From mboxrd@z Thu Jan 1 00:00:00 1970 From: mst@redhat.com (Michael S. Tsirkin) Date: Wed, 22 May 2013 14:07:29 +0300 Subject: [PATCH v2 00/10] uaccess: better might_sleep/might_fault behavior In-Reply-To: <20130522101916.GM18810@twins.programming.kicks-ass.net> References: <201305221125.36284.arnd@arndb.de> <20130522101916.GM18810@twins.programming.kicks-ass.net> Message-ID: <20130522110729.GB5643@redhat.com> To: linux-arm-kernel@lists.infradead.org List-Id: linux-arm-kernel.lists.infradead.org On Wed, May 22, 2013 at 12:19:16PM +0200, Peter Zijlstra wrote: > On Wed, May 22, 2013 at 11:25:36AM +0200, Arnd Bergmann wrote: > > Calling might_fault() for every __get_user/__put_user is rather expensive > > because it turns what should be a single instruction (plus fixup) into an > > external function call. > > We could hide it all behind CONFIG_DEBUG_ATOMIC_SLEEP just like > might_sleep() is. I'm not sure there's a point to might_fault() when > might_sleep() is a NOP. The patch that you posted gets pretty close. E.g. I'm testing this now: +#define might_fault() do { \ + if (_might_fault()) \ + __might_sleep(__FILE__, __LINE__, 0); \ + might_resched(); \ +} while(0) So if might_sleep is a NOP, __might_sleep and might_resched are NOPs so compiler will optimize this all out. However, in a related thread, you pointed out that might_sleep is not a NOP if CONFIG_PREEMPT_VOLUNTARY is set, even without CONFIG_DEBUG_ATOMIC_SLEEP. Do you think we should drop the preemption point in might_fault? Only copy_XX_user? Only __copy_XXX_user ? -- MST