Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:

 - a few hotfixes

 - various misc updates

 - ocfs2 updates

 - most of MM

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (108 commits)
  mm, memory_hotplug: move movable_node to the hotplug proper
  mm, memory_hotplug: drop CONFIG_MOVABLE_NODE
  mm, memory_hotplug: drop artificial restriction on online/offline
  mm: memcontrol: account slab stats per lruvec
  mm: memcontrol: per-lruvec stats infrastructure
  mm: memcontrol: use generic mod_memcg_page_state for kmem pages
  mm: memcontrol: use the node-native slab memory counters
  mm: vmstat: move slab statistics from zone to node counters
  mm/zswap.c: delete an error message for a failed memory allocation in zswap_dstmem_prepare()
  mm/zswap.c: improve a size determination in zswap_frontswap_init()
  mm/zswap.c: delete an error message for a failed memory allocation in zswap_pool_create()
  mm/swapfile.c: sort swap entries before free
  mm/oom_kill: count global and memory cgroup oom kills
  mm: per-cgroup memory reclaim stats
  mm: kmemleak: treat vm_struct as alternative reference to vmalloc'ed objects
  mm: kmemleak: factor object reference updating out of scan_block()
  mm: kmemleak: slightly reduce the size of some structures on 64-bit architectures
  mm, mempolicy: don't check cpuset seqlock where it doesn't matter
  mm, cpuset: always use seqlock when changing task's nodemask
  mm, mempolicy: simplify rebinding mempolicies when updating cpusets
  ...

4 files changed, 54 insertions, 64 deletions

diff --git a/arch/powerpc/include/asm/book3s/64/hugetlb.h b/arch/powerpc/include/asm/book3s/64/hugetlb.h
index 6666cd366596..5c28bd6f2ae1 100644
--- a/arch/powerpc/include/asm/book3s/64/hugetlb.h
+++ b/arch/powerpc/include/asm/book3s/64/hugetlb.h
@@ -50,4 +50,14 @@ static inline pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
 	else
 		return entry;
 }
+
+#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
+static inline bool gigantic_page_supported(void)
+{
+	if (radix_enabled())
+		return true;
+	return false;
+}
+#endif
+
 #endif
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index a4f33de4008e..c41dc44472c5 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -17,6 +17,8 @@
 #include <linux/memblock.h>
 #include <linux/bootmem.h>
 #include <linux/moduleparam.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/tlb.h>
@@ -55,7 +57,7 @@ static unsigned nr_gpages;
 
 #define hugepd_none(hpd)	(hpd_val(hpd) == 0)
 
-pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
+pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz)
 {
 	/* Only called for hugetlbfs pages, hence can ignore THP */
 	return __find_linux_pte_or_hugepte(mm->pgd, addr, NULL, NULL);
@@ -617,62 +619,39 @@ void hugetlb_free_pgd_range(struct mmu_gather *tlb,
 	} while (addr = next, addr != end);
 }
 
-/*
- * We are holding mmap_sem, so a parallel huge page collapse cannot run.
- * To prevent hugepage split, disable irq.
- */
-struct page *
-follow_huge_addr(struct mm_struct *mm, unsigned long address, int write)
+struct page *follow_huge_pd(struct vm_area_struct *vma,
+			    unsigned long address, hugepd_t hpd,
+			    int flags, int pdshift)
 {
-	bool is_thp;
-	pte_t *ptep, pte;
-	unsigned shift;
-	unsigned long mask, flags;
-	struct page *page = ERR_PTR(-EINVAL);
-
-	local_irq_save(flags);
-	ptep = find_linux_pte_or_hugepte(mm->pgd, address, &is_thp, &shift);
-	if (!ptep)
-		goto no_page;
-	pte = READ_ONCE(*ptep);
-	/*
-	 * Verify it is a huge page else bail.
-	 * Transparent hugepages are handled by generic code. We can skip them
-	 * here.
-	 */
-	if (!shift || is_thp)
-		goto no_page;
-
-	if (!pte_present(pte)) {
-		page = NULL;
-		goto no_page;
+	pte_t *ptep;
+	spinlock_t *ptl;
+	struct page *page = NULL;
+	unsigned long mask;
+	int shift = hugepd_shift(hpd);
+	struct mm_struct *mm = vma->vm_mm;
+
+retry:
+	ptl = &mm->page_table_lock;
+	spin_lock(ptl);
+
+	ptep = hugepte_offset(hpd, address, pdshift);
+	if (pte_present(*ptep)) {
+		mask = (1UL << shift) - 1;
+		page = pte_page(*ptep);
+		page += ((address & mask) >> PAGE_SHIFT);
+		if (flags & FOLL_GET)
+			get_page(page);
+	} else {
+		if (is_hugetlb_entry_migration(*ptep)) {
+			spin_unlock(ptl);
+			__migration_entry_wait(mm, ptep, ptl);
+			goto retry;
+		}
 	}
-	mask = (1UL << shift) - 1;
-	page = pte_page(pte);
-	if (page)
-		page += (address & mask) / PAGE_SIZE;
-
-no_page:
-	local_irq_restore(flags);
+	spin_unlock(ptl);
 	return page;
 }
 
