omarchy-pkgs/pkgbuilds/linux-omarchy-bore/0121-smp-preempt.patch

diff --git a/include/linux/sched.h b/include/linux/sched.h
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -848,6 +848,17 @@ struct bore_ctx {
 };
 #endif /* CONFIG_SCHED_BORE */
 
+#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
 	/*
@@ -1387,6 +1398,7 @@ 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
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -47,8 +47,7 @@ extern void __smp_call_single_queue(int cpu, struct llist_node *node);
 /* total number of cpus in this system (may exceed NR_CPUS) */
 extern unsigned int total_cpus;
 
-int smp_call_function_single(int cpuid, smp_call_func_t func, void *info,
-			     int wait);
+int smp_call_function_single(int cpuid, smp_call_func_t func, void *info, bool wait);
 
 void on_each_cpu_cond_mask(smp_cond_func_t cond_func, smp_call_func_t func,
 			   void *info, bool wait, const struct cpumask *mask);
@@ -239,6 +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
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -547,6 +547,7 @@ 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
 	/*
@@ -945,10 +946,14 @@ 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
@@ -1026,6 +1031,8 @@ 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/scftorture.c b/kernel/scftorture.c
--- 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))
diff --git a/kernel/smp.c b/kernel/smp.c
--- 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>
@@ -63,7 +64,14 @@ int smpcfd_prepare_cpu(unsigned int cpu)
 		free_cpumask_var(cfd->cpumask);
 		return -ENOMEM;
 	}
-	cfd->csd = alloc_percpu(call_single_data_t);
+
+	/*
+	 * Allocate the per-CPU CSD the first time a CPU comes up. It is
+	 * not freed when the CPU is offlined, so csd_lock_wait() can access
+	 * it even when the CPU was offlined after preemption was re-enabled.
+	 */
+	if (!cfd->csd)
+		cfd->csd = alloc_percpu(call_single_data_t);
 	if (!cfd->csd) {
 		free_cpumask_var(cfd->cpumask);
 		free_cpumask_var(cfd->cpumask_ipi);
@@ -79,7 +87,6 @@ int smpcfd_dead_cpu(unsigned int cpu)
 
 	free_cpumask_var(cfd->cpumask);
 	free_cpumask_var(cfd->cpumask_ipi);
-	free_percpu(cfd->csd);
 	return 0;
 }
 
@@ -323,6 +330,8 @@ static void __csd_lock_wait(call_single_data_t *csd)
 	int bug_id = 0;
 	u64 ts0, ts1;
 
+	guard(preempt)();
+
 	ts1 = ts0 = ktime_get_mono_fast_ns();
 	for (;;) {
 		if (csd_lock_wait_toolong(csd, ts0, &ts1, &bug_id, &nmessages))
@@ -659,17 +668,9 @@ void flush_smp_call_function_queue(void)
 	local_irq_restore(flags);
 }
 
-/**
- * smp_call_function_single - Run a function on a specific CPU
- * @cpu: Specific target CPU for this function.
- * @func: The function to run. This must be fast and non-blocking.
- * @info: An arbitrary pointer to pass to the function.
- * @wait: If true, wait until function has completed on other CPUs.
- *
- * Returns: %0 on success, else a negative status code.
- */
-int smp_call_function_single(int cpu, smp_call_func_t func, void *info,
-			     int wait)
+static int __smp_call_function_single(int cpu, smp_call_func_t func,
+				      void *info, const struct cpumask *mask,
+				      bool wait)
 {
 	call_single_data_t *csd;
 	call_single_data_t csd_stack = {
@@ -686,6 +687,14 @@ int smp_call_function_single(int cpu, smp_call_func_t func, void *info,
 	 */
 	this_cpu = get_cpu();
 
