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

Pull arm64 updates from Will Deacon:
 "It's a bit all over the place this time with no "killer feature" to
  speak of.  Support for mismatched cache line sizes should help people
  seeing whacky JIT failures on some SoCs, and the big.LITTLE perf
  updates have been a long time coming, but a lot of the changes here
  are cleanups.

  We stray outside arch/arm64 in a few areas: the arch/arm/ arch_timer
  workaround is acked by Russell, the DT/OF bits are acked by Rob, the
  arch_timer clocksource changes acked by Marc, CPU hotplug by tglx and
  jump_label by Peter (all CC'd).

  Summary:

   - Support for execute-only page permissions
   - Support for hibernate and DEBUG_PAGEALLOC
   - Support for heterogeneous systems with mismatches cache line sizes
   - Errata workarounds (A53 843419 update and QorIQ A-008585 timer bug)
   - arm64 PMU perf updates, including cpumasks for heterogeneous systems
   - Set UTS_MACHINE for building rpm packages
   - Yet another head.S tidy-up
   - Some cleanups and refactoring, particularly in the NUMA code
   - Lots of random, non-critical fixes across the board"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (100 commits)
  arm64: tlbflush.h: add __tlbi() macro
  arm64: Kconfig: remove SMP dependence for NUMA
  arm64: Kconfig: select OF/ACPI_NUMA under NUMA config
  arm64: fix dump_backtrace/unwind_frame with NULL tsk
  arm/arm64: arch_timer: Use archdata to indicate vdso suitability
  arm64: arch_timer: Work around QorIQ Erratum A-008585
  arm64: arch_timer: Add device tree binding for A-008585 erratum
  arm64: Correctly bounds check virt_addr_valid
  arm64: migrate exception table users off module.h and onto extable.h
  arm64: pmu: Hoist pmu platform device name
  arm64: pmu: Probe default hw/cache counters
  arm64: pmu: add fallback probe table
  MAINTAINERS: Update ARM PMU PROFILING AND DEBUGGING entry
  arm64: Improve kprobes test for atomic sequence
  arm64/kvm: use alternative auto-nop
  arm64: use alternative auto-nop
  arm64: alternative: add auto-nop infrastructure
  arm64: lse: convert lse alternatives NOP padding to use __nops
  arm64: barriers: introduce nops and __nops macros for NOP sequences
  arm64: sysreg: replace open-coded mrs_s/msr_s with {read,write}_sysreg_s
  ...

12 files changed, 189 insertions, 116 deletions

diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S
index 07d7352d7c38..58b5a906ff78 100644
--- a/arch/arm64/mm/cache.S
+++ b/arch/arm64/mm/cache.S
@@ -105,19 +105,20 @@ ENTRY(__clean_dcache_area_pou)
 ENDPROC(__clean_dcache_area_pou)
 
 /*
- *	__inval_cache_range(start, end)
- *	- start   - start address of region
- *	- end     - end address of region
+ *	__dma_inv_area(start, size)
+ *	- start   - virtual start address of region
+ *	- size    - size in question
  */
-ENTRY(__inval_cache_range)
+__dma_inv_area:
+	add	x1, x1, x0
 	/* FALLTHROUGH */
 
 /*
- *	__dma_inv_range(start, end)
- *	- start   - virtual start address of region
- *	- end     - virtual end address of region
+ *	__inval_cache_range(start, end)
+ *	- start   - start address of region
+ *	- end     - end address of region
  */
-__dma_inv_range:
+ENTRY(__inval_cache_range)
 	dcache_line_size x2, x3
 	sub	x3, x2, #1
 	tst	x1, x3				// end cache line aligned?
@@ -136,46 +137,43 @@ __dma_inv_range:
 	dsb	sy
 	ret
 ENDPIPROC(__inval_cache_range)
-ENDPROC(__dma_inv_range)
+ENDPROC(__dma_inv_area)
+
+/*
+ *	__clean_dcache_area_poc(kaddr, size)
+ *
+ * 	Ensure that any D-cache lines for the interval [kaddr, kaddr+size)
+ * 	are cleaned to the PoC.
+ *
+ *	- kaddr   - kernel address
+ *	- size    - size in question
+ */
+ENTRY(__clean_dcache_area_poc)
+	/* FALLTHROUGH */
 
