[PATCH AUTOSEL 6.6 1/6] perf/core: Fix narrow startup race when creating the perf nr_addr_filters sysfs file
From: Greg KH gregkh@linuxfoundation.org
[ Upstream commit 652ffc2104ec1f69dd4a46313888c33527145ccf ]
Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Link: https://lkml.kernel.org/r/2023061204-decal-flyable-6090@gregkh Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/events/core.c | 40 ++++++++++++++++++++++++++++------------ 1 file changed, 28 insertions(+), 12 deletions(-)
diff --git a/kernel/events/core.c b/kernel/events/core.c index 58ecb1c24387..f22c540350a1 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -11413,9 +11413,32 @@ static DEVICE_ATTR_RW(perf_event_mux_interval_ms); static struct attribute *pmu_dev_attrs[] = { &dev_attr_type.attr, &dev_attr_perf_event_mux_interval_ms.attr, + &dev_attr_nr_addr_filters.attr, + NULL, +}; + +static umode_t pmu_dev_is_visible(struct kobject *kobj, struct attribute *a, int n) +{ + struct device *dev = kobj_to_dev(kobj); + struct pmu *pmu = dev_get_drvdata(dev); + + if (!pmu->nr_addr_filters) + return 0; + + return a->mode; + + return 0; +} + +static struct attribute_group pmu_dev_attr_group = { + .is_visible = pmu_dev_is_visible, + .attrs = pmu_dev_attrs, +}; + +static const struct attribute_group *pmu_dev_groups[] = { + &pmu_dev_attr_group, NULL, }; -ATTRIBUTE_GROUPS(pmu_dev);
static int pmu_bus_running; static struct bus_type pmu_bus = { @@ -11452,18 +11475,11 @@ static int pmu_dev_alloc(struct pmu *pmu) if (ret) goto free_dev;
- /* For PMUs with address filters, throw in an extra attribute: */ - if (pmu->nr_addr_filters) - ret = device_create_file(pmu->dev, &dev_attr_nr_addr_filters); - - if (ret) - goto del_dev; - - if (pmu->attr_update) + if (pmu->attr_update) { ret = sysfs_update_groups(&pmu->dev->kobj, pmu->attr_update); - - if (ret) - goto del_dev; + if (ret) + goto del_dev; + }
out: return ret;
From: Andrzej Hajda andrzej.hajda@intel.com
[ Upstream commit 9bb6362652f3f4d74a87d572a91ee1b38e673ef6 ]
After release of the hashbucket lock the tracking object can be modified or freed by a concurrent thread. Using it in such a case is error prone, even for printing the object state:
1. T1 tries to deactivate destroyed object, debugobjects detects it, hash bucket lock is released.
2. T2 preempts T1 and frees the tracking object.
3. The freed tracking object is allocated and initialized for a different to be tracked kernel object.
4. T1 resumes and reports error for wrong kernel object.
Create a local copy of the tracking object before releasing the hash bucket lock and use the local copy for reporting and fixups to prevent this.
Signed-off-by: Andrzej Hajda andrzej.hajda@intel.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Link: https://lore.kernel.org/r/20231025-debugobjects_fix-v3-1-2bc3bf7084c2@intel.... Signed-off-by: Sasha Levin sashal@kernel.org --- lib/debugobjects.c | 200 ++++++++++++++++++--------------------------- 1 file changed, 78 insertions(+), 122 deletions(-)
diff --git a/lib/debugobjects.c b/lib/debugobjects.c index a517256a270b..c90834a209b5 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -620,9 +620,8 @@ static void debug_objects_fill_pool(void) static void __debug_object_init(void *addr, const struct debug_obj_descr *descr, int onstack) { - enum debug_obj_state state; + struct debug_obj *obj, o; struct debug_bucket *db; - struct debug_obj *obj; unsigned long flags;
debug_objects_fill_pool(); @@ -643,24 +642,18 @@ __debug_object_init(void *addr, const struct debug_obj_descr *descr, int onstack case ODEBUG_STATE_INIT: case ODEBUG_STATE_INACTIVE: obj->state = ODEBUG_STATE_INIT; - break; - - case ODEBUG_STATE_ACTIVE: - state = obj->state; - raw_spin_unlock_irqrestore(&db->lock, flags); - debug_print_object(obj, "init"); - debug_object_fixup(descr->fixup_init, addr, state); - return; - - case ODEBUG_STATE_DESTROYED: raw_spin_unlock_irqrestore(&db->lock, flags); - debug_print_object(obj, "init"); return; default: break; }
