Linux-libre 4.4-gnupck-4.4-gnu

12 files changed, 688 insertions, 71 deletions

diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index df7537f12..41218867a 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -419,28 +419,24 @@ config CPU_THUMBONLY
 config CPU_32v3
 	bool
 	select CPU_USE_DOMAINS if MMU
-	select NEEDS_SYSCALL_FOR_CMPXCHG if SMP
 	select NEED_KUSER_HELPERS
 	select TLS_REG_EMUL if SMP || !MMU
 
 config CPU_32v4
 	bool
 	select CPU_USE_DOMAINS if MMU
-	select NEEDS_SYSCALL_FOR_CMPXCHG if SMP
 	select NEED_KUSER_HELPERS
 	select TLS_REG_EMUL if SMP || !MMU
 
 config CPU_32v4T
 	bool
 	select CPU_USE_DOMAINS if MMU
-	select NEEDS_SYSCALL_FOR_CMPXCHG if SMP
 	select NEED_KUSER_HELPERS
 	select TLS_REG_EMUL if SMP || !MMU
 
 config CPU_32v5
 	bool
 	select CPU_USE_DOMAINS if MMU
-	select NEEDS_SYSCALL_FOR_CMPXCHG if SMP
 	select NEED_KUSER_HELPERS
 	select TLS_REG_EMUL if SMP || !MMU
 
@@ -805,14 +801,6 @@ config TLS_REG_EMUL
 	  a few prototypes like that in existence) and therefore access to
 	  that required register must be emulated.
 
-config NEEDS_SYSCALL_FOR_CMPXCHG
-	bool
-	select NEED_KUSER_HELPERS
-	help
-	  SMP on a pre-ARMv6 processor?  Well OK then.
-	  Forget about fast user space cmpxchg support.
-	  It is just not possible.
-
 config NEED_KUSER_HELPERS
 	bool
 
@@ -986,6 +974,16 @@ config CACHE_TAUROS2
 	  This option enables the Tauros2 L2 cache controller (as
 	  found on PJ1/PJ4).
 
+config CACHE_UNIPHIER
+	bool "Enable the UniPhier outer cache controller"
+	depends on ARCH_UNIPHIER
+	default y
+	select OUTER_CACHE
+	select OUTER_CACHE_SYNC
+	help
+	  This option enables the UniPhier outer cache (system cache)
+	  controller.
+
 config CACHE_XSC3L2
 	bool "Enable the L2 cache on XScale3"
 	depends on CPU_XSC3
diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile
index 57c8df500..7f76d96ce 100644
--- a/arch/arm/mm/Makefile
+++ b/arch/arm/mm/Makefile
@@ -103,3 +103,4 @@ obj-$(CONFIG_CACHE_FEROCEON_L2)	+= cache-feroceon-l2.o
 obj-$(CONFIG_CACHE_L2X0)	+= cache-l2x0.o l2c-l2x0-resume.o
 obj-$(CONFIG_CACHE_XSC3L2)	+= cache-xsc3l2.o
 obj-$(CONFIG_CACHE_TAUROS2)	+= cache-tauros2.o
+obj-$(CONFIG_CACHE_UNIPHIER)	+= cache-uniphier.o
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index 00b7f7de2..7d5f4c736 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -803,7 +803,7 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 			}
 		}
 	} else {
-		fault = probe_kernel_address(instrptr, instr);
+		fault = probe_kernel_address((void *)instrptr, instr);
 		instr = __mem_to_opcode_arm(instr);
 	}
 
