From: "Peter Zijlstra (Intel)" <[email protected]>
The static key arch_scale_freq_key only needs to be enabled once (at
boot). This change fixes a bug by which the key was enabled every time cpu0
is started, even as a secondary CPU during cpu hotplug. Secondary CPUs are
started from the idle thread: setting a static key from there means
acquiring a lock and may result in sleeping in the idle task, causing CPU
lockup.
Another consequence of this change is that init_counter_refs() is now
called on each CPU correctly; previously the function on_each_cpu() was
used, but it was called at boot when the only online cpu is cpu0.
[[email protected]: Tested and wrote changelog]
Reported-by: Chris Wilson <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Signed-off-by: Giovanni Gherdovich <[email protected]>
Fixes: 1567c3e3467c ("x86, sched: Add support for frequency invariance")
---
arch/x86/kernel/smpboot.c | 21 ++++++++++++++-------
1 file changed, 14 insertions(+), 7 deletions(-)
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 5d346b70844b..dd8e15f648bc 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) {
@@ -2005,7 +2005,7 @@ static bool intel_set_max_freq_ratio(void)
return true;
}
-static void init_counter_refs(void *arg)
+static void init_counter_refs(void)
{
u64 aperf, mperf;
@@ -2016,18 +2016,25 @@ 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");
--
2.16.4
The following commit has been merged into the sched/urgent branch of tip:
Commit-ID: b56e7d45e80796ca963ac10902245b244d823caf
Gitweb: https://git.kernel.org/tip/b56e7d45e80796ca963ac10902245b244d823caf
Author: Peter Zijlstra (Intel) <[email protected]>
AuthorDate: Thu, 16 Apr 2020 07:47:44 +02:00
Committer: Peter Zijlstra <[email protected]>
CommitterDate: Wed, 22 Apr 2020 23:10:13 +02:00
x86, sched: Don't enable static key when starting secondary CPUs
The static key arch_scale_freq_key only needs to be enabled once (at
boot). This change fixes a bug by which the key was enabled every time cpu0
is started, even as a secondary CPU during cpu hotplug. Secondary CPUs are
started from the idle thread: setting a static key from there means
acquiring a lock and may result in sleeping in the idle task, causing CPU
lockup.
Another consequence of this change is that init_counter_refs() is now
called on each CPU correctly; previously the function on_each_cpu() was
used, but it was called at boot when the only online cpu is cpu0.
[[email protected]: Tested and wrote changelog]
Fixes: 1567c3e3467c ("x86, sched: Add support for frequency invariance")
Reported-by: Chris Wilson <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Signed-off-by: Giovanni Gherdovich <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Acked-by: Rafael J. Wysocki <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
---
arch/x86/kernel/smpboot.c | 21 ++++++++++++++-------
1 file changed, 14 insertions(+), 7 deletions(-)
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 5d346b7..dd8e15f 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) {
@@ -2005,7 +2005,7 @@ out:
return true;
}
-static void init_counter_refs(void *arg)
+static void init_counter_refs(void)
{
u64 aperf, mperf;
@@ -2016,18 +2016,25 @@ 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");