This change does two things:

- it moves the get_online_cpus() call into generic code, with the aim of
  later providing some static_key ops that avoid it.

- as a side effect it inverts the lock order between cpu_hotplug_lock and
  jump_label_mutex.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: jbaron@akamai.com
Cc: bigeasy@linutronix.de
Cc: rostedt@goodmis.org
Link: http://lkml.kernel.org/r/20170418103422.590118425@infradead.org
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
---
 arch/mips/kernel/jump_label.c  |    2 --
 arch/sparc/kernel/jump_label.c |    2 --
 arch/tile/kernel/jump_label.c  |    2 --
 arch/x86/kernel/jump_label.c   |    2 --
 kernel/jump_label.c            |   14 ++++++++++++++
 5 files changed, 14 insertions(+), 8 deletions(-)

--- a/arch/mips/kernel/jump_label.c
+++ b/arch/mips/kernel/jump_label.c
@@ -58,7 +58,6 @@ void arch_jump_label_transform(struct ju
 		insn.word = 0; /* nop */
 	}
 
-	get_online_cpus();
 	mutex_lock(&text_mutex);
 	if (IS_ENABLED(CONFIG_CPU_MICROMIPS)) {
 		insn_p->halfword[0] = insn.word >> 16;
@@ -70,7 +69,6 @@ void arch_jump_label_transform(struct ju
 			   (unsigned long)insn_p + sizeof(*insn_p));
 
 	mutex_unlock(&text_mutex);
-	put_online_cpus();
 }
 
 #endif /* HAVE_JUMP_LABEL */
--- a/arch/sparc/kernel/jump_label.c
+++ b/arch/sparc/kernel/jump_label.c
@@ -41,12 +41,10 @@ void arch_jump_label_transform(struct ju
 		val = 0x01000000;
 	}
 
-	get_online_cpus();
 	mutex_lock(&text_mutex);
 	*insn = val;
 	flushi(insn);
 	mutex_unlock(&text_mutex);
-	put_online_cpus();
 }
 
 #endif
--- a/arch/tile/kernel/jump_label.c
+++ b/arch/tile/kernel/jump_label.c
@@ -45,14 +45,12 @@ static void __jump_label_transform(struc
 void arch_jump_label_transform(struct jump_entry *e,
 				enum jump_label_type type)
 {
-	get_online_cpus();
 	mutex_lock(&text_mutex);
 
 	__jump_label_transform(e, type);
 	flush_icache_range(e->code, e->code + sizeof(tilegx_bundle_bits));
 
 	mutex_unlock(&text_mutex);
-	put_online_cpus();
 }
 
 __init_or_module void arch_jump_label_transform_static(struct jump_entry *e,
--- a/arch/x86/kernel/jump_label.c
+++ b/arch/x86/kernel/jump_label.c
@@ -105,11 +105,9 @@ static void __jump_label_transform(struc
 void arch_jump_label_transform(struct jump_entry *entry,
 			       enum jump_label_type type)
 {
-	get_online_cpus();
 	mutex_lock(&text_mutex);
 	__jump_label_transform(entry, type, NULL, 0);
 	mutex_unlock(&text_mutex);
-	put_online_cpus();
 }
 
 static enum {
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -15,6 +15,7 @@
 #include <linux/static_key.h>
 #include <linux/jump_label_ratelimit.h>
 #include <linux/bug.h>
+#include <linux/cpu.h>
 
 #ifdef HAVE_JUMP_LABEL
 
@@ -124,6 +125,12 @@ void static_key_slow_inc(struct static_k
 			return;
 	}
 
+	/*
+	 * A number of architectures need to synchronize I$ across
+	 * the all CPUs, for that to be serialized against CPU hot-plug
+	 * we need to avoid CPUs coming online.
+	 */
+	get_online_cpus();
 	jump_label_lock();
 	if (atomic_read(&key->enabled) == 0) {
 		atomic_set(&key->enabled, -1);
@@ -133,6 +140,7 @@ void static_key_slow_inc(struct static_k
 		atomic_inc(&key->enabled);
 	}
 	jump_label_unlock();
+	put_online_cpus();
 }
 EXPORT_SYMBOL_GPL(static_key_slow_inc);
 
@@ -146,6 +154,7 @@ static void __static_key_slow_dec(struct
 	 * returns is unbalanced, because all other static_key_slow_inc()
 	 * instances block while the update is in progress.
 	 */
+	get_online_cpus();
 	if (!atomic_dec_and_mutex_lock(&key->enabled, &jump_label_mutex)) {
 		WARN(atomic_read(&key->enabled) < 0,
 		     "jump label: negative count!\n");
@@ -159,6 +168,7 @@ static void __static_key_slow_dec(struct
 		jump_label_update(key);
 	}
 	jump_label_unlock();
+	put_online_cpus();
 }
 
 static void jump_label_update_timeout(struct work_struct *work)
@@ -592,6 +602,10 @@ jump_label_module_notify(struct notifier
 
 	switch (val) {
 	case MODULE_STATE_COMING:
+		/*
+		 * XXX do we need get_online_cpus() ?  the module isn't
+		 * executable yet, so nothing should be looking at our code.
+		 */
 		jump_label_lock();
 		ret = jump_label_add_module(mod);
 		if (ret) {