Merge branch 'uaccess' into fixes

arch/arm/Kconfig

@@ -1700,6 +1700,21 @@ config HIGHPTE
 	  consumed by page tables.  Setting this option will allow
 	  user-space 2nd level page tables to reside in high memory.
 
+config CPU_SW_DOMAIN_PAN
+	bool "Enable use of CPU domains to implement privileged no-access"
+	depends on MMU && !ARM_LPAE
+	default y
+	help
+	  Increase kernel security by ensuring that normal kernel accesses
+	  are unable to access userspace addresses.  This can help prevent
+	  use-after-free bugs becoming an exploitable privilege escalation
+	  by ensuring that magic values (such as LIST_POISON) will always
+	  fault when dereferenced.
+
+	  CPUs with low-vector mappings use a best-efforts implementation.
+	  Their lower 1MB needs to remain accessible for the vectors, but
+	  the remainder of userspace will become appropriately inaccessible.
+
 config HW_PERF_EVENTS
 	bool "Enable hardware performance counter support for perf events"
 	depends on PERF_EVENTS

arch/arm/include/asm/assembler.h

@@ -445,6 +445,48 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 #endif
 	.endm
 
+	.macro	uaccess_disable, tmp, isb=1
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+	/*
+	 * Whenever we re-enter userspace, the domains should always be
+	 * set appropriately.
+	 */
+	mov	\tmp, #DACR_UACCESS_DISABLE
+	mcr	p15, 0, \tmp, c3, c0, 0		@ Set domain register
+	.if	\isb
+	instr_sync
+	.endif
+#endif
+	.endm
+
+	.macro	uaccess_enable, tmp, isb=1
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+	/*
+	 * Whenever we re-enter userspace, the domains should always be
+	 * set appropriately.
+	 */
+	mov	\tmp, #DACR_UACCESS_ENABLE
+	mcr	p15, 0, \tmp, c3, c0, 0
+	.if	\isb
+	instr_sync
+	.endif
+#endif
+	.endm
+
+	.macro	uaccess_save, tmp
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+	mrc	p15, 0, \tmp, c3, c0, 0
+	str	\tmp, [sp, #S_FRAME_SIZE]
+#endif
+	.endm
+
+	.macro	uaccess_restore
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+	ldr	r0, [sp, #S_FRAME_SIZE]
+	mcr	p15, 0, r0, c3, c0, 0
+#endif
+	.endm
+
 	.irp	c,,eq,ne,cs,cc,mi,pl,vs,vc,hi,ls,ge,lt,gt,le,hs,lo
 	.macro	ret\c, reg
 #if __LINUX_ARM_ARCH__ < 6

arch/arm/include/asm/domain.h

@@ -12,6 +12,7 @@
 
 #ifndef __ASSEMBLY__
 #include <asm/barrier.h>
+#include <asm/thread_info.h>
 #endif
 
 /*
@@ -34,15 +35,14 @@
  */
 #ifndef CONFIG_IO_36
 #define DOMAIN_KERNEL	0
-#define DOMAIN_TABLE	0
 #define DOMAIN_USER	1
 #define DOMAIN_IO	2
 #else
 #define DOMAIN_KERNEL	2
-#define DOMAIN_TABLE	2
 #define DOMAIN_USER	1
 #define DOMAIN_IO	0
 #endif
+#define DOMAIN_VECTORS	3
 
 /*
  * Domain types
@@ -55,30 +55,65 @@
 #define DOMAIN_MANAGER	1
 #endif
 
-#define domain_val(dom,type)	((type) << (2*(dom)))
+#define domain_mask(dom)	((3) << (2 * (dom)))
+#define domain_val(dom,type)	((type) << (2 * (dom)))
+
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+#define DACR_INIT \
+	(domain_val(DOMAIN_USER, DOMAIN_NOACCESS) | \
+	 domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) | \
+	 domain_val(DOMAIN_IO, DOMAIN_CLIENT) | \
+	 domain_val(DOMAIN_VECTORS, DOMAIN_CLIENT))
+#else
+#define DACR_INIT \
+	(domain_val(DOMAIN_USER, DOMAIN_CLIENT) | \
+	 domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) | \
+	 domain_val(DOMAIN_IO, DOMAIN_CLIENT) | \
+	 domain_val(DOMAIN_VECTORS, DOMAIN_CLIENT))
+#endif
+
+#define __DACR_DEFAULT \
+	domain_val(DOMAIN_KERNEL, DOMAIN_CLIENT) | \
+	domain_val(DOMAIN_IO, DOMAIN_CLIENT) | \
+	domain_val(DOMAIN_VECTORS, DOMAIN_CLIENT)
+
+#define DACR_UACCESS_DISABLE	\
+	(__DACR_DEFAULT | domain_val(DOMAIN_USER, DOMAIN_NOACCESS))
+#define DACR_UACCESS_ENABLE	\
+	(__DACR_DEFAULT | domain_val(DOMAIN_USER, DOMAIN_CLIENT))
 
 #ifndef __ASSEMBLY__
 
-#ifdef CONFIG_CPU_USE_DOMAINS
+static inline unsigned int get_domain(void)
+{
+	unsigned int domain;
+
+	asm(
+	"mrc	p15, 0, %0, c3, c0	@ get domain"
+	 : "=r" (domain)
+	 : "m" (current_thread_info()->cpu_domain));
+
+	return domain;
+}
+
 static inline void set_domain(unsigned val)
 {
 	asm volatile(
 	"mcr	p15, 0, %0, c3, c0	@ set domain"
-	  : : "r" (val));
+	  : : "r" (val) : "memory");
 	isb();
 }
 
+#ifdef CONFIG_CPU_USE_DOMAINS
 #define modify_domain(dom,type)					\
 	do {							\
-	struct thread_info *thread = current_thread_info();	\
-	unsigned int domain = thread->cpu_domain;		\
-	domain &= ~domain_val(dom, DOMAIN_MANAGER);		\
-	thread->cpu_domain = domain | domain_val(dom, type);	\
-	set_domain(thread->cpu_domain);				\
+		unsigned int domain = get_domain();		\
+		domain &= ~domain_mask(dom);			\
+		domain = domain | domain_val(dom, type);	\
+		set_domain(domain);				\
 	} while (0)
 
