[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20101119100939.16882.99385.stgit@ltc236.sdl.hitachi.co.jp>
Date: Fri, 19 Nov 2010 19:09:39 +0900
From: Masami Hiramatsu <masami.hiramatsu.pt@...achi.com>
To: Ingo Molnar <mingo@...e.hu>
Cc: Rusty Russell <rusty@...tcorp.com.au>,
Frederic Weisbecker <fweisbec@...il.com>,
Ananth N Mavinakayanahalli <ananth@...ibm.com>,
Jason Baron <jbaron@...hat.com>,
Mathieu Desnoyers <mathieu.desnoyers@...icios.com>,
linux-kernel@...r.kernel.org, 2nddept-manager@....hitachi.co.jp,
Masami Hiramatsu <mhiramat@...hat.com>,
Thomas Gleixner <tglx@...utronix.de>,
Ingo Molnar <mingo@...hat.com>,
"H. Peter Anvin" <hpa@...or.com>, x86@...nel.org,
Peter Zijlstra <a.p.zijlstra@...llo.nl>,
Ananth N Mavinakayanahalli <ananth@...ibm.com>,
Steven Rostedt <rostedt@...dmis.org>,
linux-kernel@...r.kernel.org,
Rusty Russell <rusty@...tcorp.com.au>,
Frederic Weisbecker <fweisbec@...il.com>
Subject: [PATCH -tip v4 2/3] kprobes/x86: Use text_poke_smp_batch
Use text_poke_smp_batch() in optimization path for reducing
the number of stop_machine() issues. If the number of optimizing
probes is more than MAX_OPTIMIZE_PROBES(=256), kprobes optimizes
first MAX_OPTIMIZE_PROBES probes and kicks optimizer for remaining
probes.
Changes in v2:
- Allocate code buffer and parameters in arch_init_kprobes()
instead of using static arraies.
- Merge previous max optimization limit patch into this patch.
So, this patch introduces upper limit of optimization at
once.
Signed-off-by: Masami Hiramatsu <mhiramat@...hat.com>
Cc: Thomas Gleixner <tglx@...utronix.de>
Cc: Ingo Molnar <mingo@...hat.com>
Cc: "H. Peter Anvin" <hpa@...or.com>
Cc: x86@...nel.org
Cc: Peter Zijlstra <a.p.zijlstra@...llo.nl>
Cc: Ananth N Mavinakayanahalli <ananth@...ibm.com>
Cc: Steven Rostedt <rostedt@...dmis.org>
Cc: linux-kernel@...r.kernel.org
Cc: Rusty Russell <rusty@...tcorp.com.au>
Cc: Frederic Weisbecker <fweisbec@...il.com>
---
arch/x86/kernel/kprobes.c | 69 ++++++++++++++++++++++++++++++++++++++++-----
include/linux/kprobes.h | 2 +
kernel/kprobes.c | 11 ++-----
3 files changed, 65 insertions(+), 17 deletions(-)
diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index 1cbd54c..2840d34 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes.c
@@ -1401,10 +1401,16 @@ int __kprobes arch_prepare_optimized_kprobe(struct optimized_kprobe *op)
return 0;
}
-/* Replace a breakpoint (int3) with a relative jump. */
-int __kprobes arch_optimize_kprobe(struct optimized_kprobe *op)
+#define MAX_OPTIMIZE_PROBES 256
+static struct text_poke_param *jump_poke_params;
+static struct jump_poke_buffer {
+ u8 buf[RELATIVEJUMP_SIZE];
+} *jump_poke_bufs;
+
+static void __kprobes setup_optimize_kprobe(struct text_poke_param *tprm,
+ u8 *insn_buf,
+ struct optimized_kprobe *op)
{
- unsigned char jmp_code[RELATIVEJUMP_SIZE];
s32 rel = (s32)((long)op->optinsn.insn -
((long)op->kp.addr + RELATIVEJUMP_SIZE));
@@ -1412,16 +1418,39 @@ int __kprobes arch_optimize_kprobe(struct optimized_kprobe *op)
memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE,
RELATIVE_ADDR_SIZE);
- jmp_code[0] = RELATIVEJUMP_OPCODE;
- *(s32 *)(&jmp_code[1]) = rel;
+ insn_buf[0] = RELATIVEJUMP_OPCODE;
+ *(s32 *)(&insn_buf[1]) = rel;
+
+ tprm->addr = op->kp.addr;
+ tprm->opcode = insn_buf;
+ tprm->len = RELATIVEJUMP_SIZE;
+}
+
+/*
+ * Replace breakpoints (int3) with relative jumps.
