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 e6e13a85796a..5a77a40567fa 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 a4168d366127..cfbf307d6dc4 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 fb6609875455..c6a07a3b433e 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 0c656850eeea..b01ef0180a03 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 aa9c94113700..66b5d697d943 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 28cbc22d7e30..6b4a47b3adf4 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 7205a9085b4d..c38976b70069 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 ae34e3a1cef1..7a0a555b366a 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 92c376279c6d..1315da6c7aeb 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 46bff1661836..7a969f4c3534 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 8a965784340c..f9c36750c6a4 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 b86a2e21693b..227c04fe60d2 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 5b0177733994..66c1e4f88d65 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 d8c8d7c9df15..868fcaf56f6b 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 7d1a3d1543fc..5ab134eeed20 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 aee4fcc24990..77fc21278fa2 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 913bfca09c4f..b8480127793d 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 88e4f69a09e5..4538e8ddde80 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 7725a9714736..a31b6234fcd7 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 2e6a8f9345d3..367ce3a4a503 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 2486bee0f93e..11d9ea28a816 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 a712a650a8b6..e7a9c4f6bfca 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;
 	}