Merge branch 'akpm' (patches from Andrew)

Merge second patch-bomb from Andrew Morton:
 "Almost all of the rest of MM.  There was an unusually large amount of
  MM material this time"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (141 commits)
  zpool: remove no-op module init/exit
  mm: zbud: constify the zbud_ops
  mm: zpool: constify the zpool_ops
  mm: swap: zswap: maybe_preload & refactoring
  zram: unify error reporting
  zsmalloc: remove null check from destroy_handle_cache()
  zsmalloc: do not take class lock in zs_shrinker_count()
  zsmalloc: use class->pages_per_zspage
  zsmalloc: consider ZS_ALMOST_FULL as migrate source
  zsmalloc: partial page ordering within a fullness_list
  zsmalloc: use shrinker to trigger auto-compaction
  zsmalloc: account the number of compacted pages
  zsmalloc/zram: introduce zs_pool_stats api
  zsmalloc: cosmetic compaction code adjustments
  zsmalloc: introduce zs_can_compact() function
  zsmalloc: always keep per-class stats
  zsmalloc: drop unused variable `nr_to_migrate'
  mm/memblock.c: fix comment in __next_mem_range()
  mm/page_alloc.c: fix type information of memoryless node
  memory-hotplug: fix comments in zone_spanned_pages_in_node() and zone_spanned_pages_in_node()
  ...

Documentation/DMA-API.txt

@@ -104,6 +104,13 @@ crossing restrictions, pass 0 for alloc; passing 4096 says memory allocated
 from this pool must not cross 4KByte boundaries.
 
 
+	void *dma_pool_zalloc(struct dma_pool *pool, gfp_t mem_flags,
+			      dma_addr_t *handle)
+
+Wraps dma_pool_alloc() and also zeroes the returned memory if the
+allocation attempt succeeded.
+
+
 	void *dma_pool_alloc(struct dma_pool *pool, gfp_t gfp_flags,
 			dma_addr_t *dma_handle);
 

Documentation/blockdev/zram.txt

@@ -144,7 +144,8 @@ mem_used_max      RW    the maximum amount memory zram have consumed to
                         store compressed data
 mem_limit         RW    the maximum amount of memory ZRAM can use to store
                         the compressed data
-num_migrated      RO    the number of objects migrated migrated by compaction
+pages_compacted   RO    the number of pages freed during compaction
+                        (available only via zram<id>/mm_stat node)
 compact           WO    trigger memory compaction
 
 WARNING

Documentation/filesystems/dax.txt

@@ -60,9 +60,10 @@ Filesystem support consists of
 - implementing the direct_IO address space operation, and calling
   dax_do_io() instead of blockdev_direct_IO() if S_DAX is set
 - implementing an mmap file operation for DAX files which sets the
-  VM_MIXEDMAP flag on the VMA, and setting the vm_ops to include handlers
-  for fault and page_mkwrite (which should probably call dax_fault() and
-  dax_mkwrite(), passing the appropriate get_block() callback)
+  VM_MIXEDMAP and VM_HUGEPAGE flags on the VMA, and setting the vm_ops to
+  include handlers for fault, pmd_fault and page_mkwrite (which should
+  probably call dax_fault(), dax_pmd_fault() and dax_mkwrite(), passing the
+  appropriate get_block() callback)
 - calling dax_truncate_page() instead of block_truncate_page() for DAX files
 - calling dax_zero_page_range() instead of zero_user() for DAX files
 - ensuring that there is sufficient locking between reads, writes,

Documentation/filesystems/proc.txt

@@ -424,6 +424,7 @@ Private_Dirty:         0 kB
 Referenced:          892 kB
 Anonymous:             0 kB
 Swap:                  0 kB
+SwapPss:               0 kB
 KernelPageSize:        4 kB
 MMUPageSize:           4 kB
 Locked:              374 kB
@@ -433,16 +434,23 @@ the first of these lines shows the same information as is displayed for the
 mapping in /proc/PID/maps.  The remaining lines show the size of the mapping
 (size), the amount of the mapping that is currently resident in RAM (RSS), the
 process' proportional share of this mapping (PSS), the number of clean and
-dirty private pages in the mapping.  Note that even a page which is part of a
-MAP_SHARED mapping, but has only a single pte mapped, i.e.  is currently used
-by only one process, is accounted as private and not as shared.  "Referenced"
-indicates the amount of memory currently marked as referenced or accessed.
+dirty private pages in the mapping.
+
+The "proportional set size" (PSS) of a process is the count of pages it has
+in memory, where each page is divided by the number of processes sharing it.
+So if a process has 1000 pages all to itself, and 1000 shared with one other
+process, its PSS will be 1500.
+Note that even a page which is part of a MAP_SHARED mapping, but has only
+a single pte mapped, i.e.  is currently used by only one process, is accounted
+as private and not as shared.
+"Referenced" indicates the amount of memory currently marked as referenced or
+accessed.
 "Anonymous" shows the amount of memory that does not belong to any file.  Even
 a mapping associated with a file may contain anonymous pages: when MAP_PRIVATE
 and a page is modified, the file page is replaced by a private anonymous copy.
 "Swap" shows how much would-be-anonymous memory is also used, but out on
 swap.
-
+"SwapPss" shows proportional swap share of this mapping.
 "VmFlags" field deserves a separate description. This member represents the kernel
 flags associated with the particular virtual memory area in two letter encoded
 manner. The codes are the following:

Documentation/sysctl/vm.txt

@@ -349,7 +349,7 @@ zone[i]'s protection[j] is calculated by following expression.
 
 (i < j):
   zone[i]->protection[j]
-  = (total sums of present_pages from zone[i+1] to zone[j] on the node)
+  = (total sums of managed_pages from zone[i+1] to zone[j] on the node)
     / lowmem_reserve_ratio[i];
 (i = j):
    (should not be protected. = 0;
@@ -360,7 +360,7 @@ The default values of lowmem_reserve_ratio[i] are
     256 (if zone[i] means DMA or DMA32 zone)
     32  (others).
 As above expression, they are reciprocal number of ratio.
-256 means 1/256. # of protection pages becomes about "0.39%" of total present
+256 means 1/256. # of protection pages becomes about "0.39%" of total managed
 pages of higher zones on the node.
 
 If you would like to protect more pages, smaller values are effective.

Documentation/sysrq.txt

@@ -75,7 +75,8 @@ On all -  write a character to /proc/sysrq-trigger.  e.g.:
 
 'e'     - Send a SIGTERM to all processes, except for init.
 
-'f'	- Will call oom_kill to kill a memory hog process.
+'f'	- Will call the oom killer to kill a memory hog process, but do not
+	  panic if nothing can be killed.
 
 'g'	- Used by kgdb (kernel debugger)
 

Documentation/vm/hugetlbpage.txt

@@ -329,7 +329,14 @@ Examples
 
 3) hugepage-mmap:  see tools/testing/selftests/vm/hugepage-mmap.c
 
-4) The libhugetlbfs (http://libhugetlbfs.sourceforge.net) library provides a
-   wide range of userspace tools to help with huge page usability, environment
-   setup, and control. Furthermore it provides useful test cases that should be
-   used when modifying code to ensure no regressions are introduced.
+4) The libhugetlbfs (https://github.com/libhugetlbfs/libhugetlbfs) library
+   provides a wide range of userspace tools to help with huge page usability,
+   environment setup, and control.
+
+Kernel development regression testing
+=====================================
+
+The most complete set of hugetlb tests are in the libhugetlbfs repository.
+If you modify any hugetlb related code, use the libhugetlbfs test suite
+to check for regressions.  In addition, if you add any new hugetlb
+functionality, please add appropriate tests to libhugetlbfs.

Documentation/vm/pagemap.txt

@@ -16,11 +16,17 @@ There are three components to pagemap:
     * Bits 0-4   swap type if swapped
     * Bits 5-54  swap offset if swapped
     * Bit  55    pte is soft-dirty (see Documentation/vm/soft-dirty.txt)
-    * Bits 56-60 zero
-    * Bit  61    page is file-page or shared-anon
+    * Bit  56    page exclusively mapped (since 4.2)
+    * Bits 57-60 zero
+    * Bit  61    page is file-page or shared-anon (since 3.5)
     * Bit  62    page swapped
     * Bit  63    page present
 
+   Since Linux 4.0 only users with the CAP_SYS_ADMIN capability can get PFNs.
+   In 4.0 and 4.1 opens by unprivileged fail with -EPERM.  Starting from
+   4.2 the PFN field is zeroed if the user does not have CAP_SYS_ADMIN.
+   Reason: information about PFNs helps in exploiting Rowhammer vulnerability.
+
    If the page is not present but in swap, then the PFN contains an
    encoding of the swap file number and the page's offset into the
    swap. Unmapped pages return a null PFN. This allows determining
@@ -159,3 +165,8 @@ Other notes:
 Reading from any of the files will return -EINVAL if you are not starting
 the read on an 8-byte boundary (e.g., if you sought an odd number of bytes
 into the file), or if the size of the read is not a multiple of 8 bytes.
+
+Before Linux 3.11 pagemap bits 55-60 were used for "page-shift" (which is
+always 12 at most architectures). Since Linux 3.11 their meaning changes
+after first clear of soft-dirty bits. Since Linux 4.2 they are used for
+flags unconditionally.

arch/arm64/kernel/setup.c

@@ -339,6 +339,67 @@ static void __init request_standard_resources(void)
 	}
 }
 
+#ifdef CONFIG_BLK_DEV_INITRD
+/*
+ * Relocate initrd if it is not completely within the linear mapping.
+ * This would be the case if mem= cuts out all or part of it.
+ */
+static void __init relocate_initrd(void)
+{
+	phys_addr_t orig_start = __virt_to_phys(initrd_start);
+	phys_addr_t orig_end = __virt_to_phys(initrd_end);
+	phys_addr_t ram_end = memblock_end_of_DRAM();
+	phys_addr_t new_start;
+	unsigned long size, to_free = 0;
+	void *dest;
+
+	if (orig_end <= ram_end)
+		return;
+
+	/*
+	 * Any of the original initrd which overlaps the linear map should
+	 * be freed after relocating.
+	 */
+	if (orig_start < ram_end)
+		to_free = ram_end - orig_start;
+
+	size = orig_end - orig_start;
+
+	/* initrd needs to be relocated completely inside linear mapping */
+	new_start = memblock_find_in_range(0, PFN_PHYS(max_pfn),
+					   size, PAGE_SIZE);
+	if (!new_start)
+		panic("Cannot relocate initrd of size %ld\n", size);
+	memblock_reserve(new_start, size);
+
+	initrd_start = __phys_to_virt(new_start);
+	initrd_end   = initrd_start + size;
+
+	pr_info("Moving initrd from [%llx-%llx] to [%llx-%llx]\n",
+		orig_start, orig_start + size - 1,
+		new_start, new_start + size - 1);
+
+	dest = (void *)initrd_start;
+
+	if (to_free) {
+		memcpy(dest, (void *)__phys_to_virt(orig_start), to_free);
+		dest += to_free;
+	}
+
+	copy_from_early_mem(dest, orig_start + to_free, size - to_free);
+
+	if (to_free) {
+		pr_info("Freeing original RAMDISK from [%llx-%llx]\n",
+			orig_start, orig_start + to_free - 1);
+		memblock_free(orig_start, to_free);
+	}
+}
+#else
+static inline void __init relocate_initrd(void)
+{
+}
+#endif
+
 u64 __cpu_logical_map[NR_CPUS] = { [0 ... NR_CPUS-1] = INVALID_HWID };
 
 void __init setup_arch(char **cmdline_p)
@@ -372,6 +433,7 @@ void __init setup_arch(char **cmdline_p)
 	acpi_boot_table_init();
 
 	paging_init();
+	relocate_initrd();
 	request_standard_resources();
 
 	early_ioremap_reset();

arch/ia64/hp/common/sba_iommu.c

@@ -1140,13 +1140,9 @@ sba_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
 
 #ifdef CONFIG_NUMA
 	{
-		int node = ioc->node;
 		struct page *page;
 
-		if (node == NUMA_NO_NODE)
-			node = numa_node_id();
-
-		page = alloc_pages_exact_node(node, flags, get_order(size));
+		page = alloc_pages_node(ioc->node, flags, get_order(size));
 		if (unlikely(!page))
 			return NULL;
 

arch/ia64/kernel/uncached.c

@@ -97,7 +97,7 @@ static int uncached_add_chunk(struct uncached_pool *uc_pool, int nid)
 
 	/* attempt to allocate a granule's worth of cached memory pages */
 
-	page = alloc_pages_exact_node(nid,
+	page = __alloc_pages_node(nid,
 				GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE,
 				IA64_GRANULE_SHIFT-PAGE_SHIFT);
 	if (!page) {

arch/ia64/sn/pci/pci_dma.c

@@ -92,7 +92,7 @@ static void *sn_dma_alloc_coherent(struct device *dev, size_t size,
 	 */
 	node = pcibus_to_node(pdev->bus);
 	if (likely(node >=0)) {
-		struct page *p = alloc_pages_exact_node(node,
+		struct page *p = __alloc_pages_node(node,
 						flags, get_order(size));
 
 		if (likely(p))

arch/powerpc/platforms/cell/ras.c

@@ -123,7 +123,7 @@ static int __init cbe_ptcal_enable_on_node(int nid, int order)
 
 	area->nid = nid;
 	area->order = order;
-	area->pages = alloc_pages_exact_node(area->nid,
+	area->pages = __alloc_pages_node(area->nid,
 						GFP_KERNEL|__GFP_THISNODE,
 						area->order);
 

arch/sparc/include/asm/pgtable_32.h

@@ -14,7 +14,7 @@
 #include <asm-generic/4level-fixup.h>
 
 #include <linux/spinlock.h>
-#include <linux/swap.h>
+#include <linux/mm_types.h>
 #include <asm/types.h>
 #include <asm/pgtsrmmu.h>
 #include <asm/vaddrs.h>

arch/x86/kernel/setup.c

@@ -317,15 +317,12 @@ static u64 __init get_ramdisk_size(void)
 	return ramdisk_size;
 }
 
-#define MAX_MAP_CHUNK	(NR_FIX_BTMAPS << PAGE_SHIFT)
 static void __init relocate_initrd(void)
 {
 	/* Assume only end is not page aligned */
 	u64 ramdisk_image = get_ramdisk_image();
 	u64 ramdisk_size  = get_ramdisk_size();
 	u64 area_size     = PAGE_ALIGN(ramdisk_size);
-	unsigned long slop, clen, mapaddr;
-	char *p, *q;
 
 	/* We need to move the initrd down into directly mapped mem */
 	relocated_ramdisk = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped),
@@ -343,25 +340,8 @@ static void __init relocate_initrd(void)
 	printk(KERN_INFO "Allocated new RAMDISK: [mem %#010llx-%#010llx]\n",
 	       relocated_ramdisk, relocated_ramdisk + ramdisk_size - 1);
 
-	q = (char *)initrd_start;
-
-	/* Copy the initrd */
-	while (ramdisk_size) {
-		slop = ramdisk_image & ~PAGE_MASK;
-		clen = ramdisk_size;
-		if (clen > MAX_MAP_CHUNK-slop)
-			clen = MAX_MAP_CHUNK-slop;
-		mapaddr = ramdisk_image & PAGE_MASK;
-		p = early_memremap(mapaddr, clen+slop);
-		memcpy(q, p+slop, clen);
-		early_memunmap(p, clen+slop);
-		q += clen;
-		ramdisk_image += clen;
-		ramdisk_size  -= clen;
-	}
+	copy_from_early_mem((void *)initrd_start, ramdisk_image, ramdisk_size);
 
-	ramdisk_image = get_ramdisk_image();
-	ramdisk_size  = get_ramdisk_size();
 	printk(KERN_INFO "Move RAMDISK from [mem %#010llx-%#010llx] to"
 		" [mem %#010llx-%#010llx]\n",
 		ramdisk_image, ramdisk_image + ramdisk_size - 1,

arch/x86/kvm/vmx.c

@@ -3150,7 +3150,7 @@ static struct vmcs *alloc_vmcs_cpu(int cpu)
 	struct page *pages;
 	struct vmcs *vmcs;
 
-	pages = alloc_pages_exact_node(node, GFP_KERNEL, vmcs_config.order);
+	pages = __alloc_pages_node(node, GFP_KERNEL, vmcs_config.order);
 	if (!pages)
 		return NULL;
 	vmcs = page_address(pages);

arch/x86/mm/numa.c

@@ -246,8 +246,10 @@ int __init numa_cleanup_meminfo(struct numa_meminfo *mi)
 		bi->start = max(bi->start, low);
 		bi->end = min(bi->end, high);
 
-		/* and there's no empty block */
-		if (bi->start >= bi->end)
+		/* and there's no empty or non-exist block */
+		if (bi->start >= bi->end ||
+		    !memblock_overlaps_region(&memblock.memory,
+			bi->start, bi->end - bi->start))
 			numa_remove_memblk_from(i--, mi);
 	}
 

drivers/block/zram/zram_drv.c

@@ -388,7 +388,6 @@ static ssize_t comp_algorithm_store(struct device *dev,
 static ssize_t compact_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t len)
 {
-	unsigned long nr_migrated;
 	struct zram *zram = dev_to_zram(dev);
 	struct zram_meta *meta;
 
@@ -399,8 +398,7 @@ static ssize_t compact_store(struct device *dev,
 	}
 
 	meta = zram->meta;
-	nr_migrated = zs_compact(meta->mem_pool);
-	atomic64_add(nr_migrated, &zram->stats.num_migrated);
+	zs_compact(meta->mem_pool);
 	up_read(&zram->init_lock);
 
 	return len;
@@ -428,26 +426,31 @@ static ssize_t mm_stat_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
 	struct zram *zram = dev_to_zram(dev);
+	struct zs_pool_stats pool_stats;
 	u64 orig_size, mem_used = 0;
 	long max_used;
 	ssize_t ret;
 
+	memset(&pool_stats, 0x00, sizeof(struct zs_pool_stats));
+
 	down_read(&zram->init_lock);
-	if (init_done(zram))
+	if (init_done(zram)) {
 		mem_used = zs_get_total_pages(zram->meta->mem_pool);
+		zs_pool_stats(zram->meta->mem_pool, &pool_stats);
+	}
 
 	orig_size = atomic64_read(&zram->stats.pages_stored);
 	max_used = atomic_long_read(&zram->stats.max_used_pages);
 
 	ret = scnprintf(buf, PAGE_SIZE,
-			"%8llu %8llu %8llu %8lu %8ld %8llu %8llu\n",
+			"%8llu %8llu %8llu %8lu %8ld %8llu %8lu\n",
 			orig_size << PAGE_SHIFT,
 			(u64)atomic64_read(&zram->stats.compr_data_size),
 			mem_used << PAGE_SHIFT,
 			zram->limit_pages << PAGE_SHIFT,
 			max_used << PAGE_SHIFT,
 			(u64)atomic64_read(&zram->stats.zero_pages),
-			(u64)atomic64_read(&zram->stats.num_migrated));
+			pool_stats.pages_compacted);
 	up_read(&zram->init_lock);
 
 	return ret;
@@ -619,7 +622,7 @@ static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
 		uncmem = user_mem;
 
 	if (!uncmem) {
-		pr_info("Unable to allocate temp memory\n");
+		pr_err("Unable to allocate temp memory\n");
 		ret = -ENOMEM;
 		goto out_cleanup;
 	}
@@ -716,7 +719,7 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
 
 	handle = zs_malloc(meta->mem_pool, clen);
 	if (!handle) {
-		pr_info("Error allocating memory for compressed page: %u, size=%zu\n",
+		pr_err("Error allocating memory for compressed page: %u, size=%zu\n",
 			index, clen);
 		ret = -ENOMEM;
 		goto out;
@@ -1036,7 +1039,7 @@ static ssize_t disksize_store(struct device *dev,
 
 	comp = zcomp_create(zram->compressor, zram->max_comp_streams);
 	if (IS_ERR(comp)) {
-		pr_info("Cannot initialise %s compressing backend\n",
+		pr_err("Cannot initialise %s compressing backend\n",
 				zram->compressor);
 		err = PTR_ERR(comp);
 		goto out_free_meta;
@@ -1214,7 +1217,7 @@ static int zram_add(void)
 	/* gendisk structure */
 	zram->disk = alloc_disk(1);
 	if (!zram->disk) {
-		pr_warn("Error allocating disk structure for device %d\n",
+		pr_err("Error allocating disk structure for device %d\n",
 			device_id);
 		ret = -ENOMEM;
 		goto out_free_queue;
@@ -1263,7 +1266,8 @@ static int zram_add(void)
 	ret = sysfs_create_group(&disk_to_dev(zram->disk)->kobj,
 				&zram_disk_attr_group);
 	if (ret < 0) {
-		pr_warn("Error creating sysfs group");
+		pr_err("Error creating sysfs group for device %d\n",
+				device_id);
 		goto out_free_disk;
 	}
 	strlcpy(zram->compressor, default_compressor, sizeof(zram->compressor));
@@ -1403,13 +1407,13 @@ static int __init zram_init(void)
 
 	ret = class_register(&zram_control_class);
 	if (ret) {
-		pr_warn("Unable to register zram-control class\n");
+		pr_err("Unable to register zram-control class\n");
 		return ret;
 	}
 
 	zram_major = register_blkdev(0, "zram");
 	if (zram_major <= 0) {
-		pr_warn("Unable to get major number\n");
+		pr_err("Unable to get major number\n");
 		class_unregister(&zram_control_class);
 		return -EBUSY;
 	}

drivers/block/zram/zram_drv.h

@@ -78,7 +78,6 @@ struct zram_stats {
 	atomic64_t compr_data_size;	/* compressed size of pages stored */
 	atomic64_t num_reads;	/* failed + successful */
 	atomic64_t num_writes;	/* --do-- */
-	atomic64_t num_migrated;	/* no. of migrated object */
 	atomic64_t failed_reads;	/* can happen when memory is too low */
 	atomic64_t failed_writes;	/* can happen when memory is too low */
 	atomic64_t invalid_io;	/* non-page-aligned I/O requests */

drivers/misc/sgi-xp/xpc_uv.c

@@ -239,7 +239,7 @@ xpc_create_gru_mq_uv(unsigned int mq_size, int cpu, char *irq_name,
 	mq->mmr_blade = uv_cpu_to_blade_id(cpu);
 
 	nid = cpu_to_node(cpu);
-	page = alloc_pages_exact_node(nid,
+	page = __alloc_pages_node(nid,
 				      GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE,
 				      pg_order);
 	if (page == NULL) {

drivers/tty/sysrq.c

@@ -353,9 +353,16 @@ static struct sysrq_key_op sysrq_term_op = {
 
 static void moom_callback(struct work_struct *ignored)
 {
+	const gfp_t gfp_mask = GFP_KERNEL;
+	struct oom_control oc = {
+		.zonelist = node_zonelist(first_memory_node, gfp_mask),
+		.nodemask = NULL,
+		.gfp_mask = gfp_mask,
+		.order = -1,
+	};
+
 	mutex_lock(&oom_lock);
-	if (!out_of_memory(node_zonelist(first_memory_node, GFP_KERNEL),
-			   GFP_KERNEL, 0, NULL, true))
+	if (!out_of_memory(&oc))
 		pr_info("OOM request ignored because killer is disabled\n");
 	mutex_unlock(&oom_lock);
 }

fs/block_dev.c

@@ -28,6 +28,7 @@
 #include <linux/namei.h>
 #include <linux/log2.h>
 #include <linux/cleancache.h>
+#include <linux/dax.h>
 #include <asm/uaccess.h>
 #include "internal.h"
 

fs/dax.c

@@ -283,7 +283,6 @@ static int copy_user_bh(struct page *to, struct buffer_head *bh,
 static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh,
 			struct vm_area_struct *vma, struct vm_fault *vmf)
 {
-	struct address_space *mapping = inode->i_mapping;
 	sector_t sector = bh->b_blocknr << (inode->i_blkbits - 9);
 	unsigned long vaddr = (unsigned long)vmf->virtual_address;
 	void __pmem *addr;
@@ -291,8 +290,6 @@ static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh,
 	pgoff_t size;
 	int error;
 
-	i_mmap_lock_read(mapping);
-
 	/*
 	 * Check truncate didn't happen while we were allocating a block.
 	 * If it did, this block may or may not be still allocated to the
@@ -322,8 +319,6 @@ static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh,
 	error = vm_insert_mixed(vma, vaddr, pfn);
 
  out:
-	i_mmap_unlock_read(mapping);
-
 	return error;
 }
 
@@ -385,15 +380,17 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 			 * from a read fault and we've raced with a truncate
 			 */
 			error = -EIO;
-			goto unlock_page;
+			goto unlock;
 		}
+	} else {
+		i_mmap_lock_write(mapping);
 	}
 
 	error = get_block(inode, block, &bh, 0);
 	if (!error && (bh.b_size < PAGE_SIZE))
 		error = -EIO;		/* fs corruption? */
 	if (error)
-		goto unlock_page;
+		goto unlock;
 
 	if (!buffer_mapped(&bh) && !buffer_unwritten(&bh) && !vmf->cow_page) {
 		if (vmf->flags & FAULT_FLAG_WRITE) {
@@ -404,8 +401,9 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 			if (!error && (bh.b_size < PAGE_SIZE))
 				error = -EIO;
 			if (error)
-				goto unlock_page;
+				goto unlock;
 		} else {
+			i_mmap_unlock_write(mapping);
 			return dax_load_hole(mapping, page, vmf);
 		}
 	}
@@ -417,17 +415,15 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 		else
 			clear_user_highpage(new_page, vaddr);
 		if (error)
-			goto unlock_page;
+			goto unlock;
 		vmf->page = page;
 		if (!page) {
-			i_mmap_lock_read(mapping);
 			/* Check we didn't race with truncate */
 			size = (i_size_read(inode) + PAGE_SIZE - 1) >>
 								PAGE_SHIFT;
 			if (vmf->pgoff >= size) {
-				i_mmap_unlock_read(mapping);
 				error = -EIO;
-				goto out;
+				goto unlock;
 			}
 		}
 		return VM_FAULT_LOCKED;
@@ -463,6 +459,8 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 			WARN_ON_ONCE(!(vmf->flags & FAULT_FLAG_WRITE));
 	}
 
+	if (!page)
+		i_mmap_unlock_write(mapping);
  out:
 	if (error == -ENOMEM)
 		return VM_FAULT_OOM | major;
@@ -471,11 +469,14 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 		return VM_FAULT_SIGBUS | major;
 	return VM_FAULT_NOPAGE | major;
 
- unlock_page:
+ unlock:
 	if (page) {
 		unlock_page(page);
 		page_cache_release(page);
+	} else {
+		i_mmap_unlock_write(mapping);
 	}
+
 	goto out;
 }
 EXPORT_SYMBOL(__dax_fault);
@@ -507,6 +508,176 @@ int dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 }
 EXPORT_SYMBOL_GPL(dax_fault);
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+/*
+ * The 'colour' (ie low bits) within a PMD of a page offset.  This comes up
+ * more often than one might expect in the below function.
+ */
+#define PG_PMD_COLOUR	((PMD_SIZE >> PAGE_SHIFT) - 1)
+
+int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
+		pmd_t *pmd, unsigned int flags, get_block_t get_block,
+		dax_iodone_t complete_unwritten)
+{
+	struct file *file = vma->vm_file;
+	struct address_space *mapping = file->f_mapping;
+	struct inode *inode = mapping->host;
+	struct buffer_head bh;
+	unsigned blkbits = inode->i_blkbits;
+	unsigned long pmd_addr = address & PMD_MASK;
+	bool write = flags & FAULT_FLAG_WRITE;
+	long length;
+	void *kaddr;
+	pgoff_t size, pgoff;
+	sector_t block, sector;
+	unsigned long pfn;
+	int result = 0;
+
+	/* Fall back to PTEs if we're going to COW */
+	if (write && !(vma->vm_flags & VM_SHARED))
+		return VM_FAULT_FALLBACK;
+	/* If the PMD would extend outside the VMA */
+	if (pmd_addr < vma->vm_start)
+		return VM_FAULT_FALLBACK;
+	if ((pmd_addr + PMD_SIZE) > vma->vm_end)
+		return VM_FAULT_FALLBACK;
+
+	pgoff = linear_page_index(vma, pmd_addr);
+	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	if (pgoff >= size)
+		return VM_FAULT_SIGBUS;
+	/* If the PMD would cover blocks out of the file */
+	if ((pgoff | PG_PMD_COLOUR) >= size)
+		return VM_FAULT_FALLBACK;
+
+	memset(&bh, 0, sizeof(bh));
+	block = (sector_t)pgoff << (PAGE_SHIFT - blkbits);
+
+	bh.b_size = PMD_SIZE;
+	i_mmap_lock_write(mapping);
+	length = get_block(inode, block, &bh, write);
+	if (length)
+		return VM_FAULT_SIGBUS;
+
+	/*
+	 * If the filesystem isn't willing to tell us the length of a hole,
+	 * just fall back to PTEs.  Calling get_block 512 times in a loop
+	 * would be silly.
+	 */
+	if (!buffer_size_valid(&bh) || bh.b_size < PMD_SIZE)
+		goto fallback;
+
+	if (buffer_unwritten(&bh) || buffer_new(&bh)) {
+		int i;
+		for (i = 0; i < PTRS_PER_PMD; i++)
+			clear_page(kaddr + i * PAGE_SIZE);
+		count_vm_event(PGMAJFAULT);
+		mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
+		result |= VM_FAULT_MAJOR;
+	}
+
+	/*
+	 * If we allocated new storage, make sure no process has any
+	 * zero pages covering this hole
+	 */
+	if (buffer_new(&bh)) {
+		i_mmap_unlock_write(mapping);
+		unmap_mapping_range(mapping, pgoff << PAGE_SHIFT, PMD_SIZE, 0);
+		i_mmap_lock_write(mapping);
+	}
+
+	/*
+	 * If a truncate happened while we were allocating blocks, we may
+	 * leave blocks allocated to the file that are beyond EOF.  We can't
+	 * take i_mutex here, so just leave them hanging; they'll be freed
+	 * when the file is deleted.
+	 */
+	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	if (pgoff >= size) {
+		result = VM_FAULT_SIGBUS;
+		goto out;
+	}
+	if ((pgoff | PG_PMD_COLOUR) >= size)
+		goto fallback;
+
+	if (!write && !buffer_mapped(&bh) && buffer_uptodate(&bh)) {
+		spinlock_t *ptl;
+		pmd_t entry;
+		struct page *zero_page = get_huge_zero_page();
+
+		if (unlikely(!zero_page))
+			goto fallback;
+
+		ptl = pmd_lock(vma->vm_mm, pmd);
+		if (!pmd_none(*pmd)) {
+			spin_unlock(ptl);
+			goto fallback;
+		}
+
+		entry = mk_pmd(zero_page, vma->vm_page_prot);
+		entry = pmd_mkhuge(entry);
+		set_pmd_at(vma->vm_mm, pmd_addr, pmd, entry);
+		result = VM_FAULT_NOPAGE;
+		spin_unlock(ptl);
+	} else {
+		sector = bh.b_blocknr << (blkbits - 9);
+		length = bdev_direct_access(bh.b_bdev, sector, &kaddr, &pfn,
+						bh.b_size);
+		if (length < 0) {
+			result = VM_FAULT_SIGBUS;
+			goto out;
+		}
+		if ((length < PMD_SIZE) || (pfn & PG_PMD_COLOUR))
+			goto fallback;
+
+		result |= vmf_insert_pfn_pmd(vma, address, pmd, pfn, write);
+	}
+
+ out:
+	if (buffer_unwritten(&bh))
+		complete_unwritten(&bh, !(result & VM_FAULT_ERROR));
+
+	i_mmap_unlock_write(mapping);
+
+	return result;
+
+ fallback:
+	count_vm_event(THP_FAULT_FALLBACK);
+	result = VM_FAULT_FALLBACK;
+	goto out;
+}
+EXPORT_SYMBOL_GPL(__dax_pmd_fault);
+
+/**
+ * dax_pmd_fault - handle a PMD fault on a DAX file
+ * @vma: The virtual memory area where the fault occurred
+ * @vmf: The description of the fault
+ * @get_block: The filesystem method used to translate file offsets to blocks
+ *
+ * When a page fault occurs, filesystems may call this helper in their
+ * pmd_fault handler for DAX files.
+ */
+int dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
+			pmd_t *pmd, unsigned int flags, get_block_t get_block,
+			dax_iodone_t complete_unwritten)
+{
+	int result;
+	struct super_block *sb = file_inode(vma->vm_file)->i_sb;
+
+	if (flags & FAULT_FLAG_WRITE) {
+		sb_start_pagefault(sb);
+		file_update_time(vma->vm_file);
+	}
+	result = __dax_pmd_fault(vma, address, pmd, flags, get_block,
+				complete_unwritten);
+	if (flags & FAULT_FLAG_WRITE)
+		sb_end_pagefault(sb);
+
+	return result;
+}
+EXPORT_SYMBOL_GPL(dax_pmd_fault);
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
 /**
  * dax_pfn_mkwrite - handle first write to DAX page
  * @vma: The virtual memory area where the fault occurred

fs/ext2/file.c

@@ -20,6 +20,7 @@
 
 #include <linux/time.h>
 #include <linux/pagemap.h>
+#include <linux/dax.h>
 #include <linux/quotaops.h>
 #include "ext2.h"
 #include "xattr.h"
@@ -31,6 +32,12 @@ static int ext2_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	return dax_fault(vma, vmf, ext2_get_block, NULL);
 }
 