 #else
-static inline void set_domain(unsigned val) { }
 static inline void modify_domain(unsigned dom, unsigned type)	{ }
 #endif
 

arch/arm/include/asm/futex.h

@@ -22,8 +22,11 @@
 #ifdef CONFIG_SMP
 
 #define __futex_atomic_op(insn, ret, oldval, tmp, uaddr, oparg)	\
+({								\
+	unsigned int __ua_flags;				\
 	smp_mb();						\
 	prefetchw(uaddr);					\
+	__ua_flags = uaccess_save_and_enable();			\
 	__asm__ __volatile__(					\
 	"1:	ldrex	%1, [%3]\n"				\
 	"	" insn "\n"					\
@@ -34,12 +37,15 @@
 	__futex_atomic_ex_table("%5")				\
 	: "=&r" (ret), "=&r" (oldval), "=&r" (tmp)		\
 	: "r" (uaddr), "r" (oparg), "Ir" (-EFAULT)		\
-	: "cc", "memory")
+	: "cc", "memory");					\
+	uaccess_restore(__ua_flags);				\
+})
 
 static inline int
 futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 			      u32 oldval, u32 newval)
 {
+	unsigned int __ua_flags;
 	int ret;
 	u32 val;
 
@@ -49,6 +55,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	smp_mb();
 	/* Prefetching cannot fault */
 	prefetchw(uaddr);
+	__ua_flags = uaccess_save_and_enable();
 	__asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n"
 	"1:	ldrex	%1, [%4]\n"
 	"	teq	%1, %2\n"
@@ -61,6 +68,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	: "=&r" (ret), "=&r" (val)
 	: "r" (oldval), "r" (newval), "r" (uaddr), "Ir" (-EFAULT)
 	: "cc", "memory");
+	uaccess_restore(__ua_flags);
 	smp_mb();
 
 	*uval = val;
@@ -73,6 +81,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 #include <asm/domain.h>
 
 #define __futex_atomic_op(insn, ret, oldval, tmp, uaddr, oparg)	\
+({								\
+	unsigned int __ua_flags = uaccess_save_and_enable();	\
 	__asm__ __volatile__(					\
 	"1:	" TUSER(ldr) "	%1, [%3]\n"			\
 	"	" insn "\n"					\
@@ -81,12 +91,15 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	__futex_atomic_ex_table("%5")				\
 	: "=&r" (ret), "=&r" (oldval), "=&r" (tmp)		\
 	: "r" (uaddr), "r" (oparg), "Ir" (-EFAULT)		\
-	: "cc", "memory")
+	: "cc", "memory");					\
+	uaccess_restore(__ua_flags);				\
+})
 
 static inline int
 futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 			      u32 oldval, u32 newval)
 {
+	unsigned int __ua_flags;
 	int ret = 0;
 	u32 val;
 
@@ -94,6 +107,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 		return -EFAULT;
 
 	preempt_disable();
+	__ua_flags = uaccess_save_and_enable();
 	__asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n"
 	"1:	" TUSER(ldr) "	%1, [%4]\n"
 	"	teq	%1, %2\n"
@@ -103,6 +117,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	: "+r" (ret), "=&r" (val)
 	: "r" (oldval), "r" (newval), "r" (uaddr), "Ir" (-EFAULT)
 	: "cc", "memory");
+	uaccess_restore(__ua_flags);
 
 	*uval = val;
 	preempt_enable();

arch/arm/include/asm/pgtable-2level-hwdef.h

@@ -23,6 +23,7 @@
 #define PMD_PXNTABLE		(_AT(pmdval_t, 1) << 2)     /* v7 */
 #define PMD_BIT4		(_AT(pmdval_t, 1) << 4)
 #define PMD_DOMAIN(x)		(_AT(pmdval_t, (x)) << 5)
+#define PMD_DOMAIN_MASK		PMD_DOMAIN(0x0f)
 #define PMD_PROTECTION		(_AT(pmdval_t, 1) << 9)		/* v5 */
 /*
  *   - section

arch/arm/include/asm/thread_info.h

@@ -25,7 +25,6 @@
 struct task_struct;
 
 #include <asm/types.h>
-#include <asm/domain.h>
 
 typedef unsigned long mm_segment_t;
 
@@ -74,9 +73,6 @@ struct thread_info {
 	.flags		= 0,						\
 	.preempt_count	= INIT_PREEMPT_COUNT,				\
 	.addr_limit	= KERNEL_DS,					\
-	.cpu_domain	= domain_val(DOMAIN_USER, DOMAIN_MANAGER) |	\
-			  domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) |	\
-			  domain_val(DOMAIN_IO, DOMAIN_CLIENT),		\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)

arch/arm/include/asm/uaccess.h

@@ -49,6 +49,35 @@ struct exception_table_entry
 
 extern int fixup_exception(struct pt_regs *regs);
 
+/*
+ * These two functions allow hooking accesses to userspace to increase
+ * system integrity by ensuring that the kernel can not inadvertantly
+ * perform such accesses (eg, via list poison values) which could then
+ * be exploited for priviledge escalation.
+ */
+static inline unsigned int uaccess_save_and_enable(void)
+{
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+	unsigned int old_domain = get_domain();
+
+	/* Set the current domain access to permit user accesses */
+	set_domain((old_domain & ~domain_mask(DOMAIN_USER)) |
+		   domain_val(DOMAIN_USER, DOMAIN_CLIENT));
+
+	return old_domain;
+#else
+	return 0;
+#endif
+}
+
+static inline void uaccess_restore(unsigned int flags)
+{
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+	/* Restore the user access mask */
+	set_domain(flags);
+#endif
+}
+
 /*
  * These two are intentionally not defined anywhere - if the kernel
  * code generates any references to them, that's a bug.
@@ -165,6 +194,7 @@ extern int __get_user_64t_4(void *);
 		register typeof(x) __r2 asm("r2");			\
 		register unsigned long __l asm("r1") = __limit;		\
 		register int __e asm("r0");				\
+		unsigned int __ua_flags = uaccess_save_and_enable();	\
 		switch (sizeof(*(__p))) {				\
 		case 1:							\
 			if (sizeof((x)) >= 8)				\
@@ -192,6 +222,7 @@ extern int __get_user_64t_4(void *);
 			break;						\
 		default: __e = __get_user_bad(); break;			\
 		}							\
+		uaccess_restore(__ua_flags);				\
 		x = (typeof(*(p))) __r2;				\
 		__e;							\
 	})
@@ -224,6 +255,7 @@ extern int __put_user_8(void *, unsigned long long);
 		register const typeof(*(p)) __user *__p asm("r0") = __tmp_p; \
 		register unsigned long __l asm("r1") = __limit;		\
 		register int __e asm("r0");				\
+		unsigned int __ua_flags = uaccess_save_and_enable();	\
 		switch (sizeof(*(__p))) {				\
 		case 1:							\
 			__put_user_x(__r2, __p, __e, __l, 1);		\
@@ -239,6 +271,7 @@ extern int __put_user_8(void *, unsigned long long);
 			break;						\
 		default: __e = __put_user_bad(); break;			\
 		}							\
+		uaccess_restore(__ua_flags);				\
 		__e;							\
 	})
 
