Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:

 - a few misc things

 - ocfs2 updates

 - most of MM

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (159 commits)
  tools/testing/selftests/proc/proc-self-syscall.c: remove duplicate include
  proc: more robust bulk read test
  proc: test /proc/*/maps, smaps, smaps_rollup, statm
  proc: use seq_puts() everywhere
  proc: read kernel cpu stat pointer once
  proc: remove unused argument in proc_pid_lookup()
  fs/proc/thread_self.c: code cleanup for proc_setup_thread_self()
  fs/proc/self.c: code cleanup for proc_setup_self()
  proc: return exit code 4 for skipped tests
  mm,mremap: bail out earlier in mremap_to under map pressure
  mm/sparse: fix a bad comparison
  mm/memory.c: do_fault: avoid usage of stale vm_area_struct
  writeback: fix inode cgroup switching comment
  mm/huge_memory.c: fix "orig_pud" set but not used
  mm/hotplug: fix an imbalance with DEBUG_PAGEALLOC
  mm/memcontrol.c: fix bad line in comment
  mm/cma.c: cma_declare_contiguous: correct err handling
  mm/page_ext.c: fix an imbalance with kmemleak
  mm/compaction: pass pgdat to too_many_isolated() instead of zone
  mm: remove zone_lru_lock() function, access ->lru_lock directly
  ...

48 files changed, 286 insertions, 268 deletions

diff --git a/arch/alpha/include/asm/topology.h b/arch/alpha/include/asm/topology.h
index e6e13a85796a6..5a77a40567fab 100644
--- a/arch/alpha/include/asm/topology.h
+++ b/arch/alpha/include/asm/topology.h
@@ -4,6 +4,7 @@
 
 #include <linux/smp.h>
 #include <linux/threads.h>
+#include <linux/numa.h>
 #include <asm/machvec.h>
 
 #ifdef CONFIG_NUMA
@@ -29,7 +30,7 @@ static const struct cpumask *cpumask_of_node(int node)
 {
 	int cpu;
 
-	if (node == -1)
+	if (node == NUMA_NO_NODE)
 		return cpu_all_mask;
 
 	cpumask_clear(&node_to_cpumask_map[node]);
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index a4168d3661277..cfbf307d6dc4e 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1467,6 +1467,10 @@ config SYSVIPC_COMPAT
 	def_bool y
 	depends on COMPAT && SYSVIPC
 
+config ARCH_ENABLE_HUGEPAGE_MIGRATION
+	def_bool y
+	depends on HUGETLB_PAGE && MIGRATION
+
 menu "Power management options"
 
 source "kernel/power/Kconfig"
diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index fb66098754559..c6a07a3b433e3 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -20,6 +20,11 @@
 
 #include <asm/page.h>
 
+#ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION
+#define arch_hugetlb_migration_supported arch_hugetlb_migration_supported
+extern bool arch_hugetlb_migration_supported(struct hstate *h);
+#endif
+
 #define __HAVE_ARCH_HUGE_PTEP_GET
 static inline pte_t huge_ptep_get(pte_t *ptep)
 {
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 0c656850eeeaa..b01ef0180a03c 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -80,11 +80,7 @@
  */
 #ifdef CONFIG_KASAN
 #define KASAN_SHADOW_SIZE	(UL(1) << (VA_BITS - KASAN_SHADOW_SCALE_SHIFT))
-#ifdef CONFIG_KASAN_EXTRA
-#define KASAN_THREAD_SHIFT	2
-#else
 #define KASAN_THREAD_SHIFT	1
-#endif /* CONFIG_KASAN_EXTRA */
 #else
 #define KASAN_SHADOW_SIZE	(0)
 #define KASAN_THREAD_SHIFT	0
diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c
index aa9c94113700e..66b5d697d943b 100644
--- a/arch/arm64/kernel/machine_kexec.c
+++ b/arch/arm64/kernel/machine_kexec.c
@@ -321,7 +321,7 @@ void crash_post_resume(void)
  * but does not hold any data of loaded kernel image.
  *
  * Note that all the pages in crash dump kernel memory have been initially
- * marked as Reserved in kexec_reserve_crashkres_pages().
+ * marked as Reserved as memory was allocated via memblock_reserve().
  *
  * In hibernation, the pages which are Reserved and yet "nosave" are excluded
  * from the hibernation iamge. crash_is_nosave() does thich check for crash
@@ -361,7 +361,6 @@ void crash_free_reserved_phys_range(unsigned long begin, unsigned long end)
 
 	for (addr = begin; addr < end; addr += PAGE_SIZE) {
 		page = phys_to_page(addr);
-		ClearPageReserved(page);
 		free_reserved_page(page);
 	}
 }
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 28cbc22d7e305..6b4a47b3adf4d 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -27,6 +27,26 @@
 #include <asm/tlbflush.h>
 #include <asm/pgalloc.h>
 
+#ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION
+bool arch_hugetlb_migration_supported(struct hstate *h)
+{
+	size_t pagesize = huge_page_size(h);
+
+	switch (pagesize) {
+#ifdef CONFIG_ARM64_4K_PAGES
+	case PUD_SIZE:
+#endif
+	case PMD_SIZE:
+	case CONT_PMD_SIZE:
+	case CONT_PTE_SIZE:
+		return true;
+	}
+	pr_warn("%s: unrecognized huge page size 0x%lx\n",
+			__func__, pagesize);
+	return false;
+}
+#endif
+
 int pmd_huge(pmd_t pmd)
 {
 	return pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT);
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 7205a9085b4de..c38976b700697 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -118,35 +118,10 @@ static void __init reserve_crashkernel(void)
 	crashk_res.start = crash_base;
 	crashk_res.end = crash_base + crash_size - 1;
 }
-
-static void __init kexec_reserve_crashkres_pages(void)
-{
-#ifdef CONFIG_HIBERNATION
-	phys_addr_t addr;
-	struct page *page;
-
-	if (!crashk_res.end)
-		return;
-
-	/*
-	 * To reduce the size of hibernation image, all the pages are
-	 * marked as Reserved initially.
-	 */
-	for (addr = crashk_res.start; addr < (crashk_res.end + 1);
-			addr += PAGE_SIZE) {
-		page = phys_to_page(addr);
-		SetPageReserved(page);
-	}
-#endif
-}
 #else
 static void __init reserve_crashkernel(void)
 {
 }
-
-static void __init kexec_reserve_crashkres_pages(void)
-{
-}
 #endif /* CONFIG_KEXEC_CORE */
 
 #ifdef CONFIG_CRASH_DUMP
@@ -586,8 +561,6 @@ void __init mem_init(void)
 	/* this will put all unused low memory onto the freelists */
 	memblock_free_all();
 
-	kexec_reserve_crashkres_pages();
-
 	mem_init_print_info(NULL);
 
 	/*
diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
index ae34e3a1cef1c..7a0a555b366af 100644
--- a/arch/arm64/mm/numa.c
+++ b/arch/arm64/mm/numa.c
@@ -120,7 +120,7 @@ static void __init setup_node_to_cpumask_map(void)
 	}
 
 	/* cpumask_of_node() will now work */
-	pr_debug("Node to cpumask map for %d nodes\n", nr_node_ids);
+	pr_debug("Node to cpumask map for %u nodes\n", nr_node_ids);
 }
 
