GitHub-Mirror/Star64_linux
2
0
Fork 0
mirror of https://github.com/Fishwaldo/Star64_linux.git synced 2025-06-22 14:41:27 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

module: Optimize __module_address() using a latched RB-tree

Browse source 
Currently __module_address() is using a linear search through all
modules in order to find the module corresponding to the provided
address. With a lot of modules this can take a lot of time.

One of the users of this is kernel_text_address() which is employed
in many stack unwinders; which in turn are used by perf-callchain and
ftrace (possibly from NMI context).

So by optimizing __module_address() we optimize many stack unwinders
which are used by both perf and tracing in performance sensitive code.

Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
This commit is contained in:
Peter Zijlstra 2015-05-27 11:09:37 +09:30 • committed by Rusty Russell
parent ade3f510f9
commit 93c2e105f6
2 changed files with 136 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

29
include/linux/module.h
View file

@ -17,6 +17,7 @@
#include <linux/moduleparam.h>
#include <linux/jump_label.h>
#include <linux/export.h>
#include <linux/rbtree_latch.h>
#include <linux/percpu.h>
#include <asm/module.h>
@ -210,6 +211,13 @@ enum module_state {
MODULE_STATE_UNFORMED, /* Still setting it up. */
};
struct module;
struct mod_tree_node {
struct module *mod;
struct latch_tree_node node;
};
struct module {
enum module_state state;
@ -269,8 +277,15 @@ struct module {
/* Startup function. */
int (*init)(void);
/* If this is non-NULL, vfree after init() returns */
void *module_init;
/*
* If this is non-NULL, vfree() after init() returns.
*
* Cacheline align here, such that:
* module_init, module_core, init_size, core_size,
* init_text_size, core_text_size and ltn_core.node[0]
* are on the same cacheline.
*/
void *module_init ____cacheline_aligned;
/* Here is the actual code + data, vfree'd on unload. */
void *module_core;
@ -281,6 +296,14 @@ struct module {
/* The size of the executable code in each section. */
unsigned int init_text_size, core_text_size;
/*
* We want mtn_core::{mod,node[0]} to be in the same cacheline as the
* above entries such that a regular lookup will only touch one
* cacheline.
*/
struct mod_tree_node mtn_core;
struct mod_tree_node mtn_init;
/* Size of RO sections of the module (text+rodata) */
unsigned int init_ro_size, core_ro_size;
@ -367,7 +390,7 @@ struct module {
ctor_fn_t *ctors;
unsigned int num_ctors;
#endif
};
} ____cacheline_aligned;
#ifndef MODULE_ARCH_INIT
#define MODULE_ARCH_INIT {}
#endif