diff --git a/arch/arm/mm/cache-uniphier.c b/arch/arm/mm/cache-uniphier.c
new file mode 100644
index 000000000..0502ba17a
--- /dev/null
+++ b/arch/arm/mm/cache-uniphier.c
@@ -0,0 +1,555 @@
+/*
+ * Copyright (C) 2015 Masahiro Yamada <yamada.masahiro@socionext.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt)		"uniphier: " fmt
+
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/log2.h>
+#include <linux/of_address.h>
+#include <linux/slab.h>
+#include <asm/hardware/cache-uniphier.h>
+#include <asm/outercache.h>
+
+/* control registers */
+#define UNIPHIER_SSCC		0x0	/* Control Register */
+#define    UNIPHIER_SSCC_BST			BIT(20)	/* UCWG burst read */
+#define    UNIPHIER_SSCC_ACT			BIT(19)	/* Inst-Data separate */
+#define    UNIPHIER_SSCC_WTG			BIT(18)	/* WT gathering on */
+#define    UNIPHIER_SSCC_PRD			BIT(17)	/* enable pre-fetch */
+#define    UNIPHIER_SSCC_ON			BIT(0)	/* enable cache */
+#define UNIPHIER_SSCLPDAWCR	0x30	/* Unified/Data Active Way Control */
+#define UNIPHIER_SSCLPIAWCR	0x34	/* Instruction Active Way Control */
+
+/* revision registers */
+#define UNIPHIER_SSCID		0x0	/* ID Register */
+
+/* operation registers */
+#define UNIPHIER_SSCOPE		0x244	/* Cache Operation Primitive Entry */
+#define    UNIPHIER_SSCOPE_CM_INV		0x0	/* invalidate */
+#define    UNIPHIER_SSCOPE_CM_CLEAN		0x1	/* clean */
+#define    UNIPHIER_SSCOPE_CM_FLUSH		0x2	/* flush */
+#define    UNIPHIER_SSCOPE_CM_SYNC		0x8	/* sync (drain bufs) */
+#define    UNIPHIER_SSCOPE_CM_FLUSH_PREFETCH	0x9	/* flush p-fetch buf */
+#define UNIPHIER_SSCOQM		0x248	/* Cache Operation Queue Mode */
+#define    UNIPHIER_SSCOQM_TID_MASK		(0x3 << 21)
+#define    UNIPHIER_SSCOQM_TID_LRU_DATA		(0x0 << 21)
+#define    UNIPHIER_SSCOQM_TID_LRU_INST		(0x1 << 21)
+#define    UNIPHIER_SSCOQM_TID_WAY		(0x2 << 21)
+#define    UNIPHIER_SSCOQM_S_MASK		(0x3 << 17)
+#define    UNIPHIER_SSCOQM_S_RANGE		(0x0 << 17)
+#define    UNIPHIER_SSCOQM_S_ALL		(0x1 << 17)
+#define    UNIPHIER_SSCOQM_S_WAY		(0x2 << 17)
+#define    UNIPHIER_SSCOQM_CE			BIT(15)	/* notify completion */
+#define    UNIPHIER_SSCOQM_CM_INV		0x0	/* invalidate */
+#define    UNIPHIER_SSCOQM_CM_CLEAN		0x1	/* clean */
+#define    UNIPHIER_SSCOQM_CM_FLUSH		0x2	/* flush */
+#define    UNIPHIER_SSCOQM_CM_PREFETCH		0x3	/* prefetch to cache */
+#define    UNIPHIER_SSCOQM_CM_PREFETCH_BUF	0x4	/* prefetch to pf-buf */
+#define    UNIPHIER_SSCOQM_CM_TOUCH		0x5	/* touch */
+#define    UNIPHIER_SSCOQM_CM_TOUCH_ZERO	0x6	/* touch to zero */
+#define    UNIPHIER_SSCOQM_CM_TOUCH_DIRTY	0x7	/* touch with dirty */
+#define UNIPHIER_SSCOQAD	0x24c	/* Cache Operation Queue Address */
+#define UNIPHIER_SSCOQSZ	0x250	/* Cache Operation Queue Size */
+#define UNIPHIER_SSCOQMASK	0x254	/* Cache Operation Queue Address Mask */
+#define UNIPHIER_SSCOQWN	0x258	/* Cache Operation Queue Way Number */
+#define UNIPHIER_SSCOPPQSEF	0x25c	/* Cache Operation Queue Set Complete*/
+#define    UNIPHIER_SSCOPPQSEF_FE		BIT(1)
+#define    UNIPHIER_SSCOPPQSEF_OE		BIT(0)
+#define UNIPHIER_SSCOLPQS	0x260	/* Cache Operation Queue Status */
+#define    UNIPHIER_SSCOLPQS_EF			BIT(2)
+#define    UNIPHIER_SSCOLPQS_EST		BIT(1)
+#define    UNIPHIER_SSCOLPQS_QST		BIT(0)
+
+/* Is the touch/pre-fetch destination specified by ways? */
+#define UNIPHIER_SSCOQM_TID_IS_WAY(op) \
+		((op & UNIPHIER_SSCOQM_TID_MASK) == UNIPHIER_SSCOQM_TID_WAY)
+/* Is the operation region specified by address range? */
+#define UNIPHIER_SSCOQM_S_IS_RANGE(op) \
+		((op & UNIPHIER_SSCOQM_S_MASK) == UNIPHIER_SSCOQM_S_RANGE)
+
+/**
+ * uniphier_cache_data - UniPhier outer cache specific data
+ *
+ * @ctrl_base: virtual base address of control registers
+ * @rev_base: virtual base address of revision registers
+ * @op_base: virtual base address of operation registers
+ * @way_present_mask: each bit specifies if the way is present
+ * @way_locked_mask: each bit specifies if the way is locked
+ * @nsets: number of associativity sets
+ * @line_size: line size in bytes
+ * @range_op_max_size: max size that can be handled by a single range operation
+ * @list: list node to include this level in the whole cache hierarchy
+ */
+struct uniphier_cache_data {
+	void __iomem *ctrl_base;
+	void __iomem *rev_base;
+	void __iomem *op_base;
+	u32 way_present_mask;
+	u32 way_locked_mask;
+	u32 nsets;
+	u32 line_size;
+	u32 range_op_max_size;
+	struct list_head list;
+};
+
+/*
+ * List of the whole outer cache hierarchy.  This list is only modified during
+ * the early boot stage, so no mutex is taken for the access to the list.
+ */
+static LIST_HEAD(uniphier_cache_list);
+
+/**
+ * __uniphier_cache_sync - perform a sync point for a particular cache level
+ *
+ * @data: cache controller specific data
+ */
+static void __uniphier_cache_sync(struct uniphier_cache_data *data)
+{
+	/* This sequence need not be atomic.  Do not disable IRQ. */
+	writel_relaxed(UNIPHIER_SSCOPE_CM_SYNC,
+		       data->op_base + UNIPHIER_SSCOPE);
+	/* need a read back to confirm */
+	readl_relaxed(data->op_base + UNIPHIER_SSCOPE);
+}
+
+/**
+ * __uniphier_cache_maint_common - run a queue operation for a particular level
+ *
+ * @data: cache controller specific data
+ * @start: start address of range operation (don't care for "all" operation)
+ * @size: data size of range operation (don't care for "all" operation)
+ * @operation: flags to specify the desired cache operation
+ */
+static void __uniphier_cache_maint_common(struct uniphier_cache_data *data,
+					  unsigned long start,
+					  unsigned long size,
+					  u32 operation)
+{
+	unsigned long flags;
+
+	/*
+	 * No spin lock is necessary here because:
+	 *
+	 * [1] This outer cache controller is able to accept maintenance
+	 * operations from multiple CPUs at a time in an SMP system; if a
+	 * maintenance operation is under way and another operation is issued,
+	 * the new one is stored in the queue.  The controller performs one
+	 * operation after another.  If the queue is full, the status register,
+	 * UNIPHIER_SSCOPPQSEF, indicates that the queue registration has
+	 * failed.  The status registers, UNIPHIER_{SSCOPPQSEF, SSCOLPQS}, have
+	 * different instances for each CPU, i.e. each CPU can track the status
+	 * of the maintenance operations triggered by itself.
+	 *
+	 * [2] The cache command registers, UNIPHIER_{SSCOQM, SSCOQAD, SSCOQSZ,
+	 * SSCOQWN}, are shared between multiple CPUs, but the hardware still
+	 * guarantees the registration sequence is atomic; the write access to
+	 * them are arbitrated by the hardware.  The first accessor to the
+	 * register, UNIPHIER_SSCOQM, holds the access right and it is released
+	 * by reading the status register, UNIPHIER_SSCOPPQSEF.  While one CPU
+	 * is holding the access right, other CPUs fail to register operations.
+	 * One CPU should not hold the access right for a long time, so local
+	 * IRQs should be disabled while the following sequence.
+	 */
+	local_irq_save(flags);
+
+	/* clear the complete notification flag */
+	writel_relaxed(UNIPHIER_SSCOLPQS_EF, data->op_base + UNIPHIER_SSCOLPQS);
+
+	do {
+		/* set cache operation */
+		writel_relaxed(UNIPHIER_SSCOQM_CE | operation,
+			       data->op_base + UNIPHIER_SSCOQM);
+
+		/* set address range if needed */
+		if (likely(UNIPHIER_SSCOQM_S_IS_RANGE(operation))) {
+			writel_relaxed(start, data->op_base + UNIPHIER_SSCOQAD);
+			writel_relaxed(size, data->op_base + UNIPHIER_SSCOQSZ);
+		}
+
+		/* set target ways if needed */
+		if (unlikely(UNIPHIER_SSCOQM_TID_IS_WAY(operation)))
+			writel_relaxed(data->way_locked_mask,
+				       data->op_base + UNIPHIER_SSCOQWN);
+	} while (unlikely(readl_relaxed(data->op_base + UNIPHIER_SSCOPPQSEF) &
+			  (UNIPHIER_SSCOPPQSEF_FE | UNIPHIER_SSCOPPQSEF_OE)));
+
+	/* wait until the operation is completed */
+	while (likely(readl_relaxed(data->op_base + UNIPHIER_SSCOLPQS) !=
+		      UNIPHIER_SSCOLPQS_EF))
+		cpu_relax();
+
+	local_irq_restore(flags);
+}
+
+static void __uniphier_cache_maint_all(struct uniphier_cache_data *data,
+				       u32 operation)
+{
+	__uniphier_cache_maint_common(data, 0, 0,
+				      UNIPHIER_SSCOQM_S_ALL | operation);
+
+	__uniphier_cache_sync(data);
+}
+
+static void __uniphier_cache_maint_range(struct uniphier_cache_data *data,
+					 unsigned long start, unsigned long end,
+					 u32 operation)
+{
+	unsigned long size;
+
+	/*
+	 * If the start address is not aligned,
+	 * perform a cache operation for the first cache-line
+	 */
+	start = start & ~(data->line_size - 1);
+
+	size = end - start;
+
+	if (unlikely(size >= (unsigned long)(-data->line_size))) {
+		/* this means cache operation for all range */
+		__uniphier_cache_maint_all(data, operation);
+		return;
+	}
+
+	/*
+	 * If the end address is not aligned,
+	 * perform a cache operation for the last cache-line
+	 */
+	size = ALIGN(size, data->line_size);
+
+	while (size) {
+		unsigned long chunk_size = min_t(unsigned long, size,
+						 data->range_op_max_size);
+
+		__uniphier_cache_maint_common(data, start, chunk_size,
+					UNIPHIER_SSCOQM_S_RANGE | operation);
+
+		start += chunk_size;
+		size -= chunk_size;
+	}
+
+	__uniphier_cache_sync(data);
+}
+
+static void __uniphier_cache_enable(struct uniphier_cache_data *data, bool on)
+{
+	u32 val = 0;
+
+	if (on)
+		val = UNIPHIER_SSCC_WTG | UNIPHIER_SSCC_PRD | UNIPHIER_SSCC_ON;
+
+	writel_relaxed(val, data->ctrl_base + UNIPHIER_SSCC);
+}
+
+static void __init __uniphier_cache_set_locked_ways(
+					struct uniphier_cache_data *data,
+					u32 way_mask)
+{
+	data->way_locked_mask = way_mask & data->way_present_mask;
+
+	writel_relaxed(~data->way_locked_mask & data->way_present_mask,
+		       data->ctrl_base + UNIPHIER_SSCLPDAWCR);
+}
+
+static void uniphier_cache_maint_range(unsigned long start, unsigned long end,
+				       u32 operation)
+{
+	struct uniphier_cache_data *data;
+
+	list_for_each_entry(data, &uniphier_cache_list, list)
+		__uniphier_cache_maint_range(data, start, end, operation);
+}
+
+static void uniphier_cache_maint_all(u32 operation)
+{
+	struct uniphier_cache_data *data;
+
+	list_for_each_entry(data, &uniphier_cache_list, list)
+		__uniphier_cache_maint_all(data, operation);
+}
+
+static void uniphier_cache_inv_range(unsigned long start, unsigned long end)
+{
+	uniphier_cache_maint_range(start, end, UNIPHIER_SSCOQM_CM_INV);
+}
+
+static void uniphier_cache_clean_range(unsigned long start, unsigned long end)
+{
+	uniphier_cache_maint_range(start, end, UNIPHIER_SSCOQM_CM_CLEAN);
+}
+
+static void uniphier_cache_flush_range(unsigned long start, unsigned long end)
+{
+	uniphier_cache_maint_range(start, end, UNIPHIER_SSCOQM_CM_FLUSH);
+}
+
+static void __init uniphier_cache_inv_all(void)
+{
+	uniphier_cache_maint_all(UNIPHIER_SSCOQM_CM_INV);
+}
+
+static void uniphier_cache_flush_all(void)
+{
+	uniphier_cache_maint_all(UNIPHIER_SSCOQM_CM_FLUSH);
+}
+
+static void uniphier_cache_disable(void)
+{
+	struct uniphier_cache_data *data;
+
+	list_for_each_entry_reverse(data, &uniphier_cache_list, list)
+		__uniphier_cache_enable(data, false);
+
+	uniphier_cache_flush_all();
+}
+
+static void __init uniphier_cache_enable(void)
+{
+	struct uniphier_cache_data *data;
+
+	uniphier_cache_inv_all();
+
+	list_for_each_entry(data, &uniphier_cache_list, list) {
+		__uniphier_cache_enable(data, true);
+		__uniphier_cache_set_locked_ways(data, 0);
+	}
+}
+
+static void uniphier_cache_sync(void)
+{
+	struct uniphier_cache_data *data;
+
+	list_for_each_entry(data, &uniphier_cache_list, list)
+		__uniphier_cache_sync(data);
+}
+
+int __init uniphier_cache_l2_is_enabled(void)
+{
+	struct uniphier_cache_data *data;
+
