From 33c52129f45e06d9ce23e1a3d50bf9fd6770748b Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Mon, 5 Oct 2015 17:48:19 -0700 Subject: [PATCH] x86/entry: Force inlining of 32-bit syscall code On systems that support fast syscalls, we only really care about the performance of the fast syscall path. Forcibly inline it and add a likely annotation. This saves 4-6 cycles. Signed-off-by: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Link: http://lkml.kernel.org/r/8472036ff1f4b426b4c4c3e3d0b3bf5264407c0c.1444091585.git.luto@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/entry/common.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 03aacd188458..d5eee851071c 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -324,9 +324,11 @@ __visible void syscall_return_slowpath(struct pt_regs *regs) #if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) /* * Does a 32-bit syscall. Called with IRQs on and does all entry and - * exit work and returns with IRQs off. + * exit work and returns with IRQs off. This function is extremely hot + * in workloads that use it, and it's usually called from + * do_fast_syscall_32, so forcibly inline it to improve performance. */ -static void do_syscall_32_irqs_on(struct pt_regs *regs) +static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs) { struct thread_info *ti = pt_regs_to_thread_info(regs); unsigned int nr = (unsigned int)regs->orig_ax; @@ -345,7 +347,7 @@ static void do_syscall_32_irqs_on(struct pt_regs *regs) nr = syscall_trace_enter(regs); } - if (nr < IA32_NR_syscalls) { + if (likely(nr < IA32_NR_syscalls)) { /* * It's possible that a 32-bit syscall implementation * takes a 64-bit parameter but nonetheless assumes that