From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752388AbdIWNCQ (ORCPT ); Sat, 23 Sep 2017 09:02:16 -0400 Received: from mail-wr0-f196.google.com ([209.85.128.196]:35535 "EHLO mail-wr0-f196.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752154AbdIWNBO (ORCPT ); Sat, 23 Sep 2017 09:01:14 -0400 X-Google-Smtp-Source: AOwi7QDszVXRfeC4gvGNbPXcjUc/OgYzMDsmN2JGeRboeWB+jbSA1a/P0PMV85DLo7197eGQL4GZ5w== From: Ingo Molnar To: linux-kernel@vger.kernel.org Cc: Andrew Morton , Eric Biggers , Andy Lutomirski , Borislav Petkov , Dave Hansen , Fenghua Yu , "H . Peter Anvin" , Linus Torvalds , Oleg Nesterov , Peter Zijlstra , Rik van Riel , Thomas Gleixner , Yu-cheng Yu Subject: [PATCH 30/33] x86/fpu: Fix stale comments about lazy FPU logic Date: Sat, 23 Sep 2017 15:00:13 +0200 Message-Id: <20170923130016.21448-31-mingo@kernel.org> X-Mailer: git-send-email 2.11.0 In-Reply-To: <20170923130016.21448-1-mingo@kernel.org> References: <20170923130016.21448-1-mingo@kernel.org> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org We don't do any lazy restore anymore, what we have are two pieces of optimization: - no-FPU tasks that don't save/restore the FPU context (kernel threads are such) - cached FPU registers maintained via the fpu->last_cpu field. This means that if an FPU task context switches to a non-FPU task then we can maintain the FPU registers as an in-FPU copies (cache), and skip the restoration of them once we switch back to the original FPU-using task. Update all the comments that still referred to old 'lazy' and 'unlazy' concepts. Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Eric Biggers Cc: Fenghua Yu Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Thomas Gleixner Signed-off-by: Ingo Molnar --- arch/x86/kernel/fpu/core.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index d770f9a6d4e1..4acfc0ebc160 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -205,9 +205,6 @@ int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu) /* * Save current FPU registers directly into the child * FPU context, without any memory-to-memory copying. - * In lazy mode, if the FPU context isn't loaded into - * fpregs, CR0.TS will be set and do_device_not_available - * will load the FPU context. * * We have to do all this with preemption disabled, * mostly because of the FNSAVE case, because in that @@ -274,13 +271,13 @@ void fpu__activate_fpstate_read(struct fpu *fpu) /* * This function must be called before we write a task's fpstate. * - * If the task has used the FPU before then unlazy it. + * If the task has used the FPU before then invalidate any cached FPU registers. * If the task has not used the FPU before then initialize its fpstate. * * After this function call, after registers in the fpstate are * modified and the child task has woken up, the child task will * restore the modified FPU state from the modified context. If we - * didn't clear its lazy status here then the lazy in-registers + * didn't clear its cached status here then the cached in-registers * state pending on its former CPU could be restored, corrupting * the modifications. */ @@ -293,7 +290,7 @@ void fpu__activate_fpstate_write(struct fpu *fpu) WARN_ON_FPU(fpu == ¤t->thread.fpu); if (fpu->initialized) { - /* Invalidate any lazy state: */ + /* Invalidate any cached state: */ __fpu_invalidate_fpregs_state(fpu); } else { fpstate_init(&fpu->state); -- 2.11.0