The following commit has been merged into the smp/core branch of tip:

Commit-ID:     9a560af15fd31b3b93235b1584a2509445a17963
Gitweb:        https://git.kernel.org/tip/9a560af15fd31b3b93235b1584a2509445a17963
Author:        Chuyi Zhou <zhouchuyi@bytedance.com>
AuthorDate:    Thu, 09 Jul 2026 20:29:23 +08:00
Committer:     Thomas Gleixner <tglx@kernel.org>
CommitterDate: Thu, 16 Jul 2026 09:24:55 +02:00

smp: Use task-local IPI cpumask in smp_call_function_many_cond()

smp_call_function_many_cond() uses the per-CPU cfd->cpumask as the list
of remote CPUs to wait for. That is safe while the caller remains pinned
to the current CPU for the whole operation, because another task cannot
run on the same CPU and reuse the per-CPU mask.

The synchronous wait is the long-latency part of the operation. To make
that wait preemptible, the mask iterated by csd_lock_wait() must remain
stable even if the task is preempted or migrates. If the wait used the
per-CPU cfd->cpumask after dropping CPU pinning, another task scheduled
on the original CPU could enter smp_call_function_many_cond() and
overwrite the mask while the first task is still iterating it.

Give each task private IPI cpumask storage and use it as the wait mask in
smp_call_function_many_cond(). Other cpumask storage choices do not fit
this use case:

 - Per-CPU storage is the state that becomes unsafe once the wait is
   made preemptible. After the caller drops CPU pinning, another task
   scheduled on the original CPU can enter smp_call_function_many_cond()
   and reuse the same per-CPU mask.

 - Stack storage is not suitable for large NR_CPUS or
   CONFIG_CPUMASK_OFFSTACK=y configurations. The wait mask needs to
   scale with cpumask_size(), and putting that storage on the stack is
   not acceptable on large systems.

 - Allocating the mask inside smp_call_function_many_cond() would put an
   allocation and a failure path in the generic IPI path. A sleeping
   allocation is not suitable because callers have historically only
   provided a preempt-disabled context, not a sleepable one. GFP_ATOMIC
   would avoid sleeping, but a failure fallback would make the latency
   improvement opportunistic instead of guaranteed.

The users are not limited to a small, pre-identifiable class of tasks. On
x86, ordinary tasks can reach this path through TLB flushes during exit,
unmap and reclaim, so allocating the mask only for a known subset of
tasks is not straightforward.

The memory cost is explicit: one word is added to task_struct. When
cpumask_size() fits in that word, the mask is stored inline and no
separate allocation is needed. Larger systems allocate cpumask_size() per
task; on x86-64 NR_CPUS=8192 this is 1 KiB per task. For context,
x86 already carries several KiB of per-task architecture and FPU state,
depending on the enabled features and configuration. That does not make
the extra cpumask free, but it puts the large-NR_CPUS case in
perspective.

Signed-off-by: Chuyi Zhou <zhouchuyi@bytedance.com>
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Tested-by: Paul E. McKenney <paulmck@kernel.org>
Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Link: https://patch.msgid.link/20260709122933.4021501-5-zhouchuyi@bytedance.com
---
 include/linux/sched.h | 12 +++++++-
 include/linux/smp.h   | 12 +++++++-
 kernel/fork.c         |  9 ++++-
 kernel/smp.c          | 71 +++++++++++++++++++++++++++++++++++++-----
 4 files changed, 95 insertions(+), 9 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 373bcc0..5738c54 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -823,6 +823,17 @@ struct kmap_ctrl {
 #endif
 };
 
+#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPTION)
+struct task_ipi_mask {
+	union {
+		cpumask_t		*ipi_mask_ptr;
+		unsigned long		ipi_mask_val;
+	};
+};
+#else
+struct task_ipi_mask { };
+#endif
+
 struct task_struct {
 #ifdef CONFIG_THREAD_INFO_IN_TASK
 	/*
@@ -1359,6 +1370,7 @@ struct task_struct {
 	struct list_head		perf_event_list;
 	struct perf_ctx_data __rcu	*perf_ctx_data;
 #endif
+	struct task_ipi_mask		__private ipi_mask;
 #ifdef CONFIG_DEBUG_PREEMPT
 	unsigned long			preempt_disable_ip;
 #endif
diff --git a/include/linux/smp.h b/include/linux/smp.h
index 11e36c7..2dfa739 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -238,6 +238,18 @@ static inline int get_boot_cpu_id(void)
 
 #endif /* !SMP */
 
+#if defined(CONFIG_PREEMPTION) && defined(CONFIG_SMP)
+int smp_task_ipi_mask_alloc(struct task_struct *task);
+void smp_task_ipi_mask_free(struct task_struct *task);
+#else
+static inline int smp_task_ipi_mask_alloc(struct task_struct *task)
+{
+	return 0;
+}
+
+static inline void smp_task_ipi_mask_free(struct task_struct *task) { }
+#endif
+
 /*
  * raw_smp_processor_id() - get the current (unstable) CPU id
  *
diff --git a/kernel/fork.c b/kernel/fork.c
index 13e38e8..ac3fc49 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -537,6 +537,7 @@ void free_task(struct task_struct *tsk)
 #endif
 	release_user_cpus_ptr(tsk);
 	scs_release(tsk);
+	smp_task_ipi_mask_free(tsk);
 
 #ifndef CONFIG_THREAD_INFO_IN_TASK
 	/*
@@ -935,10 +936,14 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 #endif
 	account_kernel_stack(tsk, 1);
 
-	err = scs_prepare(tsk, node);
+	err = smp_task_ipi_mask_alloc(tsk);
 	if (err)
 		goto free_stack;
 
