When a kthread or any other task has an affinity mask that is fully
offline or unallowed, the scheduler reaffines the task to all possible
CPUs as a last resort.
This default decision doesn't mix up very well with nohz_full CPUs that
are part of the possible cpumask but don't want to be disturbed by
unbound kthreads or even detached pinned user tasks.
Make the fallback affinity setting aware of nohz_full.
Suggested-by: Michal Hocko <mhocko@xxxxxxxx>
Signed-off-by: Frederic Weisbecker <frederic@xxxxxxxxxx>
---
arch/arm64/include/asm/cpufeature.h | 1 +
arch/arm64/include/asm/mmu_context.h | 2 ++
arch/arm64/kernel/cpufeature.c | 11 +++++++++++
include/linux/mmu_context.h | 1 +
kernel/sched/core.c | 2 +-
5 files changed, 16 insertions(+), 1 deletion(-)
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 8b4e5a3cd24c..cac5efc836c0 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -671,6 +671,7 @@ static inline bool supports_clearbhb(int scope)
}
const struct cpumask *system_32bit_el0_cpumask(void);
+const struct cpumask *fallback_32bit_el0_cpumask(void);
DECLARE_STATIC_KEY_FALSE(arm64_mismatched_32bit_el0);
static inline bool system_supports_32bit_el0(void)
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index 48b3d9553b67..7883abd6b29a 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -283,6 +283,8 @@ task_cpu_possible_mask(struct task_struct *p)
}
#define task_cpu_possible_mask task_cpu_possible_mask
+const struct cpumask *task_cpu_fallback_mask(struct task_struct *p);
+
void verify_cpu_asid_bits(void);
void post_ttbr_update_workaround(void);
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 7ce1b8ab417f..2b7aa32bf436 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -1642,6 +1642,17 @@ const struct cpumask *system_32bit_el0_cpumask(void)
return cpu_possible_mask;
}
+const struct cpumask *task_cpu_fallback_mask(struct task_struct *p)
+{
+ if (!static_branch_unlikely(&arm64_mismatched_32bit_el0))
+ return housekeeping_cpumask(HK_TYPE_TICK);
+
+ if (!is_compat_thread(task_thread_info(p)))
+ return housekeeping_cpumask(HK_TYPE_TICK);
+
+ return system_32bit_el0_cpumask();
+}
+
static int __init parse_32bit_el0_param(char *str)
{
allow_mismatched_32bit_el0 = true;
diff --git a/include/linux/mmu_context.h b/include/linux/mmu_context.h
index bbaec80c78c5..ac01dc4eb2ce 100644
--- a/include/linux/mmu_context.h
+++ b/include/linux/mmu_context.h
@@ -24,6 +24,7 @@ static inline void leave_mm(void) { }
#ifndef task_cpu_possible_mask
# define task_cpu_possible_mask(p) cpu_possible_mask
# define task_cpu_possible(cpu, p) true
+# define task_cpu_fallback_mask(p) housekeeping_cpumask(HK_TYPE_TICK)
#else
# define task_cpu_possible(cpu, p) cpumask_test_cpu((cpu), task_cpu_possible_mask(p))
#endif
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 95e40895a519..233b50b0e123 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3534,7 +3534,7 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
*
* More yuck to audit.
*/
- do_set_cpus_allowed(p, task_cpu_possible_mask(p));
+ do_set_cpus_allowed(p, task_cpu_fallback_mask(p));
state = fail;
break;
case fail:
--
2.46.0