+static int ext2_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
+						pmd_t *pmd, unsigned int flags)
+{
+	return dax_pmd_fault(vma, addr, pmd, flags, ext2_get_block, NULL);
+}
+
 static int ext2_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	return dax_mkwrite(vma, vmf, ext2_get_block, NULL);
@@ -38,6 +45,7 @@ static int ext2_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 
 static const struct vm_operations_struct ext2_dax_vm_ops = {
 	.fault		= ext2_dax_fault,
+	.pmd_fault	= ext2_dax_pmd_fault,
 	.page_mkwrite	= ext2_dax_mkwrite,
 	.pfn_mkwrite	= dax_pfn_mkwrite,
 };
@@ -49,7 +57,7 @@ static int ext2_file_mmap(struct file *file, struct vm_area_struct *vma)
 
 	file_accessed(file);
 	vma->vm_ops = &ext2_dax_vm_ops;
-	vma->vm_flags |= VM_MIXEDMAP;
+	vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE;
 	return 0;
 }
 #else

fs/ext2/inode.c

@@ -25,6 +25,7 @@
 #include <linux/time.h>
 #include <linux/highuid.h>
 #include <linux/pagemap.h>
+#include <linux/dax.h>
 #include <linux/quotaops.h>
 #include <linux/writeback.h>
 #include <linux/buffer_head.h>

fs/ext4/ext4.h

@@ -2272,6 +2272,8 @@ struct buffer_head *ext4_getblk(handle_t *, struct inode *, ext4_lblk_t, int);
 struct buffer_head *ext4_bread(handle_t *, struct inode *, ext4_lblk_t, int);
 int ext4_get_block_write(struct inode *inode, sector_t iblock,
 			 struct buffer_head *bh_result, int create);
+int ext4_get_block_dax(struct inode *inode, sector_t iblock,
+			 struct buffer_head *bh_result, int create);
 int ext4_get_block(struct inode *inode, sector_t iblock,
 				struct buffer_head *bh_result, int create);
 int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,

fs/ext4/file.c

@@ -22,6 +22,7 @@
 #include <linux/fs.h>
 #include <linux/mount.h>
 #include <linux/path.h>
+#include <linux/dax.h>
 #include <linux/quotaops.h>
 #include <linux/pagevec.h>
 #include <linux/uio.h>
@@ -195,7 +196,7 @@ out:
 static void ext4_end_io_unwritten(struct buffer_head *bh, int uptodate)
 {
 	struct inode *inode = bh->b_assoc_map->host;
-	/* XXX: breaks on 32-bit > 16GB. Is that even supported? */
+	/* XXX: breaks on 32-bit > 16TB. Is that even supported? */
 	loff_t offset = (loff_t)(uintptr_t)bh->b_private << inode->i_blkbits;
 	int err;
 	if (!uptodate)
@@ -206,17 +207,74 @@ static void ext4_end_io_unwritten(struct buffer_head *bh, int uptodate)
 
 static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
-	return dax_fault(vma, vmf, ext4_get_block, ext4_end_io_unwritten);
-					/* Is this the right get_block? */
+	int result;
+	handle_t *handle = NULL;
+	struct super_block *sb = file_inode(vma->vm_file)->i_sb;
+	bool write = vmf->flags & FAULT_FLAG_WRITE;
+
+	if (write) {
+		sb_start_pagefault(sb);
+		file_update_time(vma->vm_file);
+		handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
+						EXT4_DATA_TRANS_BLOCKS(sb));
+	}
+
+	if (IS_ERR(handle))
+		result = VM_FAULT_SIGBUS;
+	else
+		result = __dax_fault(vma, vmf, ext4_get_block_dax,
+						ext4_end_io_unwritten);
+
+	if (write) {
+		if (!IS_ERR(handle))
+			ext4_journal_stop(handle);
+		sb_end_pagefault(sb);
+	}
+
+	return result;
+}
+
+static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
+						pmd_t *pmd, unsigned int flags)
+{
+	int result;
+	handle_t *handle = NULL;
+	struct inode *inode = file_inode(vma->vm_file);
+	struct super_block *sb = inode->i_sb;
+	bool write = flags & FAULT_FLAG_WRITE;
+
+	if (write) {
+		sb_start_pagefault(sb);
+		file_update_time(vma->vm_file);
+		handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
+				ext4_chunk_trans_blocks(inode,
+							PMD_SIZE / PAGE_SIZE));
+	}
+
+	if (IS_ERR(handle))
+		result = VM_FAULT_SIGBUS;
+	else
+		result = __dax_pmd_fault(vma, addr, pmd, flags,
+				ext4_get_block_dax, ext4_end_io_unwritten);
+
+	if (write) {
+		if (!IS_ERR(handle))
+			ext4_journal_stop(handle);
+		sb_end_pagefault(sb);
+	}
+
+	return result;
 }
 
 static int ext4_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
-	return dax_mkwrite(vma, vmf, ext4_get_block, ext4_end_io_unwritten);
+	return dax_mkwrite(vma, vmf, ext4_get_block_dax,
+				ext4_end_io_unwritten);
 }
 
 static const struct vm_operations_struct ext4_dax_vm_ops = {
 	.fault		= ext4_dax_fault,
+	.pmd_fault	= ext4_dax_pmd_fault,
 	.page_mkwrite	= ext4_dax_mkwrite,
 	.pfn_mkwrite	= dax_pfn_mkwrite,
 };
@@ -244,7 +302,7 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
 	file_accessed(file);
 	if (IS_DAX(file_inode(file))) {
 		vma->vm_ops = &ext4_dax_vm_ops;
-		vma->vm_flags |= VM_MIXEDMAP;
+		vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE;
 	} else {
 		vma->vm_ops = &ext4_file_vm_ops;
 	}

fs/ext4/indirect.c

@@ -22,6 +22,7 @@
 
 #include "ext4_jbd2.h"
 #include "truncate.h"
+#include <linux/dax.h>
 #include <linux/uio.h>
 
 #include <trace/events/ext4.h>

fs/ext4/inode.c

@@ -22,6 +22,7 @@
 #include <linux/time.h>
 #include <linux/highuid.h>
 #include <linux/pagemap.h>
+#include <linux/dax.h>
 #include <linux/quotaops.h>
 #include <linux/string.h>
 #include <linux/buffer_head.h>
@@ -3020,6 +3021,17 @@ static int ext4_get_block_write_nolock(struct inode *inode, sector_t iblock,
 			       EXT4_GET_BLOCKS_NO_LOCK);
 }
 
+int ext4_get_block_dax(struct inode *inode, sector_t iblock,
+		   struct buffer_head *bh_result, int create)
+{
+	int flags = EXT4_GET_BLOCKS_PRE_IO | EXT4_GET_BLOCKS_UNWRIT_EXT;
+	if (create)
+		flags |= EXT4_GET_BLOCKS_CREATE;
+	ext4_debug("ext4_get_block_dax: inode %lu, create flag %d\n",
+		   inode->i_ino, create);
+	return _ext4_get_block(inode, iblock, bh_result, flags);
+}
+
 static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
 			    ssize_t size, void *private)
 {

fs/hugetlbfs/inode.c

@@ -12,6 +12,7 @@
 #include <linux/thread_info.h>
 #include <asm/current.h>
 #include <linux/sched.h>		/* remove ASAP */
+#include <linux/falloc.h>
 #include <linux/fs.h>
 #include <linux/mount.h>
 #include <linux/file.h>
@@ -84,6 +85,29 @@ static const match_table_t tokens = {
 	{Opt_err,	NULL},
 };
 
+#ifdef CONFIG_NUMA
+static inline void hugetlb_set_vma_policy(struct vm_area_struct *vma,
+					struct inode *inode, pgoff_t index)
+{
+	vma->vm_policy = mpol_shared_policy_lookup(&HUGETLBFS_I(inode)->policy,
+							index);
+}
+
+static inline void hugetlb_drop_vma_policy(struct vm_area_struct *vma)
+{
+	mpol_cond_put(vma->vm_policy);
+}
+#else
+static inline void hugetlb_set_vma_policy(struct vm_area_struct *vma,
+					struct inode *inode, pgoff_t index)
+{
+}
+
+static inline void hugetlb_drop_vma_policy(struct vm_area_struct *vma)
+{
+}
+#endif
+
 static void huge_pagevec_release(struct pagevec *pvec)
 {
 	int i;
@@ -293,26 +317,61 @@ static int hugetlbfs_write_end(struct file *file, struct address_space *mapping,
 	return -EINVAL;
 }
 
-static void truncate_huge_page(struct page *page)
+static void remove_huge_page(struct page *page)
 {
 	ClearPageDirty(page);
 	ClearPageUptodate(page);
 	delete_from_page_cache(page);
 }
 
-static void truncate_hugepages(struct inode *inode, loff_t lstart)
+
+/*
+ * remove_inode_hugepages handles two distinct cases: truncation and hole
+ * punch.  There are subtle differences in operation for each case.
+
+ * truncation is indicated by end of range being LLONG_MAX
+ *	In this case, we first scan the range and release found pages.
+ *	After releasing pages, hugetlb_unreserve_pages cleans up region/reserv
+ *	maps and global counts.
+ * hole punch is indicated if end is not LLONG_MAX
+ *	In the hole punch case we scan the range and release found pages.
+ *	Only when releasing a page is the associated region/reserv map
+ *	deleted.  The region/reserv map for ranges without associated
+ *	pages are not modified.
+ * Note: If the passed end of range value is beyond the end of file, but
+ * not LLONG_MAX this routine still performs a hole punch operation.
+ */
+static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
+				   loff_t lend)
 {
 	struct hstate *h = hstate_inode(inode);
 	struct address_space *mapping = &inode->i_data;
 	const pgoff_t start = lstart >> huge_page_shift(h);
+	const pgoff_t end = lend >> huge_page_shift(h);
+	struct vm_area_struct pseudo_vma;
 	struct pagevec pvec;
 	pgoff_t next;
 	int i, freed = 0;
+	long lookup_nr = PAGEVEC_SIZE;
+	bool truncate_op = (lend == LLONG_MAX);
 
+	memset(&pseudo_vma, 0, sizeof(struct vm_area_struct));
+	pseudo_vma.vm_flags = (VM_HUGETLB | VM_MAYSHARE | VM_SHARED);
 	pagevec_init(&pvec, 0);
 	next = start;
-	while (1) {
-		if (!pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) {
+	while (next < end) {
+		/*
+		 * Make sure to never grab more pages that we
+		 * might possibly need.
+		 */
+		if (end - next < lookup_nr)
+			lookup_nr = end - next;
+
+		/*
+		 * This pagevec_lookup() may return pages past 'end',
+		 * so we must check for page->index > end.
+		 */
+		if (!pagevec_lookup(&pvec, mapping, next, lookup_nr)) {
 			if (next == start)
 				break;
 			next = start;
@@ -321,26 +380,69 @@ static void truncate_hugepages(struct inode *inode, loff_t lstart)
 
 		for (i = 0; i < pagevec_count(&pvec); ++i) {
 			struct page *page = pvec.pages[i];
+			u32 hash;
+
+			hash = hugetlb_fault_mutex_hash(h, current->mm,
+							&pseudo_vma,
+							mapping, next, 0);
+			mutex_lock(&hugetlb_fault_mutex_table[hash]);
 
 			lock_page(page);
+			if (page->index >= end) {
+				unlock_page(page);
+				mutex_unlock(&hugetlb_fault_mutex_table[hash]);
+				next = end;	/* we are done */
+				break;
+			}
+
+			/*
+			 * If page is mapped, it was faulted in after being
+			 * unmapped.  Do nothing in this race case.  In the
+			 * normal case page is not mapped.
+			 */
+			if (!page_mapped(page)) {
+				bool rsv_on_error = !PagePrivate(page);
+				/*
+				 * We must free the huge page and remove
+				 * from page cache (remove_huge_page) BEFORE
+				 * removing the region/reserve map
+				 * (hugetlb_unreserve_pages).  In rare out
+				 * of memory conditions, removal of the
+				 * region/reserve map could fail.  Before
+				 * free'ing the page, note PagePrivate which
+				 * is used in case of error.
+				 */
+				remove_huge_page(page);
+				freed++;
+				if (!truncate_op) {
+					if (unlikely(hugetlb_unreserve_pages(
+							inode, next,
+							next + 1, 1)))
+						hugetlb_fix_reserve_counts(
+							inode, rsv_on_error);
+				}
+			}
+
 			if (page->index > next)
 				next = page->index;
+
 			++next;
-			truncate_huge_page(page);
 			unlock_page(page);
-			freed++;
+
+			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 		}
 		huge_pagevec_release(&pvec);
 	}
-	BUG_ON(!lstart && mapping->nrpages);
-	hugetlb_unreserve_pages(inode, start, freed);
+
+	if (truncate_op)
+		(void)hugetlb_unreserve_pages(inode, start, LONG_MAX, freed);
 }
 
 static void hugetlbfs_evict_inode(struct inode *inode)
 {
 	struct resv_map *resv_map;
 
-	truncate_hugepages(inode, 0);
+	remove_inode_hugepages(inode, 0, LLONG_MAX);
 	resv_map = (struct resv_map *)inode->i_mapping->private_data;
 	/* root inode doesn't have the resv_map, so we should check it */
 	if (resv_map)
@@ -349,11 +451,15 @@ static void hugetlbfs_evict_inode(struct inode *inode)
 }
 
 static inline void
-hugetlb_vmtruncate_list(struct rb_root *root, pgoff_t pgoff)
+hugetlb_vmdelete_list(struct rb_root *root, pgoff_t start, pgoff_t end)
 {
 	struct vm_area_struct *vma;
 
-	vma_interval_tree_foreach(vma, root, pgoff, ULONG_MAX) {
+	/*
+	 * end == 0 indicates that the entire range after
+	 * start should be unmapped.
+	 */
+	vma_interval_tree_foreach(vma, root, start, end ? end : ULONG_MAX) {
 		unsigned long v_offset;
 
 		/*
@@ -362,13 +468,20 @@ hugetlb_vmtruncate_list(struct rb_root *root, pgoff_t pgoff)
 		 * which overlap the truncated area starting at pgoff,
 		 * and no vma on a 32-bit arch can span beyond the 4GB.
 		 */
-		if (vma->vm_pgoff < pgoff)
-			v_offset = (pgoff - vma->vm_pgoff) << PAGE_SHIFT;
+		if (vma->vm_pgoff < start)
+			v_offset = (start - vma->vm_pgoff) << PAGE_SHIFT;
 		else
 			v_offset = 0;
 
-		unmap_hugepage_range(vma, vma->vm_start + v_offset,
-				     vma->vm_end, NULL);
+		if (end) {
+			end = ((end - start) << PAGE_SHIFT) +
+			       vma->vm_start + v_offset;
+			if (end > vma->vm_end)
+				end = vma->vm_end;
+		} else
+			end = vma->vm_end;
+
+		unmap_hugepage_range(vma, vma->vm_start + v_offset, end, NULL);
 	}
 }
 
@@ -384,12 +497,164 @@ static int hugetlb_vmtruncate(struct inode *inode, loff_t offset)
 	i_size_write(inode, offset);
 	i_mmap_lock_write(mapping);
 	if (!RB_EMPTY_ROOT(&mapping->i_mmap))
-		hugetlb_vmtruncate_list(&mapping->i_mmap, pgoff);
+		hugetlb_vmdelete_list(&mapping->i_mmap, pgoff, 0);
 	i_mmap_unlock_write(mapping);
-	truncate_hugepages(inode, offset);
+	remove_inode_hugepages(inode, offset, LLONG_MAX);
 	return 0;
 }
 
+static long hugetlbfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
+{
+	struct hstate *h = hstate_inode(inode);
+	loff_t hpage_size = huge_page_size(h);
+	loff_t hole_start, hole_end;
+
+	/*
+	 * For hole punch round up the beginning offset of the hole and
+	 * round down the end.
+	 */
+	hole_start = round_up(offset, hpage_size);
+	hole_end = round_down(offset + len, hpage_size);
+
+	if (hole_end > hole_start) {
+		struct address_space *mapping = inode->i_mapping;
+
+		mutex_lock(&inode->i_mutex);
+		i_mmap_lock_write(mapping);
+		if (!RB_EMPTY_ROOT(&mapping->i_mmap))
+			hugetlb_vmdelete_list(&mapping->i_mmap,
+						hole_start >> PAGE_SHIFT,
+						hole_end  >> PAGE_SHIFT);
+		i_mmap_unlock_write(mapping);
+		remove_inode_hugepages(inode, hole_start, hole_end);
+		mutex_unlock(&inode->i_mutex);
+	}
+
+	return 0;
+}
+
+static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
+				loff_t len)
+{
+	struct inode *inode = file_inode(file);
+	struct address_space *mapping = inode->i_mapping;
+	struct hstate *h = hstate_inode(inode);
+	struct vm_area_struct pseudo_vma;
+	struct mm_struct *mm = current->mm;
+	loff_t hpage_size = huge_page_size(h);
+	unsigned long hpage_shift = huge_page_shift(h);
+	pgoff_t start, index, end;
+	int error;
+	u32 hash;
+
+	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
+		return -EOPNOTSUPP;
+
+	if (mode & FALLOC_FL_PUNCH_HOLE)
+		return hugetlbfs_punch_hole(inode, offset, len);
+
+	/*
+	 * Default preallocate case.
+	 * For this range, start is rounded down and end is rounded up
+	 * as well as being converted to page offsets.
+	 */
+	start = offset >> hpage_shift;
+	end = (offset + len + hpage_size - 1) >> hpage_shift;
+
+	mutex_lock(&inode->i_mutex);
+
+	/* We need to check rlimit even when FALLOC_FL_KEEP_SIZE */
+	error = inode_newsize_ok(inode, offset + len);
+	if (error)
+		goto out;
+
+	/*
+	 * Initialize a pseudo vma as this is required by the huge page
+	 * allocation routines.  If NUMA is configured, use page index
+	 * as input to create an allocation policy.
+	 */
+	memset(&pseudo_vma, 0, sizeof(struct vm_area_struct));
+	pseudo_vma.vm_flags = (VM_HUGETLB | VM_MAYSHARE | VM_SHARED);
+	pseudo_vma.vm_file = file;
+
+	for (index = start; index < end; index++) {
+		/*
+		 * This is supposed to be the vaddr where the page is being
+		 * faulted in, but we have no vaddr here.
+		 */
+		struct page *page;
+		unsigned long addr;
+		int avoid_reserve = 0;
+
+		cond_resched();
+
+		/*
+		 * fallocate(2) manpage permits EINTR; we may have been
+		 * interrupted because we are using up too much memory.
+		 */
+		if (signal_pending(current)) {
+			error = -EINTR;
+			break;
+		}
+
+		/* Set numa allocation policy based on index */
+		hugetlb_set_vma_policy(&pseudo_vma, inode, index);
+
+		/* addr is the offset within the file (zero based) */
+		addr = index * hpage_size;
+
+		/* mutex taken here, fault path and hole punch */
+		hash = hugetlb_fault_mutex_hash(h, mm, &pseudo_vma, mapping,
+						index, addr);
+		mutex_lock(&hugetlb_fault_mutex_table[hash]);
+
+		/* See if already present in mapping to avoid alloc/free */
+		page = find_get_page(mapping, index);
+		if (page) {
+			put_page(page);
+			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
+			hugetlb_drop_vma_policy(&pseudo_vma);
+			continue;
+		}
+
+		/* Allocate page and add to page cache */
+		page = alloc_huge_page(&pseudo_vma, addr, avoid_reserve);
+		hugetlb_drop_vma_policy(&pseudo_vma);
+		if (IS_ERR(page)) {
+			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
+			error = PTR_ERR(page);
+			goto out;
+		}
+		clear_huge_page(page, addr, pages_per_huge_page(h));
+		__SetPageUptodate(page);
+		error = huge_add_to_page_cache(page, mapping, index);
+		if (unlikely(error)) {
+			put_page(page);
+			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
+			goto out;
+		}
+
+		mutex_unlock(&hugetlb_fault_mutex_table[hash]);
+
+		/*
+		 * page_put due to reference from alloc_huge_page()
+		 * unlock_page because locked by add_to_page_cache()
+		 */
+		put_page(page);
+		unlock_page(page);
+	}
+
+	if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > inode->i_size)
+		i_size_write(inode, offset + len);
+	inode->i_ctime = CURRENT_TIME;
+	spin_lock(&inode->i_lock);
+	inode->i_private = NULL;
+	spin_unlock(&inode->i_lock);
+out:
+	mutex_unlock(&inode->i_mutex);
+	return error;
+}
+
 static int hugetlbfs_setattr(struct dentry *dentry, struct iattr *attr)
 {
 	struct inode *inode = d_inode(dentry);
@@ -701,7 +966,8 @@ const struct file_operations hugetlbfs_file_operations = {
 	.mmap			= hugetlbfs_file_mmap,
 	.fsync			= noop_fsync,
 	.get_unmapped_area	= hugetlb_get_unmapped_area,
-	.llseek		= default_llseek,
+	.llseek			= default_llseek,
+	.fallocate		= hugetlbfs_fallocate,
 };
 
 static const struct inode_operations hugetlbfs_dir_inode_operations = {

fs/proc/task_mmu.c

@@ -446,6 +446,7 @@ struct mem_size_stats {
 	unsigned long anonymous_thp;
 	unsigned long swap;
 	u64 pss;
+	u64 swap_pss;
 };
 
 static void smaps_account(struct mem_size_stats *mss, struct page *page,
@@ -492,9 +493,20 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
 	} else if (is_swap_pte(*pte)) {
 		swp_entry_t swpent = pte_to_swp_entry(*pte);
 
-		if (!non_swap_entry(swpent))
+		if (!non_swap_entry(swpent)) {
+			int mapcount;
+
 			mss->swap += PAGE_SIZE;
-		else if (is_migration_entry(swpent))
+			mapcount = swp_swapcount(swpent);
+			if (mapcount >= 2) {
+				u64 pss_delta = (u64)PAGE_SIZE << PSS_SHIFT;
+
+				do_div(pss_delta, mapcount);
+				mss->swap_pss += pss_delta;
+			} else {
+				mss->swap_pss += (u64)PAGE_SIZE << PSS_SHIFT;
+			}
+		} else if (is_migration_entry(swpent))
 			page = migration_entry_to_page(swpent);
 	}
 
@@ -640,6 +652,7 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
 		   "Anonymous:      %8lu kB\n"
 		   "AnonHugePages:  %8lu kB\n"
 		   "Swap:           %8lu kB\n"
+		   "SwapPss:        %8lu kB\n"
 		   "KernelPageSize: %8lu kB\n"
 		   "MMUPageSize:    %8lu kB\n"
 		   "Locked:         %8lu kB\n",
@@ -654,6 +667,7 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
 		   mss.anonymous >> 10,
 		   mss.anonymous_thp >> 10,
 		   mss.swap >> 10,
+		   (unsigned long)(mss.swap_pss >> (10 + PSS_SHIFT)),
 		   vma_kernel_pagesize(vma) >> 10,
 		   vma_mmu_pagesize(vma) >> 10,
 		   (vma->vm_flags & VM_LOCKED) ?
@@ -712,23 +726,6 @@ const struct file_operations proc_tid_smaps_operations = {
 	.release	= proc_map_release,
 };
 
-/*
- * We do not want to have constant page-shift bits sitting in
- * pagemap entries and are about to reuse them some time soon.
- *
- * Here's the "migration strategy":
- * 1. when the system boots these bits remain what they are,
- *    but a warning about future change is printed in log;
- * 2. once anyone clears soft-dirty bits via clear_refs file,
- *    these flag is set to denote, that user is aware of the
- *    new API and those page-shift bits change their meaning.
- *    The respective warning is printed in dmesg;
- * 3. In a couple of releases we will remove all the mentions
- *    of page-shift in pagemap entries.
- */
-
-static bool soft_dirty_cleared __read_mostly;
-
 enum clear_refs_types {
 	CLEAR_REFS_ALL = 1,
 	CLEAR_REFS_ANON,
@@ -889,13 +886,6 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 	if (type < CLEAR_REFS_ALL || type >= CLEAR_REFS_LAST)
 		return -EINVAL;
 
-	if (type == CLEAR_REFS_SOFT_DIRTY) {
-		soft_dirty_cleared = true;
-		pr_warn_once("The pagemap bits 55-60 has changed their meaning!"
-			     " See the linux/Documentation/vm/pagemap.txt for "
-			     "details.\n");
-	}
-
 	task = get_proc_task(file_inode(file));
 	if (!task)
 		return -ESRCH;
@@ -963,36 +953,26 @@ typedef struct {
 struct pagemapread {
 	int pos, len;		/* units: PM_ENTRY_BYTES, not bytes */
 	pagemap_entry_t *buffer;
-	bool v2;
+	bool show_pfn;
 };
 
 #define PAGEMAP_WALK_SIZE	(PMD_SIZE)
 #define PAGEMAP_WALK_MASK	(PMD_MASK)
 
-#define PM_ENTRY_BYTES      sizeof(pagemap_entry_t)
-#define PM_STATUS_BITS      3
-#define PM_STATUS_OFFSET    (64 - PM_STATUS_BITS)
-#define PM_STATUS_MASK      (((1LL << PM_STATUS_BITS) - 1) << PM_STATUS_OFFSET)
-#define PM_STATUS(nr)       (((nr) << PM_STATUS_OFFSET) & PM_STATUS_MASK)
-#define PM_PSHIFT_BITS      6
-#define PM_PSHIFT_OFFSET    (PM_STATUS_OFFSET - PM_PSHIFT_BITS)
-#define PM_PSHIFT_MASK      (((1LL << PM_PSHIFT_BITS) - 1) << PM_PSHIFT_OFFSET)
-#define __PM_PSHIFT(x)      (((u64) (x) << PM_PSHIFT_OFFSET) & PM_PSHIFT_MASK)
-#define PM_PFRAME_MASK      ((1LL << PM_PSHIFT_OFFSET) - 1)
-#define PM_PFRAME(x)        ((x) & PM_PFRAME_MASK)
-/* in "new" pagemap pshift bits are occupied with more status bits */
-#define PM_STATUS2(v2, x)   (__PM_PSHIFT(v2 ? x : PAGE_SHIFT))
-
-#define __PM_SOFT_DIRTY      (1LL)
-#define PM_PRESENT          PM_STATUS(4LL)
-#define PM_SWAP             PM_STATUS(2LL)
-#define PM_FILE             PM_STATUS(1LL)
-#define PM_NOT_PRESENT(v2)  PM_STATUS2(v2, 0)
+#define PM_ENTRY_BYTES		sizeof(pagemap_entry_t)
+#define PM_PFRAME_BITS		55
+#define PM_PFRAME_MASK		GENMASK_ULL(PM_PFRAME_BITS - 1, 0)
+#define PM_SOFT_DIRTY		BIT_ULL(55)
+#define PM_MMAP_EXCLUSIVE	BIT_ULL(56)
+#define PM_FILE			BIT_ULL(61)
+#define PM_SWAP			BIT_ULL(62)
+#define PM_PRESENT		BIT_ULL(63)
+
 #define PM_END_OF_BUFFER    1
 
-static inline pagemap_entry_t make_pme(u64 val)
+static inline pagemap_entry_t make_pme(u64 frame, u64 flags)
 {
-	return (pagemap_entry_t) { .pme = val };
+	return (pagemap_entry_t) { .pme = (frame & PM_PFRAME_MASK) | flags };
 }
 
 static int add_to_pagemap(unsigned long addr, pagemap_entry_t *pme,
@@ -1013,7 +993,7 @@ static int pagemap_pte_hole(unsigned long start, unsigned long end,
 
 	while (addr < end) {
 		struct vm_area_struct *vma = find_vma(walk->mm, addr);
-		pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2));
+		pagemap_entry_t pme = make_pme(0, 0);
 		/* End of address space hole, which we mark as non-present. */
 		unsigned long hole_end;
 
@@ -1033,7 +1013,7 @@ static int pagemap_pte_hole(unsigned long start, unsigned long end,
 
 		/* Addresses in the VMA. */
 		if (vma->vm_flags & VM_SOFTDIRTY)
-			pme.pme |= PM_STATUS2(pm->v2, __PM_SOFT_DIRTY);
+			pme = make_pme(0, PM_SOFT_DIRTY);
 		for (; addr < min(end, vma->vm_end); addr += PAGE_SIZE) {
 			err = add_to_pagemap(addr, &pme, pm);
 			if (err)
@@ -1044,67 +1024,42 @@ out:
 	return err;
 }
 
-static void pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
+static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm,
 		struct vm_area_struct *vma, unsigned long addr, pte_t pte)
 {
-	u64 frame, flags;
+	u64 frame = 0, flags = 0;
 	struct page *page = NULL;
-	int flags2 = 0;
 
 	if (pte_present(pte)) {
-		frame = pte_pfn(pte);
-		flags = PM_PRESENT;
+		if (pm->show_pfn)
+			frame = pte_pfn(pte);
+		flags |= PM_PRESENT;
 		page = vm_normal_page(vma, addr, pte);
 		if (pte_soft_dirty(pte))
-			flags2 |= __PM_SOFT_DIRTY;
+			flags |= PM_SOFT_DIRTY;
 	} else if (is_swap_pte(pte)) {
 		swp_entry_t entry;
 		if (pte_swp_soft_dirty(pte))
-			flags2 |= __PM_SOFT_DIRTY;
+			flags |= PM_SOFT_DIRTY;
 		entry = pte_to_swp_entry(pte);
 		frame = swp_type(entry) |
 			(swp_offset(entry) << MAX_SWAPFILES_SHIFT);
-		flags = PM_SWAP;
+		flags |= PM_SWAP;
 		if (is_migration_entry(entry))
 			page = migration_entry_to_page(entry);
-	} else {
-		if (vma->vm_flags & VM_SOFTDIRTY)
-			flags2 |= __PM_SOFT_DIRTY;
-		*pme = make_pme(PM_NOT_PRESENT(pm->v2) | PM_STATUS2(pm->v2, flags2));
-		return;
 	}
 
 	if (page && !PageAnon(page))
 		flags |= PM_FILE;
-	if ((vma->vm_flags & VM_SOFTDIRTY))
-		flags2 |= __PM_SOFT_DIRTY;
-
-	*pme = make_pme(PM_PFRAME(frame) | PM_STATUS2(pm->v2, flags2) | flags);
-}
+	if (page && page_mapcount(page) == 1)
+		flags |= PM_MMAP_EXCLUSIVE;
+	if (vma->vm_flags & VM_SOFTDIRTY)
+		flags |= PM_SOFT_DIRTY;
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-static void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
-		pmd_t pmd, int offset, int pmd_flags2)
-{
-	/*
-	 * Currently pmd for thp is always present because thp can not be
-	 * swapped-out, migrated, or HWPOISONed (split in such cases instead.)
-	 * This if-check is just to prepare for future implementation.
-	 */
-	if (pmd_present(pmd))
-		*pme = make_pme(PM_PFRAME(pmd_pfn(pmd) + offset)
-				| PM_STATUS2(pm->v2, pmd_flags2) | PM_PRESENT);
-	else
-		*pme = make_pme(PM_NOT_PRESENT(pm->v2) | PM_STATUS2(pm->v2, pmd_flags2));
+	return make_pme(frame, flags);
 }
-#else
-static inline void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
-		pmd_t pmd, int offset, int pmd_flags2)
-{
-}
-#endif
 
-static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
+static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
 			     struct mm_walk *walk)
 {
 	struct vm_area_struct *vma = walk->vma;
@@ -1113,41 +1068,58 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	pte_t *pte, *orig_pte;
 	int err = 0;
 
-	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
-		int pmd_flags2;
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	if (pmd_trans_huge_lock(pmdp, vma, &ptl) == 1) {
+		u64 flags = 0, frame = 0;
+		pmd_t pmd = *pmdp;
 
-		if ((vma->vm_flags & VM_SOFTDIRTY) || pmd_soft_dirty(*pmd))
-			pmd_flags2 = __PM_SOFT_DIRTY;
-		else
-			pmd_flags2 = 0;
+		if ((vma->vm_flags & VM_SOFTDIRTY) || pmd_soft_dirty(pmd))
+			flags |= PM_SOFT_DIRTY;
+
+		/*
+		 * Currently pmd for thp is always present because thp
+		 * can not be swapped-out, migrated, or HWPOISONed
+		 * (split in such cases instead.)
+		 * This if-check is just to prepare for future implementation.
+		 */
+		if (pmd_present(pmd)) {
+			struct page *page = pmd_page(pmd);
+
+			if (page_mapcount(page) == 1)
+				flags |= PM_MMAP_EXCLUSIVE;
+
+			flags |= PM_PRESENT;
+			if (pm->show_pfn)
+				frame = pmd_pfn(pmd) +
+					((addr & ~PMD_MASK) >> PAGE_SHIFT);
+		}
 
 		for (; addr != end; addr += PAGE_SIZE) {
-			unsigned long offset;
-			pagemap_entry_t pme;
+			pagemap_entry_t pme = make_pme(frame, flags);
 
-			offset = (addr & ~PAGEMAP_WALK_MASK) >>
-					PAGE_SHIFT;
-			thp_pmd_to_pagemap_entry(&pme, pm, *pmd, offset, pmd_flags2);
 			err = add_to_pagemap(addr, &pme, pm);
 			if (err)
 				break;
+			if (pm->show_pfn && (flags & PM_PRESENT))
+				frame++;
 		}
 		spin_unlock(ptl);
 		return err;
 	}
 
