[PATCH] CPU hotplug compatible alloc_percpu()

This patch splits alloc_percpu() up into two phases.  Likewise for
free_percpu().  This allows clients to limit initial allocations to online
cpu's, and to populate or depopulate per-cpu data at run time as needed:

  struct my_struct *obj;

  /* initial allocation for online cpu's */
  obj = percpu_alloc(sizeof(struct my_struct), GFP_KERNEL);

  ...

  /* populate per-cpu data for cpu coming online */
  ptr = percpu_populate(obj, sizeof(struct my_struct), GFP_KERNEL, cpu);

  ...

  /* access per-cpu object */
  ptr = percpu_ptr(obj, smp_processor_id());

  ...

  /* depopulate per-cpu data for cpu going offline */
  percpu_depopulate(obj, cpu);

  ...

  /* final removal */
  percpu_free(obj);

Signed-off-by: Martin Peschke <mp3@de.ibm.com>
Cc: Paul Jackson <pj@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

1 files changed, 60 insertions, 19 deletions

diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index f926490a7d8..3835a9642f1 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -1,9 +1,12 @@
 #ifndef __LINUX_PERCPU_H
 #define __LINUX_PERCPU_H
+
 #include <linux/spinlock.h> /* For preempt_disable() */
 #include <linux/slab.h> /* For kmalloc() */
 #include <linux/smp.h>
 #include <linux/string.h> /* For memset() */
+#include <linux/cpumask.h>
+
 #include <asm/percpu.h>
 
 /* Enough to cover all DEFINE_PER_CPUs in kernel, including modules. */
@@ -27,39 +30,77 @@ struct percpu_data {
 	void *ptrs[NR_CPUS];
 };
 
+#define __percpu_disguise(pdata) (struct percpu_data *)~(unsigned long)(pdata)
 /* 
- * Use this to get to a cpu's version of the per-cpu object allocated using
- * alloc_percpu.  Non-atomic access to the current CPU's version should
+ * Use this to get to a cpu's version of the per-cpu object dynamically
+ * allocated. Non-atomic access to the current CPU's version should
  * probably be combined with get_cpu()/put_cpu().
  */ 
-#define per_cpu_ptr(ptr, cpu)                   \
-({                                              \
-        struct percpu_data *__p = (struct percpu_data *)~(unsigned long)(ptr); \
-        (__typeof__(ptr))__p->ptrs[(cpu)];	\
+#define percpu_ptr(ptr, cpu)                              \
+({                                                        \
+        struct percpu_data *__p = __percpu_disguise(ptr); \
+        (__typeof__(ptr))__p->ptrs[(cpu)];	          \
 })
 
-extern void *__alloc_percpu(size_t size);
-extern void free_percpu(const void *);
+extern void *percpu_populate(void *__pdata, size_t size, gfp_t gfp, int cpu);
+extern void percpu_depopulate(void *__pdata, int cpu);
+extern int __percpu_populate_mask(void *__pdata, size_t size, gfp_t gfp,
+				  cpumask_t *mask);
+extern void __percpu_depopulate_mask(void *__pdata, cpumask_t *mask);
+extern void *__percpu_alloc_mask(size_t size, gfp_t gfp, cpumask_t *mask);
+extern void percpu_free(void *__pdata);
 
 #else /* CONFIG_SMP */
 
-#define per_cpu_ptr(ptr, cpu) ({ (void)(cpu); (ptr); })
+#define percpu_ptr(ptr, cpu) ({ (void)(cpu); (ptr); })
+
+static inline void percpu_depopulate(void *__pdata, int cpu)
+{
+}
+
+static inline void __percpu_depopulate_mask(void *__pdata, cpumask_t *mask)
+{
+}
 
-static inline void *__alloc_percpu(size_t size)
+static inline void *percpu_populate(void *__pdata, size_t size, gfp_t gfp,
+				    int cpu)
 {
-	void *ret = kmalloc(size, GFP_KERNEL);
-	if (ret)
-		memset(ret, 0, size);
-	return ret;
+	return percpu_ptr(__pdata, cpu);
 }
-static inline void free_percpu(const void *ptr)
-{	
-	kfree(ptr);
+
+static inline int __percpu_populate_mask(void *__pdata, size_t size, gfp_t gfp,
+					 cpumask_t *mask)
+{
+	return 0;
+}
+
+static inline void *__percpu_alloc_mask(size_t size, gfp_t gfp, cpumask_t *mask)
+{
+	return kzalloc(size, gfp);
+}
+
+static inline void percpu_free(void *__pdata)
+{
+	kfree(__pdata);
 }
 
 #endif /* CONFIG_SMP */
 
-/* Simple wrapper for the common case: zeros memory. */
-#define alloc_percpu(type)	((type *)(__alloc_percpu(sizeof(type))))
+#define percpu_populate_mask(__pdata, size, gfp, mask) \
+	__percpu_populate_mask((__pdata), (size), (gfp), &(mask))
+#define percpu_depopulate_mask(__pdata, mask) \
+	__percpu_depopulate_mask((__pdata), &(mask))
+#define percpu_alloc_mask(size, gfp, mask) \
+	__percpu_alloc_mask((size), (gfp), &(mask))
+
+#define percpu_alloc(size, gfp) percpu_alloc_mask((size), (gfp), cpu_online_map)
+
+/* (legacy) interface for use without CPU hotplug handling */
+
+#define __alloc_percpu(size)	percpu_alloc_mask((size), GFP_KERNEL, \
+						  cpu_possible_map)
+#define alloc_percpu(type)	(type *)__alloc_percpu(sizeof(type))
+#define free_percpu(ptr)	percpu_free((ptr))
+#define per_cpu_ptr(ptr, cpu)	percpu_ptr((ptr), (cpu))
 
 #endif /* __LINUX_PERCPU_H */