@@ -300,14 +333,17 @@ static inline void set_fs(mm_segment_t fs)
 do {									\
 	unsigned long __gu_addr = (unsigned long)(ptr);			\
 	unsigned long __gu_val;						\
+	unsigned int __ua_flags;					\
 	__chk_user_ptr(ptr);						\
 	might_fault();							\
+	__ua_flags = uaccess_save_and_enable();				\
 	switch (sizeof(*(ptr))) {					\
 	case 1:	__get_user_asm_byte(__gu_val, __gu_addr, err);	break;	\
 	case 2:	__get_user_asm_half(__gu_val, __gu_addr, err);	break;	\
 	case 4:	__get_user_asm_word(__gu_val, __gu_addr, err);	break;	\
 	default: (__gu_val) = __get_user_bad();				\
 	}								\
+	uaccess_restore(__ua_flags);					\
 	(x) = (__typeof__(*(ptr)))__gu_val;				\
 } while (0)
 
@@ -381,9 +417,11 @@ do {									\
 #define __put_user_err(x, ptr, err)					\
 do {									\
 	unsigned long __pu_addr = (unsigned long)(ptr);			\
+	unsigned int __ua_flags;					\
 	__typeof__(*(ptr)) __pu_val = (x);				\
 	__chk_user_ptr(ptr);						\
 	might_fault();							\
+	__ua_flags = uaccess_save_and_enable();				\
 	switch (sizeof(*(ptr))) {					\
 	case 1: __put_user_asm_byte(__pu_val, __pu_addr, err);	break;	\
 	case 2: __put_user_asm_half(__pu_val, __pu_addr, err);	break;	\
@@ -391,6 +429,7 @@ do {									\
 	case 8:	__put_user_asm_dword(__pu_val, __pu_addr, err);	break;	\
 	default: __put_user_bad();					\
 	}								\
+	uaccess_restore(__ua_flags);					\
 } while (0)
 
 #define __put_user_asm_byte(x, __pu_addr, err)			\
@@ -474,11 +513,46 @@ do {									\
 
 
 #ifdef CONFIG_MMU
-extern unsigned long __must_check __copy_from_user(void *to, const void __user *from, unsigned long n);
-extern unsigned long __must_check __copy_to_user(void __user *to, const void *from, unsigned long n);
-extern unsigned long __must_check __copy_to_user_std(void __user *to, const void *from, unsigned long n);
-extern unsigned long __must_check __clear_user(void __user *addr, unsigned long n);
-extern unsigned long __must_check __clear_user_std(void __user *addr, unsigned long n);
+extern unsigned long __must_check
+arm_copy_from_user(void *to, const void __user *from, unsigned long n);
+
+static inline unsigned long __must_check
+__copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+	unsigned int __ua_flags = uaccess_save_and_enable();
+	n = arm_copy_from_user(to, from, n);
+	uaccess_restore(__ua_flags);
+	return n;
+}
+
+extern unsigned long __must_check
+arm_copy_to_user(void __user *to, const void *from, unsigned long n);
+extern unsigned long __must_check
+__copy_to_user_std(void __user *to, const void *from, unsigned long n);
+
+static inline unsigned long __must_check
+__copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+	unsigned int __ua_flags = uaccess_save_and_enable();
+	n = arm_copy_to_user(to, from, n);
+	uaccess_restore(__ua_flags);
+	return n;
+}
+
+extern unsigned long __must_check
+arm_clear_user(void __user *addr, unsigned long n);
+extern unsigned long __must_check
+__clear_user_std(void __user *addr, unsigned long n);
+
+static inline unsigned long __must_check
+__clear_user(void __user *addr, unsigned long n)
+{
+	unsigned int __ua_flags = uaccess_save_and_enable();
+	n = arm_clear_user(addr, n);
+	uaccess_restore(__ua_flags);
+	return n;
+}
+
 #else
 #define __copy_from_user(to, from, n)	(memcpy(to, (void __force *)from, n), 0)
 #define __copy_to_user(to, from, n)	(memcpy((void __force *)to, from, n), 0)
@@ -511,6 +585,7 @@ static inline unsigned long __must_check clear_user(void __user *to, unsigned lo
 	return n;
 }
 
+/* These are from lib/ code, and use __get_user() and friends */
 extern long strncpy_from_user(char *dest, const char __user *src, long count);
 
 extern __must_check long strlen_user(const char __user *str);

arch/arm/kernel/armksyms.c

@@ -97,9 +97,9 @@ EXPORT_SYMBOL(mmiocpy);
 #ifdef CONFIG_MMU
 EXPORT_SYMBOL(copy_page);
 
-EXPORT_SYMBOL(__copy_from_user);
-EXPORT_SYMBOL(__copy_to_user);
-EXPORT_SYMBOL(__clear_user);
+EXPORT_SYMBOL(arm_copy_from_user);
+EXPORT_SYMBOL(arm_copy_to_user);
+EXPORT_SYMBOL(arm_clear_user);
 
