21 files changed, 419 insertions, 86 deletions

diff --git a/arch/arm/mm/abort-macro.S b/arch/arm/mm/abort-macro.S
index 52162d59407..2cbf68ef0e8 100644
--- a/arch/arm/mm/abort-macro.S
+++ b/arch/arm/mm/abort-macro.S
@@ -17,7 +17,7 @@
 	cmp	\tmp, # 0x5600			@ Is it ldrsb?
 	orreq	\tmp, \tmp, #1 << 11		@ Set L-bit if yes
 	tst	\tmp, #1 << 11			@ L = 0 -> write
-	orreq	\psr, \psr, #1 << 11		@ yes.
+	orreq	\fsr, \fsr, #1 << 11		@ yes.
 	b	do_DataAbort
 not_thumb:
 	.endm
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index be7c638b648..c335c76e0d8 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -22,6 +22,7 @@
 #include <linux/sched.h>
 #include <linux/uaccess.h>
 
+#include <asm/system.h>
 #include <asm/unaligned.h>
 
 #include "fault.h"
@@ -85,6 +86,33 @@ core_param(alignment, ai_usermode, int, 0600);
 #define UM_FIXUP	(1 << 1)
 #define UM_SIGNAL	(1 << 2)
 
+/* Return true if and only if the ARMv6 unaligned access model is in use. */
+static bool cpu_is_v6_unaligned(void)
+{
+	return cpu_architecture() >= CPU_ARCH_ARMv6 && (cr_alignment & CR_U);
+}
+
+static int safe_usermode(int new_usermode, bool warn)
+{
+	/*
+	 * ARMv6 and later CPUs can perform unaligned accesses for
+	 * most single load and store instructions up to word size.
+	 * LDM, STM, LDRD and STRD still need to be handled.
+	 *
+	 * Ignoring the alignment fault is not an option on these
+	 * CPUs since we spin re-faulting the instruction without
+	 * making any progress.
+	 */
+	if (cpu_is_v6_unaligned() && !(new_usermode & (UM_FIXUP | UM_SIGNAL))) {
+		new_usermode |= UM_FIXUP;
+
+		if (warn)
+			printk(KERN_WARNING "alignment: ignoring faults is unsafe on this CPU.  Defaulting to fixup mode.\n");
+	}
+
+	return new_usermode;
+}
+
 #ifdef CONFIG_PROC_FS
 static const char *usermode_action[] = {
 	"ignored",
@@ -125,7 +153,7 @@ static ssize_t alignment_proc_write(struct file *file, const char __user *buffer
 		if (get_user(mode, buffer))
 			return -EFAULT;
 		if (mode >= '0' && mode <= '5')
-			ai_usermode = mode - '0';
+			ai_usermode = safe_usermode(mode - '0', true);
 	}
 	return count;
 }
@@ -886,9 +914,16 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	if (ai_usermode & UM_FIXUP)
 		goto fixup;
 
-	if (ai_usermode & UM_SIGNAL)
-		force_sig(SIGBUS, current);
-	else {
+	if (ai_usermode & UM_SIGNAL) {
+		siginfo_t si;
+
+		si.si_signo = SIGBUS;
+		si.si_errno = 0;
+		si.si_code = BUS_ADRALN;
+		si.si_addr = (void __user *)addr;
+
+		force_sig_info(si.si_signo, &si, current);
+	} else {
 		/*
 		 * We're about to disable the alignment trap and return to
 		 * user space.  But if an interrupt occurs before actually
@@ -926,20 +961,11 @@ static int __init alignment_init(void)
 		return -ENOMEM;
 #endif
 
-	/*
-	 * ARMv6 and later CPUs can perform unaligned accesses for
-	 * most single load and store instructions up to word size.
-	 * LDM, STM, LDRD and STRD still need to be handled.
-	 *
-	 * Ignoring the alignment fault is not an option on these
-	 * CPUs since we spin re-faulting the instruction without
-	 * making any progress.
-	 */
-	if (cpu_architecture() >= CPU_ARCH_ARMv6 && (cr_alignment & CR_U)) {
+	if (cpu_is_v6_unaligned()) {
 		cr_alignment &= ~CR_A;
 		cr_no_alignment &= ~CR_A;
 		set_cr(cr_alignment);
-		ai_usermode = UM_FIXUP;
+		ai_usermode = safe_usermode(ai_usermode, false);
 	}
 
 	hook_fault_code(1, do_alignment, SIGBUS, BUS_ADRALN,
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index 44c086710d2..8ac9e9f8479 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -16,9 +16,12 @@
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
  */
+#include <linux/err.h>
 #include <linux/init.h>
 #include <linux/spinlock.h>
 #include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
 
 #include <asm/cacheflush.h>
 #include <asm/hardware/cache-l2x0.h>
@@ -26,15 +29,23 @@
 #define CACHE_LINE_SIZE		32
 
 static void __iomem *l2x0_base;
-static DEFINE_SPINLOCK(l2x0_lock);
+static DEFINE_RAW_SPINLOCK(l2x0_lock);
 static uint32_t l2x0_way_mask;	/* Bitmask of active ways */
 static uint32_t l2x0_size;
 
+struct l2x0_regs l2x0_saved_regs;
+
+struct l2x0_of_data {
+	void (*setup)(const struct device_node *, __u32 *, __u32 *);
+	void (*save)(void);
+	void (*resume)(void);
+};
+
 static inline void cache_wait_way(void __iomem *reg, unsigned long mask)
 {
 	/* wait for cache operation by line or way to complete */
 	while (readl_relaxed(reg) & mask)
-		;
+		cpu_relax();
 }
 
 #ifdef CONFIG_CACHE_PL310
@@ -115,9 +126,9 @@ static void l2x0_cache_sync(void)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&l2x0_lock, flags);
+	raw_spin_lock_irqsave(&l2x0_lock, flags);
 	cache_sync();
-	spin_unlock_irqrestore(&l2x0_lock, flags);
+	raw_spin_unlock_irqrestore(&l2x0_lock, flags);
 }
 
 static void __l2x0_flush_all(void)
@@ -134,9 +145,9 @@ static void l2x0_flush_all(void)
 	unsigned long flags;
 
