Merge tag 'smp-core-2026-08-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull SMP core updates from Thomas Gleixner:

 - Reduce the preemption disabled sections in smp_call_function*().

   The various smp call functions keep preemption disabled accross the
   full operation which includes the wait for completion. Especially the
   latter can take some time when one of the target CPUs is not
   immediately responding to the IPI, which can result in large latency
   spikes.

   To improve this provide a per task CPU mask to track the CPUs to wait
   for. That makes the information required for the wait task local and
   therefore allows to reenable preemption before the wait.

   While this comes with moderate extra memory cost this reduces SMP
   function call induced latency measured in a fleet for high priority
   tasks from ~17ms to ~1.5ms (~90%).

 - Reduce the overhead of the CSD debug code by replacing the heavy
   memory barriers with smp_store_release()/acquire()

 - Remove obsolute unused hotplug states

* tag 'smp-core-2026-08-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  scftorture: Remove preempt_disable() in scftorture_invoke_one()
  smp: Remove preempt_disable() from on_each_cpu_cond_mask()
  smp: Remove preempt_disable() from smp_call_function()
  smp: Enable preemption early in smp_call_function_many_cond()
  smp: Alloc percpu csd data in smpcfd_prepare_cpu() only once
  smp: Use task-local IPI cpumask in smp_call_function_many_cond()
  smp: Refactor remote CPU selection in smp_call_function_any()
  smp: Enable preemption early in smp_call_function_single()
  smp: Disable preemption explicitly in __csd_lock_wait()
  cpu/hotplug: Remove CPUHP_AP_ARM_CORESIGHT_CTI_STARTING
  smp: Use release stores for csd_lock_record() state

1 files changed, 4 insertions, 9 deletions

diff --git a/kernel/scftorture.c b/kernel/scftorture.c
index 327c315f411c..2082f9b44370 100644
--- a/kernel/scftorture.c
+++ b/kernel/scftorture.c
@@ -348,6 +348,8 @@ static void scftorture_invoke_one(struct scf_statistics *scfp, struct torture_ra
 	int ret = 0;
 	struct scf_check *scfcp = NULL;
 	struct scf_selector *scfsp = scf_sel_rand(trsp);
+	bool is_single = (scfsp->scfs_prim == SCF_PRIM_SINGLE ||
+			  scfsp->scfs_prim == SCF_PRIM_SINGLE_RPC);
 
 	if (scfsp->scfs_prim == SCF_PRIM_SINGLE || scfsp->scfs_wait) {
 		scfcp = kmalloc_obj(*scfcp, GFP_ATOMIC);
@@ -364,8 +366,6 @@ static void scftorture_invoke_one(struct scf_statistics *scfp, struct torture_ra
 	}
 	if (use_cpus_read_lock)
 		cpus_read_lock();
-	else
-		preempt_disable();
 	switch (scfsp->scfs_prim) {
 	case SCF_PRIM_RESCHED:
 		if (IS_BUILTIN(CONFIG_SCF_TORTURE_TEST)) {
@@ -411,13 +411,10 @@ static void scftorture_invoke_one(struct scf_statistics *scfp, struct torture_ra
 		if (!ret) {
 			if (use_cpus_read_lock)
 				cpus_read_unlock();
-			else
-				preempt_enable();
+
 			wait_for_completion(&scfcp->scfc_completion);
 			if (use_cpus_read_lock)
 				cpus_read_lock();
-			else
-				preempt_disable();
 		} else {
 			scfp->n_single_rpc_ofl++;
 			scf_add_to_free_list(scfcp);
@@ -452,7 +449,7 @@ static void scftorture_invoke_one(struct scf_statistics *scfp, struct torture_ra
 			scfcp->scfc_out = true;
 	}
 	if (scfcp && scfsp->scfs_wait) {
-		if (WARN_ON_ONCE((num_online_cpus() > 1 || scfsp->scfs_prim == SCF_PRIM_SINGLE) &&
+		if (WARN_ON_ONCE(((use_cpus_read_lock && num_online_cpus() > 1) || is_single) &&
 				 !scfcp->scfc_out)) {
 			pr_warn("%s: Memory-ordering failure, scfs_prim: %d.\n", __func__, scfsp->scfs_prim);
 			atomic_inc(&n_mb_out_errs); // Leak rather than trash!
@@ -463,8 +460,6 @@ static void scftorture_invoke_one(struct scf_statistics *scfp, struct torture_ra
 	}
 	if (use_cpus_read_lock)
 		cpus_read_unlock();
-	else
-		preempt_enable();
 	if (allocfail)
 		schedule_timeout_idle((1 + longwait) * HZ);  // Let no-wait handlers complete.
 	else if (!(torture_random(trsp) & 0xfff))