All of lore.kernel.org
 help / color / mirror / Atom feed
From: Andy Lutomirski <luto@kernel.org>
To: x86@kernel.org, linux-kernel@vger.kernel.org
Cc: linux-arch@vger.kernel.org, Borislav Petkov <bp@alien8.de>,
	Nadav Amit <nadav.amit@gmail.com>,
	Kees Cook <keescook@chromium.org>,
	Brian Gerst <brgerst@gmail.com>,
	"kernel-hardening@lists.openwall.com" 
	<kernel-hardening@lists.openwall.com>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Josh Poimboeuf <jpoimboe@redhat.com>, Jann Horn <jann@thejh.net>,
	Heiko Carstens <heiko.carstens@de.ibm.com>,
	Andy Lutomirski <luto@kernel.org>
Subject: [PATCH v4 11/16] x86/dumpstack: When OOPSing, rewind the stack before do_exit
Date: Thu, 23 Jun 2016 21:23:06 -0700	[thread overview]
Message-ID: <2bae70091dd75abc881259747987979156f2f789.1466741835.git.luto@kernel.org> (raw)
In-Reply-To: <cover.1466741835.git.luto@kernel.org>
In-Reply-To: <cover.1466741835.git.luto@kernel.org>

If we call do_exit with a clean stack, we greatly reduce the risk of
recursive oopses due to stack overflow in do_exit, and we allow
do_exit to work even if we OOPS from an IST stack.  The latter gives
us a much better chance of surviving long enough after we detect a
stack overflow to write out our logs.

I intentionally separated this from the preceding patch that
disables do_exit-on-OOPS on IST stacks.  This way, if we need to
revert this patch, we still end up in an acceptable state wrt stack
overflow handling.

Signed-off-by: Andy Lutomirski <luto@kernel.org>
---
 arch/x86/entry/entry_32.S   | 11 +++++++++++
 arch/x86/entry/entry_64.S   | 11 +++++++++++
 arch/x86/kernel/dumpstack.c | 13 +++++++++----
 3 files changed, 31 insertions(+), 4 deletions(-)

diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 983e5d3a0d27..0b56666e6039 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -1153,3 +1153,14 @@ ENTRY(async_page_fault)
 	jmp	error_code
 END(async_page_fault)
 #endif
+
+ENTRY(rewind_stack_do_exit)
+	/* Prevent any naive code from trying to unwind to our caller. */
+	xorl	%ebp, %ebp
+
+	movl	PER_CPU_VAR(cpu_current_top_of_stack), %esi
+	leal	-TOP_OF_KERNEL_STACK_PADDING-PTREGS_SIZE(%esi), %esp
+
+	call	do_exit
+1:	jmp 1b
+END(rewind_stack_do_exit)
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 9ee0da1807ed..b846875aeea6 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1423,3 +1423,14 @@ ENTRY(ignore_sysret)
 	mov	$-ENOSYS, %eax
 	sysret
 END(ignore_sysret)
+
+ENTRY(rewind_stack_do_exit)
+	/* Prevent any naive code from trying to unwind to our caller. */
+	xorl	%ebp, %ebp
+
+	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rax
+	leaq	-TOP_OF_KERNEL_STACK_PADDING-PTREGS_SIZE(%rax), %rsp
+
+	call	do_exit
+1:	jmp 1b
+END(rewind_stack_do_exit)
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 70d5aae8b8f7..4592bc4ed3e1 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -226,6 +226,8 @@ unsigned long oops_begin(void)
 EXPORT_SYMBOL_GPL(oops_begin);
 NOKPROBE_SYMBOL(oops_begin);
 
+extern void __noreturn rewind_stack_do_exit(int signr);
+
 void oops_end(unsigned long flags, struct pt_regs *regs, int signr)
 {
 	if (regs && kexec_should_crash(current))
@@ -245,12 +247,15 @@ void oops_end(unsigned long flags, struct pt_regs *regs, int signr)
 		return;
 	if (in_interrupt())
 		panic("Fatal exception in interrupt");
-	if (((current_stack_pointer() ^ (current_top_of_stack() - 1))
-	     & ~(THREAD_SIZE - 1)) != 0)
-		panic("Fatal exception on special stack");
 	if (panic_on_oops)
 		panic("Fatal exception");
-	do_exit(signr);
+
+	/*
+	 * We're not going to return, but we might be on an IST stack or
+	 * have very little stack space left.  Rewind the stack and kill
+	 * the task.
+	 */
+	rewind_stack_do_exit(signr);
 }
 NOKPROBE_SYMBOL(oops_end);
 
