Merge branch 'x86-syscall-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull syscall updates from Ingo Molnar:
 "Improve the security of set_fs(): we now check the address limit on a
  number of key platforms (x86, arm, arm64) before returning to
  user-space - without adding overhead to the typical system call fast
  path"

* 'x86-syscall-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  arm64/syscalls: Check address limit on user-mode return
  arm/syscalls: Check address limit on user-mode return
  x86/syscalls: Check address limit on user-mode return

arch/arm/include/asm/thread_info.h

@@ -139,10 +139,11 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *,
 #define TIF_NEED_RESCHED	1	/* rescheduling necessary */
 #define TIF_NOTIFY_RESUME	2	/* callback before returning to user */
 #define TIF_UPROBE		3	/* breakpointed or singlestepping */
-#define TIF_SYSCALL_TRACE	4	/* syscall trace active */
-#define TIF_SYSCALL_AUDIT	5	/* syscall auditing active */
-#define TIF_SYSCALL_TRACEPOINT	6	/* syscall tracepoint instrumentation */
-#define TIF_SECCOMP		7	/* seccomp syscall filtering active */
+#define TIF_FSCHECK		4	/* Check FS is USER_DS on return */
+#define TIF_SYSCALL_TRACE	5	/* syscall trace active */
+#define TIF_SYSCALL_AUDIT	6	/* syscall auditing active */
+#define TIF_SYSCALL_TRACEPOINT	7	/* syscall tracepoint instrumentation */
+#define TIF_SECCOMP		8	/* seccomp syscall filtering active */
 
 #define TIF_NOHZ		12	/* in adaptive nohz mode */
 #define TIF_USING_IWMMXT	17
@@ -153,6 +154,7 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *,
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
 #define _TIF_UPROBE		(1 << TIF_UPROBE)
+#define _TIF_FSCHECK		(1 << TIF_FSCHECK)
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
 #define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
 #define _TIF_SYSCALL_TRACEPOINT	(1 << TIF_SYSCALL_TRACEPOINT)
@@ -167,7 +169,8 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *,
  * Change these and you break ASM code in entry-common.S
  */
 #define _TIF_WORK_MASK		(_TIF_NEED_RESCHED | _TIF_SIGPENDING |	\
-				 _TIF_NOTIFY_RESUME | _TIF_UPROBE)
+				 _TIF_NOTIFY_RESUME | _TIF_UPROBE |	\
+				 _TIF_FSCHECK)
 
 #endif /* __KERNEL__ */
 #endif /* __ASM_ARM_THREAD_INFO_H */

arch/arm/include/asm/uaccess.h

@@ -70,6 +70,8 @@ static inline void set_fs(mm_segment_t fs)
 {
 	current_thread_info()->addr_limit = fs;
 	modify_domain(DOMAIN_KERNEL, fs ? DOMAIN_CLIENT : DOMAIN_MANAGER);
+	/* On user-mode return, check fs is correct */
+	set_thread_flag(TIF_FSCHECK);
 }
 
 #define segment_eq(a, b)	((a) == (b))

arch/arm/kernel/entry-common.S

@@ -41,7 +41,9 @@ ret_fast_syscall:
  UNWIND(.cantunwind	)
 	disable_irq_notrace			@ disable interrupts
 	ldr	r1, [tsk, #TI_FLAGS]		@ re-check for syscall tracing
-	tst	r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK
+	tst	r1, #_TIF_SYSCALL_WORK
+	bne	fast_work_pending
+	tst	r1, #_TIF_WORK_MASK
 	bne	fast_work_pending
 
 	/* perform architecture specific actions before user return */
@@ -67,12 +69,15 @@ ret_fast_syscall:
 	str	r0, [sp, #S_R0 + S_OFF]!	@ save returned r0
 	disable_irq_notrace			@ disable interrupts
 	ldr	r1, [tsk, #TI_FLAGS]		@ re-check for syscall tracing
-	tst	r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK
+	tst	r1, #_TIF_SYSCALL_WORK
+	bne	fast_work_pending
+	tst	r1, #_TIF_WORK_MASK
 	beq	no_work_pending
  UNWIND(.fnend		)
 ENDPROC(ret_fast_syscall)
 
 	/* Slower path - fall through to work_pending */
+fast_work_pending:
 #endif
 
 	tst	r1, #_TIF_SYSCALL_WORK

arch/arm/kernel/signal.c

@@ -14,6 +14,7 @@
 #include <linux/uaccess.h>
 #include <linux/tracehook.h>
 #include <linux/uprobes.h>
+#include <linux/syscalls.h>
 
 #include <asm/elf.h>
 #include <asm/cacheflush.h>
@@ -613,6 +614,10 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall)
 	 * Update the trace code with the current status.
 	 */
 	trace_hardirqs_off();
+
+	/* Check valid user FS if needed */
+	addr_limit_user_check();
+
 	do {
 		if (likely(thread_flags & _TIF_NEED_RESCHED)) {
 			schedule();

arch/arm64/include/asm/thread_info.h

@@ -86,6 +86,7 @@ struct thread_info {
 #define TIF_NOTIFY_RESUME	2	/* callback before returning to user */
 #define TIF_FOREIGN_FPSTATE	3	/* CPU's FP state is not current's */
 #define TIF_UPROBE		4	/* uprobe breakpoint or singlestep */
+#define TIF_FSCHECK		5	/* Check FS is USER_DS on return */
 #define TIF_NOHZ		7
 #define TIF_SYSCALL_TRACE	8
 #define TIF_SYSCALL_AUDIT	9
@@ -107,11 +108,12 @@ struct thread_info {
 #define _TIF_SYSCALL_TRACEPOINT	(1 << TIF_SYSCALL_TRACEPOINT)
 #define _TIF_SECCOMP		(1 << TIF_SECCOMP)
 #define _TIF_UPROBE		(1 << TIF_UPROBE)
+#define _TIF_FSCHECK		(1 << TIF_FSCHECK)
 #define _TIF_32BIT		(1 << TIF_32BIT)
 
