linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jan Kiszka <jan.kiszka@siemens.com>
To: Joerg Roedel <joro@8bytes.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	Ingo Molnar <mingo@kernel.org>, "H . Peter Anvin" <hpa@zytor.com>
Cc: x86@kernel.org, linux-kernel@vger.kernel.org, linux-mm@kvack.org,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Andy Lutomirski <luto@kernel.org>,
	Dave Hansen <dave.hansen@intel.com>,
	Josh Poimboeuf <jpoimboe@redhat.com>,
	Juergen Gross <jgross@suse.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Borislav Petkov <bp@alien8.de>, Jiri Kosina <jkosina@suse.cz>,
	Boris Ostrovsky <boris.ostrovsky@oracle.com>,
	Brian Gerst <brgerst@gmail.com>,
	David Laight <David.Laight@aculab.com>,
	Denys Vlasenko <dvlasenk@redhat.com>,
	Eduardo Valentin <eduval@amazon.com>,
	Greg KH <gregkh@linuxfoundation.org>,
	Will Deacon <will.deacon@arm.com>,
	aliguori@amazon.com, daniel.gruss@iaik.tugraz.at,
	hughd@google.com, keescook@google.com,
	Andrea Arcangeli <aarcange@redhat.com>
Subject: Re: [PATCH 10/39] x86/entry/32: Handle Entry from Kernel-Mode on Entry-Stack
Date: Fri, 12 Oct 2018 20:29:47 +0200	[thread overview]
Message-ID: <97421241-2bc4-c3f1-4128-95b3e8a230d1@siemens.com> (raw)
In-Reply-To: <1531906876-13451-11-git-send-email-joro@8bytes.org>

[-- Attachment #1: Type: text/plain, Size: 6753 bytes --]