-- 
2.5.5

WARNING: multiple messages have this Message-ID (diff)
From: Andy Lutomirski <luto@kernel.org>
To: x86@kernel.org, linux-kernel@vger.kernel.org
Cc: linux-arch@vger.kernel.org, Borislav Petkov <bp@alien8.de>,
	Nadav Amit <nadav.amit@gmail.com>,
	Kees Cook <keescook@chromium.org>,
	Brian Gerst <brgerst@gmail.com>,
	"kernel-hardening@lists.openwall.com"
	<kernel-hardening@lists.openwall.com>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Josh Poimboeuf <jpoimboe@redhat.com>, Jann Horn <jann@thejh.net>,
	Heiko Carstens <heiko.carstens@de.ibm.com>,
	Andy Lutomirski <luto@kernel.org>
Subject: [kernel-hardening] [PATCH v4 11/16] x86/dumpstack: When OOPSing, rewind the stack before do_exit
Date: Thu, 23 Jun 2016 21:23:06 -0700	[thread overview]
Message-ID: <2bae70091dd75abc881259747987979156f2f789.1466741835.git.luto@kernel.org> (raw)
In-Reply-To: <cover.1466741835.git.luto@kernel.org>
In-Reply-To: <cover.1466741835.git.luto@kernel.org>

If we call do_exit with a clean stack, we greatly reduce the risk of
recursive oopses due to stack overflow in do_exit, and we allow
do_exit to work even if we OOPS from an IST stack.  The latter gives
us a much better chance of surviving long enough after we detect a
stack overflow to write out our logs.

I intentionally separated this from the preceding patch that
disables do_exit-on-OOPS on IST stacks.  This way, if we need to
revert this patch, we still end up in an acceptable state wrt stack
overflow handling.

Signed-off-by: Andy Lutomirski <luto@kernel.org>
---
 arch/x86/entry/entry_32.S   | 11 +++++++++++
 arch/x86/entry/entry_64.S   | 11 +++++++++++
 arch/x86/kernel/dumpstack.c | 13 +++++++++----
 3 files changed, 31 insertions(+), 4 deletions(-)

diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 983e5d3a0d27..0b56666e6039 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -1153,3 +1153,14 @@ ENTRY(async_page_fault)
 	jmp	error_code
 END(async_page_fault)
 #endif
+
+ENTRY(rewind_stack_do_exit)
+	/* Prevent any naive code from trying to unwind to our caller. */
+	xorl	%ebp, %ebp
+
+	movl	PER_CPU_VAR(cpu_current_top_of_stack), %esi
+	leal	-TOP_OF_KERNEL_STACK_PADDING-PTREGS_SIZE(%esi), %esp
+
+	call	do_exit
+1:	jmp 1b
+END(rewind_stack_do_exit)
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 9ee0da1807ed..b846875aeea6 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1423,3 +1423,14 @@ ENTRY(ignore_sysret)
 	mov	$-ENOSYS, %eax
 	sysret
 END(ignore_sysret)
+
+ENTRY(rewind_stack_do_exit)
+	/* Prevent any naive code from trying to unwind to our caller. */
+	xorl	%ebp, %ebp
+
+	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rax
+	leaq	-TOP_OF_KERNEL_STACK_PADDING-PTREGS_SIZE(%rax), %rsp
+
+	call	do_exit
+1:	jmp 1b
+END(rewind_stack_do_exit)
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 70d5aae8b8f7..4592bc4ed3e1 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -226,6 +226,8 @@ unsigned long oops_begin(void)
 EXPORT_SYMBOL_GPL(oops_begin);
 NOKPROBE_SYMBOL(oops_begin);
 
+extern void __noreturn rewind_stack_do_exit(int signr);
+
 void oops_end(unsigned long flags, struct pt_regs *regs, int signr)
 {
 	if (regs && kexec_should_crash(current))
@@ -245,12 +247,15 @@ void oops_end(unsigned long flags, struct pt_regs *regs, int signr)
 		return;
 	if (in_interrupt())
 		panic("Fatal exception in interrupt");
-	if (((current_stack_pointer() ^ (current_top_of_stack() - 1))
-	     & ~(THREAD_SIZE - 1)) != 0)
-		panic("Fatal exception on special stack");
 	if (panic_on_oops)
 		panic("Fatal exception");
-	do_exit(signr);
+
+	/*
+	 * We're not going to return, but we might be on an IST stack or
+	 * have very little stack space left.  Rewind the stack and kill
+	 * the task.
+	 */
+	rewind_stack_do_exit(signr);
 }
 NOKPROBE_SYMBOL(oops_end);
 
-- 
2.5.5

  parent reply	other threads:[~2016-06-24  4:23 UTC|newest]

Thread overview: 89+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-06-24  4:22 [PATCH v4 00/16] Virtually mapped stacks with guard pages (x86, core) Andy Lutomirski
2016-06-24  4:22 ` [kernel-hardening] " Andy Lutomirski
2016-06-24  4:22 ` Andy Lutomirski
2016-06-24  4:22 ` [PATCH v4 01/16] bluetooth: Switch SMP to crypto_cipher_encrypt_one() Andy Lutomirski
2016-06-24  4:22   ` [kernel-hardening] " Andy Lutomirski
2016-06-24  4:22   ` Andy Lutomirski
2016-06-24  6:10   ` Herbert Xu
2016-06-24  6:10     ` [kernel-hardening] " Herbert Xu
2016-06-24  6:10     ` Herbert Xu
2016-06-24  7:19   ` Johan Hedberg
2016-06-24  7:19     ` [kernel-hardening] " Johan Hedberg
2016-06-24  7:19     ` Johan Hedberg
2016-06-24  4:22 ` [PATCH v4 02/16] rxrpc: Avoid using stack memory in SG lists in rxkad Andy Lutomirski
2016-06-24  4:22   ` [kernel-hardening] " Andy Lutomirski
2016-06-24  4:22   ` Andy Lutomirski
2016-06-24  4:22 ` [PATCH v4 03/16] x86/mm/hotplug: Don't remove PGD entries in remove_pagetable() Andy Lutomirski
2016-06-24  4:22   ` [kernel-hardening] " Andy Lutomirski
2016-06-24  4:22   ` Andy Lutomirski
2016-06-24  4:22   ` Andy Lutomirski
2016-06-24  4:22 ` [PATCH v4 04/16] x86/cpa: In populate_pgd, don't set the pgd entry until it's populated Andy Lutomirski
2016-06-24  4:22   ` [kernel-hardening] " Andy Lutomirski
2016-06-24  4:22   ` Andy Lutomirski
2016-06-24  4:23 ` [PATCH v4 05/16] x86/mm: Remove kernel_unmap_pages_in_pgd() and efi_cleanup_page_tables() Andy Lutomirski
2016-06-24  4:23   ` [kernel-hardening] " Andy Lutomirski
2016-06-24  4:23   ` Andy Lutomirski
2016-06-24  4:23 ` [PATCH v4 06/16] mm: Track NR_KERNEL_STACK in KiB instead of number of stacks Andy Lutomirski
2016-06-24  4:23   ` [kernel-hardening] " Andy Lutomirski
2016-06-24  4:23   ` Andy Lutomirski
2016-06-24  4:23   ` Andy Lutomirski
2016-06-24 15:21   ` Josh Poimboeuf
2016-06-24 15:21     ` [kernel-hardening] " Josh Poimboeuf
2016-06-24 15:21     ` Josh Poimboeuf
2016-06-24 15:21     ` Josh Poimboeuf
2016-06-24  4:23 ` [PATCH v4 07/16] mm: Fix memcg stack accounting for sub-page stacks Andy Lutomirski
2016-06-24  4:23   ` [kernel-hardening] " Andy Lutomirski
2016-06-24  4:23   ` Andy Lutomirski
2016-06-24  4:23   ` Andy Lutomirski
2016-06-24 15:22   ` Josh Poimboeuf
2016-06-24 15:22     ` [kernel-hardening] " Josh Poimboeuf
2016-06-24 15:22     ` Josh Poimboeuf
2016-06-24 15:22     ` Josh Poimboeuf
2016-06-24  4:23 ` [PATCH v4 08/16] dma-api: Teach the "DMA-from-stack" check about vmapped stacks Andy Lutomirski
2016-06-24  4:23   ` [kernel-hardening] " Andy Lutomirski
2016-06-24  4:23   ` Andy Lutomirski
2016-06-24  4:23 ` [PATCH v4 09/16] fork: Add generic vmalloced stack support Andy Lutomirski
2016-06-24  4:23   ` [kernel-hardening] " Andy Lutomirski
2016-06-24  4:23   ` Andy Lutomirski
2016-06-24  4:23 ` [PATCH v4 10/16] x86/die: Don't try to recover from an OOPS on a non-default stack Andy Lutomirski
