Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Frederic Weisbecker <frederic@kernel.org>
To:     Peter Zijlstra <peterz@infradead.org>,
        Thomas Gleixner <tglx@linutronix.de>
Cc:     LKML <linux-kernel@vger.kernel.org>,
        "Rafael J . Wysocki" <rafael.j.wysocki@intel.com>,
        Yunfeng Ye <yeyunfeng@huawei.com>,
        Frederic Weisbecker <frederic@kernel.org>,
        Marcelo Tosatti <mtosatti@redhat.com>
Subject: [PATCH 1/8] tick/nohz: Evaluate the CPU expression after the static key
Date:   Thu, 22 Apr 2021 14:01:51 +0200
Message-Id: <20210422120158.33629-2-frederic@kernel.org>
In-Reply-To: <20210422120158.33629-1-frederic@kernel.org>
References: <20210422120158.33629-1-frederic@kernel.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: Peter Zijlstra <peterz@infradead.org>

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

Not-Yet-Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Yunfeng Ye <yeyunfeng@huawei.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
---
 include/linux/tick.h | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)

diff --git a/include/linux/tick.h b/include/linux/tick.h
index 7340613c7eff..2258984a0e8a 100644
--- 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)
 {
-- 
2.25.1