summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2020-04-25 12:11:47 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2020-04-25 12:11:47 -0700
commit05db498ad94431315c73efe623eab7a7d2d961c6 (patch)
treec28ba9874d2bd9ddec664668c0feb5b20793fbab
parente18588005d79853c2d4101f9416e7c1e8c9584d2 (diff)
parenteaf5a92ebde5bca3bb2565616115bd6d579486cd (diff)
Merge tag 'sched-urgent-2020-04-25' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler fixes from Ingo Molnar: "Misc fixes: - an uclamp accounting fix - three frequency invariance fixes and a readability improvement" * tag 'sched-urgent-2020-04-25' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: sched/core: Fix reset-on-fork from RT with uclamp x86, sched: Move check for CPU type to caller function x86, sched: Don't enable static key when starting secondary CPUs x86, sched: Account for CPUs with less than 4 cores in freq. invariance x86, sched: Bail out of frequency invariance if base frequency is unknown
-rw-r--r--arch/x86/kernel/smpboot.c47
-rw-r--r--kernel/sched/core.c9
2 files changed, 35 insertions, 21 deletions
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index fe3ab9632f3b..8c89e4d9ad28 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -147,7 +147,7 @@ static inline void smpboot_restore_warm_reset_vector(void)
*((volatile u32 *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = 0;
}
-static void init_freq_invariance(void);
+static void init_freq_invariance(bool secondary);
/*
* Report back to the Boot Processor during boot time or to the caller processor
@@ -185,7 +185,7 @@ static void smp_callin(void)
*/
set_cpu_sibling_map(raw_smp_processor_id());
- init_freq_invariance();
+ init_freq_invariance(true);
/*
* Get our bogomips.
@@ -1341,7 +1341,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
set_sched_topology(x86_topology);
set_cpu_sibling_map(0);
- init_freq_invariance();
+ init_freq_invariance(false);
smp_sanity_check();
switch (apic_intr_mode) {
@@ -1877,9 +1877,6 @@ static bool knl_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq,
int err, i;
u64 msr;
- if (!x86_match_cpu(has_knl_turbo_ratio_limits))
- return false;
-
err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq);
if (err)
return false;
@@ -1945,18 +1942,23 @@ static bool skx_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, int size)
static bool core_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
{
+ u64 msr;
int err;
err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq);
if (err)
return false;
- err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, turbo_freq);
+ err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &msr);
if (err)
return false;
- *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */
- *turbo_freq = (*turbo_freq >> 24) & 0xFF; /* 4C turbo */
+ *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */
+ *turbo_freq = (msr >> 24) & 0xFF; /* 4C turbo */
+
+ /* The CPU may have less than 4 cores */
+ if (!*turbo_freq)
+ *turbo_freq = msr & 0xFF; /* 1C turbo */
return true;
}
@@ -1972,7 +1974,8 @@ static bool intel_set_max_freq_ratio(void)
skx_set_max_freq_ratio(&base_freq, &turbo_freq, 1))
goto out;
- if (knl_set_max_freq_ratio(&base_freq, &turbo_freq, 1))
+ if (x86_match_cpu(has_knl_turbo_ratio_limits) &&
+ knl_set_max_freq_ratio(&base_freq, &turbo_freq, 1))
goto out;
if (x86_match_cpu(has_skx_turbo_ratio_limits) &&
@@ -1985,13 +1988,22 @@ static bool intel_set_max_freq_ratio(void)
return false;
out:
+ /*
+ * Some hypervisors advertise X86_FEATURE_APERFMPERF
+ * but then fill all MSR's with zeroes.
+ */
+ if (!base_freq) {
+ pr_debug("Couldn't determine cpu base frequency, necessary for scale-invariant accounting.\n");
+ return false;
+ }
+
arch_turbo_freq_ratio = div_u64(turbo_freq * SCHED_CAPACITY_SCALE,
base_freq);
arch_set_max_freq_ratio(turbo_disabled());
return true;
}
-static void init_counter_refs(void *arg)
+static void init_counter_refs(void)
{
u64 aperf, mperf;
@@ -2002,18 +2014,25 @@ static void init_counter_refs(void *arg)
this_cpu_write(arch_prev_mperf, mperf);
}
-static void init_freq_invariance(void)
+static void init_freq_invariance(bool secondary)
{
bool ret = false;
- if (smp_processor_id() != 0 || !boot_cpu_has(X86_FEATURE_APERFMPERF))
+ if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
return;
+ if (secondary) {
+ if (static_branch_likely(&arch_scale_freq_key)) {
+ init_counter_refs();
+ }
+ return;
+ }
+
if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
ret = intel_set_max_freq_ratio();
if (ret) {
- on_each_cpu(init_counter_refs, NULL, 1);
+ init_counter_refs();
static_branch_enable(&arch_scale_freq_key);
} else {
pr_debug("Couldn't determine max cpu frequency, necessary for scale-invariant accounting.\n");
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 3a61a3b8eaa9..9a2fbf98fd6f 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1232,13 +1232,8 @@ static void uclamp_fork(struct task_struct *p)
return;
for_each_clamp_id(clamp_id) {
- unsigned int clamp_value = uclamp_none(clamp_id);
-
- /* By default, RT tasks always get 100% boost */
- if (unlikely(rt_task(p) && clamp_id == UCLAMP_MIN))
- clamp_value = uclamp_none(UCLAMP_MAX);
-
- uclamp_se_set(&p->uclamp_req[clamp_id], clamp_value, false);
+ uclamp_se_set(&p->uclamp_req[clamp_id],
+ uclamp_none(clamp_id), false);
}
}