Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1620560 > unrolled thread

[PATCH v7 1/4] syscalls: Restore address limit after a syscall

Back to article view | Back to linux.kernel

Contents

  [PATCH v7 1/4] syscalls: Restore address limit after a syscall Thomas Garnier <thgarnie@google.com> - 2017-04-10 20:00 +0200
    [PATCH v7 3/4] arm/syscalls: Architecture specific pre-usermode check Thomas Garnier <thgarnie@google.com> - 2017-04-10 20:00 +0200
    [PATCH v7 2/4] x86/syscalls: Architecture specific pre-usermode check Thomas Garnier <thgarnie@google.com> - 2017-04-10 20:00 +0200
    [PATCH v7 4/4] arm64/syscalls: Architecture specific pre-usermode check Thomas Garnier <thgarnie@google.com> - 2017-04-10 20:00 +0200

#1620560 — [PATCH v7 1/4] syscalls: Restore address limit after a syscall

This patch ensures a syscall does not return to user-mode with a kernel
address limit. If that happened, a process can corrupt kernel-mode
memory and elevate privileges.

For example, it would mitigation this bug:

- https://bugs.chromium.org/p/project-zero/issues/detail?id=990

The CONFIG_ARCH_NO_SYSCALL_VERIFY_PRE_USERMODE_STATE option is also
added so each architecture can optimize this change.

Signed-off-by: Thomas Garnier <thgarnie@google.com>
Tested-by: Kees Cook <keescook@chromium.org>
---
Based on next-20170410
---
 arch/s390/Kconfig        |  1 +
 include/linux/syscalls.h | 26 +++++++++++++++++++++++++-
 init/Kconfig             |  6 ++++++
 kernel/sys.c             | 13 +++++++++++++
 4 files changed, 45 insertions(+), 1 deletion(-)

diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index d25435d94b6e..489a0cc6e46b 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -103,6 +103,7 @@ config S390
 	select ARCH_INLINE_WRITE_UNLOCK_BH
 	select ARCH_INLINE_WRITE_UNLOCK_IRQ
 	select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE
+	select ARCH_NO_SYSCALL_VERIFY_PRE_USERMODE_STATE
 	select ARCH_SAVE_PAGE_KEYS if HIBERNATION
 	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 980c3c9b06f8..801a7a74fe28 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -191,6 +191,27 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 	SYSCALL_METADATA(sname, x, __VA_ARGS__)			\
 	__SYSCALL_DEFINEx(x, sname, __VA_ARGS__)
 
+
+/*
+ * Called before coming back to user-mode. Returning to user-mode with an
+ * address limit different than USER_DS can allow to overwrite kernel memory.
+ */
+static inline void verify_pre_usermode_state(void) {
+	BUG_ON(!segment_eq(get_fs(), USER_DS));
+}
+
+#ifndef CONFIG_ARCH_NO_SYSCALL_VERIFY_PRE_USERMODE_STATE
+#define __CHECK_USER_CALLER() \
+	bool user_caller = segment_eq(get_fs(), USER_DS)
+#define __VERIFY_PRE_USERMODE_STATE() \
+	if (user_caller) verify_pre_usermode_state()
+#else
+#define __CHECK_USER_CALLER()
+#define __VERIFY_PRE_USERMODE_STATE()
+asmlinkage void address_limit_check_failed(void);
+#endif
+
+
 #define __PROTECT(...) asmlinkage_protect(__VA_ARGS__)
 #define __SYSCALL_DEFINEx(x, name, ...)					\
 	asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))	\
@@ -199,7 +220,10 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 	asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__));	\
 	asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__))	\
 	{								\
-		long ret = SYSC##name(__MAP(x,__SC_CAST,__VA_ARGS__));	\
+		long ret;						\
+		__CHECK_USER_CALLER();					\
+		ret = SYSC##name(__MAP(x,__SC_CAST,__VA_ARGS__));	\
+		__VERIFY_PRE_USERMODE_STATE();				\
 		__MAP(x,__SC_TEST,__VA_ARGS__);				\
 		__PROTECT(x, ret,__MAP(x,__SC_ARGS,__VA_ARGS__));	\
 		return ret;						\
diff --git a/init/Kconfig b/init/Kconfig
index 7f7027817bce..e5fbd0becfa7 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1958,6 +1958,12 @@ config PROFILING
 config TRACEPOINTS
 	bool
 