 EXPORT_SYMBOL(__get_user_1);
 EXPORT_SYMBOL(__get_user_2);

arch/arm/kernel/entry-armv.S

@@ -149,10 +149,10 @@ ENDPROC(__und_invalid)
 #define SPFIX(code...)
 #endif
 
-	.macro	svc_entry, stack_hole=0, trace=1
+	.macro	svc_entry, stack_hole=0, trace=1, uaccess=1
  UNWIND(.fnstart		)
  UNWIND(.save {r0 - pc}		)
-	sub	sp, sp, #(S_FRAME_SIZE + \stack_hole - 4)
+	sub	sp, sp, #(S_FRAME_SIZE + 8 + \stack_hole - 4)
 #ifdef CONFIG_THUMB2_KERNEL
  SPFIX(	str	r0, [sp]	)	@ temporarily saved
  SPFIX(	mov	r0, sp		)
@@ -167,7 +167,7 @@ ENDPROC(__und_invalid)
 	ldmia	r0, {r3 - r5}
 	add	r7, sp, #S_SP - 4	@ here for interlock avoidance
 	mov	r6, #-1			@  ""  ""      ""       ""
-	add	r2, sp, #(S_FRAME_SIZE + \stack_hole - 4)
+	add	r2, sp, #(S_FRAME_SIZE + 8 + \stack_hole - 4)
  SPFIX(	addeq	r2, r2, #4	)
 	str	r3, [sp, #-4]!		@ save the "real" r0 copied
 					@ from the exception stack
@@ -185,6 +185,11 @@ ENDPROC(__und_invalid)
 	@
 	stmia	r7, {r2 - r6}
 
+	uaccess_save r0
+	.if \uaccess
+	uaccess_disable r0
+	.endif
+
 	.if \trace
 #ifdef CONFIG_TRACE_IRQFLAGS
 	bl	trace_hardirqs_off
@@ -194,7 +199,7 @@ ENDPROC(__und_invalid)
 
 	.align	5
 __dabt_svc:
-	svc_entry
+	svc_entry uaccess=0
 	mov	r2, sp
 	dabt_helper
  THUMB(	ldr	r5, [sp, #S_PSR]	)	@ potentially updated CPSR
@@ -368,7 +373,7 @@ ENDPROC(__fiq_abt)
 #error "sizeof(struct pt_regs) must be a multiple of 8"
 #endif
 
-	.macro	usr_entry, trace=1
+	.macro	usr_entry, trace=1, uaccess=1
  UNWIND(.fnstart	)
  UNWIND(.cantunwind	)	@ don't unwind the user space
 	sub	sp, sp, #S_FRAME_SIZE
@@ -400,6 +405,10 @@ ENDPROC(__fiq_abt)
  ARM(	stmdb	r0, {sp, lr}^			)
  THUMB(	store_user_sp_lr r0, r1, S_SP - S_PC	)
 
+	.if \uaccess
+	uaccess_disable ip
+	.endif
+
 	@ Enable the alignment trap while in kernel mode
  ATRAP(	teq	r8, r7)
  ATRAP( mcrne	p15, 0, r8, c1, c0, 0)
@@ -435,7 +444,7 @@ ENDPROC(__fiq_abt)
 
 	.align	5
 __dabt_usr:
-	usr_entry
+	usr_entry uaccess=0
 	kuser_cmpxchg_check
 	mov	r2, sp
 	dabt_helper
@@ -458,7 +467,7 @@ ENDPROC(__irq_usr)
 
 	.align	5
 __und_usr:
-	usr_entry
+	usr_entry uaccess=0
 
 	mov	r2, r4
 	mov	r3, r5
@@ -484,6 +493,8 @@ __und_usr:
 1:	ldrt	r0, [r4]
  ARM_BE8(rev	r0, r0)				@ little endian instruction
 
+	uaccess_disable ip
+
 	@ r0 = 32-bit ARM instruction which caused the exception
 	@ r2 = PC value for the following instruction (:= regs->ARM_pc)
 	@ r4 = PC value for the faulting instruction
@@ -518,9 +529,10 @@ __und_usr_thumb:
 2:	ldrht	r5, [r4]
 ARM_BE8(rev16	r5, r5)				@ little endian instruction
 	cmp	r5, #0xe800			@ 32bit instruction if xx != 0
-	blo	__und_usr_fault_16		@ 16bit undefined instruction
+	blo	__und_usr_fault_16_pan		@ 16bit undefined instruction
 3:	ldrht	r0, [r2]
 ARM_BE8(rev16	r0, r0)				@ little endian instruction
+	uaccess_disable ip
 	add	r2, r2, #2			@ r2 is PC + 2, make it PC + 4
 	str	r2, [sp, #S_PC]			@ it's a 2x16bit instr, update
 	orr	r0, r0, r5, lsl #16
@@ -715,6 +727,8 @@ ENDPROC(no_fp)
 __und_usr_fault_32:
 	mov	r1, #4
 	b	1f
+__und_usr_fault_16_pan:
+	uaccess_disable ip
 __und_usr_fault_16:
 	mov	r1, #2
 1:	mov	r0, sp
@@ -770,6 +784,8 @@ ENTRY(__switch_to)
 	ldr	r4, [r2, #TI_TP_VALUE]
 	ldr	r5, [r2, #TI_TP_VALUE + 4]
 #ifdef CONFIG_CPU_USE_DOMAINS
+	mrc	p15, 0, r6, c3, c0, 0		@ Get domain register
+	str	r6, [r1, #TI_CPU_DOMAIN]	@ Save old domain register
 	ldr	r6, [r2, #TI_CPU_DOMAIN]
 #endif
 	switch_tls r1, r4, r5, r3, r7

arch/arm/kernel/entry-common.S

@@ -174,6 +174,8 @@ ENTRY(vector_swi)
  USER(	ldr	scno, [lr, #-4]		)	@ get SWI instruction
 #endif
 