 /*
diff --git a/arch/ia64/kernel/numa.c b/arch/ia64/kernel/numa.c
index 92c376279c6d5..1315da6c7aeba 100644
--- a/arch/ia64/kernel/numa.c
+++ b/arch/ia64/kernel/numa.c
@@ -74,7 +74,7 @@ void __init build_cpu_to_node_map(void)
 		cpumask_clear(&node_to_cpu_mask[node]);
 
 	for_each_possible_early_cpu(cpu) {
-		node = -1;
+		node = NUMA_NO_NODE;
 		for (i = 0; i < NR_CPUS; ++i)
 			if (cpu_physical_id(cpu) == node_cpuid[i].phys_id) {
 				node = node_cpuid[i].nid;
diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
index 46bff16618362..7a969f4c3534d 100644
--- a/arch/ia64/kernel/perfmon.c
+++ b/arch/ia64/kernel/perfmon.c
@@ -583,17 +583,6 @@ pfm_put_task(struct task_struct *task)
 	if (task != current) put_task_struct(task);
 }
 
-static inline void
-pfm_reserve_page(unsigned long a)
-{
-	SetPageReserved(vmalloc_to_page((void *)a));
-}
-static inline void
-pfm_unreserve_page(unsigned long a)
-{
-	ClearPageReserved(vmalloc_to_page((void*)a));
-}
-
 static inline unsigned long
 pfm_protect_ctx_ctxsw(pfm_context_t *x)
 {
@@ -816,44 +805,6 @@ pfm_reset_msgq(pfm_context_t *ctx)
 	DPRINT(("ctx=%p msgq reset\n", ctx));
 }
 
-static void *
-pfm_rvmalloc(unsigned long size)
-{
-	void *mem;
-	unsigned long addr;
-
-	size = PAGE_ALIGN(size);
-	mem  = vzalloc(size);
-	if (mem) {
-		//printk("perfmon: CPU%d pfm_rvmalloc(%ld)=%p\n", smp_processor_id(), size, mem);
-		addr = (unsigned long)mem;
-		while (size > 0) {
-			pfm_reserve_page(addr);
-			addr+=PAGE_SIZE;
-			size-=PAGE_SIZE;
-		}
-	}
-	return mem;
-}
-
-static void
-pfm_rvfree(void *mem, unsigned long size)
-{
-	unsigned long addr;
-
-	if (mem) {
-		DPRINT(("freeing physical buffer @%p size=%lu\n", mem, size));
-		addr = (unsigned long) mem;
-		while ((long) size > 0) {
-			pfm_unreserve_page(addr);
-			addr+=PAGE_SIZE;
-			size-=PAGE_SIZE;
-		}
-		vfree(mem);
-	}
-	return;
-}
-
 static pfm_context_t *
 pfm_context_alloc(int ctx_flags)
 {
@@ -1498,7 +1449,7 @@ pfm_free_smpl_buffer(pfm_context_t *ctx)
 	/*
 	 * free the buffer
 	 */
-	pfm_rvfree(ctx->ctx_smpl_hdr, ctx->ctx_smpl_size);
+	vfree(ctx->ctx_smpl_hdr);
 
 	ctx->ctx_smpl_hdr  = NULL;
 	ctx->ctx_smpl_size = 0UL;
@@ -2137,7 +2088,7 @@ doit:
 	 * All memory free operations (especially for vmalloc'ed memory)
 	 * MUST be done with interrupts ENABLED.
 	 */
-	if (smpl_buf_addr)  pfm_rvfree(smpl_buf_addr, smpl_buf_size);
+	vfree(smpl_buf_addr);
 
 	/*
 	 * return the memory used by the context
@@ -2266,10 +2217,8 @@ pfm_smpl_buffer_alloc(struct task_struct *task, struct file *filp, pfm_context_t
 
 	/*
 	 * We do the easy to undo allocations first.
- 	 *
-	 * pfm_rvmalloc(), clears the buffer, so there is no leak
 	 */
-	smpl_buf = pfm_rvmalloc(size);
+	smpl_buf = vzalloc(size);
 	if (smpl_buf == NULL) {
 		DPRINT(("Can't allocate sampling buffer\n"));
 		return -ENOMEM;
@@ -2346,7 +2295,7 @@ pfm_smpl_buffer_alloc(struct task_struct *task, struct file *filp, pfm_context_t
 error:
 	vm_area_free(vma);
 error_kmem:
-	pfm_rvfree(smpl_buf, size);
+	vfree(smpl_buf);
 
 	return -ENOMEM;
 }
diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c
index 8a965784340c5..f9c36750c6a47 100644
--- a/arch/ia64/mm/discontig.c
+++ b/arch/ia64/mm/discontig.c
@@ -227,7 +227,7 @@ void __init setup_per_cpu_areas(void)
 	 * CPUs are put into groups according to node.  Walk cpu_map
 	 * and create new groups at node boundaries.
 	 */
-	prev_node = -1;
+	prev_node = NUMA_NO_NODE;
 	ai->nr_groups = 0;
 	for (unit = 0; unit < nr_units; unit++) {
 		cpu = cpu_map[unit];
@@ -435,7 +435,7 @@ static void __init *memory_less_node_alloc(int nid, unsigned long pernodesize)
 {
 	void *ptr = NULL;
 	u8 best = 0xff;
-	int bestnode = -1, node, anynode = 0;
+	int bestnode = NUMA_NO_NODE, node, anynode = 0;
 
 	for_each_online_node(node) {
 		if (node_isset(node, memory_less_mask))
@@ -447,7 +447,7 @@ static void __init *memory_less_node_alloc(int nid, unsigned long pernodesize)
 		anynode = node;
 	}
 
-	if (bestnode == -1)
+	if (bestnode == NUMA_NO_NODE)
 		bestnode = anynode;
 
 	ptr = memblock_alloc_try_nid(pernodesize, PERCPU_PAGE_SIZE,
diff --git a/arch/m68k/mm/memory.c b/arch/m68k/mm/memory.c
index b86a2e21693ba..227c04fe60d29 100644
--- a/arch/m68k/mm/memory.c
+++ b/arch/m68k/mm/memory.c
@@ -51,7 +51,7 @@ void __init init_pointer_table(unsigned long ptable)
 	pr_debug("init_pointer_table: %lx, %x\n", ptable, PD_MARKBITS(dp));
 
 	/* unreserve the page so it's possible to free that page */
-	PD_PAGE(dp)->flags &= ~(1 << PG_reserved);
+	__ClearPageReserved(PD_PAGE(dp));
 	init_page_count(PD_PAGE(dp));
 
 	return;
diff --git a/arch/powerpc/include/asm/book3s/64/hugetlb.h b/arch/powerpc/include/asm/book3s/64/hugetlb.h
index 5b0177733994e..66c1e4f88d654 100644
--- a/arch/powerpc/include/asm/book3s/64/hugetlb.h
+++ b/arch/powerpc/include/asm/book3s/64/hugetlb.h
@@ -13,6 +13,10 @@ radix__hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 				unsigned long len, unsigned long pgoff,
 				unsigned long flags);
 
+extern void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
+						unsigned long addr, pte_t *ptep,
+						pte_t old_pte, pte_t pte);
+
 static inline int hstate_get_psize(struct hstate *hstate)
 {
 	unsigned long shift;
@@ -42,4 +46,12 @@ static inline bool gigantic_page_supported(void)
 /* hugepd entry valid bit */
 #define HUGEPD_VAL_BITS		(0x8000000000000000UL)
 