On 18.07.18 11:40, Joerg Roedel wrote:
> From: Joerg Roedel <jroedel@suse.de>
> 
> It can happen that we enter the kernel from kernel-mode and
> on the entry-stack. The most common way this happens is when
> we get an exception while loading the user-space segment
> registers on the kernel-to-userspace exit path.
> 
> The segment loading needs to be done after the entry-stack
> switch, because the stack-switch needs kernel %fs for
> per_cpu access.
> 
> When this happens, we need to make sure that we leave the
> kernel with the entry-stack again, so that the interrupted
> code-path runs on the right stack when switching to the
> user-cr3.
> 
> We do this by detecting this condition on kernel-entry by
> checking CS.RPL and %esp, and if it happens, we copy over
> the complete content of the entry stack to the task-stack.
> This needs to be done because once we enter the exception
> handlers we might be scheduled out or even migrated to a
> different CPU, so that we can't rely on the entry-stack
> contents. We also leave a marker in the stack-frame to
> detect this condition on the exit path.
> 
> On the exit path the copy is reversed, we copy all of the
> remaining task-stack back to the entry-stack and switch
> to it.
> 
> Signed-off-by: Joerg Roedel <jroedel@suse.de>
> ---
>   arch/x86/entry/entry_32.S | 116 +++++++++++++++++++++++++++++++++++++++++++++-
>   1 file changed, 115 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
> index 7635925..9d6eceb 100644
> --- a/arch/x86/entry/entry_32.S
> +++ b/arch/x86/entry/entry_32.S
> @@ -294,6 +294,9 @@
>    * copied there. So allocate the stack-frame on the task-stack and
>    * switch to it before we do any copying.
>    */
> +
> +#define CS_FROM_ENTRY_STACK	(1 << 31)
> +
>   .macro SWITCH_TO_KERNEL_STACK
>   
>   	ALTERNATIVE     "", "jmp .Lend_\@", X86_FEATURE_XENPV
> @@ -316,6 +319,16 @@
>   	/* Load top of task-stack into %edi */
>   	movl	TSS_entry2task_stack(%edi), %edi
>   
> +	/*
> +	 * Clear unused upper bits of the dword containing the word-sized CS
> +	 * slot in pt_regs in case hardware didn't clear it for us.
> +	 */
> +	andl	$(0x0000ffff), PT_CS(%esp)
> +
> +	/* Special case - entry from kernel mode via entry stack */
> +	testl	$SEGMENT_RPL_MASK, PT_CS(%esp)
> +	jz	.Lentry_from_kernel_\@
> +
>   	/* Bytes to copy */
>   	movl	$PTREGS_SIZE, %ecx
>   
> @@ -329,8 +342,8 @@
>   	 */
>   	addl	$(4 * 4), %ecx
>   
> -.Lcopy_pt_regs_\@:
>   #endif
> +.Lcopy_pt_regs_\@:
>   
>   	/* Allocate frame on task-stack */
>   	subl	%ecx, %edi
> @@ -346,6 +359,56 @@
>   	cld
>   	rep movsl
>   
> +	jmp .Lend_\@
> +
> +.Lentry_from_kernel_\@:
> +
> +	/*
> +	 * This handles the case when we enter the kernel from
> +	 * kernel-mode and %esp points to the entry-stack. When this
> +	 * happens we need to switch to the task-stack to run C code,
> +	 * 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.
> +	 *
> +	 * When we switch to the task-stack here, we can't trust the
> +	 * contents of the entry-stack anymore, as the exception handler
> +	 * might be scheduled out or moved to another CPU. Therefore we
> +	 * copy the complete entry-stack to the task-stack and set a
> +	 * marker in the iret-frame (bit 31 of the CS dword) to detect
> +	 * what we've done on the iret path.
> +	 *
> +	 * On the iret path we copy everything back and switch to the
> +	 * entry-stack, so that the interrupted kernel code-path
> +	 * continues on the same stack it was interrupted with.
> +	 *
> +	 * Be aware that an NMI can happen anytime in this code.
> +	 *
> +	 * %esi: Entry-Stack pointer (same as %esp)
> +	 * %edi: Top of the task stack
> +	 */
> +
> +	/* Calculate number of bytes on the entry stack in %ecx */
> +	movl	%esi, %ecx
> +
> +	/* %ecx to the top of entry-stack */
> +	andl	$(MASK_entry_stack), %ecx
> +	addl	$(SIZEOF_entry_stack), %ecx
> +
> +	/* Number of bytes on the entry stack to %ecx */
> +	sub	%esi, %ecx
> +
> +	/* Mark stackframe as coming from entry stack */
> +	orl	$CS_FROM_ENTRY_STACK, 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
> +	 */
> +	jmp .Lcopy_pt_regs_\@
> +
>   .Lend_\@:
>   .endm
>   
> @@ -404,6 +467,56 @@
>   .endm
>   
>   /*
> + * This macro handles the case when we return to kernel-mode on the iret
> + * path and have to switch back to the entry stack.
> + *
> + * See the comments below the .Lentry_from_kernel_\@ label in the
> + * SWITCH_TO_KERNEL_STACK macro for more details.
> + */
> +.macro PARANOID_EXIT_TO_KERNEL_MODE
> +
> +	/*
> +	 * Test if we entered the kernel with the entry-stack. Most
> +	 * likely we did not, because this code only runs on the
> +	 * return-to-kernel path.
> +	 */
> +	testl	$CS_FROM_ENTRY_STACK, PT_CS(%esp)
> +	jz	.Lend_\@
> +
> +	/* Unlikely slow-path */
> +
> +	/* Clear marker from stack-frame */
> +	andl	$(~CS_FROM_ENTRY_STACK), PT_CS(%esp)
> +
> +	/* Copy the remaining task-stack contents to entry-stack */
> +	movl	%esp, %esi
> +	movl	PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %edi
> +
> +	/* Bytes on the task-stack to ecx */
> +	movl	PER_CPU_VAR(cpu_tss_rw + TSS_sp1), %ecx
> +	subl	%esi, %ecx
> +
> +	/* Allocate stack-frame on entry-stack */
> +	subl	%ecx, %edi
> +
> +	/*
> +	 * Save future stack-pointer, we must not switch until the
> +	 * copy is done, otherwise the NMI handler could destroy the
> +	 * contents of the task-stack we are about to copy.
> +	 */
> +	movl	%edi, %ebx
> +
> +	/* Do the copy */
> +	shrl	$2, %ecx
> +	cld
> +	rep movsl
> +
> +	/* Safe to switch to entry-stack now */
> +	movl	%ebx, %esp
> +
> +.Lend_\@:
> +.endm
> +/*
>    * %eax: prev task
>    * %edx: next task
>    */
> @@ -764,6 +877,7 @@ restore_all:
>   
>   restore_all_kernel:
>   	TRACE_IRQS_IRET
> +	PARANOID_EXIT_TO_KERNEL_MODE
>   	RESTORE_REGS 4
>   	jmp	.Lirq_return
>   
> 

I've bisected down a boot breakage on Intel Quark board (config attached) to 
this commit (b92a165df17e, I additionally had to apply d1b47a7c9efc). The kernel 
prints out nothing if this is in.

The board is an Siemens IOT2000, I will check if this can also be triggered on a 
similar Galileo Gen2. Qemu does not like to reproduce it, unfortunately.