 /*
- *	__dma_clean_range(start, end)
+ *	__dma_clean_area(start, size)
  *	- start   - virtual start address of region
- *	- end     - virtual end address of region
+ *	- size    - size in question
  */
-__dma_clean_range:
-	dcache_line_size x2, x3
-	sub	x3, x2, #1
-	bic	x0, x0, x3
-1:
-alternative_if_not ARM64_WORKAROUND_CLEAN_CACHE
-	dc	cvac, x0
-alternative_else
-	dc	civac, x0
-alternative_endif
-	add	x0, x0, x2
-	cmp	x0, x1
-	b.lo	1b
-	dsb	sy
+__dma_clean_area:
+	dcache_by_line_op cvac, sy, x0, x1, x2, x3
 	ret
-ENDPROC(__dma_clean_range)
+ENDPIPROC(__clean_dcache_area_poc)
+ENDPROC(__dma_clean_area)
 
 /*
- *	__dma_flush_range(start, end)
+ *	__dma_flush_area(start, size)
+ *
+ *	clean & invalidate D / U line
+ *
  *	- start   - virtual start address of region
- *	- end     - virtual end address of region
+ *	- size    - size in question
  */
-ENTRY(__dma_flush_range)
-	dcache_line_size x2, x3
-	sub	x3, x2, #1
-	bic	x0, x0, x3
-1:	dc	civac, x0			// clean & invalidate D / U line
-	add	x0, x0, x2
-	cmp	x0, x1
-	b.lo	1b
-	dsb	sy
+ENTRY(__dma_flush_area)
+	dcache_by_line_op civac, sy, x0, x1, x2, x3
 	ret
-ENDPIPROC(__dma_flush_range)
+ENDPIPROC(__dma_flush_area)
 
 /*
  *	__dma_map_area(start, size, dir)
@@ -184,10 +182,9 @@ ENDPIPROC(__dma_flush_range)
  *	- dir	- DMA direction
  */
 ENTRY(__dma_map_area)
-	add	x1, x1, x0
 	cmp	w2, #DMA_FROM_DEVICE
-	b.eq	__dma_inv_range
-	b	__dma_clean_range
+	b.eq	__dma_inv_area
+	b	__dma_clean_area
 ENDPIPROC(__dma_map_area)
 
 /*
@@ -197,8 +194,7 @@ ENDPIPROC(__dma_map_area)
  *	- dir	- DMA direction
  */
 ENTRY(__dma_unmap_area)
-	add	x1, x1, x0
 	cmp	w2, #DMA_TO_DEVICE
-	b.ne	__dma_inv_range
+	b.ne	__dma_inv_area
 	ret
 ENDPIPROC(__dma_unmap_area)
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index c4284c432ae8..bdacead5b802 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -20,6 +20,7 @@
 #include <linux/gfp.h>
 #include <linux/acpi.h>
 #include <linux/bootmem.h>
+#include <linux/cache.h>
 #include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/genalloc.h>
@@ -30,7 +31,7 @@
 
 #include <asm/cacheflush.h>
 
-static int swiotlb __read_mostly;
+static int swiotlb __ro_after_init;
 
 static pgprot_t __get_dma_pgprot(unsigned long attrs, pgprot_t prot,
 				 bool coherent)
@@ -168,7 +169,7 @@ static void *__dma_alloc(struct device *dev, size_t size,
 		return ptr;
 
 	/* remove any dirty cache lines on the kernel alias */
-	__dma_flush_range(ptr, ptr + size);
+	__dma_flush_area(ptr, size);
 
