tick/nohz: Evaluate the CPU expression after the static key

When tick_nohz_full_cpu() is called with smp_processor_id(), the latter
is unconditionally evaluated whether the static key is on or off. It is
not necessary in the off-case though, so make sure the cpu expression
is executed at the last moment.

Illustrate with the following test function:

	int tick_nohz_test(void)
	{
		return tick_nohz_full_cpu(smp_processor_id());
	}

The resulting code before was:

	mov    %gs:0x7eea92d1(%rip),%eax   # smp_processor_id() fetch
	nopl   0x0(%rax,%rax,1)
	xor    %eax,%eax
	retq
	cmpb   $0x0,0x29d393a(%rip)        # <tick_nohz_full_running>
	je     tick_nohz_test+0x29         # jump to below eax clear
	mov    %eax,%eax
	bt     %rax,0x29d3936(%rip)        # <tick_nohz_full_mask>
	setb   %al
	movzbl %al,%eax
	retq
	xor    %eax,%eax
	retq

Now it becomes:

	nopl   0x0(%rax,%rax,1)
	xor    %eax,%eax
	retq
	cmpb   $0x0,0x29d3871(%rip)        # <tick_nohz_full_running>
	je     tick_nohz_test+0x29         # jump to below eax clear
	mov    %gs:0x7eea91f0(%rip),%eax   # smp_processor_id() fetch, after static key
	mov    %eax,%eax
	bt     %rax,0x29d3866(%rip)        # <tick_nohz_full_mask>
	setb   %al
	movzbl %al,%eax
	retq
	xor    %eax,%eax
	retq

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20210512232924.150322-2-frederic@kernel.org

diff --git a/include/linux/tick.h b/include/linux/tick.h
index 7340613c7eff7ad791634c76ae2ecd547f711c45..2258984a0e8a79b57e83a0738df971c8110e9fa8 100644 (file)
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -185,13 +185,17 @@ static inline bool tick_nohz_full_enabled(void)
        return tick_nohz_full_running;
 }
 
-static inline bool tick_nohz_full_cpu(int cpu)
-{
-       if (!tick_nohz_full_enabled())
-               return false;
-
-       return cpumask_test_cpu(cpu, tick_nohz_full_mask);
-}
+/*
+ * Check if a CPU is part of the nohz_full subset. Arrange for evaluating
+ * the cpu expression (typically smp_processor_id()) _after_ the static
+ * key.
+ */
+#define tick_nohz_full_cpu(_cpu) ({                                    \
+       bool __ret = false;                                             \
+       if (tick_nohz_full_enabled())                                   \
+               __ret = cpumask_test_cpu((_cpu), tick_nohz_full_mask);  \
+       __ret;                                                          \
+})
 
 static inline void tick_nohz_full_add_cpus_to(struct cpumask *mask)
 {