Merge branches 'fixes' and 'misc' into for-linus

arch/arm/kernel/entry-armv.S

@@ -451,9 +451,11 @@ __und_usr_thumb:
 	.arch	armv6t2
 #endif
 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
 3:	ldrht	r0, [r2]
+ARM_BE8(rev16	r0, r0)				@ little endian instruction
 	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

arch/arm/kernel/head.S

@@ -52,7 +52,8 @@
 	.equ	swapper_pg_dir, KERNEL_RAM_VADDR - PG_DIR_SIZE
 
 	.macro	pgtbl, rd, phys
-	add	\rd, \phys, #TEXT_OFFSET - PG_DIR_SIZE
+	add	\rd, \phys, #TEXT_OFFSET
+	sub	\rd, \rd, #PG_DIR_SIZE
 	.endm
 
 /*

arch/arm/kernel/io.c

@@ -1,6 +1,41 @@
 #include <linux/export.h>
 #include <linux/types.h>
 #include <linux/io.h>
+#include <linux/spinlock.h>
+
+static DEFINE_RAW_SPINLOCK(__io_lock);
+
+/*
+ * Generic atomic MMIO modify.
+ *
+ * Allows thread-safe access to registers shared by unrelated subsystems.
+ * The access is protected by a single MMIO-wide lock.
+ */
+void atomic_io_modify_relaxed(void __iomem *reg, u32 mask, u32 set)
+{
+	unsigned long flags;
+	u32 value;
+
+	raw_spin_lock_irqsave(&__io_lock, flags);
+	value = readl_relaxed(reg) & ~mask;
+	value |= (set & mask);
+	writel_relaxed(value, reg);
+	raw_spin_unlock_irqrestore(&__io_lock, flags);
+}
+EXPORT_SYMBOL(atomic_io_modify_relaxed);
+
+void atomic_io_modify(void __iomem *reg, u32 mask, u32 set)
+{
+	unsigned long flags;
+	u32 value;
+
+	raw_spin_lock_irqsave(&__io_lock, flags);
+	value = readl_relaxed(reg) & ~mask;
+	value |= (set & mask);
+	writel(value, reg);
+	raw_spin_unlock_irqrestore(&__io_lock, flags);
+}
+EXPORT_SYMBOL(atomic_io_modify);
 
 /*
  * Copy data from IO memory space to "real" memory space.