+	uaccess_disable tbl
+
 	adr	tbl, sys_call_table		@ load syscall table pointer
 
 #if defined(CONFIG_OABI_COMPAT)

arch/arm/kernel/entry-header.S

@@ -196,7 +196,7 @@
 	msr	cpsr_c, \rtemp			@ switch back to the SVC mode
 	.endm
 
-#ifndef CONFIG_THUMB2_KERNEL
+
 	.macro	svc_exit, rpsr, irq = 0
 	.if	\irq != 0
 	@ IRQs already off
@@ -215,6 +215,10 @@
 	blne	trace_hardirqs_off
 #endif
 	.endif
+	uaccess_restore
+
+#ifndef CONFIG_THUMB2_KERNEL
+	@ ARM mode SVC restore
 	msr	spsr_cxsf, \rpsr
 #if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_32v6K)
 	@ We must avoid clrex due to Cortex-A15 erratum #830321
@@ -222,6 +226,20 @@
 	strex	r1, r2, [r0]			@ clear the exclusive monitor
 #endif
 	ldmia	sp, {r0 - pc}^			@ load r0 - pc, cpsr
+#else
+	@ Thumb mode SVC restore
+	ldr	lr, [sp, #S_SP]			@ top of the stack
+	ldrd	r0, r1, [sp, #S_LR]		@ calling lr and pc
+
+	@ We must avoid clrex due to Cortex-A15 erratum #830321
+	strex	r2, r1, [sp, #S_LR]		@ clear the exclusive monitor
+
+	stmdb	lr!, {r0, r1, \rpsr}		@ calling lr and rfe context
+	ldmia	sp, {r0 - r12}
+	mov	sp, lr
+	ldr	lr, [sp], #4
+	rfeia	sp!
+#endif
 	.endm
 
 	@
@@ -241,6 +259,9 @@
 	@ on the stack remains correct).
 	@
 	.macro  svc_exit_via_fiq
+	uaccess_restore
+#ifndef CONFIG_THUMB2_KERNEL
+	@ ARM mode restore
 	mov	r0, sp
 	ldmib	r0, {r1 - r14}	@ abort is deadly from here onward (it will
 				@ clobber state restored below)
@@ -250,9 +271,27 @@
 	msr	spsr_cxsf, r9
 	ldr	r0, [r0, #S_R0]
 	ldmia	r8, {pc}^
+#else
+	@ Thumb mode restore
+	add	r0, sp, #S_R2
+	ldr	lr, [sp, #S_LR]
+	ldr	sp, [sp, #S_SP] @ abort is deadly from here onward (it will
+			        @ clobber state restored below)
+	ldmia	r0, {r2 - r12}
+	mov	r1, #FIQ_MODE | PSR_I_BIT | PSR_F_BIT
+	msr	cpsr_c, r1
+	sub	r0, #S_R2
+	add	r8, r0, #S_PC
+	ldmia	r0, {r0 - r1}
+	rfeia	r8
+#endif
 	.endm
 
+
 	.macro	restore_user_regs, fast = 0, offset = 0
+	uaccess_enable r1, isb=0
+#ifndef CONFIG_THUMB2_KERNEL
+	@ ARM mode restore
 	mov	r2, sp
 	ldr	r1, [r2, #\offset + S_PSR]	@ get calling cpsr
 	ldr	lr, [r2, #\offset + S_PC]!	@ get pc
@@ -270,72 +309,16 @@
 						@ after ldm {}^
 	add	sp, sp, #\offset + S_FRAME_SIZE
 	movs	pc, lr				@ return & move spsr_svc into cpsr
-	.endm
-
-#else	/* CONFIG_THUMB2_KERNEL */
-	.macro	svc_exit, rpsr, irq = 0
-	.if	\irq != 0
-	@ IRQs already off
-#ifdef CONFIG_TRACE_IRQFLAGS
-	@ The parent context IRQs must have been enabled to get here in
-	@ the first place, so there's no point checking the PSR I bit.
-	bl	trace_hardirqs_on
-#endif
-	.else
-	@ IRQs off again before pulling preserved data off the stack
-	disable_irq_notrace
-#ifdef CONFIG_TRACE_IRQFLAGS
-	tst	\rpsr, #PSR_I_BIT
-	bleq	trace_hardirqs_on
-	tst	\rpsr, #PSR_I_BIT
-	blne	trace_hardirqs_off
-#endif
-	.endif
-	ldr	lr, [sp, #S_SP]			@ top of the stack
-	ldrd	r0, r1, [sp, #S_LR]		@ calling lr and pc
-
-	@ We must avoid clrex due to Cortex-A15 erratum #830321
-	strex	r2, r1, [sp, #S_LR]		@ clear the exclusive monitor
-
-	stmdb	lr!, {r0, r1, \rpsr}		@ calling lr and rfe context
-	ldmia	sp, {r0 - r12}
-	mov	sp, lr
-	ldr	lr, [sp], #4
-	rfeia	sp!
-	.endm
-
-	@
-	@ svc_exit_via_fiq - like svc_exit but switches to FIQ mode before exit
-	@
-	@ For full details see non-Thumb implementation above.
-	@
-	.macro  svc_exit_via_fiq
-	add	r0, sp, #S_R2
-	ldr	lr, [sp, #S_LR]
-	ldr	sp, [sp, #S_SP] @ abort is deadly from here onward (it will
-			        @ clobber state restored below)
-	ldmia	r0, {r2 - r12}
-	mov	r1, #FIQ_MODE | PSR_I_BIT | PSR_F_BIT
-	msr	cpsr_c, r1
-	sub	r0, #S_R2
-	add	r8, r0, #S_PC
-	ldmia	r0, {r0 - r1}
-	rfeia	r8
-	.endm
-
-#ifdef CONFIG_CPU_V7M
-	/*
-	 * Note we don't need to do clrex here as clearing the local monitor is
-	 * part of each exception entry and exit sequence.
-	 */
-	.macro	restore_user_regs, fast = 0, offset = 0
+#elif defined(CONFIG_CPU_V7M)
+	@ V7M restore.
+	@ Note that we don't need to do clrex here as clearing the local
+	@ monitor is part of the exception entry and exit sequence.
 	.if	\offset
 	add	sp, #\offset
 	.endif
 	v7m_exception_slow_exit ret_r0 = \fast
-	.endm
-#else	/* ifdef CONFIG_CPU_V7M */
-	.macro	restore_user_regs, fast = 0, offset = 0
+#else
+	@ Thumb mode restore
 	mov	r2, sp
 	load_user_sp_lr r2, r3, \offset + S_SP	@ calling sp, lr
 	ldr	r1, [sp, #\offset + S_PSR]	@ get calling cpsr
@@ -353,9 +336,8 @@
 	.endif
 	add	sp, sp, #S_FRAME_SIZE - S_SP
 	movs	pc, lr				@ return & move spsr_svc into cpsr
-	.endm
-#endif	/* ifdef CONFIG_CPU_V7M / else */
 #endif	/* !CONFIG_THUMB2_KERNEL */
+	.endm
 
