From 459fbe00693449fade2d1bc802791b081c94edcf Mon Sep 17 00:00:00 2001 From: John Ogness Date: Mon, 30 Jan 2017 09:41:21 +0100 Subject: [PATCH] x86/mm/cpa: Avoid wbinvd() for PREEMPT Although wbinvd() is faster than flushing many individual pages, it blocks the memory bus for "long" periods of time (>100us), thus directly causing unusually large latencies on all CPUs, regardless of any CPU isolation features that may be active. This is an unpriviledged operatation as it is exposed to user space via the graphics subsystem. For 1024 pages, flushing those pages individually can take up to 2200us, but the task remains fully preemptible during that time. Signed-off-by: John Ogness Acked-by: Peter Zijlstra (Intel) Cc: Sebastian Siewior Cc: linux-rt-users Signed-off-by: Thomas Gleixner --- arch/x86/mm/pageattr.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 5a287e523eab..28d42130243c 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -214,7 +214,20 @@ static void cpa_flush_array(unsigned long *start, int numpages, int cache, int in_flags, struct page **pages) { unsigned int i, level; +#ifdef CONFIG_PREEMPT + /* + * Avoid wbinvd() because it causes latencies on all CPUs, + * regardless of any CPU isolation that may be in effect. + * + * This should be extended for CAT enabled systems independent of + * PREEMPT because wbinvd() does not respect the CAT partitions and + * this is exposed to unpriviledged users through the graphics + * subsystem. + */ + unsigned long do_wbinvd = 0; +#else unsigned long do_wbinvd = cache && numpages >= 1024; /* 4M threshold */ +#endif BUG_ON(irqs_disabled()); -- 2.20.1