jump label: Introduce static_branch() interface

Introduce:

static __always_inline bool static_branch(struct jump_label_key *key);

instead of the old JUMP_LABEL(key, label) macro.

In this way, jump labels become really easy to use:

Define:

        struct jump_label_key jump_key;

Can be used as:

        if (static_branch(&jump_key))
                do unlikely code

enable/disale via:

        jump_label_inc(&jump_key);
        jump_label_dec(&jump_key);

that's it!

For the jump labels disabled case, the static_branch() becomes an
atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(),
atomic_dec() operations. We show testing results for this change below.

Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct.

Since we now require a 'struct jump_label_key *key', we can store a pointer into
the jump table addresses. In this way, we can enable/disable jump labels, in
basically constant time. This change allows us to completely remove the previous
hashtable scheme. Thanks to Peter Zijlstra for this re-write.

Testing:

I ran a series of 'tbench 20' runs 5 times (with reboots) for 3
configurations, where tracepoints were disabled.

jump label configured in
avg: 815.6

jump label *not* configured in (using atomic reads)
avg: 800.1

jump label *not* configured in (regular reads)
avg: 803.4
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20110316212947.GA8792@redhat.com>
Signed-off-by: Jason Baron <jbaron@redhat.com>
Suggested-by: H. Peter Anvin <hpa@linux.intel.com>
Tested-by: David Daney <ddaney@caviumnetworks.com>
Acked-by: Ralf Baechle <ralf@linux-mips.org>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

arch/mips/include/asm/jump_label.h

@@ -20,16 +20,18 @@
 #define WORD_INSN ".word"
 #endif
 
-#define JUMP_LABEL(key, label)						\
-	do {								\
-		asm goto("1:\tnop\n\t"					\
-			"nop\n\t"					\
-			".pushsection __jump_table,  \"a\"\n\t"		\
-			WORD_INSN " 1b, %l[" #label "], %0\n\t"		\
-			".popsection\n\t"				\
-			: :  "i" (key) :  : label);			\
-	} while (0)
-
+static __always_inline bool arch_static_branch(struct jump_label_key *key)
+{
+	asm goto("1:\tnop\n\t"
+		"nop\n\t"
+		".pushsection __jump_table,  \"aw\"\n\t"
+		WORD_INSN " 1b, %l[l_yes], %0\n\t"
+		".popsection\n\t"
+		: :  "i" (key) : : l_yes);
+	return false;
+l_yes:
+	return true;
+}
 
 #endif /* __KERNEL__ */
 

arch/sparc/include/asm/jump_label.h

@@ -7,17 +7,20 @@
 
 #define JUMP_LABEL_NOP_SIZE 4
 
-#define JUMP_LABEL(key, label)					\
-	do {							\
-		asm goto("1:\n\t"				\
-			 "nop\n\t"				\
-			 "nop\n\t"				\
-			 ".pushsection __jump_table,  \"a\"\n\t"\
-			 ".align 4\n\t"				\
-			 ".word 1b, %l[" #label "], %c0\n\t"	\
-			 ".popsection \n\t"			\
-			 : :  "i" (key) :  : label);\
-	} while (0)
+static __always_inline bool arch_static_branch(struct jump_label_key *key)
+{
+		asm goto("1:\n\t"
+			 "nop\n\t"
+			 "nop\n\t"
+			 ".pushsection __jump_table,  \"aw\"\n\t"
+			 ".align 4\n\t"
+			 ".word 1b, %l[l_yes], %c0\n\t"
+			 ".popsection \n\t"
+			 : :  "i" (key) : : l_yes);
+	return false;
+l_yes:
+	return true;
+}
 
 #endif /* __KERNEL__ */
 

arch/x86/include/asm/alternative.h

@@ -4,7 +4,6 @@
 #include <linux/types.h>
 #include <linux/stddef.h>
 #include <linux/stringify.h>
-#include <linux/jump_label.h>
 #include <asm/asm.h>
 