 	/* clean all ways */
-	spin_lock_irqsave(&l2x0_lock, flags);
+	raw_spin_lock_irqsave(&l2x0_lock, flags);
 	__l2x0_flush_all();
-	spin_unlock_irqrestore(&l2x0_lock, flags);
+	raw_spin_unlock_irqrestore(&l2x0_lock, flags);
 }
 
 static void l2x0_clean_all(void)
@@ -144,11 +155,11 @@ static void l2x0_clean_all(void)
 	unsigned long flags;
 
 	/* clean all ways */
-	spin_lock_irqsave(&l2x0_lock, flags);
+	raw_spin_lock_irqsave(&l2x0_lock, flags);
 	writel_relaxed(l2x0_way_mask, l2x0_base + L2X0_CLEAN_WAY);
 	cache_wait_way(l2x0_base + L2X0_CLEAN_WAY, l2x0_way_mask);
 	cache_sync();
-	spin_unlock_irqrestore(&l2x0_lock, flags);
+	raw_spin_unlock_irqrestore(&l2x0_lock, flags);
 }
 
 static void l2x0_inv_all(void)
@@ -156,13 +167,13 @@ static void l2x0_inv_all(void)
 	unsigned long flags;
 
 	/* invalidate all ways */
-	spin_lock_irqsave(&l2x0_lock, flags);
+	raw_spin_lock_irqsave(&l2x0_lock, flags);
 	/* Invalidating when L2 is enabled is a nono */
 	BUG_ON(readl(l2x0_base + L2X0_CTRL) & 1);
 	writel_relaxed(l2x0_way_mask, l2x0_base + L2X0_INV_WAY);
 	cache_wait_way(l2x0_base + L2X0_INV_WAY, l2x0_way_mask);
 	cache_sync();
-	spin_unlock_irqrestore(&l2x0_lock, flags);
+	raw_spin_unlock_irqrestore(&l2x0_lock, flags);
 }
 
 static void l2x0_inv_range(unsigned long start, unsigned long end)
@@ -170,7 +181,7 @@ static void l2x0_inv_range(unsigned long start, unsigned long end)
 	void __iomem *base = l2x0_base;
 	unsigned long flags;
 
-	spin_lock_irqsave(&l2x0_lock, flags);
+	raw_spin_lock_irqsave(&l2x0_lock, flags);
 	if (start & (CACHE_LINE_SIZE - 1)) {
 		start &= ~(CACHE_LINE_SIZE - 1);
 		debug_writel(0x03);
@@ -195,13 +206,13 @@ static void l2x0_inv_range(unsigned long start, unsigned long end)
 		}
 
 		if (blk_end < end) {
-			spin_unlock_irqrestore(&l2x0_lock, flags);
-			spin_lock_irqsave(&l2x0_lock, flags);
+			raw_spin_unlock_irqrestore(&l2x0_lock, flags);
+			raw_spin_lock_irqsave(&l2x0_lock, flags);
 		}
 	}
 	cache_wait(base + L2X0_INV_LINE_PA, 1);
 	cache_sync();
-	spin_unlock_irqrestore(&l2x0_lock, flags);
+	raw_spin_unlock_irqrestore(&l2x0_lock, flags);
 }
 
 static void l2x0_clean_range(unsigned long start, unsigned long end)
@@ -214,7 +225,7 @@ static void l2x0_clean_range(unsigned long start, unsigned long end)
 		return;
 	}
 
-	spin_lock_irqsave(&l2x0_lock, flags);
+	raw_spin_lock_irqsave(&l2x0_lock, flags);
 	start &= ~(CACHE_LINE_SIZE - 1);
 	while (start < end) {
 		unsigned long blk_end = start + min(end - start, 4096UL);
@@ -225,13 +236,13 @@ static void l2x0_clean_range(unsigned long start, unsigned long end)
 		}
 
 		if (blk_end < end) {
-			spin_unlock_irqrestore(&l2x0_lock, flags);
-			spin_lock_irqsave(&l2x0_lock, flags);
+			raw_spin_unlock_irqrestore(&l2x0_lock, flags);
+			raw_spin_lock_irqsave(&l2x0_lock, flags);
 		}
 	}
 	cache_wait(base + L2X0_CLEAN_LINE_PA, 1);
 	cache_sync();
-	spin_unlock_irqrestore(&l2x0_lock, flags);
+	raw_spin_unlock_irqrestore(&l2x0_lock, flags);
 }
 
 static void l2x0_flush_range(unsigned long start, unsigned long end)
@@ -244,7 +255,7 @@ static void l2x0_flush_range(unsigned long start, unsigned long end)
 		return;
 	}
 
-	spin_lock_irqsave(&l2x0_lock, flags);
+	raw_spin_lock_irqsave(&l2x0_lock, flags);
 	start &= ~(CACHE_LINE_SIZE - 1);
 	while (start < end) {
 		unsigned long blk_end = start + min(end - start, 4096UL);
@@ -257,24 +268,43 @@ static void l2x0_flush_range(unsigned long start, unsigned long end)
 		debug_writel(0x00);
 
 		if (blk_end < end) {
-			spin_unlock_irqrestore(&l2x0_lock, flags);
-			spin_lock_irqsave(&l2x0_lock, flags);
+			raw_spin_unlock_irqrestore(&l2x0_lock, flags);
+			raw_spin_lock_irqsave(&l2x0_lock, flags);
 		}
 	}
 	cache_wait(base + L2X0_CLEAN_INV_LINE_PA, 1);
 	cache_sync();
-	spin_unlock_irqrestore(&l2x0_lock, flags);
+	raw_spin_unlock_irqrestore(&l2x0_lock, flags);
 }
 
 static void l2x0_disable(void)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&l2x0_lock, flags);
+	raw_spin_lock_irqsave(&l2x0_lock, flags);
 	__l2x0_flush_all();
 	writel_relaxed(0, l2x0_base + L2X0_CTRL);
 	dsb();
-	spin_unlock_irqrestore(&l2x0_lock, flags);
+	raw_spin_unlock_irqrestore(&l2x0_lock, flags);
+}
+
+static void l2x0_unlock(__u32 cache_id)
+{
+	int lockregs;
+	int i;
+
+	if (cache_id == L2X0_CACHE_ID_PART_L310)
+		lockregs = 8;
+	else
+		/* L210 and unknown types */
+		lockregs = 1;
+
+	for (i = 0; i < lockregs; i++) {
+		writel_relaxed(0x0, l2x0_base + L2X0_LOCKDOWN_WAY_D_BASE +
+			       i * L2X0_LOCKDOWN_STRIDE);
+		writel_relaxed(0x0, l2x0_base + L2X0_LOCKDOWN_WAY_I_BASE +
+			       i * L2X0_LOCKDOWN_STRIDE);
+	}
 }
 
 void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask)
@@ -328,10 +358,14 @@ void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask)
 	 * accessing the below registers will fault.
 	 */
 	if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & 1)) {
+		/* Make sure that I&D is not locked down when starting */
+		l2x0_unlock(cache_id);
 
