From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-2.6 required=3.0 tests=DKIM_SIGNED, HEADER_FROM_DIFFERENT_DOMAINS,MAILING_LIST_MULTI,SPF_PASS,T_DKIM_INVALID, URIBL_BLOCKED,USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 51A03C5CFEB for ; Wed, 11 Jul 2018 11:33:00 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id 07513208FA for ; Wed, 11 Jul 2018 11:33:00 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=fail reason="signature verification failed" (2048-bit key) header.d=8bytes.org header.i=@8bytes.org header.b="Kqc+hg5D" DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 07513208FA Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=8bytes.org Authentication-Results: mail.kernel.org; spf=none smtp.mailfrom=linux-kernel-owner@vger.kernel.org Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1732920AbeGKLeE (ORCPT ); Wed, 11 Jul 2018 07:34:04 -0400 Received: from 8bytes.org ([81.169.241.247]:37666 "EHLO theia.8bytes.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1732848AbeGKLeC (ORCPT ); Wed, 11 Jul 2018 07:34:02 -0400 Received: by theia.8bytes.org (Postfix, from userid 1000) id 66F09767; Wed, 11 Jul 2018 13:30:00 +0200 (CEST) DKIM-Signature: v=1; a=rsa-sha256; c=simple/simple; d=8bytes.org; s=mail-1; t=1531308601; bh=oYPgi3NksNzxfLZ6vmyXiBxDzFkNoDJf1JAzwjtUYjs=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=Kqc+hg5DiIjFzt8Y6OUZn1RtJE0T8OpBQaSwJm1BHW/eLT6KejO20Zre2tk0nQoKQ PKxIDiJZSzY7RrcQkCDWGk3yxZrnIgdArQddH7HXlZnzZhU3edmL2hGRK6bJyK/8CF Wt9PiAT6CQKXQcyo7vUbjLH0Ku8VDx3fz2MDFj+G80BoIZWc5UnXhyLe3l3lAFYjdU nYDb7hhcyn5gKZEb0szceUy/Qd+sJOpzB+2bXCeegT6fLSi/Tj+GHe6HNQa8jt87ng h6ZUflD3BHmp92F0fog8QMzoJMI7QSYsDhqHsW3/16NymRYbruQyC5Ms/XeRwt2Z3Z lmZFEvFhEMB1Q== From: Joerg Roedel To: Thomas Gleixner , Ingo Molnar , "H . Peter Anvin" Cc: x86@kernel.org, linux-kernel@vger.kernel.org, linux-mm@kvack.org, Linus Torvalds , Andy Lutomirski , Dave Hansen , Josh Poimboeuf , Juergen Gross , Peter Zijlstra , Borislav Petkov , Jiri Kosina , Boris Ostrovsky , Brian Gerst , David Laight , Denys Vlasenko , Eduardo Valentin , Greg KH , Will Deacon , aliguori@amazon.com, daniel.gruss@iaik.tugraz.at, hughd@google.com, keescook@google.com, Andrea Arcangeli , Waiman Long , Pavel Machek , "David H . Gutteridge" , jroedel@suse.de, joro@8bytes.org Subject: [PATCH 08/39] x86/entry/32: Leave the kernel via trampoline stack Date: Wed, 11 Jul 2018 13:29:15 +0200 Message-Id: <1531308586-29340-9-git-send-email-joro@8bytes.org> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1531308586-29340-1-git-send-email-joro@8bytes.org> References: <1531308586-29340-1-git-send-email-joro@8bytes.org> Sender: linux-kernel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org From: Joerg Roedel Switch back to the trampoline stack before returning to userspace. Signed-off-by: Joerg Roedel --- arch/x86/entry/entry_32.S | 79 +++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 77 insertions(+), 2 deletions(-) diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 528db7d..357b82b 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -347,6 +347,60 @@ .endm /* + * Switch back from the kernel stack to the entry stack. + * + * The %esp register must point to pt_regs on the task stack. It will + * first calculate the size of the stack-frame to copy, depending on + * whether we return to VM86 mode or not. With that it uses 'rep movsl' + * to copy the contents of the stack over to the entry stack. + * + * We must be very careful here, as we can't trust the contents of the + * task-stack once we switched to the entry-stack. When an NMI happens + * while on the entry-stack, the NMI handler will switch back to the top + * of the task stack, overwriting our stack-frame we are about to copy. + * Therefore we switch the stack only after everything is copied over. + */ +.macro SWITCH_TO_ENTRY_STACK + + ALTERNATIVE "", "jmp .Lend_\@", X86_FEATURE_XENPV + + /* Bytes to copy */ + movl $PTREGS_SIZE, %ecx + +#ifdef CONFIG_VM86 + testl $(X86_EFLAGS_VM), PT_EFLAGS(%esp) + jz .Lcopy_pt_regs_\@ + + /* Additional 4 registers to copy when returning to VM86 mode */ + addl $(4 * 4), %ecx + +.Lcopy_pt_regs_\@: +#endif + + /* Initialize source and destination for movsl */ + movl PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %edi + subl %ecx, %edi + movl %esp, %esi + + /* Save future stack pointer in %ebx */ + movl %edi, %ebx + + /* Copy over the stack-frame */ + shrl $2, %ecx + cld + rep movsl + + /* + * Switch to entry-stack - needs to happen after everything is + * copied because the NMI handler will overwrite the task-stack + * when on entry-stack + */ + movl %ebx, %esp + +.Lend_\@: +.endm + +/* * %eax: prev task * %edx: next task */ @@ -586,25 +640,45 @@ ENTRY(entry_SYSENTER_32) /* Opportunistic SYSEXIT */ TRACE_IRQS_ON /* User mode traces as IRQs on. */ + + /* + * Setup entry stack - we keep the pointer in %eax and do the + * switch after almost all user-state is restored. + */ + + /* Load entry stack pointer and allocate frame for eflags/eax */ + movl PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %eax + subl $(2*4), %eax + + /* Copy eflags and eax to entry stack */ + movl PT_EFLAGS(%esp), %edi + movl PT_EAX(%esp), %esi + movl %edi, (%eax) + movl %esi, 4(%eax) + + /* Restore user registers and segments */ movl PT_EIP(%esp), %edx /* pt_regs->ip */ movl PT_OLDESP(%esp), %ecx /* pt_regs->sp */ 1: mov PT_FS(%esp), %fs PTGS_TO_GS + popl %ebx /* pt_regs->bx */ addl $2*4, %esp /* skip pt_regs->cx and pt_regs->dx */ popl %esi /* pt_regs->si */ popl %edi /* pt_regs->di */ popl %ebp /* pt_regs->bp */ - popl %eax /* pt_regs->ax */ + + /* Switch to entry stack */ + movl %eax, %esp /* * Restore all flags except IF. (We restore IF separately because * STI gives a one-instruction window in which we won't be interrupted, * whereas POPF does not.) */ - addl $PT_EFLAGS-PT_DS, %esp /* point esp at pt_regs->flags */ btrl $X86_EFLAGS_IF_BIT, (%esp) popfl + popl %eax /* * Return back to the vDSO, which will pop ecx and edx. @@ -673,6 +747,7 @@ ENTRY(entry_INT80_32) restore_all: TRACE_IRQS_IRET + SWITCH_TO_ENTRY_STACK .Lrestore_all_notrace: CHECK_AND_APPLY_ESPFIX .Lrestore_nocheck: -- 2.7.4