Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1947570AbbEBUnF (ORCPT ); Sat, 2 May 2015 16:43:05 -0400 Received: from mail-ob0-f177.google.com ([209.85.214.177]:35540 "EHLO mail-ob0-f177.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S964802AbbEBUm7 (ORCPT ); Sat, 2 May 2015 16:42:59 -0400 MIME-Version: 1.0 In-Reply-To: <20150427151946.GA28094@redhat.com> References: <20150427144931.GA25690@redhat.com> <1430147441-9820-1-git-send-email-bobbypowers@gmail.com> <20150427151946.GA28094@redhat.com> Date: Sat, 2 May 2015 16:42:59 -0400 Message-ID: Subject: Re: [PATCH v2] x86/fpu: always restore_xinit_state() when use_eager_cpu() From: Bobby Powers To: Oleg Nesterov , Ingo Molnar Cc: Kernel development list , x86@kernel.org, Andi Kleen , Borislav Petkov , Andy Lutomirski , Dave Hansen , Fenghua Yu , Linus Torvalds , Pekka Riikonen , Quentin Casasnovas , Rik van Riel , Suresh Siddha Content-Type: text/plain; charset=UTF-8 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 3189 Lines: 87 Hello, Oleg Nesterov wrote: > Thanks! Dave gave this his: Tested-By: Dave Hansen over under v1 of this patch: https://lkml.kernel.org/g/5543C277.9070208@intel.com Anything else anyone sees, or anyone in particular I have to poke at to get this in? Ingo? yours, Bobby On Mon, Apr 27, 2015 at 11:19 AM, Oleg Nesterov wrote: > Thanks! > > On 04/27, Bobby Powers wrote: >> >> v2: switch used_math() -> tsk_used_math(tsk) to consistently use the >> grabbed tsk instead of current, like in the rest of flush_thread(). >> >> Oleg's commit f893959b ("x86/fpu: Don't abuse drop_init_fpu() in >> flush_thread()") removed drop_init_fpu() usage from flush_thread. >> This seems to break things for me - the Go 1.4 test suite fails all >> over the place with floating point comparision errors (offending >> commit found through bisection). >> >> The functional change was that flush_thread after f893959b only calls >> restore_init_xstate when both use_eager_fpu() and !used_math() are >> true. drop_init_fpu (now fpu_reset_state) calls restore_init_xstate() >> regardless of whether current used_math() - apply the same logic here. >> >> Fixes: f893959b ("x86/fpu: Don't abuse drop_init_fpu() in flush_thread()") >> Signed-off-by: Bobby Powers >> Acked-by: Oleg Nesterov >> Cc: Andi Kleen >> Cc: Borislav Petkov >> Cc: Ingo Molnar >> Cc: Andy Lutomirski >> Cc: Dave Hansen >> Cc: Fenghua Yu >> Cc: Linus Torvalds >> Cc: Pekka Riikonen >> Cc: Quentin Casasnovas >> Cc: Rik van Riel >> Cc: Suresh Siddha >> --- >> arch/x86/kernel/process.c | 12 +++++++----- >> 1 file changed, 7 insertions(+), 5 deletions(-) >> >> diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c >> index 8213da6..1a6fcf8 100644 >> --- a/arch/x86/kernel/process.c >> +++ b/arch/x86/kernel/process.c >> @@ -156,11 +156,13 @@ void flush_thread(void) >> /* FPU state will be reallocated lazily at the first use. */ >> drop_fpu(tsk); >> free_thread_xstate(tsk); >> - } else if (!used_math()) { >> - /* kthread execs. TODO: cleanup this horror. */ >> - if (WARN_ON(init_fpu(tsk))) >> - force_sig(SIGKILL, tsk); >> - user_fpu_begin(); >> + } else { >> + if (!tsk_used_math(tsk)) { >> + /* kthread execs. TODO: cleanup this horror. */ >> + if (WARN_ON(init_fpu(tsk))) >> + force_sig(SIGKILL, tsk); >> + user_fpu_begin(); >> + } >> restore_init_xstate(); >> } >> } >> -- >> 2.3.6 >> > -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/