 	/* create a coherent mapping */
 	page = virt_to_page(ptr);
@@ -387,7 +388,7 @@ static int __init atomic_pool_init(void)
 		void *page_addr = page_address(page);
 
 		memset(page_addr, 0, atomic_pool_size);
-		__dma_flush_range(page_addr, page_addr + atomic_pool_size);
+		__dma_flush_area(page_addr, atomic_pool_size);
 
 		atomic_pool = gen_pool_create(PAGE_SHIFT, -1);
 		if (!atomic_pool)
@@ -548,7 +549,7 @@ fs_initcall(dma_debug_do_init);
 /* Thankfully, all cache ops are by VA so we can ignore phys here */
 static void flush_page(struct device *dev, const void *virt, phys_addr_t phys)
 {
-	__dma_flush_range(virt, virt + PAGE_SIZE);
+	__dma_flush_area(virt, PAGE_SIZE);
 }
 
 static void *__iommu_alloc_attrs(struct device *dev, size_t size,
diff --git a/arch/arm64/mm/extable.c b/arch/arm64/mm/extable.c
index 81acd4706878..c9f118cd812b 100644
--- a/arch/arm64/mm/extable.c
+++ b/arch/arm64/mm/extable.c
@@ -2,7 +2,7 @@
  * Based on arch/arm/mm/extable.c
  */
 
-#include <linux/module.h>
+#include <linux/extable.h>
 #include <linux/uaccess.h>
 
 int fixup_exception(struct pt_regs *regs)
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 05d2bd776c69..53d9159662fe 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -18,7 +18,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
-#include <linux/module.h>
+#include <linux/extable.h>
 #include <linux/signal.h>
 #include <linux/mm.h>
 #include <linux/hardirq.h>
@@ -251,8 +251,7 @@ static int __do_page_fault(struct mm_struct *mm, unsigned long addr,
 good_area:
 	/*
 	 * Check that the permissions on the VMA allow for the fault which
-	 * occurred. If we encountered a write or exec fault, we must have
-	 * appropriate permissions, otherwise we allow any permission.
+	 * occurred.
 	 */
 	if (!(vma->vm_flags & vm_flags)) {
 		fault = VM_FAULT_BADACCESS;
@@ -288,7 +287,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 	struct task_struct *tsk;
 	struct mm_struct *mm;
 	int fault, sig, code;
-	unsigned long vm_flags = VM_READ | VM_WRITE | VM_EXEC;
+	unsigned long vm_flags = VM_READ | VM_WRITE;
 	unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 	if (notify_page_fault(regs, esr))
diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
index 43a76b07eb32..8377329d8c97 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -25,8 +25,6 @@
 #include <asm/cachetype.h>
 #include <asm/tlbflush.h>
 
-#include "mm.h"
-
 void flush_cache_range(struct vm_area_struct *vma, unsigned long start,
 		       unsigned long end)
 {
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index bbb7ee76e319..21c489bdeb4e 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -23,6 +23,7 @@
 #include <linux/swap.h>
 #include <linux/init.h>
 #include <linux/bootmem.h>
+#include <linux/cache.h>
 #include <linux/mman.h>
 #include <linux/nodemask.h>
 #include <linux/initrd.h>
@@ -34,6 +35,7 @@
 #include <linux/dma-contiguous.h>
 #include <linux/efi.h>
 #include <linux/swiotlb.h>
+#include <linux/vmalloc.h>
 
 #include <asm/boot.h>
 #include <asm/fixmap.h>
@@ -47,16 +49,14 @@
 #include <asm/tlb.h>
 #include <asm/alternative.h>
 
-#include "mm.h"
-
 /*
  * We need to be able to catch inadvertent references to memstart_addr
  * that occur (potentially in generic code) before arm64_memblock_init()
  * executes, which assigns it its actual value. So use a default value
  * that cannot be mistaken for a real physical address.
  */
-s64 memstart_addr __read_mostly = -1;
-phys_addr_t arm64_dma_phys_limit __read_mostly;
+s64 memstart_addr __ro_after_init = -1;
+phys_addr_t arm64_dma_phys_limit __ro_after_init;
 