-	if (pmd_trans_unstable(pmd))
+	if (pmd_trans_unstable(pmdp))
 		return 0;
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 	/*
 	 * We can assume that @vma always points to a valid one and @end never
 	 * goes beyond vma->vm_end.
 	 */
-	orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+	orig_pte = pte = pte_offset_map_lock(walk->mm, pmdp, addr, &ptl);
 	for (; addr < end; pte++, addr += PAGE_SIZE) {
 		pagemap_entry_t pme;
 
-		pte_to_pagemap_entry(&pme, pm, vma, addr, *pte);
+		pme = pte_to_pagemap_entry(pm, vma, addr, *pte);
 		err = add_to_pagemap(addr, &pme, pm);
 		if (err)
 			break;
@@ -1160,40 +1132,44 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 }
 
 #ifdef CONFIG_HUGETLB_PAGE
-static void huge_pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
-					pte_t pte, int offset, int flags2)
-{
-	if (pte_present(pte))
-		*pme = make_pme(PM_PFRAME(pte_pfn(pte) + offset)	|
-				PM_STATUS2(pm->v2, flags2)		|
-				PM_PRESENT);
-	else
-		*pme = make_pme(PM_NOT_PRESENT(pm->v2)			|
-				PM_STATUS2(pm->v2, flags2));
-}
-
 /* This function walks within one hugetlb entry in the single call */
-static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask,
+static int pagemap_hugetlb_range(pte_t *ptep, unsigned long hmask,
 				 unsigned long addr, unsigned long end,
 				 struct mm_walk *walk)
 {
 	struct pagemapread *pm = walk->private;
 	struct vm_area_struct *vma = walk->vma;
+	u64 flags = 0, frame = 0;
 	int err = 0;
-	int flags2;
-	pagemap_entry_t pme;
+	pte_t pte;
 
 	if (vma->vm_flags & VM_SOFTDIRTY)
-		flags2 = __PM_SOFT_DIRTY;
-	else
-		flags2 = 0;
+		flags |= PM_SOFT_DIRTY;
+
+	pte = huge_ptep_get(ptep);
+	if (pte_present(pte)) {
+		struct page *page = pte_page(pte);
+
+		if (!PageAnon(page))
+			flags |= PM_FILE;
+
+		if (page_mapcount(page) == 1)
+			flags |= PM_MMAP_EXCLUSIVE;
+
+		flags |= PM_PRESENT;
+		if (pm->show_pfn)
+			frame = pte_pfn(pte) +
+				((addr & ~hmask) >> PAGE_SHIFT);
+	}
 
 	for (; addr != end; addr += PAGE_SIZE) {
-		int offset = (addr & ~hmask) >> PAGE_SHIFT;
-		huge_pte_to_pagemap_entry(&pme, pm, *pte, offset, flags2);
+		pagemap_entry_t pme = make_pme(frame, flags);
+
 		err = add_to_pagemap(addr, &pme, pm);
 		if (err)
 			return err;
+		if (pm->show_pfn && (flags & PM_PRESENT))
+			frame++;
 	}
 
 	cond_resched();
@@ -1211,7 +1187,9 @@ static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask,
  * Bits 0-54  page frame number (PFN) if present
  * Bits 0-4   swap type if swapped
  * Bits 5-54  swap offset if swapped
- * Bits 55-60 page shift (page size = 1<<page shift)
+ * Bit  55    pte is soft-dirty (see Documentation/vm/soft-dirty.txt)
+ * Bit  56    page exclusively mapped
+ * Bits 57-60 zero
  * Bit  61    page is file-page or shared-anon
  * Bit  62    page swapped
  * Bit  63    page present
@@ -1229,42 +1207,37 @@ static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask,
 static ssize_t pagemap_read(struct file *file, char __user *buf,
 			    size_t count, loff_t *ppos)
 {
-	struct task_struct *task = get_proc_task(file_inode(file));
-	struct mm_struct *mm;
+	struct mm_struct *mm = file->private_data;
 	struct pagemapread pm;
-	int ret = -ESRCH;
 	struct mm_walk pagemap_walk = {};
 	unsigned long src;
 	unsigned long svpfn;
 	unsigned long start_vaddr;
 	unsigned long end_vaddr;
-	int copied = 0;
+	int ret = 0, copied = 0;
 
-	if (!task)
+	if (!mm || !atomic_inc_not_zero(&mm->mm_users))
 		goto out;
 
 	ret = -EINVAL;
 	/* file position must be aligned */
 	if ((*ppos % PM_ENTRY_BYTES) || (count % PM_ENTRY_BYTES))
-		goto out_task;
+		goto out_mm;
 
 	ret = 0;
 	if (!count)
-		goto out_task;
+		goto out_mm;
+
+	/* do not disclose physical addresses: attack vector */
+	pm.show_pfn = file_ns_capable(file, &init_user_ns, CAP_SYS_ADMIN);
 
-	pm.v2 = soft_dirty_cleared;
 	pm.len = (PAGEMAP_WALK_SIZE >> PAGE_SHIFT);
 	pm.buffer = kmalloc(pm.len * PM_ENTRY_BYTES, GFP_TEMPORARY);
 	ret = -ENOMEM;
 	if (!pm.buffer)
-		goto out_task;
-
-	mm = mm_access(task, PTRACE_MODE_READ);
-	ret = PTR_ERR(mm);
-	if (!mm || IS_ERR(mm))
-		goto out_free;
+		goto out_mm;
 
-	pagemap_walk.pmd_entry = pagemap_pte_range;
+	pagemap_walk.pmd_entry = pagemap_pmd_range;
 	pagemap_walk.pte_hole = pagemap_pte_hole;
 #ifdef CONFIG_HUGETLB_PAGE
 	pagemap_walk.hugetlb_entry = pagemap_hugetlb_range;
@@ -1275,10 +1248,10 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 	src = *ppos;
 	svpfn = src / PM_ENTRY_BYTES;
 	start_vaddr = svpfn << PAGE_SHIFT;
-	end_vaddr = TASK_SIZE_OF(task);
+	end_vaddr = mm->task_size;
 
 	/* watch out for wraparound */
-	if (svpfn > TASK_SIZE_OF(task) >> PAGE_SHIFT)
+	if (svpfn > mm->task_size >> PAGE_SHIFT)
 		start_vaddr = end_vaddr;
 
 	/*
@@ -1305,7 +1278,7 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 		len = min(count, PM_ENTRY_BYTES * pm.pos);
 		if (copy_to_user(buf, pm.buffer, len)) {
 			ret = -EFAULT;
-			goto out_mm;
+			goto out_free;
 		}
 		copied += len;
 		buf += len;
@@ -1315,24 +1288,31 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 	if (!ret || ret == PM_END_OF_BUFFER)
 		ret = copied;
 
-out_mm:
-	mmput(mm);
 out_free:
 	kfree(pm.buffer);
-out_task:
-	put_task_struct(task);
+out_mm:
+	mmput(mm);
 out:
 	return ret;
 }
 
 static int pagemap_open(struct inode *inode, struct file *file)
 {
-	/* do not disclose physical addresses: attack vector */
-	if (!capable(CAP_SYS_ADMIN))
-		return -EPERM;
-	pr_warn_once("Bits 55-60 of /proc/PID/pagemap entries are about "
-			"to stop being page-shift some time soon. See the "
-			"linux/Documentation/vm/pagemap.txt for details.\n");
+	struct mm_struct *mm;
+
+	mm = proc_mem_open(inode, PTRACE_MODE_READ);
+	if (IS_ERR(mm))
+		return PTR_ERR(mm);
+	file->private_data = mm;
+	return 0;
+}
+
+static int pagemap_release(struct inode *inode, struct file *file)
+{
+	struct mm_struct *mm = file->private_data;
+
+	if (mm)
+		mmdrop(mm);
 	return 0;
 }
 
@@ -1340,6 +1320,7 @@ const struct file_operations proc_pagemap_operations = {
 	.llseek		= mem_lseek, /* borrow this */
 	.read		= pagemap_read,
 	.open		= pagemap_open,
+	.release	= pagemap_release,
 };
 #endif /* CONFIG_PROC_PAGE_MONITOR */
 

fs/xfs/xfs_buf.h

@@ -23,6 +23,7 @@
 #include <linux/spinlock.h>
 #include <linux/mm.h>
 #include <linux/fs.h>
+#include <linux/dax.h>
 #include <linux/buffer_head.h>
 #include <linux/uio.h>
 #include <linux/list_lru.h>

fs/xfs/xfs_file.c

@@ -1546,8 +1546,36 @@ xfs_filemap_fault(
 	return ret;
 }
 
+STATIC int
+xfs_filemap_pmd_fault(
+	struct vm_area_struct	*vma,
+	unsigned long		addr,
+	pmd_t			*pmd,
+	unsigned int		flags)
+{
+	struct inode		*inode = file_inode(vma->vm_file);
+	struct xfs_inode	*ip = XFS_I(inode);
+	int			ret;
+
+	if (!IS_DAX(inode))
+		return VM_FAULT_FALLBACK;
+
+	trace_xfs_filemap_pmd_fault(ip);
+
+	sb_start_pagefault(inode->i_sb);
+	file_update_time(vma->vm_file);
+	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
+	ret = __dax_pmd_fault(vma, addr, pmd, flags, xfs_get_blocks_direct,
+				    xfs_end_io_dax_write);
+	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
+	sb_end_pagefault(inode->i_sb);
+
+	return ret;
+}
+
 static const struct vm_operations_struct xfs_file_vm_ops = {
 	.fault		= xfs_filemap_fault,
+	.pmd_fault	= xfs_filemap_pmd_fault,
 	.map_pages	= filemap_map_pages,
 	.page_mkwrite	= xfs_filemap_page_mkwrite,
 };
@@ -1560,7 +1588,7 @@ xfs_file_mmap(
 	file_accessed(filp);
 	vma->vm_ops = &xfs_file_vm_ops;
 	if (IS_DAX(file_inode(filp)))
-		vma->vm_flags |= VM_MIXEDMAP;
+		vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE;
 	return 0;
 }
 

fs/xfs/xfs_trace.h

@@ -687,6 +687,7 @@ DEFINE_INODE_EVENT(xfs_inode_clear_eofblocks_tag);
 DEFINE_INODE_EVENT(xfs_inode_free_eofblocks_invalid);
 
 DEFINE_INODE_EVENT(xfs_filemap_fault);
+DEFINE_INODE_EVENT(xfs_filemap_pmd_fault);
 DEFINE_INODE_EVENT(xfs_filemap_page_mkwrite);
 
 DECLARE_EVENT_CLASS(xfs_iref_class,

include/asm-generic/early_ioremap.h

@@ -35,6 +35,12 @@ extern void early_ioremap_setup(void);
  */
 extern void early_ioremap_reset(void);
 
+/*
+ * Early copy from unmapped memory to kernel mapped memory.
+ */
+extern void copy_from_early_mem(void *dest, phys_addr_t src,
+				unsigned long size);
+
 #else
 static inline void early_ioremap_init(void) { }
 static inline void early_ioremap_setup(void) { }

include/linux/dax.h

@@ -0,0 +1,39 @@
+#ifndef _LINUX_DAX_H
+#define _LINUX_DAX_H
+
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <asm/pgtable.h>
+
+ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *, loff_t,
+		  get_block_t, dio_iodone_t, int flags);
+int dax_clear_blocks(struct inode *, sector_t block, long size);
+int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t);
+int dax_truncate_page(struct inode *, loff_t from, get_block_t);
+int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t,
+		dax_iodone_t);
+int __dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t,
+		dax_iodone_t);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+int dax_pmd_fault(struct vm_area_struct *, unsigned long addr, pmd_t *,
+				unsigned int flags, get_block_t, dax_iodone_t);
+int __dax_pmd_fault(struct vm_area_struct *, unsigned long addr, pmd_t *,
+				unsigned int flags, get_block_t, dax_iodone_t);
+#else
+static inline int dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
+				pmd_t *pmd, unsigned int flags, get_block_t gb,
+				dax_iodone_t di)
+{
+	return VM_FAULT_FALLBACK;
+}
+#define __dax_pmd_fault dax_pmd_fault
+#endif
+int dax_pfn_mkwrite(struct vm_area_struct *, struct vm_fault *);
+#define dax_mkwrite(vma, vmf, gb, iod)		dax_fault(vma, vmf, gb, iod)
+#define __dax_mkwrite(vma, vmf, gb, iod)	__dax_fault(vma, vmf, gb, iod)
+
+static inline bool vma_is_dax(struct vm_area_struct *vma)
+{
+	return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host);
+}
+#endif

include/linux/dmapool.h

@@ -24,6 +24,12 @@ void dma_pool_destroy(struct dma_pool *pool);
 void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags,
 		     dma_addr_t *handle);
 
+static inline void *dma_pool_zalloc(struct dma_pool *pool, gfp_t mem_flags,
+				    dma_addr_t *handle)
+{
+	return dma_pool_alloc(pool, mem_flags | __GFP_ZERO, handle);
+}
+
 void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t addr);
 
 /*

include/linux/fs.h

@@ -52,7 +52,6 @@ struct swap_info_struct;
 struct seq_file;
 struct workqueue_struct;
 struct iov_iter;
-struct vm_fault;
 
 extern void __init inode_init(void);
 extern void __init inode_init_early(void);
@@ -2678,19 +2677,6 @@ extern loff_t fixed_size_llseek(struct file *file, loff_t offset,
 extern int generic_file_open(struct inode * inode, struct file * filp);
 extern int nonseekable_open(struct inode * inode, struct file * filp);
 
-ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *, loff_t,
-		  get_block_t, dio_iodone_t, int flags);
-int dax_clear_blocks(struct inode *, sector_t block, long size);
-int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t);
-int dax_truncate_page(struct inode *, loff_t from, get_block_t);
-int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t,
-		dax_iodone_t);
-int __dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t,
-		dax_iodone_t);
-int dax_pfn_mkwrite(struct vm_area_struct *, struct vm_fault *);
-#define dax_mkwrite(vma, vmf, gb, iod)		dax_fault(vma, vmf, gb, iod)
-#define __dax_mkwrite(vma, vmf, gb, iod)	__dax_fault(vma, vmf, gb, iod)
-
 #ifdef CONFIG_BLOCK
 typedef void (dio_submit_t)(int rw, struct bio *bio, struct inode *inode,
 			    loff_t file_offset);

include/linux/gfp.h

@@ -63,7 +63,10 @@ struct vm_area_struct;
  * but it is definitely preferable to use the flag rather than opencode endless
  * loop around allocator.
  *
- * __GFP_NORETRY: The VM implementation must not retry indefinitely.
+ * __GFP_NORETRY: The VM implementation must not retry indefinitely and will
+ * return NULL when direct reclaim and memory compaction have failed to allow
+ * the allocation to succeed.  The OOM killer is not called with the current
+ * implementation.
  *
  * __GFP_MOVABLE: Flag that this page will be movable by the page migration
  * mechanism or reclaimed
@@ -300,22 +303,31 @@ __alloc_pages(gfp_t gfp_mask, unsigned int order,
 	return __alloc_pages_nodemask(gfp_mask, order, zonelist, NULL);
 }
 
-static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask,
-						unsigned int order)
+/*
+ * Allocate pages, preferring the node given as nid. The node must be valid and
+ * online. For more general interface, see alloc_pages_node().
+ */
+static inline struct page *
+__alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order)
 {
-	/* Unknown node is current node */
-	if (nid < 0)
-		nid = numa_node_id();
+	VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES);
+	VM_WARN_ON(!node_online(nid));
 
 	return __alloc_pages(gfp_mask, order, node_zonelist(nid, gfp_mask));
 }
 
-static inline struct page *alloc_pages_exact_node(int nid, gfp_t gfp_mask,
+/*
+ * Allocate pages, preferring the node given as nid. When nid == NUMA_NO_NODE,
+ * prefer the current CPU's closest node. Otherwise node must be valid and
+ * online.
+ */
+static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask,
 						unsigned int order)
 {
-	VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES || !node_online(nid));
+	if (nid == NUMA_NO_NODE)
+		nid = numa_mem_id();
 
-	return __alloc_pages(gfp_mask, order, node_zonelist(nid, gfp_mask));
+	return __alloc_pages_node(nid, gfp_mask, order);
 }
 
 #ifdef CONFIG_NUMA
@@ -354,7 +366,6 @@ extern unsigned long get_zeroed_page(gfp_t gfp_mask);
 
 void *alloc_pages_exact(size_t size, gfp_t gfp_mask);
 void free_pages_exact(void *virt, size_t size);
-/* This is different from alloc_pages_exact_node !!! */
 void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask);
 
 #define __get_free_page(gfp_mask) \

include/linux/huge_mm.h

@@ -33,6 +33,8 @@ extern int move_huge_pmd(struct vm_area_struct *vma,
 extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 			unsigned long addr, pgprot_t newprot,
 			int prot_numa);
+int vmf_insert_pfn_pmd(struct vm_area_struct *, unsigned long addr, pmd_t *,
+			unsigned long pfn, bool write);
 
 enum transparent_hugepage_flag {
 	TRANSPARENT_HUGEPAGE_FLAG,
@@ -122,7 +124,7 @@ extern void split_huge_page_pmd_mm(struct mm_struct *mm, unsigned long address,
 #endif
 extern int hugepage_madvise(struct vm_area_struct *vma,
 			    unsigned long *vm_flags, int advice);
-extern void __vma_adjust_trans_huge(struct vm_area_struct *vma,
+extern void vma_adjust_trans_huge(struct vm_area_struct *vma,
 				    unsigned long start,
 				    unsigned long end,
 				    long adjust_next);
@@ -138,15 +140,6 @@ static inline int pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
 	else
 		return 0;
 }
-static inline void vma_adjust_trans_huge(struct vm_area_struct *vma,
-					 unsigned long start,
-					 unsigned long end,
-					 long adjust_next)
-{
-	if (!vma->anon_vma || vma->vm_ops)
-		return;
-	__vma_adjust_trans_huge(vma, start, end, adjust_next);
-}
 static inline int hpage_nr_pages(struct page *page)
 {
 	if (unlikely(PageTransHuge(page)))
@@ -164,6 +157,13 @@ static inline bool is_huge_zero_page(struct page *page)
 	return ACCESS_ONCE(huge_zero_page) == page;
 }
 
+static inline bool is_huge_zero_pmd(pmd_t pmd)
+{
+	return is_huge_zero_page(pmd_page(pmd));
+}
+
+struct page *get_huge_zero_page(void);
+
 #else /* CONFIG_TRANSPARENT_HUGEPAGE */
 #define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; })
 #define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; })

include/linux/hugetlb.h

@@ -35,6 +35,9 @@ struct resv_map {
 	struct kref refs;
 	spinlock_t lock;
 	struct list_head regions;
+	long adds_in_progress;
+	struct list_head region_cache;
+	long region_cache_count;
 };
 extern struct resv_map *resv_map_alloc(void);
 void resv_map_release(struct kref *ref);
@@ -80,11 +83,18 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 int hugetlb_reserve_pages(struct inode *inode, long from, long to,
 						struct vm_area_struct *vma,
 						vm_flags_t vm_flags);
-void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed);
+long hugetlb_unreserve_pages(struct inode *inode, long start, long end,
+						long freed);
 int dequeue_hwpoisoned_huge_page(struct page *page);
 bool isolate_huge_page(struct page *page, struct list_head *list);
 void putback_active_hugepage(struct page *page);
 void free_huge_page(struct page *page);
+void hugetlb_fix_reserve_counts(struct inode *inode, bool restore_reserve);
+extern struct mutex *hugetlb_fault_mutex_table;
+u32 hugetlb_fault_mutex_hash(struct hstate *h, struct mm_struct *mm,
+				struct vm_area_struct *vma,
+				struct address_space *mapping,
+				pgoff_t idx, unsigned long address);
 
 #ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE
 pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud);
@@ -320,9 +330,13 @@ struct huge_bootmem_page {
 #endif
 };
 
+struct page *alloc_huge_page(struct vm_area_struct *vma,
+				unsigned long addr, int avoid_reserve);
 struct page *alloc_huge_page_node(struct hstate *h, int nid);
 struct page *alloc_huge_page_noerr(struct vm_area_struct *vma,
 				unsigned long addr, int avoid_reserve);
+int huge_add_to_page_cache(struct page *page, struct address_space *mapping,
+			pgoff_t idx);
 
 /* arch callback */
 int __init alloc_bootmem_huge_page(struct hstate *h);
@@ -471,6 +485,7 @@ static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
 
 #else	/* CONFIG_HUGETLB_PAGE */
 struct hstate {};
+#define alloc_huge_page(v, a, r) NULL
 #define alloc_huge_page_node(h, nid) NULL
 #define alloc_huge_page_noerr(v, a, r) NULL
 #define alloc_bootmem_huge_page(h) NULL

include/linux/memblock.h

@@ -77,6 +77,8 @@ int memblock_remove(phys_addr_t base, phys_addr_t size);
 int memblock_free(phys_addr_t base, phys_addr_t size);
 int memblock_reserve(phys_addr_t base, phys_addr_t size);
 void memblock_trim_memory(phys_addr_t align);
+bool memblock_overlaps_region(struct memblock_type *type,
+			      phys_addr_t base, phys_addr_t size);
 int memblock_mark_hotplug(phys_addr_t base, phys_addr_t size);
 int memblock_clear_hotplug(phys_addr_t base, phys_addr_t size);
 int memblock_mark_mirror(phys_addr_t base, phys_addr_t size);
@@ -323,7 +325,7 @@ void memblock_enforce_memory_limit(phys_addr_t memory_limit);
 int memblock_is_memory(phys_addr_t addr);
 int memblock_is_region_memory(phys_addr_t base, phys_addr_t size);
 int memblock_is_reserved(phys_addr_t addr);
-int memblock_is_region_reserved(phys_addr_t base, phys_addr_t size);
+bool memblock_is_region_reserved(phys_addr_t base, phys_addr_t size);
 
 extern void __memblock_dump_all(void);
 

include/linux/memcontrol.h

@@ -23,6 +23,11 @@
 #include <linux/vm_event_item.h>
 #include <linux/hardirq.h>
 #include <linux/jump_label.h>
+#include <linux/page_counter.h>
+#include <linux/vmpressure.h>
+#include <linux/eventfd.h>
+#include <linux/mmzone.h>
+#include <linux/writeback.h>
 
 struct mem_cgroup;
 struct page;
@@ -67,12 +72,221 @@ enum mem_cgroup_events_index {
 	MEMCG_NR_EVENTS,
 };
 
+/*
+ * Per memcg event counter is incremented at every pagein/pageout. With THP,
+ * it will be incremated by the number of pages. This counter is used for
+ * for trigger some periodic events. This is straightforward and better
+ * than using jiffies etc. to handle periodic memcg event.
+ */
+enum mem_cgroup_events_target {
+	MEM_CGROUP_TARGET_THRESH,
+	MEM_CGROUP_TARGET_SOFTLIMIT,
+	MEM_CGROUP_TARGET_NUMAINFO,
+	MEM_CGROUP_NTARGETS,
+};
+
+/*
+ * Bits in struct cg_proto.flags
+ */
+enum cg_proto_flags {
+	/* Currently active and new sockets should be assigned to cgroups */
+	MEMCG_SOCK_ACTIVE,
+	/* It was ever activated; we must disarm static keys on destruction */
+	MEMCG_SOCK_ACTIVATED,
+};
+
+struct cg_proto {
+	struct page_counter	memory_allocated;	/* Current allocated memory. */
+	struct percpu_counter	sockets_allocated;	/* Current number of sockets. */
+	int			memory_pressure;
+	long			sysctl_mem[3];
+	unsigned long		flags;
+	/*
+	 * memcg field is used to find which memcg we belong directly
+	 * Each memcg struct can hold more than one cg_proto, so container_of
+	 * won't really cut.
+	 *
+	 * The elegant solution would be having an inverse function to
+	 * proto_cgroup in struct proto, but that means polluting the structure
+	 * for everybody, instead of just for memcg users.
+	 */
+	struct mem_cgroup	*memcg;
+};
+
 #ifdef CONFIG_MEMCG
+struct mem_cgroup_stat_cpu {
+	long count[MEM_CGROUP_STAT_NSTATS];
+	unsigned long events[MEMCG_NR_EVENTS];
+	unsigned long nr_page_events;
+	unsigned long targets[MEM_CGROUP_NTARGETS];
+};
+
+struct mem_cgroup_reclaim_iter {
+	struct mem_cgroup *position;
+	/* scan generation, increased every round-trip */
+	unsigned int generation;
+};
+
+/*
+ * per-zone information in memory controller.
+ */
+struct mem_cgroup_per_zone {
+	struct lruvec		lruvec;
+	unsigned long		lru_size[NR_LRU_LISTS];
+
+	struct mem_cgroup_reclaim_iter	iter[DEF_PRIORITY + 1];
+
+	struct rb_node		tree_node;	/* RB tree node */
+	unsigned long		usage_in_excess;/* Set to the value by which */
+						/* the soft limit is exceeded*/
+	bool			on_tree;
+	struct mem_cgroup	*memcg;		/* Back pointer, we cannot */
+						/* use container_of	   */
+};
+
+struct mem_cgroup_per_node {
+	struct mem_cgroup_per_zone zoneinfo[MAX_NR_ZONES];
+};
+
+struct mem_cgroup_threshold {
+	struct eventfd_ctx *eventfd;
+	unsigned long threshold;
+};
+
+/* For threshold */
+struct mem_cgroup_threshold_ary {
+	/* An array index points to threshold just below or equal to usage. */
+	int current_threshold;
+	/* Size of entries[] */
+	unsigned int size;
+	/* Array of thresholds */
+	struct mem_cgroup_threshold entries[0];
+};
+
+struct mem_cgroup_thresholds {
+	/* Primary thresholds array */
+	struct mem_cgroup_threshold_ary *primary;
+	/*
+	 * Spare threshold array.
+	 * This is needed to make mem_cgroup_unregister_event() "never fail".
+	 * It must be able to store at least primary->size - 1 entries.
+	 */
+	struct mem_cgroup_threshold_ary *spare;
+};
+
+/*
+ * The memory controller data structure. The memory controller controls both
+ * page cache and RSS per cgroup. We would eventually like to provide
+ * statistics based on the statistics developed by Rik Van Riel for clock-pro,
+ * to help the administrator determine what knobs to tune.
+ */
+struct mem_cgroup {
+	struct cgroup_subsys_state css;
+
+	/* Accounted resources */
+	struct page_counter memory;
+	struct page_counter memsw;
+	struct page_counter kmem;
+
+	/* Normal memory consumption range */
+	unsigned long low;
+	unsigned long high;
+
+	unsigned long soft_limit;
+
+	/* vmpressure notifications */
+	struct vmpressure vmpressure;
+
+	/* css_online() has been completed */
+	int initialized;
+
+	/*
+	 * Should the accounting and control be hierarchical, per subtree?
+	 */
+	bool use_hierarchy;
+
+	/* protected by memcg_oom_lock */
+	bool		oom_lock;
+	int		under_oom;
+
+	int	swappiness;
+	/* OOM-Killer disable */
+	int		oom_kill_disable;
+
+	/* protect arrays of thresholds */
+	struct mutex thresholds_lock;
+
+	/* thresholds for memory usage. RCU-protected */
+	struct mem_cgroup_thresholds thresholds;
+
+	/* thresholds for mem+swap usage. RCU-protected */
+	struct mem_cgroup_thresholds memsw_thresholds;
+
+	/* For oom notifier event fd */
+	struct list_head oom_notify;
+
+	/*
+	 * Should we move charges of a task when a task is moved into this
+	 * mem_cgroup ? And what type of charges should we move ?
+	 */
+	unsigned long move_charge_at_immigrate;
+	/*
+	 * set > 0 if pages under this cgroup are moving to other cgroup.
+	 */
+	atomic_t		moving_account;
+	/* taken only while moving_account > 0 */
+	spinlock_t		move_lock;
+	struct task_struct	*move_lock_task;
+	unsigned long		move_lock_flags;
+	/*
+	 * percpu counter.
+	 */
+	struct mem_cgroup_stat_cpu __percpu *stat;
+	spinlock_t pcp_counter_lock;
+
+#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_INET)
+	struct cg_proto tcp_mem;
+#endif
+#if defined(CONFIG_MEMCG_KMEM)
+        /* Index in the kmem_cache->memcg_params.memcg_caches array */
+	int kmemcg_id;
+	bool kmem_acct_activated;
+	bool kmem_acct_active;
+#endif
+
+	int last_scanned_node;
+#if MAX_NUMNODES > 1
+	nodemask_t	scan_nodes;
+	atomic_t	numainfo_events;
+	atomic_t	numainfo_updating;
+#endif
+
+#ifdef CONFIG_CGROUP_WRITEBACK
+	struct list_head cgwb_list;
+	struct wb_domain cgwb_domain;
+#endif
+
+	/* List of events which userspace want to receive */
+	struct list_head event_list;
+	spinlock_t event_list_lock;
+
+	struct mem_cgroup_per_node *nodeinfo[0];
+	/* WARNING: nodeinfo must be the last member here */
+};
 extern struct cgroup_subsys_state *mem_cgroup_root_css;
 
-void mem_cgroup_events(struct mem_cgroup *memcg,
+/**
+ * mem_cgroup_events - count memory events against a cgroup
+ * @memcg: the memory cgroup
+ * @idx: the event index
+ * @nr: the number of events to account for
+ */
+static inline void mem_cgroup_events(struct mem_cgroup *memcg,
 		       enum mem_cgroup_events_index idx,
-		       unsigned int nr);
+		       unsigned int nr)
+{
+	this_cpu_add(memcg->stat->events[idx], nr);
+}
 
 bool mem_cgroup_low(struct mem_cgroup *root, struct mem_cgroup *memcg);
 
@@ -90,15 +304,31 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage,
 struct lruvec *mem_cgroup_zone_lruvec(struct zone *, struct mem_cgroup *);
 struct lruvec *mem_cgroup_page_lruvec(struct page *, struct zone *);
 
-bool mem_cgroup_is_descendant(struct mem_cgroup *memcg,
-			      struct mem_cgroup *root);
 bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg);
 
-extern struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page);
-extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
+struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page);
+struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
+
+struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg);
+static inline
+struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){
+	return css ? container_of(css, struct mem_cgroup, css) : NULL;
+}
+
+struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *,
+				   struct mem_cgroup *,
+				   struct mem_cgroup_reclaim_cookie *);
+void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *);
 
-extern struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg);
-extern struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css);
+static inline bool mem_cgroup_is_descendant(struct mem_cgroup *memcg,
+			      struct mem_cgroup *root)
+{
+	if (root == memcg)
+		return true;
+	if (!root->use_hierarchy)
+		return false;
+	return cgroup_is_descendant(memcg->css.cgroup, root->css.cgroup);
+}
 
 static inline bool mm_match_cgroup(struct mm_struct *mm,
 				   struct mem_cgroup *memcg)
@@ -114,24 +344,67 @@ static inline bool mm_match_cgroup(struct mm_struct *mm,
 	return match;
 }
 
-extern struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg);
-extern struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page);
+struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page);
 
-struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *,
-				   struct mem_cgroup *,
-				   struct mem_cgroup_reclaim_cookie *);
-void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *);
+static inline bool mem_cgroup_disabled(void)
+{
+	if (memory_cgrp_subsys.disabled)
+		return true;
+	return false;
+}
 
 /*
  * For memory reclaim.
  */
-int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec);
-bool mem_cgroup_lruvec_online(struct lruvec *lruvec);
 int mem_cgroup_select_victim_node(struct mem_cgroup *memcg);
-unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list);
-void mem_cgroup_update_lru_size(struct lruvec *, enum lru_list, int);
-extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg,
-					struct task_struct *p);
+
+void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
+		int nr_pages);
+
+static inline bool mem_cgroup_lruvec_online(struct lruvec *lruvec)
+{
+	struct mem_cgroup_per_zone *mz;
+	struct mem_cgroup *memcg;
+
+	if (mem_cgroup_disabled())
+		return true;
+
+	mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec);
+	memcg = mz->memcg;
+
+	return !!(memcg->css.flags & CSS_ONLINE);
+}
+
+static inline
+unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru)
+{
+	struct mem_cgroup_per_zone *mz;
+
+	mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec);
+	return mz->lru_size[lru];
+}
+
+static inline int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec)
+{
+	unsigned long inactive_ratio;
+	unsigned long inactive;
+	unsigned long active;
+	unsigned long gb;
+
+	inactive = mem_cgroup_get_lru_size(lruvec, LRU_INACTIVE_ANON);
+	active = mem_cgroup_get_lru_size(lruvec, LRU_ACTIVE_ANON);
+
+	gb = (inactive + active) >> (30 - PAGE_SHIFT);
+	if (gb)
+		inactive_ratio = int_sqrt(10 * gb);
+	else
+		inactive_ratio = 1;
+
+	return inactive * inactive_ratio < active;
+}
+
+void mem_cgroup_print_oom_info(struct mem_cgroup *memcg,
+				struct task_struct *p);
 
 static inline void mem_cgroup_oom_enable(void)
 {
@@ -156,18 +429,26 @@ bool mem_cgroup_oom_synchronize(bool wait);
 extern int do_swap_account;
 #endif
 
-static inline bool mem_cgroup_disabled(void)
-{
-	if (memory_cgrp_subsys.disabled)
-		return true;
-	return false;
-}
-
 struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page);
-void mem_cgroup_update_page_stat(struct mem_cgroup *memcg,
-				 enum mem_cgroup_stat_index idx, int val);
 void mem_cgroup_end_page_stat(struct mem_cgroup *memcg);
 
