Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Will Deacon:

 - virt_to_page/page_address optimisations

 - support for NUMA systems described using device-tree

 - support for hibernate/suspend-to-disk

 - proper support for maxcpus= command line parameter

 - detection and graceful handling of AArch64-only CPUs

 - miscellaneous cleanups and non-critical fixes

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (92 commits)
  arm64: do not enforce strict 16 byte alignment to stack pointer
  arm64: kernel: Fix incorrect brk randomization
  arm64: cpuinfo: Missing NULL terminator in compat_hwcap_str
  arm64: secondary_start_kernel: Remove unnecessary barrier
  arm64: Ensure pmd_present() returns false after pmd_mknotpresent()
  arm64: Replace hard-coded values in the pmd/pud_bad() macros
  arm64: Implement pmdp_set_access_flags() for hardware AF/DBM
  arm64: Fix typo in the pmdp_huge_get_and_clear() definition
  arm64: mm: remove unnecessary EXPORT_SYMBOL_GPL
  arm64: always use STRICT_MM_TYPECHECKS
  arm64: kvm: Fix kvm teardown for systems using the extended idmap
  arm64: kaslr: increase randomization granularity
  arm64: kconfig: drop CONFIG_RTC_LIB dependency
  arm64: make ARCH_SUPPORTS_DEBUG_PAGEALLOC depend on !HIBERNATION
  arm64: hibernate: Refuse to hibernate if the boot cpu is offline
  arm64: kernel: Add support for hibernate/suspend-to-disk
  PM / Hibernate: Call flush_icache_range() on pages restored in-place
  arm64: Add new asm macro copy_page
  arm64: Promote KERNEL_START/KERNEL_END definitions to a header file
  arm64: kernel: Include _AC definition in page.h
  ...

7 files changed, 238 insertions, 29 deletions

diff --git a/drivers/firmware/efi/arm-init.c b/drivers/firmware/efi/arm-init.c
index ef90f0c4b70a..a850cbc48d8d 100644
--- a/drivers/firmware/efi/arm-init.c
+++ b/drivers/firmware/efi/arm-init.c
@@ -178,6 +178,14 @@ static __init void reserve_regions(void)
 	if (efi_enabled(EFI_DBG))
 		pr_info("Processing EFI memory map:\n");
 
+	/*
+	 * Discard memblocks discovered so far: if there are any at this
+	 * point, they originate from memory nodes in the DT, and UEFI
+	 * uses its own memory map instead.
+	 */
+	memblock_dump_all();
+	memblock_remove(0, (phys_addr_t)ULLONG_MAX);
+
 	for_each_efi_memory_desc(md) {
 		paddr = md->phys_addr;
 		npages = md->num_pages;
diff --git a/drivers/firmware/efi/libstub/arm64-stub.c b/drivers/firmware/efi/libstub/arm64-stub.c
index a90f6459f5c6..eae693eb3e91 100644
--- a/drivers/firmware/efi/libstub/arm64-stub.c
+++ b/drivers/firmware/efi/libstub/arm64-stub.c
@@ -81,15 +81,24 @@ efi_status_t handle_kernel_image(efi_system_table_t *sys_table_arg,
 
 	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && phys_seed != 0) {
 		/*
+		 * If CONFIG_DEBUG_ALIGN_RODATA is not set, produce a
+		 * displacement in the interval [0, MIN_KIMG_ALIGN) that
+		 * is a multiple of the minimal segment alignment (SZ_64K)
+		 */
+		u32 mask = (MIN_KIMG_ALIGN - 1) & ~(SZ_64K - 1);
+		u32 offset = !IS_ENABLED(CONFIG_DEBUG_ALIGN_RODATA) ?
+			     (phys_seed >> 32) & mask : TEXT_OFFSET;
+
+		/*
 		 * If KASLR is enabled, and we have some randomness available,
 		 * locate the kernel at a randomized offset in physical memory.
 		 */
-		*reserve_size = kernel_memsize + TEXT_OFFSET;
+		*reserve_size = kernel_memsize + offset;
 		status = efi_random_alloc(sys_table_arg, *reserve_size,
 					  MIN_KIMG_ALIGN, reserve_addr,
-					  phys_seed);
+					  (u32)phys_seed);
 
-		*image_addr = *reserve_addr + TEXT_OFFSET;
+		*image_addr = *reserve_addr + offset;
 	} else {
 		/*
 		 * Else, try a straight allocation at the preferred offset.
diff --git a/drivers/firmware/efi/libstub/fdt.c b/drivers/firmware/efi/libstub/fdt.c
index 6dba78aef337..e58abfa953cc 100644
--- a/drivers/firmware/efi/libstub/fdt.c
+++ b/drivers/firmware/efi/libstub/fdt.c
@@ -24,7 +24,7 @@ efi_status_t update_fdt(efi_system_table_t *sys_table, void *orig_fdt,
 			unsigned long map_size, unsigned long desc_size,
 			u32 desc_ver)
 {
-	int node, prev, num_rsv;
+	int node, num_rsv;
 	int status;
 	u32 fdt_val32;
 	u64 fdt_val64;
@@ -54,28 +54,6 @@ efi_status_t update_fdt(efi_system_table_t *sys_table, void *orig_fdt,
 		goto fdt_set_fail;
 
