From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Google-Smtp-Source: AG47ELtXn3cJXCGXRPOGg2xpIKBKMdzqlQSz138MQ2Qh9VoD9RFrcMwAf3u2G9dEdqNDiSsDuCAX ARC-Seal: i=1; a=rsa-sha256; t=1520245576; cv=none; d=google.com; s=arc-20160816; b=Q6esvyV331KWEGQAEyHf2wqj0y4bJesO+CvK7m095VU7FSjYBndMToHQeEYHqQB8Jc kK7pao+algIi0QcEGEToCFftXVBHgUCYHv3kNLkr+y7bN3vKrYOPwpeIkDFsJl3UYUef B6qtRWcvAFy8ymvBUDGQZl+7Otn5/e6++SvPN/5fCzPvTyu6lsOSB4H7s1dRMuwi+XOr T3KbGsoBOU6VxSpg07l63xZ71nyF6No9hm04xBYsv9ixgSVkXWRPf13Y/VQFMjeNXECe m/QTT7KBMpME1srRITGYLxiTu3ZRNCzK1v4gp64Sxy/e4JULKYdPNgjCTe171xCCUhrx IV4w== 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=wbV5tAu0wTyAC9OBsjsZxEDpC5ifUQw0rFsnbh3Eu9o=; b=SiqUgFn3UZ16qUo61rDfUoAs2G+w+VIIO5ERllJhA1dzRsjIcWukL5mvQmhcimadnq hCpNpqyYVqN3s10a9zVdFjiAL0cB91YcoQKJAGY/rQRwU+jJaPhyo3trk3zn8HTtWadh sigi6rWz8Z81lyxGtUZPL5PoJe5chZmtrJC8RcP5SVOE1n0ssmu0lAM7UAzv7ZmHFjej xyy397d5i+QhF+5vFHGdrVeaHkw7E7Mql9iAQ6uXyuQULHLHiaHDZ7abgdQyofFhYEny 318PeMNOCqCCQDZtGI9hXonhyFf1e3cnX70Y7Ivvtp4qVHYb0nhQjQG5XWXpu37uNggM R1UQ== ARC-Authentication-Results: i=1; mx.google.com; dkim=pass (test mode) header.i=@8bytes.org header.s=mail-1 header.b=qVf7Rtk4; spf=pass (google.com: domain of joro@8bytes.org designates 2a01:238:4383:600:38bc:a715:4b6d:a889 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=qVf7Rtk4; spf=pass (google.com: domain of joro@8bytes.org designates 2a01:238:4383:600:38bc:a715:4b6d:a889 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 14/34] x86/entry/32: Add PTI cr3 switch to non-NMI entry/exit points Date: Mon, 5 Mar 2018 11:25:43 +0100 Message-Id: <1520245563-8444-15-git-send-email-joro@8bytes.org> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1520245563-8444-1-git-send-email-joro@8bytes.org> References: <1520245563-8444-1-git-send-email-joro@8bytes.org> X-getmail-retrieved-from-mailbox: INBOX X-GMAIL-THRID: =?utf-8?q?1594093025228329287?= X-GMAIL-MSGID: =?utf-8?q?1594093025228329287?= X-Mailing-List: linux-kernel@vger.kernel.org List-ID: From: Joerg Roedel Add unconditional cr3 switches between user and kernel cr3 to all non-NMI entry and exit points. Signed-off-by: Joerg Roedel --- arch/x86/entry/entry_32.S | 91 +++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 88 insertions(+), 3 deletions(-) diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 35379e5..8f78abc 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -328,6 +328,30 @@ #endif /* CONFIG_X86_ESPFIX32 */ .endm +/* Unconditionally switch to user cr3 */ +.macro SWITCH_TO_USER_CR3 scratch_reg:req + ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI + + movl %cr3, \scratch_reg + orl $PTI_SWITCH_MASK, \scratch_reg + movl \scratch_reg, %cr3 +.Lend_\@: +.endm + +/* Unconditionally switch to kernel cr3 */ +.macro SWITCH_TO_KERNEL_CR3 scratch_reg:req + ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI + movl %cr3, \scratch_reg + /* Test if we are already on kernel CR3 */ + testl $PTI_SWITCH_MASK, \scratch_reg + jz .Lend_\@ + andl $(~PTI_SWITCH_MASK), \scratch_reg + movl \scratch_reg, %cr3 + /* Return original CR3 in \scratch_reg */ + orl $PTI_SWITCH_MASK, \scratch_reg +.Lend_\@: +.endm + /* * Called with pt_regs fully populated and kernel segments loaded, @@ -341,11 +365,19 @@ */ #define CS_FROM_ENTRY_STACK (1 << 31) +#define CS_FROM_USER_CR3 (1 << 30) .macro SWITCH_TO_KERNEL_STACK ALTERNATIVE "", "jmp .Lend_\@", X86_FEATURE_XENPV + SWITCH_TO_KERNEL_CR3 