+/**
+ * mem_cgroup_update_page_stat - update page state statistics
+ * @memcg: memcg to account against
+ * @idx: page state item to account
+ * @val: number of pages (positive or negative)
+ *
+ * See mem_cgroup_begin_page_stat() for locking requirements.
+ */
+static inline void mem_cgroup_update_page_stat(struct mem_cgroup *memcg,
+				 enum mem_cgroup_stat_index idx, int val)
+{
+	VM_BUG_ON(!rcu_read_lock_held());
+
+	if (memcg)
+		this_cpu_add(memcg->stat->count[idx], val);
+}
+
 static inline void mem_cgroup_inc_page_stat(struct mem_cgroup *memcg,
 					    enum mem_cgroup_stat_index idx)
 {
@@ -184,13 +465,31 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
 						gfp_t gfp_mask,
 						unsigned long *total_scanned);
 
-void __mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx);
 static inline void mem_cgroup_count_vm_event(struct mm_struct *mm,
 					     enum vm_event_item idx)
 {
+	struct mem_cgroup *memcg;
+
 	if (mem_cgroup_disabled())
 		return;
-	__mem_cgroup_count_vm_event(mm, idx);
+
+	rcu_read_lock();
+	memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
+	if (unlikely(!memcg))
+		goto out;
+
+	switch (idx) {
+	case PGFAULT:
+		this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGFAULT]);
+		break;
+	case PGMAJFAULT:
+		this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGMAJFAULT]);
+		break;
+	default:
+		BUG();
+	}
+out:
+	rcu_read_unlock();
 }
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 void mem_cgroup_split_huge_fixup(struct page *head);
@@ -199,8 +498,6 @@ void mem_cgroup_split_huge_fixup(struct page *head);
 #else /* CONFIG_MEMCG */
 struct mem_cgroup;
 
-#define mem_cgroup_root_css ((struct cgroup_subsys_state *)ERR_PTR(-EINVAL))
-
 static inline void mem_cgroup_events(struct mem_cgroup *memcg,
 				     enum mem_cgroup_events_index idx,
 				     unsigned int nr)
@@ -275,12 +572,6 @@ static inline bool task_in_mem_cgroup(struct task_struct *task,
 	return true;
 }
 
-static inline struct cgroup_subsys_state
-		*mem_cgroup_css(struct mem_cgroup *memcg)
-{
-	return NULL;
-}
-
 static inline struct mem_cgroup *
 mem_cgroup_iter(struct mem_cgroup *root,
 		struct mem_cgroup *prev,
@@ -428,8 +719,8 @@ static inline void sock_release_memcg(struct sock *sk)
 extern struct static_key memcg_kmem_enabled_key;
 
 extern int memcg_nr_cache_ids;
-extern void memcg_get_cache_ids(void);
-extern void memcg_put_cache_ids(void);
+void memcg_get_cache_ids(void);
+void memcg_put_cache_ids(void);
 
 /*
  * Helper macro to loop through all memcg-specific caches. Callers must still
@@ -444,7 +735,10 @@ static inline bool memcg_kmem_enabled(void)
 	return static_key_false(&memcg_kmem_enabled_key);
 }
 
-bool memcg_kmem_is_active(struct mem_cgroup *memcg);
+static inline bool memcg_kmem_is_active(struct mem_cgroup *memcg)
+{
+	return memcg->kmem_acct_active;
+}
 
 /*
  * In general, we'll do everything in our power to not incur in any overhead
@@ -463,7 +757,15 @@ void __memcg_kmem_commit_charge(struct page *page,
 				       struct mem_cgroup *memcg, int order);
 void __memcg_kmem_uncharge_pages(struct page *page, int order);
 
-int memcg_cache_id(struct mem_cgroup *memcg);
+/*
+ * helper for acessing a memcg's index. It will be used as an index in the
+ * child cache array in kmem_cache, and also to derive its name. This function
+ * will return -1 when this is not a kmem-limited memcg.
+ */
+static inline int memcg_cache_id(struct mem_cgroup *memcg)
+{
+	return memcg ? memcg->kmemcg_id : -1;
+}
 
 struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep);
 void __memcg_kmem_put_cache(struct kmem_cache *cachep);

include/linux/mm.h

@@ -249,6 +249,8 @@ struct vm_operations_struct {
 	void (*close)(struct vm_area_struct * area);
 	int (*mremap)(struct vm_area_struct * area);
 	int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf);
+	int (*pmd_fault)(struct vm_area_struct *, unsigned long address,
+						pmd_t *, unsigned int flags);
 	void (*map_pages)(struct vm_area_struct *vma, struct vm_fault *vmf);
 
 	/* notification that a previously read-only page is about to become
@@ -307,18 +309,6 @@ struct inode;
 #define page_private(page)		((page)->private)
 #define set_page_private(page, v)	((page)->private = (v))
 
-/* It's valid only if the page is free path or free_list */
-static inline void set_freepage_migratetype(struct page *page, int migratetype)
-{
-	page->index = migratetype;
-}
-
-/* It's valid only if the page is free path or free_list */
-static inline int get_freepage_migratetype(struct page *page)
-{
-	return page->index;
-}
-
 /*
  * FIXME: take this include out, include page-flags.h in
  * files which need it (119 of them)
@@ -359,18 +349,6 @@ static inline int get_page_unless_zero(struct page *page)
 	return atomic_inc_not_zero(&page->_count);
 }
 
-/*
- * Try to drop a ref unless the page has a refcount of one, return false if
- * that is the case.
- * This is to make sure that the refcount won't become zero after this drop.
- * This can be called when MMU is off so it must not access
- * any of the virtual mappings.
- */
-static inline int put_page_unless_one(struct page *page)
-{
-	return atomic_add_unless(&page->_count, -1, 1);
-}
-
 extern int page_is_ram(unsigned long pfn);
 
 enum {
@@ -1267,6 +1245,11 @@ static inline int vma_growsdown(struct vm_area_struct *vma, unsigned long addr)
 	return vma && (vma->vm_end == addr) && (vma->vm_flags & VM_GROWSDOWN);
 }
 
+static inline bool vma_is_anonymous(struct vm_area_struct *vma)
+{
+	return !vma->vm_ops;
+}
+
 static inline int stack_guard_page_start(struct vm_area_struct *vma,
 					     unsigned long addr)
 {
@@ -2193,6 +2176,7 @@ extern int memory_failure(unsigned long pfn, int trapno, int flags);
 extern void memory_failure_queue(unsigned long pfn, int trapno, int flags);
 extern int unpoison_memory(unsigned long pfn);
 extern int get_hwpoison_page(struct page *page);
+extern void put_hwpoison_page(struct page *page);
 extern int sysctl_memory_failure_early_kill;
 extern int sysctl_memory_failure_recovery;
 extern void shake_page(struct page *p, int access);

include/linux/mm_types.h

@@ -235,7 +235,7 @@ struct page_frag_cache {
 	bool pfmemalloc;
 };
 
-typedef unsigned long __nocast vm_flags_t;
+typedef unsigned long vm_flags_t;
 
 /*
  * A region containing a mapping of a non-memory backed file under NOMMU

include/linux/oom.h

@@ -12,6 +12,27 @@ struct notifier_block;
 struct mem_cgroup;
 struct task_struct;
 
+/*
+ * Details of the page allocation that triggered the oom killer that are used to
+ * determine what should be killed.
+ */
+struct oom_control {
+	/* Used to determine cpuset */
+	struct zonelist *zonelist;
+
+	/* Used to determine mempolicy */
+	nodemask_t *nodemask;
+
+	/* Used to determine cpuset and node locality requirement */
+	const gfp_t gfp_mask;
+
+	/*
+	 * order == -1 means the oom kill is required by sysrq, otherwise only
+	 * for display purposes.
+	 */
+	const int order;
+};
+
 /*
  * Types of limitations to the nodes from which allocations may occur
  */
@@ -57,21 +78,18 @@ extern unsigned long oom_badness(struct task_struct *p,
 
 extern int oom_kills_count(void);
 extern void note_oom_kill(void);
-extern void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
+extern void oom_kill_process(struct oom_control *oc, struct task_struct *p,
 			     unsigned int points, unsigned long totalpages,
-			     struct mem_cgroup *memcg, nodemask_t *nodemask,
-			     const char *message);
+			     struct mem_cgroup *memcg, const char *message);
 
-extern void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask,
-			       int order, const nodemask_t *nodemask,
+extern void check_panic_on_oom(struct oom_control *oc,
+			       enum oom_constraint constraint,
 			       struct mem_cgroup *memcg);
 
-extern enum oom_scan_t oom_scan_process_thread(struct task_struct *task,
-		unsigned long totalpages, const nodemask_t *nodemask,
-		bool force_kill);
+extern enum oom_scan_t oom_scan_process_thread(struct oom_control *oc,
+		struct task_struct *task, unsigned long totalpages);
 
-extern bool out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
-		int order, nodemask_t *mask, bool force_kill);
+extern bool out_of_memory(struct oom_control *oc);
 
 extern void exit_oom_victim(void);
 

include/linux/page-isolation.h

@@ -65,11 +65,6 @@ undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn,
 			bool skip_hwpoisoned_pages);
 
-/*
- * Internal functions. Changes pageblock's migrate type.
- */
-int set_migratetype_isolate(struct page *page, bool skip_hwpoisoned_pages);
-void unset_migratetype_isolate(struct page *page, unsigned migratetype);
 struct page *alloc_migrate_target(struct page *page, unsigned long private,
 				int **resultp);
 

include/linux/pci.h

@@ -1227,6 +1227,8 @@ int pci_set_vga_state(struct pci_dev *pdev, bool decode,
 		dma_pool_create(name, &pdev->dev, size, align, allocation)
 #define	pci_pool_destroy(pool) dma_pool_destroy(pool)
 #define	pci_pool_alloc(pool, flags, handle) dma_pool_alloc(pool, flags, handle)
+#define	pci_pool_zalloc(pool, flags, handle) \
+		dma_pool_zalloc(pool, flags, handle)
 #define	pci_pool_free(pool, vaddr, addr) dma_pool_free(pool, vaddr, addr)
 
 struct msix_entry {

include/linux/swap.h

@@ -351,7 +351,15 @@ extern void check_move_unevictable_pages(struct page **, int nr_pages);
 extern int kswapd_run(int nid);
 extern void kswapd_stop(int nid);
 #ifdef CONFIG_MEMCG
-extern int mem_cgroup_swappiness(struct mem_cgroup *mem);
+static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg)
+{
+	/* root ? */
+	if (mem_cgroup_disabled() || !memcg->css.parent)
+		return vm_swappiness;
+
+	return memcg->swappiness;
+}
+
 #else
 static inline int mem_cgroup_swappiness(struct mem_cgroup *mem)
 {
@@ -398,6 +406,9 @@ extern void free_pages_and_swap_cache(struct page **, int);
 extern struct page *lookup_swap_cache(swp_entry_t);
 extern struct page *read_swap_cache_async(swp_entry_t, gfp_t,
 			struct vm_area_struct *vma, unsigned long addr);
+extern struct page *__read_swap_cache_async(swp_entry_t, gfp_t,
+			struct vm_area_struct *vma, unsigned long addr,
+			bool *new_page_allocated);
 extern struct page *swapin_readahead(swp_entry_t, gfp_t,
 			struct vm_area_struct *vma, unsigned long addr);
 
@@ -431,6 +442,7 @@ extern unsigned int count_swap_pages(int, int);
 extern sector_t map_swap_page(struct page *, struct block_device **);
 extern sector_t swapdev_block(int, pgoff_t);
 extern int page_swapcount(struct page *);
+extern int swp_swapcount(swp_entry_t entry);
 extern struct swap_info_struct *page_swap_info(struct page *);
 extern int reuse_swap_page(struct page *);
 extern int try_to_free_swap(struct page *);
@@ -522,6 +534,11 @@ static inline int page_swapcount(struct page *page)
 	return 0;
 }
 
+static inline int swp_swapcount(swp_entry_t entry)
+{
+	return 0;
+}
+
 #define reuse_swap_page(page)	(page_mapcount(page) == 1)
 
 static inline int try_to_free_swap(struct page *page)

include/linux/swapops.h

@@ -164,6 +164,9 @@ static inline int is_write_migration_entry(swp_entry_t entry)
 #endif
 
 #ifdef CONFIG_MEMORY_FAILURE
+
+extern atomic_long_t num_poisoned_pages __read_mostly;
+
 /*
  * Support for hardware poisoned pages
  */
@@ -177,6 +180,31 @@ static inline int is_hwpoison_entry(swp_entry_t entry)
 {
 	return swp_type(entry) == SWP_HWPOISON;
 }
+
+static inline bool test_set_page_hwpoison(struct page *page)
+{
+	return TestSetPageHWPoison(page);
+}
+
+static inline void num_poisoned_pages_inc(void)
+{
+	atomic_long_inc(&num_poisoned_pages);
+}
+
+static inline void num_poisoned_pages_dec(void)
+{
+	atomic_long_dec(&num_poisoned_pages);
+}
+
+static inline void num_poisoned_pages_add(long num)
+{
+	atomic_long_add(num, &num_poisoned_pages);
+}
+
+static inline void num_poisoned_pages_sub(long num)
+{
+	atomic_long_sub(num, &num_poisoned_pages);
+}
 #else
 
 static inline swp_entry_t make_hwpoison_entry(struct page *page)
@@ -188,6 +216,15 @@ static inline int is_hwpoison_entry(swp_entry_t swp)
 {
 	return 0;
 }
+
+static inline bool test_set_page_hwpoison(struct page *page)
+{
+	return false;
+}
+
+static inline void num_poisoned_pages_inc(void)
+{
+}
 #endif
 
 #if defined(CONFIG_MEMORY_FAILURE) || defined(CONFIG_MIGRATION)

include/linux/zbud.h

@@ -9,7 +9,7 @@ struct zbud_ops {
 	int (*evict)(struct zbud_pool *pool, unsigned long handle);
 };
 
-struct zbud_pool *zbud_create_pool(gfp_t gfp, struct zbud_ops *ops);
+struct zbud_pool *zbud_create_pool(gfp_t gfp, const struct zbud_ops *ops);
 void zbud_destroy_pool(struct zbud_pool *pool);
 int zbud_alloc(struct zbud_pool *pool, size_t size, gfp_t gfp,
 	unsigned long *handle);

include/linux/zpool.h

@@ -37,7 +37,7 @@ enum zpool_mapmode {
 };
 
 struct zpool *zpool_create_pool(char *type, char *name,
-			gfp_t gfp, struct zpool_ops *ops);
+			gfp_t gfp, const struct zpool_ops *ops);
 
 char *zpool_get_type(struct zpool *pool);
 
@@ -81,7 +81,7 @@ struct zpool_driver {
 	atomic_t refcount;
 	struct list_head list;
 
-	void *(*create)(char *name, gfp_t gfp, struct zpool_ops *ops,
+	void *(*create)(char *name, gfp_t gfp, const struct zpool_ops *ops,
 			struct zpool *zpool);
 	void (*destroy)(void *pool);
 

include/linux/zsmalloc.h

@@ -34,6 +34,11 @@ enum zs_mapmode {
 	 */
 };
 
+struct zs_pool_stats {
+	/* How many pages were migrated (freed) */
+	unsigned long pages_compacted;
+};
+
 struct zs_pool;
 
 struct zs_pool *zs_create_pool(char *name, gfp_t flags);
@@ -49,4 +54,5 @@ void zs_unmap_object(struct zs_pool *pool, unsigned long handle);
 unsigned long zs_get_total_pages(struct zs_pool *pool);
 unsigned long zs_compact(struct zs_pool *pool);
 
+void zs_pool_stats(struct zs_pool *pool, struct zs_pool_stats *stats);
 #endif

include/net/sock.h

@@ -1042,42 +1042,9 @@ struct proto {
 #endif
 };
 
-/*
- * Bits in struct cg_proto.flags
- */
-enum cg_proto_flags {
-	/* Currently active and new sockets should be assigned to cgroups */
-	MEMCG_SOCK_ACTIVE,
-	/* It was ever activated; we must disarm static keys on destruction */
-	MEMCG_SOCK_ACTIVATED,
-};
-
-struct cg_proto {
-	struct page_counter	memory_allocated;	/* Current allocated memory. */
-	struct percpu_counter	sockets_allocated;	/* Current number of sockets. */
-	int			memory_pressure;
-	long			sysctl_mem[3];
-	unsigned long		flags;
-	/*
-	 * memcg field is used to find which memcg we belong directly
-	 * Each memcg struct can hold more than one cg_proto, so container_of
-	 * won't really cut.
-	 *
-	 * The elegant solution would be having an inverse function to
-	 * proto_cgroup in struct proto, but that means polluting the structure
-	 * for everybody, instead of just for memcg users.
-	 */
-	struct mem_cgroup	*memcg;
-};
-
 int proto_register(struct proto *prot, int alloc_slab);
 void proto_unregister(struct proto *prot);
 
-static inline bool memcg_proto_active(struct cg_proto *cg_proto)
-{
-	return test_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags);
-}
-
 #ifdef SOCK_REFCNT_DEBUG
 static inline void sk_refcnt_debug_inc(struct sock *sk)
 {

kernel/cgroup.c

@@ -1342,7 +1342,7 @@ static int cgroup_show_options(struct seq_file *seq,
 	if (root != &cgrp_dfl_root)
 		for_each_subsys(ss, ssid)
 			if (root->subsys_mask & (1 << ssid))
-				seq_show_option(seq, ss->name, NULL);
+				seq_show_option(seq, ss->legacy_name, NULL);
 	if (root->flags & CGRP_ROOT_NOPREFIX)
 		seq_puts(seq, ",noprefix");
 	if (root->flags & CGRP_ROOT_XATTR)

kernel/profile.c

@@ -339,7 +339,7 @@ static int profile_cpu_callback(struct notifier_block *info,
 		node = cpu_to_mem(cpu);
 		per_cpu(cpu_profile_flip, cpu) = 0;
 		if (!per_cpu(cpu_profile_hits, cpu)[1]) {
-			page = alloc_pages_exact_node(node,
+			page = __alloc_pages_node(node,
 					GFP_KERNEL | __GFP_ZERO,
 					0);
 			if (!page)
@@ -347,7 +347,7 @@ static int profile_cpu_callback(struct notifier_block *info,
 			per_cpu(cpu_profile_hits, cpu)[1] = page_address(page);
 		}
 		if (!per_cpu(cpu_profile_hits, cpu)[0]) {
-			page = alloc_pages_exact_node(node,
+			page = __alloc_pages_node(node,
 					GFP_KERNEL | __GFP_ZERO,
 					0);
 			if (!page)
@@ -543,14 +543,14 @@ static int create_hash_tables(void)
 		int node = cpu_to_mem(cpu);
 		struct page *page;
 
-		page = alloc_pages_exact_node(node,
+		page = __alloc_pages_node(node,
 				GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE,
 				0);
 		if (!page)
 			goto out_cleanup;
 		per_cpu(cpu_profile_hits, cpu)[1]
 				= (struct profile_hit *)page_address(page);
-		page = alloc_pages_exact_node(node,
+		page = __alloc_pages_node(node,
 				GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE,
 				0);
 		if (!page)

lib/show_mem.c

@@ -38,11 +38,9 @@ void show_mem(unsigned int filter)
 
 	printk("%lu pages RAM\n", total);
 	printk("%lu pages HighMem/MovableOnly\n", highmem);
+	printk("%lu pages reserved\n", reserved);
 #ifdef CONFIG_CMA
-	printk("%lu pages reserved\n", (reserved - totalcma_pages));
 	printk("%lu pages cma reserved\n", totalcma_pages);
-#else
-	printk("%lu pages reserved\n", reserved);
 #endif
 #ifdef CONFIG_QUICKLIST
 	printk("%lu pages in pagetable cache\n",

mm/bootmem.c

@@ -236,6 +236,7 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
 	count += pages;
 	while (pages--)
 		__free_pages_bootmem(page++, cur++, 0);
+	bdata->node_bootmem_map = NULL;
 
 	bdebug("nid=%td released=%lx\n", bdata - bootmem_node_data, count);
 
@@ -294,6 +295,9 @@ static void __init __free(bootmem_data_t *bdata,
 		sidx + bdata->node_min_pfn,
 		eidx + bdata->node_min_pfn);
 
+	if (WARN_ON(bdata->node_bootmem_map == NULL))
+		return;
+
 	if (bdata->hint_idx > sidx)
 		bdata->hint_idx = sidx;
 
@@ -314,6 +318,9 @@ static int __init __reserve(bootmem_data_t *bdata, unsigned long sidx,
 		eidx + bdata->node_min_pfn,
 		flags);
 
+	if (WARN_ON(bdata->node_bootmem_map == NULL))
+		return 0;
+
 	for (idx = sidx; idx < eidx; idx++)
 		if (test_and_set_bit(idx, bdata->node_bootmem_map)) {
 			if (exclusive) {

mm/compaction.c

@@ -207,6 +207,13 @@ static inline bool isolation_suitable(struct compact_control *cc,
 	return !get_pageblock_skip(page);
 }
 
+static void reset_cached_positions(struct zone *zone)
+{
+	zone->compact_cached_migrate_pfn[0] = zone->zone_start_pfn;
+	zone->compact_cached_migrate_pfn[1] = zone->zone_start_pfn;
+	zone->compact_cached_free_pfn = zone_end_pfn(zone);
+}
+
 /*
  * This function is called to clear all cached information on pageblocks that
  * should be skipped for page isolation when the migrate and free page scanner
@@ -218,9 +225,6 @@ static void __reset_isolation_suitable(struct zone *zone)
 	unsigned long end_pfn = zone_end_pfn(zone);
 	unsigned long pfn;
 
-	zone->compact_cached_migrate_pfn[0] = start_pfn;
-	zone->compact_cached_migrate_pfn[1] = start_pfn;
-	zone->compact_cached_free_pfn = end_pfn;
 	zone->compact_blockskip_flush = false;
 
 	/* Walk the zone and mark every pageblock as suitable for isolation */
@@ -238,6 +242,8 @@ static void __reset_isolation_suitable(struct zone *zone)
 
 		clear_pageblock_skip(page);
 	}
+
+	reset_cached_positions(zone);
 }
 
 void reset_isolation_suitable(pg_data_t *pgdat)
@@ -431,6 +437,24 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 
 		if (!valid_page)
 			valid_page = page;
+
+		/*
+		 * For compound pages such as THP and hugetlbfs, we can save
+		 * potentially a lot of iterations if we skip them at once.
+		 * The check is racy, but we can consider only valid values
+		 * and the only danger is skipping too much.
+		 */
+		if (PageCompound(page)) {
+			unsigned int comp_order = compound_order(page);
+
+			if (likely(comp_order < MAX_ORDER)) {
+				blockpfn += (1UL << comp_order) - 1;
+				cursor += (1UL << comp_order) - 1;
+			}
+
+			goto isolate_fail;
+		}
+
 		if (!PageBuddy(page))
 			goto isolate_fail;
 
@@ -490,6 +514,13 @@ isolate_fail:
 
 	}
 
+	/*
+	 * There is a tiny chance that we have read bogus compound_order(),
+	 * so be careful to not go outside of the pageblock.
+	 */
+	if (unlikely(blockpfn > end_pfn))
+		blockpfn = end_pfn;
+
 	trace_mm_compaction_isolate_freepages(*start_pfn, blockpfn,
 					nr_scanned, total_isolated);
 
@@ -674,6 +705,8 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 
 	/* Time to isolate some pages for migration */
 	for (; low_pfn < end_pfn; low_pfn++) {
+		bool is_lru;
+
 		/*
 		 * Periodically drop the lock (if held) regardless of its
 		 * contention, to give chance to IRQs. Abort async compaction
@@ -717,36 +750,35 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		 * It's possible to migrate LRU pages and balloon pages
 		 * Skip any other type of page
 		 */
-		if (!PageLRU(page)) {
+		is_lru = PageLRU(page);
+		if (!is_lru) {
 			if (unlikely(balloon_page_movable(page))) {
 				if (balloon_page_isolate(page)) {
 					/* Successfully isolated */
 					goto isolate_success;
 				}
 			}
-			continue;
 		}
 
 		/*
-		 * PageLRU is set. lru_lock normally excludes isolation
-		 * splitting and collapsing (collapsing has already happened
-		 * if PageLRU is set) but the lock is not necessarily taken
-		 * here and it is wasteful to take it just to check transhuge.
-		 * Check TransHuge without lock and skip the whole pageblock if
-		 * it's either a transhuge or hugetlbfs page, as calling
-		 * compound_order() without preventing THP from splitting the
-		 * page underneath us may return surprising results.
+		 * Regardless of being on LRU, compound pages such as THP and
+		 * hugetlbfs are not to be compacted. We can potentially save
+		 * a lot of iterations if we skip them at once. The check is
+		 * racy, but we can consider only valid values and the only
+		 * danger is skipping too much.
 		 */
-		if (PageTransHuge(page)) {
-			if (!locked)
-				low_pfn = ALIGN(low_pfn + 1,
-						pageblock_nr_pages) - 1;
-			else
-				low_pfn += (1 << compound_order(page)) - 1;
+		if (PageCompound(page)) {
+			unsigned int comp_order = compound_order(page);
+
+			if (likely(comp_order < MAX_ORDER))
+				low_pfn += (1UL << comp_order) - 1;
 
 			continue;
 		}
 
+		if (!is_lru)
+			continue;
+
 		/*
 		 * Migration will fail if an anonymous page is pinned in memory,
 		 * so avoid taking lru_lock and isolating it unnecessarily in an
@@ -763,11 +795,17 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 			if (!locked)
 				break;
 
-			/* Recheck PageLRU and PageTransHuge under lock */
+			/* Recheck PageLRU and PageCompound under lock */
 			if (!PageLRU(page))
 				continue;
-			if (PageTransHuge(page)) {
-				low_pfn += (1 << compound_order(page)) - 1;
+
+			/*
+			 * Page become compound since the non-locked check,
+			 * and it's on LRU. It can only be a THP so the order
+			 * is safe to read and it's 0 for tail pages.
+			 */
+			if (unlikely(PageCompound(page))) {
+				low_pfn += (1UL << compound_order(page)) - 1;
 				continue;
 			}
 		}
@@ -778,7 +816,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		if (__isolate_lru_page(page, isolate_mode) != 0)
 			continue;
 
-		VM_BUG_ON_PAGE(PageTransCompound(page), page);
+		VM_BUG_ON_PAGE(PageCompound(page), page);
 
 		/* Successfully isolated */
 		del_page_from_lru_list(page, lruvec, page_lru(page));
@@ -897,6 +935,16 @@ static bool suitable_migration_target(struct page *page)
 	return false;
 }
 
+/*
+ * Test whether the free scanner has reached the same or lower pageblock than
+ * the migration scanner, and compaction should thus terminate.
+ */
+static inline bool compact_scanners_met(struct compact_control *cc)
+{
+	return (cc->free_pfn >> pageblock_order)
+		<= (cc->migrate_pfn >> pageblock_order);
+}
+
 /*
  * Based on information in the current compact_control, find blocks
  * suitable for isolating free pages from and then isolate them.
@@ -933,8 +981,7 @@ static void isolate_freepages(struct compact_control *cc)
 	 * pages on cc->migratepages. We stop searching if the migrate
 	 * and free page scanners meet or enough free pages are isolated.
 	 */
-	for (; block_start_pfn >= low_pfn &&
-			cc->nr_migratepages > cc->nr_freepages;
+	for (; block_start_pfn >= low_pfn;
 				block_end_pfn = block_start_pfn,
 				block_start_pfn -= pageblock_nr_pages,
 				isolate_start_pfn = block_start_pfn) {
@@ -966,6 +1013,8 @@ static void isolate_freepages(struct compact_control *cc)
 					block_end_pfn, freelist, false);
 
 		/*
+		 * If we isolated enough freepages, or aborted due to async
+		 * compaction being contended, terminate the loop.
 		 * Remember where the free scanner should restart next time,
 		 * which is where isolate_freepages_block() left off.
 		 * But if it scanned the whole pageblock, isolate_start_pfn
@@ -974,27 +1023,31 @@ static void isolate_freepages(struct compact_control *cc)
 		 * In that case we will however want to restart at the start
 		 * of the previous pageblock.
 		 */
-		cc->free_pfn = (isolate_start_pfn < block_end_pfn) ?
-				isolate_start_pfn :
-				block_start_pfn - pageblock_nr_pages;
-
-		/*
-		 * isolate_freepages_block() might have aborted due to async
-		 * compaction being contended
-		 */
-		if (cc->contended)
+		if ((cc->nr_freepages >= cc->nr_migratepages)
+							|| cc->contended) {
+			if (isolate_start_pfn >= block_end_pfn)
+				isolate_start_pfn =
+					block_start_pfn - pageblock_nr_pages;
 			break;
+		} else {
+			/*
+			 * isolate_freepages_block() should not terminate
+			 * prematurely unless contended, or isolated enough
+			 */
+			VM_BUG_ON(isolate_start_pfn < block_end_pfn);
+		}
 	}
 
 	/* split_free_page does not map the pages */
 	map_pages(freelist);
 
 	/*
-	 * If we crossed the migrate scanner, we want to keep it that way
-	 * so that compact_finished() may detect this
+	 * Record where the free scanner will restart next time. Either we
+	 * broke from the loop and set isolate_start_pfn based on the last
+	 * call to isolate_freepages_block(), or we met the migration scanner
+	 * and the loop terminated due to isolate_start_pfn < low_pfn
 	 */
-	if (block_start_pfn < low_pfn)
-		cc->free_pfn = cc->migrate_pfn;
+	cc->free_pfn = isolate_start_pfn;
 }
 
 /*
@@ -1062,6 +1115,7 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 					struct compact_control *cc)
 {
 	unsigned long low_pfn, end_pfn;
+	unsigned long isolate_start_pfn;
 	struct page *page;
 	const isolate_mode_t isolate_mode =
 		(sysctl_compact_unevictable_allowed ? ISOLATE_UNEVICTABLE : 0) |
@@ -1110,6 +1164,7 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 			continue;
 
 		/* Perform the isolation */
+		isolate_start_pfn = low_pfn;
 		low_pfn = isolate_migratepages_block(cc, low_pfn, end_pfn,
 								isolate_mode);
 
@@ -1118,6 +1173,15 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 			return ISOLATE_ABORT;
 		}
 
+		/*
+		 * Record where we could have freed pages by migration and not
+		 * yet flushed them to buddy allocator.
+		 * - this is the lowest page that could have been isolated and
+		 * then freed by migration.
+		 */
+		if (cc->nr_migratepages && !cc->last_migrated_pfn)
+			cc->last_migrated_pfn = isolate_start_pfn;
+
 		/*
 		 * Either we isolated something and proceed with migration. Or
 		 * we failed and compact_zone should decide if we should
@@ -1127,12 +1191,8 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 	}
 
 	acct_isolated(zone, cc);
-	/*
-	 * Record where migration scanner will be restarted. If we end up in
-	 * the same pageblock as the free scanner, make the scanners fully
-	 * meet so that compact_finished() terminates compaction.
-	 */
-	cc->migrate_pfn = (end_pfn <= cc->free_pfn) ? low_pfn : cc->free_pfn;
+	/* Record where migration scanner will be restarted. */
+	cc->migrate_pfn = low_pfn;
 
 	return cc->nr_migratepages ? ISOLATE_SUCCESS : ISOLATE_NONE;
 }
@@ -1147,11 +1207,9 @@ static int __compact_finished(struct zone *zone, struct compact_control *cc,
 		return COMPACT_PARTIAL;
 
 	/* Compaction run completes if the migrate and free scanner meet */
-	if (cc->free_pfn <= cc->migrate_pfn) {
+	if (compact_scanners_met(cc)) {
 		/* Let the next compaction start anew. */
-		zone->compact_cached_migrate_pfn[0] = zone->zone_start_pfn;
-		zone->compact_cached_migrate_pfn[1] = zone->zone_start_pfn;
-		zone->compact_cached_free_pfn = zone_end_pfn(zone);
+		reset_cached_positions(zone);
 
 		/*
 		 * Mark that the PG_migrate_skip information should be cleared
@@ -1295,7 +1353,6 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 	unsigned long end_pfn = zone_end_pfn(zone);
 	const int migratetype = gfpflags_to_migratetype(cc->gfp_mask);
 	const bool sync = cc->mode != MIGRATE_ASYNC;
-	unsigned long last_migrated_pfn = 0;
 
 	ret = compaction_suitable(zone, cc->order, cc->alloc_flags,
 							cc->classzone_idx);
@@ -1333,6 +1390,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 		zone->compact_cached_migrate_pfn[0] = cc->migrate_pfn;
 		zone->compact_cached_migrate_pfn[1] = cc->migrate_pfn;
 	}
+	cc->last_migrated_pfn = 0;
 
 	trace_mm_compaction_begin(start_pfn, cc->migrate_pfn,
 				cc->free_pfn, end_pfn, sync);
@@ -1342,7 +1400,6 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 	while ((ret = compact_finished(zone, cc, migratetype)) ==
 						COMPACT_CONTINUE) {
 		int err;
-		unsigned long isolate_start_pfn = cc->migrate_pfn;
 
 		switch (isolate_migratepages(zone, cc)) {
 		case ISOLATE_ABORT:
@@ -1376,22 +1433,12 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 			 * migrate_pages() may return -ENOMEM when scanners meet
 			 * and we want compact_finished() to detect it
 			 */
-			if (err == -ENOMEM && cc->free_pfn > cc->migrate_pfn) {
+			if (err == -ENOMEM && !compact_scanners_met(cc)) {
 				ret = COMPACT_PARTIAL;
 				goto out;
 			}
 		}
 
