Merge branch 'akpm' (patches from Andrew)

Merge updates from Andrew Morton:

 - a few hot fixes

 - ocfs2 updates

 - almost all of -mm (slab-generic, slab, slub, kmemleak, kasan,
   cleanups, debug, pagecache, memcg, gup, pagemap, memory-hotplug,
   sparsemem, vmalloc, initialization, z3fold, compaction, mempolicy,
   oom-kill, hugetlb, migration, thp, mmap, madvise, shmem, zswap,
   zsmalloc)

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (132 commits)
  mm/zsmalloc.c: fix a -Wunused-function warning
  zswap: do not map same object twice
  zswap: use movable memory if zpool support allocate movable memory
  zpool: add malloc_support_movable to zpool_driver
  shmem: fix obsolete comment in shmem_getpage_gfp()
  mm/madvise: reduce code duplication in error handling paths
  mm: mmap: increase sockets maximum memory size pgoff for 32bits
  mm/mmap.c: refine find_vma_prev() with rb_last()
  riscv: make mmap allocation top-down by default
  mips: use generic mmap top-down layout and brk randomization
  mips: replace arch specific way to determine 32bit task with generic version
  mips: adjust brk randomization offset to fit generic version
  mips: use STACK_TOP when computing mmap base address
  mips: properly account for stack randomization and stack guard gap
  arm: use generic mmap top-down layout and brk randomization
  arm: use STACK_TOP when computing mmap base address
  arm: properly account for stack randomization and stack guard gap
  arm64, mm: make randomization selected by generic topdown mmap layout
  arm64, mm: move generic mmap layout functions to mm
  arm64: consider stack randomization for mmap base only when necessary
  ...

12 files changed, 58 insertions, 101 deletions

diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 20c39d1bcef8..6bea4f3f8040 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -100,26 +100,9 @@ unsigned long __weak memory_block_size_bytes(void)
 }
 EXPORT_SYMBOL_GPL(memory_block_size_bytes);
 
-static unsigned long get_memory_block_size(void)
-{
-	unsigned long block_sz;
-
-	block_sz = memory_block_size_bytes();
-
-	/* Validate blk_sz is a power of 2 and not less than section size */
-	if ((block_sz & (block_sz - 1)) || (block_sz < MIN_MEMORY_BLOCK_SIZE)) {
-		WARN_ON(1);
-		block_sz = MIN_MEMORY_BLOCK_SIZE;
-	}
-
-	return block_sz;
-}
-
 /*
- * use this as the physical section index that this memsection
- * uses.
+ * Show the first physical section index (number) of this memory block.
  */
-
 static ssize_t phys_index_show(struct device *dev,
 			       struct device_attribute *attr, char *buf)
 {
@@ -131,7 +114,10 @@ static ssize_t phys_index_show(struct device *dev,
 }
 
 /*
- * Show whether the section of memory is likely to be hot-removable
+ * Show whether the memory block is likely to be offlineable (or is already
+ * offline). Once offline, the memory block could be removed. The return
+ * value does, however, not indicate that there is a way to remove the
+ * memory block.
  */
 static ssize_t removable_show(struct device *dev, struct device_attribute *attr,
 			      char *buf)
@@ -455,12 +441,12 @@ static DEVICE_ATTR_RO(phys_device);
 static DEVICE_ATTR_RO(removable);
 
 /*
- * Block size attribute stuff
+ * Show the memory block size (shared by all memory blocks).
  */
 static ssize_t block_size_bytes_show(struct device *dev,
 				     struct device_attribute *attr, char *buf)
 {
-	return sprintf(buf, "%lx\n", get_memory_block_size());
+	return sprintf(buf, "%lx\n", memory_block_size_bytes());
 }
 
 static DEVICE_ATTR_RO(block_size_bytes);
@@ -670,10 +656,10 @@ static int init_memory_block(struct memory_block **memory,
 		return -ENOMEM;
 
 	mem->start_section_nr = block_id * sections_per_block;
-	mem->end_section_nr = mem->start_section_nr + sections_per_block - 1;
 	mem->state = state;
 	start_pfn = section_nr_to_pfn(mem->start_section_nr);
 	mem->phys_device = arch_get_memory_phys_device(start_pfn);
+	mem->nid = NUMA_NO_NODE;
 
 	ret = register_memory(mem);
 