 	/*
-	 * Delete any memory nodes present. We must delete nodes which
-	 * early_init_dt_scan_memory may try to use.
-	 */
-	prev = 0;
-	for (;;) {
-		const char *type;
-		int len;
-
-		node = fdt_next_node(fdt, prev, NULL);
-		if (node < 0)
-			break;
-
-		type = fdt_getprop(fdt, node, "device_type", &len);
-		if (type && strncmp(type, "memory", len) == 0) {
-			fdt_del_node(fdt, node);
-			continue;
-		}
-
-		prev = node;
-	}
-
-	/*
 	 * Delete all memory reserve map entries. When booting via UEFI,
 	 * kernel will use the UEFI memory map to find reserved regions.
 	 */
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index 282344b95ec2..095bb5b5c3f2 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -55,7 +55,7 @@
 
 static void gic_check_cpu_features(void)
 {
-	WARN_TAINT_ONCE(cpus_have_cap(ARM64_HAS_SYSREG_GIC_CPUIF),
+	WARN_TAINT_ONCE(this_cpu_has_cap(ARM64_HAS_SYSREG_GIC_CPUIF),
 			TAINT_CPU_OUT_OF_SPEC,
 			"GICv3 system registers enabled, broken firmware!\n");
 }
@@ -490,6 +490,7 @@ static void gic_cpu_init(struct gic_chip_data *gic)
 		 * Get what the GIC says our CPU mask is.
 		 */
 		BUG_ON(cpu >= NR_GIC_CPU_IF);
+		gic_check_cpu_features();
 		cpu_mask = gic_get_cpumask(gic);
 		gic_cpu_map[cpu] = cpu_mask;
 
@@ -1021,8 +1022,6 @@ static void __init __gic_init_bases(unsigned int gic_nr, int irq_start,
 
 	BUG_ON(gic_nr >= CONFIG_ARM_GIC_MAX_NR);
 
-	gic_check_cpu_features();
-
 	gic = &gic_data[gic_nr];
 
 	/* Initialize irq_chip */
diff --git a/drivers/of/Kconfig b/drivers/of/Kconfig
index e2a48415d969..b3bec3aaa45d 100644
--- a/drivers/of/Kconfig
+++ b/drivers/of/Kconfig
@@ -112,4 +112,7 @@ config OF_OVERLAY
 	  While this option is selected automatically when needed, you can
 	  enable it manually to improve device tree unit test coverage.
 
+config OF_NUMA
+	bool
+
 endif # OF
diff --git a/drivers/of/Makefile b/drivers/of/Makefile
index 156c072b3117..bee3fa96b981 100644
--- a/drivers/of/Makefile
+++ b/drivers/of/Makefile
@@ -14,5 +14,6 @@ obj-$(CONFIG_OF_MTD)	+= of_mtd.o
 obj-$(CONFIG_OF_RESERVED_MEM) += of_reserved_mem.o
 obj-$(CONFIG_OF_RESOLVE)  += resolver.o
 obj-$(CONFIG_OF_OVERLAY) += overlay.o
+obj-$(CONFIG_OF_NUMA) += of_numa.o
 
