x86: Introduce text_poke_smp_batch() for batch-code modifying

Introduce text_poke_smp_batch(). This function modifies several
text areas with one stop_machine() on SMP. Because calling
stop_machine() is heavy task, it is better to aggregate
text_poke requests.

( Note: I've talked with Rusty about this interface, and
  he would not like to expand stop_machine() interface, since
  it is not for generic use. )

Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com>
Cc: Jason Baron <jbaron@redhat.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Jan Beulich <jbeulich@novell.com>
Cc: 2nddept-manager@sdl.hitachi.co.jp
LKML-Reference: <20101203095422.2961.51217.stgit@ltc236.sdl.hitachi.co.jp>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

arch/x86/include/asm/alternative.h

@@ -180,8 +180,15 @@ extern void *text_poke_early(void *addr, const void *opcode, size_t len);
  * On the local CPU you need to be protected again NMI or MCE handlers seeing an
  * inconsistent instruction while you patch.
  */
+struct text_poke_param {
+	void *addr;
+	const void *opcode;
+	size_t len;
+};
+
 extern void *text_poke(void *addr, const void *opcode, size_t len);
 extern void *text_poke_smp(void *addr, const void *opcode, size_t len);
+extern void text_poke_smp_batch(struct text_poke_param *params, int n);
 
 #if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL)
 #define IDEAL_NOP_SIZE_5 5

arch/x86/kernel/alternative.c

@@ -591,17 +591,21 @@ static atomic_t stop_machine_first;
 static int wrote_text;
 
 struct text_poke_params {
-	void *addr;
-	const void *opcode;
-	size_t len;
+	struct text_poke_param *params;
+	int nparams;
 };
 
 static int __kprobes stop_machine_text_poke(void *data)
 {
 	struct text_poke_params *tpp = data;
+	struct text_poke_param *p;
+	int i;
 
 	if (atomic_dec_and_test(&stop_machine_first)) {
-		text_poke(tpp->addr, tpp->opcode, tpp->len);
+		for (i = 0; i < tpp->nparams; i++) {
+			p = &tpp->params[i];
+			text_poke(p->addr, p->opcode, p->len);
+		}
 		smp_wmb();	/* Make sure other cpus see that this has run */
 		wrote_text = 1;
 	} else {
@@ -610,8 +614,12 @@ static int __kprobes stop_machine_text_poke(void *data)
 		smp_mb();	/* Load wrote_text before following execution */
 	}
 
-	flush_icache_range((unsigned long)tpp->addr,
-			   (unsigned long)tpp->addr + tpp->len);
+	for (i = 0; i < tpp->nparams; i++) {
+		p = &tpp->params[i];
+		flush_icache_range((unsigned long)p->addr,
+				   (unsigned long)p->addr + p->len);
+	}
+
 	return 0;
 }
 
@@ -631,10 +639,13 @@ static int __kprobes stop_machine_text_poke(void *data)
 void *__kprobes text_poke_smp(void *addr, const void *opcode, size_t len)
 {
 	struct text_poke_params tpp;
+	struct text_poke_param p;
 
-	tpp.addr = addr;
-	tpp.opcode = opcode;
-	tpp.len = len;
+	p.addr = addr;
+	p.opcode = opcode;
+	p.len = len;
+	tpp.params = &p;
+	tpp.nparams = 1;
 	atomic_set(&stop_machine_first, 1);
 	wrote_text = 0;
 	/* Use __stop_machine() because the caller already got online_cpus. */
@@ -642,6 +653,26 @@ void *__kprobes text_poke_smp(void *addr, const void *opcode, size_t len)
 	return addr;
 }
 
+/**
+ * text_poke_smp_batch - Update instructions on a live kernel on SMP
+ * @params: an array of text_poke parameters
+ * @n: the number of elements in params.
+ *
+ * Modify multi-byte instruction by using stop_machine() on SMP. Since the
+ * stop_machine() is heavy task, it is better to aggregate text_poke requests
+ * and do it once if possible.
+ *
+ * Note: Must be called under get_online_cpus() and text_mutex.
+ */
+void __kprobes text_poke_smp_batch(struct text_poke_param *params, int n)
+{
+	struct text_poke_params tpp = {.params = params, .nparams = n};
+
+	atomic_set(&stop_machine_first, 1);
+	wrote_text = 0;
+	stop_machine(stop_machine_text_poke, (void *)&tpp, NULL);
+}
+
 #if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL)
 
 #ifdef CONFIG_X86_64