+	data = list_first_entry_or_null(&uniphier_cache_list,
+					struct uniphier_cache_data, list);
+	if (!data)
+		return 0;
+
+	return !!(readl_relaxed(data->ctrl_base + UNIPHIER_SSCC) &
+		  UNIPHIER_SSCC_ON);
+}
+
+void __init uniphier_cache_l2_touch_range(unsigned long start,
+					  unsigned long end)
+{
+	struct uniphier_cache_data *data;
+
+	data = list_first_entry_or_null(&uniphier_cache_list,
+					struct uniphier_cache_data, list);
+	if (data)
+		__uniphier_cache_maint_range(data, start, end,
+					     UNIPHIER_SSCOQM_TID_WAY |
+					     UNIPHIER_SSCOQM_CM_TOUCH);
+}
+
+void __init uniphier_cache_l2_set_locked_ways(u32 way_mask)
+{
+	struct uniphier_cache_data *data;
+
+	data = list_first_entry_or_null(&uniphier_cache_list,
+					struct uniphier_cache_data, list);
+	if (data)
+		__uniphier_cache_set_locked_ways(data, way_mask);
+}
+
+static const struct of_device_id uniphier_cache_match[] __initconst = {
+	{
+		.compatible = "socionext,uniphier-system-cache",
+	},
+	{ /* sentinel */ }
+};
+
+static struct device_node * __init uniphier_cache_get_next_level_node(
+							struct device_node *np)
+{
+	u32 phandle;
+
+	if (of_property_read_u32(np, "next-level-cache", &phandle))
+		return NULL;
+
+	return of_find_node_by_phandle(phandle);
+}
+
+static int __init __uniphier_cache_init(struct device_node *np,
+					unsigned int *cache_level)
+{
+	struct uniphier_cache_data *data;
+	u32 level, cache_size;
+	struct device_node *next_np;
+	int ret = 0;
+
+	if (!of_match_node(uniphier_cache_match, np)) {
+		pr_err("L%d: not compatible with uniphier cache\n",
+		       *cache_level);
+		return -EINVAL;
+	}
+
+	if (of_property_read_u32(np, "cache-level", &level)) {
+		pr_err("L%d: cache-level is not specified\n", *cache_level);
+		return -EINVAL;
+	}
+
+	if (level != *cache_level) {
+		pr_err("L%d: cache-level is unexpected value %d\n",
+		       *cache_level, level);
+		return -EINVAL;
+	}
+
+	if (!of_property_read_bool(np, "cache-unified")) {
+		pr_err("L%d: cache-unified is not specified\n", *cache_level);
+		return -EINVAL;
+	}
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	if (of_property_read_u32(np, "cache-line-size", &data->line_size) ||
+	    !is_power_of_2(data->line_size)) {
+		pr_err("L%d: cache-line-size is unspecified or invalid\n",
+		       *cache_level);
+		ret = -EINVAL;
+		goto err;
+	}
+
+	if (of_property_read_u32(np, "cache-sets", &data->nsets) ||
+	    !is_power_of_2(data->nsets)) {
+		pr_err("L%d: cache-sets is unspecified or invalid\n",
+		       *cache_level);
+		ret = -EINVAL;
+		goto err;
+	}
+
+	if (of_property_read_u32(np, "cache-size", &cache_size) ||
+	    cache_size == 0 || cache_size % (data->nsets * data->line_size)) {
+		pr_err("L%d: cache-size is unspecified or invalid\n",
+		       *cache_level);
+		ret = -EINVAL;
+		goto err;
+	}
+
+	data->way_present_mask =
+		((u32)1 << cache_size / data->nsets / data->line_size) - 1;
+
+	data->ctrl_base = of_iomap(np, 0);
+	if (!data->ctrl_base) {
+		pr_err("L%d: failed to map control register\n", *cache_level);
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	data->rev_base = of_iomap(np, 1);
+	if (!data->rev_base) {
+		pr_err("L%d: failed to map revision register\n", *cache_level);
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	data->op_base = of_iomap(np, 2);
+	if (!data->op_base) {
+		pr_err("L%d: failed to map operation register\n", *cache_level);
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	if (*cache_level == 2) {
+		u32 revision = readl(data->rev_base + UNIPHIER_SSCID);
+		/*
+		 * The size of range operation is limited to (1 << 22) or less
+		 * for PH-sLD8 or older SoCs.
+		 */
+		if (revision <= 0x16)
+			data->range_op_max_size = (u32)1 << 22;
+	}
+
+	data->range_op_max_size -= data->line_size;
+
+	INIT_LIST_HEAD(&data->list);
+	list_add_tail(&data->list, &uniphier_cache_list); /* no mutex */
+
+	/*
+	 * OK, this level has been successfully initialized.  Look for the next
+	 * level cache.  Do not roll back even if the initialization of the
+	 * next level cache fails because we want to continue with available
+	 * cache levels.
+	 */
+	next_np = uniphier_cache_get_next_level_node(np);
+	if (next_np) {
+		(*cache_level)++;
+		ret = __uniphier_cache_init(next_np, cache_level);
+	}
+	of_node_put(next_np);
+
+	return ret;
+err:
+	iounmap(data->op_base);
+	iounmap(data->rev_base);
+	iounmap(data->ctrl_base);
+	kfree(data);
+
+	return ret;
+}
+
+int __init uniphier_cache_init(void)
+{
+	struct device_node *np = NULL;
+	unsigned int cache_level;
+	int ret = 0;
+
+	/* look for level 2 cache */
+	while ((np = of_find_matching_node(np, uniphier_cache_match)))
+		if (!of_property_read_u32(np, "cache-level", &cache_level) &&
+		    cache_level == 2)
+			break;
+
+	if (!np)
+		return -ENODEV;
+
+	ret = __uniphier_cache_init(np, &cache_level);
+	of_node_put(np);
+
+	if (ret) {
+		/*
+		 * Error out iif L2 initialization fails.  Continue with any
+		 * error on L3 or outer because they are optional.
+		 */
+		if (cache_level == 2) {
+			pr_err("failed to initialize L2 cache\n");
+			return ret;
+		}
+
+		cache_level--;
+		ret = 0;
+	}
+
+	outer_cache.inv_range = uniphier_cache_inv_range;
+	outer_cache.clean_range = uniphier_cache_clean_range;
+	outer_cache.flush_range = uniphier_cache_flush_range;
+	outer_cache.flush_all = uniphier_cache_flush_all;
+	outer_cache.disable = uniphier_cache_disable;
+	outer_cache.sync = uniphier_cache_sync;
+
+	uniphier_cache_enable();
+
+	pr_info("enabled outer cache (cache level: %d)\n", cache_level);
+
+	return ret;
+}
diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c
index 845769e41..c8c8b9ed0 100644
--- a/arch/arm/mm/context.c
+++ b/arch/arm/mm/context.c
@@ -165,13 +165,28 @@ static void flush_context(unsigned int cpu)
 		__flush_icache_all();
 }
 
