diff options
Diffstat (limited to 'kernel')
| -rw-r--r-- | kernel/bpf/verifier.c | 5 | ||||
| -rw-r--r-- | kernel/extable.c | 2 | ||||
| -rw-r--r-- | kernel/sched/core.c | 22 | ||||
| -rw-r--r-- | kernel/sched/cpufreq_schedutil.c | 154 | ||||
| -rw-r--r-- | kernel/sched/walt.c | 8 | ||||
| -rw-r--r-- | kernel/sysctl.c | 3 | ||||
| -rw-r--r-- | kernel/time/tick-sched.c | 12 | ||||
| -rw-r--r-- | kernel/trace/trace_kprobe.c | 21 |
8 files changed, 142 insertions, 85 deletions
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 85de5094b936..c97bce6a0e0e 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -765,6 +765,11 @@ static int check_xadd(struct verifier_env *env, struct bpf_insn *insn) if (err) return err; + if (is_pointer_value(env, insn->src_reg)) { + verbose("R%d leaks addr into mem\n", insn->src_reg); + return -EACCES; + } + /* check whether atomic_add can read the memory */ err = check_mem_access(env, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_READ, -1); diff --git a/kernel/extable.c b/kernel/extable.c index e820ccee9846..4f06fc34313f 100644 --- a/kernel/extable.c +++ b/kernel/extable.c @@ -66,7 +66,7 @@ static inline int init_kernel_text(unsigned long addr) return 0; } -int core_kernel_text(unsigned long addr) +int notrace core_kernel_text(unsigned long addr) { if (addr >= (unsigned long)_stext && addr < (unsigned long)_etext) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 0071785e698b..18f4fb65cd1d 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6924,6 +6924,9 @@ enum s_alloc { * Build an iteration mask that can exclude certain CPUs from the upwards * domain traversal. * + * Only CPUs that can arrive at this group should be considered to continue + * balancing. + * * Asymmetric node setups can result in situations where the domain tree is of * unequal depth, make sure to skip domains that already cover the entire * range. @@ -6935,18 +6938,31 @@ enum s_alloc { */ static void build_group_mask(struct sched_domain *sd, struct sched_group *sg) { - const struct cpumask *span = sched_domain_span(sd); + const struct cpumask *sg_span = sched_group_cpus(sg); struct sd_data *sdd = sd->private; struct sched_domain *sibling; int i; - for_each_cpu(i, span) { + for_each_cpu(i, sg_span) { sibling = *per_cpu_ptr(sdd->sd, i); - if (!cpumask_test_cpu(i, sched_domain_span(sibling))) + + /* + * Can happen in the asymmetric case, where these siblings are + * unused. The mask will not be empty because those CPUs that + * do have the top domain _should_ span the domain. + */ + if (!sibling->child) + continue; + + /* If we would not end up here, we can't continue from here */ + if (!cpumask_equal(sg_span, sched_domain_span(sibling->child))) continue; cpumask_set_cpu(i, sched_group_mask(sg)); } + + /* We must not have empty masks here */ + WARN_ON_ONCE(cpumask_empty(sched_group_mask(sg))); } /* diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 75bfbb336722..e12309c1b07b 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -47,6 +47,7 @@ struct sugov_policy { s64 up_rate_delay_ns; s64 down_rate_delay_ns; unsigned int next_freq; + unsigned int cached_raw_freq; /* The next fields are only needed if fast switch cannot be used. */ struct irq_work irq_work; @@ -63,7 +64,6 @@ struct sugov_cpu { struct update_util_data update_util; struct sugov_policy *sg_policy; - unsigned int cached_raw_freq; unsigned long iowait_boost; unsigned long iowait_boost_max; u64 last_update; @@ -72,6 +72,11 @@ struct sugov_cpu { unsigned long util; unsigned long max; unsigned int flags; + + /* The field below is for single-CPU policies only. */ +#ifdef CONFIG_NO_HZ_COMMON + unsigned long saved_idle_calls; +#endif }; static DEFINE_PER_CPU(struct sugov_cpu, sugov_cpu); @@ -127,22 +132,20 @@ static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time, if (sugov_up_down_rate_limit(sg_policy, time, next_freq)) return; + if (sg_policy->next_freq == next_freq) + return; + + sg_policy->next_freq = next_freq; + sg_policy->last_freq_update_time = time; + if (policy->fast_switch_enabled) { - if (sg_policy->next_freq == next_freq) { - trace_cpu_frequency(policy->cur, smp_processor_id()); - return; - } - sg_policy->next_freq = next_freq; - sg_policy->last_freq_update_time = time; next_freq = cpufreq_driver_fast_switch(policy, next_freq); if (next_freq == CPUFREQ_ENTRY_INVALID) return; policy->cur = next_freq; trace_cpu_frequency(next_freq, smp_processor_id()); - } else if (sg_policy->next_freq != next_freq) { - sg_policy->next_freq = next_freq; - sg_policy->last_freq_update_time = time; + } else { sg_policy->work_in_progress = true; irq_work_queue(&sg_policy->irq_work); } @@ -150,7 +153,7 @@ static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time, /** * get_next_freq - Compute a new frequency for a given cpufreq policy. - * @sg_cpu: schedutil cpu object to compute the new frequency for. + * @sg_policy: schedutil policy object to compute the new frequency for. * @util: Current CPU utilization. * @max: CPU capacity. * @@ -170,19 +173,18 @@ static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time, * next_freq (as calculated above) is returned, subject to policy min/max and * cpufreq driver limitations. */ -static unsigned int get_next_freq(struct sugov_cpu *sg_cpu, unsigned long util, - unsigned long max) +static unsigned int get_next_freq(struct sugov_policy *sg_policy, + unsigned long util, unsigned long max) { - struct sugov_policy *sg_policy = sg_cpu->sg_policy; struct cpufreq_policy *policy = sg_policy->policy; unsigned int freq = arch_scale_freq_invariant() ? policy->cpuinfo.max_freq : policy->cur; freq = (freq + (freq >> 2)) * util / max; - if (freq == sg_cpu->cached_raw_freq && sg_policy->next_freq != UINT_MAX) + if (freq == sg_policy->cached_raw_freq && sg_policy->next_freq != UINT_MAX) return sg_policy->next_freq; - sg_cpu->cached_raw_freq = freq; + sg_policy->cached_raw_freq = freq; return cpufreq_driver_resolve_freq(policy, freq); } @@ -248,6 +250,19 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, unsigned long *util, sg_cpu->iowait_boost >>= 1; } +#ifdef CONFIG_NO_HZ_COMMON +static bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) +{ + unsigned long idle_calls = tick_nohz_get_idle_calls(); + bool ret = idle_calls == sg_cpu->saved_idle_calls; + + sg_cpu->saved_idle_calls = idle_calls; + return ret; +} +#else +static inline bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { return false; } +#endif /* CONFIG_NO_HZ_COMMON */ + static void sugov_update_single(struct update_util_data *hook, u64 time, unsigned int flags) { @@ -256,6 +271,7 @@ static void sugov_update_single(struct update_util_data *hook, u64 time, struct cpufreq_policy *policy = sg_policy->policy; unsigned long util, max; unsigned int next_f; + bool busy; sugov_set_iowait_boost(sg_cpu, time, flags); sg_cpu->last_update = time; @@ -263,40 +279,37 @@ static void sugov_update_single(struct update_util_data *hook, u64 time, if (!sugov_should_update_freq(sg_policy, time)) return; + busy = sugov_cpu_is_busy(sg_cpu); + if (flags & SCHED_CPUFREQ_DL) { next_f = policy->cpuinfo.max_freq; } else { sugov_get_util(&util, &max, time); sugov_iowait_boost(sg_cpu, &util, &max); - next_f = get_next_freq(sg_cpu, util, max); + next_f = get_next_freq(sg_policy, util, max); + /* + * Do not reduce the frequency if the CPU has not been idle + * recently, as the reduction is likely to be premature then. + */ + if (busy && next_f < sg_policy->next_freq) + next_f = sg_policy->next_freq; } sugov_update_commit(sg_policy, time, next_f); } -static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, - unsigned long util, unsigned long max, - unsigned int flags) +static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu) { struct sugov_policy *sg_policy = sg_cpu->sg_policy; struct cpufreq_policy *policy = sg_policy->policy; - unsigned int max_f = policy->cpuinfo.max_freq; u64 last_freq_update_time = sg_policy->last_freq_update_time; + unsigned long util = 0, max = 1; unsigned int j; - if (flags & SCHED_CPUFREQ_DL) - return max_f; - - sugov_iowait_boost(sg_cpu, &util, &max); - for_each_cpu(j, policy->cpus) { - struct sugov_cpu *j_sg_cpu; + struct sugov_cpu *j_sg_cpu = &per_cpu(sugov_cpu, j); unsigned long j_util, j_max; s64 delta_ns; - if (j == smp_processor_id()) - continue; - - j_sg_cpu = &per_cpu(sugov_cpu, j); /* * If the CPU utilization was last updated before the previous * frequency update and the time elapsed between the last update @@ -310,7 +323,7 