The commit look unsuspicious at first glance - maybe it is just changing some 
layout in an unfortunate way. Any ideas?

Thanks,
Jan

-- 
Siemens AG, Corporate Technology, CT RDA IOT SES-DE
Corporate Competence Center Embedded Linux

[-- Attachment #2: .config.xz --]
[-- Type: application/x-xz, Size: 25424 bytes --]

  parent reply	other threads:[~2018-10-12 18:31 UTC|newest]

Thread overview: 105+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-07-18  9:40 [PATCH 00/39 v8] PTI support for x86-32 Joerg Roedel
2018-07-18  9:40 ` [PATCH 01/39] x86/asm-offsets: Move TSS_sp0 and TSS_sp1 to asm-offsets.c Joerg Roedel
2018-07-19 23:18   ` [tip:x86/pti] " tip-bot for Joerg Roedel
2018-07-18  9:40 ` [PATCH 02/39] x86/entry/32: Rename TSS_sysenter_sp0 to TSS_entry2task_stack Joerg Roedel
2018-07-19 23:19   ` [tip:x86/pti] " tip-bot for Joerg Roedel
2018-07-18  9:40 ` [PATCH 03/39] x86/entry/32: Load task stack from x86_tss.sp1 in SYSENTER handler Joerg Roedel
2018-07-19 23:19   ` [tip:x86/pti] " tip-bot for Joerg Roedel
2018-07-18  9:40 ` [PATCH 04/39] x86/entry/32: Put ESPFIX code into a macro Joerg Roedel
2018-07-19 23:20   ` [tip:x86/pti] " tip-bot for Joerg Roedel
2018-07-18  9:40 ` [PATCH 05/39] x86/entry/32: Unshare NMI return path Joerg Roedel
2018-07-19 23:21   ` [tip:x86/pti] " tip-bot for Joerg Roedel
2018-07-18  9:40 ` [PATCH 06/39] x86/entry/32: Split off return-to-kernel path Joerg Roedel
2018-07-19 23:21   ` [tip:x86/pti] " tip-bot for Joerg Roedel
2018-07-18  9:40 ` [PATCH 07/39] x86/entry/32: Enter the kernel via trampoline stack Joerg Roedel
2018-07-18 18:09   ` Brian Gerst
2018-07-19 20:52     ` Thomas Gleixner
2018-07-19 23:22   ` [tip:x86/pti] " tip-bot for Joerg Roedel
2018-07-18  9:40 ` [PATCH 08/39] x86/entry/32: Leave " Joerg Roedel
2018-07-19 23:22   ` [tip:x86/pti] " tip-bot for Joerg Roedel
2018-07-18  9:40 ` [PATCH 09/39] x86/entry/32: Introduce SAVE_ALL_NMI and RESTORE_ALL_NMI Joerg Roedel
2018-07-19 23:23   ` [tip:x86/pti] " tip-bot for Joerg Roedel
2018-07-18  9:40 ` [PATCH 10/39] x86/entry/32: Handle Entry from Kernel-Mode on Entry-Stack Joerg Roedel
2018-07-19 23:23   ` [tip:x86/pti] " tip-bot for Joerg Roedel
2018-10-12 18:29   ` Jan Kiszka [this message]
2018-10-13  9:54     ` [PATCH] x86/entry/32: Fix setup of CS high bits Jan Kiszka
2018-10-13 15:12       ` Andy Lutomirski
2018-10-15 13:08         ` Jan Kiszka
2018-10-15 13:14           ` David Laight
2018-10-15 13:18             ` Jan Kiszka
2018-10-15 13:29               ` David Laight
2018-10-15  9:10       ` Joerg Roedel
2018-10-15 14:09       ` [PATCH v2] " Jan Kiszka
2018-10-15 15:09         ` [tip:x86/urgent] x86/entry/32: Clear the " tip-bot for Jan Kiszka
2018-10-18  6:21         ` tip-bot for Jan Kiszka
2018-07-18  9:40 ` [PATCH 11/39] x86/entry/32: Simplify debug entry point Joerg Roedel
2018-07-19 23:24   ` [tip:x86/pti] " tip-bot for Joerg Roedel
2018-07-18  9:40 ` [PATCH 12/39] x86/entry/32: Add PTI cr3 switch to non-NMI entry/exit points Joerg Roedel
2018-07-19 23:24   ` [tip:x86/pti] " tip-bot for Joerg Roedel
2018-07-18  9:40 ` [PATCH 13/39] x86/entry/32: Add PTI cr3 switches to NMI handler code Joerg Roedel
2018-07-19 23:25   ` [tip:x86/pti] x86/entry/32: Add PTI CR3 " tip-bot for Joerg Roedel
2018-07-18  9:40 ` [PATCH 14/39] x86/entry: Rename update_sp0 to update_task_stack Joerg Roedel
2018-07-19 23:25   ` [tip:x86/pti] " tip-bot for Joerg Roedel
2018-07-18  9:40 ` [PATCH 15/39] x86/pgtable: Rename pti_set_user_pgd to pti_set_user_pgtbl Joerg Roedel
2018-07-19 23:26   ` [tip:x86/pti] x86/pgtable: Rename pti_set_user_pgd() to pti_set_user_pgtbl() tip-bot for Joerg Roedel
2018-07-18  9:40 ` [PATCH 16/39] x86/pgtable/pae: Unshare kernel PMDs when PTI is enabled Joerg Roedel
2018-07-19 23:26   ` [tip:x86/pti] " tip-bot for Joerg Roedel
2018-07-18  9:40 ` [PATCH 17/39] x86/pgtable/32: Allocate 8k page-tables " Joerg Roedel
2018-07-19 23:27   ` [tip:x86/pti] " tip-bot for Joerg Roedel
2018-07-18  9:40 ` [PATCH 18/39] x86/pgtable: Move pgdp kernel/user conversion functions to pgtable.h Joerg Roedel
2018-07-19 23:27   ` [tip:x86/pti] " tip-bot for Joerg Roedel