 /*
@@ -191,7 +190,7 @@ 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)
+#if defined(CONFIG_DYNAMIC_FTRACE) || defined(CONFIG_JUMP_LABEL)
 #define IDEAL_NOP_SIZE_5 5
 extern unsigned char ideal_nop5[IDEAL_NOP_SIZE_5];
 extern void arch_init_ideal_nop5(void);

arch/x86/include/asm/jump_label.h

@@ -5,20 +5,24 @@
 
 #include <linux/types.h>
 #include <asm/nops.h>
+#include <asm/asm.h>
 
 #define JUMP_LABEL_NOP_SIZE 5
 
-# define JUMP_LABEL_INITIAL_NOP ".byte 0xe9 \n\t .long 0\n\t"
-
-# define JUMP_LABEL(key, label)					\
-	do {							\
-		asm goto("1:"					\
-			JUMP_LABEL_INITIAL_NOP			\
-			".pushsection __jump_table,  \"aw\" \n\t"\
-			_ASM_PTR "1b, %l[" #label "], %c0 \n\t" \
-			".popsection \n\t"			\
-			: :  "i" (key) :  : label);		\
-	} while (0)
+#define JUMP_LABEL_INITIAL_NOP ".byte 0xe9 \n\t .long 0\n\t"
+
+static __always_inline bool arch_static_branch(struct jump_label_key *key)
+{
+	asm goto("1:"
+		JUMP_LABEL_INITIAL_NOP
+		".pushsection __jump_table,  \"aw\" \n\t"
+		_ASM_PTR "1b, %l[l_yes], %c0 \n\t"
+		".popsection \n\t"
+		: :  "i" (key) : : l_yes);
+	return false;
+l_yes:
+	return true;
+}
 
 #endif /* __KERNEL__ */
 

arch/x86/kernel/alternative.c

@@ -679,7 +679,7 @@ void __kprobes text_poke_smp_batch(struct text_poke_param *params, int n)
 	__stop_machine(stop_machine_text_poke, (void *)&tpp, NULL);
 }
 
-#if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL)
+#if defined(CONFIG_DYNAMIC_FTRACE) || defined(CONFIG_JUMP_LABEL)
 
 #ifdef CONFIG_X86_64
 unsigned char ideal_nop5[5] = { 0x66, 0x66, 0x66, 0x66, 0x90 };

arch/x86/kernel/module.c

@@ -24,6 +24,7 @@
 #include <linux/bug.h>
 #include <linux/mm.h>
 #include <linux/gfp.h>
+#include <linux/jump_label.h>
 
 #include <asm/system.h>
 #include <asm/page.h>

include/asm-generic/vmlinux.lds.h

@@ -170,6 +170,10 @@
 	STRUCT_ALIGN();							\
 	*(__tracepoints)						\
 	/* implement dynamic printk debug */				\
+	. = ALIGN(8);                                                   \
+	VMLINUX_SYMBOL(__start___jump_table) = .;                       \
+	*(__jump_table)                                                 \
+	VMLINUX_SYMBOL(__stop___jump_table) = .;                        \
 	. = ALIGN(8);							\
 	VMLINUX_SYMBOL(__start___verbose) = .;                          \
 	*(__verbose)                                                    \
@@ -228,8 +232,6 @@
 									\
 	BUG_TABLE							\
 									\
-	JUMP_TABLE							\
-									\
 	/* PCI quirks */						\
 	.pci_fixup        : AT(ADDR(.pci_fixup) - LOAD_OFFSET) {	\
 		VMLINUX_SYMBOL(__start_pci_fixups_early) = .;		\
@@ -589,14 +591,6 @@
 #define BUG_TABLE
 #endif
 
-#define JUMP_TABLE							\
-	. = ALIGN(8);							\
-	__jump_table : AT(ADDR(__jump_table) - LOAD_OFFSET) {		\
-		VMLINUX_SYMBOL(__start___jump_table) = .;		\
-		*(__jump_table)						\
-		VMLINUX_SYMBOL(__stop___jump_table) = .;		\
-	}
-
 #ifdef CONFIG_PM_TRACE
 #define TRACEDATA							\
 	. = ALIGN(4);							\

include/linux/dynamic_debug.h

 #ifndef _DYNAMIC_DEBUG_H
 #define _DYNAMIC_DEBUG_H
 
-#include <linux/jump_label.h>
-
 /* dynamic_printk_enabled, and dynamic_printk_enabled2 are bitmasks in which
  * bit n is set to 1 if any modname hashes into the bucket n, 0 otherwise. They
  * use independent hash functions, to reduce the chance of false positives.