+#define huge_ptep_modify_prot_start huge_ptep_modify_prot_start
+extern pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
+					 unsigned long addr, pte_t *ptep);
+
+#define huge_ptep_modify_prot_commit huge_ptep_modify_prot_commit
+extern void huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
+					 unsigned long addr, pte_t *ptep,
+					 pte_t old_pte, pte_t new_pte);
 #endif
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index d8c8d7c9df151..868fcaf56f6bf 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -1306,6 +1306,24 @@ static inline int pud_pfn(pud_t pud)
 	BUILD_BUG();
 	return 0;
 }
+#define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
+pte_t ptep_modify_prot_start(struct vm_area_struct *, unsigned long, pte_t *);
+void ptep_modify_prot_commit(struct vm_area_struct *, unsigned long,
+			     pte_t *, pte_t, pte_t);
+
+/*
+ * Returns true for a R -> RW upgrade of pte
+ */
+static inline bool is_pte_rw_upgrade(unsigned long old_val, unsigned long new_val)
+{
+	if (!(old_val & _PAGE_READ))
+		return false;
+
+	if ((!(old_val & _PAGE_WRITE)) && (new_val & _PAGE_WRITE))
+		return true;
+
+	return false;
+}
 
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_POWERPC_BOOK3S_64_PGTABLE_H_ */
diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h
index 7d1a3d1543fc0..5ab134eeed20c 100644
--- a/arch/powerpc/include/asm/book3s/64/radix.h
+++ b/arch/powerpc/include/asm/book3s/64/radix.h
@@ -127,6 +127,10 @@ extern void radix__ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep
 					 pte_t entry, unsigned long address,
 					 int psize);
 
+extern void radix__ptep_modify_prot_commit(struct vm_area_struct *vma,
+					   unsigned long addr, pte_t *ptep,
+					   pte_t old_pte, pte_t pte);
+
 static inline unsigned long __radix_pte_update(pte_t *ptep, unsigned long clr,
 					       unsigned long set)
 {
diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index aee4fcc249902..77fc21278fa2a 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -10,6 +10,7 @@
 #include <linux/pci.h>
 #include <linux/list.h>
 #include <linux/ioport.h>
+#include <linux/numa.h>
 
 struct device_node;
 
@@ -265,7 +266,7 @@ extern int pcibios_map_io_space(struct pci_bus *bus);
 #ifdef CONFIG_NUMA
 #define PHB_SET_NODE(PHB, NODE)		((PHB)->node = (NODE))
 #else
-#define PHB_SET_NODE(PHB, NODE)		((PHB)->node = -1)
+#define PHB_SET_NODE(PHB, NODE)		((PHB)->node = NUMA_NO_NODE)
 #endif
 
 #endif	/* CONFIG_PPC64 */
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index 913bfca09c4f1..b8480127793db 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -11,6 +11,7 @@
 #include <linux/export.h>
 #include <linux/memblock.h>
 #include <linux/sched/task.h>
+#include <linux/numa.h>
 
 #include <asm/lppaca.h>
 #include <asm/paca.h>
@@ -36,7 +37,7 @@ static void *__init alloc_paca_data(unsigned long size, unsigned long align,
 	 * which will put its paca in the right place.
 	 */
 	if (cpu == boot_cpuid) {
-		nid = -1;
+		nid = NUMA_NO_NODE;
 		memblock_set_bottom_up(true);
 	} else {
 		nid = early_cpu_to_node(cpu);
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 88e4f69a09e52..4538e8ddde807 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -32,6 +32,7 @@
 #include <linux/vmalloc.h>
 #include <linux/slab.h>
 #include <linux/vgaarb.h>
+#include <linux/numa.h>
 
 #include <asm/processor.h>
 #include <asm/io.h>
@@ -132,7 +133,7 @@ struct pci_controller *pcibios_alloc_controller(struct device_node *dev)
 		int nid = of_node_to_nid(dev);
 
 		if (nid < 0 || !node_online(nid))
-			nid = -1;
+			nid = NUMA_NO_NODE;
 
 		PHB_SET_NODE(phb, nid);
 	}
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index 7725a97147367..a31b6234fcd7c 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -798,7 +798,6 @@ static int __init vdso_init(void)
 	BUG_ON(vdso32_pagelist == NULL);
 	for (i = 0; i < vdso32_pages; i++) {
 		struct page *pg = virt_to_page(vdso32_kbase + i*PAGE_SIZE);
-		ClearPageReserved(pg);
 		get_page(pg);
 		vdso32_pagelist[i] = pg;
 	}
@@ -812,7 +811,6 @@ static int __init vdso_init(void)
 	BUG_ON(vdso64_pagelist == NULL);
 	for (i = 0; i < vdso64_pages; i++) {
 		struct page *pg = virt_to_page(vdso64_kbase + i*PAGE_SIZE);
-		ClearPageReserved(pg);
 		get_page(pg);
 		vdso64_pagelist[i] = pg;
 	}
diff --git a/arch/powerpc/mm/hugetlbpage-hash64.c b/arch/powerpc/mm/hugetlbpage-hash64.c
index 2e6a8f9345d37..367ce3a4a5039 100644
--- a/arch/powerpc/mm/hugetlbpage-hash64.c
+++ b/arch/powerpc/mm/hugetlbpage-hash64.c
@@ -121,3 +121,28 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
 	*ptep = __pte(new_pte & ~H_PAGE_BUSY);
 	return 0;
 }
+
+pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
+				  unsigned long addr, pte_t *ptep)
+{
+	unsigned long pte_val;
+	/*
+	 * Clear the _PAGE_PRESENT so that no hardware parallel update is
+	 * possible. Also keep the pte_present true so that we don't take
+	 * wrong fault.
+	 */
+	pte_val = pte_update(vma->vm_mm, addr, ptep,
+			     _PAGE_PRESENT, _PAGE_INVALID, 1);
+
+	return __pte(pte_val);
+}
+
+void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
+				  pte_t *ptep, pte_t old_pte, pte_t pte)
+{
+
+	if (radix_enabled())
+		return radix__huge_ptep_modify_prot_commit(vma, addr, ptep,
+							   old_pte, pte);
+	set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+}
diff --git a/arch/powerpc/mm/hugetlbpage-radix.c b/arch/powerpc/mm/hugetlbpage-radix.c
index 2486bee0f93e3..11d9ea28a816a 100644
--- a/arch/powerpc/mm/hugetlbpage-radix.c
+++ b/arch/powerpc/mm/hugetlbpage-radix.c
@@ -90,3 +90,20 @@ radix__hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 
 	return vm_unmapped_area(&info);
 }
+
+void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
+					 unsigned long addr, pte_t *ptep,
+					 pte_t old_pte, pte_t pte)
+{
+	struct mm_struct *mm = vma->vm_mm;
+
+	/*
+	 * To avoid NMMU hang while relaxing access we need to flush the tlb before
+	 * we set the new value.
+	 */
+	if (is_pte_rw_upgrade(pte_val(old_pte), pte_val(pte)) &&
+	    (atomic_read(&mm->context.copros) > 0))
+		radix__flush_hugetlb_page(vma, addr);
+
+	set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+}
diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
index a712a650a8b6d..e7a9c4f6bfca4 100644
--- a/arch/powerpc/mm/mmu_context_iommu.c
+++ b/arch/powerpc/mm/mmu_context_iommu.c
@@ -21,6 +21,7 @@
 #include <linux/sizes.h>
 #include <asm/mmu_context.h>
 #include <asm/pte-walk.h>
+#include <linux/mm_inline.h>
 
 static DEFINE_MUTEX(mem_list_mutex);
 