+ o = *obj; raw_spin_unlock_irqrestore(&db->lock, flags); + debug_print_object(&o, "init"); + + if (o.state == ODEBUG_STATE_ACTIVE) + debug_object_fixup(descr->fixup_init, addr, o.state); }
/** @@ -701,11 +694,9 @@ EXPORT_SYMBOL_GPL(debug_object_init_on_stack); int debug_object_activate(void *addr, const struct debug_obj_descr *descr) { struct debug_obj o = { .object = addr, .state = ODEBUG_STATE_NOTAVAILABLE, .descr = descr }; - enum debug_obj_state state; struct debug_bucket *db; struct debug_obj *obj; unsigned long flags; - int ret;
if (!debug_objects_enabled) return 0; @@ -717,49 +708,38 @@ int debug_object_activate(void *addr, const struct debug_obj_descr *descr) raw_spin_lock_irqsave(&db->lock, flags);
obj = lookup_object_or_alloc(addr, db, descr, false, true); - if (likely(!IS_ERR_OR_NULL(obj))) { - bool print_object = false; - + if (unlikely(!obj)) { + raw_spin_unlock_irqrestore(&db->lock, flags); + debug_objects_oom(); + return 0; + } else if (likely(!IS_ERR(obj))) { switch (obj->state) { - case ODEBUG_STATE_INIT: - case ODEBUG_STATE_INACTIVE: - obj->state = ODEBUG_STATE_ACTIVE; - ret = 0; - break; - case ODEBUG_STATE_ACTIVE: - state = obj->state; - raw_spin_unlock_irqrestore(&db->lock, flags); - debug_print_object(obj, "activate"); - ret = debug_object_fixup(descr->fixup_activate, addr, state); - return ret ? 0 : -EINVAL; - case ODEBUG_STATE_DESTROYED: - print_object = true; - ret = -EINVAL; + o = *obj; break; + case ODEBUG_STATE_INIT: + case ODEBUG_STATE_INACTIVE: + obj->state = ODEBUG_STATE_ACTIVE; + fallthrough; default: - ret = 0; - break; + raw_spin_unlock_irqrestore(&db->lock, flags); + return 0; } - raw_spin_unlock_irqrestore(&db->lock, flags); - if (print_object) - debug_print_object(obj, "activate"); - return ret; }
raw_spin_unlock_irqrestore(&db->lock, flags); + debug_print_object(&o, "activate");
- /* If NULL the allocation has hit OOM */ - if (!obj) { - debug_objects_oom(); - return 0; + switch (o.state) { + case ODEBUG_STATE_ACTIVE: + case ODEBUG_STATE_NOTAVAILABLE: + if (debug_object_fixup(descr->fixup_activate, addr, o.state)) + return 0; + fallthrough; + default: + return -EINVAL; } - - /* Object is neither static nor tracked. It's not initialized */ - debug_print_object(&o, "activate"); - ret = debug_object_fixup(descr->fixup_activate, addr, ODEBUG_STATE_NOTAVAILABLE); - return ret ? 0 : -EINVAL; } EXPORT_SYMBOL_GPL(debug_object_activate);
@@ -770,10 +750,10 @@ EXPORT_SYMBOL_GPL(debug_object_activate); */ void debug_object_deactivate(void *addr, const struct debug_obj_descr *descr) { + struct debug_obj o = { .object = addr, .state = ODEBUG_STATE_NOTAVAILABLE, .descr = descr }; struct debug_bucket *db; struct debug_obj *obj; unsigned long flags; - bool print_object = false;
if (!debug_objects_enabled) return; @@ -785,33 +765,24 @@ void debug_object_deactivate(void *addr, const struct debug_obj_descr *descr) obj = lookup_object(addr, db); if (obj) { switch (obj->state) { + case ODEBUG_STATE_DESTROYED: + break; case ODEBUG_STATE_INIT: case ODEBUG_STATE_INACTIVE: case ODEBUG_STATE_ACTIVE: - if (!obj->astate) - obj->state = ODEBUG_STATE_INACTIVE; - else - print_object = true; - break; - - case ODEBUG_STATE_DESTROYED: - print_object = true; - break; + if (obj->astate) + break; + obj->state = ODEBUG_STATE_INACTIVE; + fallthrough; default: - break; + raw_spin_unlock_irqrestore(&db->lock, flags); + return; } + o = *obj; }
raw_spin_unlock_irqrestore(&db->lock, flags); - if (!obj) { - struct debug_obj o = { .object = addr, - .state = ODEBUG_STATE_NOTAVAILABLE, - .descr = descr }; - - debug_print_object(&o, "deactivate"); - } else if (print_object) { - debug_print_object(obj, "deactivate"); - } + debug_print_object(&o, "deactivate"); } EXPORT_SYMBOL_GPL(debug_object_deactivate);
