modules: Use a better scheme for refcounting
Current refcounting for modules (done if CONFIG_MODULE_UNLOAD=y) is
using a lot of memory.
Each 'struct module' contains an [NR_CPUS] array of full cache lines.
This patch uses existing infrastructure (percpu_modalloc() &
percpu_modfree()) to allocate percpu space for the refcount storage.
Instead of wasting NR_CPUS*128 bytes (on i386), we now use
nr_cpu_ids*sizeof(local_t) bytes.
On a typical distro, where NR_CPUS=8, shiping 2000 modules, we reduce
size of module files by about 2 Mbytes. (1Kb per module)
Instead of having all refcounters in the same memory node - with TLB misses
because of vmalloc() - this new implementation permits to have better
NUMA properties, since each CPU will use storage on its preferred node,
thanks to percpu storage.
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/kernel/module.c b/kernel/module.c
index e8b51d4..ba22484 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -573,13 +573,13 @@
/* Init the unload section of the module. */
static void module_unload_init(struct module *mod)
{
- unsigned int i;
+ int cpu;
INIT_LIST_HEAD(&mod->modules_which_use_me);
- for (i = 0; i < NR_CPUS; i++)
- local_set(&mod->ref[i].count, 0);
+ for_each_possible_cpu(cpu)
+ local_set(__module_ref_addr(mod, cpu), 0);
/* Hold reference count during initialization. */
- local_set(&mod->ref[raw_smp_processor_id()].count, 1);
+ local_set(__module_ref_addr(mod, raw_smp_processor_id()), 1);
/* Backwards compatibility macros put refcount during init. */
mod->waiter = current;
}
@@ -717,10 +717,11 @@
unsigned int module_refcount(struct module *mod)
{
- unsigned int i, total = 0;
+ unsigned int total = 0;
+ int cpu;
- for (i = 0; i < NR_CPUS; i++)
- total += local_read(&mod->ref[i].count);
+ for_each_possible_cpu(cpu)
+ total += local_read(__module_ref_addr(mod, cpu));
return total;
}
EXPORT_SYMBOL(module_refcount);
@@ -894,7 +895,7 @@
{
if (module) {
unsigned int cpu = get_cpu();
- local_dec(&module->ref[cpu].count);
+ local_dec(__module_ref_addr(module, cpu));
/* Maybe they're waiting for us to drop reference? */
if (unlikely(!module_is_live(module)))
wake_up_process(module->waiter);
@@ -1464,7 +1465,10 @@
kfree(mod->args);
if (mod->percpu)
percpu_modfree(mod->percpu);
-
+#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
+ if (mod->refptr)
+ percpu_modfree(mod->refptr);
+#endif
/* Free lock-classes: */
lockdep_free_key_range(mod->module_core, mod->core_size);
@@ -2011,6 +2015,14 @@
if (err < 0)
goto free_mod;
+#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
+ mod->refptr = percpu_modalloc(sizeof(local_t), __alignof__(local_t),
+ mod->name);
+ if (!mod->refptr) {
+ err = -ENOMEM;
+ goto free_mod;
+ }
+#endif
if (pcpuindex) {
/* We have a special allocation for this section. */
percpu = percpu_modalloc(sechdrs[pcpuindex].sh_size,
@@ -2018,7 +2030,7 @@
mod->name);
if (!percpu) {
err = -ENOMEM;
- goto free_mod;
+ goto free_percpu;
}
sechdrs[pcpuindex].sh_flags &= ~(unsigned long)SHF_ALLOC;
mod->percpu = percpu;
@@ -2282,6 +2294,9 @@
free_percpu:
if (percpu)
percpu_modfree(percpu);
+#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
+ percpu_modfree(mod->refptr);
+#endif
free_mod:
kfree(args);
free_hdr: