static keys: Introduce 'struct static_key', static_key_true()/false()…

… and static_key_slow_[inc|dec]()

So here's a boot tested patch on top of Jason's series that does
all the cleanups I talked about and turns jump labels into a
more intuitive to use facility. It should also address the
various misconceptions and confusions that surround jump labels.

Typical usage scenarios:

        #include <linux/static_key.h>

        struct static_key key = STATIC_KEY_INIT_TRUE;

        if (static_key_false(&key))
                do unlikely code
        else
                do likely code

Or:

        if (static_key_true(&key))
                do likely code
        else
                do unlikely code

The static key is modified via:

        static_key_slow_inc(&key);
        ...
        static_key_slow_dec(&key);

The 'slow' prefix makes it abundantly clear that this is an
expensive operation.

I've updated all in-kernel code to use this everywhere. Note
that I (intentionally) have not pushed through the rename
blindly through to the lowest levels: the actual jump-label
patching arch facility should be named like that, so we want to
decouple jump labels from the static-key facility a bit.

On non-jump-label enabled architectures static keys default to
likely()/unlikely() branches.

Signed-off-by: Ingo Molnar <mingo@elte.hu>
Acked-by: Jason Baron <jbaron@redhat.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: a.p.zijlstra@chello.nl
Cc: mathieu.desnoyers@efficios.com
Cc: davem@davemloft.net
Cc: ddaney.cavm@gmail.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20120222085809.GA26397@elte.hu
Signed-off-by: Ingo Molnar <mingo@elte.hu>

arch/Kconfig

@@ -47,18 +47,29 @@ config KPROBES
 	  If in doubt, say "N".
 
 config JUMP_LABEL
-       bool "Optimize trace point call sites"
+       bool "Optimize very unlikely/likely branches"
        depends on HAVE_ARCH_JUMP_LABEL
        help
+         This option enables a transparent branch optimization that
+	 makes certain almost-always-true or almost-always-false branch
+	 conditions even cheaper to execute within the kernel.
+
+	 Certain performance-sensitive kernel code, such as trace points,
+	 scheduler functionality, networking code and KVM have such
+	 branches and include support for this optimization technique.
+
          If it is detected that the compiler has support for "asm goto",
-	 the kernel will compile trace point locations with just a
-	 nop instruction. When trace points are enabled, the nop will
-	 be converted to a jump to the trace function. This technique
-	 lowers overhead and stress on the branch prediction of the
-	 processor.
-
-	 On i386, options added to the compiler flags may increase
-	 the size of the kernel slightly.
+	 the kernel will compile such branches with just a nop
+	 instruction. When the condition flag is toggled to true, the
+	 nop will be converted to a jump instruction to execute the
+	 conditional block of instructions.
+
+	 This technique lowers overhead and stress on the branch prediction
+	 of the processor and generally makes the kernel faster. The update
+	 of the condition is slower, but those are always very rare.
+
+	 ( On 32-bit x86, the necessary options added to the compiler
+	   flags may increase the size of the kernel slightly. )
 
 config OPTPROBES
 	def_bool y

arch/ia64/include/asm/paravirt.h

@@ -281,9 +281,9 @@ paravirt_init_missing_ticks_accounting(int cpu)
 		pv_time_ops.init_missing_ticks_accounting(cpu);
 }
 
-struct jump_label_key;
-extern struct jump_label_key paravirt_steal_enabled;
-extern struct jump_label_key paravirt_steal_rq_enabled;
+struct static_key;
+extern struct static_key paravirt_steal_enabled;
+extern struct static_key paravirt_steal_rq_enabled;
 
 static inline int
 paravirt_do_steal_accounting(unsigned long *new_itm)

arch/ia64/kernel/paravirt.c

@@ -634,8 +634,8 @@ struct pv_irq_ops pv_irq_ops = {
  * pv_time_ops
  * time operations
  */
-struct jump_label_key paravirt_steal_enabled;
-struct jump_label_key paravirt_steal_rq_enabled;
+struct static_key paravirt_steal_enabled;
+struct static_key paravirt_steal_rq_enabled;
 
 static int
 ia64_native_do_steal_accounting(unsigned long *new_itm)

arch/mips/include/asm/jump_label.h

@@ -20,7 +20,7 @@
 #define WORD_INSN ".word"
 #endif
 
-static __always_inline bool arch_static_branch(struct jump_label_key *key)
+static __always_inline bool arch_static_branch(struct static_key *key)
 {
 	asm goto("1:\tnop\n\t"
 		"nop\n\t"

arch/powerpc/include/asm/jump_label.h

@@ -17,7 +17,7 @@
 #define JUMP_ENTRY_TYPE		stringify_in_c(FTR_ENTRY_LONG)
 #define JUMP_LABEL_NOP_SIZE	4
 