 		/* l2x0 controller is disabled */
 		writel_relaxed(aux, l2x0_base + L2X0_AUX_CTRL);
 
+		l2x0_saved_regs.aux_ctrl = aux;
+
 		l2x0_inv_all();
 
 		/* enable L2X0 */
@@ -351,3 +385,202 @@ void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask)
 	printk(KERN_INFO "l2x0: %d ways, CACHE_ID 0x%08x, AUX_CTRL 0x%08x, Cache size: %d B\n",
 			ways, cache_id, aux, l2x0_size);
 }
+
+#ifdef CONFIG_OF
+static void __init l2x0_of_setup(const struct device_node *np,
+				 __u32 *aux_val, __u32 *aux_mask)
+{
+	u32 data[2] = { 0, 0 };
+	u32 tag = 0;
+	u32 dirty = 0;
+	u32 val = 0, mask = 0;
+
+	of_property_read_u32(np, "arm,tag-latency", &tag);
+	if (tag) {
+		mask |= L2X0_AUX_CTRL_TAG_LATENCY_MASK;
+		val |= (tag - 1) << L2X0_AUX_CTRL_TAG_LATENCY_SHIFT;
+	}
+
+	of_property_read_u32_array(np, "arm,data-latency",
+				   data, ARRAY_SIZE(data));
+	if (data[0] && data[1]) {
+		mask |= L2X0_AUX_CTRL_DATA_RD_LATENCY_MASK |
+			L2X0_AUX_CTRL_DATA_WR_LATENCY_MASK;
+		val |= ((data[0] - 1) << L2X0_AUX_CTRL_DATA_RD_LATENCY_SHIFT) |
+		       ((data[1] - 1) << L2X0_AUX_CTRL_DATA_WR_LATENCY_SHIFT);
+	}
+
+	of_property_read_u32(np, "arm,dirty-latency", &dirty);
+	if (dirty) {
+		mask |= L2X0_AUX_CTRL_DIRTY_LATENCY_MASK;
+		val |= (dirty - 1) << L2X0_AUX_CTRL_DIRTY_LATENCY_SHIFT;
+	}
+
+	*aux_val &= ~mask;
+	*aux_val |= val;
+	*aux_mask &= ~mask;
+}
+
+static void __init pl310_of_setup(const struct device_node *np,
+				  __u32 *aux_val, __u32 *aux_mask)
+{
+	u32 data[3] = { 0, 0, 0 };
+	u32 tag[3] = { 0, 0, 0 };
+	u32 filter[2] = { 0, 0 };
+
+	of_property_read_u32_array(np, "arm,tag-latency", tag, ARRAY_SIZE(tag));
+	if (tag[0] && tag[1] && tag[2])
+		writel_relaxed(
+			((tag[0] - 1) << L2X0_LATENCY_CTRL_RD_SHIFT) |
+			((tag[1] - 1) << L2X0_LATENCY_CTRL_WR_SHIFT) |
+			((tag[2] - 1) << L2X0_LATENCY_CTRL_SETUP_SHIFT),
+			l2x0_base + L2X0_TAG_LATENCY_CTRL);
+
+	of_property_read_u32_array(np, "arm,data-latency",
+				   data, ARRAY_SIZE(data));
+	if (data[0] && data[1] && data[2])
+		writel_relaxed(
+			((data[0] - 1) << L2X0_LATENCY_CTRL_RD_SHIFT) |
+			((data[1] - 1) << L2X0_LATENCY_CTRL_WR_SHIFT) |
+			((data[2] - 1) << L2X0_LATENCY_CTRL_SETUP_SHIFT),
+			l2x0_base + L2X0_DATA_LATENCY_CTRL);
+
+	of_property_read_u32_array(np, "arm,filter-ranges",
+				   filter, ARRAY_SIZE(filter));
+	if (filter[1]) {
+		writel_relaxed(ALIGN(filter[0] + filter[1], SZ_1M),
+			       l2x0_base + L2X0_ADDR_FILTER_END);
+		writel_relaxed((filter[0] & ~(SZ_1M - 1)) | L2X0_ADDR_FILTER_EN,
+			       l2x0_base + L2X0_ADDR_FILTER_START);
+	}
+}
+
+static void __init pl310_save(void)
+{
+	u32 l2x0_revision = readl_relaxed(l2x0_base + L2X0_CACHE_ID) &
+		L2X0_CACHE_ID_RTL_MASK;
+
+	l2x0_saved_regs.tag_latency = readl_relaxed(l2x0_base +
+		L2X0_TAG_LATENCY_CTRL);
+	l2x0_saved_regs.data_latency = readl_relaxed(l2x0_base +
+		L2X0_DATA_LATENCY_CTRL);
+	l2x0_saved_regs.filter_end = readl_relaxed(l2x0_base +
+		L2X0_ADDR_FILTER_END);
+	l2x0_saved_regs.filter_start = readl_relaxed(l2x0_base +
+		L2X0_ADDR_FILTER_START);
+
+	if (l2x0_revision >= L2X0_CACHE_ID_RTL_R2P0) {
+		/*
+		 * From r2p0, there is Prefetch offset/control register
+		 */
+		l2x0_saved_regs.prefetch_ctrl = readl_relaxed(l2x0_base +
+			L2X0_PREFETCH_CTRL);
+		/*
+		 * From r3p0, there is Power control register
+		 */
+		if (l2x0_revision >= L2X0_CACHE_ID_RTL_R3P0)
+			l2x0_saved_regs.pwr_ctrl = readl_relaxed(l2x0_base +
+				L2X0_POWER_CTRL);
+	}
+}
+
