[PATCH] Module per-cpu alignment cannot always be met

The module code assumes noone will ever ask for a per-cpu area more than
SMP_CACHE_BYTES aligned. However, as these cases show, gcc asks sometimes
asks for 32-byte alignment for the per-cpu section on a module, and if
CONFIG_X86_L1_CACHE_SHIFT is 4, we hit that BUG_ON(). This is obviously an
unusual combination, as there have been few reports, but better to warn
than die.

See:
http://www.ussg.iu.edu/hypermail/linux/kernel/0409.0/0768.html

And more recently:
http://bugs.gentoo.org/show_bug.cgi?id=97006

Signed-off-by: Rusty Russell <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
Signed-off-by: Linus Torvalds <[e-mail]>

kernel/module.c

···
 /* Created by linker magic */
 extern char __per_cpu_start[], __per_cpu_end[];
 
-static void *percpu_modalloc(unsigned long size, unsigned long align)
+static void *percpu_modalloc(unsigned long size, unsigned long align,
+			     const char *name)
 {
 	unsigned long extra;
 	unsigned int i;
 	void *ptr;
 
-	BUG_ON(align > SMP_CACHE_BYTES);
+	if (align > SMP_CACHE_BYTES) {
+		printk(KERN_WARNING "%s: per-cpu alignment %li > %i\n",
+		       name, align, SMP_CACHE_BYTES);
+		align = SMP_CACHE_BYTES;
+	}
 
 	ptr = __per_cpu_start;
 	for (i = 0; i < pcpu_num_used; ptr += block_size(pcpu_size[i]), i++) {
···
 }	
 __initcall(percpu_modinit);
 #else /* ... !CONFIG_SMP */
-static inline void *percpu_modalloc(unsigned long size, unsigned long align)
+static inline void *percpu_modalloc(unsigned long size, unsigned long align,
+				    const char *name)
 {
 	return NULL;
 }
···
 	if (pcpuindex) {
 		/* We have a special allocation for this section. */
 		percpu = percpu_modalloc(sechdrs[pcpuindex].sh_size,
-					 sechdrs[pcpuindex].sh_addralign);
+					 sechdrs[pcpuindex].sh_addralign,
+					 mod->name);
 		if (!percpu) {
 			err = -ENOMEM;
 			goto free_mod;