From: Tejun Heo <tj@kernel.org>
Date: Fri, 8 Nov 2024 20:40:44 +0000 (-1000)
Subject: Merge branch 'for-6.12-fixes' into for-6.13
X-Git-Tag: v6.13-rc1~164^2~9
X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=f07b806ad8ebcca0a25738b78557736ef9674797;p=thirdparty%2Fkernel%2Flinux.git

Merge branch 'for-6.12-fixes' into for-6.13

Pull sched_ext/for-6.12-fixes to receive 0e7ffff1b811 ("scx: Fix raciness in
scx_ops_bypass()"). Planned updates for scx_ops_bypass() depends on it.

Signed-off-by: Tejun Heo <tj@kernel.org>
---

f07b806ad8ebcca0a25738b78557736ef9674797
diff --cc kernel/sched/ext.c
index 012a7fc772630,3bdb08fc2056a..c074a64c20f03
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@@ -3274,70 -3087,21 +3302,65 @@@ static s32 scx_select_cpu_dfl(struct ta
  
  	*found = false;
  
- 	if (!static_branch_likely(&scx_builtin_idle_enabled)) {
- 		scx_ops_error("built-in idle tracking is disabled");
- 		return prev_cpu;
- 	}
- 
  	/*
 -	 * If WAKE_SYNC, the waker's local DSQ is empty, and the system is
 -	 * under utilized, wake up @p to the local DSQ of the waker. Checking
 -	 * only for an empty local DSQ is insufficient as it could give the
 -	 * wakee an unfair advantage when the system is oversaturated.
 -	 * Checking only for the presence of idle CPUs is also insufficient as
 -	 * the local DSQ of the waker could have tasks piled up on it even if
 -	 * there is an idle core elsewhere on the system.
 -	 */
 -	cpu = smp_processor_id();
 -	if ((wake_flags & SCX_WAKE_SYNC) &&
 -	    !cpumask_empty(idle_masks.cpu) && !(current->flags & PF_EXITING) &&
 -	    cpu_rq(cpu)->scx.local_dsq.nr == 0) {
 -		if (cpumask_test_cpu(cpu, p->cpus_ptr))
 +	 * Determine the scheduling domain only if the task is allowed to run
 +	 * on all CPUs.
 +	 *
 +	 * This is done primarily for efficiency, as it avoids the overhead of
 +	 * updating a cpumask every time we need to select an idle CPU (which
 +	 * can be costly in large SMP systems), but it also aligns logically:
 +	 * if a task's scheduling domain is restricted by user-space (through
 +	 * CPU affinity), the task will simply use the flat scheduling domain
 +	 * defined by user-space.
 +	 */
 +	if (p->nr_cpus_allowed >= num_possible_cpus()) {
 +		if (static_branch_maybe(CONFIG_NUMA, &scx_selcpu_topo_numa))
 +			numa_cpus = cpumask_of_node(cpu_to_node(prev_cpu));
 +
 +		if (static_branch_maybe(CONFIG_SCHED_MC, &scx_selcpu_topo_llc)) {
 +			struct sched_domain *sd;
 +
 +			sd = rcu_dereference(per_cpu(sd_llc, prev_cpu));
 +			if (sd)
 +				llc_cpus = sched_domain_span(sd);
 +		}
 +	}
 +
 +	/*
 +	 * If WAKE_SYNC, try to migrate the wakee to the waker's CPU.
 +	 */
 +	if (wake_flags & SCX_WAKE_SYNC) {
 +		cpu = smp_processor_id();
 +
 +		/*
 +		 * If the waker's CPU is cache affine and prev_cpu is idle,
 +		 * then avoid a migration.
 +		 */
 +		if (cpus_share_cache(cpu, prev_cpu) &&
 +		    test_and_clear_cpu_idle(prev_cpu)) {
 +			cpu = prev_cpu;
  			goto cpu_found;
 +		}
 +
 +		/*
 +		 * If the waker's local DSQ is empty, and the system is under
 +		 * utilized, try to wake up @p to the local DSQ of the waker.
 +		 *
 +		 * Checking only for an empty local DSQ is insufficient as it
 +		 * could give the wakee an unfair advantage when the system is
 +		 * oversaturated.
 +		 *
 +		 * Checking only for the presence of idle CPUs is also
 +		 * insufficient as the local DSQ of the waker could have tasks
 +		 * piled up on it even if there is an idle core elsewhere on
 +		 * the system.
 +		 */
 +		if (!cpumask_empty(idle_masks.cpu) &&
 +		    !(current->flags & PF_EXITING) &&
 +		    cpu_rq(cpu)->scx.local_dsq.nr == 0) {
 +			if (cpumask_test_cpu(cpu, p->cpus_ptr))
 +				goto cpu_found;
 +		}
  	}
  
  	/*