@@ -34,8 +35,18 @@ struct mm_iommu_table_group_mem_t {
 	atomic64_t mapped;
 	unsigned int pageshift;
 	u64 ua;			/* userspace address */
-	u64 entries;		/* number of entries in hpas[] */
-	u64 *hpas;		/* vmalloc'ed */
+	u64 entries;		/* number of entries in hpas/hpages[] */
+	/*
+	 * in mm_iommu_get we temporarily use this to store
+	 * struct page address.
+	 *
+	 * We need to convert ua to hpa in real mode. Make it
+	 * simpler by storing physical address.
+	 */
+	union {
+		struct page **hpages;	/* vmalloc'ed */
+		phys_addr_t *hpas;
+	};
 #define MM_IOMMU_TABLE_INVALID_HPA	((uint64_t)-1)
 	u64 dev_hpa;		/* Device memory base address */
 };
@@ -80,64 +91,13 @@ bool mm_iommu_preregistered(struct mm_struct *mm)
 }
 EXPORT_SYMBOL_GPL(mm_iommu_preregistered);
 
-/*
- * Taken from alloc_migrate_target with changes to remove CMA allocations
- */
-struct page *new_iommu_non_cma_page(struct page *page, unsigned long private)
-{
-	gfp_t gfp_mask = GFP_USER;
-	struct page *new_page;
-
-	if (PageCompound(page))
-		return NULL;
-
-	if (PageHighMem(page))
-		gfp_mask |= __GFP_HIGHMEM;
-
-	/*
-	 * We don't want the allocation to force an OOM if possibe
-	 */
-	new_page = alloc_page(gfp_mask | __GFP_NORETRY | __GFP_NOWARN);
-	return new_page;
-}
-
-static int mm_iommu_move_page_from_cma(struct page *page)
-{
-	int ret = 0;
-	LIST_HEAD(cma_migrate_pages);
-
-	/* Ignore huge pages for now */
-	if (PageCompound(page))
-		return -EBUSY;
-
-	lru_add_drain();
-	ret = isolate_lru_page(page);
-	if (ret)
-		return ret;
-
-	list_add(&page->lru, &cma_migrate_pages);
-	put_page(page); /* Drop the gup reference */
-
-	ret = migrate_pages(&cma_migrate_pages, new_iommu_non_cma_page,
-				NULL, 0, MIGRATE_SYNC, MR_CONTIG_RANGE);
-	if (ret) {
-		if (!list_empty(&cma_migrate_pages))
-			putback_movable_pages(&cma_migrate_pages);
-	}
-
-	return 0;
-}
-
 static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
-		unsigned long entries, unsigned long dev_hpa,
-		struct mm_iommu_table_group_mem_t **pmem)
+			      unsigned long entries, unsigned long dev_hpa,
+			      struct mm_iommu_table_group_mem_t **pmem)
 {
 	struct mm_iommu_table_group_mem_t *mem;
-	long i, j, ret = 0, locked_entries = 0;
+	long i, ret, locked_entries = 0;
 	unsigned int pageshift;
-	unsigned long flags;
-	unsigned long cur_ua;
-	struct page *page = NULL;
 
 	mutex_lock(&mem_list_mutex);
 
@@ -187,62 +147,43 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
 		goto unlock_exit;
 	}
 
+	down_read(&mm->mmap_sem);
+	ret = get_user_pages_longterm(ua, entries, FOLL_WRITE, mem->hpages, NULL);
+	up_read(&mm->mmap_sem);
+	if (ret != entries) {
+		/* free the reference taken */
+		for (i = 0; i < ret; i++)
+			put_page(mem->hpages[i]);
+
+		vfree(mem->hpas);
+		kfree(mem);
+		ret = -EFAULT;
+		goto unlock_exit;
+	}
+
+	pageshift = PAGE_SHIFT;
 	for (i = 0; i < entries; ++i) {
-		cur_ua = ua + (i << PAGE_SHIFT);
-		if (1 != get_user_pages_fast(cur_ua,
-					1/* pages */, 1/* iswrite */, &page)) {
-			ret = -EFAULT;
-			for (j = 0; j < i; ++j)
-				put_page(pfn_to_page(mem->hpas[j] >>
-						PAGE_SHIFT));
-			vfree(mem->hpas);
-			kfree(mem);
-			goto unlock_exit;
-		}
+		struct page *page = mem->hpages[i];
+
 		/*
-		 * If we get a page from the CMA zone, since we are going to
-		 * be pinning these entries, we might as well move them out
-		 * of the CMA zone if possible. NOTE: faulting in + migration
-		 * can be expensive. Batching can be considered later
+		 * Allow to use larger than 64k IOMMU pages. Only do that
+		 * if we are backed by hugetlb.
 		 */
-		if (is_migrate_cma_page(page)) {
-			if (mm_iommu_move_page_from_cma(page))
-				goto populate;
-			if (1 != get_user_pages_fast(cur_ua,
-						1/* pages */, 1/* iswrite */,
-						&page)) {
-				ret = -EFAULT;
-				for (j = 0; j < i; ++j)
-					put_page(pfn_to_page(mem->hpas[j] >>
-								PAGE_SHIFT));
-				vfree(mem->hpas);
-				kfree(mem);
-				goto unlock_exit;
-			}
-		}
-populate:
-		pageshift = PAGE_SHIFT;
-		if (mem->pageshift > PAGE_SHIFT && PageCompound(page)) {
-			pte_t *pte;
+		if ((mem->pageshift > PAGE_SHIFT) && PageHuge(page)) {
 			struct page *head = compound_head(page);
-			unsigned int compshift = compound_order(head);
-			unsigned int pteshift;
-
-			local_irq_save(flags); /* disables as well */
-			pte = find_linux_pte(mm->pgd, cur_ua, NULL, &pteshift);
-
-			/* Double check it is still the same pinned page */
-			if (pte && pte_page(*pte) == head &&
-			    pteshift == compshift + PAGE_SHIFT)
-				pageshift = max_t(unsigned int, pteshift,
-						PAGE_SHIFT);
-			local_irq_restore(flags);
+
+			pageshift = compound_order(head) + PAGE_SHIFT;
 		}
 		mem->pageshift = min(mem->pageshift, pageshift);
+		/*
+		 * We don't need struct page reference any more, switch
+		 * to physical address.
+		 */
 		mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT;
 	}
 
 good_exit:
+	ret = 0;
 	atomic64_set(&mem->mapped, 1);
 	mem->used = 1;
 	mem->ua = ua;
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 87f0dd0042957..df1e11ebbabbf 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -84,7 +84,7 @@ static void __init setup_node_to_cpumask_map(void)
 		alloc_bootmem_cpumask_var(&node_to_cpumask_map[node]);
 