@@ -822,11 +793,9 @@ EXPORT_SYMBOL_GPL(debug_object_deactivate); */ void debug_object_destroy(void *addr, const struct debug_obj_descr *descr) { - enum debug_obj_state state; + struct debug_obj *obj, o; struct debug_bucket *db; - struct debug_obj *obj; unsigned long flags; - bool print_object = false;
if (!debug_objects_enabled) return; @@ -836,32 +805,31 @@ void debug_object_destroy(void *addr, const struct debug_obj_descr *descr) raw_spin_lock_irqsave(&db->lock, flags);
obj = lookup_object(addr, db); - if (!obj) - goto out_unlock; + if (!obj) { + raw_spin_unlock_irqrestore(&db->lock, flags); + return; + }
switch (obj->state) { + case ODEBUG_STATE_ACTIVE: + case ODEBUG_STATE_DESTROYED: + break; case ODEBUG_STATE_NONE: case ODEBUG_STATE_INIT: case ODEBUG_STATE_INACTIVE: obj->state = ODEBUG_STATE_DESTROYED; - break; - case ODEBUG_STATE_ACTIVE: - state = obj->state; + fallthrough; + default: raw_spin_unlock_irqrestore(&db->lock, flags); - debug_print_object(obj, "destroy"); - debug_object_fixup(descr->fixup_destroy, addr, state); return; - - case ODEBUG_STATE_DESTROYED: - print_object = true; - break; - default: - break; } -out_unlock: + + o = *obj; raw_spin_unlock_irqrestore(&db->lock, flags); - if (print_object) - debug_print_object(obj, "destroy"); + debug_print_object(&o, "destroy"); + + if (o.state == ODEBUG_STATE_ACTIVE) + debug_object_fixup(descr->fixup_destroy, addr, o.state); } EXPORT_SYMBOL_GPL(debug_object_destroy);
@@ -872,9 +840,8 @@ EXPORT_SYMBOL_GPL(debug_object_destroy); */ void debug_object_free(void *addr, const struct debug_obj_descr *descr) { - enum debug_obj_state state; + struct debug_obj *obj, o; struct debug_bucket *db; - struct debug_obj *obj; unsigned long flags;
if (!debug_objects_enabled) @@ -885,24 +852,26 @@ void debug_object_free(void *addr, const struct debug_obj_descr *descr) raw_spin_lock_irqsave(&db->lock, flags);
obj = lookup_object(addr, db); - if (!obj) - goto out_unlock; + if (!obj) { + raw_spin_unlock_irqrestore(&db->lock, flags); + return; + }
switch (obj->state) { case ODEBUG_STATE_ACTIVE: - state = obj->state; - raw_spin_unlock_irqrestore(&db->lock, flags); - debug_print_object(obj, "free"); - debug_object_fixup(descr->fixup_free, addr, state); - return; + break; default: hlist_del(&obj->node); raw_spin_unlock_irqrestore(&db->lock, flags); free_object(obj); return; } -out_unlock: + + o = *obj; raw_spin_unlock_irqrestore(&db->lock, flags); + debug_print_object(&o, "free"); + + debug_object_fixup(descr->fixup_free, addr, o.state); } EXPORT_SYMBOL_GPL(debug_object_free);
@@ -954,10 +923,10 @@ void debug_object_active_state(void *addr, const struct debug_obj_descr *descr, unsigned int expect, unsigned int next) { + struct debug_obj o = { .object = addr, .state = ODEBUG_STATE_NOTAVAILABLE, .descr = descr }; struct debug_bucket *db; struct debug_obj *obj; unsigned long flags; - bool print_object = false;
if (!debug_objects_enabled) return; @@ -970,28 +939,19 @@ debug_object_active_state(void *addr, const struct debug_obj_descr *descr, if (obj) { switch (obj->state) { case ODEBUG_STATE_ACTIVE: - if (obj->astate == expect) - obj->astate = next; - else - print_object = true; - break; - + if (obj->astate != expect) + break; + obj->astate = next; + raw_spin_unlock_irqrestore(&db->lock, flags); + return; default: - print_object = true; break; } + o = *obj; }
raw_spin_unlock_irqrestore(&db->lock, flags); - if (!obj) { - struct debug_obj o = { .object = addr, - .state = ODEBUG_STATE_NOTAVAILABLE, - .descr = descr }; - - debug_print_object(&o, "active_state"); - } else if (print_object) { - debug_print_object(obj, "active_state"); - } + debug_print_object(&o, "active_state"); } EXPORT_SYMBOL_GPL(debug_object_active_state);
