[PATCH v7 3/4] arm/syscalls: Architecture specific pre-usermode check

From: Thomas Garnier <thgarnie@google.com>
To: "Martin Schwidefsky" <schwidefsky@de.ibm.com>,
	"Heiko Carstens" <heiko.carstens@de.ibm.com>,
	"Arnd Bergmann" <arnd@arndb.de>,
	"Dave Hansen" <dave.hansen@intel.com>,
	"Andrew Morton" <akpm@linux-foundation.org>,
	"Thomas Garnier" <thgarnie@google.com>,
	"David Howells" <dhowells@redhat.com>,
	"René Nyffenegger" <mail@renenyffenegger.ch>,
	"Paul E . McKenney" <paulmck@linux.vnet.ibm.com>,
	"Ingo Molnar" <mingo@kernel.org>,
	"Thomas Gleixner" <tglx@linutronix.de>,
	"Oleg Nesterov" <oleg@redhat.com>,
	"Stephen Smalley" <sds@tycho.nsa.gov>,
	"Pavel Tikhomirov" <ptikhomirov@virtuozzo.com>,
	"Ingo Molnar" <mingo@redhat.com>,
	"H . Peter Anvin" <hpa@zytor.com>,
	"Andy Lutomirski" <luto@kernel.org>,
	"Paolo Bonzini" <pbonzini@redhat.com>,
	"Kees Cook" <keescook@chromium.org>,
	"Rik van Riel" <riel@redhat.com>,
	"Josh Poimboeuf" <jpoimboe@redhat.com>,
	"Borislav Petkov" <bp@alien8.de>,
	"Brian Gerst" <brgerst@gmail.com>,
	"Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>,
	"Christian Borntraeger" <borntraeger@de.ibm.com>,
	"Russell King" <linux@armlinux.org.uk>,
	"Will Deacon" <will.deacon@arm.com>,
	"Catalin Marinas" <catalin.marinas@arm.com>,
	"Mark Rutland" <mark.rutland@arm.com>,
	"James Morse" <james.morse@arm.com>
Cc: linux-s390@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-api@vger.kernel.org, x86@kernel.org,
	linux-arm-kernel@lists.infradead.org,
	kernel-hardening@lists.openwall.com
Subject: [PATCH v7 3/4] arm/syscalls: Architecture specific pre-usermode check
Date: Mon, 10 Apr 2017 09:44:19 -0700	[thread overview]
Message-ID: <20170410164420.64003-3-thgarnie@google.com> (raw)
In-Reply-To: <20170410164420.64003-1-thgarnie@google.com>

Disable the generic pre-usermode check in favor of an optimized
implementation. This patch adds specific checks on user-mode return path
to make it faster and smaller.

The address limit is checked on each syscall return path to user-mode
path as well as the irq user-mode return function. If the address limit
was changed, a generic handler is called to stop the kernel on an
explicit check.

Signed-off-by: Thomas Garnier <thgarnie@google.com>
---
Based on next-20170410
---
 arch/arm/Kconfig               |  1 +
 arch/arm/kernel/entry-common.S | 10 +++++++++-
 2 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index b0e8c9763e94..af0992debfd2 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -12,6 +12,7 @@ config ARM
 	select ARCH_HAVE_CUSTOM_GPIO_H
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_MIGHT_HAVE_PC_PARPORT
+	select ARCH_NO_SYSCALL_VERIFY_PRE_USERMODE_STATE
 	select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX
 	select ARCH_OPTIONAL_KERNEL_RWX_DEFAULT if CPU_V7
 	select ARCH_SUPPORTS_ATOMIC_RMW
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index eb5cd77bf1d8..c8a8ba5c22ad 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -12,6 +12,7 @@
 #include <asm/unistd.h>
 #include <asm/ftrace.h>
 #include <asm/unwind.h>
+#include <asm/memory.h>
 #ifdef CONFIG_AEABI
 #include <asm/unistd-oabi.h>
 #endif
@@ -27,7 +28,6 @@
 
 #include "entry-header.S"
 
-
 	.align	5
 #if !(IS_ENABLED(CONFIG_TRACE_IRQFLAGS) || IS_ENABLED(CONFIG_CONTEXT_TRACKING))
 /*
@@ -40,9 +40,12 @@ ret_fast_syscall:
  UNWIND(.fnstart	)
  UNWIND(.cantunwind	)
 	disable_irq_notrace			@ disable interrupts
+	ldr	r2, [tsk, #TI_ADDR_LIMIT]
 	ldr	r1, [tsk, #TI_FLAGS]		@ re-check for syscall tracing
 	tst	r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK
 	bne	fast_work_pending
+	cmp	r2, #TASK_SIZE
+	blne	address_limit_check_failed
 
 	/* perform architecture specific actions before user return */
 	arch_ret_to_user r1, lr
@@ -66,6 +69,7 @@ ret_fast_syscall:
  UNWIND(.cantunwind	)
 	str	r0, [sp, #S_R0 + S_OFF]!	@ save returned r0
 	disable_irq_notrace			@ disable interrupts
+	ldr	r2, [tsk, #TI_ADDR_LIMIT]
 	ldr	r1, [tsk, #TI_FLAGS]		@ re-check for syscall tracing
 	tst	r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK
 	beq	no_work_pending
@@ -82,6 +86,7 @@ slow_work_pending:
 	mov	r2, why				@ 'syscall'
 	bl	do_work_pending
 	cmp	r0, #0
+	ldreq   r2, [tsk, #TI_ADDR_LIMIT]
 	beq	no_work_pending
 	movlt	scno, #(__NR_restart_syscall - __NR_SYSCALL_BASE)
 	ldmia	sp, {r0 - r6}			@ have to reload r0 - r6
@@ -99,9 +104,12 @@ ret_slow_syscall:
 	disable_irq_notrace			@ disable interrupts
 ENTRY(ret_to_user_from_irq)
 	ldr	r1, [tsk, #TI_FLAGS]
+	ldr	r2, [tsk, #TI_ADDR_LIMIT]
 	tst	r1, #_TIF_WORK_MASK
 	bne	slow_work_pending
 no_work_pending:
+	cmp	r2, #TASK_SIZE
+	blne	address_limit_check_failed
 	asm_trace_hardirqs_on save = 0
 
 	/* perform architecture specific actions before user return */
-- 
2.12.2.715.g7642488e1d-goog