+static void l2x0_resume(void)
+{
+	if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & 1)) {
+		/* restore aux ctrl and enable l2 */
+		l2x0_unlock(readl_relaxed(l2x0_base + L2X0_CACHE_ID));
+
+		writel_relaxed(l2x0_saved_regs.aux_ctrl, l2x0_base +
+			L2X0_AUX_CTRL);
+
+		l2x0_inv_all();
+
+		writel_relaxed(1, l2x0_base + L2X0_CTRL);
+	}
+}
+
+static void pl310_resume(void)
+{
+	u32 l2x0_revision;
+
+	if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & 1)) {
+		/* restore pl310 setup */
+		writel_relaxed(l2x0_saved_regs.tag_latency,
+			l2x0_base + L2X0_TAG_LATENCY_CTRL);
+		writel_relaxed(l2x0_saved_regs.data_latency,
+			l2x0_base + L2X0_DATA_LATENCY_CTRL);
+		writel_relaxed(l2x0_saved_regs.filter_end,
+			l2x0_base + L2X0_ADDR_FILTER_END);
+		writel_relaxed(l2x0_saved_regs.filter_start,
+			l2x0_base + L2X0_ADDR_FILTER_START);
+
+		l2x0_revision = readl_relaxed(l2x0_base + L2X0_CACHE_ID) &
+			L2X0_CACHE_ID_RTL_MASK;
+
+		if (l2x0_revision >= L2X0_CACHE_ID_RTL_R2P0) {
+			writel_relaxed(l2x0_saved_regs.prefetch_ctrl,
+				l2x0_base + L2X0_PREFETCH_CTRL);
+			if (l2x0_revision >= L2X0_CACHE_ID_RTL_R3P0)
+				writel_relaxed(l2x0_saved_regs.pwr_ctrl,
+					l2x0_base + L2X0_POWER_CTRL);
+		}
+	}
+
+	l2x0_resume();
+}
+
+static const struct l2x0_of_data pl310_data = {
+	pl310_of_setup,
+	pl310_save,
+	pl310_resume,
+};
+
+static const struct l2x0_of_data l2x0_data = {
+	l2x0_of_setup,
+	NULL,
+	l2x0_resume,
+};
+
+static const struct of_device_id l2x0_ids[] __initconst = {
+	{ .compatible = "arm,pl310-cache", .data = (void *)&pl310_data },
+	{ .compatible = "arm,l220-cache", .data = (void *)&l2x0_data },
+	{ .compatible = "arm,l210-cache", .data = (void *)&l2x0_data },
+	{}
+};
+
+int __init l2x0_of_init(__u32 aux_val, __u32 aux_mask)
+{
+	struct device_node *np;
+	struct l2x0_of_data *data;
+	struct resource res;
+
+	np = of_find_matching_node(NULL, l2x0_ids);
+	if (!np)
+		return -ENODEV;
+
+	if (of_address_to_resource(np, 0, &res))
+		return -ENODEV;
+
+	l2x0_base = ioremap(res.start, resource_size(&res));
+	if (!l2x0_base)
+		return -ENOMEM;
+
+	l2x0_saved_regs.phy_base = res.start;
+
+	data = of_match_node(l2x0_ids, np)->data;
+
+	/* L2 configuration can only be changed if the cache is disabled */
+	if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & 1)) {
+		if (data->setup)
+			data->setup(np, &aux_val, &aux_mask);
+	}
+
+	if (data->save)
+		data->save();
+
+	l2x0_init(l2x0_base, aux_val, aux_mask);
+
+	outer_cache.resume = data->resume;
+	return 0;
+}
+#endif
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index 3b24bfa3b82..07c4bc8ea0a 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -174,6 +174,10 @@ ENTRY(v7_coherent_user_range)
 	dcache_line_size r2, r3
 	sub	r3, r2, #1
 	bic	r12, r0, r3
+#ifdef CONFIG_ARM_ERRATA_764369
+	ALT_SMP(W(dsb))
+	ALT_UP(W(nop))
+#endif
 1:
  USER(	mcr	p15, 0, r12, c7, c11, 1	)	@ clean D line to the point of unification
 	add	r12, r12, r2
@@ -223,6 +227,10 @@ ENTRY(v7_flush_kern_dcache_area)
 	add	r1, r0, r1
 	sub	r3, r2, #1
 	bic	r0, r0, r3
+#ifdef CONFIG_ARM_ERRATA_764369
+	ALT_SMP(W(dsb))
+	ALT_UP(W(nop))
+#endif
 1:
 	mcr	p15, 0, r0, c7, c14, 1		@ clean & invalidate D line / unified line
 	add	r0, r0, r2
@@ -247,6 +255,10 @@ v7_dma_inv_range:
 	sub	r3, r2, #1
 	tst	r0, r3
 	bic	r0, r0, r3
+#ifdef CONFIG_ARM_ERRATA_764369
+	ALT_SMP(W(dsb))
+	ALT_UP(W(nop))
+#endif
 	mcrne	p15, 0, r0, c7, c14, 1		@ clean & invalidate D / U line
 