@@ -810,19 +796,22 @@ static const struct attribute_group *memory_root_attr_groups[] = {
 /*
  * Initialize the sysfs support for memory devices...
  */
-int __init memory_dev_init(void)
+void __init memory_dev_init(void)
 {
 	int ret;
 	int err;
 	unsigned long block_sz, nr;
 
+	/* Validate the configured memory block size */
+	block_sz = memory_block_size_bytes();
+	if (!is_power_of_2(block_sz) || block_sz < MIN_MEMORY_BLOCK_SIZE)
+		panic("Memory block size not suitable: 0x%lx\n", block_sz);
+	sections_per_block = block_sz / MIN_MEMORY_BLOCK_SIZE;
+
 	ret = subsys_system_register(&memory_subsys, memory_root_attr_groups);
 	if (ret)
 		goto out;
 
-	block_sz = get_memory_block_size();
-	sections_per_block = block_sz / MIN_MEMORY_BLOCK_SIZE;
-
 	/*
 	 * Create entries for memory sections that were found
 	 * during boot and have been initialized
@@ -838,8 +827,7 @@ int __init memory_dev_init(void)
 
 out:
 	if (ret)
-		printk(KERN_ERR "%s() failed: %d\n", __func__, ret);
-	return ret;
+		panic("%s() failed: %d\n", __func__, ret);
 }
 
 /**
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 75b7e6f6535b..296546ffed6c 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -427,6 +427,8 @@ static ssize_t node_read_meminfo(struct device *dev,
 		       "Node %d AnonHugePages:  %8lu kB\n"
 		       "Node %d ShmemHugePages: %8lu kB\n"
 		       "Node %d ShmemPmdMapped: %8lu kB\n"
+		       "Node %d FileHugePages: %8lu kB\n"
+		       "Node %d FilePmdMapped: %8lu kB\n"
 #endif
 			,
 		       nid, K(node_page_state(pgdat, NR_FILE_DIRTY)),
@@ -452,6 +454,10 @@ static ssize_t node_read_meminfo(struct device *dev,
 		       nid, K(node_page_state(pgdat, NR_SHMEM_THPS) *
 				       HPAGE_PMD_NR),
 		       nid, K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED) *
+				       HPAGE_PMD_NR),
+		       nid, K(node_page_state(pgdat, NR_FILE_THPS) *
+				       HPAGE_PMD_NR),
+		       nid, K(node_page_state(pgdat, NR_FILE_PMDMAPPED) *
 				       HPAGE_PMD_NR)
 #endif
 		       );
@@ -756,15 +762,13 @@ static int __ref get_nid_for_pfn(unsigned long pfn)
 static int register_mem_sect_under_node(struct memory_block *mem_blk,
 					 void *arg)
 {
+	unsigned long memory_block_pfns = memory_block_size_bytes() / PAGE_SIZE;
+	unsigned long start_pfn = section_nr_to_pfn(mem_blk->start_section_nr);
+	unsigned long end_pfn = start_pfn + memory_block_pfns - 1;
 	int ret, nid = *(int *)arg;
-	unsigned long pfn, sect_start_pfn, sect_end_pfn;
+	unsigned long pfn;
 
-	mem_blk->nid = nid;
-
-	sect_start_pfn = section_nr_to_pfn(mem_blk->start_section_nr);
-	sect_end_pfn = section_nr_to_pfn(mem_blk->end_section_nr);
-	sect_end_pfn += PAGES_PER_SECTION - 1;
-	for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) {
+	for (pfn = start_pfn; pfn <= end_pfn; pfn++) {
 		int page_nid;
 