scratch_reg=%eax + + /* + * %eax now contains the entry cr3 and we carry it forward in + * that register for the time this macro runs + */ + /* Are we on the entry stack? Bail out if not! */ movl PER_CPU_VAR(cpu_entry_area), %edi addl $CPU_ENTRY_AREA_entry_stack, %edi @@ -408,7 +440,8 @@ * but switch back to the entry-stack again when we approach * iret and return to the interrupted code-path. This usually * happens when we hit an exception while restoring user-space - * segment registers on the way back to user-space. + * segment registers on the way back to user-space or when the + * sysenter handler runs with eflags.tf set. * * When we switch to the task-stack here, we can't trust the * contents of the entry-stack anymore, as the exception handler @@ -425,6 +458,7 @@ * * %esi: Entry-Stack pointer (same as %esp) * %edi: Top of the task stack + * %eax: CR3 on kernel entry */ /* Calculate number of bytes on the entry stack in %ecx */ @@ -441,6 +475,14 @@ orl $CS_FROM_ENTRY_STACK, PT_CS(%esp) /* + * Test the cr3 used to enter the kernel and add a marker + * so that we can switch back to it before iret. + */ + testl $PTI_SWITCH_MASK, %eax + jz .Lcopy_pt_regs_\@ + orl $CS_FROM_USER_CR3, PT_CS(%esp) + + /* * %esi and %edi are unchanged, %ecx contains the number of * bytes to copy. The code at .Lcopy_pt_regs_\@ will allocate * the stack-frame on task-stack and copy everything over @@ -506,7 +548,7 @@ /* * This macro handles the case when we return to kernel-mode on the iret - * path and have to switch back to the entry stack. + * path and have to switch back to the entry stack and/or user-cr3 * * See the comments below the .Lentry_from_kernel_\@ label in the * SWITCH_TO_KERNEL_STACK macro for more details. @@ -552,6 +594,18 @@ /* Safe to switch to entry-stack now */ movl %ebx, %esp + /* + * We came from entry-stack and need to check if we also need to + * switch back to user cr3. + */ + testl $CS_FROM_USER_CR3, PT_CS(%esp) + jz .Lend_\@ + + /* Clear marker from stack-frame */ + andl $(~CS_FROM_USER_CR3), PT_CS(%esp) + + SWITCH_TO_USER_CR3 scratch_reg=%eax + .Lend_\@: .endm /* @@ -746,6 +800,18 @@ ENTRY(xen_sysenter_target) * 0(%ebp) arg6 */ ENTRY(entry_SYSENTER_32) + /* + * On entry-stack with all userspace-regs live - save and + * restore eflags and %eax to use it as scratch-reg for the cr3 + * switch. + */ + pushfl + pushl %eax + SWITCH_TO_KERNEL_CR3 scratch_reg=%eax + popl %eax + popfl + + /* Stack empty again, switch to task stack */ movl TSS_entry_stack(%esp), %esp .Lsysenter_past_esp: @@ -826,6 +892,9 @@ ENTRY(entry_SYSENTER_32) /* Switch to entry stack */ movl %eax, %esp + /* Now ready to switch the cr3 */ + SWITCH_TO_USER_CR3 scratch_reg=%eax + /* * Restore all flags except IF. (We restore IF separately because * STI gives a one-instruction window in which we won't be interrupted, @@ -906,7 +975,23 @@ restore_all: .Lrestore_all_notrace: CHECK_AND_APPLY_ESPFIX .Lrestore_nocheck: - RESTORE_REGS 4 # skip orig_eax/error_code + /* + * First restore user segments. This can cause exceptions, so we + * run it with kernel cr3. + */ + RESTORE_SEGMENTS + + /* + * Segments are restored - no more exceptions from here on except on + * iret, but that handled safely. + */ + SWITCH_TO_USER_CR3 scratch_reg=%eax + + /* Restore rest */ + RESTORE_INT_REGS + + /* Unwind stack to the iret frame */ + RESTORE_SKIP_SEGMENTS 4 # skip orig_eax/error_code .Lirq_return: INTERRUPT_RETURN -- 2.7.4