percpu: implement new dynamic percpu allocator

Impact: new scalable dynamic percpu allocator which allows dynamic
        percpu areas to be accessed the same way as static ones

Implement scalable dynamic percpu allocator which can be used for both
static and dynamic percpu areas.  This will allow static and dynamic
areas to share faster direct access methods.  This feature is optional
and enabled only when CONFIG_HAVE_DYNAMIC_PER_CPU_AREA is defined by
arch.  Please read comment on top of mm/percpu.c for details.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>

kernel/module.c

@@ -51,6 +51,7 @@
 #include <linux/tracepoint.h>
 #include <linux/ftrace.h>
 #include <linux/async.h>
+#include <linux/percpu.h>
 
 #if 0
 #define DEBUGP printk
@@ -366,6 +367,34 @@ static struct module *find_module(const char *name)
 }
 
 #ifdef CONFIG_SMP
+
+#ifdef CONFIG_HAVE_DYNAMIC_PER_CPU_AREA
+
+static void *percpu_modalloc(unsigned long size, unsigned long align,
+			     const char *name)
+{
+	void *ptr;
+
+	if (align > PAGE_SIZE) {
+		printk(KERN_WARNING "%s: per-cpu alignment %li > %li\n",
+		       name, align, PAGE_SIZE);
+		align = PAGE_SIZE;
+	}
+
+	ptr = __alloc_percpu(size, align);
+	if (!ptr)
+		printk(KERN_WARNING
+		       "Could not allocate %lu bytes percpu data\n", size);
+	return ptr;
+}
+
+static void percpu_modfree(void *freeme)
+{
+	free_percpu(freeme);
+}
+
+#else /* ... !CONFIG_HAVE_DYNAMIC_PER_CPU_AREA */
+
 /* Number of blocks used and allocated. */
 static unsigned int pcpu_num_used, pcpu_num_allocated;
 /* Size of each block.  -ve means used. */
@@ -499,6 +528,8 @@ static int percpu_modinit(void)
 }
 __initcall(percpu_modinit);
 
+#endif /* CONFIG_HAVE_DYNAMIC_PER_CPU_AREA */
+
 static unsigned int find_pcpusec(Elf_Ehdr *hdr,
 				 Elf_Shdr *sechdrs,
 				 const char *secstrings)