 obj-$(CONFIG_OF_UNITTEST) += unittest-data/
diff --git a/drivers/of/of_numa.c b/drivers/of/of_numa.c
new file mode 100644
index 000000000000..0f2784bc1874
--- /dev/null
+++ b/drivers/of/of_numa.c
@@ -0,0 +1,211 @@
+/*
+ * OF NUMA Parsing support.
+ *
+ * Copyright (C) 2015 - 2016 Cavium Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/nodemask.h>
+
+#include <asm/numa.h>
+
+/* define default numa node to 0 */
+#define DEFAULT_NODE 0
+
+/*
+ * Even though we connect cpus to numa domains later in SMP
+ * init, we need to know the node ids now for all cpus.
+*/
+static void __init of_numa_parse_cpu_nodes(void)
+{
+	u32 nid;
+	int r;
+	struct device_node *cpus;
+	struct device_node *np = NULL;
+
+	cpus = of_find_node_by_path("/cpus");
+	if (!cpus)
+		return;
+
+	for_each_child_of_node(cpus, np) {
+		/* Skip things that are not CPUs */
+		if (of_node_cmp(np->type, "cpu") != 0)
+			continue;
+
+		r = of_property_read_u32(np, "numa-node-id", &nid);
+		if (r)
+			continue;
+
+		pr_debug("NUMA: CPU on %u\n", nid);
+		if (nid >= MAX_NUMNODES)
+			pr_warn("NUMA: Node id %u exceeds maximum value\n",
+				nid);
+		else
+			node_set(nid, numa_nodes_parsed);
+	}
+}
+
+static int __init of_numa_parse_memory_nodes(void)
+{
+	struct device_node *np = NULL;
+	struct resource rsrc;
+	u32 nid;
+	int r = 0;
+
+	for (;;) {
+		np = of_find_node_by_type(np, "memory");
+		if (!np)
+			break;
+
+		r = of_property_read_u32(np, "numa-node-id", &nid);
+		if (r == -EINVAL)
+			/*
+			 * property doesn't exist if -EINVAL, continue
+			 * looking for more memory nodes with
+			 * "numa-node-id" property
+			 */
+			continue;
+		else if (r)
+			/* some other error */
+			break;
+
+		r = of_address_to_resource(np, 0, &rsrc);
+		if (r) {
+			pr_err("NUMA: bad reg property in memory node\n");
+			break;
+		}
+
+		pr_debug("NUMA:  base = %llx len = %llx, node = %u\n",
+			 rsrc.start, rsrc.end - rsrc.start + 1, nid);
+
+		r = numa_add_memblk(nid, rsrc.start,
+				    rsrc.end - rsrc.start + 1);
+		if (r)
+			break;
+	}
+	of_node_put(np);
+
+	return r;
+}
+
+static int __init of_numa_parse_distance_map_v1(struct device_node *map)
+{
+	const __be32 *matrix;
+	int entry_count;
+	int i;
+
+	pr_info("NUMA: parsing numa-distance-map-v1\n");
+
+	matrix = of_get_property(map, "distance-matrix", NULL);
+	if (!matrix) {
+		pr_err("NUMA: No distance-matrix property in distance-map\n");
+		return -EINVAL;
+	}
+
+	entry_count = of_property_count_u32_elems(map, "distance-matrix");
+	if (entry_count <= 0) {
+		pr_err("NUMA: Invalid distance-matrix\n");
+		return -EINVAL;
+	}
+
+	for (i = 0; i + 2 < entry_count; i += 3) {
+		u32 nodea, nodeb, distance;
+
+		nodea = of_read_number(matrix, 1);
+		matrix++;
+		nodeb = of_read_number(matrix, 1);
+		matrix++;
+		distance = of_read_number(matrix, 1);
+		matrix++;
+
+		numa_set_distance(nodea, nodeb, distance);
+		pr_debug("NUMA:  distance[node%d -> node%d] = %d\n",
+			 nodea, nodeb, distance);
+
+		/* Set default distance of node B->A same as A->B */
+		if (nodeb > nodea)
+			numa_set_distance(nodeb, nodea, distance);
+	}
+
+	return 0;
+}
+
+static int __init of_numa_parse_distance_map(void)
+{
+	int ret = 0;
+	struct device_node *np;
+
+	np = of_find_compatible_node(NULL, NULL,
+				     "numa-distance-map-v1");
+	if (np)
+		ret = of_numa_parse_distance_map_v1(np);
+
+	of_node_put(np);
+	return ret;
+}
+
+int of_node_to_nid(struct device_node *device)
+{
+	struct device_node *np;
+	u32 nid;
+	int r = -ENODATA;
+
+	np = of_node_get(device);
+
+	while (np) {
+		struct device_node *parent;
+
+		r = of_property_read_u32(np, "numa-node-id", &nid);
+		/*
+		 * -EINVAL indicates the property was not found, and
+		 *  we walk up the tree trying to find a parent with a
+		 *  "numa-node-id".  Any other type of error indicates
+		 *  a bad device tree and we give up.
+		 */
+		if (r != -EINVAL)
+			break;
+
+		parent = of_get_parent(np);
+		of_node_put(np);
+		np = parent;
+	}
+	if (np && r)
+		pr_warn("NUMA: Invalid \"numa-node-id\" property in node %s\n",
+			np->name);
+	of_node_put(np);
+
+	if (!r) {
+		if (nid >= MAX_NUMNODES)
+			pr_warn("NUMA: Node id %u exceeds maximum value\n",
+				nid);
+		else
+			return nid;
+	}
+
+	return NUMA_NO_NODE;
+}
+EXPORT_SYMBOL(of_node_to_nid);
+
+int __init of_numa_init(void)
+{
+	int r;
+
+	of_numa_parse_cpu_nodes();
+	r = of_numa_parse_memory_nodes();
+	if (r)
+		return r;
+	return of_numa_parse_distance_map();
+}