 #ifdef CONFIG_BLK_DEV_INITRD
 static int __init early_initrd(char *p)
@@ -485,7 +485,12 @@ void free_initmem(void)
 {
 	free_reserved_area(__va(__pa(__init_begin)), __va(__pa(__init_end)),
 			   0, "unused kernel");
-	fixup_init();
+	/*
+	 * Unmap the __init region but leave the VM area in place. This
+	 * prevents the region from being reused for kernel modules, which
+	 * is not supported by kallsyms.
+	 */
+	unmap_kernel_range((u64)__init_begin, (u64)(__init_end - __init_begin));
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
diff --git a/arch/arm64/mm/mm.h b/arch/arm64/mm/mm.h
deleted file mode 100644
index 71fe98985455..000000000000
--- a/arch/arm64/mm/mm.h
+++ /dev/null
@@ -1,2 +0,0 @@
-
-void fixup_init(void);
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 4989948d1feb..05615a3fdc6f 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -17,6 +17,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/cache.h>
 #include <linux/export.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
@@ -42,11 +43,9 @@
 #include <asm/memblock.h>
 #include <asm/mmu_context.h>
 
-#include "mm.h"
-
 u64 idmap_t0sz = TCR_T0SZ(VA_BITS);
 
-u64 kimage_voffset __read_mostly;
+u64 kimage_voffset __ro_after_init;
 EXPORT_SYMBOL(kimage_voffset);
 
 /*
@@ -399,16 +398,6 @@ void mark_rodata_ro(void)
 			    section_size, PAGE_KERNEL_RO);
 }
 
-void fixup_init(void)
-{
-	/*
-	 * Unmap the __init region but leave the VM area in place. This
-	 * prevents the region from being reused for kernel modules, which
-	 * is not supported by kallsyms.
-	 */
-	unmap_kernel_range((u64)__init_begin, (u64)(__init_end - __init_begin));
-}
-
 static void __init map_kernel_segment(pgd_t *pgd, void *va_start, void *va_end,
 				      pgprot_t prot, struct vm_struct *vma)
 {
diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
index 5bb15eab6f00..778a985c8a70 100644
--- a/arch/arm64/mm/numa.c
+++ b/arch/arm64/mm/numa.c
@@ -17,6 +17,8 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#define pr_fmt(fmt) "NUMA: " fmt
+
 #include <linux/acpi.h>
 #include <linux/bootmem.h>
 #include <linux/memblock.h>
@@ -24,6 +26,7 @@
 #include <linux/of.h>
 
 #include <asm/acpi.h>
+#include <asm/sections.h>
 
 struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
 EXPORT_SYMBOL(node_data);
@@ -38,10 +41,9 @@ static __init int numa_parse_early_param(char *opt)
 {
 	if (!opt)
 		return -EINVAL;
-	if (!strncmp(opt, "off", 3)) {
-		pr_info("%s\n", "NUMA turned off");
+	if (!strncmp(opt, "off", 3))
 		numa_off = true;
-	}
+
 	return 0;
 }
 early_param("numa", numa_parse_early_param);
@@ -93,7 +95,6 @@ void numa_clear_node(unsigned int cpu)
  */
 static void __init setup_node_to_cpumask_map(void)
 {
-	unsigned int cpu;
 	int node;
 
 	/* setup nr_node_ids if not done yet */
@@ -106,11 +107,8 @@ static void __init setup_node_to_cpumask_map(void)
 		cpumask_clear(node_to_cpumask_map[node]);
 	}
 
-	for_each_possible_cpu(cpu)
-		set_cpu_numa_node(cpu, NUMA_NO_NODE);
-
 	/* cpumask_of_node() will now work */
-	pr_debug("NUMA: Node to cpumask map for %d nodes\n", nr_node_ids);
+	pr_debug("Node to cpumask map for %d nodes\n", nr_node_ids);
 }
 