 		/*
@@ -789,6 +793,13 @@ static int register_mem_sect_under_node(struct memory_block *mem_blk,
 			if (page_nid != nid)
 				continue;
 		}
+
+		/*
+		 * If this memory block spans multiple nodes, we only indicate
+		 * the last processed node.
+		 */
+		mem_blk->nid = nid;
+
 		ret = sysfs_create_link_nowarn(&node_devices[nid]->dev.kobj,
 					&mem_blk->dev.kobj,
 					kobject_name(&mem_blk->dev.kobj));
@@ -804,32 +815,18 @@ static int register_mem_sect_under_node(struct memory_block *mem_blk,
 }
 
 /*
- * Unregister memory block device under all nodes that it spans.
- * Has to be called with mem_sysfs_mutex held (due to unlinked_nodes).
+ * Unregister a memory block device under the node it spans. Memory blocks
+ * with multiple nodes cannot be offlined and therefore also never be removed.
  */
 void unregister_memory_block_under_nodes(struct memory_block *mem_blk)
 {
-	unsigned long pfn, sect_start_pfn, sect_end_pfn;
-	static nodemask_t unlinked_nodes;
-
-	nodes_clear(unlinked_nodes);
-	sect_start_pfn = section_nr_to_pfn(mem_blk->start_section_nr);
-	sect_end_pfn = section_nr_to_pfn(mem_blk->end_section_nr);
-	for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) {
-		int nid;
+	if (mem_blk->nid == NUMA_NO_NODE)
+		return;
 
-		nid = get_nid_for_pfn(pfn);
-		if (nid < 0)
-			continue;
-		if (!node_online(nid))
-			continue;
-		if (node_test_and_set(nid, unlinked_nodes))
-			continue;
-		sysfs_remove_link(&node_devices[nid]->dev.kobj,
-			 kobject_name(&mem_blk->dev.kobj));
-		sysfs_remove_link(&mem_blk->dev.kobj,
-			 kobject_name(&node_devices[nid]->dev.kobj));
-	}
+	sysfs_remove_link(&node_devices[mem_blk->nid]->dev.kobj,
+			  kobject_name(&mem_blk->dev.kobj));
+	sysfs_remove_link(&mem_blk->dev.kobj,
+			  kobject_name(&node_devices[mem_blk->nid]->dev.kobj));
 }
 
 int link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn)
diff --git a/drivers/crypto/chelsio/chtls/chtls_io.c b/drivers/crypto/chelsio/chtls/chtls_io.c
index c70cb5f272cf..0891ab829b1b 100644
--- a/drivers/crypto/chelsio/chtls/chtls_io.c
+++ b/drivers/crypto/chelsio/chtls/chtls_io.c
@@ -1078,7 +1078,7 @@ new_buf:
 			bool merge;
 
 			if (page)
-				pg_size <<= compound_order(page);
+				pg_size = page_size(page);
 			if (off < pg_size &&
 			    skb_can_coalesce(skb, i, page, off)) {
 				merge = 1;
@@ -1105,8 +1105,7 @@ new_buf:
 							   __GFP_NORETRY,
 							   order);
 					if (page)
-						pg_size <<=
-							compound_order(page);
+						pg_size <<= order;
 				}
 				if (!page) {
 					page = alloc_page(gfp);
diff --git a/drivers/gpu/drm/via/via_dmablit.c b/drivers/gpu/drm/via/via_dmablit.c
index feaa538026a0..3db000aacd26 100644
--- a/drivers/gpu/drm/via/via_dmablit.c
+++ b/drivers/gpu/drm/via/via_dmablit.c
@@ -174,7 +174,6 @@ via_map_blit_for_device(struct pci_dev *pdev,
 static void
 via_free_sg_info(struct pci_dev *pdev, drm_via_sg_info_t *vsg)
 {
-	struct page *page;
 	int i;
 