-static int is_reserved_asid(u64 asid)
+static bool check_update_reserved_asid(u64 asid, u64 newasid)
 {
 	int cpu;
-	for_each_possible_cpu(cpu)
-		if (per_cpu(reserved_asids, cpu) == asid)
-			return 1;
-	return 0;
+	bool hit = false;
+
+	/*
+	 * Iterate over the set of reserved ASIDs looking for a match.
+	 * If we find one, then we can update our mm to use newasid
+	 * (i.e. the same ASID in the current generation) but we can't
+	 * exit the loop early, since we need to ensure that all copies
+	 * of the old ASID are updated to reflect the mm. Failure to do
+	 * so could result in us missing the reserved ASID in a future
+	 * generation.
+	 */
+	for_each_possible_cpu(cpu) {
+		if (per_cpu(reserved_asids, cpu) == asid) {
+			hit = true;
+			per_cpu(reserved_asids, cpu) = newasid;
+		}
+	}
+
+	return hit;
 }
 
 static u64 new_context(struct mm_struct *mm, unsigned int cpu)
@@ -181,12 +196,14 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu)
 	u64 generation = atomic64_read(&asid_generation);
 
 	if (asid != 0) {
+		u64 newasid = generation | (asid & ~ASID_MASK);
+
 		/*
 		 * If our current ASID was active during a rollover, we
 		 * can continue to use it and this was just a false alarm.
 		 */
-		if (is_reserved_asid(asid))
-			return generation | (asid & ~ASID_MASK);
+		if (check_update_reserved_asid(asid, newasid))
+			return newasid;
 