 /*
@@ -118,18 +116,77 @@ static void __init setup_node_to_cpumask_map(void)
  */
 void numa_store_cpu_info(unsigned int cpu)
 {
-	map_cpu_to_node(cpu, numa_off ? 0 : cpu_to_node_map[cpu]);
+	map_cpu_to_node(cpu, cpu_to_node_map[cpu]);
 }
 
 void __init early_map_cpu_to_node(unsigned int cpu, int nid)
 {
 	/* fallback to node 0 */
-	if (nid < 0 || nid >= MAX_NUMNODES)
+	if (nid < 0 || nid >= MAX_NUMNODES || numa_off)
 		nid = 0;
 
 	cpu_to_node_map[cpu] = nid;
+
+	/*
+	 * We should set the numa node of cpu0 as soon as possible, because it
+	 * has already been set up online before. cpu_to_node(0) will soon be
+	 * called.
+	 */
+	if (!cpu)
+		set_cpu_numa_node(cpu, nid);
+}
+
+#ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA
+unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
+EXPORT_SYMBOL(__per_cpu_offset);
+
+static int __init early_cpu_to_node(int cpu)
+{
+	return cpu_to_node_map[cpu];
+}
+
+static int __init pcpu_cpu_distance(unsigned int from, unsigned int to)
+{
+	return node_distance(from, to);
 }
 
+static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size,
+				       size_t align)
+{
+	int nid = early_cpu_to_node(cpu);
+
+	return  memblock_virt_alloc_try_nid(size, align,
+			__pa(MAX_DMA_ADDRESS), MEMBLOCK_ALLOC_ACCESSIBLE, nid);
+}
+
+static void __init pcpu_fc_free(void *ptr, size_t size)
+{
+	memblock_free_early(__pa(ptr), size);
+}
+
+void __init setup_per_cpu_areas(void)
+{
+	unsigned long delta;
+	unsigned int cpu;
+	int rc;
+
+	/*
+	 * Always reserve area for module percpu variables.  That's
+	 * what the legacy allocator did.
+	 */
+	rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE,
+				    PERCPU_DYNAMIC_RESERVE, PAGE_SIZE,
+				    pcpu_cpu_distance,
+				    pcpu_fc_alloc, pcpu_fc_free);
+	if (rc < 0)
+		panic("Failed to initialize percpu areas.");
+
+	delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
+	for_each_possible_cpu(cpu)
+		__per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu];
+}
+#endif
+
 /**
  * numa_add_memblk - Set node id to memblk
  * @nid: NUMA node ID of the new memblk
@@ -145,13 +202,13 @@ int __init numa_add_memblk(int nid, u64 start, u64 end)
 
 	ret = memblock_set_node(start, (end - start), &memblock.memory, nid);
 	if (ret < 0) {
-		pr_err("NUMA: memblock [0x%llx - 0x%llx] failed to add on node %d\n",
+		pr_err("memblock [0x%llx - 0x%llx] failed to add on node %d\n",
 			start, (end - 1), nid);
 		return ret;
 	}
 
 	node_set(nid, numa_nodes_parsed);
-	pr_info("NUMA: Adding memblock [0x%llx - 0x%llx] on node %d\n",
+	pr_info("Adding memblock [0x%llx - 0x%llx] on node %d\n",
 			start, (end - 1), nid);
 	return ret;
 }
@@ -166,19 +223,18 @@ static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
 	void *nd;
 	int tnid;
 
-	pr_info("NUMA: Initmem setup node %d [mem %#010Lx-%#010Lx]\n",
-			nid, start_pfn << PAGE_SHIFT,
-			(end_pfn << PAGE_SHIFT) - 1);
+	pr_info("Initmem setup node %d [mem %#010Lx-%#010Lx]\n",
+		nid, start_pfn << PAGE_SHIFT, (end_pfn << PAGE_SHIFT) - 1);
 
 	nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid);
 	nd = __va(nd_pa);
 
