Merge branch 'for-linus' of git://git.linaro.org/people/rmk/linux-arm

Pull late ARM updates from Russell King:
 "Here is the late set of ARM updates for this merge window; in here is:

   - The ARM parts of the broadcast timer support, core parts merged
     through tglx's tree.  This was left over from the previous merge to
     allow the dependency on tglx's tree to be resolved.

   - A fix to the VFP code which shows up on Raspberry Pi's, as well as
     fixing the fallout from a previous commit in this area.

   - A number of smaller fixes scattered throughout the ARM tree"

* 'for-linus' of git://git.linaro.org/people/rmk/linux-arm:
  ARM: Fix broken commit 0cc41e4a21d43 corrupting kernel messages
  ARM: fix scheduling while atomic warning in alignment handling code
  ARM: VFP: fix emulation of second VFP instruction
  ARM: 7656/1: uImage: Error out on build of multiplatform without LOADADDR
  ARM: 7640/1: memory: tegra_ahb_enable_smmu() depends on TEGRA_IOMMU_SMMU
  ARM: 7654/1: Preserve L_PTE_VALID in pte_modify()
  ARM: 7653/2: do not scale loops_per_jiffy when using a constant delay clock
  ARM: 7651/1: remove unused smp_timer_broadcast #define
diff --git a/arch/arm/boot/Makefile b/arch/arm/boot/Makefile
index abfce28..71768b8 100644
--- a/arch/arm/boot/Makefile
+++ b/arch/arm/boot/Makefile
@@ -68,8 +68,8 @@
 endif
 
 check_for_multiple_loadaddr = \
-if [ $(words $(UIMAGE_LOADADDR)) -gt 1 ]; then \
-	echo 'multiple load addresses: $(UIMAGE_LOADADDR)'; \
+if [ $(words $(UIMAGE_LOADADDR)) -ne 1 ]; then \
+	echo 'multiple (or no) load addresses: $(UIMAGE_LOADADDR)'; \
 	echo 'This is incompatible with uImages'; \
 	echo 'Specify LOADADDR on the commandline to build an uImage'; \
 	false; \
diff --git a/arch/arm/include/asm/delay.h b/arch/arm/include/asm/delay.h
index ab98fdd..720799f 100644
--- a/arch/arm/include/asm/delay.h
+++ b/arch/arm/include/asm/delay.h
@@ -24,6 +24,7 @@
 	void (*delay)(unsigned long);
 	void (*const_udelay)(unsigned long);
 	void (*udelay)(unsigned long);
+	bool const_clock;
 } arm_delay_ops;
 
 #define __delay(n)		arm_delay_ops.delay(n)
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index f30ac3b..80d6fc4 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -247,7 +247,8 @@
 
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
-	const pteval_t mask = L_PTE_XN | L_PTE_RDONLY | L_PTE_USER | L_PTE_NONE;
+	const pteval_t mask = L_PTE_XN | L_PTE_RDONLY | L_PTE_USER |
+		L_PTE_NONE | L_PTE_VALID;
 	pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask);
 	return pte;
 }
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 5f73f70..1bdfd87 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -466,8 +466,6 @@
 {
 	smp_cross_call(mask, IPI_TIMER);
 }
-#else
-#define smp_timer_broadcast	NULL
 #endif
 
 static void broadcast_timer_set_mode(enum clock_event_mode mode,
@@ -674,6 +672,9 @@
 	if (freq->flags & CPUFREQ_CONST_LOOPS)
 		return NOTIFY_OK;
 
+	if (arm_delay_ops.const_clock)
+		return NOTIFY_OK;
+
 	if (!per_cpu(l_p_j_ref, cpu)) {
 		per_cpu(l_p_j_ref, cpu) =
 			per_cpu(cpu_data, cpu).loops_per_jiffy;
diff --git a/arch/arm/lib/delay.c b/arch/arm/lib/delay.c
index 0dc5385..6b93f6a 100644
--- a/arch/arm/lib/delay.c
+++ b/arch/arm/lib/delay.c
@@ -77,6 +77,7 @@
 		arm_delay_ops.delay		= __timer_delay;
 		arm_delay_ops.const_udelay	= __timer_const_udelay;
 		arm_delay_ops.udelay		= __timer_udelay;
+		arm_delay_ops.const_clock	= true;
 		delay_calibrated		= true;
 	} else {
 		pr_info("Ignoring duplicate/late registration of read_current_timer delay\n");
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index b820eda..db26e2e 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -749,7 +749,6 @@
 	unsigned long instr = 0, instrptr;
 	int (*handler)(unsigned long addr, unsigned long instr, struct pt_regs *regs);
 	unsigned int type;
-	mm_segment_t fs;
 	unsigned int fault;
 	u16 tinstr = 0;
 	int isize = 4;
@@ -760,16 +759,15 @@
 
 	instrptr = instruction_pointer(regs);
 