@@ -999,12 +959,10 @@ EXPORT_SYMBOL_GPL(debug_object_active_state); static void __debug_check_no_obj_freed(const void *address, unsigned long size) { unsigned long flags, oaddr, saddr, eaddr, paddr, chunks; - const struct debug_obj_descr *descr; - enum debug_obj_state state; + int cnt, objs_checked = 0; + struct debug_obj *obj, o; struct debug_bucket *db; struct hlist_node *tmp; - struct debug_obj *obj; - int cnt, objs_checked = 0;
saddr = (unsigned long) address; eaddr = saddr + size; @@ -1026,12 +984,10 @@ static void __debug_check_no_obj_freed(const void *address, unsigned long size)
switch (obj->state) { case ODEBUG_STATE_ACTIVE: - descr = obj->descr; - state = obj->state; + o = *obj; raw_spin_unlock_irqrestore(&db->lock, flags); - debug_print_object(obj, "free"); - debug_object_fixup(descr->fixup_free, - (void *) oaddr, state); + debug_print_object(&o, "free"); + debug_object_fixup(o.descr->fixup_free, (void *)oaddr, o.state); goto repeat; default: hlist_del(&obj->node);
From: Vincent Guittot vincent.guittot@linaro.org
[ Upstream commit 9942cb22ea458c34fa17b73d143ea32d4df1caca ]
Create a new method to get a unique and fixed max frequency. Currently cpuinfo.max_freq or the highest (or last) state of performance domain are used as the max frequency when computing the frequency for a level of utilization, but:
- cpuinfo_max_freq can change at runtime. boost is one example of such change.
- cpuinfo.max_freq and last item of the PD can be different leading to different results between cpufreq and energy model.
We need to save the reference frequency that has been used when computing the CPUs capacity and use this fixed and coherent value to convert between frequency and CPU's capacity.
In fact, we already save the frequency that has been used when computing the capacity of each CPU. We extend the precision to save kHz instead of MHz currently and we modify the type to be aligned with other variables used when converting frequency to capacity and the other way.
[ mingo: Minor edits. ]
Signed-off-by: Vincent Guittot vincent.guittot@linaro.org Signed-off-by: Ingo Molnar mingo@kernel.org Tested-by: Lukasz Luba lukasz.luba@arm.com Reviewed-by: Lukasz Luba lukasz.luba@arm.com Acked-by: Sudeep Holla sudeep.holla@arm.com Link: https://lore.kernel.org/r/20231211104855.558096-2-vincent.guittot@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/include/asm/topology.h | 1 + arch/arm64/include/asm/topology.h | 1 + arch/riscv/include/asm/topology.h | 1 + drivers/base/arch_topology.c | 29 ++++++++++++++--------------- include/linux/arch_topology.h | 7 +++++++ include/linux/sched/topology.h | 8 ++++++++ 6 files changed, 32 insertions(+), 15 deletions(-)
diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h index c7d2510e5a78..853c4f81ba4a 100644 --- a/arch/arm/include/asm/topology.h +++ b/arch/arm/include/asm/topology.h @@ -13,6 +13,7 @@ #define arch_set_freq_scale topology_set_freq_scale #define arch_scale_freq_capacity topology_get_freq_scale #define arch_scale_freq_invariant topology_scale_freq_invariant +#define arch_scale_freq_ref topology_get_freq_ref #endif
/* Replace task scheduler's default cpu-invariant accounting */ diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h index 9fab663dd2de..a323b109b9c4 100644 --- a/arch/arm64/include/asm/topology.h +++ b/arch/arm64/include/asm/topology.h @@ -23,6 +23,7 @@ void update_freq_counters_refs(void); #define arch_set_freq_scale topology_set_freq_scale #define arch_scale_freq_capacity topology_get_freq_scale #define arch_scale_freq_invariant topology_scale_freq_invariant +#define arch_scale_freq_ref topology_get_freq_ref