 	/* report and initialize */
-	pr_info("NUMA: NODE_DATA [mem %#010Lx-%#010Lx]\n",
+	pr_info("NODE_DATA [mem %#010Lx-%#010Lx]\n",
 		nd_pa, nd_pa + nd_size - 1);
 	tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT);
 	if (tnid != nid)
-		pr_info("NUMA: NODE_DATA(%d) on node %d\n", nid, tnid);
+		pr_info("NODE_DATA(%d) on node %d\n", nid, tnid);
 
 	node_data[nid] = nd;
 	memset(NODE_DATA(nid), 0, sizeof(pg_data_t));
@@ -235,8 +291,7 @@ static int __init numa_alloc_distance(void)
 			numa_distance[i * numa_distance_cnt + j] = i == j ?
 				LOCAL_DISTANCE : REMOTE_DISTANCE;
 
-	pr_debug("NUMA: Initialized distance table, cnt=%d\n",
-			numa_distance_cnt);
+	pr_debug("Initialized distance table, cnt=%d\n", numa_distance_cnt);
 
 	return 0;
 }
@@ -257,20 +312,20 @@ static int __init numa_alloc_distance(void)
 void __init numa_set_distance(int from, int to, int distance)
 {
 	if (!numa_distance) {
-		pr_warn_once("NUMA: Warning: distance table not allocated yet\n");
+		pr_warn_once("Warning: distance table not allocated yet\n");
 		return;
 	}
 
 	if (from >= numa_distance_cnt || to >= numa_distance_cnt ||
 			from < 0 || to < 0) {
-		pr_warn_once("NUMA: Warning: node ids are out of bound, from=%d to=%d distance=%d\n",
+		pr_warn_once("Warning: node ids are out of bound, from=%d to=%d distance=%d\n",
 			    from, to, distance);
 		return;
 	}
 
 	if ((u8)distance != distance ||
 	    (from == to && distance != LOCAL_DISTANCE)) {
-		pr_warn_once("NUMA: Warning: invalid distance parameter, from=%d to=%d distance=%d\n",
+		pr_warn_once("Warning: invalid distance parameter, from=%d to=%d distance=%d\n",
 			     from, to, distance);
 		return;
 	}
@@ -297,7 +352,7 @@ static int __init numa_register_nodes(void)
 	/* Check that valid nid is set to memblks */
 	for_each_memblock(memory, mblk)
 		if (mblk->nid == NUMA_NO_NODE || mblk->nid >= MAX_NUMNODES) {
-			pr_warn("NUMA: Warning: invalid memblk node %d [mem %#010Lx-%#010Lx]\n",
+			pr_warn("Warning: invalid memblk node %d [mem %#010Lx-%#010Lx]\n",
 				mblk->nid, mblk->base,
 				mblk->base + mblk->size - 1);
 			return -EINVAL;
@@ -335,8 +390,10 @@ static int __init numa_init(int (*init_func)(void))
 	if (ret < 0)
 		return ret;
 
-	if (nodes_empty(numa_nodes_parsed))
+	if (nodes_empty(numa_nodes_parsed)) {
+		pr_info("No NUMA configuration found\n");
 		return -EINVAL;
+	}
 
 	ret = numa_register_nodes();
 	if (ret < 0)
@@ -344,10 +401,6 @@ static int __init numa_init(int (*init_func)(void))
 
 	setup_node_to_cpumask_map();
 
-	/* init boot processor */
-	cpu_to_node_map[0] = 0;
-	map_cpu_to_node(0, 0);
-
 	return 0;
 }
 
@@ -367,10 +420,8 @@ static int __init dummy_numa_init(void)
 
 	if (numa_off)
 		pr_info("NUMA disabled\n"); /* Forced off on command line. */
-	else
-		pr_info("No NUMA configuration found\n");
-	pr_info("NUMA: Faking a node at [mem %#018Lx-%#018Lx]\n",
-	       0LLU, PFN_PHYS(max_pfn) - 1);
+	pr_info("Faking a node at [mem %#018Lx-%#018Lx]\n",
+		0LLU, PFN_PHYS(max_pfn) - 1);
 
