From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Google-Smtp-Source: AG47ELtPQbcq4y0z+EbkbOwsq4l5JYR+ERrbq4O/5VuKF7YqdGFK+Ld68JrFMG0tvF7K48ka8ugI ARC-Seal: i=1; a=rsa-sha256; t=1521228604; cv=none; d=google.com; s=arc-20160816; b=XL0n2xjKhOYU4vrHGJUYSUTnFxSW+pEYNMeKWF5BD1Pm4i0210YM/Vz04oNBdsNSjA +5q0SiOMzmIZFUWflp/s+AFGQcREs4Lsj5R7yucglcqLz5tN7S1V8OdHollbnbz96FB3 VUrnBSUgCfNbw0TEDBZh5iCBRfR1CGKhVV7ZAMgOnabBX6P8owr/4uzHwA/qIcblt61b Sek5FV/gUqdafjdanVHWk44mkDcg/tWqMqLlB9RL+o6A3JBiTroTab8hyKKADBltBJkC fZBHHyFcxaUUfz7wBERrIZJ63FexuhVwY8vcjdXbi1oFl3I994HrZdct0Bqo7IkNQFg+ Zibg== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=references:in-reply-to:message-id:date:subject:cc:to:from :dkim-signature:arc-authentication-results; bh=YezuAPxlJMP42Enbh8mmngV2fQl2fjWxXRax15qN5kA=; b=jfFoyZ8pv81Sur+ZmNPEYHgnegkk3zgS6pvmVt61jtUdnAExetOEehLajkJeAjjVee 6Avp5enaIQTlJ2ZMdg1ByPHrscR28QOt5AkAKVOJMTei/obLT7hzKJCFN0aUOiRCggZu 1wXn/rlXSSizaX7xKXGQmjTS5NGmuClFkJ395tVyk4ZwrE6kZLMWQiHEtfexqXfDR2wB WE3AsQSeTL4Vz06E9Oj/1HO/4XtEoJIIl8dst2XeAd+2urwGF581jS3Fkbeq+UOJeoSF wsRK6evK+FSq0+Vbi9MLDzesS/+TRNBG0iY2BepY5Y3m4D0w8C0vTgE07TIpLF7/RqPI zLZA== ARC-Authentication-Results: i=1; mx.google.com; dkim=pass (test mode) header.i=@8bytes.org header.s=mail-1 header.b=dNmKKgyu; spf=pass (google.com: domain of joro@8bytes.org designates 81.169.241.247 as permitted sender) smtp.mailfrom=joro@8bytes.org; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=8bytes.org Authentication-Results: mx.google.com; dkim=pass (test mode) header.i=@8bytes.org header.s=mail-1 header.b=dNmKKgyu; spf=pass (google.com: domain of joro@8bytes.org designates 81.169.241.247 as permitted sender) smtp.mailfrom=joro@8bytes.org; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=8bytes.org 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 , jroedel@suse.de, joro@8bytes.org Subject: [PATCH 08/35] x86/entry/32: Leave the kernel via trampoline stack Date: Fri, 16 Mar 2018 20:29:26 +0100 Message-Id: <1521228593-3820-9-git-send-email-joro@8bytes.org> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1521228593-3820-1-git-send-email-joro@8bytes.org> References: <1521228593-3820-1-git-send-email-joro@8bytes.org> X-getmail-retrieved-from-mailbox: INBOX X-GMAIL-THRID: =?utf-8?q?1595123805543481336?= X-GMAIL-MSGID: =?utf-8?q?1595123805543481336?= X-Mailing-List: linux-kernel@vger.kernel.org List-ID: 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 88aefb9..73cde25 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 */ @@ -587,25 +641,45 @@ 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 */ btr $X86_EFLAGS_IF_BIT, (%esp) popfl + popl %eax /* * Return back to the vDSO, which will pop ecx and edx. @@ -674,6 +748,7 @@ 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