 /*
  * Context tracking subsystem.  Used to instrument transitions

arch/arm/kernel/head.S

@@ -464,10 +464,7 @@ __enable_mmu:
 #ifdef CONFIG_ARM_LPAE
 	mcrr	p15, 0, r4, r5, c2		@ load TTBR0
 #else
-	mov	r5, #(domain_val(DOMAIN_USER, DOMAIN_MANAGER) | \
-		      domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) | \
-		      domain_val(DOMAIN_TABLE, DOMAIN_MANAGER) | \
-		      domain_val(DOMAIN_IO, DOMAIN_CLIENT))
+	mov	r5, #DACR_INIT
 	mcr	p15, 0, r5, c3, c0, 0		@ load domain access register
 	mcr	p15, 0, r4, c2, c0, 0		@ load page table pointer
 #endif

arch/arm/kernel/process.c

@@ -129,12 +129,36 @@ void __show_regs(struct pt_regs *regs)
 	buf[4] = '\0';
 
 #ifndef CONFIG_CPU_V7M
-	printk("Flags: %s  IRQs o%s  FIQs o%s  Mode %s  ISA %s  Segment %s\n",
-		buf, interrupts_enabled(regs) ? "n" : "ff",
-		fast_interrupts_enabled(regs) ? "n" : "ff",
-		processor_modes[processor_mode(regs)],
-		isa_modes[isa_mode(regs)],
-		get_fs() == get_ds() ? "kernel" : "user");
+	{
+		unsigned int domain = get_domain();
+		const char *segment;
+
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+		/*
+		 * Get the domain register for the parent context. In user
+		 * mode, we don't save the DACR, so lets use what it should
+		 * be. For other modes, we place it after the pt_regs struct.
+		 */
+		if (user_mode(regs))
+			domain = DACR_UACCESS_ENABLE;
+		else
+			domain = *(unsigned int *)(regs + 1);
+#endif
+
+		if ((domain & domain_mask(DOMAIN_USER)) ==
+		    domain_val(DOMAIN_USER, DOMAIN_NOACCESS))
+			segment = "none";
+		else if (get_fs() == get_ds())
+			segment = "kernel";
+		else
+			segment = "user";
+
+		printk("Flags: %s  IRQs o%s  FIQs o%s  Mode %s  ISA %s  Segment %s\n",
+			buf, interrupts_enabled(regs) ? "n" : "ff",
+			fast_interrupts_enabled(regs) ? "n" : "ff",
+			processor_modes[processor_mode(regs)],
+			isa_modes[isa_mode(regs)], segment);
+	}
 #else
 	printk("xPSR: %08lx\n", regs->ARM_cpsr);
 #endif
@@ -146,10 +170,9 @@ void __show_regs(struct pt_regs *regs)
 		buf[0] = '\0';
 #ifdef CONFIG_CPU_CP15_MMU
 		{
-			unsigned int transbase, dac;
+			unsigned int transbase, dac = get_domain();
 			asm("mrc p15, 0, %0, c2, c0\n\t"
-			    "mrc p15, 0, %1, c3, c0\n"
-			    : "=r" (transbase), "=r" (dac));
+			    : "=r" (transbase));
 			snprintf(buf, sizeof(buf), "  Table: %08x  DAC: %08x",
 			  	transbase, dac);
 		}
@@ -210,6 +233,16 @@ copy_thread(unsigned long clone_flags, unsigned long stack_start,
 
 	memset(&thread->cpu_context, 0, sizeof(struct cpu_context_save));
 
+#ifdef CONFIG_CPU_USE_DOMAINS
+	/*
+	 * Copy the initial value of the domain access control register
+	 * from the current thread: thread->addr_limit will have been
+	 * copied from the current thread via setup_thread_stack() in
+	 * kernel/fork.c
+	 */
+	thread->cpu_domain = get_domain();
+#endif
+
 	if (likely(!(p->flags & PF_KTHREAD))) {
 		*childregs = *current_pt_regs();
 		childregs->ARM_r0 = 0;

arch/arm/kernel/swp_emulate.c

@@ -141,11 +141,14 @@ static int emulate_swpX(unsigned int address, unsigned int *data,
 
 	while (1) {
 		unsigned long temp;
+		unsigned int __ua_flags;
 
+		__ua_flags = uaccess_save_and_enable();
 		if (type == TYPE_SWPB)
 			__user_swpb_asm(*data, address, res, temp);
 		else
 			__user_swp_asm(*data, address, res, temp);
+		uaccess_restore(__ua_flags);
 
 		if (likely(res != -EAGAIN) || signal_pending(current))
 			break;

arch/arm/kernel/traps.c

@@ -870,7 +870,6 @@ void __init early_trap_init(void *vectors_base)
 	kuser_init(vectors_base);
 
 	flush_icache_range(vectors, vectors + PAGE_SIZE * 2);
-	modify_domain(DOMAIN_USER, DOMAIN_CLIENT);
 #else /* ifndef CONFIG_CPU_V7M */
 	/*
 	 * on V7-M there is no need to copy the vector table to a dedicated

arch/arm/lib/clear_user.S

@@ -12,14 +12,14 @@
 
 		.text
 
-/* Prototype: int __clear_user(void *addr, size_t sz)
+/* Prototype: unsigned long arm_clear_user(void *addr, size_t sz)
  * Purpose  : clear some user memory
  * Params   : addr - user memory address to clear
  *          : sz   - number of bytes to clear
  * Returns  : number of bytes NOT cleared
  */
 ENTRY(__clear_user_std)
-WEAK(__clear_user)
+WEAK(arm_clear_user)
 		stmfd	sp!, {r1, lr}
 		mov	r2, #0
 		cmp	r1, #4
@@ -44,7 +44,7 @@ WEAK(__clear_user)
 USER(		strnebt	r2, [r0])
 		mov	r0, #0
 		ldmfd	sp!, {r1, pc}
-ENDPROC(__clear_user)
+ENDPROC(arm_clear_user)
 ENDPROC(__clear_user_std)
 
