modules: Take a shortcut for checking if an address is in a module

This patch keeps track of the boundaries of module allocation, in
order to speed up module_text_address().

Inspired by Arjan's version, which required arch-specific defines:

	Various pieces of the kernel (lockdep, latencytop, etc) tend
	to store backtraces, sometimes at a relatively high
	frequency. In itself this isn't a big performance deal (after
	all you're using diagnostics features), but there have been
	some complaints from people who have over 100 modules loaded
	that this is a tad too slow.

	This is due to the new backtracer code which looks at every
	slot on the stack to see if it's a kernel/module text address,
	so that's 1024 slots.  1024 times 100 modules... that's a lot
	of list walking.

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>

diff --git a/kernel/module.c b/kernel/module.c
index 5c7eb0695b3ce82d2a41386c2df0970466089a3c..d8b5605132a038114c53a52279a71d7ba33c88b6 100644 (file)
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -70,6 +70,9 @@ static DECLARE_WAIT_QUEUE_HEAD(module_wq);
 
 static BLOCKING_NOTIFIER_HEAD(module_notify_list);
 
+/* Bounds of module allocation, for speeding __module_text_address */
+static unsigned long module_addr_min = -1UL, module_addr_max = 0;
+
 int register_module_notifier(struct notifier_block * nb)
 {
        return blocking_notifier_chain_register(&module_notify_list, nb);
@@ -1779,6 +1782,20 @@ static inline void add_kallsyms(struct module *mod,
 }
 #endif /* CONFIG_KALLSYMS */
 
+static void *module_alloc_update_bounds(unsigned long size)
+{
+       void *ret = module_alloc(size);
+
+       if (ret) {
+               /* Update module bounds. */
+               if ((unsigned long)ret < module_addr_min)
+                       module_addr_min = (unsigned long)ret;
+               if ((unsigned long)ret + size > module_addr_max)
+                       module_addr_max = (unsigned long)ret + size;
+       }
+       return ret;
+}
+
 /* Allocate and load the module: note that size of section 0 is always
    zero, and we rely on this for optional sections. */
 static struct module *load_module(void __user *umod,
@@ -1980,7 +1997,7 @@ static struct module *load_module(void __user *umod,
        layout_sections(mod, hdr, sechdrs, secstrings);
 
        /* Do the allocs. */
-       ptr = module_alloc(mod->core_size);
+       ptr = module_alloc_update_bounds(mod->core_size);
        if (!ptr) {
                err = -ENOMEM;
                goto free_percpu;
@@ -1988,7 +2005,7 @@ static struct module *load_module(void __user *umod,
        memset(ptr, 0, mod->core_size);
        mod->module_core = ptr;
 
-       ptr = module_alloc(mod->init_size);
+       ptr = module_alloc_update_bounds(mod->init_size);
        if (!ptr && mod->init_size) {
                err = -ENOMEM;
                goto free_core;
@@ -2645,6 +2662,9 @@ struct module *__module_text_address(unsigned long addr)
 {
        struct module *mod;
 
+       if (addr < module_addr_min || addr > module_addr_max)
+               return NULL;
+
        list_for_each_entry(mod, &modules, list)
                if (within(addr, mod->module_init, mod->init_text_size)
                    || within(addr, mod->module_core, mod->core_text_size))