 	switch (vsg->state) {
@@ -189,13 +188,8 @@ via_free_sg_info(struct pci_dev *pdev, drm_via_sg_info_t *vsg)
 		kfree(vsg->desc_pages);
 		/* fall through */
 	case dr_via_pages_locked:
-		for (i = 0; i < vsg->num_pages; ++i) {
-			if (NULL != (page = vsg->pages[i])) {
-				if (!PageReserved(page) && (DMA_FROM_DEVICE == vsg->direction))
-					SetPageDirty(page);
-				put_page(page);
-			}
-		}
+		put_user_pages_dirty_lock(vsg->pages, vsg->num_pages,
+					  (vsg->direction == DMA_FROM_DEVICE));
 		/* fall through */
 	case dr_via_pages_alloc:
 		vfree(vsg->pages);
diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index 41f9e268e3fb..24244a2f68cc 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -54,10 +54,7 @@ static void __ib_umem_release(struct ib_device *dev, struct ib_umem *umem, int d
 
 	for_each_sg_page(umem->sg_head.sgl, &sg_iter, umem->sg_nents, 0) {
 		page = sg_page_iter_page(&sg_iter);
-		if (umem->writable && dirty)
-			put_user_pages_dirty_lock(&page, 1);
-		else
-			put_user_page(page);
+		put_user_pages_dirty_lock(&page, 1, umem->writable && dirty);
 	}
 
 	sg_free_table(&umem->sg_head);
diff --git a/drivers/infiniband/hw/hfi1/user_pages.c b/drivers/infiniband/hw/hfi1/user_pages.c
index b89a9b9aef7a..469acb961fbd 100644
--- a/drivers/infiniband/hw/hfi1/user_pages.c
+++ b/drivers/infiniband/hw/hfi1/user_pages.c
@@ -118,10 +118,7 @@ int hfi1_acquire_user_pages(struct mm_struct *mm, unsigned long vaddr, size_t np
 void hfi1_release_user_pages(struct mm_struct *mm, struct page **p,
 			     size_t npages, bool dirty)
 {
-	if (dirty)
-		put_user_pages_dirty_lock(p, npages);
-	else
-		put_user_pages(p, npages);
+	put_user_pages_dirty_lock(p, npages, dirty);
 
 	if (mm) { /* during close after signal, mm can be NULL */
 		atomic64_sub(npages, &mm->pinned_vm);
diff --git a/drivers/infiniband/hw/qib/qib_user_pages.c b/drivers/infiniband/hw/qib/qib_user_pages.c
index bfbfbb7e0ff4..6bf764e41891 100644
--- a/drivers/infiniband/hw/qib/qib_user_pages.c
+++ b/drivers/infiniband/hw/qib/qib_user_pages.c
@@ -40,10 +40,7 @@
 static void __qib_release_user_pages(struct page **p, size_t num_pages,
 				     int dirty)
 {
-	if (dirty)
-		put_user_pages_dirty_lock(p, num_pages);
-	else
-		put_user_pages(p, num_pages);
+	put_user_pages_dirty_lock(p, num_pages, dirty);
 }
 
 /**
diff --git a/drivers/infiniband/hw/usnic/usnic_uiom.c b/drivers/infiniband/hw/usnic/usnic_uiom.c
index 0b0237d41613..62e6ffa9ad78 100644
--- a/drivers/infiniband/hw/usnic/usnic_uiom.c
+++ b/drivers/infiniband/hw/usnic/usnic_uiom.c
@@ -75,10 +75,7 @@ static void usnic_uiom_put_pages(struct list_head *chunk_list, int dirty)
 		for_each_sg(chunk->page_list, sg, chunk->nents, i) {
 			page = sg_page(sg);
 			pa = sg_phys(sg);
-			if (dirty)
-				put_user_pages_dirty_lock(&page, 1);
-			else
-				put_user_page(page);
+			put_user_pages_dirty_lock(&page, 1, dirty);
 			usnic_dbg("pa: %pa\n", &pa);
 		}
 		kfree(chunk);
diff --git a/drivers/infiniband/sw/siw/siw_mem.c b/drivers/infiniband/sw/siw/siw_mem.c
index 87a56039f0ef..e99983f07663 100644
--- a/drivers/infiniband/sw/siw/siw_mem.c
+++ b/drivers/infiniband/sw/siw/siw_mem.c
@@ -63,15 +63,7 @@ struct siw_mem *siw_mem_id2obj(struct siw_device *sdev, int stag_index)
 static void siw_free_plist(struct siw_page_chunk *chunk, int num_pages,
 			   bool dirty)
 {
-	struct page **p = chunk->plist;
-
-	while (num_pages--) {
-		if (!PageDirty(*p) && dirty)
-			put_user_pages_dirty_lock(p, 1);
-		else
-			put_user_page(*p);
-		p++;
-	}
+	put_user_pages_dirty_lock(chunk->plist, num_pages, dirty);
 }
 