 #define _TIF_WORK_MASK		(_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
 				 _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE | \
-				 _TIF_UPROBE)
+				 _TIF_UPROBE | _TIF_FSCHECK)
 
 #define _TIF_SYSCALL_WORK	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
 				 _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \

arch/arm64/include/asm/uaccess.h

@@ -45,6 +45,9 @@ static inline void set_fs(mm_segment_t fs)
 {
 	current_thread_info()->addr_limit = fs;
 
+	/* On user-mode return, check fs is correct */
+	set_thread_flag(TIF_FSCHECK);
+
 	/*
 	 * Enable/disable UAO so that copy_to_user() etc can access
 	 * kernel memory with the unprivileged instructions.

arch/arm64/kernel/signal.c

@@ -29,6 +29,7 @@
 #include <linux/string.h>
 #include <linux/tracehook.h>
 #include <linux/ratelimit.h>
+#include <linux/syscalls.h>
 
 #include <asm/debug-monitors.h>
 #include <asm/elf.h>
@@ -749,6 +750,10 @@ asmlinkage void do_notify_resume(struct pt_regs *regs,
 	 * Update the trace code with the current status.
 	 */
 	trace_hardirqs_off();
+
+	/* Check valid user FS if needed */
+	addr_limit_user_check();
+
 	do {
 		if (thread_flags & _TIF_NEED_RESCHED) {
 			schedule();

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;
 
+	addr_limit_user_check();
+
 	if (IS_ENABLED(CONFIG_PROVE_LOCKING) && WARN_ON(!irqs_disabled()))
 		local_irq_disable();
 

arch/x86/include/asm/thread_info.h

@@ -98,6 +98,7 @@ struct thread_info {
 #define TIF_SYSCALL_TRACEPOINT	28	/* syscall tracepoint instrumentation */
 #define TIF_ADDR32		29	/* 32-bit address space on 64 bits */
 #define TIF_X32			30	/* 32-bit native x86-64 binary */
+#define TIF_FSCHECK		31	/* Check FS is USER_DS on return */
 
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
@@ -122,6 +123,7 @@ struct thread_info {
 #define _TIF_SYSCALL_TRACEPOINT	(1 << TIF_SYSCALL_TRACEPOINT)
 #define _TIF_ADDR32		(1 << TIF_ADDR32)
 #define _TIF_X32		(1 << TIF_X32)
+#define _TIF_FSCHECK		(1 << TIF_FSCHECK)
 
 /*
  * work to do in syscall_trace_enter().  Also includes TIF_NOHZ for
@@ -137,7 +139,8 @@ struct thread_info {
 	(_TIF_SYSCALL_TRACE | _TIF_NOTIFY_RESUME | _TIF_SIGPENDING |	\
 	 _TIF_NEED_RESCHED | _TIF_SINGLESTEP | _TIF_SYSCALL_EMU |	\
 	 _TIF_SYSCALL_AUDIT | _TIF_USER_RETURN_NOTIFY | _TIF_UPROBE |	\
-	 _TIF_PATCH_PENDING | _TIF_NOHZ | _TIF_SYSCALL_TRACEPOINT)
+	 _TIF_PATCH_PENDING | _TIF_NOHZ | _TIF_SYSCALL_TRACEPOINT |	\
+	 _TIF_FSCHECK)
 
 /* flags to check in __switch_to() */
 #define _TIF_WORK_CTXSW							\

arch/x86/include/asm/uaccess.h

@@ -26,7 +26,12 @@
 
 #define get_ds()	(KERNEL_DS)
 #define get_fs()	(current->thread.addr_limit)
-#define set_fs(x)	(current->thread.addr_limit = (x))
+static inline void set_fs(mm_segment_t fs)
+{
+	current->thread.addr_limit = fs;
+	/* On user-mode return, check fs is correct */
+	set_thread_flag(TIF_FSCHECK);
+}
 
 #define segment_eq(a, b)	((a).seg == (b).seg)
 

include/linux/syscalls.h

@@ -207,6 +207,22 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 	}								\
 	static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__))
 
+#ifdef TIF_FSCHECK
+/*
+ * 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 addr_limit_user_check(void)
+{
+
+	if (!test_thread_flag(TIF_FSCHECK))
+		return;
+
+	BUG_ON(!segment_eq(get_fs(), USER_DS));
+	clear_thread_flag(TIF_FSCHECK);
+}
+#endif
+
 asmlinkage long sys32_quotactl(unsigned int cmd, const char __user *special,
 			       qid_t id, void __user *addr);
 asmlinkage long sys_time(time_t __user *tloc);