 		.pushsection .text.fixup,"ax"

arch/arm/lib/copy_from_user.S

@@ -17,7 +17,7 @@
 /*
  * Prototype:
  *
- *	size_t __copy_from_user(void *to, const void *from, size_t n)
+ *	size_t arm_copy_from_user(void *to, const void *from, size_t n)
  *
  * Purpose:
  *
@@ -89,11 +89,11 @@
 
 	.text
 
-ENTRY(__copy_from_user)
+ENTRY(arm_copy_from_user)
 
 #include "copy_template.S"
 
-ENDPROC(__copy_from_user)
+ENDPROC(arm_copy_from_user)
 
 	.pushsection .fixup,"ax"
 	.align 0

arch/arm/lib/copy_to_user.S

@@ -17,7 +17,7 @@
 /*
  * Prototype:
  *
- *	size_t __copy_to_user(void *to, const void *from, size_t n)
+ *	size_t arm_copy_to_user(void *to, const void *from, size_t n)
  *
  * Purpose:
  *
@@ -93,11 +93,11 @@
 	.text
 
 ENTRY(__copy_to_user_std)
-WEAK(__copy_to_user)
+WEAK(arm_copy_to_user)
 
 #include "copy_template.S"
 
-ENDPROC(__copy_to_user)
+ENDPROC(arm_copy_to_user)
 ENDPROC(__copy_to_user_std)
 
 	.pushsection .text.fixup,"ax"

arch/arm/lib/csumpartialcopyuser.S

@@ -17,6 +17,19 @@
 
 		.text
 
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+		.macro	save_regs
+		mrc	p15, 0, ip, c3, c0, 0
+		stmfd	sp!, {r1, r2, r4 - r8, ip, lr}
+		uaccess_enable ip
+		.endm
+
+		.macro	load_regs
+		ldmfd	sp!, {r1, r2, r4 - r8, ip, lr}
+		mcr	p15, 0, ip, c3, c0, 0
+		ret	lr
+		.endm
+#else
 		.macro	save_regs
 		stmfd	sp!, {r1, r2, r4 - r8, lr}
 		.endm
@@ -24,6 +37,7 @@
 		.macro	load_regs
 		ldmfd	sp!, {r1, r2, r4 - r8, pc}
 		.endm
+#endif
 
 		.macro	load1b,	reg1
 		ldrusr	\reg1, r0, 1

arch/arm/lib/uaccess_with_memcpy.c

@@ -136,7 +136,7 @@ __copy_to_user_memcpy(void __user *to, const void *from, unsigned long n)
 }
 
 unsigned long
-__copy_to_user(void __user *to, const void *from, unsigned long n)
+arm_copy_to_user(void __user *to, const void *from, unsigned long n)
 {
 	/*
 	 * This test is stubbed out of the main function above to keep
@@ -190,7 +190,7 @@ __clear_user_memset(void __user *addr, unsigned long n)
 	return n;
 }
 
-unsigned long __clear_user(void __user *addr, unsigned long n)
+unsigned long arm_clear_user(void __user *addr, unsigned long n)
 {
 	/* See rational for this in __copy_to_user() above. */
 	if (n < 64)

arch/arm/mm/abort-ev4.S

@@ -19,6 +19,7 @@ ENTRY(v4_early_abort)
 	mrc	p15, 0, r1, c5, c0, 0		@ get FSR
 	mrc	p15, 0, r0, c6, c0, 0		@ get FAR
 	ldr	r3, [r4]			@ read aborted ARM instruction
+	uaccess_disable ip			@ disable userspace access
 	bic	r1, r1, #1 << 11 | 1 << 10	@ clear bits 11 and 10 of FSR
 	tst	r3, #1 << 20			@ L = 1 -> write?
 	orreq	r1, r1, #1 << 11		@ yes.

arch/arm/mm/abort-ev5t.S

@@ -21,8 +21,10 @@ ENTRY(v5t_early_abort)
 	mrc	p15, 0, r0, c6, c0, 0		@ get FAR
 	do_thumb_abort fsr=r1, pc=r4, psr=r5, tmp=r3
 	ldreq	r3, [r4]			@ read aborted ARM instruction
+	uaccess_disable ip			@ disable user access
 	bic	r1, r1, #1 << 11		@ clear bits 11 of FSR
-	do_ldrd_abort tmp=ip, insn=r3
+	teq_ldrd tmp=ip, insn=r3		@ insn was LDRD?
+	beq	do_DataAbort			@ yes
 	tst	r3, #1 << 20			@ check write
 	orreq	r1, r1, #1 << 11
 	b	do_DataAbort

arch/arm/mm/abort-ev5tj.S

@@ -24,7 +24,9 @@ ENTRY(v5tj_early_abort)
 	bne	do_DataAbort
 	do_thumb_abort fsr=r1, pc=r4, psr=r5, tmp=r3
 	ldreq	r3, [r4]			@ read aborted ARM instruction
-	do_ldrd_abort tmp=ip, insn=r3
+	uaccess_disable ip			@ disable userspace access
+	teq_ldrd tmp=ip, insn=r3		@ insn was LDRD?
+	beq	do_DataAbort			@ yes
 	tst	r3, #1 << 20			@ L = 0 -> write
 	orreq	r1, r1, #1 << 11		@ yes.
 	b	do_DataAbort

arch/arm/mm/abort-ev6.S

@@ -26,16 +26,18 @@ ENTRY(v6_early_abort)
 	ldr	ip, =0x4107b36
 	mrc	p15, 0, r3, c0, c0, 0		@ get processor id
 	teq	ip, r3, lsr #4			@ r0 ARM1136?
-	bne	do_DataAbort
+	bne	1f
 	tst	r5, #PSR_J_BIT			@ Java?
 	tsteq	r5, #PSR_T_BIT			@ Thumb?
-	bne	do_DataAbort
+	bne	1f
 	bic	r1, r1, #1 << 11		@ clear bit 11 of FSR
 	ldr	r3, [r4]			@ read aborted ARM instruction
  ARM_BE8(rev	r3, r3)
 