-		/*
-		 * Record where we could have freed pages by migration and not
-		 * yet flushed them to buddy allocator. We use the pfn that
-		 * isolate_migratepages() started from in this loop iteration
-		 * - this is the lowest page that could have been isolated and
-		 * then freed by migration.
-		 */
-		if (!last_migrated_pfn)
-			last_migrated_pfn = isolate_start_pfn;
-
 check_drain:
 		/*
 		 * Has the migration scanner moved away from the previous
@@ -1400,18 +1447,18 @@ check_drain:
 		 * compact_finished() can detect immediately if allocation
 		 * would succeed.
 		 */
-		if (cc->order > 0 && last_migrated_pfn) {
+		if (cc->order > 0 && cc->last_migrated_pfn) {
 			int cpu;
 			unsigned long current_block_start =
 				cc->migrate_pfn & ~((1UL << cc->order) - 1);
 
-			if (last_migrated_pfn < current_block_start) {
+			if (cc->last_migrated_pfn < current_block_start) {
 				cpu = get_cpu();
 				lru_add_drain_cpu(cpu);
 				drain_local_pages(zone);
 				put_cpu();
 				/* No more flushing until we migrate again */
-				last_migrated_pfn = 0;
+				cc->last_migrated_pfn = 0;
 			}
 		}
 

mm/dmapool.c

@@ -271,6 +271,9 @@ void dma_pool_destroy(struct dma_pool *pool)
 {
 	bool empty = false;
 
+	if (unlikely(!pool))
+		return;
+
 	mutex_lock(&pools_reg_lock);
 	mutex_lock(&pools_lock);
 	list_del(&pool->pools);
@@ -334,7 +337,7 @@ void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags,
 	/* pool_alloc_page() might sleep, so temporarily drop &pool->lock */
 	spin_unlock_irqrestore(&pool->lock, flags);
 
-	page = pool_alloc_page(pool, mem_flags);
+	page = pool_alloc_page(pool, mem_flags & (~__GFP_ZERO));
 	if (!page)
 		return NULL;
 
@@ -372,9 +375,14 @@ void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags,
 			break;
 		}
 	}
-	memset(retval, POOL_POISON_ALLOCATED, pool->size);
+	if (!(mem_flags & __GFP_ZERO))
+		memset(retval, POOL_POISON_ALLOCATED, pool->size);
 #endif
 	spin_unlock_irqrestore(&pool->lock, flags);
+
+	if (mem_flags & __GFP_ZERO)
+		memset(retval, 0, pool->size);
+
 	return retval;
 }
 EXPORT_SYMBOL(dma_pool_alloc);

mm/early_ioremap.c

@@ -224,6 +224,28 @@ early_memremap_ro(resource_size_t phys_addr, unsigned long size)
 	return (__force void *)__early_ioremap(phys_addr, size, FIXMAP_PAGE_RO);
 }
 #endif
+
+#define MAX_MAP_CHUNK	(NR_FIX_BTMAPS << PAGE_SHIFT)
+
+void __init copy_from_early_mem(void *dest, phys_addr_t src, unsigned long size)
+{
+	unsigned long slop, clen;
+	char *p;
+
+	while (size) {
+		slop = src & ~PAGE_MASK;
+		clen = size;
+		if (clen > MAX_MAP_CHUNK - slop)
+			clen = MAX_MAP_CHUNK - slop;
+		p = early_memremap(src & PAGE_MASK, clen + slop);
+		memcpy(dest, p + slop, clen);
+		early_memunmap(p, clen + slop);
+		dest += clen;
+		src += clen;
+		size -= clen;
+	}
+}
+
 #else /* CONFIG_MMU */
 
 void __init __iomem *

mm/filemap.c

@@ -674,7 +674,7 @@ struct page *__page_cache_alloc(gfp_t gfp)
 		do {
 			cpuset_mems_cookie = read_mems_allowed_begin();
 			n = cpuset_mem_spread_node();
-			page = alloc_pages_exact_node(n, gfp, 0);
+			page = __alloc_pages_node(n, gfp, 0);
 		} while (!page && read_mems_allowed_retry(cpuset_mems_cookie));
 
 		return page;
@@ -2473,21 +2473,6 @@ ssize_t generic_perform_write(struct file *file,
 						iov_iter_count(i));
 
 again:
-		/*
-		 * Bring in the user page that we will copy from _first_.
-		 * Otherwise there's a nasty deadlock on copying from the
-		 * same page as we're writing to, without it being marked
-		 * up-to-date.
-		 *
-		 * Not only is this an optimisation, but it is also required
-		 * to check that the address is actually valid, when atomic
-		 * usercopies are used, below.
-		 */
-		if (unlikely(iov_iter_fault_in_readable(i, bytes))) {
-			status = -EFAULT;
-			break;
-		}
-
 		status = a_ops->write_begin(file, mapping, pos, bytes, flags,
 						&page, &fsdata);
 		if (unlikely(status < 0))
@@ -2495,8 +2480,17 @@ again:
 
 		if (mapping_writably_mapped(mapping))
 			flush_dcache_page(page);
-
+		/*
+		 * 'page' is now locked.  If we are trying to copy from a
+		 * mapping of 'page' in userspace, the copy might fault and
+		 * would need PageUptodate() to complete.  But, page can not be
+		 * made Uptodate without acquiring the page lock, which we hold.
+		 * Deadlock.  Avoid with pagefault_disable().  Fix up below with
+		 * iov_iter_fault_in_readable().
+		 */
+		pagefault_disable();
 		copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes);
+		pagefault_enable();
 		flush_dcache_page(page);
 
 		status = a_ops->write_end(file, mapping, pos, bytes, copied,
@@ -2519,6 +2513,14 @@ again:
 			 */
 			bytes = min_t(unsigned long, PAGE_CACHE_SIZE - offset,
 						iov_iter_single_seg_count(i));
+			/*
+			 * This is the fallback to recover if the copy from
+			 * userspace above faults.
+			 */
+			if (unlikely(iov_iter_fault_in_readable(i, bytes))) {
+				status = -EFAULT;
+				break;
+			}
 			goto again;
 		}
 		pos += copied;

mm/huge_memory.c

@@ -16,6 +16,7 @@
 #include <linux/swap.h>
 #include <linux/shrinker.h>
 #include <linux/mm_inline.h>
+#include <linux/dax.h>
 #include <linux/kthread.h>
 #include <linux/khugepaged.h>
 #include <linux/freezer.h>
@@ -105,7 +106,7 @@ static struct khugepaged_scan khugepaged_scan = {
 };
 
 
-static int set_recommended_min_free_kbytes(void)
+static void set_recommended_min_free_kbytes(void)
 {
 	struct zone *zone;
 	int nr_zones = 0;
@@ -140,7 +141,6 @@ static int set_recommended_min_free_kbytes(void)
 		min_free_kbytes = recommended_min;
 	}
 	setup_per_zone_wmarks();
-	return 0;
 }
 
 static int start_stop_khugepaged(void)
@@ -172,12 +172,7 @@ fail:
 static atomic_t huge_zero_refcount;
 struct page *huge_zero_page __read_mostly;
 
-static inline bool is_huge_zero_pmd(pmd_t pmd)
-{
-	return is_huge_zero_page(pmd_page(pmd));
-}
-
-static struct page *get_huge_zero_page(void)
+struct page *get_huge_zero_page(void)
 {
 	struct page *zero_page;
 retry:
@@ -794,16 +789,19 @@ static inline gfp_t alloc_hugepage_gfpmask(int defrag, gfp_t extra_gfp)
 }
 
 /* Caller must hold page table lock. */
-static void set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm,
+static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm,
 		struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd,
 		struct page *zero_page)
 {
 	pmd_t entry;
+	if (!pmd_none(*pmd))
+		return false;
 	entry = mk_pmd(zero_page, vma->vm_page_prot);
 	entry = pmd_mkhuge(entry);
 	pgtable_trans_huge_deposit(mm, pmd, pgtable);
 	set_pmd_at(mm, haddr, pmd, entry);
 	atomic_long_inc(&mm->nr_ptes);
+	return true;
 }
 
 int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
@@ -870,6 +868,49 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 					    flags);
 }
 
+static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
+		pmd_t *pmd, unsigned long pfn, pgprot_t prot, bool write)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	pmd_t entry;
+	spinlock_t *ptl;
+
+	ptl = pmd_lock(mm, pmd);
+	if (pmd_none(*pmd)) {
+		entry = pmd_mkhuge(pfn_pmd(pfn, prot));
+		if (write) {
+			entry = pmd_mkyoung(pmd_mkdirty(entry));
+			entry = maybe_pmd_mkwrite(entry, vma);
+		}
+		set_pmd_at(mm, addr, pmd, entry);
+		update_mmu_cache_pmd(vma, addr, pmd);
+	}
+	spin_unlock(ptl);
+}
+
+int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
+			pmd_t *pmd, unsigned long pfn, bool write)
+{
+	pgprot_t pgprot = vma->vm_page_prot;
+	/*
+	 * If we had pmd_special, we could avoid all these restrictions,
+	 * but we need to be consistent with PTEs and architectures that
+	 * can't support a 'special' bit.
+	 */
+	BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)));
+	BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) ==
+						(VM_PFNMAP|VM_MIXEDMAP));
+	BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags));
+	BUG_ON((vma->vm_flags & VM_MIXEDMAP) && pfn_valid(pfn));
+
+	if (addr < vma->vm_start || addr >= vma->vm_end)
+		return VM_FAULT_SIGBUS;
+	if (track_pfn_insert(vma, &pgprot, pfn))
+		return VM_FAULT_SIGBUS;
+	insert_pfn_pmd(vma, addr, pmd, pfn, pgprot, write);
+	return VM_FAULT_NOPAGE;
+}
+
 int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		  pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
 		  struct vm_area_struct *vma)
@@ -1414,41 +1455,41 @@ out:
 int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		 pmd_t *pmd, unsigned long addr)
 {
+	pmd_t orig_pmd;
 	spinlock_t *ptl;
-	int ret = 0;
 
-	if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
-		struct page *page;
-		pgtable_t pgtable;
-		pmd_t orig_pmd;
-		/*
-		 * For architectures like ppc64 we look at deposited pgtable
-		 * when calling pmdp_huge_get_and_clear. So do the
-		 * pgtable_trans_huge_withdraw after finishing pmdp related
-		 * operations.
-		 */
-		orig_pmd = pmdp_huge_get_and_clear_full(tlb->mm, addr, pmd,
-							tlb->fullmm);
-		tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
-		pgtable = pgtable_trans_huge_withdraw(tlb->mm, pmd);
-		if (is_huge_zero_pmd(orig_pmd)) {
-			atomic_long_dec(&tlb->mm->nr_ptes);
-			spin_unlock(ptl);
+	if (__pmd_trans_huge_lock(pmd, vma, &ptl) != 1)
+		return 0;
+	/*
+	 * For architectures like ppc64 we look at deposited pgtable
+	 * when calling pmdp_huge_get_and_clear. So do the
+	 * pgtable_trans_huge_withdraw after finishing pmdp related
+	 * operations.
+	 */
+	orig_pmd = pmdp_huge_get_and_clear_full(tlb->mm, addr, pmd,
+			tlb->fullmm);
+	tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
+	if (vma_is_dax(vma)) {
+		spin_unlock(ptl);
+		if (is_huge_zero_pmd(orig_pmd))
 			put_huge_zero_page();
-		} else {
-			page = pmd_page(orig_pmd);
-			page_remove_rmap(page);
-			VM_BUG_ON_PAGE(page_mapcount(page) < 0, page);
-			add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR);
-			VM_BUG_ON_PAGE(!PageHead(page), page);
-			atomic_long_dec(&tlb->mm->nr_ptes);
-			spin_unlock(ptl);
-			tlb_remove_page(tlb, page);
-		}
-		pte_free(tlb->mm, pgtable);
-		ret = 1;
+	} else if (is_huge_zero_pmd(orig_pmd)) {
+		pte_free(tlb->mm, pgtable_trans_huge_withdraw(tlb->mm, pmd));
+		atomic_long_dec(&tlb->mm->nr_ptes);
+		spin_unlock(ptl);
+		put_huge_zero_page();
+	} else {
+		struct page *page = pmd_page(orig_pmd);
+		page_remove_rmap(page);
+		VM_BUG_ON_PAGE(page_mapcount(page) < 0, page);
+		add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR);
+		VM_BUG_ON_PAGE(!PageHead(page), page);
+		pte_free(tlb->mm, pgtable_trans_huge_withdraw(tlb->mm, pmd));
+		atomic_long_dec(&tlb->mm->nr_ptes);
+		spin_unlock(ptl);
+		tlb_remove_page(tlb, page);
 	}
-	return ret;
+	return 1;
 }
 
 int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma,
@@ -2285,8 +2326,12 @@ static void __collapse_huge_page_copy(pte_t *pte, struct page *page,
 
 static void khugepaged_alloc_sleep(void)
 {
-	wait_event_freezable_timeout(khugepaged_wait, false,
-			msecs_to_jiffies(khugepaged_alloc_sleep_millisecs));
+	DEFINE_WAIT(wait);
+
+	add_wait_queue(&khugepaged_wait, &wait);
+	freezable_schedule_timeout_interruptible(
+		msecs_to_jiffies(khugepaged_alloc_sleep_millisecs));
+	remove_wait_queue(&khugepaged_wait, &wait);
 }
 
 static int khugepaged_node_load[MAX_NUMNODES];
@@ -2373,7 +2418,7 @@ khugepaged_alloc_page(struct page **hpage, gfp_t gfp, struct mm_struct *mm,
 	 */
 	up_read(&mm->mmap_sem);
 
-	*hpage = alloc_pages_exact_node(node, gfp, HPAGE_PMD_ORDER);
+	*hpage = __alloc_pages_node(node, gfp, HPAGE_PMD_ORDER);
 	if (unlikely(!*hpage)) {
 		count_vm_event(THP_COLLAPSE_ALLOC_FAILED);
 		*hpage = ERR_PTR(-ENOMEM);
@@ -2911,7 +2956,7 @@ void __split_huge_page_pmd(struct vm_area_struct *vma, unsigned long address,
 		pmd_t *pmd)
 {
 	spinlock_t *ptl;
-	struct page *page;
+	struct page *page = NULL;
 	struct mm_struct *mm = vma->vm_mm;
 	unsigned long haddr = address & HPAGE_PMD_MASK;
 	unsigned long mmun_start;	/* For mmu_notifiers */
@@ -2924,25 +2969,27 @@ void __split_huge_page_pmd(struct vm_area_struct *vma, unsigned long address,
 again:
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
 	ptl = pmd_lock(mm, pmd);
-	if (unlikely(!pmd_trans_huge(*pmd))) {
-		spin_unlock(ptl);
-		mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
-		return;
-	}
-	if (is_huge_zero_pmd(*pmd)) {
+	if (unlikely(!pmd_trans_huge(*pmd)))
+		goto unlock;
+	if (vma_is_dax(vma)) {
+		pmd_t _pmd = pmdp_huge_clear_flush_notify(vma, haddr, pmd);
+		if (is_huge_zero_pmd(_pmd))
+			put_huge_zero_page();
+	} else if (is_huge_zero_pmd(*pmd)) {
 		__split_huge_zero_page_pmd(vma, haddr, pmd);
-		spin_unlock(ptl);
-		mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
-		return;
+	} else {
+		page = pmd_page(*pmd);
+		VM_BUG_ON_PAGE(!page_count(page), page);
+		get_page(page);
 	}
-	page = pmd_page(*pmd);
-	VM_BUG_ON_PAGE(!page_count(page), page);
-	get_page(page);
+ unlock:
 	spin_unlock(ptl);
 	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 
-	split_huge_page(page);
+	if (!page)
+		return;
 
+	split_huge_page(page);
 	put_page(page);
 
 	/*
@@ -2991,7 +3038,7 @@ static void split_huge_page_address(struct mm_struct *mm,
 	split_huge_page_pmd_mm(mm, address, pmd);
 }
 
-void __vma_adjust_trans_huge(struct vm_area_struct *vma,
+void vma_adjust_trans_huge(struct vm_area_struct *vma,
 			     unsigned long start,
 			     unsigned long end,
 			     long adjust_next)

mm/hugetlb.c

@@ -64,7 +64,7 @@ DEFINE_SPINLOCK(hugetlb_lock);
  * prevent spurious OOMs when the hugepage pool is fully utilized.
  */
 static int num_fault_mutexes;
-static struct mutex *htlb_fault_mutex_table ____cacheline_aligned_in_smp;
+struct mutex *hugetlb_fault_mutex_table ____cacheline_aligned_in_smp;
 
 /* Forward declaration */
 static int hugetlb_acct_memory(struct hstate *h, long delta);
@@ -240,11 +240,14 @@ struct file_region {
 
 /*
  * Add the huge page range represented by [f, t) to the reserve
- * map.  Existing regions will be expanded to accommodate the
- * specified range.  We know only existing regions need to be
- * expanded, because region_add is only called after region_chg
- * with the same range.  If a new file_region structure must
- * be allocated, it is done in region_chg.
+ * map.  In the normal case, existing regions will be expanded
+ * to accommodate the specified range.  Sufficient regions should
+ * exist for expansion due to the previous call to region_chg
+ * with the same range.  However, it is possible that region_del
+ * could have been called after region_chg and modifed the map
+ * in such a way that no region exists to be expanded.  In this
+ * case, pull a region descriptor from the cache associated with
+ * the map and use that for the new range.
  *
  * Return the number of new huge pages added to the map.  This
  * number is greater than or equal to zero.
@@ -261,6 +264,28 @@ static long region_add(struct resv_map *resv, long f, long t)
 		if (f <= rg->to)
 			break;
 
+	/*
+	 * If no region exists which can be expanded to include the
+	 * specified range, the list must have been modified by an
+	 * interleving call to region_del().  Pull a region descriptor
+	 * from the cache and use it for this range.
+	 */
+	if (&rg->link == head || t < rg->from) {
+		VM_BUG_ON(resv->region_cache_count <= 0);
+
+		resv->region_cache_count--;
+		nrg = list_first_entry(&resv->region_cache, struct file_region,
+					link);
+		list_del(&nrg->link);
+
+		nrg->from = f;
+		nrg->to = t;
+		list_add(&nrg->link, rg->link.prev);
+
+		add += t - f;
+		goto out_locked;
+	}
+
 	/* Round our left edge to the current segment if it encloses us. */
 	if (f > rg->from)
 		f = rg->from;
@@ -294,6 +319,8 @@ static long region_add(struct resv_map *resv, long f, long t)
 	add += t - nrg->to;		/* Added to end of region */
 	nrg->to = t;
 
+out_locked:
+	resv->adds_in_progress--;
 	spin_unlock(&resv->lock);
 	VM_BUG_ON(add < 0);
 	return add;
@@ -312,11 +339,14 @@ static long region_add(struct resv_map *resv, long f, long t)
  * so that the subsequent region_add call will have all the
  * regions it needs and will not fail.
  *
- * Returns the number of huge pages that need to be added
- * to the existing reservation map for the range [f, t).
- * This number is greater or equal to zero.  -ENOMEM is
- * returned if a new file_region structure is needed and can
- * not be allocated.
+ * Upon entry, region_chg will also examine the cache of region descriptors
+ * associated with the map.  If there are not enough descriptors cached, one
+ * will be allocated for the in progress add operation.
+ *
+ * Returns the number of huge pages that need to be added to the existing
+ * reservation map for the range [f, t).  This number is greater or equal to
+ * zero.  -ENOMEM is returned if a new file_region structure or cache entry
+ * is needed and can not be allocated.
  */
 static long region_chg(struct resv_map *resv, long f, long t)
 {
@@ -326,6 +356,31 @@ static long region_chg(struct resv_map *resv, long f, long t)
 
 retry:
 	spin_lock(&resv->lock);
+retry_locked:
+	resv->adds_in_progress++;
+
+	/*
+	 * Check for sufficient descriptors in the cache to accommodate
+	 * the number of in progress add operations.
+	 */
+	if (resv->adds_in_progress > resv->region_cache_count) {
+		struct file_region *trg;
+
+		VM_BUG_ON(resv->adds_in_progress - resv->region_cache_count > 1);
+		/* Must drop lock to allocate a new descriptor. */
+		resv->adds_in_progress--;
+		spin_unlock(&resv->lock);
+
+		trg = kmalloc(sizeof(*trg), GFP_KERNEL);
+		if (!trg)
+			return -ENOMEM;
+
+		spin_lock(&resv->lock);
+		list_add(&trg->link, &resv->region_cache);
+		resv->region_cache_count++;
+		goto retry_locked;
+	}
+
 	/* Locate the region we are before or in. */
 	list_for_each_entry(rg, head, link)
 		if (f <= rg->to)
@@ -336,6 +391,7 @@ retry:
 	 * size such that we can guarantee to record the reservation. */
 	if (&rg->link == head || t < rg->from) {
 		if (!nrg) {
+			resv->adds_in_progress--;
 			spin_unlock(&resv->lock);
 			nrg = kmalloc(sizeof(*nrg), GFP_KERNEL);
 			if (!nrg)
@@ -385,43 +441,131 @@ out_nrg:
 }
 
 /*
- * Truncate the reserve map at index 'end'.  Modify/truncate any
- * region which contains end.  Delete any regions past end.
- * Return the number of huge pages removed from the map.
+ * Abort the in progress add operation.  The adds_in_progress field
+ * of the resv_map keeps track of the operations in progress between
+ * calls to region_chg and region_add.  Operations are sometimes
+ * aborted after the call to region_chg.  In such cases, region_abort
+ * is called to decrement the adds_in_progress counter.
+ *
+ * NOTE: The range arguments [f, t) are not needed or used in this
+ * routine.  They are kept to make reading the calling code easier as
+ * arguments will match the associated region_chg call.
  */
-static long region_truncate(struct resv_map *resv, long end)
+static void region_abort(struct resv_map *resv, long f, long t)
+{
+	spin_lock(&resv->lock);
+	VM_BUG_ON(!resv->region_cache_count);
+	resv->adds_in_progress--;
+	spin_unlock(&resv->lock);
+}
+
+/*
+ * Delete the specified range [f, t) from the reserve map.  If the
+ * t parameter is LONG_MAX, this indicates that ALL regions after f
+ * should be deleted.  Locate the regions which intersect [f, t)
+ * and either trim, delete or split the existing regions.
+ *
+ * Returns the number of huge pages deleted from the reserve map.
+ * In the normal case, the return value is zero or more.  In the
+ * case where a region must be split, a new region descriptor must
+ * be allocated.  If the allocation fails, -ENOMEM will be returned.
+ * NOTE: If the parameter t == LONG_MAX, then we will never split
+ * a region and possibly return -ENOMEM.  Callers specifying
+ * t == LONG_MAX do not need to check for -ENOMEM error.
+ */
+static long region_del(struct resv_map *resv, long f, long t)
 {
 	struct list_head *head = &resv->regions;
 	struct file_region *rg, *trg;
-	long chg = 0;
+	struct file_region *nrg = NULL;
+	long del = 0;
 
+retry:
 	spin_lock(&resv->lock);
-	/* Locate the region we are either in or before. */
-	list_for_each_entry(rg, head, link)
-		if (end <= rg->to)
+	list_for_each_entry_safe(rg, trg, head, link) {
+		if (rg->to <= f)
+			continue;
+		if (rg->from >= t)
 			break;
-	if (&rg->link == head)
-		goto out;
 
-	/* If we are in the middle of a region then adjust it. */
-	if (end > rg->from) {
-		chg = rg->to - end;
-		rg->to = end;
-		rg = list_entry(rg->link.next, typeof(*rg), link);
-	}
+		if (f > rg->from && t < rg->to) { /* Must split region */
+			/*
+			 * Check for an entry in the cache before dropping
+			 * lock and attempting allocation.
+			 */
+			if (!nrg &&
+			    resv->region_cache_count > resv->adds_in_progress) {
+				nrg = list_first_entry(&resv->region_cache,
+							struct file_region,
+							link);
+				list_del(&nrg->link);
+				resv->region_cache_count--;
+			}
 
-	/* Drop any remaining regions. */
-	list_for_each_entry_safe(rg, trg, rg->link.prev, link) {
-		if (&rg->link == head)
+			if (!nrg) {
+				spin_unlock(&resv->lock);
+				nrg = kmalloc(sizeof(*nrg), GFP_KERNEL);
+				if (!nrg)
+					return -ENOMEM;
+				goto retry;
+			}
+
+			del += t - f;
+
+			/* New entry for end of split region */
+			nrg->from = t;
+			nrg->to = rg->to;
+			INIT_LIST_HEAD(&nrg->link);
+
+			/* Original entry is trimmed */
+			rg->to = f;
+
+			list_add(&nrg->link, &rg->link);
+			nrg = NULL;
 			break;
-		chg += rg->to - rg->from;
-		list_del(&rg->link);
-		kfree(rg);
+		}
+
+		if (f <= rg->from && t >= rg->to) { /* Remove entire region */
+			del += rg->to - rg->from;
+			list_del(&rg->link);
+			kfree(rg);
+			continue;
+		}
+
+		if (f <= rg->from) {	/* Trim beginning of region */
+			del += t - rg->from;
+			rg->from = t;
+		} else {		/* Trim end of region */
+			del += rg->to - f;
+			rg->to = f;
+		}
 	}
 
-out:
 	spin_unlock(&resv->lock);
-	return chg;
+	kfree(nrg);
+	return del;
+}
+
+/*
+ * A rare out of memory error was encountered which prevented removal of
+ * the reserve map region for a page.  The huge page itself was free'ed
+ * and removed from the page cache.  This routine will adjust the subpool
+ * usage count, and the global reserve count if needed.  By incrementing
+ * these counts, the reserve map entry which could not be deleted will
+ * appear as a "reserved" entry instead of simply dangling with incorrect
+ * counts.
+ */
+void hugetlb_fix_reserve_counts(struct inode *inode, bool restore_reserve)
+{
+	struct hugepage_subpool *spool = subpool_inode(inode);
+	long rsv_adjust;
+
+	rsv_adjust = hugepage_subpool_get_pages(spool, 1);
+	if (restore_reserve && rsv_adjust) {
+		struct hstate *h = hstate_inode(inode);
+
+		hugetlb_acct_memory(h, 1);
+	}
 }
 
 /*
@@ -544,22 +688,44 @@ static void set_vma_private_data(struct vm_area_struct *vma,
 struct resv_map *resv_map_alloc(void)
 {
 	struct resv_map *resv_map = kmalloc(sizeof(*resv_map), GFP_KERNEL);
-	if (!resv_map)
+	struct file_region *rg = kmalloc(sizeof(*rg), GFP_KERNEL);
+
+	if (!resv_map || !rg) {
+		kfree(resv_map);
+		kfree(rg);
 		return NULL;
+	}
 
 	kref_init(&resv_map->refs);
 	spin_lock_init(&resv_map->lock);
 	INIT_LIST_HEAD(&resv_map->regions);
 
+	resv_map->adds_in_progress = 0;
+
+	INIT_LIST_HEAD(&resv_map->region_cache);
+	list_add(&rg->link, &resv_map->region_cache);
+	resv_map->region_cache_count = 1;
+
 	return resv_map;
 }
 
 void resv_map_release(struct kref *ref)
 {
 	struct resv_map *resv_map = container_of(ref, struct resv_map, refs);
+	struct list_head *head = &resv_map->region_cache;
+	struct file_region *rg, *trg;
 
 	/* Clear out any active regions before we release the map. */
-	region_truncate(resv_map, 0);
+	region_del(resv_map, 0, LONG_MAX);
+
+	/* ... and any entries left in the cache */
+	list_for_each_entry_safe(rg, trg, head, link) {
+		list_del(&rg->link);
+		kfree(rg);
+	}
+
+	VM_BUG_ON(resv_map->adds_in_progress);
+
 	kfree(resv_map);
 }
 
@@ -635,8 +801,19 @@ static bool vma_has_reserves(struct vm_area_struct *vma, long chg)
 	}
 
 	/* Shared mappings always use reserves */
-	if (vma->vm_flags & VM_MAYSHARE)
-		return true;
+	if (vma->vm_flags & VM_MAYSHARE) {
+		/*
+		 * We know VM_NORESERVE is not set.  Therefore, there SHOULD
+		 * be a region map for all pages.  The only situation where
+		 * there is no region map is if a hole was punched via
+		 * fallocate.  In this case, there really are no reverves to
+		 * use.  This situation is indicated if chg != 0.
+		 */
+		if (chg)
+			return false;
+		else
+			return true;
+	}
 
 	/*
 	 * Only the process that called mmap() has reserves for
@@ -1154,7 +1331,7 @@ static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
 {
 	struct page *page;
 
-	page = alloc_pages_exact_node(nid,
+	page = __alloc_pages_node(nid,
 		htlb_alloc_mask(h)|__GFP_COMP|__GFP_THISNODE|
 						__GFP_REPEAT|__GFP_NOWARN,
 		huge_page_order(h));
@@ -1306,7 +1483,7 @@ static struct page *alloc_buddy_huge_page(struct hstate *h, int nid)
 				   __GFP_REPEAT|__GFP_NOWARN,
 				   huge_page_order(h));
 	else
-		page = alloc_pages_exact_node(nid,
+		page = __alloc_pages_node(nid,
 			htlb_alloc_mask(h)|__GFP_COMP|__GFP_THISNODE|
 			__GFP_REPEAT|__GFP_NOWARN, huge_page_order(h));
 
@@ -1473,16 +1650,19 @@ static void return_unused_surplus_pages(struct hstate *h,
 	}
 }
 
+
 /*
- * vma_needs_reservation and vma_commit_reservation are used by the huge
- * page allocation routines to manage reservations.
+ * vma_needs_reservation, vma_commit_reservation and vma_end_reservation
+ * are used by the huge page allocation routines to manage reservations.
  *
  * vma_needs_reservation is called to determine if the huge page at addr
  * within the vma has an associated reservation.  If a reservation is
  * needed, the value 1 is returned.  The caller is then responsible for
  * managing the global reservation and subpool usage counts.  After
  * the huge page has been allocated, vma_commit_reservation is called
- * to add the page to the reservation map.
+ * to add the page to the reservation map.  If the page allocation fails,
+ * the reservation must be ended instead of committed.  vma_end_reservation
+ * is called in such cases.
  *
  * In the normal case, vma_commit_reservation returns the same value
  * as the preceding vma_needs_reservation call.  The only time this
@@ -1490,9 +1670,14 @@ static void return_unused_surplus_pages(struct hstate *h,
  * is the responsibility of the caller to notice the difference and
  * take appropriate action.
  */
+enum vma_resv_mode {
+	VMA_NEEDS_RESV,
+	VMA_COMMIT_RESV,
+	VMA_END_RESV,
+};
 static long __vma_reservation_common(struct hstate *h,
 				struct vm_area_struct *vma, unsigned long addr,
-				bool commit)
+				enum vma_resv_mode mode)
 {
 	struct resv_map *resv;
 	pgoff_t idx;
@@ -1503,10 +1688,20 @@ static long __vma_reservation_common(struct hstate *h,
 		return 1;
 
 	idx = vma_hugecache_offset(h, vma, addr);
-	if (commit)
-		ret = region_add(resv, idx, idx + 1);
-	else
+	switch (mode) {
+	case VMA_NEEDS_RESV:
 		ret = region_chg(resv, idx, idx + 1);
+		break;
+	case VMA_COMMIT_RESV:
+		ret = region_add(resv, idx, idx + 1);
+		break;
+	case VMA_END_RESV:
+		region_abort(resv, idx, idx + 1);
+		ret = 0;
+		break;
+	default:
+		BUG();
+	}
 
 	if (vma->vm_flags & VM_MAYSHARE)
 		return ret;
@@ -1517,47 +1712,79 @@ static long __vma_reservation_common(struct hstate *h,
 static long vma_needs_reservation(struct hstate *h,
 			struct vm_area_struct *vma, unsigned long addr)
 {
-	return __vma_reservation_common(h, vma, addr, false);
+	return __vma_reservation_common(h, vma, addr, VMA_NEEDS_RESV);
 }
 
 static long vma_commit_reservation(struct hstate *h,
 			struct vm_area_struct *vma, unsigned long addr)
 {
-	return __vma_reservation_common(h, vma, addr, true);
+	return __vma_reservation_common(h, vma, addr, VMA_COMMIT_RESV);
+}
+
+static void vma_end_reservation(struct hstate *h,
+			struct vm_area_struct *vma, unsigned long addr)
+{
+	(void)__vma_reservation_common(h, vma, addr, VMA_END_RESV);
 }
 
-static struct page *alloc_huge_page(struct vm_area_struct *vma,
+struct page *alloc_huge_page(struct vm_area_struct *vma,
 				    unsigned long addr, int avoid_reserve)
 {
 	struct hugepage_subpool *spool = subpool_vma(vma);
 	struct hstate *h = hstate_vma(vma);
 	struct page *page;
-	long chg, commit;
+	long map_chg, map_commit;
+	long gbl_chg;
 	int ret, idx;
 	struct hugetlb_cgroup *h_cg;
 
 	idx = hstate_index(h);
 	/*
-	 * Processes that did not create the mapping will have no
-	 * reserves and will not have accounted against subpool
-	 * limit. Check that the subpool limit can be made before
-	 * satisfying the allocation MAP_NORESERVE mappings may also
-	 * need pages and subpool limit allocated allocated if no reserve
-	 * mapping overlaps.
+	 * Examine the region/reserve map to determine if the process
+	 * has a reservation for the page to be allocated.  A return
+	 * code of zero indicates a reservation exists (no change).
 	 */
-	chg = vma_needs_reservation(h, vma, addr);
-	if (chg < 0)
+	map_chg = gbl_chg = vma_needs_reservation(h, vma, addr);
+	if (map_chg < 0)
 		return ERR_PTR(-ENOMEM);
-	if (chg || avoid_reserve)
-		if (hugepage_subpool_get_pages(spool, 1) < 0)
+
+	/*
+	 * Processes that did not create the mapping will have no
+	 * reserves as indicated by the region/reserve map. Check
+	 * that the allocation will not exceed the subpool limit.
+	 * Allocations for MAP_NORESERVE mappings also need to be
+	 * checked against any subpool limit.
+	 */
+	if (map_chg || avoid_reserve) {
+		gbl_chg = hugepage_subpool_get_pages(spool, 1);
+		if (gbl_chg < 0) {
+			vma_end_reservation(h, vma, addr);
 			return ERR_PTR(-ENOSPC);
+		}
+
+		/*
+		 * Even though there was no reservation in the region/reserve
+		 * map, there could be reservations associated with the
+		 * subpool that can be used.  This would be indicated if the
+		 * return value of hugepage_subpool_get_pages() is zero.
+		 * However, if avoid_reserve is specified we still avoid even
+		 * the subpool reservations.
+		 */
+		if (avoid_reserve)
+			gbl_chg = 1;
+	}
 
 	ret = hugetlb_cgroup_charge_cgroup(idx, pages_per_huge_page(h), &h_cg);
 	if (ret)
 		goto out_subpool_put;
 
 	spin_lock(&hugetlb_lock);
-	page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve, chg);
+	/*
+	 * glb_chg is passed to indicate whether or not a page must be taken
+	 * from the global free pool (global change).  gbl_chg == 0 indicates
+	 * a reservation exists for the allocation.
+	 */
+	page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve, gbl_chg);
 	if (!page) {
 		spin_unlock(&hugetlb_lock);
 		page = alloc_buddy_huge_page(h, NUMA_NO_NODE);
@@ -1573,8 +1800,8 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma,
 
 	set_page_private(page, (unsigned long)spool);
 
-	commit = vma_commit_reservation(h, vma, addr);
-	if (unlikely(chg > commit)) {
+	map_commit = vma_commit_reservation(h, vma, addr);
+	if (unlikely(map_chg > map_commit)) {
 		/*
 		 * The page was added to the reservation map between
 		 * vma_needs_reservation and vma_commit_reservation.
@@ -1594,8 +1821,9 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma,
 out_uncharge_cgroup:
 	hugetlb_cgroup_uncharge_cgroup(idx, pages_per_huge_page(h), h_cg);
 out_subpool_put:
-	if (chg || avoid_reserve)
+	if (map_chg || avoid_reserve)
 		hugepage_subpool_put_pages(spool, 1);
+	vma_end_reservation(h, vma, addr);
 	return ERR_PTR(-ENOSPC);
 }
 
@@ -2311,7 +2539,7 @@ static void __exit hugetlb_exit(void)
 	}
 
 	kobject_put(hugepages_kobj);
-	kfree(htlb_fault_mutex_table);
+	kfree(hugetlb_fault_mutex_table);
 }
 module_exit(hugetlb_exit);
 
@@ -2344,12 +2572,12 @@ static int __init hugetlb_init(void)
 #else
 	num_fault_mutexes = 1;
 #endif
-	htlb_fault_mutex_table =
+	hugetlb_fault_mutex_table =
 		kmalloc(sizeof(struct mutex) * num_fault_mutexes, GFP_KERNEL);
-	BUG_ON(!htlb_fault_mutex_table);
+	BUG_ON(!hugetlb_fault_mutex_table);
 
 	for (i = 0; i < num_fault_mutexes; i++)
-		mutex_init(&htlb_fault_mutex_table[i]);
+		mutex_init(&hugetlb_fault_mutex_table[i]);
 	return 0;
 }
 module_init(hugetlb_init);
@@ -3147,6 +3375,23 @@ static bool hugetlbfs_pagecache_present(struct hstate *h,
 	return page != NULL;
 }
 
+int huge_add_to_page_cache(struct page *page, struct address_space *mapping,
+			   pgoff_t idx)
+{
+	struct inode *inode = mapping->host;
+	struct hstate *h = hstate_inode(inode);
+	int err = add_to_page_cache(page, mapping, idx, GFP_KERNEL);
+
+	if (err)
+		return err;
+	ClearPagePrivate(page);
+
+	spin_lock(&inode->i_lock);
+	inode->i_blocks += blocks_per_huge_page(h);
+	spin_unlock(&inode->i_lock);
+	return 0;
+}
+
 static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			   struct address_space *mapping, pgoff_t idx,
 			   unsigned long address, pte_t *ptep, unsigned int flags)
@@ -3194,21 +3439,13 @@ retry:
 		set_page_huge_active(page);
 
 		if (vma->vm_flags & VM_MAYSHARE) {
-			int err;
-			struct inode *inode = mapping->host;
-
-			err = add_to_page_cache(page, mapping, idx, GFP_KERNEL);
+			int err = huge_add_to_page_cache(page, mapping, idx);
 			if (err) {
 				put_page(page);
 				if (err == -EEXIST)
 					goto retry;
 				goto out;
 			}
-			ClearPagePrivate(page);
-
-			spin_lock(&inode->i_lock);
-			inode->i_blocks += blocks_per_huge_page(h);
-			spin_unlock(&inode->i_lock);
 		} else {
 			lock_page(page);
 			if (unlikely(anon_vma_prepare(vma))) {
@@ -3236,11 +3473,14 @@ retry:
 	 * any allocations necessary to record that reservation occur outside
 	 * the spinlock.
 	 */
-	if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED))
+	if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) {
 		if (vma_needs_reservation(h, vma, address) < 0) {
 			ret = VM_FAULT_OOM;
 			goto backout_unlocked;
 		}
+		/* Just decrements count, does not deallocate */
+		vma_end_reservation(h, vma, address);
+	}
 
 	ptl = huge_pte_lockptr(h, mm, ptep);
 	spin_lock(ptl);
@@ -3280,7 +3520,7 @@ backout_unlocked:
 }
 
 #ifdef CONFIG_SMP
-static u32 fault_mutex_hash(struct hstate *h, struct mm_struct *mm,
+u32 hugetlb_fault_mutex_hash(struct hstate *h, struct mm_struct *mm,
 			    struct vm_area_struct *vma,
 			    struct address_space *mapping,
 			    pgoff_t idx, unsigned long address)
@@ -3305,7 +3545,7 @@ static u32 fault_mutex_hash(struct hstate *h, struct mm_struct *mm,
  * For uniprocesor systems we always use a single mutex, so just
  * return 0 and avoid the hashing overhead.
  */
-static u32 fault_mutex_hash(struct hstate *h, struct mm_struct *mm,
+u32 hugetlb_fault_mutex_hash(struct hstate *h, struct mm_struct *mm,
 			    struct vm_area_struct *vma,
 			    struct address_space *mapping,
 			    pgoff_t idx, unsigned long address)
@@ -3353,8 +3593,8 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * get spurious allocation failures if two CPUs race to instantiate
 	 * the same page in the page cache.
 	 */
-	hash = fault_mutex_hash(h, mm, vma, mapping, idx, address);
-	mutex_lock(&htlb_fault_mutex_table[hash]);
+	hash = hugetlb_fault_mutex_hash(h, mm, vma, mapping, idx, address);
+	mutex_lock(&hugetlb_fault_mutex_table[hash]);
 
 	entry = huge_ptep_get(ptep);
 	if (huge_pte_none(entry)) {
@@ -3387,6 +3627,8 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 			ret = VM_FAULT_OOM;
 			goto out_mutex;
 		}
+		/* Just decrements count, does not deallocate */
+		vma_end_reservation(h, vma, address);
 
 		if (!(vma->vm_flags & VM_MAYSHARE))
 			pagecache_page = hugetlbfs_pagecache_page(h,
@@ -3437,7 +3679,7 @@ out_ptl:
 		put_page(pagecache_page);
 	}
 out_mutex:
-	mutex_unlock(&htlb_fault_mutex_table[hash]);
+	mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 	/*
 	 * Generally it's safe to hold refcount during waiting page lock. But
 	 * here we just wait to defer the next page fault to avoid busy loop and
@@ -3726,12 +3968,15 @@ int hugetlb_reserve_pages(struct inode *inode,
 	}
 	return 0;
 out_err:
+	if (!vma || vma->vm_flags & VM_MAYSHARE)
+		region_abort(resv_map, from, to);
 	if (vma && is_vma_resv_set(vma, HPAGE_RESV_OWNER))
 		kref_put(&resv_map->refs, resv_map_release);
 	return ret;
 }
 
-void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed)
+long hugetlb_unreserve_pages(struct inode *inode, long start, long end,
+								long freed)
 {
 	struct hstate *h = hstate_inode(inode);
 	struct resv_map *resv_map = inode_resv_map(inode);
@@ -3739,8 +3984,17 @@ void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed)
 	struct hugepage_subpool *spool = subpool_inode(inode);
 	long gbl_reserve;
 
-	if (resv_map)
-		chg = region_truncate(resv_map, offset);
+	if (resv_map) {
+		chg = region_del(resv_map, start, end);
+		/*
+		 * region_del() can fail in the rare case where a region
+		 * must be split and another region descriptor can not be
+		 * allocated.  If end == LONG_MAX, it will not fail.
+		 */
+		if (chg < 0)
+			return chg;
+	}
+
 	spin_lock(&inode->i_lock);
 	inode->i_blocks -= (blocks_per_huge_page(h) * freed);
 	spin_unlock(&inode->i_lock);
@@ -3751,6 +4005,8 @@ void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed)
 	 */
 	gbl_reserve = hugepage_subpool_put_pages(spool, (chg - freed));
 	hugetlb_acct_memory(h, -gbl_reserve);
+
+	return 0;
 }
 
 #ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE

mm/hwpoison-inject.c

@@ -58,7 +58,7 @@ inject:
 	pr_info("Injecting memory failure at pfn %#lx\n", pfn);
 	return memory_failure(pfn, 18, MF_COUNT_INCREASED);
 put_out:
-	put_page(p);
+	put_hwpoison_page(p);
 	return 0;
 }
 

mm/internal.h

@@ -182,6 +182,7 @@ struct compact_control {
 	unsigned long nr_migratepages;	/* Number of pages to migrate */
 	unsigned long free_pfn;		/* isolate_freepages search base */
 	unsigned long migrate_pfn;	/* isolate_migratepages search base */
+	unsigned long last_migrated_pfn;/* Not yet flushed page being freed */
 	enum migrate_mode mode;		/* Async or sync migration mode */
 	bool ignore_skip_hint;		/* Scan blocks even if marked skip */
 	int order;			/* order a direct compactor needs */

mm/kmemleak.c

@@ -838,6 +838,7 @@ static void __init log_early(int op_type, const void *ptr, size_t size,
 	}
 
 	if (crt_early_log >= ARRAY_SIZE(early_log)) {
+		crt_early_log++;
 		kmemleak_disable();
 		return;
 	}
@@ -1882,7 +1883,7 @@ void __init kmemleak_init(void)
 	object_cache = KMEM_CACHE(kmemleak_object, SLAB_NOLEAKTRACE);
 	scan_area_cache = KMEM_CACHE(kmemleak_scan_area, SLAB_NOLEAKTRACE);
 
-	if (crt_early_log >= ARRAY_SIZE(early_log))
+	if (crt_early_log > ARRAY_SIZE(early_log))
 		pr_warning("Early log buffer exceeded (%d), please increase "
 			   "DEBUG_KMEMLEAK_EARLY_LOG_SIZE\n", crt_early_log);
 

mm/list_lru.c

@@ -99,8 +99,8 @@ bool list_lru_add(struct list_lru *lru, struct list_head *item)
 	struct list_lru_one *l;
 
 	spin_lock(&nlru->lock);
-	l = list_lru_from_kmem(nlru, item);
 	if (list_empty(item)) {
+		l = list_lru_from_kmem(nlru, item);
 		list_add_tail(item, &l->list);
 		l->nr_items++;
 		spin_unlock(&nlru->lock);
@@ -118,8 +118,8 @@ bool list_lru_del(struct list_lru *lru, struct list_head *item)
 	struct list_lru_one *l;
 
 	spin_lock(&nlru->lock);
-	l = list_lru_from_kmem(nlru, item);
 	if (!list_empty(item)) {
+		l = list_lru_from_kmem(nlru, item);
 		list_del_init(item);
 		l->nr_items--;
 		spin_unlock(&nlru->lock);

mm/madvise.c

@@ -301,7 +301,7 @@ static long madvise_remove(struct vm_area_struct *vma,
 
 	*prev = NULL;	/* tell sys_madvise we drop mmap_sem */
 
-	if (vma->vm_flags & (VM_LOCKED | VM_HUGETLB))
+	if (vma->vm_flags & VM_LOCKED)
 		return -EINVAL;
 
 	f = vma->vm_file;

mm/memblock.c

@@ -91,7 +91,7 @@ static unsigned long __init_memblock memblock_addrs_overlap(phys_addr_t base1, p
 	return ((base1 < (base2 + size2)) && (base2 < (base1 + size1)));
 }
 
-static long __init_memblock memblock_overlaps_region(struct memblock_type *type,
+bool __init_memblock memblock_overlaps_region(struct memblock_type *type,
 					phys_addr_t base, phys_addr_t size)
 {
 	unsigned long i;
@@ -103,7 +103,7 @@ static long __init_memblock memblock_overlaps_region(struct memblock_type *type,
 			break;
 	}
 
-	return (i < type->cnt) ? i : -1;
+	return i < type->cnt;
 }
 
 /*
@@ -569,6 +569,7 @@ repeat:
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
 			WARN_ON(nid != memblock_get_region_node(rgn));
 #endif
+			WARN_ON(flags != rgn->flags);
 			nr_new++;
 			if (insert)
 				memblock_insert_region(type, i++, base,
@@ -614,14 +615,14 @@ static int __init_memblock memblock_add_region(phys_addr_t base,
 						int nid,
 						unsigned long flags)
 {
-	struct memblock_type *_rgn = &memblock.memory;
+	struct memblock_type *type = &memblock.memory;
 
 	memblock_dbg("memblock_add: [%#016llx-%#016llx] flags %#02lx %pF\n",
 		     (unsigned long long)base,
 		     (unsigned long long)base + size - 1,
 		     flags, (void *)_RET_IP_);
 
-	return memblock_add_range(_rgn, base, size, nid, flags);
+	return memblock_add_range(type, base, size, nid, flags);
 }
 
 int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size)
@@ -761,7 +762,7 @@ int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size)
  *
  * This function isolates region [@base, @base + @size), and sets/clears flag
  *
- * Return 0 on succees, -errno on failure.
+ * Return 0 on success, -errno on failure.
  */
 static int __init_memblock memblock_setclr_flag(phys_addr_t base,
 				phys_addr_t size, int set, int flag)
@@ -788,7 +789,7 @@ static int __init_memblock memblock_setclr_flag(phys_addr_t base,
  * @base: the base phys addr of the region
  * @size: the size of the region
  *
- * Return 0 on succees, -errno on failure.
+ * Return 0 on success, -errno on failure.
  */
 int __init_memblock memblock_mark_hotplug(phys_addr_t base, phys_addr_t size)
 {
@@ -800,7 +801,7 @@ int __init_memblock memblock_mark_hotplug(phys_addr_t base, phys_addr_t size)
  * @base: the base phys addr of the region
  * @size: the size of the region
  *
- * Return 0 on succees, -errno on failure.
+ * Return 0 on success, -errno on failure.
  */
 int __init_memblock memblock_clear_hotplug(phys_addr_t base, phys_addr_t size)
 {
@@ -812,7 +813,7 @@ int __init_memblock memblock_clear_hotplug(phys_addr_t base, phys_addr_t size)
  * @base: the base phys addr of the region
  * @size: the size of the region
  *
- * Return 0 on succees, -errno on failure.
+ * Return 0 on success, -errno on failure.
  */
 int __init_memblock memblock_mark_mirror(phys_addr_t base, phys_addr_t size)
 {
@@ -834,10 +835,10 @@ void __init_memblock __next_reserved_mem_region(u64 *idx,
 					   phys_addr_t *out_start,
 					   phys_addr_t *out_end)
 {
-	struct memblock_type *rsv = &memblock.reserved;
+	struct memblock_type *type = &memblock.reserved;
 
-	if (*idx >= 0 && *idx < rsv->cnt) {
-		struct memblock_region *r = &rsv->regions[*idx];
+	if (*idx >= 0 && *idx < type->cnt) {
+		struct memblock_region *r = &type->regions[*idx];
 		phys_addr_t base = r->base;
 		phys_addr_t size = r->size;
 
@@ -975,7 +976,7 @@ void __init_memblock __next_mem_range(u64 *idx, int nid, ulong flags,
  * in type_b.
  *
  * @idx: pointer to u64 loop variable
- * @nid: nid: node selector, %NUMA_NO_NODE for all nodes
+ * @nid: node selector, %NUMA_NO_NODE for all nodes
  * @flags: pick from blocks based on memory attributes
  * @type_a: pointer to memblock_type from where the range is taken
  * @type_b: pointer to memblock_type which excludes memory from being taken
@@ -1565,12 +1566,12 @@ int __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t size
  * Check if the region [@base, @base+@size) intersects a reserved memory block.
  *
  * RETURNS:
- * 0 if false, non-zero if true
+ * True if they intersect, false if not.
  */
-int __init_memblock memblock_is_region_reserved(phys_addr_t base, phys_addr_t size)
+bool __init_memblock memblock_is_region_reserved(phys_addr_t base, phys_addr_t size)
 {
 	memblock_cap_size(base, &size);
-	return memblock_overlaps_region(&memblock.reserved, base, size) >= 0;
+	return memblock_overlaps_region(&memblock.reserved, base, size);
 }
 
 void __init_memblock memblock_trim_memory(phys_addr_t align)

mm/memcontrol.c

@@ -111,56 +111,10 @@ static const char * const mem_cgroup_lru_names[] = {
 	"unevictable",
 };
 
-/*
- * Per memcg event counter is incremented at every pagein/pageout. With THP,
- * it will be incremated by the number of pages. This counter is used for
- * for trigger some periodic events. This is straightforward and better
- * than using jiffies etc. to handle periodic memcg event.
- */
-enum mem_cgroup_events_target {
-	MEM_CGROUP_TARGET_THRESH,
-	MEM_CGROUP_TARGET_SOFTLIMIT,
-	MEM_CGROUP_TARGET_NUMAINFO,
-	MEM_CGROUP_NTARGETS,
-};
 #define THRESHOLDS_EVENTS_TARGET 128
 #define SOFTLIMIT_EVENTS_TARGET 1024
 #define NUMAINFO_EVENTS_TARGET	1024
 
-struct mem_cgroup_stat_cpu {
-	long count[MEM_CGROUP_STAT_NSTATS];
-	unsigned long events[MEMCG_NR_EVENTS];
-	unsigned long nr_page_events;
-	unsigned long targets[MEM_CGROUP_NTARGETS];
-};
-
-struct reclaim_iter {
-	struct mem_cgroup *position;
-	/* scan generation, increased every round-trip */
-	unsigned int generation;
-};
-
-/*
- * per-zone information in memory controller.
- */
-struct mem_cgroup_per_zone {
-	struct lruvec		lruvec;
-	unsigned long		lru_size[NR_LRU_LISTS];
-
-	struct reclaim_iter	iter[DEF_PRIORITY + 1];
-
-	struct rb_node		tree_node;	/* RB tree node */
-	unsigned long		usage_in_excess;/* Set to the value by which */
-						/* the soft limit is exceeded*/
-	bool			on_tree;
-	struct mem_cgroup	*memcg;		/* Back pointer, we cannot */
-						/* use container_of	   */
-};
-
-struct mem_cgroup_per_node {
-	struct mem_cgroup_per_zone zoneinfo[MAX_NR_ZONES];
-};
-
 /*
  * Cgroups above their limits are maintained in a RB-Tree, independent of
  * their hierarchy representation
@@ -181,32 +135,6 @@ struct mem_cgroup_tree {
 
 static struct mem_cgroup_tree soft_limit_tree __read_mostly;
 
-struct mem_cgroup_threshold {
-	struct eventfd_ctx *eventfd;
-	unsigned long threshold;
-};
-
-/* For threshold */
-struct mem_cgroup_threshold_ary {
-	/* An array index points to threshold just below or equal to usage. */
-	int current_threshold;
-	/* Size of entries[] */
-	unsigned int size;
-	/* Array of thresholds */
-	struct mem_cgroup_threshold entries[0];
-};
-
-struct mem_cgroup_thresholds {
-	/* Primary thresholds array */
-	struct mem_cgroup_threshold_ary *primary;
-	/*
-	 * Spare threshold array.
-	 * This is needed to make mem_cgroup_unregister_event() "never fail".
-	 * It must be able to store at least primary->size - 1 entries.
-	 */
-	struct mem_cgroup_threshold_ary *spare;
-};
-
 /* for OOM */
 struct mem_cgroup_eventfd_list {
 	struct list_head list;
@@ -256,113 +184,6 @@ struct mem_cgroup_event {
 static void mem_cgroup_threshold(struct mem_cgroup *memcg);
 static void mem_cgroup_oom_notify(struct mem_cgroup *memcg);
 
-/*
- * The memory controller data structure. The memory controller controls both
- * page cache and RSS per cgroup. We would eventually like to provide
- * statistics based on the statistics developed by Rik Van Riel for clock-pro,
- * to help the administrator determine what knobs to tune.
- */
-struct mem_cgroup {
-	struct cgroup_subsys_state css;
-
-	/* Accounted resources */
-	struct page_counter memory;
-	struct page_counter memsw;
-	struct page_counter kmem;
-
-	/* Normal memory consumption range */
-	unsigned long low;
-	unsigned long high;
-
-	unsigned long soft_limit;
-
-	/* vmpressure notifications */
-	struct vmpressure vmpressure;
-
-	/* css_online() has been completed */
-	int initialized;
-
-	/*
-	 * Should the accounting and control be hierarchical, per subtree?
-	 */
-	bool use_hierarchy;
-
-	/* protected by memcg_oom_lock */
-	bool		oom_lock;
-	int		under_oom;
-
-	int	swappiness;
-	/* OOM-Killer disable */
-	int		oom_kill_disable;
-
-	/* protect arrays of thresholds */
-	struct mutex thresholds_lock;
-
-	/* thresholds for memory usage. RCU-protected */
-	struct mem_cgroup_thresholds thresholds;
-
-	/* thresholds for mem+swap usage. RCU-protected */
-	struct mem_cgroup_thresholds memsw_thresholds;
-
-	/* For oom notifier event fd */
-	struct list_head oom_notify;
-
-	/*
-	 * Should we move charges of a task when a task is moved into this
-	 * mem_cgroup ? And what type of charges should we move ?
-	 */
-	unsigned long move_charge_at_immigrate;
-	/*
-	 * set > 0 if pages under this cgroup are moving to other cgroup.
-	 */
-	atomic_t		moving_account;
-	/* taken only while moving_account > 0 */
-	spinlock_t		move_lock;
-	struct task_struct	*move_lock_task;
-	unsigned long		move_lock_flags;
-	/*
-	 * percpu counter.
-	 */
-	struct mem_cgroup_stat_cpu __percpu *stat;
-	spinlock_t pcp_counter_lock;
-
-#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_INET)
-	struct cg_proto tcp_mem;
-#endif
-#if defined(CONFIG_MEMCG_KMEM)
-        /* Index in the kmem_cache->memcg_params.memcg_caches array */
-	int kmemcg_id;
-	bool kmem_acct_activated;
-	bool kmem_acct_active;
-#endif
-
-	int last_scanned_node;
-#if MAX_NUMNODES > 1
-	nodemask_t	scan_nodes;
-	atomic_t	numainfo_events;
-	atomic_t	numainfo_updating;
-#endif
-
-#ifdef CONFIG_CGROUP_WRITEBACK
-	struct list_head cgwb_list;
-	struct wb_domain cgwb_domain;
-#endif
-
-	/* List of events which userspace want to receive */
-	struct list_head event_list;
-	spinlock_t event_list_lock;
-
-	struct mem_cgroup_per_node *nodeinfo[0];
-	/* WARNING: nodeinfo must be the last member here */
-};
-
-#ifdef CONFIG_MEMCG_KMEM
-bool memcg_kmem_is_active(struct mem_cgroup *memcg)
-{
-	return memcg->kmem_acct_active;
-}
-#endif
-
 /* Stuffs for move charges at task migration. */
 /*
  * Types of charges to be moved.
@@ -423,11 +244,6 @@ enum res_type {
  */
 static DEFINE_MUTEX(memcg_create_mutex);
 
-struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *s)
-{
-	return s ? container_of(s, struct mem_cgroup, css) : NULL;
-}
-
 /* Some nice accessors for the vmpressure. */
 struct vmpressure *memcg_to_vmpressure(struct mem_cgroup *memcg)
 {
@@ -499,8 +315,7 @@ void sock_update_memcg(struct sock *sk)
 		rcu_read_lock();
 		memcg = mem_cgroup_from_task(current);
 		cg_proto = sk->sk_prot->proto_cgroup(memcg);
-		if (!mem_cgroup_is_root(memcg) &&
-		    memcg_proto_active(cg_proto) &&
+		if (cg_proto && test_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags) &&
 		    css_tryget_online(&memcg->css)) {
 			sk->sk_cgrp = cg_proto;
 		}
@@ -593,11 +408,6 @@ mem_cgroup_zone_zoneinfo(struct mem_cgroup *memcg, struct zone *zone)
 	return &memcg->nodeinfo[nid]->zoneinfo[zid];
 }
 
-struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg)
-{
-	return &memcg->css;
-}
-
 /**
  * mem_cgroup_css_from_page - css of the memcg associated with a page
  * @page: page of interest
@@ -876,14 +686,6 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg,
 	__this_cpu_add(memcg->stat->nr_page_events, nr_pages);
 }
 
-unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru)
-{
-	struct mem_cgroup_per_zone *mz;
-
-	mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec);
-	return mz->lru_size[lru];
-}
-
 static unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
 						  int nid,
 						  unsigned int lru_mask)
@@ -986,6 +788,7 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
 
 	return mem_cgroup_from_css(task_css(p, memory_cgrp_id));
 }
+EXPORT_SYMBOL(mem_cgroup_from_task);
 
 static struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm)
 {
@@ -1031,7 +834,7 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 				   struct mem_cgroup *prev,
 				   struct mem_cgroup_reclaim_cookie *reclaim)
 {
-	struct reclaim_iter *uninitialized_var(iter);
+	struct mem_cgroup_reclaim_iter *uninitialized_var(iter);
 	struct cgroup_subsys_state *css = NULL;
 	struct mem_cgroup *memcg = NULL;
 	struct mem_cgroup *pos = NULL;
@@ -1173,30 +976,6 @@ void mem_cgroup_iter_break(struct mem_cgroup *root,
 	     iter != NULL;				\
 	     iter = mem_cgroup_iter(NULL, iter, NULL))
 
-void __mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx)
-{
-	struct mem_cgroup *memcg;
-
-	rcu_read_lock();
-	memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
-	if (unlikely(!memcg))
-		goto out;
-
-	switch (idx) {
-	case PGFAULT:
-		this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGFAULT]);
-		break;
-	case PGMAJFAULT:
-		this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGMAJFAULT]);
-		break;
-	default:
-		BUG();
-	}
-out:
-	rcu_read_unlock();
-}
-EXPORT_SYMBOL(__mem_cgroup_count_vm_event);
-
 /**
  * mem_cgroup_zone_lruvec - get the lru list vector for a zone and memcg
  * @zone: zone of the wanted lruvec
@@ -1295,15 +1074,6 @@ void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
 	VM_BUG_ON((long)(*lru_size) < 0);
 }
 
-bool mem_cgroup_is_descendant(struct mem_cgroup *memcg, struct mem_cgroup *root)
-{
-	if (root == memcg)
-		return true;
-	if (!root->use_hierarchy)
-		return false;
-	return cgroup_is_descendant(memcg->css.cgroup, root->css.cgroup);
-}
-
 bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg)
 {
 	struct mem_cgroup *task_memcg;
@@ -1330,39 +1100,6 @@ bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg)
 	return ret;
 }
 
-int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec)
-{
-	unsigned long inactive_ratio;
-	unsigned long inactive;
-	unsigned long active;
-	unsigned long gb;
-
-	inactive = mem_cgroup_get_lru_size(lruvec, LRU_INACTIVE_ANON);
-	active = mem_cgroup_get_lru_size(lruvec, LRU_ACTIVE_ANON);
-
-	gb = (inactive + active) >> (30 - PAGE_SHIFT);
-	if (gb)
-		inactive_ratio = int_sqrt(10 * gb);
-	else
-		inactive_ratio = 1;
-
-	return inactive * inactive_ratio < active;
-}
-
-bool mem_cgroup_lruvec_online(struct lruvec *lruvec)
-{
-	struct mem_cgroup_per_zone *mz;
-	struct mem_cgroup *memcg;
-
-	if (mem_cgroup_disabled())
-		return true;
-
-	mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec);
-	memcg = mz->memcg;
-
-	return !!(memcg->css.flags & CSS_ONLINE);
-}
-
 #define mem_cgroup_from_counter(counter, member)	\
 	container_of(counter, struct mem_cgroup, member)
 
@@ -1394,15 +1131,6 @@ static unsigned long mem_cgroup_margin(struct mem_cgroup *memcg)
 	return margin;
 }
 
-int mem_cgroup_swappiness(struct mem_cgroup *memcg)
-{
-	/* root ? */
-	if (mem_cgroup_disabled() || !memcg->css.parent)
-		return vm_swappiness;
-
-	return memcg->swappiness;
-}
-
 /*
  * A routine for checking "mem" is under move_account() or not.
  *
@@ -1545,6 +1273,12 @@ static unsigned long mem_cgroup_get_limit(struct mem_cgroup *memcg)
 static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 				     int order)
 {
+	struct oom_control oc = {
+		.zonelist = NULL,
+		.nodemask = NULL,
+		.gfp_mask = gfp_mask,
+		.order = order,
+	};
 	struct mem_cgroup *iter;
 	unsigned long chosen_points = 0;
 	unsigned long totalpages;
@@ -1563,7 +1297,7 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 		goto unlock;
 	}
 
-	check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, order, NULL, memcg);
+	check_panic_on_oom(&oc, CONSTRAINT_MEMCG, memcg);
 	totalpages = mem_cgroup_get_limit(memcg) ? : 1;
 	for_each_mem_cgroup_tree(iter, memcg) {
 		struct css_task_iter it;
@@ -1571,8 +1305,7 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 
 		css_task_iter_start(&iter->css, &it);
 		while ((task = css_task_iter_next(&it))) {
-			switch (oom_scan_process_thread(task, totalpages, NULL,
-							false)) {
+			switch (oom_scan_process_thread(&oc, task, totalpages)) {
 			case OOM_SCAN_SELECT:
 				if (chosen)
 					put_task_struct(chosen);
@@ -1610,8 +1343,8 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 
 	if (chosen) {
 		points = chosen_points * 1000 / totalpages;
-		oom_kill_process(chosen, gfp_mask, order, points, totalpages,
-				 memcg, NULL, "Memory cgroup out of memory");
+		oom_kill_process(&oc, chosen, points, totalpages, memcg,
+				 "Memory cgroup out of memory");
 	}
 unlock:
 	mutex_unlock(&oom_lock);
@@ -2062,23 +1795,6 @@ void mem_cgroup_end_page_stat(struct mem_cgroup *memcg)
 }
 EXPORT_SYMBOL(mem_cgroup_end_page_stat);
 
-/**
- * mem_cgroup_update_page_stat - update page state statistics
- * @memcg: memcg to account against
- * @idx: page state item to account
- * @val: number of pages (positive or negative)
- *
- * See mem_cgroup_begin_page_stat() for locking requirements.
- */
-void mem_cgroup_update_page_stat(struct mem_cgroup *memcg,
-				 enum mem_cgroup_stat_index idx, int val)
-{
-	VM_BUG_ON(!rcu_read_lock_held());
-
-	if (memcg)
-		this_cpu_add(memcg->stat->count[idx], val);
-}
-
 /*
  * size of first charge trial. "32" comes from vmscan.c's magic value.
  * TODO: maybe necessary to use big numbers in big irons.
@@ -2504,16 +2220,6 @@ void memcg_uncharge_kmem(struct mem_cgroup *memcg, unsigned long nr_pages)
 	css_put_many(&memcg->css, nr_pages);
 }
 
-/*
- * helper for acessing a memcg's index. It will be used as an index in the
- * child cache array in kmem_cache, and also to derive its name. This function
- * will return -1 when this is not a kmem-limited memcg.
- */
-int memcg_cache_id(struct mem_cgroup *memcg)
-{
-	return memcg ? memcg->kmemcg_id : -1;
-}
-
 static int memcg_alloc_cache_id(void)
 {
 	int id, size;
@@ -5127,10 +4833,12 @@ static void mem_cgroup_clear_mc(void)
 static int mem_cgroup_can_attach(struct cgroup_subsys_state *css,
 				 struct cgroup_taskset *tset)
 {
-	struct task_struct *p = cgroup_taskset_first(tset);
-	int ret = 0;
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+	struct mem_cgroup *from;
+	struct task_struct *p;
+	struct mm_struct *mm;
 	unsigned long move_flags;
+	int ret = 0;
 
 	/*
 	 * We are now commited to this value whatever it is. Changes in this
@@ -5138,36 +4846,37 @@ static int mem_cgroup_can_attach(struct cgroup_subsys_state *css,
 	 * So we need to save it, and keep it going.
 	 */
 	move_flags = READ_ONCE(memcg->move_charge_at_immigrate);
-	if (move_flags) {
-		struct mm_struct *mm;
-		struct mem_cgroup *from = mem_cgroup_from_task(p);
+	if (!move_flags)
+		return 0;
 
-		VM_BUG_ON(from == memcg);
+	p = cgroup_taskset_first(tset);
+	from = mem_cgroup_from_task(p);
 
-		mm = get_task_mm(p);
-		if (!mm)
-			return 0;
-		/* We move charges only when we move a owner of the mm */
-		if (mm->owner == p) {
-			VM_BUG_ON(mc.from);
-			VM_BUG_ON(mc.to);
-			VM_BUG_ON(mc.precharge);
-			VM_BUG_ON(mc.moved_charge);
-			VM_BUG_ON(mc.moved_swap);
-
-			spin_lock(&mc.lock);
-			mc.from = from;
-			mc.to = memcg;
-			mc.flags = move_flags;
-			spin_unlock(&mc.lock);
-			/* We set mc.moving_task later */
-
-			ret = mem_cgroup_precharge_mc(mm);
-			if (ret)
-				mem_cgroup_clear_mc();
-		}
-		mmput(mm);
+	VM_BUG_ON(from == memcg);
+
+	mm = get_task_mm(p);
+	if (!mm)
+		return 0;
+	/* We move charges only when we move a owner of the mm */
+	if (mm->owner == p) {
+		VM_BUG_ON(mc.from);
+		VM_BUG_ON(mc.to);
+		VM_BUG_ON(mc.precharge);
+		VM_BUG_ON(mc.moved_charge);
+		VM_BUG_ON(mc.moved_swap);
+
+		spin_lock(&mc.lock);
+		mc.from = from;
+		mc.to = memcg;
+		mc.flags = move_flags;
+		spin_unlock(&mc.lock);
+		/* We set mc.moving_task later */
+
+		ret = mem_cgroup_precharge_mc(mm);
+		if (ret)
+			mem_cgroup_clear_mc();
 	}
+	mmput(mm);
 	return ret;
 }
 
@@ -5520,19 +5229,6 @@ struct cgroup_subsys memory_cgrp_subsys = {
 	.early_init = 0,
 };
 
-/**
- * mem_cgroup_events - count memory events against a cgroup
- * @memcg: the memory cgroup
- * @idx: the event index
- * @nr: the number of events to account for
- */
-void mem_cgroup_events(struct mem_cgroup *memcg,
-		       enum mem_cgroup_events_index idx,
-		       unsigned int nr)
-{
-	this_cpu_add(memcg->stat->events[idx], nr);
-}
-
 /**
  * mem_cgroup_low - check if memory consumption is below the normal range
  * @root: the highest ancestor to consider

mm/memory-failure.c

@@ -146,7 +146,7 @@ static int hwpoison_filter_task(struct page *p)
 	if (!mem)
 		return -EINVAL;
 
-	css = mem_cgroup_css(mem);
+	css = &mem->css;
 	ino = cgroup_ino(css->cgroup);
 	css_put(css);
 
@@ -934,6 +934,27 @@ int get_hwpoison_page(struct page *page)
 }
 EXPORT_SYMBOL_GPL(get_hwpoison_page);
 
+/**
+ * put_hwpoison_page() - Put refcount for memory error handling:
+ * @page:	raw error page (hit by memory error)
+ */
+void put_hwpoison_page(struct page *page)
+{
+	struct page *head = compound_head(page);
+
+	if (PageHuge(head)) {
+		put_page(head);
+		return;
+	}
+
+	if (PageTransHuge(head))
+		if (page != head)
+			put_page(head);
+
+	put_page(page);
+}
+EXPORT_SYMBOL_GPL(put_hwpoison_page);
+
 /*
  * Do all that is necessary to remove user space mappings. Unmap
  * the pages and send SIGBUS to the processes if the data was dirty.
@@ -1100,7 +1121,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 		nr_pages = 1 << compound_order(hpage);
 	else /* normal page or thp */
 		nr_pages = 1;
-	atomic_long_add(nr_pages, &num_poisoned_pages);
+	num_poisoned_pages_add(nr_pages);
 
 	/*
 	 * We need/can do nothing about count=0 pages.
@@ -1128,7 +1149,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 			if (PageHWPoison(hpage)) {
 				if ((hwpoison_filter(p) && TestClearPageHWPoison(p))
 				    || (p != hpage && TestSetPageHWPoison(hpage))) {
-					atomic_long_sub(nr_pages, &num_poisoned_pages);
+					num_poisoned_pages_sub(nr_pages);
 					unlock_page(hpage);
 					return 0;
 				}
@@ -1152,10 +1173,8 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 			else
 				pr_err("MCE: %#lx: thp split failed\n", pfn);
 			if (TestClearPageHWPoison(p))
-				atomic_long_sub(nr_pages, &num_poisoned_pages);
-			put_page(p);
-			if (p != hpage)
-				put_page(hpage);
+				num_poisoned_pages_sub(nr_pages);
+			put_hwpoison_page(p);
 			return -EBUSY;
 		}
 		VM_BUG_ON_PAGE(!page_count(p), p);
@@ -1214,16 +1233,16 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 	 */
 	if (!PageHWPoison(p)) {
 		printk(KERN_ERR "MCE %#lx: just unpoisoned\n", pfn);
-		atomic_long_sub(nr_pages, &num_poisoned_pages);
+		num_poisoned_pages_sub(nr_pages);
 		unlock_page(hpage);
-		put_page(hpage);
+		put_hwpoison_page(hpage);
 		return 0;
 	}
 	if (hwpoison_filter(p)) {
 		if (TestClearPageHWPoison(p))
-			atomic_long_sub(nr_pages, &num_poisoned_pages);
+			num_poisoned_pages_sub(nr_pages);
 		unlock_page(hpage);
-		put_page(hpage);
+		put_hwpoison_page(hpage);
 		return 0;
 	}
 
@@ -1237,7 +1256,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 	if (PageHuge(p) && PageTail(p) && TestSetPageHWPoison(hpage)) {
 		action_result(pfn, MF_MSG_POISONED_HUGE, MF_IGNORED);
 		unlock_page(hpage);
-		put_page(hpage);
+		put_hwpoison_page(hpage);
 		return 0;
 	}
 	/*
@@ -1426,6 +1445,22 @@ int unpoison_memory(unsigned long pfn)
 		return 0;
 	}
 
+	if (page_count(page) > 1) {
+		pr_info("MCE: Someone grabs the hwpoison page %#lx\n", pfn);
+		return 0;
+	}
+
+	if (page_mapped(page)) {
+		pr_info("MCE: Someone maps the hwpoison page %#lx\n", pfn);
+		return 0;
+	}
+
+	if (page_mapping(page)) {
+		pr_info("MCE: the hwpoison page has non-NULL mapping %#lx\n",
+			pfn);
+		return 0;
+	}
+
 	/*
 	 * unpoison_memory() can encounter thp only when the thp is being
 	 * worked by memory_failure() and the page lock is not held yet.
@@ -1450,7 +1485,7 @@ int unpoison_memory(unsigned long pfn)
 			return 0;
 		}
 		if (TestClearPageHWPoison(p))
-			atomic_long_dec(&num_poisoned_pages);
+			num_poisoned_pages_dec();
 		pr_info("MCE: Software-unpoisoned free page %#lx\n", pfn);
 		return 0;
 	}
@@ -1464,16 +1499,16 @@ int unpoison_memory(unsigned long pfn)
 	 */
 	if (TestClearPageHWPoison(page)) {
 		pr_info("MCE: Software-unpoisoned page %#lx\n", pfn);
-		atomic_long_sub(nr_pages, &num_poisoned_pages);
+		num_poisoned_pages_sub(nr_pages);
 		freeit = 1;
 		if (PageHuge(page))
 			clear_page_hwpoison_huge_page(page);
 	}
 	unlock_page(page);
 
-	put_page(page);
+	put_hwpoison_page(page);
 	if (freeit && !(pfn == my_zero_pfn(0) && page_count(p) == 1))
-		put_page(page);
+		put_hwpoison_page(page);
 
 	return 0;
 }
@@ -1486,7 +1521,7 @@ static struct page *new_page(struct page *p, unsigned long private, int **x)
 		return alloc_huge_page_node(page_hstate(compound_head(p)),
 						   nid);
 	else
-		return alloc_pages_exact_node(nid, GFP_HIGHUSER_MOVABLE, 0);
+		return __alloc_pages_node(nid, GFP_HIGHUSER_MOVABLE, 0);
 }
 
 /*
@@ -1533,7 +1568,7 @@ static int get_any_page(struct page *page, unsigned long pfn, int flags)
 		/*
 		 * Try to free it.
 		 */
-		put_page(page);
+		put_hwpoison_page(page);
 		shake_page(page, 1);
 
 		/*
@@ -1542,7 +1577,7 @@ static int get_any_page(struct page *page, unsigned long pfn, int flags)
 		ret = __get_any_page(page, pfn, 0);
 		if (!PageLRU(page)) {
 			/* Drop page reference which is from __get_any_page() */
-			put_page(page);
+			put_hwpoison_page(page);
 			pr_info("soft_offline: %#lx: unknown non LRU page type %lx\n",
 				pfn, page->flags);
 			return -EIO;
@@ -1565,7 +1600,7 @@ static int soft_offline_huge_page(struct page *page, int flags)
 	lock_page(hpage);
 	if (PageHWPoison(hpage)) {
 		unlock_page(hpage);
-		put_page(hpage);
+		put_hwpoison_page(hpage);
 		pr_info("soft offline: %#lx hugepage already poisoned\n", pfn);
 		return -EBUSY;
 	}
@@ -1576,7 +1611,7 @@ static int soft_offline_huge_page(struct page *page, int flags)
 	 * get_any_page() and isolate_huge_page() takes a refcount each,
 	 * so need to drop one here.
 	 */
-	put_page(hpage);
+	put_hwpoison_page(hpage);
 	if (!ret) {
 		pr_info("soft offline: %#lx hugepage failed to isolate\n", pfn);
 		return -EBUSY;
@@ -1600,11 +1635,10 @@ static int soft_offline_huge_page(struct page *page, int flags)
 		if (PageHuge(page)) {
 			set_page_hwpoison_huge_page(hpage);
 			dequeue_hwpoisoned_huge_page(hpage);
-			atomic_long_add(1 << compound_order(hpage),
-					&num_poisoned_pages);
+			num_poisoned_pages_add(1 << compound_order(hpage));
 		} else {
 			SetPageHWPoison(page);
-			atomic_long_inc(&num_poisoned_pages);
+			num_poisoned_pages_inc();
 		}
 	}
 	return ret;
@@ -1625,7 +1659,7 @@ static int __soft_offline_page(struct page *page, int flags)
 	wait_on_page_writeback(page);
 	if (PageHWPoison(page)) {
 		unlock_page(page);
-		put_page(page);
+		put_hwpoison_page(page);
 		pr_info("soft offline: %#lx page already poisoned\n", pfn);
 		return -EBUSY;
 	}
@@ -1640,10 +1674,10 @@ static int __soft_offline_page(struct page *page, int flags)
 	 * would need to fix isolation locking first.
 	 */
 	if (ret == 1) {
-		put_page(page);
+		put_hwpoison_page(page);
 		pr_info("soft_offline: %#lx: invalidated\n", pfn);
 		SetPageHWPoison(page);
-		atomic_long_inc(&num_poisoned_pages);
+		num_poisoned_pages_inc();
 		return 0;
 	}
 
@@ -1657,14 +1691,12 @@ static int __soft_offline_page(struct page *page, int flags)
 	 * Drop page reference which is came from get_any_page()
 	 * successful isolate_lru_page() already took another one.
 	 */
-	put_page(page);
+	put_hwpoison_page(page);
 	if (!ret) {
 		LIST_HEAD(pagelist);
 		inc_zone_page_state(page, NR_ISOLATED_ANON +
 					page_is_file_cache(page));
 		list_add(&page->lru, &pagelist);
-		if (!TestSetPageHWPoison(page))
-			atomic_long_inc(&num_poisoned_pages);
 		ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL,
 					MIGRATE_SYNC, MR_MEMORY_FAILURE);
 		if (ret) {
@@ -1679,8 +1711,6 @@ static int __soft_offline_page(struct page *page, int flags)
 				pfn, ret, page->flags);
 			if (ret > 0)
 				ret = -EIO;
-			if (TestClearPageHWPoison(page))
-				atomic_long_dec(&num_poisoned_pages);
 		}
 	} else {
 		pr_info("soft offline: %#lx: isolation failed: %d, page count %d, type %lx\n",
@@ -1719,12 +1749,16 @@ int soft_offline_page(struct page *page, int flags)
 
 	if (PageHWPoison(page)) {
 		pr_info("soft offline: %#lx page already poisoned\n", pfn);
+		if (flags & MF_COUNT_INCREASED)
+			put_hwpoison_page(page);
 		return -EBUSY;
 	}
 	if (!PageHuge(page) && PageTransHuge(hpage)) {
 		if (PageAnon(hpage) && unlikely(split_huge_page(hpage))) {
 			pr_info("soft offline: %#lx: failed to split THP\n",
 				pfn);
+			if (flags & MF_COUNT_INCREASED)
+				put_hwpoison_page(page);
 			return -EBUSY;
 		}
 	}
@@ -1742,11 +1776,10 @@ int soft_offline_page(struct page *page, int flags)
 		if (PageHuge(page)) {
 			set_page_hwpoison_huge_page(hpage);
 			if (!dequeue_hwpoisoned_huge_page(hpage))
-				atomic_long_add(1 << compound_order(hpage),
-					&num_poisoned_pages);
+				num_poisoned_pages_add(1 << compound_order(hpage));
 		} else {
 			if (!TestSetPageHWPoison(page))
-				atomic_long_inc(&num_poisoned_pages);
+				num_poisoned_pages_inc();
 		}
 	}
 	return ret;

mm/memory.c

@@ -2426,8 +2426,6 @@ void unmap_mapping_range(struct address_space *mapping,
 	if (details.last_index < details.first_index)
 		details.last_index = ULONG_MAX;
 
-
-	/* DAX uses i_mmap_lock to serialise file truncate vs page fault */
 	i_mmap_lock_write(mapping);
 	if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap)))
 		unmap_mapping_range_tree(&mapping->i_mmap, &details);
@@ -3015,9 +3013,9 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		} else {
 			/*
 			 * The fault handler has no page to lock, so it holds
-			 * i_mmap_lock for read to protect against truncate.
+			 * i_mmap_lock for write to protect against truncate.
 			 */
-			i_mmap_unlock_read(vma->vm_file->f_mapping);
+			i_mmap_unlock_write(vma->vm_file->f_mapping);
 		}
 		goto uncharge_out;
 	}
@@ -3031,9 +3029,9 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	} else {
 		/*
 		 * The fault handler has no page to lock, so it holds
-		 * i_mmap_lock for read to protect against truncate.
+		 * i_mmap_lock for write to protect against truncate.
 		 */
-		i_mmap_unlock_read(vma->vm_file->f_mapping);
+		i_mmap_unlock_write(vma->vm_file->f_mapping);
 	}
 	return ret;
 uncharge_out:
@@ -3232,6 +3230,27 @@ out:
 	return 0;
 }
 
+static int create_huge_pmd(struct mm_struct *mm, struct vm_area_struct *vma,
+			unsigned long address, pmd_t *pmd, unsigned int flags)
+{
+	if (!vma->vm_ops)
+		return do_huge_pmd_anonymous_page(mm, vma, address, pmd, flags);
+	if (vma->vm_ops->pmd_fault)
+		return vma->vm_ops->pmd_fault(vma, address, pmd, flags);
+	return VM_FAULT_FALLBACK;
+}
+
+static int wp_huge_pmd(struct mm_struct *mm, struct vm_area_struct *vma,
+			unsigned long address, pmd_t *pmd, pmd_t orig_pmd,
+			unsigned int flags)
+{
+	if (!vma->vm_ops)
+		return do_huge_pmd_wp_page(mm, vma, address, pmd, orig_pmd);
+	if (vma->vm_ops->pmd_fault)
+		return vma->vm_ops->pmd_fault(vma, address, pmd, flags);
+	return VM_FAULT_FALLBACK;
+}
+
 /*
  * These routines also need to handle stuff like marking pages dirty
  * and/or accessed for architectures that don't do it in hardware (most
@@ -3267,12 +3286,12 @@ static int handle_pte_fault(struct mm_struct *mm,
 	barrier();
 	if (!pte_present(entry)) {
 		if (pte_none(entry)) {
-			if (vma->vm_ops)
+			if (vma_is_anonymous(vma))
+				return do_anonymous_page(mm, vma, address,
+							 pte, pmd, flags);
+			else
 				return do_fault(mm, vma, address, pte, pmd,
 						flags, entry);
-
-			return do_anonymous_page(mm, vma, address, pte, pmd,
-					flags);
 		}
 		return do_swap_page(mm, vma, address,
 					pte, pmd, flags, entry);
@@ -3334,10 +3353,7 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (!pmd)
 		return VM_FAULT_OOM;
 	if (pmd_none(*pmd) && transparent_hugepage_enabled(vma)) {
-		int ret = VM_FAULT_FALLBACK;
-		if (!vma->vm_ops)
-			ret = do_huge_pmd_anonymous_page(mm, vma, address,
-					pmd, flags);
+		int ret = create_huge_pmd(mm, vma, address, pmd, flags);
 		if (!(ret & VM_FAULT_FALLBACK))
 			return ret;
 	} else {
@@ -3361,8 +3377,8 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 							     orig_pmd, pmd);
 
 			if (dirty && !pmd_write(orig_pmd)) {
-				ret = do_huge_pmd_wp_page(mm, vma, address, pmd,
-							  orig_pmd);
+				ret = wp_huge_pmd(mm, vma, address, pmd,
+							orig_pmd, flags);
 				if (!(ret & VM_FAULT_FALLBACK))
 					return ret;
 			} else {

mm/mempolicy.c

@@ -608,9 +608,6 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end,
 
 	qp->prev = vma;
 
-	if (vma->vm_flags & VM_PFNMAP)
-		return 1;
-
 	if (flags & MPOL_MF_LAZY) {
 		/* Similar to task_numa_work, skip inaccessible VMAs */
 		if (vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))
@@ -945,7 +942,7 @@ static struct page *new_node_page(struct page *page, unsigned long node, int **x
 		return alloc_huge_page_node(page_hstate(compound_head(page)),
 					node);
 	else
-		return alloc_pages_exact_node(node, GFP_HIGHUSER_MOVABLE |
+		return __alloc_pages_node(node, GFP_HIGHUSER_MOVABLE |
 						    __GFP_THISNODE, 0);
 }
 
@@ -2001,7 +1998,7 @@ retry_cpuset:
 		nmask = policy_nodemask(gfp, pol);
 		if (!nmask || node_isset(hpage_node, *nmask)) {
 			mpol_cond_put(pol);
-			page = alloc_pages_exact_node(hpage_node,
+			page = __alloc_pages_node(hpage_node,
 						gfp | __GFP_THISNODE, order);
 			goto out;
 		}

mm/mempool.c

@@ -150,6 +150,9 @@ static void *remove_element(mempool_t *pool)
  */
 void mempool_destroy(mempool_t *pool)
 {
+	if (unlikely(!pool))
+		return;
+
 	while (pool->curr_nr) {
 		void *element = remove_element(pool);
 		pool->free(element, pool->pool_data);

mm/memtest.c

@@ -1,11 +1,6 @@
 #include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/string.h>
 #include <linux/types.h>
-#include <linux/mm.h>
-#include <linux/smp.h>
 #include <linux/init.h>
-#include <linux/pfn.h>
 #include <linux/memblock.h>
 
 static u64 patterns[] __initdata = {
@@ -31,10 +26,8 @@ static u64 patterns[] __initdata = {
 
 static void __init reserve_bad_mem(u64 pattern, phys_addr_t start_bad, phys_addr_t end_bad)
 {
-	printk(KERN_INFO "  %016llx bad mem addr %010llx - %010llx reserved\n",
-	       (unsigned long long) pattern,
-	       (unsigned long long) start_bad,
-	       (unsigned long long) end_bad);
+	pr_info("  %016llx bad mem addr %pa - %pa reserved\n",
+		cpu_to_be64(pattern), &start_bad, &end_bad);
 	memblock_reserve(start_bad, end_bad - start_bad);
 }
 
@@ -79,26 +72,26 @@ static void __init do_one_pass(u64 pattern, phys_addr_t start, phys_addr_t end)
 		this_start = clamp(this_start, start, end);
 		this_end = clamp(this_end, start, end);
 		if (this_start < this_end) {
-			printk(KERN_INFO "  %010llx - %010llx pattern %016llx\n",
-			       (unsigned long long)this_start,
-			       (unsigned long long)this_end,
-			       (unsigned long long)cpu_to_be64(pattern));
+			pr_info("  %pa - %pa pattern %016llx\n",
+				&this_start, &this_end, cpu_to_be64(pattern));
 			memtest(pattern, this_start, this_end - this_start);
 		}
 	}
 }
 
 /* default is disabled */
-static int memtest_pattern __initdata;
+static unsigned int memtest_pattern __initdata;
 
 static int __init parse_memtest(char *arg)
 {
+	int ret = 0;
+
 	if (arg)
-		memtest_pattern = simple_strtoul(arg, NULL, 0);
+		ret = kstrtouint(arg, 0, &memtest_pattern);
 	else
 		memtest_pattern = ARRAY_SIZE(patterns);
 
-	return 0;
+	return ret;
 }
 
 early_param("memtest", parse_memtest);
@@ -111,7 +104,7 @@ void __init early_memtest(phys_addr_t start, phys_addr_t end)
 	if (!memtest_pattern)
 		return;
 
-	printk(KERN_INFO "early_memtest: # of tests: %d\n", memtest_pattern);
+	pr_info("early_memtest: # of tests: %u\n", memtest_pattern);
 	for (i = memtest_pattern-1; i < UINT_MAX; --i) {
 		idx = i % ARRAY_SIZE(patterns);
 		do_one_pass(patterns[idx], start, end);

mm/migrate.c

@@ -880,8 +880,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage,
 	/* Establish migration ptes or remove ptes */
 	if (page_mapped(page)) {
 		try_to_unmap(page,
-			TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS|
-			TTU_IGNORE_HWPOISON);
+			TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS);
 		page_was_mapped = 1;
 	}
 
@@ -952,9 +951,11 @@ out:
 		dec_zone_page_state(page, NR_ISOLATED_ANON +
 				page_is_file_cache(page));
 		/* Soft-offlined page shouldn't go through lru cache list */
-		if (reason == MR_MEMORY_FAILURE)
+		if (reason == MR_MEMORY_FAILURE) {
 			put_page(page);
-		else
+			if (!test_set_page_hwpoison(page))
+				num_poisoned_pages_inc();
+		} else
 			putback_lru_page(page);
 	}
 
@@ -1194,7 +1195,7 @@ static struct page *new_page_node(struct page *p, unsigned long private,
 		return alloc_huge_page_node(page_hstate(compound_head(p)),
 					pm->node);
 	else
-		return alloc_pages_exact_node(pm->node,
+		return __alloc_pages_node(pm->node,
 				GFP_HIGHUSER_MOVABLE | __GFP_THISNODE, 0);
 }
 
@@ -1554,7 +1555,7 @@ static struct page *alloc_misplaced_dst_page(struct page *page,
 	int nid = (int) data;
 	struct page *newpage;
 
-	newpage = alloc_pages_exact_node(nid,
+	newpage = __alloc_pages_node(nid,
 					 (GFP_HIGHUSER_MOVABLE |
 					  __GFP_THISNODE | __GFP_NOMEMALLOC |
 					  __GFP_NORETRY | __GFP_NOWARN) &

mm/mmap.c

@@ -2455,7 +2455,7 @@ static int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
 	      unsigned long addr, int new_below)
 {
 	struct vm_area_struct *new;
-	int err = -ENOMEM;
+	int err;
 
 	if (is_vm_hugetlb_page(vma) && (addr &
 					~(huge_page_mask(hstate_vma(vma)))))
@@ -2463,7 +2463,7 @@ static int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
 	if (!new)
-		goto out_err;
+		return -ENOMEM;
 
 	/* most fields are the same, copy all, and then fixup */
 	*new = *vma;
@@ -2511,7 +2511,6 @@ static int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
 	mpol_put(vma_policy(new));
  out_free_vma:
 	kmem_cache_free(vm_area_cachep, new);
- out_err:
 	return err;
 }
 
@@ -2872,6 +2871,13 @@ int insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma)
 	struct vm_area_struct *prev;
 	struct rb_node **rb_link, *rb_parent;
 
+	if (find_vma_links(mm, vma->vm_start, vma->vm_end,
+			   &prev, &rb_link, &rb_parent))
+		return -ENOMEM;
+	if ((vma->vm_flags & VM_ACCOUNT) &&
+	     security_vm_enough_memory_mm(mm, vma_pages(vma)))
+		return -ENOMEM;
+
 	/*
 	 * The vm_pgoff of a purely anonymous vma should be irrelevant
 	 * until its first write fault, when page's anon_vma and index
@@ -2884,16 +2890,10 @@ int insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma)
 	 * using the existing file pgoff checks and manipulations.
 	 * Similarly in do_mmap_pgoff and in do_brk.
 	 */
-	if (!vma->vm_file) {
+	if (vma_is_anonymous(vma)) {
 		BUG_ON(vma->anon_vma);
 		vma->vm_pgoff = vma->vm_start >> PAGE_SHIFT;
 	}
-	if (find_vma_links(mm, vma->vm_start, vma->vm_end,
-			   &prev, &rb_link, &rb_parent))
-		return -ENOMEM;
-	if ((vma->vm_flags & VM_ACCOUNT) &&
-	     security_vm_enough_memory_mm(mm, vma_pages(vma)))
-		return -ENOMEM;
 
 	vma_link(mm, vma, prev, rb_link, rb_parent);
 	return 0;
@@ -2918,7 +2918,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
 	 * If anonymous vma has not yet been faulted, update new pgoff
 	 * to match new location, to increase its chance of merging.
 	 */
-	if (unlikely(!vma->vm_file && !vma->anon_vma)) {
+	if (unlikely(vma_is_anonymous(vma) && !vma->anon_vma)) {
 		pgoff = addr >> PAGE_SHIFT;
 		faulted_in_anon_vma = false;
 	}
@@ -2952,30 +2952,31 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
 		*need_rmap_locks = (new_vma->vm_pgoff <= vma->vm_pgoff);
 	} else {
 		new_vma = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
-		if (new_vma) {
-			*new_vma = *vma;
-			new_vma->vm_start = addr;
-			new_vma->vm_end = addr + len;
-			new_vma->vm_pgoff = pgoff;
-			if (vma_dup_policy(vma, new_vma))
-				goto out_free_vma;
-			INIT_LIST_HEAD(&new_vma->anon_vma_chain);
-			if (anon_vma_clone(new_vma, vma))
-				goto out_free_mempol;
-			if (new_vma->vm_file)
-				get_file(new_vma->vm_file);
-			if (new_vma->vm_ops && new_vma->vm_ops->open)
-				new_vma->vm_ops->open(new_vma);
-			vma_link(mm, new_vma, prev, rb_link, rb_parent);
-			*need_rmap_locks = false;
-		}
+		if (!new_vma)
+			goto out;
+		*new_vma = *vma;
+		new_vma->vm_start = addr;
+		new_vma->vm_end = addr + len;
+		new_vma->vm_pgoff = pgoff;
+		if (vma_dup_policy(vma, new_vma))
+			goto out_free_vma;
+		INIT_LIST_HEAD(&new_vma->anon_vma_chain);
+		if (anon_vma_clone(new_vma, vma))
+			goto out_free_mempol;
+		if (new_vma->vm_file)
+			get_file(new_vma->vm_file);
+		if (new_vma->vm_ops && new_vma->vm_ops->open)
+			new_vma->vm_ops->open(new_vma);
+		vma_link(mm, new_vma, prev, rb_link, rb_parent);
+		*need_rmap_locks = false;
 	}
 	return new_vma;
 
- out_free_mempol:
+out_free_mempol:
 	mpol_put(vma_policy(new_vma));
- out_free_vma:
+out_free_vma:
 	kmem_cache_free(vm_area_cachep, new_vma);
+out:
 	return NULL;
 }
 
@@ -3027,21 +3028,13 @@ static int special_mapping_fault(struct vm_area_struct *vma,
 	pgoff_t pgoff;
 	struct page **pages;
 
-	/*
-	 * special mappings have no vm_file, and in that case, the mm
-	 * uses vm_pgoff internally. So we have to subtract it from here.
-	 * We are allowed to do this because we are the mm; do not copy
-	 * this code into drivers!
-	 */
-	pgoff = vmf->pgoff - vma->vm_pgoff;
-
 	if (vma->vm_ops == &legacy_special_mapping_vmops)
 		pages = vma->vm_private_data;
 	else
 		pages = ((struct vm_special_mapping *)vma->vm_private_data)->
 			pages;
 
-	for (; pgoff && *pages; ++pages)
+	for (pgoff = vmf->pgoff; pgoff && *pages; ++pages)
 		pgoff--;
 
 	if (*pages) {

mm/oom_kill.c

@@ -196,27 +196,26 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
  * Determine the type of allocation constraint.
  */
 #ifdef CONFIG_NUMA
-static enum oom_constraint constrained_alloc(struct zonelist *zonelist,
-				gfp_t gfp_mask, nodemask_t *nodemask,
-				unsigned long *totalpages)
+static enum oom_constraint constrained_alloc(struct oom_control *oc,
+					     unsigned long *totalpages)
 {
 	struct zone *zone;
 	struct zoneref *z;
-	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
+	enum zone_type high_zoneidx = gfp_zone(oc->gfp_mask);
 	bool cpuset_limited = false;
 	int nid;
 
 	/* Default to all available memory */
 	*totalpages = totalram_pages + total_swap_pages;
 
-	if (!zonelist)
+	if (!oc->zonelist)
 		return CONSTRAINT_NONE;
 	/*
 	 * Reach here only when __GFP_NOFAIL is used. So, we should avoid
 	 * to kill current.We have to random task kill in this case.
 	 * Hopefully, CONSTRAINT_THISNODE...but no way to handle it, now.
 	 */
-	if (gfp_mask & __GFP_THISNODE)
+	if (oc->gfp_mask & __GFP_THISNODE)
 		return CONSTRAINT_NONE;
 
 	/*
@@ -224,17 +223,18 @@ static enum oom_constraint constrained_alloc(struct zonelist *zonelist,
 	 * the page allocator means a mempolicy is in effect.  Cpuset policy
 	 * is enforced in get_page_from_freelist().
 	 */
-	if (nodemask && !nodes_subset(node_states[N_MEMORY], *nodemask)) {
+	if (oc->nodemask &&
+	    !nodes_subset(node_states[N_MEMORY], *oc->nodemask)) {
 		*totalpages = total_swap_pages;
-		for_each_node_mask(nid, *nodemask)
+		for_each_node_mask(nid, *oc->nodemask)
 			*totalpages += node_spanned_pages(nid);
 		return CONSTRAINT_MEMORY_POLICY;
 	}
 
 	/* Check this allocation failure is caused by cpuset's wall function */
-	for_each_zone_zonelist_nodemask(zone, z, zonelist,
-			high_zoneidx, nodemask)
-		if (!cpuset_zone_allowed(zone, gfp_mask))
+	for_each_zone_zonelist_nodemask(zone, z, oc->zonelist,
+			high_zoneidx, oc->nodemask)
+		if (!cpuset_zone_allowed(zone, oc->gfp_mask))
 			cpuset_limited = true;
 
 	if (cpuset_limited) {
@@ -246,20 +246,18 @@ static enum oom_constraint constrained_alloc(struct zonelist *zonelist,
 	return CONSTRAINT_NONE;
 }
 #else
-static enum oom_constraint constrained_alloc(struct zonelist *zonelist,
-				gfp_t gfp_mask, nodemask_t *nodemask,
-				unsigned long *totalpages)
+static enum oom_constraint constrained_alloc(struct oom_control *oc,
+					     unsigned long *totalpages)
 {
 	*totalpages = totalram_pages + total_swap_pages;
 	return CONSTRAINT_NONE;
 }
 #endif
 
-enum oom_scan_t oom_scan_process_thread(struct task_struct *task,
-		unsigned long totalpages, const nodemask_t *nodemask,
-		bool force_kill)
+enum oom_scan_t oom_scan_process_thread(struct oom_control *oc,
+			struct task_struct *task, unsigned long totalpages)
 {
-	if (oom_unkillable_task(task, NULL, nodemask))
+	if (oom_unkillable_task(task, NULL, oc->nodemask))
 		return OOM_SCAN_CONTINUE;
 