+	if (mask) {
+		/* Try for same CPU (cheapest) */
+		if (!cpumask_test_cpu(this_cpu, mask))
+			cpu = sched_numa_find_nth_cpu(mask, 0, cpu_to_node(this_cpu));
+		else
+			cpu = this_cpu;
+	}
+
 	/*
 	 * Can deadlock when called with interrupts disabled.
 	 * We allow cpu's that are not yet online though, as no one else can
@@ -718,13 +727,32 @@ int smp_call_function_single(int cpu, smp_call_func_t func, void *info,
 
 	err = generic_exec_single(cpu, csd);
 
+	/*
+	 * @csd is stack-allocated when @wait is true. No concurrent access
+	 * except from the IPI completion path, so we can re-enable preemption
+	 * early to reduce latency.
+	 */
+	put_cpu();
+
 	if (wait)
 		csd_lock_wait(csd);
 
-	put_cpu();
-
 	return err;
 }
+
+/**
+ * smp_call_function_single - Run a function on a specific CPU
+ * @cpu:	Specific target CPU for this function.
+ * @func:	The function to run. This must be fast and non-blocking.
+ * @info:	An arbitrary pointer to pass to the function.
+ * @wait:	If true, wait until function has completed on other CPUs.
+ *
+ * Returns: %0 on success, else a negative status code.
+ */
+int smp_call_function_single(int cpu, smp_call_func_t func, void *info, bool wait)
+{
+	return __smp_call_function_single(cpu, func, info, NULL, wait);
+}
 EXPORT_SYMBOL(smp_call_function_single);
 
 /**
@@ -775,10 +803,10 @@ EXPORT_SYMBOL_GPL(smp_call_function_single_async);
 
 /**
  * smp_call_function_any - Run a function on any of the given cpus
- * @mask: The mask of cpus it can run on.
- * @func: The function to run. This must be fast and non-blocking.
- * @info: An arbitrary pointer to pass to the function.
- * @wait: If true, wait until function has completed.
+ * @mask:	The mask of cpus it can run on.
+ * @func:	The function to run. This must be fast and non-blocking.
+ * @info:	An arbitrary pointer to pass to the function.
+ * @wait:	If true, wait until function has completed.
  *
  * Selection preference:
  *	1) current cpu if in @mask
@@ -789,20 +817,54 @@ EXPORT_SYMBOL_GPL(smp_call_function_single_async);
 int smp_call_function_any(const struct cpumask *mask,
 			  smp_call_func_t func, void *info, int wait)
 {
-	unsigned int cpu;
-	int ret;
-
-	/* Try for same CPU (cheapest) */
-	cpu = get_cpu();
-	if (!cpumask_test_cpu(cpu, mask))
-		cpu = sched_numa_find_nth_cpu(mask, 0, cpu_to_node(cpu));
-
-	ret = smp_call_function_single(cpu, func, info, wait);
-	put_cpu();
-	return ret;
+	return __smp_call_function_single(-1, func, info, mask, wait);
 }
 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().
  *
@@ -817,13 +879,20 @@ static void smp_call_function_many_cond(const struct cpumask *mask,
 					unsigned int scf_flags,
 					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;
+	int cpu, last_cpu, this_cpu;
 	bool run_remote = false;
+	int nr_cpus = 0;
 
-	lockdep_assert_preemption_disabled();
+	this_cpu = get_cpu();
+	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.
@@ -845,16 +914,15 @@ 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;
 			}
 
@@ -904,8 +972,18 @@ static void smp_call_function_many_cond(const struct cpumask *mask,
 		local_irq_restore(flags);
 	}
 
+	/*
+	 * The IPI work has been queued and dispatched. On PREEMPT kernels,
+	 * tasks created through dup_task_struct() have task-local wait masks.
+	 * The boot init_task can fall back to cfd->cpumask when the mask is
+	 * not inlined, but other tasks still use task-local masks and cannot
+	 * overwrite it. On !PREEMPT kernels, preempt_enable() cannot schedule
+	 * another task, so the per-CPU mask remains protected.
+	 */
+	put_cpu();
+
 	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);
@@ -916,15 +994,14 @@ static void smp_call_function_many_cond(const struct cpumask *mask,
 