+ * Caller must call with locking kprobe_mutex and text_mutex.
+ */
+void __kprobes arch_optimize_kprobes(struct list_head *oplist)
+{
+ struct optimized_kprobe *op, *tmp;
+ int c = 0;
+
+ list_for_each_entry_safe(op, tmp, oplist, list) {
+ WARN_ON(kprobe_disabled(&op->kp));
+ /* Setup param */
+ setup_optimize_kprobe(&jump_poke_params[c],
+ jump_poke_bufs[c].buf, op);
+ list_del_init(&op->list);
+ if (++c >= MAX_OPTIMIZE_PROBES)
+ break;
+ }
/*
* text_poke_smp doesn't support NMI/MCE code modifying.
* However, since kprobes itself also doesn't support NMI/MCE
* code probing, it's not a problem.
*/
- text_poke_smp(op->kp.addr, jmp_code, RELATIVEJUMP_SIZE);
- return 0;
+ text_poke_smp_batch(jump_poke_params, c);
}
/* Replace a relative jump with a breakpoint (int3). */
@@ -1453,11 +1482,35 @@ static int __kprobes setup_detour_execution(struct kprobe *p,
}
return 0;
}
+
+static int __kprobes init_poke_params(void)
+{
+ /* Allocate code buffer and parameter array */
+ jump_poke_bufs = kmalloc(sizeof(struct jump_poke_buffer) *
+ MAX_OPTIMIZE_PROBES, GFP_KERNEL);
+ if (!jump_poke_bufs)
+ return -ENOMEM;
+
+ jump_poke_params = kmalloc(sizeof(struct text_poke_param) *
+ MAX_OPTIMIZE_PROBES, GFP_KERNEL);
+ if (!jump_poke_params) {
+ kfree(jump_poke_bufs);
+ jump_poke_bufs = NULL;
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+#else /* !CONFIG_OPTPROBES */
+static int __kprobes init_poke_params(void)
+{
+ return 0;
+}
#endif
int __init arch_init_kprobes(void)
{
- return 0;
+ return init_poke_params();
}
int __kprobes arch_trampoline_kprobe(struct kprobe *p)
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index e7d1b2e..fe157ba 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -275,7 +275,7 @@ extern int arch_prepared_optinsn(struct arch_optimized_insn *optinsn);
extern int arch_check_optimized_kprobe(struct optimized_kprobe *op);
extern int arch_prepare_optimized_kprobe(struct optimized_kprobe *op);
extern void arch_remove_optimized_kprobe(struct optimized_kprobe *op);
-extern int arch_optimize_kprobe(struct optimized_kprobe *op);
+extern void arch_optimize_kprobes(struct list_head *oplist);
extern void arch_unoptimize_kprobe(struct optimized_kprobe *op);
extern kprobe_opcode_t *get_optinsn_slot(void);
extern void free_optinsn_slot(kprobe_opcode_t *slot, int dirty);
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 9737a76..4db766f 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -430,8 +430,6 @@ static DECLARE_DELAYED_WORK(optimizing_work, kprobe_optimizer);
/* Kprobe jump optimizer */
static __kprobes void kprobe_optimizer(struct work_struct *work)
{
- struct optimized_kprobe *op, *tmp;
-
/* Lock modules while optimizing kprobes */
mutex_lock(&module_mutex);
mutex_lock(&kprobe_mutex);
@@ -459,14 +457,11 @@ static __kprobes void kprobe_optimizer(struct work_struct *work)
*/
get_online_cpus();
mutex_lock(&text_mutex);
- list_for_each_entry_safe(op, tmp, &optimizing_list, list) {
- WARN_ON(kprobe_disabled(&op->kp));
- if (arch_optimize_kprobe(op) < 0)
- op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED;
- list_del_init(&op->list);
- }
+ arch_optimize_kprobes(&optimizing_list);
mutex_unlock(&text_mutex);
put_online_cpus();
+ if (!list_empty(&optimizing_list))
+ schedule_delayed_work(&optimizing_work, OPTIMIZE_DELAY);
end:
mutex_unlock(&kprobe_mutex);
mutex_unlock(&module_mutex);
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists