Merge tag 'v3.4.12' into v3.4-rt

This is the 3.4.12 stable release

11 files changed, 115 insertions, 159 deletions

diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 047a20780fc1..1d6402cbf4b2 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -283,10 +283,10 @@ zImage Image xipImage bootpImage uImage: vmlinux
 zinstall uinstall install: vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) MACHINE=$(MACHINE) $@
 
-%.dtb:
+%.dtb: scripts
 	$(Q)$(MAKE) $(build)=$(boot) MACHINE=$(MACHINE) $(boot)/$@
 
-dtbs:
+dtbs: scripts
 	$(Q)$(MAKE) $(build)=$(boot) MACHINE=$(MACHINE) $(boot)/$@
 
 # We use MRPROPER_FILES and CLEAN_FILES now
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index dc7e8ce8e6be..87278fc80d9f 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -648,6 +648,7 @@ __armv7_mmu_cache_on:
 		mcrne	p15, 0, r0, c8, c7, 0	@ flush I,D TLBs
 #endif
 		mrc	p15, 0, r0, c1, c0, 0	@ read control reg
+		bic	r0, r0, #1 << 28	@ clear SCTLR.TRE
 		orr	r0, r0, #0x5000		@ I-cache enable, RR cache replacement
 		orr	r0, r0, #0x003c		@ write buffer
 #ifdef CONFIG_MMU
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 03fb93621d0d..5c8b3bf4d825 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -320,4 +320,12 @@
 	.size \name , . - \name
 	.endm
 
+	.macro check_uaccess, addr:req, size:req, limit:req, tmp:req, bad:req
+#ifndef CONFIG_CPU_USE_DOMAINS
+	adds	\tmp, \addr, #\size - 1
+	sbcccs	\tmp, \tmp, \limit
+	bcs	\bad
+#endif
+	.endm
+
 #endif /* __ASM_ASSEMBLER_H__ */
diff --git a/arch/arm/include/asm/mutex.h b/arch/arm/include/asm/mutex.h
index 93226cf23ae0..b1479fd04a95 100644
--- a/arch/arm/include/asm/mutex.h
+++ b/arch/arm/include/asm/mutex.h
@@ -7,121 +7,10 @@
  */
 #ifndef _ASM_MUTEX_H
 #define _ASM_MUTEX_H
-
-#if __LINUX_ARM_ARCH__ < 6
-/* On pre-ARMv6 hardware the swp based implementation is the most efficient. */
-# include <asm-generic/mutex-xchg.h>
-#else
-
 /*
- * Attempting to lock a mutex on ARMv6+ can be done with a bastardized
- * atomic decrement (it is not a reliable atomic decrement but it satisfies
- * the defined semantics for our purpose, while being smaller and faster
- * than a real atomic decrement or atomic swap.  The idea is to attempt
- * decrementing the lock value only once.  If once decremented it isn't zero,
- * or if its store-back fails due to a dispute on the exclusive store, we
- * simply bail out immediately through the slow path where the lock will be
- * reattempted until it succeeds.
+ * On pre-ARMv6 hardware this results in a swp-based implementation,
+ * which is the most efficient. For ARMv6+, we emit a pair of exclusive
+ * accesses instead.
  */
-static inline void
-__mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *))
-{
-	int __ex_flag, __res;
-
-	__asm__ (
-
-		"ldrex	%0, [%2]	\n\t"
-		"sub	%0, %0, #1	\n\t"
-		"strex	%1, %0, [%2]	"
-
-		: "=&r" (__res), "=&r" (__ex_flag)
-		: "r" (&(count)->counter)
-		: "cc","memory" );
-
-	__res |= __ex_flag;
-	if (unlikely(__res != 0))
-		fail_fn(count);
-}
-
-static inline int
-__mutex_fastpath_lock_retval(atomic_t *count, int (*fail_fn)(atomic_t *))
-{
-	int __ex_flag, __res;
-
-	__asm__ (
-
-		"ldrex	%0, [%2]	\n\t"
-		"sub	%0, %0, #1	\n\t"
-		"strex	%1, %0, [%2]	"
-
-		: "=&r" (__res), "=&r" (__ex_flag)
-		: "r" (&(count)->counter)
-		: "cc","memory" );
-
-	__res |= __ex_flag;
-	if (unlikely(__res != 0))
-		__res = fail_fn(count);
-	return __res;
-}
-
-/*
- * Same trick is used for the unlock fast path. However the original value,
- * rather than the result, is used to test for success in order to have
- * better generated assembly.
- */
-static inline void
-__mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *))
-{
-	int __ex_flag, __res, __orig;
-
-	__asm__ (
-
-		"ldrex	%0, [%3]	\n\t"
-		"add	%1, %0, #1	\n\t"
-		"strex	%2, %1, [%3]	"
-
-		: "=&r" (__orig), "=&r" (__res), "=&r" (__ex_flag)
-		: "r" (&(count)->counter)
-		: "cc","memory" );
-
-	__orig |= __ex_flag;
-	if (unlikely(__orig != 0))
-		fail_fn(count);
-}
-
-/*
- * If the unlock was done on a contended lock, or if the unlock simply fails
- * then the mutex remains locked.
- */
-#define __mutex_slowpath_needs_to_unlock()	1
-
-/*
- * For __mutex_fastpath_trylock we use another construct which could be
- * described as a "single value cmpxchg".
- *
- * This provides the needed trylock semantics like cmpxchg would, but it is
- * lighter and less generic than a true cmpxchg implementation.
- */
-static inline int
-__mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *))
-{
-	int __ex_flag, __res, __orig;
-
-	__asm__ (
-
-		"1: ldrex	%0, [%3]	\n\t"
-		"subs		%1, %0, #1	\n\t"
-		"strexeq	%2, %1, [%3]	\n\t"
-		"movlt		%0, #0		\n\t"
-		"cmpeq		%2, #0		\n\t"
-		"bgt		1b		"
-
-		: "=&r" (__orig), "=&r" (__res), "=&r" (__ex_flag)
-		: "r" (&count->counter)
-		: "cc", "memory" );
-
-	return __orig;
-}
-
-#endif
+#include <asm-generic/mutex-xchg.h>
 #endif
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 71f6536d17ac..0a070e98625d 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -101,28 +101,39 @@ extern int __get_user_1(void *);
 extern int __get_user_2(void *);
 extern int __get_user_4(void *);
 
-#define __get_user_x(__r2,__p,__e,__s,__i...)				\
+#define __GUP_CLOBBER_1	"lr", "cc"
+#ifdef CONFIG_CPU_USE_DOMAINS
+#define __GUP_CLOBBER_2	"ip", "lr", "cc"
+#else
+#define __GUP_CLOBBER_2 "lr", "cc"
+#endif
+#define __GUP_CLOBBER_4	"lr", "cc"
+
+#define __get_user_x(__r2,__p,__e,__l,__s)				\
 	   __asm__ __volatile__ (					\
 		__asmeq("%0", "r0") __asmeq("%1", "r2")			\
+		__asmeq("%3", "r1")					\
 		"bl	__get_user_" #__s				\
 		: "=&r" (__e), "=r" (__r2)				\
-		: "0" (__p)						\
-		: __i, "cc")
+		: "0" (__p), "r" (__l)					\
+		: __GUP_CLOBBER_##__s)
 
 #define get_user(x,p)							\
 	({								\
+		unsigned long __limit = current_thread_info()->addr_limit - 1; \
 		register const typeof(*(p)) __user *__p asm("r0") = (p);\
 		register unsigned long __r2 asm("r2");			\
+		register unsigned long __l asm("r1") = __limit;		\
 		register int __e asm("r0");				\
 		switch (sizeof(*(__p))) {				\
 		case 1:							\
-			__get_user_x(__r2, __p, __e, 1, "lr");		\
-	       		break;						\
+			__get_user_x(__r2, __p, __e, __l, 1);		\
+			break;						\
 		case 2:							\
-			__get_user_x(__r2, __p, __e, 2, "r3", "lr");	\
+			__get_user_x(__r2, __p, __e, __l, 2);		\
 			break;						\
 		case 4:							\
-	       		__get_user_x(__r2, __p, __e, 4, "lr");		\
+			__get_user_x(__r2, __p, __e, __l, 4);		\
 			break;						\
 		default: __e = __get_user_bad(); break;			\
 		}							\
@@ -135,31 +146,34 @@ extern int __put_user_2(void *, unsigned int);
 extern int __put_user_4(void *, unsigned int);
 extern int __put_user_8(void *, unsigned long long);
 
-#define __put_user_x(__r2,__p,__e,__s)					\
+#define __put_user_x(__r2,__p,__e,__l,__s)				\
 	   __asm__ __volatile__ (					\
 		__asmeq("%0", "r0") __asmeq("%2", "r2")			\
+		__asmeq("%3", "r1")					\
 		"bl	__put_user_" #__s				\
 		: "=&r" (__e)						\
-		: "0" (__p), "r" (__r2)					\
+		: "0" (__p), "r" (__r2), "r" (__l)			\
 		: "ip", "lr", "cc")
 
 #define put_user(x,p)							\
 	({								\
+		unsigned long __limit = current_thread_info()->addr_limit - 1; \
 		register const typeof(*(p)) __r2 asm("r2") = (x);	\
 		register const typeof(*(p)) __user *__p asm("r0") = (p);\
+		register unsigned long __l asm("r1") = __limit;		\
 		register int __e asm("r0");				\
 		switch (sizeof(*(__p))) {				\
 		case 1:							\
-			__put_user_x(__r2, __p, __e, 1);		\
+			__put_user_x(__r2, __p, __e, __l, 1);		\
 			break;						\
 		case 2:							\
-			__put_user_x(__r2, __p, __e, 2);		\
+			__put_user_x(__r2, __p, __e, __l, 2);		\
 			break;						\
 		case 4:							\
-			__put_user_x(__r2, __p, __e, 4);		\
+			__put_user_x(__r2, __p, __e, __l, 4);		\
 			break;						\
 		case 8:							\
-			__put_user_x(__r2, __p, __e, 8);		\
+			__put_user_x(__r2, __p, __e, __l, 8);		\
 			break;						\
 		default: __e = __put_user_bad(); break;			\
 		}							\
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index ba386bd94107..18d39ea4c02f 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -159,6 +159,12 @@ static int debug_arch_supported(void)
 		arch >= ARM_DEBUG_ARCH_V7_1;
 }
 
+/* Can we determine the watchpoint access type from the fsr? */
+static int debug_exception_updates_fsr(void)
+{
+	return 0;
+}
+
 /* Determine number of WRP registers available. */
 static int get_num_wrp_resources(void)
 {
@@ -619,18 +625,35 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 	info->address &= ~alignment_mask;
 	info->ctrl.len <<= offset;
 
-	/*
-	 * Currently we rely on an overflow handler to take
-	 * care of single-stepping the breakpoint when it fires.
-	 * In the case of userspace breakpoints on a core with V7 debug,
-	 * we can use the mismatch feature as a poor-man's hardware
-	 * single-step, but this only works for per-task breakpoints.
-	 */
-	if (!bp->overflow_handler && (arch_check_bp_in_kernelspace(bp) ||
-	    !core_has_mismatch_brps() || !bp->hw.bp_target)) {
-		pr_warning("overflow handler required but none found\n");
-		ret = -EINVAL;
+	if (!bp->overflow_handler) {
+		/*
+		 * Mismatch breakpoints are required for single-stepping
+		 * breakpoints.
+		 */
+		if (!core_has_mismatch_brps())
+			return -EINVAL;
+
+		/* We don't allow mismatch breakpoints in kernel space. */
+		if (arch_check_bp_in_kernelspace(bp))
+			return -EPERM;
+
+		/*
+		 * Per-cpu breakpoints are not supported by our stepping
+		 * mechanism.
+		 */
+		if (!bp->hw.bp_target)
+			return -EINVAL;
+
+		/*
+		 * We only support specific access types if the fsr
+		 * reports them.
+		 */
+		if (!debug_exception_updates_fsr() &&
+		    (info->ctrl.type == ARM_BREAKPOINT_LOAD ||
+		     info->ctrl.type == ARM_BREAKPOINT_STORE))
+			return -EINVAL;
 	}
+
 out:
 	return ret;
 }
@@ -706,10 +729,12 @@ static void watchpoint_handler(unsigned long addr, unsigned int fsr,
 				goto unlock;
 