 	for_each_memblock(memory, mblk) {
 		ret = numa_add_memblk(0, mblk->base, mblk->base + mblk->size);
diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c
index ca6d268e3313..8def55e7249b 100644
--- a/arch/arm64/mm/pageattr.c
+++ b/arch/arm64/mm/pageattr.c
@@ -139,4 +139,43 @@ void __kernel_map_pages(struct page *page, int numpages, int enable)
 					__pgprot(0),
 					__pgprot(PTE_VALID));
 }
-#endif
+#ifdef CONFIG_HIBERNATION
+/*
+ * When built with CONFIG_DEBUG_PAGEALLOC and CONFIG_HIBERNATION, this function
+ * is used to determine if a linear map page has been marked as not-valid by
+ * CONFIG_DEBUG_PAGEALLOC. Walk the page table and check the PTE_VALID bit.
+ * This is based on kern_addr_valid(), which almost does what we need.
+ *
+ * Because this is only called on the kernel linear map,  p?d_sect() implies
+ * p?d_present(). When debug_pagealloc is enabled, sections mappings are
+ * disabled.
+ */
+bool kernel_page_present(struct page *page)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+	unsigned long addr = (unsigned long)page_address(page);
+
+	pgd = pgd_offset_k(addr);
+	if (pgd_none(*pgd))
+		return false;
+
+	pud = pud_offset(pgd, addr);
+	if (pud_none(*pud))
+		return false;
+	if (pud_sect(*pud))
+		return true;
+
+	pmd = pmd_offset(pud, addr);
+	if (pmd_none(*pmd))
+		return false;
+	if (pmd_sect(*pmd))
+		return true;
+
+	pte = pte_offset_kernel(pmd, addr);
+	return pte_valid(*pte);
+}
+#endif /* CONFIG_HIBERNATION */
+#endif /* CONFIG_DEBUG_PAGEALLOC */
diff --git a/arch/arm64/mm/pgd.c b/arch/arm64/mm/pgd.c
index ae11d4e03d0e..371c5f03a170 100644
--- a/arch/arm64/mm/pgd.c
+++ b/arch/arm64/mm/pgd.c
@@ -26,8 +26,6 @@
 #include <asm/page.h>
 #include <asm/tlbflush.h>
 
-#include "mm.h"
-
 static struct kmem_cache *pgd_cache;
 
 pgd_t *pgd_alloc(struct mm_struct *mm)
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 9d37e967fa19..352c73b6a59e 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -83,6 +83,7 @@ ENDPROC(cpu_do_suspend)
  *
  * x0: Address of context pointer
  */
+	.pushsection ".idmap.text", "ax"
 ENTRY(cpu_do_resume)
 	ldp	x2, x3, [x0]
 	ldp	x4, x5, [x0, #16]
@@ -120,6 +121,7 @@ ENTRY(cpu_do_resume)
 	isb
 	ret
 ENDPROC(cpu_do_resume)
+	.popsection
 #endif
 
 /*
@@ -134,17 +136,12 @@ ENTRY(cpu_do_switch_mm)
 	bfi	x0, x1, #48, #16		// set the ASID
 	msr	ttbr0_el1, x0			// set TTBR0
 	isb
-alternative_if_not ARM64_WORKAROUND_CAVIUM_27456
-	ret
-	nop
-	nop
-	nop
-alternative_else
+alternative_if ARM64_WORKAROUND_CAVIUM_27456
 	ic	iallu
 	dsb	nsh
 	isb
+alternative_else_nop_endif
 	ret
-alternative_endif
 ENDPROC(cpu_do_switch_mm)
 
 	.pushsection ".idmap.text", "ax"
@@ -181,6 +178,7 @@ ENDPROC(idmap_cpu_replace_ttbr1)
  *	Initialise the processor for turning the MMU on.  Return in x0 the
  *	value of the SCTLR_EL1 register.
  */
+	.pushsection ".idmap.text", "ax"
 ENTRY(__cpu_setup)
 	tlbi	vmalle1				// Invalidate local TLB
 	dsb	nsh
@@ -266,3 +264,4 @@ ENDPROC(__cpu_setup)
 crval:
 	.word	0xfcffffff			// clear
 	.word	0x34d5d91d			// set
+	.popsection