-struct page *
-follow_huge_pmd(struct mm_struct *mm, unsigned long address,
-		pmd_t *pmd, int write)
-{
-	BUG();
-	return NULL;
-}
-
-struct page *
-follow_huge_pud(struct mm_struct *mm, unsigned long address,
-		pud_t *pud, int write)
-{
-	BUG();
-	return NULL;
-}
-
 static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end,
 				      unsigned long sz)
 {
@@ -763,8 +742,11 @@ static int __init add_huge_page_size(unsigned long long size)
 	 * Hash: 16M and 16G
 	 */
 	if (radix_enabled()) {
-		if (mmu_psize != MMU_PAGE_2M)
-			return -EINVAL;
+		if (mmu_psize != MMU_PAGE_2M) {
+			if (cpu_has_feature(CPU_FTR_POWER9_DD1) ||
+			    (mmu_psize != MMU_PAGE_1G))
+				return -EINVAL;
+		}
 	} else {
 		if (mmu_psize != MMU_PAGE_16M && mmu_psize != MMU_PAGE_16G)
 			return -EINVAL;
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 9ee536ec0739..de5a90e1ceaa 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -126,18 +126,14 @@ int __weak remove_section_mapping(unsigned long start, unsigned long end)
 	return -ENODEV;
 }
 
-int arch_add_memory(int nid, u64 start, u64 size, bool for_device)
+int arch_add_memory(int nid, u64 start, u64 size, bool want_memblock)
 {
-	struct pglist_data *pgdata;
-	struct zone *zone;
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 	int rc;
 
 	resize_hpt_for_hotplug(memblock_phys_mem_size());
 
-	pgdata = NODE_DATA(nid);
-
 	start = (unsigned long)__va(start);
 	rc = create_section_mapping(start, start + size);
 	if (rc) {
@@ -147,11 +143,7 @@ int arch_add_memory(int nid, u64 start, u64 size, bool for_device)
 		return -EFAULT;
 	}
 
-	/* this should work for most non-highmem platforms */
-	zone = pgdata->node_zones +
-		zone_for_memory(nid, start, size, 0, for_device);
-
-	return __add_pages(nid, zone, start_pfn, nr_pages);
+	return __add_pages(nid, start_pfn, nr_pages, want_memblock);
 }
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 684e886eaae4..2f629e0551e9 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -344,12 +344,18 @@ config PPC_STD_MMU_64
 config PPC_RADIX_MMU
 	bool "Radix MMU Support"
 	depends on PPC_BOOK3S_64
+	select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA
 	default y
 	help
 	  Enable support for the Power ISA 3.0 Radix style MMU. Currently this
 	  is only implemented by IBM Power9 CPUs, if you don't have one of them
 	  you can probably disable this.
 
+config ARCH_ENABLE_HUGEPAGE_MIGRATION
+	def_bool y
+	depends on PPC_BOOK3S_64 && HUGETLB_PAGE && MIGRATION
+
+
 config PPC_MMU_NOHASH
 	def_bool y
 	depends on !PPC_STD_MMU