 			/* Check that the access type matches. */
-			access = (fsr & ARM_FSR_ACCESS_MASK) ? HW_BREAKPOINT_W :
-				 HW_BREAKPOINT_R;
-			if (!(access & hw_breakpoint_type(wp)))
-				goto unlock;
+			if (debug_exception_updates_fsr()) {
+				access = (fsr & ARM_FSR_ACCESS_MASK) ?
+					  HW_BREAKPOINT_W : HW_BREAKPOINT_R;
+				if (!(access & hw_breakpoint_type(wp)))
+					goto unlock;
+			}
 
 			/* We have a winner. */
 			info->trigger = addr;
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index a8ad1e34902e..a53a5a3c3c2e 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -388,20 +388,23 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
 #endif
 			instr = *(u32 *) pc;
 	} else if (thumb_mode(regs)) {
-		get_user(instr, (u16 __user *)pc);
+		if (get_user(instr, (u16 __user *)pc))
+			goto die_sig;
 		if (is_wide_instruction(instr)) {
 			unsigned int instr2;
-			get_user(instr2, (u16 __user *)pc+1);
+			if (get_user(instr2, (u16 __user *)pc+1))
+				goto die_sig;
 			instr <<= 16;
 			instr |= instr2;
 		}
-	} else {
-		get_user(instr, (u32 __user *)pc);
+	} else if (get_user(instr, (u32 __user *)pc)) {
+		goto die_sig;
 	}
 
 	if (call_undef_hook(regs, instr) == 0)
 		return;
 
+die_sig:
 #ifdef CONFIG_DEBUG_USER
 	if (user_debug & UDBG_UNDEFINED) {
 		printk(KERN_INFO "%s (%d): undefined instruction: pc=%p\n",
diff --git a/arch/arm/lib/getuser.S b/arch/arm/lib/getuser.S
index 11093a7c3e32..9b06bb41fca6 100644
--- a/arch/arm/lib/getuser.S
+++ b/arch/arm/lib/getuser.S
@@ -16,8 +16,9 @@
  * __get_user_X
  *
  * Inputs:	r0 contains the address
+ *		r1 contains the address limit, which must be preserved
  * Outputs:	r0 is the error code
- *		r2, r3 contains the zero-extended value
+ *		r2 contains the zero-extended value
  *		lr corrupted
  *
  * No other registers must be altered.  (see <asm/uaccess.h>
@@ -27,33 +28,39 @@
  * Note also that it is intended that __get_user_bad is not global.
  */
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 #include <asm/errno.h>
 #include <asm/domain.h>
 
 ENTRY(__get_user_1)
+	check_uaccess r0, 1, r1, r2, __get_user_bad
 1: TUSER(ldrb)	r2, [r0]
 	mov	r0, #0
 	mov	pc, lr
 ENDPROC(__get_user_1)
 
 ENTRY(__get_user_2)
-#ifdef CONFIG_THUMB2_KERNEL
-2: TUSER(ldrb)	r2, [r0]
-3: TUSER(ldrb)	r3, [r0, #1]
+	check_uaccess r0, 2, r1, r2, __get_user_bad
+#ifdef CONFIG_CPU_USE_DOMAINS
+rb	.req	ip
+2:	ldrbt	r2, [r0], #1
+3:	ldrbt	rb, [r0], #0
 #else
-2: TUSER(ldrb)	r2, [r0], #1
-3: TUSER(ldrb)	r3, [r0]
+rb	.req	r0
+2:	ldrb	r2, [r0]
+3:	ldrb	rb, [r0, #1]
 #endif
 #ifndef __ARMEB__
-	orr	r2, r2, r3, lsl #8
+	orr	r2, r2, rb, lsl #8
 #else
-	orr	r2, r3, r2, lsl #8
+	orr	r2, rb, r2, lsl #8
 #endif
 	mov	r0, #0
 	mov	pc, lr
 ENDPROC(__get_user_2)
 