include/linux/jump_label.h

 #ifndef _LINUX_JUMP_LABEL_H
 #define _LINUX_JUMP_LABEL_H
 
+#include <linux/types.h>
+#include <linux/compiler.h>
+
 #if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_JUMP_LABEL)
+
+struct jump_label_key {
+	atomic_t enabled;
+	struct jump_entry *entries;
+#ifdef CONFIG_MODULES
+	struct jump_label_mod *next;
+#endif
+};
+
 # include <asm/jump_label.h>
 # define HAVE_JUMP_LABEL
 #endif
 
 enum jump_label_type {
+	JUMP_LABEL_DISABLE = 0,
 	JUMP_LABEL_ENABLE,
-	JUMP_LABEL_DISABLE
 };
 
 struct module;
 
 #ifdef HAVE_JUMP_LABEL
 
+#ifdef CONFIG_MODULES
+#define JUMP_LABEL_INIT {{ 0 }, NULL, NULL}
+#else
+#define JUMP_LABEL_INIT {{ 0 }, NULL}
+#endif
+
+static __always_inline bool static_branch(struct jump_label_key *key)
+{
+	return arch_static_branch(key);
+}
+
 extern struct jump_entry __start___jump_table[];
 extern struct jump_entry __stop___jump_table[];
 
@@ -23,37 +46,37 @@ extern void jump_label_unlock(void);
 extern void arch_jump_label_transform(struct jump_entry *entry,
 				 enum jump_label_type type);
 extern void arch_jump_label_text_poke_early(jump_label_t addr);
-extern void jump_label_update(unsigned long key, enum jump_label_type type);
-extern void jump_label_apply_nops(struct module *mod);
 extern int jump_label_text_reserved(void *start, void *end);
+extern void jump_label_inc(struct jump_label_key *key);
+extern void jump_label_dec(struct jump_label_key *key);
+extern bool jump_label_enabled(struct jump_label_key *key);
+extern void jump_label_apply_nops(struct module *mod);
 
-#define jump_label_enable(key) \
-	jump_label_update((unsigned long)key, JUMP_LABEL_ENABLE);
+#else
 
-#define jump_label_disable(key) \
-	jump_label_update((unsigned long)key, JUMP_LABEL_DISABLE);
+#include <asm/atomic.h>
 
-#else
+#define JUMP_LABEL_INIT {ATOMIC_INIT(0)}
 
-#define JUMP_LABEL(key, label)			\
-do {						\
-	if (unlikely(*key))			\
-		goto label;			\
-} while (0)
+struct jump_label_key {
+	atomic_t enabled;
+};
 
-#define jump_label_enable(cond_var)	\
-do {					\
-       *(cond_var) = 1;			\
-} while (0)
+static __always_inline bool static_branch(struct jump_label_key *key)
+{
+	if (unlikely(atomic_read(&key->enabled)))
+		return true;
+	return false;
+}
 
-#define jump_label_disable(cond_var)	\
-do {					\
-       *(cond_var) = 0;			\
-} while (0)
+static inline void jump_label_inc(struct jump_label_key *key)
+{
+	atomic_inc(&key->enabled);
+}
 
-static inline int jump_label_apply_nops(struct module *mod)
+static inline void jump_label_dec(struct jump_label_key *key)
 {
-	return 0;
+	atomic_dec(&key->enabled);
 }
 
 static inline int jump_label_text_reserved(void *start, void *end)
@@ -64,16 +87,16 @@ static inline int jump_label_text_reserved(void *start, void *end)
 static inline void jump_label_lock(void) {}
 static inline void jump_label_unlock(void) {}
 
-#endif
+static inline bool jump_label_enabled(struct jump_label_key *key)
+{
+	return !!atomic_read(&key->enabled);
+}
 
-#define COND_STMT(key, stmt)					\
-do {								\
-	__label__ jl_enabled;					\
-	JUMP_LABEL(key, jl_enabled);				\
-	if (0) {						\
-jl_enabled:							\
-		stmt;						\
-	}							\
-} while (0)
+static inline int jump_label_apply_nops(struct module *mod)
+{
+	return 0;
+}
+
+#endif
 