 	/* cpumask_of_node() will now work */
-	dbg("Node to cpumask map for %d nodes\n", nr_node_ids);
+	dbg("Node to cpumask map for %u nodes\n", nr_node_ids);
 }
 
 static int __init fake_numa_create_new_node(unsigned long end_pfn,
@@ -215,7 +215,7 @@ static void initialize_distance_lookup_table(int nid,
  */
 static int associativity_to_nid(const __be32 *associativity)
 {
-	int nid = -1;
+	int nid = NUMA_NO_NODE;
 
 	if (min_common_depth == -1)
 		goto out;
@@ -225,7 +225,7 @@ static int associativity_to_nid(const __be32 *associativity)
 
 	/* POWER4 LPAR uses 0xffff as invalid node */
 	if (nid == 0xffff || nid >= MAX_NUMNODES)
-		nid = -1;
+		nid = NUMA_NO_NODE;
 
 	if (nid > 0 &&
 		of_read_number(associativity, 1) >= distance_ref_points_depth) {
@@ -244,7 +244,7 @@ out:
  */
 static int of_node_to_nid_single(struct device_node *device)
 {
-	int nid = -1;
+	int nid = NUMA_NO_NODE;
 	const __be32 *tmp;
 
 	tmp = of_get_associativity(device);
@@ -256,7 +256,7 @@ static int of_node_to_nid_single(struct device_node *device)
 /* Walk the device tree upwards, looking for an associativity id */
 int of_node_to_nid(struct device_node *device)
 {
-	int nid = -1;
+	int nid = NUMA_NO_NODE;
 
 	of_node_get(device);
 	while (device) {
@@ -454,7 +454,7 @@ static int of_drconf_to_nid_single(struct drmem_lmb *lmb)
  */
 static int numa_setup_cpu(unsigned long lcpu)
 {
-	int nid = -1;
+	int nid = NUMA_NO_NODE;
 	struct device_node *cpu;
 
 	/*
@@ -930,7 +930,7 @@ static int hot_add_drconf_scn_to_nid(unsigned long scn_addr)
 {
 	struct drmem_lmb *lmb;
 	unsigned long lmb_size;
-	int nid = -1;
+	int nid = NUMA_NO_NODE;
 
 	lmb_size = drmem_lmb_size();
 
@@ -960,7 +960,7 @@ static int hot_add_drconf_scn_to_nid(unsigned long scn_addr)
 static int hot_add_node_scn_to_nid(unsigned long scn_addr)
 {
 	struct device_node *memory;
-	int nid = -1;
+	int nid = NUMA_NO_NODE;
 
 	for_each_node_by_type(memory, "memory") {
 		unsigned long start, size;
diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c
index ecd31569a120a..e7da590c7a786 100644
--- a/arch/powerpc/mm/pgtable-book3s64.c
+++ b/arch/powerpc/mm/pgtable-book3s64.c
@@ -401,6 +401,31 @@ void arch_report_meminfo(struct seq_file *m)
 }
 #endif /* CONFIG_PROC_FS */
 
+pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr,
+			     pte_t *ptep)
+{
+	unsigned long pte_val;
+
+	/*
+	 * Clear the _PAGE_PRESENT so that no hardware parallel update is
+	 * possible. Also keep the pte_present true so that we don't take
+	 * wrong fault.
+	 */
+	pte_val = pte_update(vma->vm_mm, addr, ptep, _PAGE_PRESENT, _PAGE_INVALID, 0);
+
+	return __pte(pte_val);
+
+}
+
+void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
+			     pte_t *ptep, pte_t old_pte, pte_t pte)
+{
+	if (radix_enabled())
+		return radix__ptep_modify_prot_commit(vma, addr,
+						      ptep, old_pte, pte);
+	set_pte_at(vma->vm_mm, addr, ptep, pte);
+}
+
 /*
  * For hash translation mode, we use the deposited table to store hash slot
  * information and they are stored at PTRS_PER_PMD offset from related pmd
diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c
index 931156069a81b..dced3cd241c29 100644
--- a/arch/powerpc/mm/pgtable-radix.c
+++ b/arch/powerpc/mm/pgtable-radix.c
@@ -1063,3 +1063,21 @@ void radix__ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep,
 	}
 	/* See ptesync comment in radix__set_pte_at */
 }
+
+void radix__ptep_modify_prot_commit(struct vm_area_struct *vma,
+				    unsigned long addr, pte_t *ptep,
+				    pte_t old_pte, pte_t pte)
+{
+	struct mm_struct *mm = vma->vm_mm;
+
+	/*
+	 * To avoid NMMU hang while relaxing access we need to flush the tlb before
+	 * we set the new value. We need to do this only for radix, because hash
+	 * translation does flush when updating the linux pte.
+	 */
+	if (is_pte_rw_upgrade(pte_val(old_pte), pte_val(pte)) &&
+	    (atomic_read(&mm->context.copros) > 0))
+		radix__flush_tlb_page(vma, addr);
+
+	set_pte_at(mm, addr, ptep, pte);
+}
diff --git a/arch/powerpc/platforms/powernv/memtrace.c b/arch/powerpc/platforms/powernv/memtrace.c
index 84d038ed3882a..248a38ad25c79 100644
--- a/arch/powerpc/platforms/powernv/memtrace.c
+++ b/arch/powerpc/platforms/powernv/memtrace.c
@@ -20,6 +20,7 @@
 #include <linux/slab.h>
 #include <linux/memory.h>
 #include <linux/memory_hotplug.h>
+#include <linux/numa.h>
 #include <asm/machdep.h>
 #include <asm/debugfs.h>
 
@@ -223,7 +224,7 @@ static int memtrace_online(void)
 		ent = &memtrace_array[i];
 
 		/* We have onlined this chunk previously */
-		if (ent->nid == -1)
+		if (ent->nid == NUMA_NO_NODE)
 			continue;
 
 		/* Remove from io mappings */
@@ -257,7 +258,7 @@ static int memtrace_online(void)
 		 */
 		debugfs_remove_recursive(ent->dir);
 		pr_info("Added trace memory back to node %d\n", ent->nid);
-		ent->size = ent->start = ent->nid = -1;
+		ent->size = ent->start = ent->nid = NUMA_NO_NODE;
 	}
 	if (ret)
 		return ret;
diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c
index 582cb153eb248..0cd044122234e 100644
--- a/arch/riscv/kernel/vdso.c
+++ b/arch/riscv/kernel/vdso.c
@@ -54,7 +54,6 @@ static int __init vdso_init(void)
 		struct page *pg;
 
 		pg = virt_to_page(vdso_start + (i << PAGE_SHIFT));
-		ClearPageReserved(pg);
 		vdso_pagelist[i] = pg;
 	}
 	vdso_pagelist[i] = virt_to_page(vdso_data);
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 063732414dfbb..76dc344edb8cf 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -1069,8 +1069,9 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
 }
 
 #define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
-pte_t ptep_modify_prot_start(struct mm_struct *, unsigned long, pte_t *);
-void ptep_modify_prot_commit(struct mm_struct *, unsigned long, pte_t *, pte_t);
+pte_t ptep_modify_prot_start(struct vm_area_struct *, unsigned long, pte_t *);
+void ptep_modify_prot_commit(struct vm_area_struct *, unsigned long,
+			     pte_t *, pte_t, pte_t);
 