+config ARCH_NO_SYSCALL_VERIFY_PRE_USERMODE_STATE
+	bool
+	help
+	  Disable the generic pre-usermode state verification. Allow each
+	  architecture to optimize how and when the verification is done.
+
 source "arch/Kconfig"
 
 endmenu		# General setup
diff --git a/kernel/sys.c b/kernel/sys.c
index 196c7134bee6..d30530ff8166 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2459,3 +2459,16 @@ COMPAT_SYSCALL_DEFINE1(sysinfo, struct compat_sysinfo __user *, info)
 	return 0;
 }
 #endif /* CONFIG_COMPAT */
+
+#ifdef CONFIG_ARCH_NO_SYSCALL_VERIFY_PRE_USERMODE_STATE
+/*
+ * This function is called when an architecture specific implementation detected
+ * an invalid address limit. The generic user-mode state checker will finish on
+ * the appropriate BUG_ON.
+ */
+asmlinkage void address_limit_check_failed(void)
+{
+	verify_pre_usermode_state();
+	panic("address_limit_check_failed called with a valid user-mode state");
+}
+#endif
-- 
2.12.2.715.g7642488e1d-goog

[toc] | [next] | [standalone]

#1620563 — [PATCH v7 3/4] arm/syscalls: Architecture specific pre-usermode check

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

[toc] | [prev] | [next] | [standalone]

#1620565 — [PATCH v7 2/4] x86/syscalls: Architecture specific pre-usermode check

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 user-mode state check is added to the prepare_exit_to_usermode
function. This function is called before any user-mode return on 32-bit
and on the 64-bit syscall slowpath. For the 64-bit syscall fast path, an
assembly address limit check redirects to the slow path if the address
limit is different.

The TASK_SIZE_MAX define is moved to the pgtable_64_types header so it
can be used in assembly code.

Signed-off-by: Thomas Garnier <thgarnie@google.com>
---
Based on next-20170410
---
 arch/x86/Kconfig                        |  1 +
 arch/x86/entry/common.c                 |  3 +++
 arch/x86/entry/entry_64.S               |  8 ++++++++
 arch/x86/include/asm/pgtable_64_types.h | 11 +++++++++++
 arch/x86/include/asm/processor.h        | 11 -----------
 5 files changed, 23 insertions(+), 11 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index c43f47622440..74185795eb24 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -63,6 +63,7 @@ config X86
 	select ARCH_MIGHT_HAVE_ACPI_PDC		if ACPI
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
+	select ARCH_NO_SYSCALL_VERIFY_PRE_USERMODE_STATE
 	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
 	select ARCH_SUPPORTS_NUMA_BALANCING	if X86_64
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index cdefcfdd9e63..76ef050255c9 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -23,6 +23,7 @@
 #include <linux/user-return-notifier.h>
 #include <linux/uprobes.h>
 #include <linux/livepatch.h>
+#include <linux/syscalls.h>
 
 #include <asm/desc.h>
 #include <asm/traps.h>
@@ -183,6 +184,8 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs)
 	struct thread_info *ti = current_thread_info();
 	u32 cached_flags;
 
+	verify_pre_usermode_state();
+
 	if (IS_ENABLED(CONFIG_PROVE_LOCKING) && WARN_ON(!irqs_disabled()))
 		local_irq_disable();
 
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 607d72c4a485..62aca6dcdaf4 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -218,6 +218,14 @@ entry_SYSCALL_64_fastpath:
 	testl	$_TIF_ALLWORK_MASK, TASK_TI_flags(%r11)
 	jnz	1f
 
+	/*
+	 * If address limit is not based on user-mode, jump to slow path for
+	 * additional security checks.
+	 */
+	movq	$TASK_SIZE_MAX, %rcx
+	cmp	%rcx, TASK_addr_limit(%r11)
+	jne	1f
+
 	LOCKDEP_SYS_EXIT
 	TRACE_IRQS_ON		/* user mode is traced as IRQs on */
 	movq	RIP(%rsp), %rcx
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 06470da156ba..78af4d43a7ce 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -104,4 +104,15 @@ typedef struct { pteval_t pte; } pte_t;
 