#ifdef CONFIG_ACPI_CPPC_LIB #define arch_init_invariance_cppc topology_init_cpu_capacity_cppc diff --git a/arch/riscv/include/asm/topology.h b/arch/riscv/include/asm/topology.h index e316ab3b77f3..61183688bdd5 100644 --- a/arch/riscv/include/asm/topology.h +++ b/arch/riscv/include/asm/topology.h @@ -9,6 +9,7 @@ #define arch_set_freq_scale topology_set_freq_scale #define arch_scale_freq_capacity topology_get_freq_scale #define arch_scale_freq_invariant topology_scale_freq_invariant +#define arch_scale_freq_ref topology_get_freq_ref
/* Replace task scheduler's default cpu-invariant accounting */ #define arch_scale_cpu_capacity topology_get_cpu_scale diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index b741b5ba82bd..0c9ae5b157b1 100644 --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -19,6 +19,7 @@ #include <linux/init.h> #include <linux/rcupdate.h> #include <linux/sched.h> +#include <linux/units.h>
#define CREATE_TRACE_POINTS #include <trace/events/thermal_pressure.h> @@ -26,7 +27,8 @@ static DEFINE_PER_CPU(struct scale_freq_data __rcu *, sft_data); static struct cpumask scale_freq_counters_mask; static bool scale_freq_invariant; -static DEFINE_PER_CPU(u32, freq_factor) = 1; +DEFINE_PER_CPU(unsigned long, capacity_freq_ref) = 1; +EXPORT_PER_CPU_SYMBOL_GPL(capacity_freq_ref);
static bool supports_scale_freq_counters(const struct cpumask *cpus) { @@ -170,9 +172,9 @@ DEFINE_PER_CPU(unsigned long, thermal_pressure); * operating on stale data when hot-plug is used for some CPUs. The * @capped_freq reflects the currently allowed max CPUs frequency due to * thermal capping. It might be also a boost frequency value, which is bigger - * than the internal 'freq_factor' max frequency. In such case the pressure - * value should simply be removed, since this is an indication that there is - * no thermal throttling. The @capped_freq must be provided in kHz. + * than the internal 'capacity_freq_ref' max frequency. In such case the + * pressure value should simply be removed, since this is an indication that + * there is no thermal throttling. The @capped_freq must be provided in kHz. */ void topology_update_thermal_pressure(const struct cpumask *cpus, unsigned long capped_freq) @@ -183,10 +185,7 @@ void topology_update_thermal_pressure(const struct cpumask *cpus,
cpu = cpumask_first(cpus); max_capacity = arch_scale_cpu_capacity(cpu); - max_freq = per_cpu(freq_factor, cpu); - - /* Convert to MHz scale which is used in 'freq_factor' */ - capped_freq /= 1000; + max_freq = arch_scale_freq_ref(cpu);
/* * Handle properly the boost frequencies, which should simply clean @@ -279,13 +278,13 @@ void topology_normalize_cpu_scale(void)
capacity_scale = 1; for_each_possible_cpu(cpu) { - capacity = raw_capacity[cpu] * per_cpu(freq_factor, cpu); + capacity = raw_capacity[cpu] * per_cpu(capacity_freq_ref, cpu); capacity_scale = max(capacity, capacity_scale); }
pr_debug("cpu_capacity: capacity_scale=%llu\n", capacity_scale); for_each_possible_cpu(cpu) { - capacity = raw_capacity[cpu] * per_cpu(freq_factor, cpu); + capacity = raw_capacity[cpu] * per_cpu(capacity_freq_ref, cpu); capacity = div64_u64(capacity << SCHED_CAPACITY_SHIFT, capacity_scale); topology_set_cpu_scale(cpu, capacity); @@ -321,15 +320,15 @@ bool __init topology_parse_cpu_capacity(struct device_node *cpu_node, int cpu) cpu_node, raw_capacity[cpu]);
/* - * Update freq_factor for calculating early boot cpu capacities. + * Update capacity_freq_ref for calculating early boot CPU capacities. * For non-clk CPU DVFS mechanism, there's no way to get the * frequency value now, assuming they are running at the same - * frequency (by keeping the initial freq_factor value). + * frequency (by keeping the initial capacity_freq_ref value). */ cpu_clk = of_clk_get(cpu_node, 0); if (!PTR_ERR_OR_ZERO(cpu_clk)) { - per_cpu(freq_factor, cpu) = - clk_get_rate(cpu_clk) / 1000; + per_cpu(capacity_freq_ref, cpu) = + clk_get_rate(cpu_clk) / HZ_PER_KHZ; clk_put(cpu_clk); } } else { @@ -411,7 +410,7 @@ init_cpu_capacity_callback(struct notifier_block *nb, cpumask_andnot(cpus_to_visit, cpus_to_visit, policy->related_cpus);