 	tst	r1, r3
@@ -270,6 +282,10 @@ v7_dma_clean_range:
 	dcache_line_size r2, r3
 	sub	r3, r2, #1
 	bic	r0, r0, r3
+#ifdef CONFIG_ARM_ERRATA_764369
+	ALT_SMP(W(dsb))
+	ALT_UP(W(nop))
+#endif
 1:
 	mcr	p15, 0, r0, c7, c10, 1		@ clean D / U line
 	add	r0, r0, r2
@@ -288,6 +304,10 @@ ENTRY(v7_dma_flush_range)
 	dcache_line_size r2, r3
 	sub	r3, r2, #1
 	bic	r0, r0, r3
+#ifdef CONFIG_ARM_ERRATA_764369
+	ALT_SMP(W(dsb))
+	ALT_UP(W(nop))
+#endif
 1:
 	mcr	p15, 0, r0, c7, c14, 1		@ clean & invalidate D / U line
 	add	r0, r0, r2
diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c
index b0ee9ba3cfa..93aac068da9 100644
--- a/arch/arm/mm/context.c
+++ b/arch/arm/mm/context.c
@@ -16,7 +16,7 @@
 #include <asm/mmu_context.h>
 #include <asm/tlbflush.h>
 
-static DEFINE_SPINLOCK(cpu_asid_lock);
+static DEFINE_RAW_SPINLOCK(cpu_asid_lock);
 unsigned int cpu_last_asid = ASID_FIRST_VERSION;
 #ifdef CONFIG_SMP
 DEFINE_PER_CPU(struct mm_struct *, current_mm);
@@ -31,7 +31,7 @@ DEFINE_PER_CPU(struct mm_struct *, current_mm);
 void __init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 {
 	mm->context.id = 0;
-	spin_lock_init(&mm->context.id_lock);
+	raw_spin_lock_init(&mm->context.id_lock);
 }
 
 static void flush_context(void)
@@ -58,7 +58,7 @@ static void set_mm_context(struct mm_struct *mm, unsigned int asid)
 	 * the broadcast. This function is also called via IPI so the
 	 * mm->context.id_lock has to be IRQ-safe.
 	 */
-	spin_lock_irqsave(&mm->context.id_lock, flags);
+	raw_spin_lock_irqsave(&mm->context.id_lock, flags);
 	if (likely((mm->context.id ^ cpu_last_asid) >> ASID_BITS)) {
 		/*
 		 * Old version of ASID found. Set the new one and
@@ -67,7 +67,7 @@ static void set_mm_context(struct mm_struct *mm, unsigned int asid)
 		mm->context.id = asid;
 		cpumask_clear(mm_cpumask(mm));
 	}
-	spin_unlock_irqrestore(&mm->context.id_lock, flags);
+	raw_spin_unlock_irqrestore(&mm->context.id_lock, flags);
 
 	/*
 	 * Set the mm_cpumask(mm) bit for the current CPU.
@@ -117,7 +117,7 @@ void __new_context(struct mm_struct *mm)
 {
 	unsigned int asid;
 
-	spin_lock(&cpu_asid_lock);
+	raw_spin_lock(&cpu_asid_lock);
 #ifdef CONFIG_SMP
 	/*
 	 * Check the ASID again, in case the change was broadcast from
@@ -125,7 +125,7 @@ void __new_context(struct mm_struct *mm)
 	 */
 	if (unlikely(((mm->context.id ^ cpu_last_asid) >> ASID_BITS) == 0)) {
 		cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm));
-		spin_unlock(&cpu_asid_lock);
+		raw_spin_unlock(&cpu_asid_lock);
 		return;
 	}
 #endif
@@ -153,5 +153,5 @@ void __new_context(struct mm_struct *mm)
 	}
 
 	set_mm_context(mm, asid);
-	spin_unlock(&cpu_asid_lock);
+	raw_spin_unlock(&cpu_asid_lock);
 }
diff --git a/arch/arm/mm/copypage-v4mc.c b/arch/arm/mm/copypage-v4mc.c
index b8061519ce7..7d0a8c23034 100644
--- a/arch/arm/mm/copypage-v4mc.c
+++ b/arch/arm/mm/copypage-v4mc.c
@@ -30,7 +30,7 @@
 #define minicache_pgprot __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | \
 				  L_PTE_MT_MINICACHE)
 
-static DEFINE_SPINLOCK(minicache_lock);
+static DEFINE_RAW_SPINLOCK(minicache_lock);
 
 /*
  * ARMv4 mini-dcache optimised copy_user_highpage
@@ -76,14 +76,14 @@ void v4_mc_copy_user_highpage(struct page *to, struct page *from,
 	if (!test_and_set_bit(PG_dcache_clean, &from->flags))
 		__flush_dcache_page(page_mapping(from), from);
 
-	spin_lock(&minicache_lock);
+	raw_spin_lock(&minicache_lock);
 
 	set_pte_ext(TOP_PTE(0xffff8000), pfn_pte(page_to_pfn(from), minicache_pgprot), 0);
 	flush_tlb_kernel_page(0xffff8000);
 
 	mc_copy_user_page((void *)0xffff8000, kto);
 
-	spin_unlock(&minicache_lock);
+	raw_spin_unlock(&minicache_lock);
 
 	kunmap_atomic(kto, KM_USER1);
 }
diff --git a/arch/arm/mm/copypage-v6.c b/arch/arm/mm/copypage-v6.c
index 63cca009713..3d9a1552cef 100644
--- a/arch/arm/mm/copypage-v6.c
+++ b/arch/arm/mm/copypage-v6.c
@@ -27,7 +27,7 @@
 #define from_address	(0xffff8000)
 #define to_address	(0xffffc000)
 
-static DEFINE_SPINLOCK(v6_lock);
+static DEFINE_RAW_SPINLOCK(v6_lock);
 
 /*
  * Copy the user page.  No aliasing to deal with so we can just
@@ -88,7 +88,7 @@ static void v6_copy_user_highpage_aliasing(struct page *to,
 	 * Now copy the page using the same cache colour as the
 	 * pages ultimate destination.
 	 */
-	spin_lock(&v6_lock);
+	raw_spin_lock(&v6_lock);
 
 	set_pte_ext(TOP_PTE(from_address) + offset, pfn_pte(page_to_pfn(from), PAGE_KERNEL), 0);
 	set_pte_ext(TOP_PTE(to_address) + offset, pfn_pte(page_to_pfn(to), PAGE_KERNEL), 0);
@@ -101,7 +101,7 @@ static void v6_copy_user_highpage_aliasing(struct page *to,
 
 	copy_page((void *)kto, (void *)kfrom);
 
-	spin_unlock(&v6_lock);
+	raw_spin_unlock(&v6_lock);
 }
 
 /*
@@ -121,13 +121,13 @@ static void v6_clear_user_highpage_aliasing(struct page *page, unsigned long vad
 	 * Now clear the page using the same cache colour as
 	 * the pages ultimate destination.
 	 */
-	spin_lock(&v6_lock);
+	raw_spin_lock(&v6_lock);
 
 	set_pte_ext(TOP_PTE(to_address) + offset, pfn_pte(page_to_pfn(page), PAGE_KERNEL), 0);
 	flush_tlb_kernel_page(to);
 	clear_page((void *)to);
 