-static __always_inline bool arch_static_branch(struct jump_label_key *key)
+static __always_inline bool arch_static_branch(struct static_key *key)
 {
 	asm goto("1:\n\t"
 		 "nop\n\t"

arch/s390/include/asm/jump_label.h

@@ -13,7 +13,7 @@
 #define ASM_ALIGN ".balign 4"
 #endif
 
-static __always_inline bool arch_static_branch(struct jump_label_key *key)
+static __always_inline bool arch_static_branch(struct static_key *key)
 {
 	asm goto("0:	brcl 0,0\n"
 		".pushsection __jump_table, \"aw\"\n"

arch/sparc/include/asm/jump_label.h

@@ -7,7 +7,7 @@
 
 #define JUMP_LABEL_NOP_SIZE 4
 
-static __always_inline bool arch_static_branch(struct jump_label_key *key)
+static __always_inline bool arch_static_branch(struct static_key *key)
 {
 		asm goto("1:\n\t"
 			 "nop\n\t"

arch/x86/include/asm/jump_label.h

@@ -9,12 +9,12 @@
 
 #define JUMP_LABEL_NOP_SIZE 5
 
-#define JUMP_LABEL_INITIAL_NOP ".byte 0xe9 \n\t .long 0\n\t"
+#define STATIC_KEY_INITIAL_NOP ".byte 0xe9 \n\t .long 0\n\t"
 
-static __always_inline bool arch_static_branch(struct jump_label_key *key)
+static __always_inline bool arch_static_branch(struct static_key *key)
 {
 	asm goto("1:"
-		JUMP_LABEL_INITIAL_NOP
+		STATIC_KEY_INITIAL_NOP
 		".pushsection __jump_table,  \"aw\" \n\t"
 		_ASM_ALIGN "\n\t"
 		_ASM_PTR "1b, %l[l_yes], %c0 \n\t"

arch/x86/include/asm/paravirt.h

@@ -230,9 +230,9 @@ static inline unsigned long long paravirt_sched_clock(void)
 	return PVOP_CALL0(unsigned long long, pv_time_ops.sched_clock);
 }
 
-struct jump_label_key;
-extern struct jump_label_key paravirt_steal_enabled;
-extern struct jump_label_key paravirt_steal_rq_enabled;
+struct static_key;
+extern struct static_key paravirt_steal_enabled;
+extern struct static_key paravirt_steal_rq_enabled;
 
 static inline u64 paravirt_steal_clock(int cpu)
 {

arch/x86/kernel/kvm.c

@@ -438,9 +438,9 @@ void __init kvm_guest_init(void)
 static __init int activate_jump_labels(void)
 {
 	if (has_steal_clock) {
-		jump_label_inc(&paravirt_steal_enabled);
+		static_key_slow_inc(&paravirt_steal_enabled);
 		if (steal_acc)
-			jump_label_inc(&paravirt_steal_rq_enabled);
+			static_key_slow_inc(&paravirt_steal_rq_enabled);
 	}
 
 	return 0;

arch/x86/kernel/paravirt.c

@@ -202,8 +202,8 @@ static void native_flush_tlb_single(unsigned long addr)
 	__native_flush_tlb_single(addr);
 }
 
-struct jump_label_key paravirt_steal_enabled;
-struct jump_label_key paravirt_steal_rq_enabled;
+struct static_key paravirt_steal_enabled;
+struct static_key paravirt_steal_rq_enabled;
 
 static u64 native_steal_clock(int cpu)
 {

arch/x86/kvm/mmu_audit.c

@@ -234,7 +234,7 @@ static void audit_vcpu_spte(struct kvm_vcpu *vcpu)
 }
 
 static bool mmu_audit;
-static struct jump_label_key mmu_audit_key;
+static struct static_key mmu_audit_key;
 
 static void __kvm_mmu_audit(struct kvm_vcpu *vcpu, int point)
 {
@@ -250,7 +250,7 @@ static void __kvm_mmu_audit(struct kvm_vcpu *vcpu, int point)
 
 static inline void kvm_mmu_audit(struct kvm_vcpu *vcpu, int point)
 {
-	if (static_branch((&mmu_audit_key)))
+	if (static_key_false((&mmu_audit_key)))
 		__kvm_mmu_audit(vcpu, point);
 }
 
@@ -259,7 +259,7 @@ static void mmu_audit_enable(void)
 	if (mmu_audit)
 		return;
 
-	jump_label_inc(&mmu_audit_key);
+	static_key_slow_inc(&mmu_audit_key);
 	mmu_audit = true;
 }
 
@@ -268,7 +268,7 @@ static void mmu_audit_disable(void)
 	if (!mmu_audit)
 		return;
 
-	jump_label_dec(&mmu_audit_key);
+	static_key_slow_dec(&mmu_audit_key);
 	mmu_audit = false;
 }