for_each_cpu(cpu, policy->related_cpus) - per_cpu(freq_factor, cpu) = policy->cpuinfo.max_freq / 1000; + per_cpu(capacity_freq_ref, cpu) = policy->cpuinfo.max_freq;
if (cpumask_empty(cpus_to_visit)) { topology_normalize_cpu_scale(); diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h index a07b510e7dc5..32c24ff4f2a8 100644 --- a/include/linux/arch_topology.h +++ b/include/linux/arch_topology.h @@ -27,6 +27,13 @@ static inline unsigned long topology_get_cpu_scale(int cpu)
void topology_set_cpu_scale(unsigned int cpu, unsigned long capacity);
+DECLARE_PER_CPU(unsigned long, capacity_freq_ref); + +static inline unsigned long topology_get_freq_ref(int cpu) +{ + return per_cpu(capacity_freq_ref, cpu); +} + DECLARE_PER_CPU(unsigned long, arch_freq_scale);
static inline unsigned long topology_get_freq_scale(int cpu) diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 67b573d5bf28..9671b7234684 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -275,6 +275,14 @@ void arch_update_thermal_pressure(const struct cpumask *cpus, { } #endif
+#ifndef arch_scale_freq_ref +static __always_inline +unsigned int arch_scale_freq_ref(int cpu) +{ + return 0; +} +#endif + static inline int task_node(const struct task_struct *p) { return cpu_to_node(task_cpu(p));
From: Vincent Guittot vincent.guittot@linaro.org
[ Upstream commit 599457ba15403037b489fe536266a3d5f9efaed7 ]
cpuinfo.max_freq can change at runtime because of boost as an example. This implies that the value could be different from the frequency that has been used to compute the capacity of a CPU.
The new arch_scale_freq_ref() returns a fixed and coherent frequency that can be used to compute the capacity for a given frequency.
[ Also fix a arch_set_freq_scale() newline style wart in <linux/cpufreq.h>. ]
Signed-off-by: Vincent Guittot vincent.guittot@linaro.org Signed-off-by: Ingo Molnar mingo@kernel.org Tested-by: Lukasz Luba lukasz.luba@arm.com Reviewed-by: Lukasz Luba lukasz.luba@arm.com Acked-by: Viresh Kumar viresh.kumar@linaro.org Acked-by: Rafael J. Wysocki rafael@kernel.org Link: https://lore.kernel.org/r/20231211104855.558096-3-vincent.guittot@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/cpufreq/cpufreq.c | 4 ++-- include/linux/cpufreq.h | 1 + 2 files changed, 3 insertions(+), 2 deletions(-)
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 60ed89000e82..8c4f9c2f9c44 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -454,7 +454,7 @@ void cpufreq_freq_transition_end(struct cpufreq_policy *policy,
arch_set_freq_scale(policy->related_cpus, policy->cur, - policy->cpuinfo.max_freq); + arch_scale_freq_ref(policy->cpu));
spin_lock(&policy->transition_lock); policy->transition_ongoing = false; @@ -2174,7 +2174,7 @@ unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy,
policy->cur = freq; arch_set_freq_scale(policy->related_cpus, freq, - policy->cpuinfo.max_freq); + arch_scale_freq_ref(policy->cpu)); cpufreq_stats_record_transition(policy, freq);
if (trace_cpu_frequency_enabled()) { diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 71d186d6933a..738dcddf3cfe 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -1211,6 +1211,7 @@ void arch_set_freq_scale(const struct cpumask *cpus, { } #endif + /* the following are really really optional */ extern struct freq_attr cpufreq_freq_attr_scaling_available_freqs; extern struct freq_attr cpufreq_freq_attr_scaling_boost_freqs;
From: Vincent Guittot vincent.guittot@linaro.org
[ Upstream commit b3edde44e5d4504c23a176819865cd603fd16d6c ]
cpuinfo.max_freq can change at runtime because of boost as an example. This implies that the value could be different than the one that has been used when computing the capacity of a CPU.