2018-07-18  9:40 ` [PATCH 19/39] x86/pgtable: Move pti_set_user_pgtbl() " Joerg Roedel
2018-07-19 23:28   ` [tip:x86/pti] " tip-bot for Joerg Roedel
2018-07-18  9:40 ` [PATCH 20/39] x86/pgtable: Move two more functions from pgtable_64.h " Joerg Roedel
2018-07-19 23:28   ` [tip:x86/pti] " tip-bot for Joerg Roedel
2018-07-18  9:40 ` [PATCH 21/39] x86/mm/pae: Populate valid user PGD entries Joerg Roedel
2018-07-19 23:29   ` [tip:x86/pti] " tip-bot for Joerg Roedel
2018-07-18  9:40 ` [PATCH 22/39] x86/mm/pae: Populate the user page-table with user pgd's Joerg Roedel
2018-07-19 23:30   ` [tip:x86/pti] " tip-bot for Joerg Roedel
2018-07-18  9:41 ` [PATCH 23/39] x86/mm/legacy: " Joerg Roedel
2018-07-19 23:30   ` [tip:x86/pti] " tip-bot for Joerg Roedel
2018-07-18  9:41 ` [PATCH 24/39] x86/mm/pti: Add an overflow check to pti_clone_pmds() Joerg Roedel
2018-07-19 23:31   ` [tip:x86/pti] " tip-bot for Joerg Roedel
2018-07-18  9:41 ` [PATCH 25/39] x86/mm/pti: Define X86_CR3_PTI_PCID_USER_BIT on x86_32 Joerg Roedel
2018-07-19 23:31   ` [tip:x86/pti] " tip-bot for Joerg Roedel
2018-07-18  9:41 ` [PATCH 26/39] x86/mm/pti: Clone CPU_ENTRY_AREA on PMD level " Joerg Roedel
2018-07-19 23:32   ` [tip:x86/pti] " tip-bot for Joerg Roedel
2018-07-18  9:41 ` [PATCH 27/39] x86/mm/pti: Make pti_clone_kernel_text() compile on 32 bit Joerg Roedel
2018-07-19 23:32   ` [tip:x86/pti] " tip-bot for Joerg Roedel
2018-07-18  9:41 ` [PATCH 28/39] x86/mm/pti: Keep permissions when cloning kernel text in pti_clone_kernel_text() Joerg Roedel
2018-07-19 23:33   ` [tip:x86/pti] " tip-bot for Joerg Roedel
2018-07-18  9:41 ` [PATCH 29/39] x86/mm/pti: Introduce pti_finalize() Joerg Roedel
2018-07-19 23:33   ` [tip:x86/pti] " tip-bot for Joerg Roedel
2018-07-18  9:41 ` [PATCH 30/39] x86/mm/pti: Clone entry-text again in pti_finalize() Joerg Roedel
2018-07-19 23:34   ` [tip:x86/pti] " tip-bot for Joerg Roedel
2018-07-18  9:41 ` [PATCH 31/39] x86/mm/dump_pagetables: Define INIT_PGD Joerg Roedel
2018-07-19 23:34   ` [tip:x86/pti] " tip-bot for Joerg Roedel
2018-07-18  9:41 ` [PATCH 32/39] x86/pgtable/pae: Use separate kernel PMDs for user page-table Joerg Roedel
2018-07-19 23:35   ` [tip:x86/pti] " tip-bot for Joerg Roedel
2018-10-05 14:06   ` [PATCH 32/39] " Arnd Bergmann
2018-07-18  9:41 ` [PATCH 33/39] x86/ldt: Reserve address-space range on 32 bit for the LDT Joerg Roedel
2018-07-19 23:35   ` [tip:x86/pti] " tip-bot for Joerg Roedel
2018-07-18  9:41 ` [PATCH 34/39] x86/ldt: Define LDT_END_ADDR Joerg Roedel
2018-07-19 23:36   ` [tip:x86/pti] " tip-bot for Joerg Roedel
2018-07-18  9:41 ` [PATCH 35/39] x86/ldt: Split out sanity check in map_ldt_struct() Joerg Roedel
2018-07-19 23:36   ` [tip:x86/pti] " tip-bot for Joerg Roedel
2018-07-18  9:41 ` [PATCH 36/39] x86/ldt: Enable LDT user-mapping for PAE Joerg Roedel
2018-07-19 23:37   ` [tip:x86/pti] " tip-bot for Joerg Roedel
2018-07-18  9:41 ` [PATCH 37/39] x86/pti: Allow CONFIG_PAGE_TABLE_ISOLATION for x86_32 Joerg Roedel
2018-07-19 23:37   ` [tip:x86/pti] " tip-bot for Joerg Roedel
2018-07-18  9:41 ` [PATCH 38/39] x86/mm/pti: Add Warning when booting on a PCID capable CPU Joerg Roedel
2018-07-19 23:38   ` [tip:x86/pti] " tip-bot for Joerg Roedel
2018-07-18  9:41 ` [PATCH 39/39] x86/entry/32: Add debug code to check entry/exit cr3 Joerg Roedel
2018-07-19 23:38   ` [tip:x86/pti] x86/entry/32: Add debug code to check entry/exit CR3 tip-bot for Joerg Roedel
2018-07-18 11:59 ` [PATCH 00/39 v8] PTI support for x86-32 Pavel Machek
2018-07-19 23:21 ` Thomas Gleixner
2018-07-20  7:59   ` Joerg Roedel
  -- strict thread matches above, loose matches on Subject: below --
2018-07-11 11:29 [PATCH 00/39 v7] " Joerg Roedel
2018-07-11 11:29 ` [PATCH 10/39] x86/entry/32: Handle Entry from Kernel-Mode on Entry-Stack Joerg Roedel
2018-07-13 23:31   ` Andy Lutomirski
2018-07-14  5:21     ` Joerg Roedel
2018-07-14  6:26       ` Andy Lutomirski
2018-07-14  8:01         ` Joerg Roedel
2018-07-14 14:36           ` Andy Lutomirski
2018-07-17  7:15             ` Joerg Roedel
2018-07-17 20:06               ` Andy Lutomirski
2018-07-18 11:59                 ` Joerg Roedel

