Re: [PATCH] audit: speedup for syscalls when auditing is disabled

[Michael Neuling]

> > > I wonder if you could get much back, in terms of performance, by moving
> > > the
> > >          context->dummy = !audit_n_rules;
> > > line to the top and just returning if context->dummy == 1;
> > 
> > We get 668.09 cycles with this optimisation, so it comes down a bit, but
> > no where near if the auditing is disabled altogether.
> 
> Clean that patch up and send it.  Sounds like a win no matter what else
> we do.

ok...

audit: speedup audit_syscall_entry when there are zero rules

This creates a check at the start of audit_syscall_entry to see if there
are zero rules in the audit filter list.  If there are zero rules return
immediately.

This buys about ~10% on a null syscall on powerpc.

Signed-off-by: Michael Neuling <mikey@xxxxxxxxxxx>

diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 1b31c13..bc0872b 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -1579,6 +1579,9 @@ void audit_syscall_entry(int arch, int major,
 	if (unlikely(!context))
 		return;
 
+	context->dummy = !audit_n_rules;
+	if (context->dummy == 1)
+		return;
 	/*
 	 * This happens only on certain architectures that make system
 	 * calls in kernel_thread via the entry.S interface, instead of
@@ -1628,7 +1631,6 @@ void audit_syscall_entry(int arch, int major,
 	context->argv[3]    = a4;
 
 	state = context->state;
-	context->dummy = !audit_n_rules;
 	if (!context->dummy && state == AUDIT_BUILD_CONTEXT) {
 		context->prio = 0;
 		state = audit_filter_syscall(tsk, context, &audit_filter_list[AUDIT_FILTER_ENTRY]);

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/