The new arch_scale_freq_ref() returns a fixed and coherent reference frequency that can be used when computing a frequency based on utilization.
Use this arch_scale_freq_ref() when available and fallback to policy otherwise.
Signed-off-by: Vincent Guittot vincent.guittot@linaro.org Signed-off-by: Ingo Molnar mingo@kernel.org Tested-by: Lukasz Luba lukasz.luba@arm.com Reviewed-by: Lukasz Luba lukasz.luba@arm.com Reviewed-by: Dietmar Eggemann dietmar.eggemann@arm.com Acked-by: Rafael J. Wysocki rafael@kernel.org Acked-by: Viresh Kumar viresh.kumar@linaro.org Link: https://lore.kernel.org/r/20231211104855.558096-4-vincent.guittot@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/sched/cpufreq_schedutil.c | 26 ++++++++++++++++++++++++-- 1 file changed, 24 insertions(+), 2 deletions(-)
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 458d359f5991..7f6c9874a200 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -114,6 +114,28 @@ static void sugov_deferred_update(struct sugov_policy *sg_policy) } }
+/** + * get_capacity_ref_freq - get the reference frequency that has been used to + * correlate frequency and compute capacity for a given cpufreq policy. We use + * the CPU managing it for the arch_scale_freq_ref() call in the function. + * @policy: the cpufreq policy of the CPU in question. + * + * Return: the reference CPU frequency to compute a capacity. + */ +static __always_inline +unsigned long get_capacity_ref_freq(struct cpufreq_policy *policy) +{ + unsigned int freq = arch_scale_freq_ref(policy->cpu); + + if (freq) + return freq; + + if (arch_scale_freq_invariant()) + return policy->cpuinfo.max_freq; + + return policy->cur; +} + /** * get_next_freq - Compute a new frequency for a given cpufreq policy. * @sg_policy: schedutil policy object to compute the new frequency for. @@ -140,9 +162,9 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy, unsigned long util, unsigned long max) { struct cpufreq_policy *policy = sg_policy->policy; - unsigned int freq = arch_scale_freq_invariant() ? - policy->cpuinfo.max_freq : policy->cur; + unsigned int freq;
+ freq = get_capacity_ref_freq(policy); util = map_util_perf(util); freq = map_util_freq(util, freq, max);
From: Vincent Guittot vincent.guittot@linaro.org
[ Upstream commit 15cbbd1d317e07b4e5c6aca5d4c5579539a82784 ]
The last item of a performance domain is not always the performance point that has been used to compute CPU's capacity. This can lead to different target frequency compared with other part of the system like schedutil and would result in wrong energy estimation.
A new arch_scale_freq_ref() is available to return a fixed and coherent frequency reference that can be used when computing the CPU's frequency for an level of utilization. Use this function to get this reference frequency.
Energy model is never used without defining arch_scale_freq_ref() but can be compiled. Define a default arch_scale_freq_ref() returning 0 in such case.
Signed-off-by: Vincent Guittot vincent.guittot@linaro.org Signed-off-by: Ingo Molnar mingo@kernel.org Tested-by: Lukasz Luba lukasz.luba@arm.com Reviewed-by: Lukasz Luba lukasz.luba@arm.com Link: https://lore.kernel.org/r/20231211104855.558096-5-vincent.guittot@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/energy_model.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index b9caa01dfac4..c19e7effe764 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -224,7 +224,7 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd, unsigned long max_util, unsigned long sum_util, unsigned long allowed_cpu_cap) { - unsigned long freq, scale_cpu; + unsigned long freq, ref_freq, scale_cpu; struct em_perf_state *ps; int cpu;
@@ -241,11 +241,11 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd, */ cpu = cpumask_first(to_cpumask(pd->cpus)); scale_cpu = arch_scale_cpu_capacity(cpu); - ps = &pd->table[pd->nr_perf_states - 1]; + ref_freq = arch_scale_freq_ref(cpu);
max_util = map_util_perf(max_util); max_util = min(max_util, allowed_cpu_cap); - freq = map_util_freq(max_util, ps->frequency, scale_cpu); + freq = map_util_freq(max_util, ref_freq, scale_cpu);
/* * Find the lowest performance state of the Energy Model above the
linux-stable-mirror@lists.linaro.org
-
Sasha Levin