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=97421241-2bc4-c3f1-4128-95b3e8a230d1@siemens.com \
    --to=jan.kiszka@siemens.com \
    --cc=David.Laight@aculab.com \
    --cc=aarcange@redhat.com \
    --cc=aliguori@amazon.com \
    --cc=boris.ostrovsky@oracle.com \
    --cc=bp@alien8.de \
    --cc=brgerst@gmail.com \
    --cc=daniel.gruss@iaik.tugraz.at \
    --cc=dave.hansen@intel.com \
    --cc=dvlasenk@redhat.com \
    --cc=eduval@amazon.com \
    --cc=gregkh@linuxfoundation.org \
    --cc=hpa@zytor.com \
    --cc=hughd@google.com \
    --cc=jgross@suse.com \
    --cc=jkosina@suse.cz \
    --cc=joro@8bytes.org \
    --cc=jpoimboe@redhat.com \
    --cc=keescook@google.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=luto@kernel.org \
    --cc=mingo@kernel.org \
    --cc=peterz@infradead.org \
    --cc=tglx@linutronix.de \
    --cc=torvalds@linux-foundation.org \
    --cc=will.deacon@arm.com \
    --cc=x86@kernel.org \
    --subject='Re: [PATCH 10/39] x86/entry/32: Handle Entry from Kernel-Mode on Entry-Stack' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
on how to clone and mirror all data and code used for this inbox