 #define __HAVE_ARCH_PTEP_CLEAR_FLUSH
 static inline pte_t ptep_clear_flush(struct vm_area_struct *vma,
diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c
index 4ff354887db41..e7920a68a12ec 100644
--- a/arch/s390/kernel/vdso.c
+++ b/arch/s390/kernel/vdso.c
@@ -291,7 +291,6 @@ static int __init vdso_init(void)
 	BUG_ON(vdso32_pagelist == NULL);
 	for (i = 0; i < vdso32_pages - 1; i++) {
 		struct page *pg = virt_to_page(vdso32_kbase + i*PAGE_SIZE);
-		ClearPageReserved(pg);
 		get_page(pg);
 		vdso32_pagelist[i] = pg;
 	}
@@ -309,7 +308,6 @@ static int __init vdso_init(void)
 	BUG_ON(vdso64_pagelist == NULL);
 	for (i = 0; i < vdso64_pages - 1; i++) {
 		struct page *pg = virt_to_page(vdso64_kbase + i*PAGE_SIZE);
-		ClearPageReserved(pg);
 		get_page(pg);
 		vdso64_pagelist[i] = pg;
 	}
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 689b66f29fc60..8485d6dc27549 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -301,12 +301,13 @@ pte_t ptep_xchg_lazy(struct mm_struct *mm, unsigned long addr,
 }
 EXPORT_SYMBOL(ptep_xchg_lazy);
 
-pte_t ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr,
+pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr,
 			     pte_t *ptep)
 {
 	pgste_t pgste;
 	pte_t old;
 	int nodat;
+	struct mm_struct *mm = vma->vm_mm;
 
 	preempt_disable();
 	pgste = ptep_xchg_start(mm, addr, ptep);
@@ -319,10 +320,11 @@ pte_t ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr,
 	return old;
 }
 
-void ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
-			     pte_t *ptep, pte_t pte)
+void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
+			     pte_t *ptep, pte_t old_pte, pte_t pte)
 {
 	pgste_t pgste;
+	struct mm_struct *mm = vma->vm_mm;
 
 	if (!MACHINE_HAS_NX)
 		pte_val(pte) &= ~_PAGE_NOEXEC;
diff --git a/arch/sh/kernel/syscalls/syscalltbl.sh b/arch/sh/kernel/syscalls/syscalltbl.sh
index 85d78d9309adc..904b8e6e625d2 100644
--- a/arch/sh/kernel/syscalls/syscalltbl.sh
+++ b/arch/sh/kernel/syscalls/syscalltbl.sh
@@ -13,10 +13,10 @@ emit() {
 	t_entry="$3"
 
 	while [ $t_nxt -lt $t_nr ]; do
-		printf "__SYSCALL(%s, sys_ni_syscall, )\n" "${t_nxt}"
+		printf "__SYSCALL(%s,sys_ni_syscall)\n" "${t_nxt}"
 		t_nxt=$((t_nxt+1))
 	done
-	printf "__SYSCALL(%s, %s, )\n" "${t_nxt}" "${t_entry}"
+	printf "__SYSCALL(%s,%s)\n" "${t_nxt}" "${t_entry}"
 }
 
 grep -E "^[0-9A-Fa-fXx]+[[:space:]]+${my_abis}" "$in" | sort -n | (
diff --git a/arch/sh/kernel/syscalls_32.S b/arch/sh/kernel/syscalls_32.S
index 96e9c54a07f52..bd1a9c5447673 100644
--- a/arch/sh/kernel/syscalls_32.S
+++ b/arch/sh/kernel/syscalls_32.S
@@ -10,7 +10,7 @@
 #include <linux/sys.h>
 #include <linux/linkage.h>
 
-#define __SYSCALL(nr, entry, nargs) .long entry
+#define __SYSCALL(nr, entry)	.long entry
 	.data
 ENTRY(sys_call_table)
 #include <asm/syscall_table.h>
diff --git a/arch/sparc/kernel/pci_fire.c b/arch/sparc/kernel/pci_fire.c
index be71ae0866226..0ca08d455e805 100644
--- a/arch/sparc/kernel/pci_fire.c
+++ b/arch/sparc/kernel/pci_fire.c
@@ -11,6 +11,7 @@
 #include <linux/export.h>
 #include <linux/irq.h>
 #include <linux/of_device.h>
+#include <linux/numa.h>
 
 #include <asm/prom.h>
 #include <asm/irq.h>
@@ -416,7 +417,7 @@ static int pci_fire_pbm_init(struct pci_pbm_info *pbm,
 	struct device_node *dp = op->dev.of_node;
 	int err;
 
-	pbm->numa_node = -1;
+	pbm->numa_node = NUMA_NO_NODE;
 
 	pbm->pci_ops = &sun4u_pci_ops;
 	pbm->config_space_reg_bits = 12;
diff --git a/arch/sparc/kernel/pci_schizo.c b/arch/sparc/kernel/pci_schizo.c
index 934b97c72f7cc..421aba00e6b0a 100644
--- a/arch/sparc/kernel/pci_schizo.c
+++ b/arch/sparc/kernel/pci_schizo.c
@@ -12,6 +12,7 @@
 #include <linux/export.h>
 #include <linux/interrupt.h>
 #include <linux/of_device.h>
+#include <linux/numa.h>
 
 #include <asm/iommu.h>
 #include <asm/irq.h>
@@ -1347,7 +1348,7 @@ static int schizo_pbm_init(struct pci_pbm_info *pbm,
 	pbm->next = pci_pbm_root;
 	pci_pbm_root = pbm;
 
-	pbm->numa_node = -1;
+	pbm->numa_node = NUMA_NO_NODE;
 
 	pbm->pci_ops = &sun4u_pci_ops;
 	pbm->config_space_reg_bits = 8;
diff --git a/arch/sparc/kernel/psycho_common.c b/arch/sparc/kernel/psycho_common.c
index 81aa91e5c0e6c..e90bcb6bad7fc 100644
--- a/arch/sparc/kernel/psycho_common.c
+++ b/arch/sparc/kernel/psycho_common.c
@@ -5,6 +5,7 @@
  */
 #include <linux/kernel.h>
 #include <linux/interrupt.h>
+#include <linux/numa.h>
 
 #include <asm/upa.h>
 
@@ -454,7 +455,7 @@ void psycho_pbm_init_common(struct pci_pbm_info *pbm, struct platform_device *op
 	struct device_node *dp = op->dev.of_node;
 
 	pbm->name = dp->full_name;
-	pbm->numa_node = -1;
+	pbm->numa_node = NUMA_NO_NODE;
 	pbm->chip_type = chip_type;
 	pbm->chip_version = of_getintprop_default(dp, "version#", 0);
 	pbm->chip_revision = of_getintprop_default(dp, "module-revision#", 0);
diff --git a/arch/sparc/kernel/sbus.c b/arch/sparc/kernel/sbus.c
index 41c5deb581b8d..32141e1006c4a 100644
--- a/arch/sparc/kernel/sbus.c
+++ b/arch/sparc/kernel/sbus.c
@@ -15,6 +15,7 @@
 #include <linux/interrupt.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
+#include <linux/numa.h>
 
 #include <asm/page.h>
 #include <asm/io.h>
@@ -561,7 +562,7 @@ static void __init sbus_iommu_init(struct platform_device *op)
 
 	op->dev.archdata.iommu = iommu;
 	op->dev.archdata.stc = strbuf;
-	op->dev.archdata.numa_node = -1;
+	op->dev.archdata.numa_node = NUMA_NO_NODE;
 
 	reg_base = regs + SYSIO_IOMMUREG_BASE;
 	iommu->iommu_control = reg_base + IOMMU_CONTROL;
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index b4221d3727d0a..9e6bd868ba6f1 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -976,13 +976,13 @@ static u64 __init memblock_nid_range_sun4u(u64 start, u64 end, int *nid)
 {
 	int prev_nid, new_nid;
 