-	do_ldrd_abort tmp=ip, insn=r3
+	teq_ldrd tmp=ip, insn=r3		@ insn was LDRD?
+	beq	1f				@ yes
 	tst	r3, #1 << 20			@ L = 0 -> write
 	orreq	r1, r1, #1 << 11		@ yes.
 #endif
+1:	uaccess_disable ip			@ disable userspace access
 	b	do_DataAbort

arch/arm/mm/abort-ev7.S

@@ -15,6 +15,7 @@
 ENTRY(v7_early_abort)
 	mrc	p15, 0, r1, c5, c0, 0		@ get FSR
 	mrc	p15, 0, r0, c6, c0, 0		@ get FAR
+	uaccess_disable ip			@ disable userspace access
 
 	/*
 	 * V6 code adjusts the returned DFSR.

arch/arm/mm/abort-lv4t.S

@@ -26,6 +26,7 @@ ENTRY(v4t_late_abort)
 #endif
 	bne	.data_thumb_abort
 	ldr	r8, [r4]			@ read arm instruction
+	uaccess_disable ip			@ disable userspace access
 	tst	r8, #1 << 20			@ L = 1 -> write?
 	orreq	r1, r1, #1 << 11		@ yes.
 	and	r7, r8, #15 << 24
@@ -155,6 +156,7 @@ ENTRY(v4t_late_abort)
 
 .data_thumb_abort:
 	ldrh	r8, [r4]			@ read instruction
+	uaccess_disable ip			@ disable userspace access
 	tst	r8, #1 << 11			@ L = 1 -> write?
 	orreq	r1, r1, #1 << 8			@ yes
 	and	r7, r8, #15 << 12

arch/arm/mm/abort-macro.S

@@ -13,6 +13,7 @@
 	tst	\psr, #PSR_T_BIT
 	beq	not_thumb
 	ldrh	\tmp, [\pc]			@ Read aborted Thumb instruction
+	uaccess_disable ip			@ disable userspace access
 	and	\tmp, \tmp, # 0xfe00		@ Mask opcode field
 	cmp	\tmp, # 0x5600			@ Is it ldrsb?
 	orreq	\tmp, \tmp, #1 << 11		@ Set L-bit if yes
@@ -29,12 +30,9 @@ not_thumb:
  *   [7:4] == 1101
  *    [20] == 0
  */
-	.macro	do_ldrd_abort, tmp, insn
-	tst	\insn, #0x0e100000		@ [27:25,20] == 0
-	bne	not_ldrd
-	and	\tmp, \insn, #0x000000f0	@ [7:4] == 1101
-	cmp	\tmp, #0x000000d0
-	beq	do_DataAbort
-not_ldrd:
+	.macro	teq_ldrd, tmp, insn
+	mov	\tmp, #0x0e100000
+	orr	\tmp, #0x000000f0
+	and	\tmp, \insn, \tmp
+	teq	\tmp, #0x000000d0
 	.endm
-

arch/arm/mm/mmu.c

@@ -291,13 +291,13 @@ static struct mem_type mem_types[] = {
 		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
 				L_PTE_RDONLY,
 		.prot_l1   = PMD_TYPE_TABLE,
-		.domain    = DOMAIN_USER,
+		.domain    = DOMAIN_VECTORS,
 	},
 	[MT_HIGH_VECTORS] = {
 		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
 				L_PTE_USER | L_PTE_RDONLY,
 		.prot_l1   = PMD_TYPE_TABLE,
-		.domain    = DOMAIN_USER,
+		.domain    = DOMAIN_VECTORS,
 	},
 	[MT_MEMORY_RWX] = {
 		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY,

arch/arm/mm/pgd.c

@@ -84,6 +84,16 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 		if (!new_pte)
 			goto no_pte;
 
+#ifndef CONFIG_ARM_LPAE
+		/*
+		 * Modify the PTE pointer to have the correct domain.  This
+		 * needs to be the vectors domain to avoid the low vectors
+		 * being unmapped.
+		 */
+		pmd_val(*new_pmd) &= ~PMD_DOMAIN_MASK;
+		pmd_val(*new_pmd) |= PMD_DOMAIN(DOMAIN_VECTORS);
+#endif
+
 		init_pud = pud_offset(init_pgd, 0);
 		init_pmd = pmd_offset(init_pud, 0);
 		init_pte = pte_offset_map(init_pmd, 0);

arch/arm/nwfpe/entry.S

@@ -95,9 +95,10 @@ emulate:
 	reteq	r4			@ no, return failure
 
 next:
+	uaccess_enable r3
 .Lx1:	ldrt	r6, [r5], #4		@ get the next instruction and
 					@ increment PC
-
+	uaccess_disable r3
 	and	r2, r6, #0x0F000000	@ test for FP insns
 	teq	r2, #0x0C000000
 	teqne	r2, #0x0D000000

arch/arm/xen/hypercall.S

@@ -98,8 +98,23 @@ ENTRY(privcmd_call)
 	mov r1, r2
 	mov r2, r3
 	ldr r3, [sp, #8]
+	/*
+	 * Privcmd calls are issued by the userspace. We need to allow the
+	 * kernel to access the userspace memory before issuing the hypercall.
+	 */
+	uaccess_enable r4
+
+	/* r4 is loaded now as we use it as scratch register before */
 	ldr r4, [sp, #4]
 	__HVC(XEN_IMM)
+
+	/*
+	 * Disable userspace access from kernel. This is fine to do it
+	 * unconditionally as no set_fs(KERNEL_DS)/set_fs(get_ds()) is
+	 * called before.
+	 */
+	uaccess_disable r4
+
 	ldm sp!, {r4}
 	ret lr
 ENDPROC(privcmd_call);