 void siw_umem_release(struct siw_umem *umem, bool dirty)
diff --git a/drivers/staging/android/ion/ion_system_heap.c b/drivers/staging/android/ion/ion_system_heap.c
index aa8d8425be25..b83a1d16bd89 100644
--- a/drivers/staging/android/ion/ion_system_heap.c
+++ b/drivers/staging/android/ion/ion_system_heap.c
@@ -120,7 +120,7 @@ static int ion_system_heap_allocate(struct ion_heap *heap,
 		if (!page)
 			goto free_pages;
 		list_add_tail(&page->lru, &pages);
-		size_remaining -= PAGE_SIZE << compound_order(page);
+		size_remaining -= page_size(page);
 		max_order = compound_order(page);
 		i++;
 	}
@@ -133,7 +133,7 @@ static int ion_system_heap_allocate(struct ion_heap *heap,
 
 	sg = table->sgl;
 	list_for_each_entry_safe(page, tmp_page, &pages, lru) {
-		sg_set_page(sg, page, PAGE_SIZE << compound_order(page), 0);
+		sg_set_page(sg, page, page_size(page), 0);
 		sg = sg_next(sg);
 		list_del(&page->lru);
 	}
diff --git a/drivers/target/tcm_fc/tfc_io.c b/drivers/target/tcm_fc/tfc_io.c
index a254792d882c..1354a157e9af 100644
--- a/drivers/target/tcm_fc/tfc_io.c
+++ b/drivers/target/tcm_fc/tfc_io.c
@@ -136,8 +136,7 @@ int ft_queue_data_in(struct se_cmd *se_cmd)
 					   page, off_in_page, tlen);
 			fr_len(fp) += tlen;
 			fp_skb(fp)->data_len += tlen;
-			fp_skb(fp)->truesize +=
-					PAGE_SIZE << compound_order(page);
+			fp_skb(fp)->truesize += page_size(page);
 		} else {
 			BUG_ON(!page);
 			from = kmap_atomic(page + (mem_off >> PAGE_SHIFT));
diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index 3b18fa4d090a..26cef65b41e7 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -176,13 +176,13 @@ put_exit:
 }
 
 static bool tce_page_is_contained(struct mm_struct *mm, unsigned long hpa,
-		unsigned int page_shift)
+		unsigned int it_page_shift)
 {
 	struct page *page;
 	unsigned long size = 0;
 
-	if (mm_iommu_is_devmem(mm, hpa, page_shift, &size))
-		return size == (1UL << page_shift);
+	if (mm_iommu_is_devmem(mm, hpa, it_page_shift, &size))
+		return size == (1UL << it_page_shift);
 
 	page = pfn_to_page(hpa >> PAGE_SHIFT);
 	/*
@@ -190,7 +190,7 @@ static bool tce_page_is_contained(struct mm_struct *mm, unsigned long hpa,
 	 * a page we just found. Otherwise the hardware can get access to
 	 * a bigger memory chunk that it should.
 	 */
-	return (PAGE_SHIFT + compound_order(compound_head(page))) >= page_shift;
+	return page_shift(compound_head(page)) >= it_page_shift;
 }
 
 static inline bool tce_groups_attached(struct tce_container *container)