 deletions(-)
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 3fffad3bc8a8..217f81ecae17 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -50,10 +50,10 @@ struct sugov_cpu {
bool iowait_boost_pending; unsigned int iowait_boost; - unsigned int iowait_boost_max; u64 last_update;
unsigned long bw_dl; + unsigned long min; unsigned long max;
/* The field below is for single-CPU policies only: */ @@ -283,8 +283,7 @@ static bool sugov_iowait_reset(struct sugov_cpu *sg_cpu, u64 time, if (delta_ns <= TICK_NSEC) return false;
- sg_cpu->iowait_boost = set_iowait_boost - ? sg_cpu->sg_policy->policy->min : 0; + sg_cpu->iowait_boost = set_iowait_boost ? sg_cpu->min : 0; sg_cpu->iowait_boost_pending = set_iowait_boost;
return true; @@ -324,14 +323,13 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, u64 time,
/* Double the boost at each request */ if (sg_cpu->iowait_boost) { - sg_cpu->iowait_boost <<= 1; - if (sg_cpu->iowait_boost > sg_cpu->iowait_boost_max) - sg_cpu->iowait_boost = sg_cpu->iowait_boost_max; + sg_cpu->iowait_boost = + min_t(unsigned int, sg_cpu->iowait_boost << 1, SCHED_CAPACITY_SCALE); return; }
/* First wakeup after IO: start with minimum boost */ - sg_cpu->iowait_boost = sg_cpu->sg_policy->policy->min; + sg_cpu->iowait_boost = sg_cpu->min; }
/** @@ -353,47 +351,38 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, u64 time, * This mechanism is designed to boost high frequently IO waiting tasks, while * being more conservative on tasks which does sporadic IO operations. */ -static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time, - unsigned long *util, unsigned long *max) +static unsigned long sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time, + unsigned long util, unsigned long max) { - unsigned int boost_util, boost_max; + unsigned long boost;
/* No boost currently required */ if (!sg_cpu->iowait_boost) - return; + return util;
/* Reset boost if the CPU appears to have been idle enough */ if (sugov_iowait_reset(sg_cpu, time, false)) - return; + return util;
- /* - * An IO waiting task has just woken up: - * allow to further double the boost value - */ - if (sg_cpu->iowait_boost_pending) { - sg_cpu->iowait_boost_pending = false; - } else { + if (!sg_cpu->iowait_boost_pending) { /* - * Otherwise: reduce the boost value and disable it when we - * reach the minimum. + * No boost pending; reduce the boost value. */ sg_cpu->iowait_boost >>= 1; - if (sg_cpu->iowait_boost < sg_cpu->sg_policy->policy->min) { + if (sg_cpu->iowait_boost < sg_cpu->min) { sg_cpu->iowait_boost = 0; - return; + return util; } }
+ sg_cpu->iowait_boost_pending = false; + /* - * Apply the current boost value: a CPU is boosted only if its current - * utilization is smaller then the current IO boost level. + * @util is already in capacity scale; convert iowait_boost + * into the same scale so we can compare. */ - boost_util = sg_cpu->iowait_boost; - boost_max = sg_cpu->iowait_boost_max; - if (*util * boost_max < *max * boost_util) { - *util = boost_util; - *max = boost_max; - } + boost = (sg_cpu->iowait_boost * max) >> SCHED_CAPACITY_SHIFT; + return max(boost, util); }
#ifdef CONFIG_NO_HZ_COMMON @@ -440,7 +429,7 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
util = sugov_get_util(sg_cpu); max = sg_cpu->max; - sugov_iowait_apply(sg_cpu, time, &util, &max); + util = sugov_iowait_apply(sg_cpu, time, util, max); next_f = get_next_freq(sg_policy, util, max); /* * Do not reduce the frequency if the CPU has not been idle @@ -480,7 +469,7 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time)
j_util = sugov_get_util(j_sg_cpu); j_max = j_sg_cpu->max; - sugov_iowait_apply(j_sg_cpu, time, &j_util, &j_max); + j_util = sugov_iowait_apply(j_sg_cpu, time, j_util, j_max);
if (j_util * max > j_max * util) { util = j_util; @@ -817,7 +806,9 @@ static int sugov_start(struct cpufreq_policy *policy) memset(sg_cpu, 0, sizeof(*sg_cpu)); sg_cpu->cpu = cpu; sg_cpu->sg_policy = sg_policy; - sg_cpu->iowait_boost_max = policy->cpuinfo.max_freq; + sg_cpu->min = + (SCHED_CAPACITY_SCALE * policy->cpuinfo.min_freq) / + policy->cpuinfo.max_freq; }
for_each_cpu(cpu, policy->cpus) {