[PATCH v2 3/3] x86_64,entry: Remove the syscall exit audit and schedule optimizations

From: Andy Lutomirski <luto@amacapital.net>
To: x86@kernel.org, linux-kernel@vger.kernel.org,
	Linus Torvalds <torvalds@linux-foundation.org>
Cc: "Frédéric Weisbecker" <fweisbec@gmail.com>,
	"Oleg Nesterov" <oleg@redhat.com>,
	"kvm list" <kvm@vger.kernel.org>, "Borislav Petkov" <bp@suse.de>,
	"Rik van Riel" <riel@redhat.com>,
	"Andy Lutomirski" <luto@amacapital.net>
Subject: [PATCH v2 3/3] x86_64,entry: Remove the syscall exit audit and schedule optimizations
Date: Fri, 16 Jan 2015 16:19:29 -0800	[thread overview]
Message-ID: <22f2aa4a0361707a5cfb1de9d45260b39965dead.1421453410.git.luto@amacapital.net> (raw)
In-Reply-To: <cover.1421453410.git.luto@amacapital.net>
In-Reply-To: <cover.1421453410.git.luto@amacapital.net>

We used to optimize rescheduling and audit on syscall exit.  Now
that the full slow path is reasonably fast, remove these
optimizations.  Syscall exit auditing is now handled exclusively by
syscall_trace_leave.

This adds something like 10ns to the previously optimized paths on
my computer, presumably due mostly to SAVE_REST / RESTORE_REST.

I think that we should eventually replace both the syscall and
non-paranoid interrupt exit slow paths with a pair of C functions
along the lines of the syscall entry hooks.

Acked-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Andy Lutomirski <luto@amacapital.net>
---
 arch/x86/kernel/entry_64.S | 52 +++++-----------------------------------------
 1 file changed, 5 insertions(+), 47 deletions(-)

diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index eeab4cf8b2c9..db13655c3a2a 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -361,15 +361,12 @@ system_call_fastpath:
  * Has incomplete stack frame and undefined top of stack.
  */
 ret_from_sys_call:
-	movl $_TIF_ALLWORK_MASK,%edi
-	/* edi:	flagmask */
-sysret_check:
+	testl $_TIF_ALLWORK_MASK,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
+	jnz int_ret_from_sys_call_fixup	/* Go the the slow path */
+
 	LOCKDEP_SYS_EXIT
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
-	movl TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET),%edx
-	andl %edi,%edx
-	jnz  sysret_careful
 	CFI_REMEMBER_STATE
 	/*
 	 * sysretq will re-enable interrupts:
@@ -383,49 +380,10 @@ sysret_check:
 	USERGS_SYSRET64
 
 	CFI_RESTORE_STATE
-	/* Handle reschedules */
-	/* edx:	work, edi: workmask */
-sysret_careful:
-	bt $TIF_NEED_RESCHED,%edx
-	jnc sysret_signal
-	TRACE_IRQS_ON
-	ENABLE_INTERRUPTS(CLBR_NONE)
-	pushq_cfi %rdi
-	SCHEDULE_USER
-	popq_cfi %rdi
-	jmp sysret_check
 
-	/* Handle a signal */
-sysret_signal:
-	TRACE_IRQS_ON
-	ENABLE_INTERRUPTS(CLBR_NONE)
-#ifdef CONFIG_AUDITSYSCALL
-	bt $TIF_SYSCALL_AUDIT,%edx
-	jc sysret_audit
-#endif
-	/*
-	 * We have a signal, or exit tracing or single-step.
-	 * These all wind up with the iret return path anyway,
-	 * so just join that path right now.
-	 */
+int_ret_from_sys_call_fixup:
 	FIXUP_TOP_OF_STACK %r11, -ARGOFFSET
-	jmp int_check_syscall_exit_work
-
-#ifdef CONFIG_AUDITSYSCALL
-	/*
-	 * Return fast path for syscall audit.  Call __audit_syscall_exit()
-	 * directly and then jump back to the fast path with TIF_SYSCALL_AUDIT
-	 * masked off.
-	 */
-sysret_audit:
-	movq RAX-ARGOFFSET(%rsp),%rsi	/* second arg, syscall return value */
-	cmpq $-MAX_ERRNO,%rsi	/* is it < -MAX_ERRNO? */
-	setbe %al		/* 1 if so, 0 if not */
-	movzbl %al,%edi		/* zero-extend that into %edi */
-	call __audit_syscall_exit
-	movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),%edi
-	jmp sysret_check
-#endif	/* CONFIG_AUDITSYSCALL */
+	jmp int_ret_from_sys_call
 
 	/* Do syscall tracing */
 tracesys:
-- 
2.1.0