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, continue; } if (j_sg_cpu->flags & SCHED_CPUFREQ_DL) - return max_f; + return policy->cpuinfo.max_freq; j_util = j_sg_cpu->util; j_max = j_sg_cpu->max; @@ -322,7 +335,7 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, sugov_iowait_boost(j_sg_cpu, &util, &max); } - return get_next_freq(sg_cpu, util, max); + return get_next_freq(sg_policy, util, max); } static void sugov_update_shared(struct update_util_data *hook, u64 time, @@ -345,7 +358,11 @@ static void sugov_update_shared(struct update_util_data *hook, u64 time, sg_cpu->last_update = time; if (sugov_should_update_freq(sg_policy, time)) { - next_f = sugov_next_freq_shared(sg_cpu, util, max, flags); + if (flags & SCHED_CPUFREQ_DL) + next_f = sg_policy->policy->cpuinfo.max_freq; + else + next_f = sugov_next_freq_shared(sg_cpu); + sugov_update_commit(sg_policy, time, next_f); } @@ -371,15 +388,15 @@ static void sugov_irq_work(struct irq_work *irq_work) sg_policy = container_of(irq_work, struct sugov_policy, irq_work); /* - * For Real Time and Deadline tasks, schedutil governor shoots the - * frequency to maximum. And special care must be taken to ensure that - * this kthread doesn't result in that. + * For RT and deadline tasks, the schedutil governor shoots the + * frequency to maximum. Special care must be taken to ensure that this + * kthread doesn't result in the same behavior. * * This is (mostly) guaranteed by the work_in_progress flag. The flag is - * updated only at the end of the sugov_work() and before that schedutil - * rejects all other frequency scaling requests. + * updated only at the end of the sugov_work() function and before that + * the schedutil governor rejects all other frequency scaling requests. * - * Though there is a very rare case where the RT thread yields right + * There is a very rare case though, where the RT thread yields right * after the work_in_progress flag is cleared. The effects of that are * neglected for now. */ @@ -489,15 +506,12 @@ static struct sugov_policy *sugov_policy_alloc(struct cpufreq_policy *policy) return NULL; sg_policy->policy = policy; - init_irq_work(&sg_policy->irq_work, sugov_irq_work); - mutex_init(&sg_policy->work_lock); raw_spin_lock_init(&sg_policy->update_lock); return sg_policy; } static void sugov_policy_free(struct sugov_policy *sg_policy) { - mutex_destroy(&sg_policy->work_lock); kfree(sg_policy); } @@ -531,6 +545,9 @@ static int sugov_kthread_create(struct sugov_policy *sg_policy) sg_policy->thread = thread; kthread_bind_mask(thread, policy->related_cpus); + init_irq_work(&sg_policy->irq_work, sugov_irq_work); + mutex_init(&sg_policy->work_lock); + wake_up_process(thread); return 0; @@ -544,6 +561,7 @@ static void sugov_kthread_stop(struct sugov_policy *sg_policy) flush_kthread_worker(&sg_policy->worker); kthread_stop(sg_policy->thread); + mutex_destroy(&sg_policy->work_lock); } static struct sugov_tunables *sugov_tunables_alloc(struct sugov_policy *sg_policy) @@ -578,9 +596,13 @@ static int sugov_init(struct cpufreq_policy *policy) if (policy->governor_data) return -EBUSY; + cpufreq_enable_fast_switch(policy); + sg_policy = sugov_policy_alloc(policy); - if (!sg_policy) - return -ENOMEM; + if (!sg_policy) { + ret = -ENOMEM; + goto disable_fast_switch; + } ret = sugov_kthread_create(sg_policy); if (ret) @@ -623,13 +645,11 @@ static int sugov_init(struct cpufreq_policy *policy) if (ret) goto fail; - out: +out: mutex_unlock(&global_tunables_lock); - - cpufreq_enable_fast_switch(policy); return 0; - fail: +fail: policy->governor_data = NULL; sugov_tunables_free(tunables); @@ -640,6 +660,10 @@ free_sg_policy: mutex_unlock(&global_tunables_lock); sugov_policy_free(sg_policy); + +disable_fast_switch: + cpufreq_disable_fast_switch(policy); + pr_err("initialization failed (error %d)\n", ret); return ret; } @@ -650,8 +674,6 @@ static int sugov_exit(struct cpufreq_policy *policy) struct sugov_tunables *tunables = sg_policy->tunables; unsigned int count; - cpufreq_disable_fast_switch(policy); - mutex_lock(&global_tunables_lock); count = gov_attr_set_put(&tunables->attr_set, &sg_policy->tunables_hook); @@ -664,6 +686,7 @@ static int sugov_exit(struct cpufreq_policy *policy) sugov_kthread_stop(sg_policy); sugov_policy_free(sg_policy); + cpufreq_disable_fast_switch(policy); return 0; } @@ -681,25 +704,19 @@ static int sugov_start(struct cpufreq_policy *policy) sg_policy->next_freq = UINT_MAX; sg_policy->work_in_progress = false; sg_policy->need_freq_update = false; + sg_policy->cached_raw_freq = 0; for_each_cpu(cpu, policy->cpus) { struct sugov_cpu *sg_cpu = &per_cpu(sugov_cpu, cpu); + memset(sg_cpu, 0, sizeof(*sg_cpu)); sg_cpu->sg_policy = sg_policy; - if (policy_is_shared(policy)) { - sg_cpu->util = 0; - sg_cpu->max = 0; - sg_cpu->flags = SCHED_CPUFREQ_DL; - sg_cpu->last_update = 0; - sg_cpu->cached_raw_freq = 0; - sg_cpu->iowait_boost = 0; - sg_cpu->iowait_boost_max = policy->cpuinfo.max_freq; - cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util, - sugov_update_shared); - } else { - cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util, - sugov_update_single); - } + sg_cpu->flags = SCHED_CPUFREQ_DL; + sg_cpu->iowait_boost_max = policy->cpuinfo.max_freq; + cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util, + policy_is_shared(policy) ? + sugov_update_shared : + sugov_update_single); } return 0; } @@ -714,9 +731,10 @@ static int sugov_stop(struct cpufreq_policy *policy) synchronize_sched(); - irq_work_sync(&sg_policy->irq_work); - kthread_cancel_work_sync(&sg_policy->work); - + if (!policy->fast_switch_enabled) { + irq_work_sync(&sg_policy->irq_work); + kthread_cancel_work_sync(&sg_policy->work); + } return 0; } diff --git a/kernel/sched/walt.c b/kernel/sched/walt.c index 6e053bd9830c..92c3aae8e056 100644 --- a/kernel/sched/walt.c +++ b/kernel/sched/walt.c @@ -72,7 +72,15 @@ static cpumask_t mpc_mask = CPU_MASK_ALL; __read_mostly unsigned int walt_ravg_window = 20000000; /* Min window size (in ns) = 10ms */ +#ifdef CONFIG_HZ_300 +/* + * Tick interval becomes to 3333333 due to + * rounding error when HZ=300. + */ +#define MIN_SCHED_RAVG_WINDOW (3333333 * 6) +#else #define MIN_SCHED_RAVG_WINDOW 10000000 +#endif /* Max window size (in ns) = 1s */ #define MAX_SCHED_RAVG_WINDOW 1000000000 diff --git a/kernel/sysctl.c b/kernel/sysctl.c index f27d2ba78d14..8576e6385d63 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2380,9 +2380,12 @@ static int do_proc_douintvec_conv(bool *negp, unsigned long *lvalp, if (write) { if (*negp) return -EINVAL; + if (*lvalp > UINT_MAX) + return -EINVAL; *valp = *lvalp; } else { unsigned int val = *valp; + *negp = false; *lvalp = (unsigned long)val; } return 0; diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index ec2102104cb8..333f627a3a3b 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -896,6 +896,18 @@ ktime_t tick_nohz_get_sleep_length(void) return ts->sleep_length; } +/** + * tick_nohz_get_idle_calls - return the current idle calls counter value + * + * Called from the schedutil frequency scaling governor in scheduler context. + */ +unsigned long tick_nohz_get_idle_calls(void) +{ + struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); + + return ts->idle_calls; +} + static void tick_nohz_account_idle_ticks(struct tick_sched *ts) { #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 12ea4ea619ee..e9092a0247bf 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -659,30 +659,25 @@ static int create_trace_kprobe(int argc, char **argv) pr_info("Probe point is not specified.\n"); return -EINVAL; } - if (isdigit(argv[1][0])) { - if (is_return) { - pr_info("Return probe point must be a symbol.\n"); - return -EINVAL; - } - /* an address specified */ - ret = kstrtoul(&argv[1][0], 0, (unsigned long *)&addr); - if (ret) { - pr_info("Failed to parse address.\n"); - return ret; - } - } else { + + /* try to parse an address. if that fails, try to read the + * input as a symbol. */ + if (kstrtoul(argv[1], 0, (unsigned long *)&addr)) { /* a symbol specified */ symbol = argv[1]; /* TODO: support .init module functions */ ret = traceprobe_split_symbol_offset(symbol, &offset); if (ret) { - pr_info("Failed to parse symbol.\n"); + pr_info("Failed to parse either an address or a symbol.\n"); return ret; } if (offset && is_return) { pr_info("Return probe must be used without offset.\n"); return -EINVAL; } + } else if (is_return) { + pr_info("Return probe point must be a symbol.\n"); + return -EINVAL; } argc -= 2; argv += 2; |