-	prev_nid = -1;
+	prev_nid = NUMA_NO_NODE;
 	for ( ; start < end; start += PAGE_SIZE) {
 		for (new_nid = 0; new_nid < num_node_masks; new_nid++) {
 			struct node_mem_mask *p = &node_masks[new_nid];
 
 			if ((start & p->mask) == p->match) {
-				if (prev_nid == -1)
+				if (prev_nid == NUMA_NO_NODE)
 					prev_nid = new_nid;
 				break;
 			}
@@ -1208,7 +1208,7 @@ int of_node_to_nid(struct device_node *dp)
 	md = mdesc_grab();
 
 	count = 0;
-	nid = -1;
+	nid = NUMA_NO_NODE;
 	mdesc_for_each_node_by_name(md, grp, "group") {
 		if (!scan_arcs_for_cfg_handle(md, grp, cfg_handle)) {
 			nid = count;
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index a97f28d914d56..c25c38a05c1c9 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -422,25 +422,26 @@ static inline pgdval_t pgd_val(pgd_t pgd)
 }
 
 #define  __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
-static inline pte_t ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr,
+static inline pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr,
 					   pte_t *ptep)
 {
 	pteval_t ret;
 
-	ret = PVOP_CALL3(pteval_t, mmu.ptep_modify_prot_start, mm, addr, ptep);
+	ret = PVOP_CALL3(pteval_t, mmu.ptep_modify_prot_start, vma, addr, ptep);
 
 	return (pte_t) { .pte = ret };
 }
 
-static inline void ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
-					   pte_t *ptep, pte_t pte)
+static inline void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
+					   pte_t *ptep, pte_t old_pte, pte_t pte)
 {
+
 	if (sizeof(pteval_t) > sizeof(long))
 		/* 5 arg words */
-		pv_ops.mmu.ptep_modify_prot_commit(mm, addr, ptep, pte);
+		pv_ops.mmu.ptep_modify_prot_commit(vma, addr, ptep, pte);
 	else
 		PVOP_VCALL4(mmu.ptep_modify_prot_commit,
-			    mm, addr, ptep, pte.pte);
+			    vma, addr, ptep, pte.pte);
 }
 
 static inline void set_pte(pte_t *ptep, pte_t pte)
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 488c59686a733..2474e434a6f72 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -55,6 +55,7 @@ struct task_struct;
 struct cpumask;
 struct flush_tlb_info;
 struct mmu_gather;
+struct vm_area_struct;
 
 /*
  * Wrapper type for pointers to code which uses the non-standard
@@ -254,9 +255,9 @@ struct pv_mmu_ops {
 			   pte_t *ptep, pte_t pteval);
 	void (*set_pmd)(pmd_t *pmdp, pmd_t pmdval);
 
-	pte_t (*ptep_modify_prot_start)(struct mm_struct *mm, unsigned long addr,
+	pte_t (*ptep_modify_prot_start)(struct vm_area_struct *vma, unsigned long addr,
 					pte_t *ptep);
-	void (*ptep_modify_prot_commit)(struct mm_struct *mm, unsigned long addr,
+	void (*ptep_modify_prot_commit)(struct vm_area_struct *vma, unsigned long addr,
 					pte_t *ptep, pte_t pte);
 
 	struct paravirt_callee_save pte_val;
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index 662963681ea6c..e662f987dfa2c 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -7,6 +7,7 @@
 #include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/scatterlist.h>
+#include <linux/numa.h>
 #include <asm/io.h>
 #include <asm/pat.h>
 #include <asm/x86_init.h>
@@ -141,7 +142,7 @@ cpumask_of_pcibus(const struct pci_bus *bus)
 	int node;
 
 	node = __pcibus_to_node(bus);
-	return (node == -1) ? cpu_online_mask :
+	return (node == NUMA_NO_NODE) ? cpu_online_mask :
 			      cpumask_of_node(node);
 }
 #endif
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 5e49a0acb5eeb..62004d22524a7 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -75,7 +75,7 @@ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, un
 #endif
 
 /**
- * access_ok: - Checks if a user space pointer is valid
+ * access_ok - Checks if a user space pointer is valid
  * @addr: User space pointer to start of block to check
  * @size: Size of block to check
  *
@@ -84,12 +84,12 @@ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, un
  *
  * Checks if a pointer to a block of memory in user space is valid.
  *
- * Returns true (nonzero) if the memory block may be valid, false (zero)
- * if it is definitely invalid.
- *
  * Note that, depending on architecture, this function probably just
  * checks that the pointer is in the user space range - after calling
  * this function, memory access functions may still return -EFAULT.
+ *
+ * Return: true (nonzero) if the memory block may be valid, false (zero)
+ * if it is definitely invalid.
  */
 #define access_ok(addr, size)					\
 ({									\
@@ -134,7 +134,7 @@ extern int __get_user_bad(void);
 __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL))
 
 /**
- * get_user: - Get a simple variable from user space.
+ * get_user - Get a simple variable from user space.
  * @x:   Variable to store result.
  * @ptr: Source address, in user space.
  *
@@ -148,7 +148,7 @@ __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL))
  * @ptr must have pointer-to-simple-variable type, and the result of
  * dereferencing @ptr must be assignable to @x without a cast.
  *
- * Returns zero on success, or -EFAULT on error.
+ * Return: zero on success, or -EFAULT on error.
  * On error, the variable @x is set to zero.
  */
 /*
@@ -226,7 +226,7 @@ extern void __put_user_4(void);
 extern void __put_user_8(void);
 
 /**
- * put_user: - Write a simple value into user space.
+ * put_user - Write a simple value into user space.
  * @x:   Value to copy to user space.
  * @ptr: Destination address, in user space.
  *
@@ -240,7 +240,7 @@ extern void __put_user_8(void);
  * @ptr must have pointer-to-simple-variable type, and @x must be assignable
  * to the result of dereferencing @ptr.
  *
- * Returns zero on success, or -EFAULT on error.
+ * Return: zero on success, or -EFAULT on error.
  */
 #define put_user(x, ptr)					\
 ({								\
@@ -502,7 +502,7 @@ struct __large_struct { unsigned long buf[100]; };
 } while (0)
 
 /**
- * __get_user: - Get a simple variable from user space, with less checking.
+ * __get_user - Get a simple variable from user space, with less checking.
  * @x:   Variable to store result.
  * @ptr: Source address, in user space.
  *
@@ -519,7 +519,7 @@ struct __large_struct { unsigned long buf[100]; };
  * Caller must check the pointer with access_ok() before calling this
  * function.
  *
- * Returns zero on success, or -EFAULT on error.
+ * Return: zero on success, or -EFAULT on error.
  * On error, the variable @x is set to zero.
  */
 
@@ -527,7 +527,7 @@ struct __large_struct { unsigned long buf[100]; };
 	__get_user_nocheck((x), (ptr), sizeof(*(ptr)))
 
