提交 720eba31 编写于 作者: E Eric Dumazet 提交者: Linus Torvalds

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: NEric Dumazet <dada1@cosmosbay.com>
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
上级 27421e21
master alk-4.19.24 alk-4.19.30 alk-4.19.34 alk-4.19.36 alk-4.19.43 alk-4.19.48 alk-4.19.57 ck-4.19.67 ck-4.19.81 ck-4.19.91 github/fork/deepanshu1422/fix-typo-in-comment github/fork/haosdent/fix-typo linux-next v4.19.91 v4.19.90 v4.19.89 v4.19.88 v4.19.87 v4.19.86 v4.19.85 v4.19.84 v4.19.83 v4.19.82 v4.19.81 v4.19.80 v4.19.79 v4.19.78 v4.19.77 v4.19.76 v4.19.75 v4.19.74 v4.19.73 v4.19.72 v4.19.71 v4.19.70 v4.19.69 v4.19.68 v4.19.67 v4.19.66 v4.19.65 v4.19.64 v4.19.63 v4.19.62 v4.19.61 v4.19.60 v4.19.59 v4.19.58 v4.19.57 v4.19.56 v4.19.55 v4.19.54 v4.19.53 v4.19.52 v4.19.51 v4.19.50 v4.19.49 v4.19.48 v4.19.47 v4.19.46 v4.19.45 v4.19.44 v4.19.43 v4.19.42 v4.19.41 v4.19.40 v4.19.39 v4.19.38 v4.19.37 v4.19.36 v4.19.35 v4.19.34 v4.19.33 v4.19.32 v4.19.31 v4.19.30 v4.19.29 v4.19.28 v4.19.27 v4.19.26 v4.19.25 v4.19.24 v4.19.23 v4.19.22 v4.19.21 v4.19.20 v4.19.19 v4.19.18 v4.19.17 v4.19.16 v4.19.15 v4.19.14 v4.19.13 v4.19.12 v4.19.11 v4.19.10 v4.19.9 v4.19.8 v4.19.7 v4.19.6 v4.19.5 v4.19.4 v4.19.3 v4.19.2 v4.19.1 v4.19 v4.19-rc8 v4.19-rc7 v4.19-rc6 v4.19-rc5 v4.19-rc4 v4.19-rc3 v4.19-rc2 v4.19-rc1 ck-release-21 ck-release-20 ck-release-19.2 ck-release-19.1 ck-release-19 ck-release-18 ck-release-17.2 ck-release-17.1 ck-release-17 ck-release-16 ck-release-15.1 ck-release-15 ck-release-14 ck-release-13.2 ck-release-13 ck-release-12 ck-release-11 ck-release-10 ck-release-9 ck-release-7 alk-release-15 alk-release-14 alk-release-13.2 alk-release-13 alk-release-12 alk-release-11 alk-release-10 alk-release-9 alk-release-7
无相关合并请求
......@@ -219,11 +219,6 @@ void *__symbol_get_gpl(const char *symbol);
#endif
struct module_ref
{
local_t count;
} ____cacheline_aligned;
enum module_state
{
MODULE_STATE_LIVE,
......@@ -344,8 +339,11 @@ struct module
/* Destruction function. */
void (*exit)(void);
/* Reference counts */
struct module_ref ref[NR_CPUS];
#ifdef CONFIG_SMP
char *refptr;
#else
local_t ref;
#endif
#endif
};
#ifndef MODULE_ARCH_INIT
......@@ -395,13 +393,22 @@ void __symbol_put(const char *symbol);
#define symbol_put(x) __symbol_put(MODULE_SYMBOL_PREFIX #x)
void symbol_put_addr(void *addr);
static inline local_t *__module_ref_addr(struct module *mod, int cpu)
{
#ifdef CONFIG_SMP
return (local_t *) (mod->refptr + per_cpu_offset(cpu));
#else
return &mod->ref;
#endif
}
/* Sometimes we know we already have a refcount, and it's easier not
to handle the error case (which only happens with rmmod --wait). */
static inline void __module_get(struct module *module)
{
if (module) {
BUG_ON(module_refcount(module) == 0);
local_inc(&module->ref[get_cpu()].count);
local_inc(__module_ref_addr(module, get_cpu()));
put_cpu();
}
}
......@@ -413,7 +420,7 @@ static inline int try_module_get(struct module *module)
if (module) {
unsigned int cpu = get_cpu();
if (likely(module_is_live(module)))
local_inc(&module->ref[cpu].count);
local_inc(__module_ref_addr(module, cpu));
else
ret = 0;
put_cpu();
......
......@@ -573,13 +573,13 @@ static char last_unloaded_module[MODULE_NAME_LEN+1];
/* 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 @@ static int try_stop_module(struct module *mod, int flags, int *forced)
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 @@ void module_put(struct module *module)
{
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 @@ static void free_module(struct module *mod)
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 @@ static noinline struct module *load_module(void __user *umod,
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 @@ static noinline struct module *load_module(void __user *umod,
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 @@ static noinline struct module *load_module(void __user *umod,
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:
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册
反馈
建议
客服 返回
顶部