-	spin_unlock(&v6_lock);
+	raw_spin_unlock(&v6_lock);
 }
 
 struct cpu_user_fns v6_user_fns __initdata = {
diff --git a/arch/arm/mm/copypage-xscale.c b/arch/arm/mm/copypage-xscale.c
index 649bbcd325b..610c24ced31 100644
--- a/arch/arm/mm/copypage-xscale.c
+++ b/arch/arm/mm/copypage-xscale.c
@@ -32,7 +32,7 @@
 #define minicache_pgprot __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | \
 				  L_PTE_MT_MINICACHE)
 
-static DEFINE_SPINLOCK(minicache_lock);
+static DEFINE_RAW_SPINLOCK(minicache_lock);
 
 /*
  * XScale mini-dcache optimised copy_user_highpage
@@ -98,14 +98,14 @@ void xscale_mc_copy_user_highpage(struct page *to, struct page *from,
 	if (!test_and_set_bit(PG_dcache_clean, &from->flags))
 		__flush_dcache_page(page_mapping(from), from);
 
-	spin_lock(&minicache_lock);
+	raw_spin_lock(&minicache_lock);
 
 	set_pte_ext(TOP_PTE(COPYPAGE_MINICACHE), pfn_pte(page_to_pfn(from), minicache_pgprot), 0);
 	flush_tlb_kernel_page(COPYPAGE_MINICACHE);
 
 	mc_copy_user_page((void *)COPYPAGE_MINICACHE, kto);
 
-	spin_unlock(&minicache_lock);
+	raw_spin_unlock(&minicache_lock);
 
 	kunmap_atomic(kto, KM_USER1);
 }
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 0a0a1e7c20d..235eb775fc7 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -123,8 +123,8 @@ static void __dma_free_buffer(struct page *page, size_t size)
 #endif
 
 #define CONSISTENT_OFFSET(x)	(((unsigned long)(x) - CONSISTENT_BASE) >> PAGE_SHIFT)
-#define CONSISTENT_PTE_INDEX(x) (((unsigned long)(x) - CONSISTENT_BASE) >> PGDIR_SHIFT)
-#define NUM_CONSISTENT_PTES (CONSISTENT_DMA_SIZE >> PGDIR_SHIFT)
+#define CONSISTENT_PTE_INDEX(x) (((unsigned long)(x) - CONSISTENT_BASE) >> PMD_SHIFT)
+#define NUM_CONSISTENT_PTES (CONSISTENT_DMA_SIZE >> PMD_SHIFT)
 
 /*
  * These are the page tables (2MB each) covering uncached, DMA consistent allocations
@@ -183,7 +183,7 @@ static int __init consistent_init(void)
 		}
 
 		consistent_pte[i++] = pte;
-		base += (1 << PGDIR_SHIFT);
+		base += PMD_SIZE;
 	} while (base < CONSISTENT_END);
 
 	return ret;
@@ -324,6 +324,8 @@ __dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp,
 
 	if (addr)
 		*handle = pfn_to_dma(dev, page_to_pfn(page));
+	else
+		__dma_free_buffer(page, size);
 
 	return addr;
 }
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 3b5ea68acbb..aa33949fef6 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -20,6 +20,7 @@
 #include <linux/highmem.h>
 #include <linux/perf_event.h>
 
+#include <asm/exception.h>
 #include <asm/system.h>
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 2fee782077c..f8037ba338a 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -298,7 +298,7 @@ static void __init arm_bootmem_free(unsigned long min, unsigned long max_low,
 #ifdef CONFIG_HAVE_ARCH_PFN_VALID
 int pfn_valid(unsigned long pfn)
 {
-	return memblock_is_memory(pfn << PAGE_SHIFT);
+	return memblock_is_memory(__pfn_to_phys(pfn));
 }
 EXPORT_SYMBOL(pfn_valid);
 #endif
@@ -441,7 +441,7 @@ static inline int free_area(unsigned long pfn, unsigned long end, char *s)
 static inline void poison_init_mem(void *s, size_t count)
 {
 	u32 *p = (u32 *)s;
-	while ((count = count - 4))
+	for (; count != 0; count -= 4)
 		*p++ = 0xe7fddef0;
 }
 
@@ -496,6 +496,13 @@ static void __init free_unused_memmap(struct meminfo *mi)
 		 */
 		bank_start = min(bank_start,
 				 ALIGN(prev_bank_end, PAGES_PER_SECTION));
+#else
+		/*
+		 * Align down here since the VM subsystem insists that the
+		 * memmap entries are valid from the bank start aligned to
+		 * MAX_ORDER_NR_PAGES.
+		 */
+		bank_start = round_down(bank_start, MAX_ORDER_NR_PAGES);
 #endif
 		/*
 		 * If we had a previous bank, and there is a space
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index ab506272b2d..bdb248c4f55 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -289,6 +289,27 @@ __arm_ioremap(unsigned long phys_addr, size_t size, unsigned int mtype)
 }
 EXPORT_SYMBOL(__arm_ioremap);
 
+/*
+ * Remap an arbitrary physical address space into the kernel virtual
+ * address space as memory. Needed when the kernel wants to execute
+ * code in external memory. This is needed for reprogramming source
+ * clocks that would affect normal memory for example. Please see
+ * CONFIG_GENERIC_ALLOCATOR for allocating external memory.
+ */
+void __iomem *
+__arm_ioremap_exec(unsigned long phys_addr, size_t size, bool cached)
+{
+	unsigned int mtype;
+
+	if (cached)
+		mtype = MT_MEMORY;
+	else
+		mtype = MT_MEMORY_NONCACHED;
+
+	return __arm_ioremap_caller(phys_addr, size, mtype,
+			__builtin_return_address(0));
+}
+
 void __iounmap(volatile void __iomem *io_addr)
 {
 	void *addr = (void *)(PAGE_MASK & (unsigned long)io_addr);
diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h
index 010566799c8..ad7cce3bc43 100644
--- a/arch/arm/mm/mm.h
+++ b/arch/arm/mm/mm.h
@@ -12,8 +12,8 @@ static inline pmd_t *pmd_off_k(unsigned long virt)
 
 struct mem_type {
 	pteval_t prot_pte;
-	unsigned int prot_l1;
-	unsigned int prot_sect;
+	pmdval_t prot_l1;
+	pmdval_t prot_sect;
 	unsigned int domain;
 };
 
