cpumask: introduce new API, without changing anything

Impact: introduce new APIs

We want to deprecate cpumasks on the stack, as we are headed for
gynormous numbers of CPUs.  Eventually, we want to head towards an
undefined 'struct cpumask' so they can never be declared on stack.

1) New cpumask functions which take pointers instead of copies.
   (cpus_* -> cpumask_*)

2) Several new helpers to reduce requirements for temporary cpumasks
   (cpumask_first_and, cpumask_next_and, cpumask_any_and)

3) Helpers for declaring cpumasks on or offstack for large NR_CPUS
   (cpumask_var_t, alloc_cpumask_var and free_cpumask_var)

4) 'struct cpumask' for explicitness and to mark new-style code.

5) Make iterator functions stop at nr_cpu_ids (a runtime constant),
   not NR_CPUS for time efficiency and for smaller dynamic allocations
   in future.

6) cpumask_copy() so we can allocate less than a full cpumask eventually
   (for alloc_cpumask_var), and so we can eliminate the 'struct cpumask'
   definition eventually.

7) work_on_cpu() helper for doing task on a CPU, rather than saving old
   cpumask for current thread and manipulating it.

8) smp_call_function_many() which is smp_call_function_mask() except
   taking a cpumask pointer.

Note that this patch simply introduces the new functions and leaves
the obsolescent ones in place.  This is to simplify the transition
patches.
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

include/linux/smp.h

@@ -64,8 +64,17 @@ extern void smp_cpus_done(unsigned int max_cpus);
  * Call a function on all other processors
  */
 int smp_call_function(void(*func)(void *info), void *info, int wait);
+/* Deprecated: use smp_call_function_many() which uses a cpumask ptr. */
 int smp_call_function_mask(cpumask_t mask, void(*func)(void *info), void *info,
 				int wait);
+
+static inline void smp_call_function_many(const struct cpumask *mask,
+					  void (*func)(void *info), void *info,
+					  int wait)
+{
+	smp_call_function_mask(*mask, func, info, wait);
+}
+
 int smp_call_function_single(int cpuid, void (*func) (void *info), void *info,
 				int wait);
 void __smp_call_function_single(int cpuid, struct call_single_data *data);

include/linux/workqueue.h

@@ -240,4 +240,12 @@ void cancel_rearming_delayed_work(struct delayed_work *work)
 	cancel_delayed_work_sync(work);
 }
 
+#ifndef CONFIG_SMP
+static inline long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg)
+{
+	return fn(arg);
+}
+#else
+long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg);
+#endif /* CONFIG_SMP */
 #endif

kernel/cpu.c

@@ -499,3 +499,6 @@ const unsigned long cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)] = {
 #endif
 };
 EXPORT_SYMBOL_GPL(cpu_bit_bitmap);
+
+const DECLARE_BITMAP(cpu_all_bits, NR_CPUS) = CPU_BITS_ALL;
+EXPORT_SYMBOL(cpu_all_bits);

kernel/workqueue.c

@@ -970,6 +970,51 @@ static int __devinit workqueue_cpu_callback(struct notifier_block *nfb,
 	return ret;
 }
 
+#ifdef CONFIG_SMP
+struct work_for_cpu {
+	struct work_struct work;
+	long (*fn)(void *);
+	void *arg;
+	long ret;
+};
+
+static void do_work_for_cpu(struct work_struct *w)
+{
+	struct work_for_cpu *wfc = container_of(w, struct work_for_cpu, work);
+
+	wfc->ret = wfc->fn(wfc->arg);
+}
+
+/**
+ * work_on_cpu - run a function in user context on a particular cpu
+ * @cpu: the cpu to run on
+ * @fn: the function to run
+ * @arg: the function arg
+ *
+ * This will return -EINVAL in the cpu is not online, or the return value
+ * of @fn otherwise.
+ */
+long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg)
+{
+	struct work_for_cpu wfc;
+
+	INIT_WORK(&wfc.work, do_work_for_cpu);
+	wfc.fn = fn;
+	wfc.arg = arg;
+	get_online_cpus();
+	if (unlikely(!cpu_online(cpu)))
+		wfc.ret = -EINVAL;
+	else {
+		schedule_work_on(cpu, &wfc.work);
+		flush_work(&wfc.work);
+	}
+	put_online_cpus();
+
+	return wfc.ret;
+}
+EXPORT_SYMBOL_GPL(work_on_cpu);
+#endif /* CONFIG_SMP */
+
 void __init init_workqueues(void)
 {
 	cpu_populated_map = cpu_online_map;

lib/cpumask.c

@@ -2,6 +2,7 @@
 #include <linux/bitops.h>
 #include <linux/cpumask.h>
 #include <linux/module.h>
+#include <linux/bootmem.h>
 
 int __first_cpu(const cpumask_t *srcp)
 {
@@ -35,3 +36,75 @@ int __any_online_cpu(const cpumask_t *mask)
 	return cpu;
 }
 EXPORT_SYMBOL(__any_online_cpu);
+
+/**
+ * cpumask_next_and - get the next cpu in *src1p & *src2p
+ * @n: the cpu prior to the place to search (ie. return will be > @n)
+ * @src1p: the first cpumask pointer
+ * @src2p: the second cpumask pointer
+ *
+ * Returns >= nr_cpu_ids if no further cpus set in both.
+ */
+int cpumask_next_and(int n, const struct cpumask *src1p,
+		     const struct cpumask *src2p)
+{
+	while ((n = cpumask_next(n, src1p)) < nr_cpu_ids)
+		if (cpumask_test_cpu(n, src2p))
+			break;
+	return n;
+}
+EXPORT_SYMBOL(cpumask_next_and);
+
+/**
+ * cpumask_any_but - return a "random" in a cpumask, but not this one.
+ * @mask: the cpumask to search
+ * @cpu: the cpu to ignore.
+ *
+ * Often used to find any cpu but smp_processor_id() in a mask.
+ * Returns >= nr_cpu_ids if no cpus set.
+ */
+int cpumask_any_but(const struct cpumask *mask, unsigned int cpu)
+{
+	unsigned int i;
+
+	for_each_cpu(i, mask)
+		if (i != cpu)
+			break;
+	return i;
+}
+
+/* These are not inline because of header tangles. */
+#ifdef CONFIG_CPUMASK_OFFSTACK
+bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
+{
+	if (likely(slab_is_available()))
+		*mask = kmalloc(cpumask_size(), flags);
+	else {
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+		printk(KERN_ERR
+			"=> alloc_cpumask_var: kmalloc not available!\n");
+		dump_stack();
+#endif
+		*mask = NULL;
+	}
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+	if (!*mask) {
+		printk(KERN_ERR "=> alloc_cpumask_var: failed!\n");
+		dump_stack();
+	}
+#endif
+	return *mask != NULL;
+}
+EXPORT_SYMBOL(alloc_cpumask_var);
+
+void __init alloc_bootmem_cpumask_var(cpumask_var_t *mask)
+{
+	*mask = alloc_bootmem(cpumask_size());
+}
+
+void free_cpumask_var(cpumask_var_t mask)
+{
+	kfree(mask);
+}
+EXPORT_SYMBOL(free_cpumask_var);
+#endif