 /**
  * smp_call_function_many() - Run a function on a set of CPUs.
- * @mask: The set of cpus to run on (only runs on online subset).
- * @func: The function to run. This must be fast and non-blocking.
- * @info: An arbitrary pointer to pass to the function.
- * @wait: If true, wait (atomically) until function has completed
- *        on other CPUs.
+ * @mask:	The set of cpus to run on (only runs on online subset).
+ * @func:	The function to run. This must be fast and non-blocking.
+ * @info:	An arbitrary pointer to pass to the function.
+ * @wait:	If true, wait (atomically) until function has completed
+ *		on other CPUs.
  *
  * You must not call this function with disabled interrupts or from a
- * hardware interrupt handler or from a bottom half handler. Preemption
- * must be disabled when calling this function.
+ * hardware interrupt handler or from a bottom half handler.
  *
  * @func is not called on the local CPU even if @mask contains it.  Consider
  * using on_each_cpu_cond_mask() instead if this is not desirable.
@@ -938,10 +1015,10 @@ EXPORT_SYMBOL(smp_call_function_many);
 
 /**
  * smp_call_function() - Run a function on all other CPUs.
- * @func: The function to run. This must be fast and non-blocking.
- * @info: An arbitrary pointer to pass to the function.
- * @wait: If true, wait (atomically) until function has completed
- *        on other CPUs.
+ * @func:	The function to run. This must be fast and non-blocking.
+ * @info:	An arbitrary pointer to pass to the function.
+ * @wait:	If true, wait (atomically) until function has completed
+ *		on other CPUs.
  *
  * If @wait is true, then returns once @func has returned; otherwise
  * it returns just before the target cpu calls @func.
@@ -951,9 +1028,8 @@ EXPORT_SYMBOL(smp_call_function_many);
  */
 void smp_call_function(smp_call_func_t func, void *info, int wait)
 {
-	preempt_disable();
-	smp_call_function_many(cpu_online_mask, func, info, wait);
-	preempt_enable();
+	smp_call_function_many_cond(cpu_online_mask, func, info,
+				    wait ? SCF_WAIT : 0, NULL);
 }
 EXPORT_SYMBOL(smp_call_function);
 
@@ -1019,6 +1095,9 @@ 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. */
@@ -1055,12 +1134,14 @@ void __init smp_init(void)
  * @func:	The function to run on all applicable CPUs.
  *		This must be fast and non-blocking.
  * @info:	An arbitrary pointer to pass to both functions.
- * @wait:	If true, wait (atomically) until function has
- *		completed on other CPUs.
+ * @wait:	If true, wait until function has completed on other CPUs.
  * @mask:	The set of cpus to run on (only runs on online subset).
  *
- * Preemption is disabled to protect against CPUs going offline but not online.
- * CPUs going online during the call will not be seen or sent an IPI.
+ * Target CPU selection and work queueing are done with preemption
+ * disabled. This protects against CPUs going offline, but not against
+ * CPUs coming online concurrently; newly online CPUs are not guaranteed
+ * to be seen or sent an IPI. If @wait is true, the final wait for remote
+ * completion happens after that preemption-disabled section.
  *
  * You must not call this function with disabled interrupts or
  * from a hardware interrupt handler or from a bottom half handler.
@@ -1073,9 +1154,7 @@ void on_each_cpu_cond_mask(smp_cond_func_t cond_func, smp_call_func_t func,
 	if (wait)
 		scf_flags |= SCF_WAIT;
 
-	preempt_disable();
 	smp_call_function_many_cond(mask, func, info, scf_flags, cond_func);
-	preempt_enable();
 }
 EXPORT_SYMBOL(on_each_cpu_cond_mask);
 
diff --git a/kernel/up.c b/kernel/up.c
--- a/kernel/up.c
+++ b/kernel/up.c
@@ -9,8 +9,7 @@
 #include <linux/smp.h>
 #include <linux/hypervisor.h>
 
-int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
-				int wait)
+int smp_call_function_single(int cpu, void (*func)(void *info), void *info, bool wait)
 {
 	unsigned long flags;