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 594d677b92c..226f1804be1 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -60,7 +60,7 @@ EXPORT_SYMBOL(pgprot_kernel);
 struct cachepolicy {
 	const char	policy[16];
 	unsigned int	cr_mask;
-	unsigned int	pmd;
+	pmdval_t	pmd;
 	pteval_t	pte;
 };
 
@@ -288,7 +288,7 @@ static void __init build_mem_type_table(void)
 {
 	struct cachepolicy *cp;
 	unsigned int cr = get_cr();
-	unsigned int user_pgprot, kern_pgprot, vecs_pgprot;
+	pteval_t user_pgprot, kern_pgprot, vecs_pgprot;
 	int cpu_arch = cpu_architecture();
 	int i;
 
@@ -863,14 +863,14 @@ static inline void prepare_page_table(void)
 	/*
 	 * Clear out all the mappings below the kernel image.
 	 */
-	for (addr = 0; addr < MODULES_VADDR; addr += PGDIR_SIZE)
+	for (addr = 0; addr < MODULES_VADDR; addr += PMD_SIZE)
 		pmd_clear(pmd_off_k(addr));
 
 #ifdef CONFIG_XIP_KERNEL
 	/* The XIP kernel is mapped in the module area -- skip over it */
-	addr = ((unsigned long)_etext + PGDIR_SIZE - 1) & PGDIR_MASK;
+	addr = ((unsigned long)_etext + PMD_SIZE - 1) & PMD_MASK;
 #endif
-	for ( ; addr < PAGE_OFFSET; addr += PGDIR_SIZE)
+	for ( ; addr < PAGE_OFFSET; addr += PMD_SIZE)
 		pmd_clear(pmd_off_k(addr));
 
 	/*
@@ -885,10 +885,12 @@ static inline void prepare_page_table(void)
 	 * memory bank, up to the end of the vmalloc region.
 	 */
 	for (addr = __phys_to_virt(end);
-	     addr < VMALLOC_END; addr += PGDIR_SIZE)
+	     addr < VMALLOC_END; addr += PMD_SIZE)
 		pmd_clear(pmd_off_k(addr));
 }
 
+#define SWAPPER_PG_DIR_SIZE	(PTRS_PER_PGD * sizeof(pgd_t))
+
 /*
  * Reserve the special regions of memory
  */
@@ -898,7 +900,7 @@ void __init arm_mm_memblock_reserve(void)
 	 * Reserve the page tables.  These are already in use,
 	 * and can only be in node 0.
 	 */
-	memblock_reserve(__pa(swapper_pg_dir), PTRS_PER_PGD * sizeof(pgd_t));
+	memblock_reserve(__pa(swapper_pg_dir), SWAPPER_PG_DIR_SIZE);
 
 #ifdef CONFIG_SA1111
 	/*
@@ -926,7 +928,7 @@ static void __init devicemaps_init(struct machine_desc *mdesc)
 	 */
 	vectors_page = early_alloc(PAGE_SIZE);
 
-	for (addr = VMALLOC_END; addr; addr += PGDIR_SIZE)
+	for (addr = VMALLOC_END; addr; addr += PMD_SIZE)
 		pmd_clear(pmd_off_k(addr));
 
 	/*
diff --git a/arch/arm/mm/proc-arm920.S b/arch/arm/mm/proc-arm920.S
index 92bd102e398..2e6849b41f6 100644
--- a/arch/arm/mm/proc-arm920.S
+++ b/arch/arm/mm/proc-arm920.S
@@ -379,7 +379,7 @@ ENTRY(cpu_arm920_set_pte_ext)
 
 /* Suspend/resume support: taken from arch/arm/plat-s3c24xx/sleep.S */
 .globl	cpu_arm920_suspend_size
-.equ	cpu_arm920_suspend_size, 4 * 3
+.equ	cpu_arm920_suspend_size, 4 * 4
 #ifdef CONFIG_PM_SLEEP
 ENTRY(cpu_arm920_do_suspend)
 	stmfd	sp!, {r4 - r7, lr}
diff --git a/arch/arm/mm/proc-arm926.S b/arch/arm/mm/proc-arm926.S
index 2bbcf053dff..cd8f79c3a28 100644
--- a/arch/arm/mm/proc-arm926.S
+++ b/arch/arm/mm/proc-arm926.S
@@ -394,7 +394,7 @@ ENTRY(cpu_arm926_set_pte_ext)
 
 /* Suspend/resume support: taken from arch/arm/plat-s3c24xx/sleep.S */
 .globl	cpu_arm926_suspend_size
-.equ	cpu_arm926_suspend_size, 4 * 3
+.equ	cpu_arm926_suspend_size, 4 * 4
 #ifdef CONFIG_PM_SLEEP
 ENTRY(cpu_arm926_do_suspend)
 	stmfd	sp!, {r4 - r7, lr}
diff --git a/arch/arm/mm/proc-arm946.S b/arch/arm/mm/proc-arm946.S
index f8f7ea34bfc..683af3a182b 100644
--- a/arch/arm/mm/proc-arm946.S
+++ b/arch/arm/mm/proc-arm946.S
@@ -410,6 +410,7 @@ __arm946_proc_info:
 	.long	0x41009460
 	.long	0xff00fff0
 	.long	0
+	.long	0
 	b	__arm946_setup
 	.long	cpu_arch_name
 	.long	cpu_elf_name
@@ -418,6 +419,6 @@ __arm946_proc_info:
 	.long	arm946_processor_functions
 	.long	0
 	.long	0
-	.long	arm940_cache_fns
+	.long	arm946_cache_fns
 	.size	__arm946_proc_info, . - __arm946_proc_info
 
diff --git a/arch/arm/mm/proc-sa1100.S b/arch/arm/mm/proc-sa1100.S
index 07219c2ae11..69e7f2ef738 100644
--- a/arch/arm/mm/proc-sa1100.S
+++ b/arch/arm/mm/proc-sa1100.S
@@ -182,11 +182,11 @@ ENDPROC(cpu_sa1100_do_suspend)
 