 #endif

include/linux/jump_label_ref.h

-#ifndef _LINUX_JUMP_LABEL_REF_H
-#define _LINUX_JUMP_LABEL_REF_H
-
-#include <linux/jump_label.h>
-#include <asm/atomic.h>
-
-#ifdef HAVE_JUMP_LABEL
-
-static inline void jump_label_inc(atomic_t *key)
-{
-	if (atomic_add_return(1, key) == 1)
-		jump_label_enable(key);
-}
-
-static inline void jump_label_dec(atomic_t *key)
-{
-	if (atomic_dec_and_test(key))
-		jump_label_disable(key);
-}
-
-#else /* !HAVE_JUMP_LABEL */
-
-static inline void jump_label_inc(atomic_t *key)
-{
-	atomic_inc(key);
-}
-
-static inline void jump_label_dec(atomic_t *key)
-{
-	atomic_dec(key);
-}
-
-#undef JUMP_LABEL
-#define JUMP_LABEL(key, label)						\
-do {									\
-	if (unlikely(__builtin_choose_expr(				\
-	      __builtin_types_compatible_p(typeof(key), atomic_t *),	\
-	      atomic_read((atomic_t *)(key)), *(key))))			\
-		goto label;						\
-} while (0)
-
-#endif /* HAVE_JUMP_LABEL */
-
-#endif /* _LINUX_JUMP_LABEL_REF_H */

include/linux/perf_event.h

@@ -505,7 +505,7 @@ struct perf_guest_info_callbacks {
 #include <linux/ftrace.h>
 #include <linux/cpu.h>
 #include <linux/irq_work.h>
-#include <linux/jump_label_ref.h>
+#include <linux/jump_label.h>
 #include <asm/atomic.h>
 #include <asm/local.h>
 
@@ -1034,7 +1034,7 @@ static inline int is_software_event(struct perf_event *event)
 	return event->pmu->task_ctx_nr == perf_sw_context;
 }
 
-extern atomic_t perf_swevent_enabled[PERF_COUNT_SW_MAX];
+extern struct jump_label_key perf_swevent_enabled[PERF_COUNT_SW_MAX];
 
 extern void __perf_sw_event(u32, u64, int, struct pt_regs *, u64);
 
@@ -1063,22 +1063,21 @@ perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr)
 {
 	struct pt_regs hot_regs;
 
-	JUMP_LABEL(&perf_swevent_enabled[event_id], have_event);
-	return;
-
-have_event:
-	if (!regs) {
-		perf_fetch_caller_regs(&hot_regs);
-		regs = &hot_regs;
+	if (static_branch(&perf_swevent_enabled[event_id])) {
+		if (!regs) {
+			perf_fetch_caller_regs(&hot_regs);
+			regs = &hot_regs;
+		}
+		__perf_sw_event(event_id, nr, nmi, regs, addr);
 	}
-	__perf_sw_event(event_id, nr, nmi, regs, addr);
 }
 
-extern atomic_t perf_sched_events;
+extern struct jump_label_key perf_sched_events;
 
 static inline void perf_event_task_sched_in(struct task_struct *task)
 {
-	COND_STMT(&perf_sched_events, __perf_event_task_sched_in(task));
+	if (static_branch(&perf_sched_events))
+		__perf_event_task_sched_in(task);
 }
 
 static inline
@@ -1086,7 +1085,8 @@ void perf_event_task_sched_out(struct task_struct *task, struct task_struct *nex
 {
 	perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, NULL, 0);
 
-	COND_STMT(&perf_sched_events, __perf_event_task_sched_out(task, next));
+	if (static_branch(&perf_sched_events))
+		__perf_event_task_sched_out(task, next);
 }
 
 extern void perf_event_mmap(struct vm_area_struct *vma);