 ENTRY(__get_user_4)
+	check_uaccess r0, 4, r1, r2, __get_user_bad
 4: TUSER(ldr)	r2, [r0]
 	mov	r0, #0
 	mov	pc, lr
diff --git a/arch/arm/lib/putuser.S b/arch/arm/lib/putuser.S
index 7db25990c589..3d73dcb959b0 100644
--- a/arch/arm/lib/putuser.S
+++ b/arch/arm/lib/putuser.S
@@ -16,6 +16,7 @@
  * __put_user_X
  *
  * Inputs:	r0 contains the address
+ *		r1 contains the address limit, which must be preserved
  *		r2, r3 contains the value
  * Outputs:	r0 is the error code
  *		lr corrupted
@@ -27,16 +28,19 @@
  * Note also that it is intended that __put_user_bad is not global.
  */
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 #include <asm/errno.h>
 #include <asm/domain.h>
 
 ENTRY(__put_user_1)
+	check_uaccess r0, 1, r1, ip, __put_user_bad
 1: TUSER(strb)	r2, [r0]
 	mov	r0, #0
 	mov	pc, lr
 ENDPROC(__put_user_1)
 
 ENTRY(__put_user_2)
+	check_uaccess r0, 2, r1, ip, __put_user_bad
 	mov	ip, r2, lsr #8
 #ifdef CONFIG_THUMB2_KERNEL
 #ifndef __ARMEB__
@@ -60,12 +64,14 @@ ENTRY(__put_user_2)
 ENDPROC(__put_user_2)
 
 ENTRY(__put_user_4)
+	check_uaccess r0, 4, r1, ip, __put_user_bad
 4: TUSER(str)	r2, [r0]
 	mov	r0, #0
 	mov	pc, lr
 ENDPROC(__put_user_4)
 
 ENTRY(__put_user_8)
+	check_uaccess r0, 8, r1, ip, __put_user_bad
 #ifdef CONFIG_THUMB2_KERNEL
 5: TUSER(str)	r2, [r0]
 6: TUSER(str)	r3, [r0, #4]
diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h
index 27f4a619b35d..d3f25c9aaf82 100644
--- a/arch/arm/mm/mm.h
+++ b/arch/arm/mm/mm.h
@@ -55,6 +55,9 @@ extern void __flush_dcache_page(struct address_space *mapping, struct page *page
 /* permanent static mappings from iotable_init() */
 #define VM_ARM_STATIC_MAPPING	0x40000000
 
+/* empty mapping */
+#define VM_ARM_EMPTY_MAPPING	0x20000000
+
 /* mapping type (attributes) for permanent static mappings */
 #define VM_ARM_MTYPE(mt)		((mt) << 20)
 #define VM_ARM_MTYPE_MASK	(0x1f << 20)
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 75f9f9d67097..7d419193d49a 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -805,7 +805,7 @@ static void __init pmd_empty_section_gap(unsigned long addr)
 	vm = early_alloc_aligned(sizeof(*vm), __alignof__(*vm));
 	vm->addr = (void *)addr;
 	vm->size = SECTION_SIZE;
-	vm->flags = VM_IOREMAP | VM_ARM_STATIC_MAPPING;
+	vm->flags = VM_IOREMAP | VM_ARM_EMPTY_MAPPING;
 	vm->caller = pmd_empty_section_gap;
 	vm_area_add_early(vm);
 }
@@ -818,7 +818,7 @@ static void __init fill_pmd_gaps(void)
 
 	/* we're still single threaded hence no lock needed here */
 	for (vm = vmlist; vm; vm = vm->next) {
-		if (!(vm->flags & VM_ARM_STATIC_MAPPING))
+		if (!(vm->flags & (VM_ARM_STATIC_MAPPING | VM_ARM_EMPTY_MAPPING)))
 			continue;
 		addr = (unsigned long)vm->addr;
 		if (addr < next)