 ENTRY(cpu_sa1100_do_resume)
 	ldmia	r0, {r4 - r7}			@ load cp regs
-	mov	r1, #0
-	mcr	p15, 0, r1, c8, c7, 0		@ flush I+D TLBs
-	mcr	p15, 0, r1, c7, c7, 0		@ flush I&D cache
-	mcr	p15, 0, r1, c9, c0, 0		@ invalidate RB
-	mcr	p15, 0, r1, c9, c0, 5		@ allow user space to use RB
+	mov	ip, #0
+	mcr	p15, 0, ip, c8, c7, 0		@ flush I+D TLBs
+	mcr	p15, 0, ip, c7, c7, 0		@ flush I&D cache
+	mcr	p15, 0, ip, c9, c0, 0		@ invalidate RB
+	mcr	p15, 0, ip, c9, c0, 5		@ allow user space to use RB
 
 	mcr	p15, 0, r4, c3, c0, 0		@ domain ID
 	mcr	p15, 0, r5, c2, c0, 0		@ translation table base addr
diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S
index 219138d2f15..a923aa0fd00 100644
--- a/arch/arm/mm/proc-v6.S
+++ b/arch/arm/mm/proc-v6.S
@@ -223,6 +223,22 @@ __v6_setup:
 	mrc	p15, 0, r0, c1, c0, 0		@ read control register
 	bic	r0, r0, r5			@ clear bits them
 	orr	r0, r0, r6			@ set them
+#ifdef CONFIG_ARM_ERRATA_364296
+	/*
+	 * Workaround for the 364296 ARM1136 r0p2 erratum (possible cache data
+	 * corruption with hit-under-miss enabled). The conditional code below
+	 * (setting the undocumented bit 31 in the auxiliary control register
+	 * and the FI bit in the control register) disables hit-under-miss
+	 * without putting the processor into full low interrupt latency mode.
+	 */
+	ldr	r6, =0x4107b362			@ id for ARM1136 r0p2
+	mrc	p15, 0, r5, c0, c0, 0		@ get processor id
+	teq	r5, r6				@ check for the faulty core
+	mrceq	p15, 0, r5, c1, c0, 1		@ load aux control reg
+	orreq	r5, r5, #(1 << 31)		@ set the undocumented bit 31
+	mcreq	p15, 0, r5, c1, c0, 1		@ write aux control reg
+	orreq	r0, r0, #(1 << 21)		@ low interrupt latency configuration
+#endif
 	mov	pc, lr				@ return to head.S:__ret
 
 	/*
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index a30e78542cc..9591c8e9fb8 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -66,6 +66,7 @@ ENDPROC(cpu_v7_proc_fin)
 ENTRY(cpu_v7_reset)
 	mrc	p15, 0, r1, c1, c0, 0		@ ctrl register
 	bic	r1, r1, #0x1			@ ...............m
+ THUMB(	bic	r1, r1, #1 << 30 )		@ SCTLR.TE (Thumb exceptions)
 	mcr	p15, 0, r1, c1, c0, 0		@ disable MMU
 	isb
 	mov	pc, r0
@@ -217,7 +218,7 @@ ENDPROC(cpu_v7_set_pte_ext)
 /* Suspend/resume support: derived from arch/arm/mach-s5pv210/sleep.S */
 .globl	cpu_v7_suspend_size
 .equ	cpu_v7_suspend_size, 4 * 9
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_ARM_CPU_SUSPEND
 ENTRY(cpu_v7_do_suspend)
 	stmfd	sp!, {r4 - r11, lr}
 	mrc	p15, 0, r4, c13, c0, 0	@ FCSE/PID
@@ -247,13 +248,16 @@ ENTRY(cpu_v7_do_resume)
 	mcr	p15, 0, r7, c2, c0, 0	@ TTB 0
 	mcr	p15, 0, r8, c2, c0, 1	@ TTB 1
 	mcr	p15, 0, ip, c2, c0, 2	@ TTB control register
-	mcr	p15, 0, r10, c1, c0, 1	@ Auxiliary control register
+	mrc	p15, 0, r4, c1, c0, 1	@ Read Auxiliary control register
+	teq	r4, r10			@ Is it already set?
+	mcrne	p15, 0, r10, c1, c0, 1	@ No, so write it
 	mcr	p15, 0, r11, c1, c0, 2	@ Co-processor access control
 	ldr	r4, =PRRR		@ PRRR
 	ldr	r5, =NMRR		@ NMRR
 	mcr	p15, 0, r4, c10, c2, 0	@ write PRRR
 	mcr	p15, 0, r5, c10, c2, 1	@ write NMRR
 	isb
+	dsb
 	mov	r0, r9			@ control register
 	mov	r2, r7, lsr #14		@ get TTB0 base
 	mov	r2, r2, lsl #14
diff --git a/arch/arm/mm/proc-xsc3.S b/arch/arm/mm/proc-xsc3.S
index 28c72a2006a..755e1bf2268 100644
--- a/arch/arm/mm/proc-xsc3.S
+++ b/arch/arm/mm/proc-xsc3.S
@@ -406,7 +406,7 @@ ENTRY(cpu_xsc3_set_pte_ext)
 	.align
 
 .globl	cpu_xsc3_suspend_size
-.equ	cpu_xsc3_suspend_size, 4 * 8
+.equ	cpu_xsc3_suspend_size, 4 * 7
 #ifdef CONFIG_PM_SLEEP
 ENTRY(cpu_xsc3_do_suspend)
 	stmfd	sp!, {r4 - r10, lr}
@@ -418,12 +418,12 @@ ENTRY(cpu_xsc3_do_suspend)
 	mrc	p15, 0, r9, c1, c0, 1	@ auxiliary control reg
 	mrc 	p15, 0, r10, c1, c0, 0	@ control reg
 	bic	r4, r4, #2		@ clear frequency change bit
-	stmia	r0, {r1, r4 - r10}	@ store v:p offset + cp regs
+	stmia	r0, {r4 - r10}		@ store cp regs
 	ldmia	sp!, {r4 - r10, pc}
 ENDPROC(cpu_xsc3_do_suspend)
 
 ENTRY(cpu_xsc3_do_resume)
-	ldmia	r0, {r1, r4 - r10}	@ load v:p offset + cp regs
+	ldmia	r0, {r4 - r10}		@ load cp regs
 	mov	ip, #0
 	mcr	p15, 0, ip, c7, c7, 0	@ invalidate I & D caches, BTB
 	mcr	p15, 0, ip, c7, c10, 4	@ drain write (&fill) buffer