+	err = scs_prepare(tsk, node);
+	if (err)
+		goto free_ipi_mask;
+
 #ifdef CONFIG_SECCOMP
 	/*
 	 * We must handle setting up seccomp filters once we're under
@@ -1011,6 +1016,8 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 #endif
 	return tsk;
 
+free_ipi_mask:
+	smp_task_ipi_mask_free(tsk);
 free_stack:
 	exit_task_stack_account(tsk);
 	free_thread_stack(tsk);
diff --git a/kernel/smp.c b/kernel/smp.c
index 5c05029..19fdee6 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -16,6 +16,7 @@
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/gfp.h>
+#include <linux/slab.h>
 #include <linux/smp.h>
 #include <linux/cpu.h>
 #include <linux/sched.h>
@@ -806,6 +807,50 @@ int smp_call_function_any(const struct cpumask *mask,
 }
 EXPORT_SYMBOL_GPL(smp_call_function_any);
 
+static DEFINE_STATIC_KEY_FALSE(ipi_mask_inlined);
+
+#ifdef CONFIG_PREEMPTION
+
+int smp_task_ipi_mask_alloc(struct task_struct *task)
+{
+	if (static_branch_unlikely(&ipi_mask_inlined))
+		return 0;
+
+	ACCESS_PRIVATE(task, ipi_mask).ipi_mask_ptr =
+		kmalloc(cpumask_size(), GFP_KERNEL);
+	if (!ACCESS_PRIVATE(task, ipi_mask).ipi_mask_ptr)
+		return -ENOMEM;
+
+	return 0;
+}
+
+void smp_task_ipi_mask_free(struct task_struct *task)
+{
+	if (static_branch_unlikely(&ipi_mask_inlined))
+		return;
+
+	kfree(ACCESS_PRIVATE(task, ipi_mask).ipi_mask_ptr);
+}
+
+static cpumask_t *smp_task_ipi_mask(struct task_struct *cur)
+{
+	/*
+	 * If cpumask_size() is smaller than or equal to the pointer
+	 * size, it stashes the cpumask in the pointer itself to
+	 * avoid extra memory allocations.
+	 */
+	if (static_branch_unlikely(&ipi_mask_inlined))
+		return (cpumask_t *)&ACCESS_PRIVATE(cur, ipi_mask).ipi_mask_val;
+
+	return ACCESS_PRIVATE(cur, ipi_mask).ipi_mask_ptr;
+}
+#else
+static cpumask_t *smp_task_ipi_mask(struct task_struct *cur)
+{
+	return NULL;
+}
+#endif
+
 /*
  * Flags to be used as scf_flags argument of smp_call_function_many_cond().
  *
@@ -821,13 +866,21 @@ static void smp_call_function_many_cond(const struct cpumask *mask,
 					smp_cond_func_t cond_func)
 {
 	int cpu, last_cpu, this_cpu = smp_processor_id();
-	struct call_function_data *cfd;
+	struct cpumask *cpumask, *task_mask;
 	bool wait = scf_flags & SCF_WAIT;
-	int nr_cpus = 0;
+	struct call_function_data *cfd;
 	bool run_remote = false;
+	int nr_cpus = 0;
 
 	lockdep_assert_preemption_disabled();
 
+	cfd = this_cpu_ptr(&cfd_data);
+	task_mask = smp_task_ipi_mask(current);
+	if (task_mask)
+		cpumask = task_mask;
+	else
+		cpumask = cfd->cpumask;
+
 	/*
 	 * Can deadlock when called with interrupts disabled.
 	 * We allow cpu's that are not yet online though, as no one else can
@@ -848,16 +901,15 @@ static void smp_call_function_many_cond(const struct cpumask *mask,
 
 	/* Check if we need remote execution, i.e., any CPU excluding this one. */
 	if (cpumask_any_and_but(mask, cpu_online_mask, this_cpu) < nr_cpu_ids) {
-		cfd = this_cpu_ptr(&cfd_data);
-		cpumask_and(cfd->cpumask, mask, cpu_online_mask);
-		__cpumask_clear_cpu(this_cpu, cfd->cpumask);
+		cpumask_and(cpumask, mask, cpu_online_mask);
+		__cpumask_clear_cpu(this_cpu, cpumask);
 
 		cpumask_clear(cfd->cpumask_ipi);
-		for_each_cpu(cpu, cfd->cpumask) {
+		for_each_cpu(cpu, cpumask) {
 			call_single_data_t *csd = per_cpu_ptr(cfd->csd, cpu);
 
 			if (cond_func && !cond_func(cpu, info)) {
-				__cpumask_clear_cpu(cpu, cfd->cpumask);
+				__cpumask_clear_cpu(cpu, cpumask);
 				continue;
 			}
 
@@ -908,7 +960,7 @@ static void smp_call_function_many_cond(const struct cpumask *mask,
 	}
 
 	if (run_remote && wait) {
-		for_each_cpu(cpu, cfd->cpumask) {
+		for_each_cpu(cpu, cpumask) {
 			call_single_data_t *csd;
 
 			csd = per_cpu_ptr(cfd->csd, cpu);
@@ -1022,6 +1074,9 @@ EXPORT_SYMBOL(nr_cpu_ids);
 void __init setup_nr_cpu_ids(void)
 {
 	set_nr_cpu_ids(find_last_bit(cpumask_bits(cpu_possible_mask), NR_CPUS) + 1);
+
+	if (IS_ENABLED(CONFIG_PREEMPTION) && cpumask_size() <= sizeof(unsigned long))
+		static_branch_enable(&ipi_mask_inlined);
 }
 
 /* Called by boot processor to activate the rest. */