 		/*
 		 * We had a valid ASID in a previous life, so try to re-use
@@ -194,7 +211,7 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu)
 		 */
 		asid &= ~ASID_MASK;
 		if (!__test_and_set_bit(asid, asid_map))
-			goto bump_gen;
+			return newasid;
 	}
 
 	/*
@@ -216,11 +233,8 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu)
 
 	__set_bit(asid, asid_map);
 	cur_idx = asid;
-
-bump_gen:
-	asid |= generation;
 	cpumask_clear(mm_cpumask(mm));
-	return asid;
+	return asid | generation;
 }
 
 void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk)
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index ad4eb2d26..534a60ae2 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -651,12 +651,12 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 
 	if (nommu())
 		addr = __alloc_simple_buffer(dev, size, gfp, &page);
-	else if (dev_get_cma_area(dev) && (gfp & __GFP_WAIT))
+	else if (dev_get_cma_area(dev) && (gfp & __GFP_DIRECT_RECLAIM))
 		addr = __alloc_from_contiguous(dev, size, prot, &page,
 					       caller, want_vaddr);
 	else if (is_coherent)
 		addr = __alloc_simple_buffer(dev, size, gfp, &page);
-	else if (!(gfp & __GFP_WAIT))
+	else if (!gfpflags_allow_blocking(gfp))
 		addr = __alloc_from_pool(size, &page);
 	else
 		addr = __alloc_remap_buffer(dev, size, gfp, prot, &page,
@@ -1363,7 +1363,7 @@ static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
 	*handle = DMA_ERROR_CODE;
 	size = PAGE_ALIGN(size);
 