include/linux/tracepoint.h

@@ -29,7 +29,7 @@ struct tracepoint_func {
 
 struct tracepoint {
 	const char *name;		/* Tracepoint name */
-	int state;			/* State. */
+	struct jump_label_key key;
 	void (*regfunc)(void);
 	void (*unregfunc)(void);
 	struct tracepoint_func __rcu *funcs;
@@ -146,9 +146,7 @@ void tracepoint_update_probe_range(struct tracepoint * const *begin,
 	extern struct tracepoint __tracepoint_##name;			\
 	static inline void trace_##name(proto)				\
 	{								\
-		JUMP_LABEL(&__tracepoint_##name.state, do_trace);	\
-		return;							\
-do_trace:								\
+		if (static_branch(&__tracepoint_##name.key))		\
 			__DO_TRACE(&__tracepoint_##name,		\
 				TP_PROTO(data_proto),			\
 				TP_ARGS(data_args),			\
@@ -176,14 +174,14 @@ do_trace:								\
  * structures, so we create an array of pointers that will be used for iteration
  * on the tracepoints.
  */
-#define DEFINE_TRACE_FN(name, reg, unreg)				\
-	static const char __tpstrtab_##name[]				\
-	__attribute__((section("__tracepoints_strings"))) = #name;	\
-	struct tracepoint __tracepoint_##name				\
-	__attribute__((section("__tracepoints"))) =			\
-		{ __tpstrtab_##name, 0, reg, unreg, NULL };		\
-	static struct tracepoint * const __tracepoint_ptr_##name __used	\
-	__attribute__((section("__tracepoints_ptrs"))) =		\
+#define DEFINE_TRACE_FN(name, reg, unreg)				 \
+	static const char __tpstrtab_##name[]				 \
+	__attribute__((section("__tracepoints_strings"))) = #name;	 \
+	struct tracepoint __tracepoint_##name				 \
+	__attribute__((section("__tracepoints"))) =			 \
+		{ __tpstrtab_##name, JUMP_LABEL_INIT, reg, unreg, NULL };\
+	static struct tracepoint * const __tracepoint_ptr_##name __used	 \
+	__attribute__((section("__tracepoints_ptrs"))) =		 \
 		&__tracepoint_##name;
 
 #define DEFINE_TRACE(name)						\

kernel/perf_event.c

@@ -125,7 +125,7 @@ enum event_type_t {
  * perf_sched_events : >0 events exist
  * perf_cgroup_events: >0 per-cpu cgroup events exist on this cpu
  */
-atomic_t perf_sched_events __read_mostly;
+struct jump_label_key perf_sched_events __read_mostly;
 static DEFINE_PER_CPU(atomic_t, perf_cgroup_events);
 
 static atomic_t nr_mmap_events __read_mostly;
@@ -5417,7 +5417,7 @@ static int swevent_hlist_get(struct perf_event *event)
 	return err;
 }
 
-atomic_t perf_swevent_enabled[PERF_COUNT_SW_MAX];
+struct jump_label_key perf_swevent_enabled[PERF_COUNT_SW_MAX];
 
 static void sw_perf_event_destroy(struct perf_event *event)
 {

kernel/tracepoint.c

@@ -251,9 +251,9 @@ static void set_tracepoint(struct tracepoint_entry **entry,
 {
 	WARN_ON(strcmp((*entry)->name, elem->name) != 0);
 
-	if (elem->regfunc && !elem->state && active)
+	if (elem->regfunc && !jump_label_enabled(&elem->key) && active)
 		elem->regfunc();
-	else if (elem->unregfunc && elem->state && !active)
+	else if (elem->unregfunc && jump_label_enabled(&elem->key) && !active)
 		elem->unregfunc();
 
 	/*
@@ -264,13 +264,10 @@ static void set_tracepoint(struct tracepoint_entry **entry,
 	 * is used.
 	 */
 	rcu_assign_pointer(elem->funcs, (*entry)->funcs);
-	if (!elem->state && active) {
-		jump_label_enable(&elem->state);
-		elem->state = active;
-	} else if (elem->state && !active) {
-		jump_label_disable(&elem->state);
-		elem->state = active;
-	}
+	if (active && !jump_label_enabled(&elem->key))
+		jump_label_inc(&elem->key);
+	else if (!active && jump_label_enabled(&elem->key))
+		jump_label_dec(&elem->key);
 }
 
 /*
@@ -281,13 +278,11 @@ static void set_tracepoint(struct tracepoint_entry **entry,
  */
 static void disable_tracepoint(struct tracepoint *elem)
 {
-	if (elem->unregfunc && elem->state)
+	if (elem->unregfunc && jump_label_enabled(&elem->key))
 		elem->unregfunc();
 
-	if (elem->state) {
-		jump_label_disable(&elem->state);
-		elem->state = 0;
-	}
+	if (jump_label_enabled(&elem->key))
+		jump_label_dec(&elem->key);
 	rcu_assign_pointer(elem->funcs, NULL);
 }