2016-06-24  4:23   ` [kernel-hardening] " Andy Lutomirski
2016-06-24  4:23   ` Andy Lutomirski
2016-06-24  4:23 ` Andy Lutomirski [this message]
2016-06-24  4:23   ` [kernel-hardening] [PATCH v4 11/16] x86/dumpstack: When OOPSing, rewind the stack before do_exit Andy Lutomirski
2016-06-24  4:23   ` Andy Lutomirski
2016-06-24 15:30   ` Josh Poimboeuf
2016-06-24 15:30     ` [kernel-hardening] " Josh Poimboeuf
2016-06-24 15:30     ` Josh Poimboeuf
2016-06-24 15:35     ` Brian Gerst
2016-06-24 15:35       ` [kernel-hardening] " Brian Gerst
2016-06-24 15:35       ` Brian Gerst
2016-06-24 15:48       ` Josh Poimboeuf
2016-06-24 15:48         ` [kernel-hardening] " Josh Poimboeuf
2016-06-24 15:48         ` Josh Poimboeuf
2016-06-24  4:23 ` [PATCH v4 12/16] x86/dumpstack: When dumping stack bytes due to OOPS, start with regs->sp Andy Lutomirski
2016-06-24  4:23   ` [kernel-hardening] " Andy Lutomirski
2016-06-24  4:23   ` Andy Lutomirski
2016-06-24 15:31   ` Josh Poimboeuf
2016-06-24 15:31     ` [kernel-hardening] " Josh Poimboeuf
2016-06-24 15:31     ` Josh Poimboeuf
2016-06-24  4:23 ` [PATCH v4 13/16] x86/dumpstack: Try harder to get a call trace on stack overflow Andy Lutomirski
2016-06-24  4:23   ` [kernel-hardening] " Andy Lutomirski
2016-06-24  4:23   ` Andy Lutomirski
2016-06-24 15:35   ` Josh Poimboeuf
2016-06-24 15:35     ` [kernel-hardening] " Josh Poimboeuf
2016-06-24 15:35     ` Josh Poimboeuf
2016-06-26 16:59     ` Andy Lutomirski
2016-06-26 16:59       ` [kernel-hardening] " Andy Lutomirski
2016-06-26 16:59       ` Andy Lutomirski
2016-06-24  4:23 ` [PATCH v4 14/16] x86/dumpstack/64: Handle faults when printing the "Stack:" part of an OOPS Andy Lutomirski
2016-06-24  4:23   ` [kernel-hardening] " Andy Lutomirski
2016-06-24  4:23   ` Andy Lutomirski
2016-06-24 15:36   ` Josh Poimboeuf
2016-06-24 15:36     ` [kernel-hardening] " Josh Poimboeuf
2016-06-24 15:36     ` Josh Poimboeuf
2016-06-24  4:23 ` [PATCH v4 15/16] x86/mm/64: Enable vmapped stacks Andy Lutomirski
2016-06-24  4:23   ` [kernel-hardening] " Andy Lutomirski
2016-06-24  4:23   ` Andy Lutomirski
2016-06-24  4:23 ` [PATCH v4 16/16] x86/mm: Improve stack-overflow #PF handling Andy Lutomirski
2016-06-24  4:23   ` [kernel-hardening] " Andy Lutomirski
2016-06-24  4:23   ` Andy Lutomirski

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=2bae70091dd75abc881259747987979156f2f789.1466741835.git.luto@kernel.org \
    --to=luto@kernel.org \
    --cc=bp@alien8.de \
    --cc=brgerst@gmail.com \
    --cc=heiko.carstens@de.ibm.com \
    --cc=jann@thejh.net \
    --cc=jpoimboe@redhat.com \
    --cc=keescook@chromium.org \
    --cc=kernel-hardening@lists.openwall.com \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=nadav.amit@gmail.com \
    --cc=torvalds@linux-foundation.org \
    --cc=x86@kernel.org \
    /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
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.