jump_label: Reorder hotplug lock and jump_label_lock

The conversion of the hotplug locking to a percpu rwsem unearthed lock
ordering issues all over the place.

The jump_label code has two issues:

 1) Nested get_online_cpus() invocations

 2) Ordering problems vs. the cpus rwsem and the jump_label_mutex

To cure these, the following lock order has been established;

   cpus_rwsem -> jump_label_lock -> text_mutex

Even if not all architectures need protection against CPU hotplug, taking
cpus_rwsem before jump_label_lock is now mandatory in code pathes which
actually modify code and therefor need text_mutex protection.

Move the get_online_cpus() invocations into the core jump label code and
establish the proper lock order where required.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Ingo Molnar <mingo@kernel.org>
Acked-by: "David S. Miller" <davem@davemloft.net>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Chris Metcalf <cmetcalf@mellanox.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sebastian Siewior <bigeasy@linutronix.de>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Jason Baron <jbaron@akamai.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Link: http://lkml.kernel.org/r/20170524081549.025830817@linutronix.de

arch/mips/kernel/jump_label.c

@@ -58,7 +58,6 @@ void arch_jump_label_transform(struct jump_entry *e,
 		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 jump_entry *e,
 			   (unsigned long)insn_p + sizeof(*insn_p));
 
 	mutex_unlock(&text_mutex);
-	put_online_cpus();
 }
 
 #endif /* HAVE_JUMP_LABEL */

arch/sparc/kernel/jump_label.c

@@ -41,12 +41,10 @@ void arch_jump_label_transform(struct jump_entry *entry,
 		val = 0x01000000;
 	}
 
-	get_online_cpus();
 	mutex_lock(&text_mutex);
 	*insn = val;
 	flushi(insn);
 	mutex_unlock(&text_mutex);
-	put_online_cpus();
 }
 
 #endif

arch/tile/kernel/jump_label.c

@@ -45,14 +45,12 @@ static void __jump_label_transform(struct jump_entry *e,
 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,

arch/x86/kernel/jump_label.c

@@ -105,11 +105,9 @@ static void __jump_label_transform(struct jump_entry *entry,
 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 {

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 +125,7 @@ void static_key_slow_inc(struct static_key *key)
 			return;
 	}
 
+	cpus_read_lock();
 	jump_label_lock();
 	if (atomic_read(&key->enabled) == 0) {
 		atomic_set(&key->enabled, -1);
@@ -133,12 +135,14 @@ void static_key_slow_inc(struct static_key *key)
 		atomic_inc(&key->enabled);
 	}
 	jump_label_unlock();
+	cpus_read_unlock();
 }
 EXPORT_SYMBOL_GPL(static_key_slow_inc);
 
 static void __static_key_slow_dec(struct static_key *key,
 		unsigned long rate_limit, struct delayed_work *work)
 {
+	cpus_read_lock();
 	/*
 	 * The negative count check is valid even when a negative
 	 * key->enabled is in use by static_key_slow_inc(); a
@@ -149,6 +153,7 @@ static void __static_key_slow_dec(struct static_key *key,
 	if (!atomic_dec_and_mutex_lock(&key->enabled, &jump_label_mutex)) {
 		WARN(atomic_read(&key->enabled) < 0,
 		     "jump label: negative count!\n");
+		cpus_read_unlock();
 		return;
 	}
 
@@ -159,6 +164,7 @@ static void __static_key_slow_dec(struct static_key *key,
 		jump_label_update(key);
 	}
 	jump_label_unlock();
+	cpus_read_unlock();
 }
 
 static void jump_label_update_timeout(struct work_struct *work)
@@ -334,6 +340,7 @@ void __init jump_label_init(void)
 	if (static_key_initialized)
 		return;
 
+	cpus_read_lock();
 	jump_label_lock();
 	jump_label_sort_entries(iter_start, iter_stop);
 
@@ -353,6 +360,7 @@ void __init jump_label_init(void)
 	}
 	static_key_initialized = true;
 	jump_label_unlock();
+	cpus_read_unlock();
 }
 
 #ifdef CONFIG_MODULES
@@ -590,28 +598,28 @@ jump_label_module_notify(struct notifier_block *self, unsigned long val,
 	struct module *mod = data;
 	int ret = 0;
 
+	cpus_read_lock();
+	jump_label_lock();
+
 	switch (val) {
 	case MODULE_STATE_COMING:
-		jump_label_lock();
 		ret = jump_label_add_module(mod);
 		if (ret) {
 			WARN(1, "Failed to allocatote memory: jump_label may not work properly.\n");
 			jump_label_del_module(mod);
 		}
-		jump_label_unlock();
 		break;
 	case MODULE_STATE_GOING:
-		jump_label_lock();
 		jump_label_del_module(mod);
-		jump_label_unlock();
 		break;
 	case MODULE_STATE_LIVE:
-		jump_label_lock();
 		jump_label_invalidate_module_init(mod);
-		jump_label_unlock();
 		break;
 	}
 
+	jump_label_unlock();
+	cpus_read_unlock();
+
 	return notifier_from_errno(ret);
 }