-	if (!(gfp & __GFP_WAIT))
+	if (!gfpflags_allow_blocking(gfp))
 		return __iommu_alloc_atomic(dev, size, handle);
 
 	/*
@@ -1521,7 +1521,7 @@ static int __map_sg_chunk(struct device *dev, struct scatterlist *sg,
 		return -ENOMEM;
 
 	for (count = 0, s = sg; count < (size >> PAGE_SHIFT); s = sg_next(s)) {
-		phys_addr_t phys = sg_phys(s) & PAGE_MASK;
+		phys_addr_t phys = page_to_phys(sg_page(s));
 		unsigned int len = PAGE_ALIGN(s->offset + s->length);
 
 		if (!is_coherent &&
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 0d629b8f9..daafcf121 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -593,6 +593,28 @@ do_PrefetchAbort(unsigned long addr, unsigned int ifsr, struct pt_regs *regs)
 	arm_notify_die("", regs, &info, ifsr, 0);
 }
 
+/*
+ * Abort handler to be used only during first unmasking of asynchronous aborts
+ * on the boot CPU. This makes sure that the machine will not die if the
+ * firmware/bootloader left an imprecise abort pending for us to trip over.
+ */
+static int __init early_abort_handler(unsigned long addr, unsigned int fsr,
+				      struct pt_regs *regs)
+{
+	pr_warn("Hit pending asynchronous external abort (FSR=0x%08x) during "
+		"first unmask, this is most likely caused by a "
+		"firmware/bootloader bug.\n", fsr);
+
+	return 0;
+}
+
+void __init early_abt_enable(void)
+{
+	fsr_info[22].fn = early_abort_handler;
+	local_abt_enable();
+	fsr_info[22].fn = do_bad;
+}
+
 #ifndef CONFIG_ARM_LPAE
 static int __init exceptions_init(void)
 {
diff --git a/arch/arm/mm/fault.h b/arch/arm/mm/fault.h
index cf08bdfbe..05ec5e0df 100644
--- a/arch/arm/mm/fault.h
+++ b/arch/arm/mm/fault.h
@@ -24,5 +24,6 @@ static inline int fsr_fs(unsigned int fsr)
 
 void do_bad_area(unsigned long addr, unsigned int fsr, struct pt_regs *regs);
 unsigned long search_exception_table(unsigned long addr);
+void early_abt_enable(void);
 
 #endif	/* __ARCH_ARM_FAULT_H */
diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c
index 9df5f0958..d02f8187b 100644
--- a/arch/arm/mm/highmem.c
+++ b/arch/arm/mm/highmem.c
@@ -147,13 +147,3 @@ void *kmap_atomic_pfn(unsigned long pfn)
 
 	return (void *)vaddr;
 }
-
-struct page *kmap_atomic_to_page(const void *ptr)
-{
-	unsigned long vaddr = (unsigned long)ptr;
-
-	if (vaddr < FIXADDR_START)
-		return virt_to_page(ptr);
-
-	return pte_page(get_fixmap_pte(vaddr));
-}
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 8a63b4cdc..7f8cd1b35 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -22,6 +22,7 @@
 #include <linux/memblock.h>
 #include <linux/dma-contiguous.h>
 #include <linux/sizes.h>
+#include <linux/stop_machine.h>
 
 #include <asm/cp15.h>
 #include <asm/mach-types.h>
@@ -627,12 +628,10 @@ static struct section_perm ro_perms[] = {
  * safe to be called with preemption disabled, as under stop_machine().
  */
 static inline void section_update(unsigned long addr, pmdval_t mask,
-				  pmdval_t prot)
+				  pmdval_t prot, struct mm_struct *mm)
 {
-	struct mm_struct *mm;
 	pmd_t *pmd;
 
-	mm = current->active_mm;
 	pmd = pmd_offset(pud_offset(pgd_offset(mm, addr), addr), addr);
 
 #ifdef CONFIG_ARM_LPAE
@@ -656,49 +655,82 @@ static inline bool arch_has_strict_perms(void)
 	return !!(get_cr() & CR_XP);
 }
 