-	fs = get_fs();
-	set_fs(KERNEL_DS);
 	if (thumb_mode(regs)) {
-		fault = __get_user(tinstr, (u16 *)(instrptr & ~1));
+		u16 *ptr = (u16 *)(instrptr & ~1);
+		fault = probe_kernel_address(ptr, tinstr);
 		if (!fault) {
 			if (cpu_architecture() >= CPU_ARCH_ARMv7 &&
 			    IS_T32(tinstr)) {
 				/* Thumb-2 32-bit */
 				u16 tinst2 = 0;
-				fault = __get_user(tinst2, (u16 *)(instrptr+2));
+				fault = probe_kernel_address(ptr + 1, tinst2);
 				instr = (tinstr << 16) | tinst2;
 				thumb2_32b = 1;
 			} else {
@@ -778,8 +776,7 @@
 			}
 		}
 	} else
-		fault = __get_user(instr, (u32 *)instrptr);
-	set_fs(fs);
+		fault = probe_kernel_address(instrptr, instr);
 
 	if (fault) {
 		type = TYPE_FAULT;
diff --git a/arch/arm/vfp/vfphw.S b/arch/arm/vfp/vfphw.S
index dd5e56f..8d10dc8 100644
--- a/arch/arm/vfp/vfphw.S
+++ b/arch/arm/vfp/vfphw.S
@@ -22,12 +22,14 @@
 	.macro	DBGSTR, str
 #ifdef DEBUG
 	stmfd	sp!, {r0-r3, ip, lr}
-	add	r0, pc, #4
+	ldr	r0, =1f
 	bl	printk
-	b	1f
-	.asciz  KERN_DEBUG "VFP: \str\n"
-	.balign 4
-1:	ldmfd	sp!, {r0-r3, ip, lr}
+	ldmfd	sp!, {r0-r3, ip, lr}
+
+	.pushsection .rodata, "a"
+1:	.ascii	KERN_DEBUG "VFP: \str\n"
+	.byte	0
+	.previous
 #endif
 	.endm
 
@@ -35,12 +37,14 @@
 #ifdef DEBUG
 	stmfd	sp!, {r0-r3, ip, lr}
 	mov	r1, \arg
-	add	r0, pc, #4
+	ldr	r0, =1f
 	bl	printk
-	b	1f
-	.asciz  KERN_DEBUG "VFP: \str\n"
-	.balign 4
-1:	ldmfd	sp!, {r0-r3, ip, lr}
+	ldmfd	sp!, {r0-r3, ip, lr}
+
+	.pushsection .rodata, "a"
+1:	.ascii	KERN_DEBUG "VFP: \str\n"
+	.byte	0
+	.previous
 #endif
 	.endm
 
@@ -50,12 +54,14 @@
 	mov	r3, \arg3
 	mov	r2, \arg2
 	mov	r1, \arg1
-	add	r0, pc, #4
+	ldr	r0, =1f
 	bl	printk
-	b	1f
-	.asciz  KERN_DEBUG "VFP: \str\n"
-	.balign 4
-1:	ldmfd	sp!, {r0-r3, ip, lr}
+	ldmfd	sp!, {r0-r3, ip, lr}
+
+	.pushsection .rodata, "a"
+1:	.ascii	KERN_DEBUG "VFP: \str\n"
+	.byte	0
+	.previous
 #endif
 	.endm
 
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index 3b44e0d..5dfbb0b 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -413,7 +413,7 @@
 	 * If there isn't a second FP instruction, exit now. Note that
 	 * the FPEXC.FP2V bit is valid only if FPEXC.EX is 1.
 	 */
-	if (fpexc ^ (FPEXC_EX | FPEXC_FP2V))
+	if ((fpexc & (FPEXC_EX | FPEXC_FP2V)) != (FPEXC_EX | FPEXC_FP2V))
 		goto exit;
 
 	/*
diff --git a/drivers/amba/tegra-ahb.c b/drivers/amba/tegra-ahb.c
index ab92785..093c435 100644
--- a/drivers/amba/tegra-ahb.c
+++ b/drivers/amba/tegra-ahb.c
@@ -130,7 +130,7 @@
 	writel(value, ahb->regs + offset);
 }
 
-#ifdef CONFIG_ARCH_TEGRA_3x_SOC
+#ifdef CONFIG_TEGRA_IOMMU_SMMU
 static int tegra_ahb_match_by_smmu(struct device *dev, void *data)
 {
 	struct tegra_ahb *ahb = dev_get_drvdata(dev);