 #define EARLY_DYNAMIC_PAGE_TABLES	64
 
+/*
+ * User space process size. 47bits minus one guard page.  The guard
+ * page is necessary on Intel CPUs: if a SYSCALL instruction is at
+ * the highest possible canonical userspace address, then that
+ * syscall will enter the kernel with a non-canonical return
+ * address, and SYSRET will explode dangerously.  We avoid this
+ * particular problem by preventing anything from being mapped
+ * at the maximum canonical address.
+ */
+#define TASK_SIZE_MAX	((_AC(1, UL) << 47) - PAGE_SIZE)
+
 #endif /* _ASM_X86_PGTABLE_64_DEFS_H */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 3cada998a402..e80822582d3e 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -825,17 +825,6 @@ static inline void spin_lock_prefetch(const void *x)
 #define KSTK_ESP(task)		(task_pt_regs(task)->sp)
 
 #else
-/*
- * User space process size. 47bits minus one guard page.  The guard
- * page is necessary on Intel CPUs: if a SYSCALL instruction is at
- * the highest possible canonical userspace address, then that
- * syscall will enter the kernel with a non-canonical return
- * address, and SYSRET will explode dangerously.  We avoid this
- * particular problem by preventing anything from being mapped
- * at the maximum canonical address.
- */
-#define TASK_SIZE_MAX	((1UL << 47) - PAGE_SIZE)
-
 /* This decides where the kernel will search for a free chunk of vm
  * space during mmap's.
  */
-- 
2.12.2.715.g7642488e1d-goog

[toc] | [prev] | [next] | [standalone]

#1620566 — [PATCH v7 4/4] arm64/syscalls: Architecture specific pre-usermode check

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.
If it 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/arm64/Kconfig        |  1 +
 arch/arm64/kernel/entry.S | 13 +++++++++++++
 2 files changed, 14 insertions(+)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 9b8fcab7da56..3f9e8e7d9376 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -24,6 +24,7 @@ config ARM64
 	select ARCH_WANT_COMPAT_IPC_PARSE_VERSION
 	select ARCH_WANT_FRAME_POINTERS
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
+	select ARCH_NO_SYSCALL_VERIFY_PRE_USERMODE_STATE
 	select ARM_AMBA
 	select ARM_ARCH_TIMER
 	select ARM_GIC
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 43512d4d7df2..bdd094c7837a 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -744,6 +744,8 @@ ENDPROC(cpu_switch_to)
 ret_fast_syscall:
 	disable_irq				// disable interrupts
 	str	x0, [sp, #S_X0]			// returned x0
+	ldr	x2, [tsk, #TSK_TI_ADDR_LIMIT]	// check addr limit change
+	tbnz	x2, #63, addr_limit_fail
 	ldr	x1, [tsk, #TSK_TI_FLAGS]	// re-check for syscall tracing
 	and	x2, x1, #_TIF_SYSCALL_WORK
 	cbnz	x2, ret_fast_syscall_trace
@@ -771,6 +773,9 @@ work_pending:
  */
 ret_to_user:
 	disable_irq				// disable interrupts
+	ldr	x2, [tsk, #TSK_TI_ADDR_LIMIT]	// check addr limit change
+	tbnz	x2, #63, addr_limit_fail
+
 	ldr	x1, [tsk, #TSK_TI_FLAGS]
 	and	x2, x1, #_TIF_WORK_MASK
 	cbnz	x2, work_pending
@@ -780,6 +785,14 @@ finish_ret_to_user:
 ENDPROC(ret_to_user)
 
 /*
+ * Address limit was incorrect before returning in user-mode which could be
+ * used to elevate privileges. Call the generic handler to stop the kernel on
+ * the appropriate check. This function does not return.
+ */
+addr_limit_fail:
+	bl address_limit_check_failed
+
+/*
  * This is how we return from a fork.
  */
 ENTRY(ret_from_fork)
-- 
2.12.2.715.g7642488e1d-goog

[toc] | [prev] | [standalone]

Back to top | Article view | linux.kernel

csiph-web