 /**
- * __put_user: - Write a simple value into user space, with less checking.
+ * __put_user - Write a simple value into user space, with less checking.
  * @x:   Value to copy to user space.
  * @ptr: Destination address, in user space.
  *
@@ -544,7 +544,7 @@ struct __large_struct { unsigned long buf[100]; };
  * Caller must check the pointer with access_ok() before calling this
  * function.
  *
- * Returns zero on success, or -EFAULT on error.
+ * Return: zero on success, or -EFAULT on error.
  */
 
 #define __put_user(x, ptr)						\
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index a555da0941570..1e225528f0d7f 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -27,6 +27,7 @@
 #include <linux/crash_dump.h>
 #include <linux/reboot.h>
 #include <linux/memory.h>
+#include <linux/numa.h>
 
 #include <asm/uv/uv_mmrs.h>
 #include <asm/uv/uv_hub.h>
@@ -1390,7 +1391,7 @@ static void __init build_socket_tables(void)
 	}
 
 	/* Set socket -> node values: */
-	lnid = -1;
+	lnid = NUMA_NO_NODE;
 	for_each_present_cpu(cpu) {
 		int nid = cpu_to_node(cpu);
 		int apicid, sockid;
@@ -1521,7 +1522,7 @@ static void __init uv_system_init_hub(void)
 			new_hub->pnode = 0xffff;
 
 		new_hub->numa_blade_id = uv_node_to_blade_id(nodeid);
-		new_hub->memory_nid = -1;
+		new_hub->memory_nid = NUMA_NO_NODE;
 		new_hub->nr_possible_cpus = 0;
 		new_hub->nr_online_cpus = 0;
 	}
@@ -1538,7 +1539,7 @@ static void __init uv_system_init_hub(void)
 
 		uv_cpu_info_per(cpu)->p_uv_hub_info = uv_hub_info_list(nodeid);
 		uv_cpu_info_per(cpu)->blade_cpu_id = uv_cpu_hub_info(cpu)->nr_possible_cpus++;
-		if (uv_cpu_hub_info(cpu)->memory_nid == -1)
+		if (uv_cpu_hub_info(cpu)->memory_nid == NUMA_NO_NODE)
 			uv_cpu_hub_info(cpu)->memory_nid = cpu_to_node(cpu);
 
 		/* Init memoryless node: */
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index e8796fcd7e5a5..13af08827eefc 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -171,7 +171,7 @@ void __init setup_per_cpu_areas(void)
 	unsigned long delta;
 	int rc;
 
-	pr_info("NR_CPUS:%d nr_cpumask_bits:%d nr_cpu_ids:%u nr_node_ids:%d\n",
+	pr_info("NR_CPUS:%d nr_cpumask_bits:%d nr_cpu_ids:%u nr_node_ids:%u\n",
 		NR_CPUS, nr_cpumask_bits, nr_cpu_ids, nr_node_ids);
 
 	/*
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index ccd1f2a8e5577..c91ff9f9fe8a7 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -56,6 +56,7 @@
 #include <linux/stackprotector.h>
 #include <linux/gfp.h>
 #include <linux/cpuidle.h>
+#include <linux/numa.h>
 
 #include <asm/acpi.h>
 #include <asm/desc.h>
@@ -841,7 +842,7 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
 /* reduce the number of lines printed when booting a large cpu count system */
 static void announce_cpu(int cpu, int apicid)
 {
-	static int current_node = -1;
+	static int current_node = NUMA_NO_NODE;
 	int node = early_cpu_to_node(cpu);
 	static int width, node_width;
 
diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c
index bfd94e7812fcb..7d290777246d2 100644
--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -54,13 +54,13 @@ do {									\
 } while (0)
 
 /**
- * clear_user: - Zero a block of memory in user space.
+ * clear_user - Zero a block of memory in user space.
  * @to:   Destination address, in user space.
  * @n:    Number of bytes to zero.
  *
  * Zero a block of memory in user space.
  *
- * Returns number of bytes that could not be cleared.
+ * Return: number of bytes that could not be cleared.
  * On success, this will be zero.
  */
 unsigned long
@@ -74,14 +74,14 @@ clear_user(void __user *to, unsigned long n)
 EXPORT_SYMBOL(clear_user);
 
 /**
- * __clear_user: - Zero a block of memory in user space, with less checking.
+ * __clear_user - Zero a block of memory in user space, with less checking.
  * @to:   Destination address, in user space.
  * @n:    Number of bytes to zero.
  *
  * Zero a block of memory in user space.  Caller must check
  * the specified block with access_ok() before calling this function.
  *
- * Returns number of bytes that could not be cleared.
+ * Return: number of bytes that could not be cleared.
  * On success, this will be zero.
  */
 unsigned long
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 1308f5408bf74..12c1b7a83ed7b 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -123,7 +123,7 @@ void __init setup_node_to_cpumask_map(void)
 		alloc_bootmem_cpumask_var(&node_to_cpumask_map[node]);
 
 	/* cpumask_of_node() will now work */
-	pr_debug("Node to cpumask map for %d nodes\n", nr_node_ids);
+	pr_debug("Node to cpumask map for %u nodes\n", nr_node_ids);
 }
 
 static int __init numa_add_memblk_to(int nid, u64 start, u64 end,
@@ -866,7 +866,7 @@ const struct cpumask *cpumask_of_node(int node)
 {
 	if (node >= nr_node_ids) {
 		printk(KERN_WARNING
-			"cpumask_of_node(%d): node > nr_node_ids(%d)\n",
+			"cpumask_of_node(%d): node > nr_node_ids(%u)\n",
 			node, nr_node_ids);
 		dump_stack();
 		return cpu_none_mask;
diff --git a/arch/x86/xen/mmu.h b/arch/x86/xen/mmu.h
index a7e47cf7ec6cd..6e4c6bd622033 100644
--- a/arch/x86/xen/mmu.h
+++ b/arch/x86/xen/mmu.h
@@ -17,8 +17,8 @@ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn);
 
 void set_pte_mfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags);
 
-pte_t xen_ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
-void  xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
+pte_t xen_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep);
+void  xen_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
 				  pte_t *ptep, pte_t pte);
 
 unsigned long xen_read_cr2_direct(void);
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 0f4fe206dcc20..856a85814f005 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -306,20 +306,20 @@ static void xen_set_pte_at(struct mm_struct *mm, unsigned long addr,
 	__xen_set_pte(ptep, pteval);
 }
 
-pte_t xen_ptep_modify_prot_start(struct mm_struct *mm,
+pte_t xen_ptep_modify_prot_start(struct vm_area_struct *vma,
 				 unsigned long addr, pte_t *ptep)
 {
 	/* Just return the pte as-is.  We preserve the bits on commit */
-	trace_xen_mmu_ptep_modify_prot_start(mm, addr, ptep, *ptep);
+	trace_xen_mmu_ptep_modify_prot_start(vma->vm_mm, addr, ptep, *ptep);
 	return *ptep;
 }
 
-void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
+void xen_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
 				 pte_t *ptep, pte_t pte)
 {
 	struct mmu_update u;
 
-	trace_xen_mmu_ptep_modify_prot_commit(mm, addr, ptep, pte);
+	trace_xen_mmu_ptep_modify_prot_commit(vma->vm_mm, addr, ptep, pte);
 	xen_mc_batch();
 
 	u.ptr = virt_to_machine(ptep).maddr | MMU_PT_UPDATE_PRESERVE_AD;