-#define set_section_perms(perms, field)	{				\
-	size_t i;							\
-	unsigned long addr;						\
-									\
-	if (!arch_has_strict_perms())					\
-		return;							\
-									\
-	for (i = 0; i < ARRAY_SIZE(perms); i++) {			\
-		if (!IS_ALIGNED(perms[i].start, SECTION_SIZE) ||	\
-		    !IS_ALIGNED(perms[i].end, SECTION_SIZE)) {		\
-			pr_err("BUG: section %lx-%lx not aligned to %lx\n", \
-				perms[i].start, perms[i].end,		\
-				SECTION_SIZE);				\
-			continue;					\
-		}							\
-									\
-		for (addr = perms[i].start;				\
-		     addr < perms[i].end;				\
-		     addr += SECTION_SIZE)				\
-			section_update(addr, perms[i].mask,		\
-				       perms[i].field);			\
-	}								\
+void set_section_perms(struct section_perm *perms, int n, bool set,
+			struct mm_struct *mm)
+{
+	size_t i;
+	unsigned long addr;
+
+	if (!arch_has_strict_perms())
+		return;
+
+	for (i = 0; i < n; i++) {
+		if (!IS_ALIGNED(perms[i].start, SECTION_SIZE) ||
+		    !IS_ALIGNED(perms[i].end, SECTION_SIZE)) {
+			pr_err("BUG: section %lx-%lx not aligned to %lx\n",
+				perms[i].start, perms[i].end,
+				SECTION_SIZE);
+			continue;
+		}
+
+		for (addr = perms[i].start;
+		     addr < perms[i].end;
+		     addr += SECTION_SIZE)
+			section_update(addr, perms[i].mask,
+				set ? perms[i].prot : perms[i].clear, mm);
+	}
+
 }
 
-static inline void fix_kernmem_perms(void)
+static void update_sections_early(struct section_perm perms[], int n)
 {
-	set_section_perms(nx_perms, prot);
+	struct task_struct *t, *s;
+
+	read_lock(&tasklist_lock);
+	for_each_process(t) {
+		if (t->flags & PF_KTHREAD)
+			continue;
+		for_each_thread(t, s)
+			set_section_perms(perms, n, true, s->mm);
+	}
+	read_unlock(&tasklist_lock);
+	set_section_perms(perms, n, true, current->active_mm);
+	set_section_perms(perms, n, true, &init_mm);
+}
+
+int __fix_kernmem_perms(void *unused)
+{
+	update_sections_early(nx_perms, ARRAY_SIZE(nx_perms));
+	return 0;
+}
+
+void fix_kernmem_perms(void)
+{
+	stop_machine(__fix_kernmem_perms, NULL, NULL);
 }
 
 #ifdef CONFIG_DEBUG_RODATA
+int __mark_rodata_ro(void *unused)
+{
+	update_sections_early(ro_perms, ARRAY_SIZE(ro_perms));
+	return 0;
+}
+
 void mark_rodata_ro(void)
 {
-	set_section_perms(ro_perms, prot);
+	stop_machine(__mark_rodata_ro, NULL, NULL);
 }
 
 void set_kernel_text_rw(void)
 {
-	set_section_perms(ro_perms, clear);
+	set_section_perms(ro_perms, ARRAY_SIZE(ro_perms), false,
+				current->active_mm);
 }
 
 void set_kernel_text_ro(void)
 {
-	set_section_perms(ro_perms, prot);
+	set_section_perms(ro_perms, ARRAY_SIZE(ro_perms), true,
+				current->active_mm);
 }
 #endif /* CONFIG_DEBUG_RODATA */
 
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 7cd15143a..4867f5daf 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -38,6 +38,7 @@
 #include <asm/mach/pci.h>
 #include <asm/fixmap.h>
 
+#include "fault.h"
 #include "mm.h"
 #include "tcm.h"
 
@@ -1363,6 +1364,9 @@ static void __init devicemaps_init(const struct machine_desc *mdesc)
 	 */
 	local_flush_tlb_all();
 	flush_cache_all();
+
+	/* Enable asynchronous aborts */
+	early_abt_enable();
 }
 
 static void __init kmap_init(void)
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index de2b246fe..8e1ea433c 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -95,7 +95,7 @@ ENDPROC(cpu_v7_dcache_clean_area)
 .equ	cpu_v7_suspend_size, 4 * 9
 #ifdef CONFIG_ARM_CPU_SUSPEND
 ENTRY(cpu_v7_do_suspend)
-	stmfd	sp!, {r4 - r10, lr}
+	stmfd	sp!, {r4 - r11, lr}
 	mrc	p15, 0, r4, c13, c0, 0	@ FCSE/PID
 	mrc	p15, 0, r5, c13, c0, 3	@ User r/o thread ID
 	stmia	r0!, {r4 - r5}
@@ -112,7 +112,7 @@ ENTRY(cpu_v7_do_suspend)
 	mrc	p15, 0, r9, c1, c0, 1	@ Auxiliary control register
 	mrc	p15, 0, r10, c1, c0, 2	@ Co-processor access control
 	stmia	r0, {r5 - r11}
-	ldmfd	sp!, {r4 - r10, pc}
+	ldmfd	sp!, {r4 - r11, pc}
 ENDPROC(cpu_v7_do_suspend)
 
 ENTRY(cpu_v7_do_resume)