 	/*
@@ -267,7 +265,7 @@ enum oom_scan_t oom_scan_process_thread(struct task_struct *task,
 	 * Don't allow any other task to have access to the reserves.
 	 */
 	if (test_tsk_thread_flag(task, TIF_MEMDIE)) {
-		if (!force_kill)
+		if (oc->order != -1)
 			return OOM_SCAN_ABORT;
 	}
 	if (!task->mm)
@@ -280,7 +278,7 @@ enum oom_scan_t oom_scan_process_thread(struct task_struct *task,
 	if (oom_task_origin(task))
 		return OOM_SCAN_SELECT;
 
-	if (task_will_free_mem(task) && !force_kill)
+	if (task_will_free_mem(task) && oc->order != -1)
 		return OOM_SCAN_ABORT;
 
 	return OOM_SCAN_OK;
@@ -289,12 +287,9 @@ enum oom_scan_t oom_scan_process_thread(struct task_struct *task,
 /*
  * Simple selection loop. We chose the process with the highest
  * number of 'points'.  Returns -1 on scan abort.
- *
- * (not docbooked, we don't want this one cluttering up the manual)
  */
-static struct task_struct *select_bad_process(unsigned int *ppoints,
-		unsigned long totalpages, const nodemask_t *nodemask,
-		bool force_kill)
+static struct task_struct *select_bad_process(struct oom_control *oc,
+		unsigned int *ppoints, unsigned long totalpages)
 {
 	struct task_struct *g, *p;
 	struct task_struct *chosen = NULL;
@@ -304,8 +299,7 @@ static struct task_struct *select_bad_process(unsigned int *ppoints,
 	for_each_process_thread(g, p) {
 		unsigned int points;
 
-		switch (oom_scan_process_thread(p, totalpages, nodemask,
-						force_kill)) {
+		switch (oom_scan_process_thread(oc, p, totalpages)) {
 		case OOM_SCAN_SELECT:
 			chosen = p;
 			chosen_points = ULONG_MAX;
@@ -318,7 +312,7 @@ static struct task_struct *select_bad_process(unsigned int *ppoints,
 		case OOM_SCAN_OK:
 			break;
 		};
-		points = oom_badness(p, NULL, nodemask, totalpages);
+		points = oom_badness(p, NULL, oc->nodemask, totalpages);
 		if (!points || points < chosen_points)
 			continue;
 		/* Prefer thread group leaders for display purposes */
@@ -380,13 +374,13 @@ static void dump_tasks(struct mem_cgroup *memcg, const nodemask_t *nodemask)
 	rcu_read_unlock();
 }
 
-static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order,
-			struct mem_cgroup *memcg, const nodemask_t *nodemask)
+static void dump_header(struct oom_control *oc, struct task_struct *p,
+			struct mem_cgroup *memcg)
 {
 	task_lock(current);
 	pr_warning("%s invoked oom-killer: gfp_mask=0x%x, order=%d, "
 		"oom_score_adj=%hd\n",
-		current->comm, gfp_mask, order,
+		current->comm, oc->gfp_mask, oc->order,
 		current->signal->oom_score_adj);
 	cpuset_print_task_mems_allowed(current);
 	task_unlock(current);
@@ -396,7 +390,7 @@ static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order,
 	else
 		show_mem(SHOW_MEM_FILTER_NODES);
 	if (sysctl_oom_dump_tasks)
-		dump_tasks(memcg, nodemask);
+		dump_tasks(memcg, oc->nodemask);
 }
 
 /*
@@ -487,10 +481,9 @@ void oom_killer_enable(void)
  * Must be called while holding a reference to p, which will be released upon
  * returning.
  */
-void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
+void oom_kill_process(struct oom_control *oc, struct task_struct *p,
 		      unsigned int points, unsigned long totalpages,
-		      struct mem_cgroup *memcg, nodemask_t *nodemask,
-		      const char *message)
+		      struct mem_cgroup *memcg, const char *message)
 {
 	struct task_struct *victim = p;
 	struct task_struct *child;
@@ -514,7 +507,7 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 	task_unlock(p);
 
 	if (__ratelimit(&oom_rs))
-		dump_header(p, gfp_mask, order, memcg, nodemask);
+		dump_header(oc, p, memcg);
 
 	task_lock(p);
 	pr_err("%s: Kill process %d (%s) score %u or sacrifice child\n",
@@ -537,7 +530,7 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 			/*
 			 * oom_badness() returns 0 if the thread is unkillable
 			 */
-			child_points = oom_badness(child, memcg, nodemask,
+			child_points = oom_badness(child, memcg, oc->nodemask,
 								totalpages);
 			if (child_points > victim_points) {
 				put_task_struct(victim);
@@ -600,8 +593,7 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 /*
  * Determines whether the kernel must panic because of the panic_on_oom sysctl.
  */
-void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask,
-			int order, const nodemask_t *nodemask,
+void check_panic_on_oom(struct oom_control *oc, enum oom_constraint constraint,
 			struct mem_cgroup *memcg)
 {
 	if (likely(!sysctl_panic_on_oom))
@@ -615,7 +607,10 @@ void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask,
 		if (constraint != CONSTRAINT_NONE)
 			return;
 	}
-	dump_header(NULL, gfp_mask, order, memcg, nodemask);
+	/* Do not panic for oom kills triggered by sysrq */
+	if (oc->order == -1)
+		return;
+	dump_header(oc, NULL, memcg);
 	panic("Out of memory: %s panic_on_oom is enabled\n",
 		sysctl_panic_on_oom == 2 ? "compulsory" : "system-wide");
 }
@@ -635,28 +630,21 @@ int unregister_oom_notifier(struct notifier_block *nb)
 EXPORT_SYMBOL_GPL(unregister_oom_notifier);
 
 /**
- * __out_of_memory - kill the "best" process when we run out of memory
- * @zonelist: zonelist pointer
- * @gfp_mask: memory allocation flags
- * @order: amount of memory being requested as a power of 2
- * @nodemask: nodemask passed to page allocator
- * @force_kill: true if a task must be killed, even if others are exiting
+ * out_of_memory - kill the "best" process when we run out of memory
+ * @oc: pointer to struct oom_control
  *
  * If we run out of memory, we have the choice between either
  * killing a random task (bad), letting the system crash (worse)
  * OR try to be smart about which process to kill. Note that we
  * don't have to be perfect here, we just have to be good.
  */
-bool out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
-		   int order, nodemask_t *nodemask, bool force_kill)
+bool out_of_memory(struct oom_control *oc)
 {
-	const nodemask_t *mpol_mask;
 	struct task_struct *p;
 	unsigned long totalpages;
 	unsigned long freed = 0;
 	unsigned int uninitialized_var(points);
 	enum oom_constraint constraint = CONSTRAINT_NONE;
-	int killed = 0;
 
 	if (oom_killer_disabled)
 		return false;
@@ -664,7 +652,7 @@ bool out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
 	blocking_notifier_call_chain(&oom_notify_list, 0, &freed);
 	if (freed > 0)
 		/* Got some memory back in the last second. */
-		goto out;
+		return true;
 
 	/*
 	 * If current has a pending SIGKILL or is exiting, then automatically
@@ -677,47 +665,42 @@ bool out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
 	if (current->mm &&
 	    (fatal_signal_pending(current) || task_will_free_mem(current))) {
 		mark_oom_victim(current);
-		goto out;
+		return true;
 	}
 
 	/*
 	 * Check if there were limitations on the allocation (only relevant for
 	 * NUMA) that may require different handling.
 	 */
-	constraint = constrained_alloc(zonelist, gfp_mask, nodemask,
-						&totalpages);
-	mpol_mask = (constraint == CONSTRAINT_MEMORY_POLICY) ? nodemask : NULL;
-	check_panic_on_oom(constraint, gfp_mask, order, mpol_mask, NULL);
+	constraint = constrained_alloc(oc, &totalpages);
+	if (constraint != CONSTRAINT_MEMORY_POLICY)
+		oc->nodemask = NULL;
+	check_panic_on_oom(oc, constraint, NULL);
 
 	if (sysctl_oom_kill_allocating_task && current->mm &&
-	    !oom_unkillable_task(current, NULL, nodemask) &&
+	    !oom_unkillable_task(current, NULL, oc->nodemask) &&
 	    current->signal->oom_score_adj != OOM_SCORE_ADJ_MIN) {
 		get_task_struct(current);
-		oom_kill_process(current, gfp_mask, order, 0, totalpages, NULL,
-				 nodemask,
+		oom_kill_process(oc, current, 0, totalpages, NULL,
 				 "Out of memory (oom_kill_allocating_task)");
-		goto out;
+		return true;
 	}
 
-	p = select_bad_process(&points, totalpages, mpol_mask, force_kill);
+	p = select_bad_process(oc, &points, totalpages);
 	/* Found nothing?!?! Either we hang forever, or we panic. */
-	if (!p) {
-		dump_header(NULL, gfp_mask, order, NULL, mpol_mask);
+	if (!p && oc->order != -1) {
+		dump_header(oc, NULL, NULL);
 		panic("Out of memory and no killable processes...\n");
 	}
-	if (p != (void *)-1UL) {
-		oom_kill_process(p, gfp_mask, order, points, totalpages, NULL,
-				 nodemask, "Out of memory");
-		killed = 1;
-	}
-out:
-	/*
-	 * Give the killed threads a good chance of exiting before trying to
-	 * allocate memory again.
-	 */
-	if (killed)
+	if (p && p != (void *)-1UL) {
+		oom_kill_process(oc, p, points, totalpages, NULL,
+				 "Out of memory");
+		/*
+		 * Give the killed process a good chance to exit before trying
+		 * to allocate memory again.
+		 */
 		schedule_timeout_killable(1);
-
+	}
 	return true;
 }
 
@@ -728,13 +711,20 @@ out:
  */
 void pagefault_out_of_memory(void)
 {
+	struct oom_control oc = {
+		.zonelist = NULL,
+		.nodemask = NULL,
+		.gfp_mask = 0,
+		.order = 0,
+	};
+
 	if (mem_cgroup_oom_synchronize(true))
 		return;
 
 	if (!mutex_trylock(&oom_lock))
 		return;
 
-	if (!out_of_memory(NULL, 0, 0, NULL, false)) {
+	if (!out_of_memory(&oc)) {
 		/*
 		 * There shouldn't be any user tasks runnable while the
 		 * OOM killer is disabled, so the current task has to

mm/page_alloc.c

@@ -125,6 +125,24 @@ unsigned long dirty_balance_reserve __read_mostly;
 int percpu_pagelist_fraction;
 gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK;
 
+/*
+ * A cached value of the page's pageblock's migratetype, used when the page is
+ * put on a pcplist. Used to avoid the pageblock migratetype lookup when
+ * freeing from pcplists in most cases, at the cost of possibly becoming stale.
+ * Also the migratetype set in the page does not necessarily match the pcplist
+ * index, e.g. page might have MIGRATE_CMA set but be on a pcplist with any
+ * other index - this ensures that it will be put on the correct CMA freelist.
+ */
+static inline int get_pcppage_migratetype(struct page *page)
+{
+	return page->index;
+}
+
+static inline void set_pcppage_migratetype(struct page *page, int migratetype)
+{
+	page->index = migratetype;
+}
+
 #ifdef CONFIG_PM_SLEEP
 /*
  * The following functions are used by the suspend/hibernate code to temporarily
@@ -791,7 +809,11 @@ static void free_pcppages_bulk(struct zone *zone, int count,
 			page = list_entry(list->prev, struct page, lru);
 			/* must delete as __free_one_page list manipulates */
 			list_del(&page->lru);
-			mt = get_freepage_migratetype(page);
+
+			mt = get_pcppage_migratetype(page);
+			/* MIGRATE_ISOLATE page should not go to pcplists */
+			VM_BUG_ON_PAGE(is_migrate_isolate(mt), page);
+			/* Pageblock could have been isolated meanwhile */
 			if (unlikely(has_isolate_pageblock(zone)))
 				mt = get_pageblock_migratetype(page);
 
@@ -955,7 +977,6 @@ static void __free_pages_ok(struct page *page, unsigned int order)
 	migratetype = get_pfnblock_migratetype(page, pfn);
 	local_irq_save(flags);
 	__count_vm_events(PGFREE, 1 << order);
-	set_freepage_migratetype(page, migratetype);
 	free_one_page(page_zone(page), page, pfn, order, migratetype);
 	local_irq_restore(flags);
 }
@@ -1383,7 +1404,7 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order,
 		rmv_page_order(page);
 		area->nr_free--;
 		expand(zone, page, order, current_order, area, migratetype);
-		set_freepage_migratetype(page, migratetype);
+		set_pcppage_migratetype(page, migratetype);
 		return page;
 	}
 
@@ -1460,7 +1481,6 @@ int move_freepages(struct zone *zone,
 		order = page_order(page);
 		list_move(&page->lru,
 			  &zone->free_area[order].free_list[migratetype]);
-		set_freepage_migratetype(page, migratetype);
 		page += 1 << order;
 		pages_moved += 1 << order;
 	}
@@ -1630,14 +1650,13 @@ __rmqueue_fallback(struct zone *zone, unsigned int order, int start_migratetype)
 		expand(zone, page, order, current_order, area,
 					start_migratetype);
 		/*
-		 * The freepage_migratetype may differ from pageblock's
+		 * The pcppage_migratetype may differ from pageblock's
 		 * migratetype depending on the decisions in
-		 * try_to_steal_freepages(). This is OK as long as it
-		 * does not differ for MIGRATE_CMA pageblocks. For CMA
-		 * we need to make sure unallocated pages flushed from
-		 * pcp lists are returned to the correct freelist.
+		 * find_suitable_fallback(). This is OK as long as it does not
+		 * differ for MIGRATE_CMA pageblocks. Those can be used as
+		 * fallback only via special __rmqueue_cma_fallback() function
 		 */
-		set_freepage_migratetype(page, start_migratetype);
+		set_pcppage_migratetype(page, start_migratetype);
 
 		trace_mm_page_alloc_extfrag(page, order, current_order,
 			start_migratetype, fallback_mt);
@@ -1713,7 +1732,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
 		else
 			list_add_tail(&page->lru, list);
 		list = &page->lru;
-		if (is_migrate_cma(get_freepage_migratetype(page)))
+		if (is_migrate_cma(get_pcppage_migratetype(page)))
 			__mod_zone_page_state(zone, NR_FREE_CMA_PAGES,
 					      -(1 << order));
 	}
@@ -1910,7 +1929,7 @@ void free_hot_cold_page(struct page *page, bool cold)
 		return;
 
 	migratetype = get_pfnblock_migratetype(page, pfn);
-	set_freepage_migratetype(page, migratetype);
+	set_pcppage_migratetype(page, migratetype);
 	local_irq_save(flags);
 	__count_vm_event(PGFREE);
 
@@ -2115,7 +2134,7 @@ struct page *buffered_rmqueue(struct zone *preferred_zone,
 		if (!page)
 			goto failed;
 		__mod_zone_freepage_state(zone, -(1 << order),
-					  get_freepage_migratetype(page));
+					  get_pcppage_migratetype(page));
 	}
 
 	__mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order));
@@ -2696,6 +2715,12 @@ static inline struct page *
 __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 	const struct alloc_context *ac, unsigned long *did_some_progress)
 {
+	struct oom_control oc = {
+		.zonelist = ac->zonelist,
+		.nodemask = ac->nodemask,
+		.gfp_mask = gfp_mask,
+		.order = order,
+	};
 	struct page *page;
 
 	*did_some_progress = 0;
@@ -2747,8 +2772,7 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 			goto out;
 	}
 	/* Exhausted what can be done so it's blamo time */
-	if (out_of_memory(ac->zonelist, gfp_mask, order, ac->nodemask, false)
-			|| WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL))
+	if (out_of_memory(&oc) || WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL))
 		*did_some_progress = 1;
 out:
 	mutex_unlock(&oom_lock);
@@ -3490,8 +3514,6 @@ EXPORT_SYMBOL(alloc_pages_exact);
  *
  * Like alloc_pages_exact(), but try to allocate on node nid first before falling
  * back.
- * Note this is not alloc_pages_exact_node() which allocates on a specific node,
- * but is not exact.
  */
 void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask)
 {
@@ -5066,7 +5088,7 @@ static unsigned long __meminit zone_spanned_pages_in_node(int nid,
 {
 	unsigned long zone_start_pfn, zone_end_pfn;
 
-	/* When hotadd a new node, the node should be empty */
+	/* When hotadd a new node from cpu_up(), the node should be empty */
 	if (!node_start_pfn && !node_end_pfn)
 		return 0;
 
@@ -5133,7 +5155,7 @@ static unsigned long __meminit zone_absent_pages_in_node(int nid,
 	unsigned long zone_high = arch_zone_highest_possible_pfn[zone_type];
 	unsigned long zone_start_pfn, zone_end_pfn;
 
-	/* When hotadd a new node, the node should be empty */
+	/* When hotadd a new node from cpu_up(), the node should be empty */
 	if (!node_start_pfn && !node_end_pfn)
 		return 0;
 
@@ -5306,8 +5328,7 @@ static unsigned long __paginginit calc_memmap_size(unsigned long spanned_pages,
  *
  * NOTE: pgdat should get zeroed by caller.
  */
-static void __paginginit free_area_init_core(struct pglist_data *pgdat,
-		unsigned long node_start_pfn, unsigned long node_end_pfn)
+static void __paginginit free_area_init_core(struct pglist_data *pgdat)
 {
 	enum zone_type j;
 	int nid = pgdat->node_id;
@@ -5458,7 +5479,8 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
 	get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
 	pr_info("Initmem setup node %d [mem %#018Lx-%#018Lx]\n", nid,
-		(u64)start_pfn << PAGE_SHIFT, ((u64)end_pfn << PAGE_SHIFT) - 1);
+		(u64)start_pfn << PAGE_SHIFT,
+		end_pfn ? ((u64)end_pfn << PAGE_SHIFT) - 1 : 0);
 #endif
 	calculate_node_totalpages(pgdat, start_pfn, end_pfn,
 				  zones_size, zholes_size);
@@ -5470,7 +5492,7 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
 		(unsigned long)pgdat->node_mem_map);
 #endif
 
-	free_area_init_core(pgdat, start_pfn, end_pfn);
+	free_area_init_core(pgdat);
 }
 
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
@@ -5481,11 +5503,9 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
  */
 void __init setup_nr_node_ids(void)
 {
-	unsigned int node;
-	unsigned int highest = 0;
+	unsigned int highest;
 
-	for_each_node_mask(node, node_possible_map)
-		highest = node;
+	highest = find_last_bit(node_possible_map.bits, MAX_NUMNODES);
 	nr_node_ids = highest + 1;
 }
 #endif
@@ -6006,7 +6026,7 @@ void __init mem_init_print_info(const char *str)
  * set_dma_reserve - set the specified number of pages reserved in the first zone
  * @new_dma_reserve: The number of pages to mark reserved
  *
- * The per-cpu batchsize and zone watermarks are determined by present_pages.
+ * The per-cpu batchsize and zone watermarks are determined by managed_pages.
  * In the DMA zone, a significant percentage may be consumed by kernel image
  * and other unfreeable allocations which can skew the watermarks badly. This
  * function may optionally be used to account for unfreeable pages in the
@@ -6059,7 +6079,7 @@ void __init page_alloc_init(void)
 }
 
 /*
- * calculate_totalreserve_pages - called when sysctl_lower_zone_reserve_ratio
+ * calculate_totalreserve_pages - called when sysctl_lowmem_reserve_ratio
  *	or min_free_kbytes changes.
  */
 static void calculate_totalreserve_pages(void)
@@ -6103,7 +6123,7 @@ static void calculate_totalreserve_pages(void)
 
 /*
  * setup_per_zone_lowmem_reserve - called whenever
- *	sysctl_lower_zone_reserve_ratio changes.  Ensures that each zone
+ *	sysctl_lowmem_reserve_ratio changes.  Ensures that each zone
  *	has a correct pages reserved value, so an adequate number of
  *	pages are left in the zone after a successful __alloc_pages().
  */

mm/page_isolation.c

@@ -9,7 +9,8 @@
 #include <linux/hugetlb.h>
 #include "internal.h"
 
-int set_migratetype_isolate(struct page *page, bool skip_hwpoisoned_pages)
+static int set_migratetype_isolate(struct page *page,
+				bool skip_hwpoisoned_pages)
 {
 	struct zone *zone;
 	unsigned long flags, pfn;
@@ -72,7 +73,7 @@ out:
 	return ret;
 }
 
-void unset_migratetype_isolate(struct page *page, unsigned migratetype)
+static void unset_migratetype_isolate(struct page *page, unsigned migratetype)
 {
 	struct zone *zone;
 	unsigned long flags, nr_pages;
@@ -223,34 +224,16 @@ __test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn,
 			continue;
 		}
 		page = pfn_to_page(pfn);
-		if (PageBuddy(page)) {
+		if (PageBuddy(page))
 			/*
-			 * If race between isolatation and allocation happens,
-			 * some free pages could be in MIGRATE_MOVABLE list
-			 * although pageblock's migratation type of the page
-			 * is MIGRATE_ISOLATE. Catch it and move the page into
-			 * MIGRATE_ISOLATE list.
+			 * If the page is on a free list, it has to be on
+			 * the correct MIGRATE_ISOLATE freelist. There is no
+			 * simple way to verify that as VM_BUG_ON(), though.
 			 */
-			if (get_freepage_migratetype(page) != MIGRATE_ISOLATE) {
-				struct page *end_page;
-
-				end_page = page + (1 << page_order(page)) - 1;
-				move_freepages(page_zone(page), page, end_page,
-						MIGRATE_ISOLATE);
-			}
 			pfn += 1 << page_order(page);
-		}
-		else if (page_count(page) == 0 &&
-			get_freepage_migratetype(page) == MIGRATE_ISOLATE)
-			pfn += 1;
-		else if (skip_hwpoisoned_pages && PageHWPoison(page)) {
-			/*
-			 * The HWPoisoned page may be not in buddy
-			 * system, and page_count() is not 0.
-			 */
+		else if (skip_hwpoisoned_pages && PageHWPoison(page))
+			/* A HWPoisoned page cannot be also PageBuddy */
 			pfn++;
-			continue;
-		}
 		else
 			break;
 	}

mm/shmem.c

@@ -542,6 +542,21 @@ void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
 }
 EXPORT_SYMBOL_GPL(shmem_truncate_range);
 
+static int shmem_getattr(struct vfsmount *mnt, struct dentry *dentry,
+			 struct kstat *stat)
+{
+	struct inode *inode = dentry->d_inode;
+	struct shmem_inode_info *info = SHMEM_I(inode);
+
+	spin_lock(&info->lock);
+	shmem_recalc_inode(inode);
+	spin_unlock(&info->lock);
+
+	generic_fillattr(inode, stat);
+
+	return 0;
+}
+
 static int shmem_setattr(struct dentry *dentry, struct iattr *attr)
 {
 	struct inode *inode = d_inode(dentry);
@@ -3122,6 +3137,7 @@ static const struct file_operations shmem_file_operations = {
 };
 
 static const struct inode_operations shmem_inode_operations = {
+	.getattr	= shmem_getattr,
 	.setattr	= shmem_setattr,
 #ifdef CONFIG_TMPFS_XATTR
 	.setxattr	= shmem_setxattr,

mm/slab.c

@@ -1595,7 +1595,7 @@ static struct page *kmem_getpages(struct kmem_cache *cachep, gfp_t flags,
 	if (memcg_charge_slab(cachep, flags, cachep->gfporder))
 		return NULL;
 
-	page = alloc_pages_exact_node(nodeid, flags | __GFP_NOTRACK, cachep->gfporder);
+	page = __alloc_pages_node(nodeid, flags | __GFP_NOTRACK, cachep->gfporder);
 	if (!page) {
 		memcg_uncharge_slab(cachep, cachep->gfporder);
 		slab_out_of_memory(cachep, flags, nodeid);

mm/slab_common.c

@@ -500,7 +500,7 @@ void memcg_create_kmem_cache(struct mem_cgroup *memcg,
 			     struct kmem_cache *root_cache)
 {
 	static char memcg_name_buf[NAME_MAX + 1]; /* protected by slab_mutex */
-	struct cgroup_subsys_state *css = mem_cgroup_css(memcg);
+	struct cgroup_subsys_state *css = &memcg->css;
 	struct memcg_cache_array *arr;
 	struct kmem_cache *s = NULL;
 	char *cache_name;
@@ -640,6 +640,9 @@ void kmem_cache_destroy(struct kmem_cache *s)
 	bool need_rcu_barrier = false;
 	bool busy = false;
 
+	if (unlikely(!s))
+		return;
+
 	BUG_ON(!is_root_cache(s));
 
 	get_online_cpus();

mm/slob.c

@@ -45,7 +45,7 @@
  * NUMA support in SLOB is fairly simplistic, pushing most of the real
  * logic down to the page allocator, and simply doing the node accounting
  * on the upper levels. In the event that a node id is explicitly
- * provided, alloc_pages_exact_node() with the specified node id is used
+ * provided, __alloc_pages_node() with the specified node id is used
  * instead. The common case (or when the node id isn't explicitly provided)
  * will default to the current node, as per numa_node_id().
  *
@@ -193,7 +193,7 @@ static void *slob_new_pages(gfp_t gfp, int order, int node)
 
 #ifdef CONFIG_NUMA
 	if (node != NUMA_NO_NODE)
-		page = alloc_pages_exact_node(node, gfp, order);
+		page = __alloc_pages_node(node, gfp, order);
 	else
 #endif
 		page = alloc_pages(gfp, order);

mm/slub.c

@@ -1334,7 +1334,7 @@ static inline struct page *alloc_slab_page(struct kmem_cache *s,
 	if (node == NUMA_NO_NODE)
 		page = alloc_pages(flags, order);
 	else
-		page = alloc_pages_exact_node(node, flags, order);
+		page = __alloc_pages_node(node, flags, order);
 
 	if (!page)
 		memcg_uncharge_slab(s, order);

mm/swap_state.c

@@ -288,17 +288,14 @@ struct page * lookup_swap_cache(swp_entry_t entry)
 	return page;
 }
 
-/* 
- * Locate a page of swap in physical memory, reserving swap cache space
- * and reading the disk if it is not already cached.
- * A failure return means that either the page allocation failed or that
- * the swap entry is no longer in use.
- */
-struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
-			struct vm_area_struct *vma, unsigned long addr)
+struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
+			struct vm_area_struct *vma, unsigned long addr,
+			bool *new_page_allocated)
 {
 	struct page *found_page, *new_page = NULL;
+	struct address_space *swapper_space = swap_address_space(entry);
 	int err;
+	*new_page_allocated = false;
 
 	do {
 		/*
@@ -306,8 +303,7 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 		 * called after lookup_swap_cache() failed, re-calling
 		 * that would confuse statistics.
 		 */
-		found_page = find_get_page(swap_address_space(entry),
-					entry.val);
+		found_page = find_get_page(swapper_space, entry.val);
 		if (found_page)
 			break;
 
@@ -366,7 +362,7 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 			 * Initiate read into locked page and return.
 			 */
 			lru_cache_add_anon(new_page);
-			swap_readpage(new_page);
+			*new_page_allocated = true;
 			return new_page;
 		}
 		radix_tree_preload_end();
@@ -384,6 +380,25 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 	return found_page;
 }
 
+/*
+ * Locate a page of swap in physical memory, reserving swap cache space
+ * and reading the disk if it is not already cached.
+ * A failure return means that either the page allocation failed or that
+ * the swap entry is no longer in use.
+ */
+struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
+			struct vm_area_struct *vma, unsigned long addr)
+{
+	bool page_was_allocated;
+	struct page *retpage = __read_swap_cache_async(entry, gfp_mask,
+			vma, addr, &page_was_allocated);
+
+	if (page_was_allocated)
+		swap_readpage(retpage);
+
+	return retpage;
+}
+
 static unsigned long swapin_nr_pages(unsigned long offset)
 {
 	static unsigned long prev_offset;

mm/swapfile.c

@@ -874,6 +874,48 @@ int page_swapcount(struct page *page)
 	return count;
 }
 
+/*
+ * How many references to @entry are currently swapped out?
+ * This considers COUNT_CONTINUED so it returns exact answer.
+ */
+int swp_swapcount(swp_entry_t entry)
+{
+	int count, tmp_count, n;
+	struct swap_info_struct *p;
+	struct page *page;
+	pgoff_t offset;
+	unsigned char *map;
+
+	p = swap_info_get(entry);
+	if (!p)
+		return 0;
+
+	count = swap_count(p->swap_map[swp_offset(entry)]);
+	if (!(count & COUNT_CONTINUED))
+		goto out;
+
+	count &= ~COUNT_CONTINUED;
+	n = SWAP_MAP_MAX + 1;
+
+	offset = swp_offset(entry);
+	page = vmalloc_to_page(p->swap_map + offset);
+	offset &= ~PAGE_MASK;
+	VM_BUG_ON(page_private(page) != SWP_CONTINUED);
+
+	do {
+		page = list_entry(page->lru.next, struct page, lru);
+		map = kmap_atomic(page);
+		tmp_count = map[offset];
+		kunmap_atomic(map);
+
+		count += (tmp_count & ~COUNT_CONTINUED) * n;
+		n *= (SWAP_CONT_MAX + 1);
+	} while (tmp_count & COUNT_CONTINUED);
+out:
+	spin_unlock(&p->lock);
+	return count;
+}
+
 /*
  * We can write to an anon page without COW if there are no other references
  * to it.  And as a side-effect, free up its swap: because the old content

mm/vmscan.c

@@ -175,7 +175,7 @@ static bool sane_reclaim(struct scan_control *sc)
 	if (!memcg)
 		return true;
 #ifdef CONFIG_CGROUP_WRITEBACK
-	if (cgroup_on_dfl(mem_cgroup_css(memcg)->cgroup))
+	if (memcg->css.cgroup)
 		return true;
 #endif
 	return false;
@@ -985,7 +985,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		 *    __GFP_IO|__GFP_FS for this reason); but more thought
 		 *    would probably show more reasons.
 		 *
-		 * 3) Legacy memcg encounters a page that is not already marked
+		 * 3) Legacy memcg encounters a page that is already marked
 		 *    PageReclaim. memcg does not have any dirty pages
 		 *    throttling so we could easily OOM just because too many
 		 *    pages are in writeback and there is nothing else to
@@ -1015,12 +1015,15 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 				 */
 				SetPageReclaim(page);
 				nr_writeback++;
-
 				goto keep_locked;
 
 			/* Case 3 above */
 			} else {
+				unlock_page(page);
 				wait_on_page_writeback(page);
+				/* then go back and try same page again */
+				list_add_tail(&page->lru, page_list);
+				continue;
 			}
 		}
 
@@ -1196,7 +1199,7 @@ cull_mlocked:
 		if (PageSwapCache(page))
 			try_to_free_swap(page);
 		unlock_page(page);
-		putback_lru_page(page);
+		list_add(&page->lru, &ret_pages);
 		continue;
 
 activate_locked:
@@ -1359,7 +1362,8 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 	unsigned long nr_taken = 0;
 	unsigned long scan;
 
-	for (scan = 0; scan < nr_to_scan && !list_empty(src); scan++) {
+	for (scan = 0; scan < nr_to_scan && nr_taken < nr_to_scan &&
+					!list_empty(src); scan++) {
 		struct page *page;
 		int nr_pages;
 

mm/zbud.c

@@ -96,10 +96,10 @@ struct zbud_pool {
 	struct list_head buddied;
 	struct list_head lru;
 	u64 pages_nr;
-	struct zbud_ops *ops;
+	const struct zbud_ops *ops;
 #ifdef CONFIG_ZPOOL
 	struct zpool *zpool;
-	struct zpool_ops *zpool_ops;
+	const struct zpool_ops *zpool_ops;
 #endif
 };
 
@@ -133,12 +133,12 @@ static int zbud_zpool_evict(struct zbud_pool *pool, unsigned long handle)
 		return -ENOENT;
 }
 
-static struct zbud_ops zbud_zpool_ops = {
+static const struct zbud_ops zbud_zpool_ops = {
 	.evict =	zbud_zpool_evict
 };
 
 static void *zbud_zpool_create(char *name, gfp_t gfp,
-			       struct zpool_ops *zpool_ops,
+			       const struct zpool_ops *zpool_ops,
 			       struct zpool *zpool)
 {
 	struct zbud_pool *pool;
@@ -302,7 +302,7 @@ static int num_free_chunks(struct zbud_header *zhdr)
  * Return: pointer to the new zbud pool or NULL if the metadata allocation
  * failed.
  */
-struct zbud_pool *zbud_create_pool(gfp_t gfp, struct zbud_ops *ops)
+struct zbud_pool *zbud_create_pool(gfp_t gfp, const struct zbud_ops *ops)
 {
 	struct zbud_pool *pool;
 	int i;

mm/zpool.c

@@ -22,7 +22,7 @@ struct zpool {
 
 	struct zpool_driver *driver;
 	void *pool;
-	struct zpool_ops *ops;
+	const struct zpool_ops *ops;
 
 	struct list_head list;
 };
@@ -115,7 +115,7 @@ static void zpool_put_driver(struct zpool_driver *driver)
  * Returns: New zpool on success, NULL on failure.
  */
 struct zpool *zpool_create_pool(char *type, char *name, gfp_t gfp,
-		struct zpool_ops *ops)
+		const struct zpool_ops *ops)
 {
 	struct zpool_driver *driver;
 	struct zpool *zpool;
@@ -320,20 +320,6 @@ u64 zpool_get_total_size(struct zpool *zpool)
 	return zpool->driver->total_size(zpool->pool);
 }
 
-static int __init init_zpool(void)
-{
-	pr_info("loaded\n");
-	return 0;
-}
-
-static void __exit exit_zpool(void)
-{
-	pr_info("unloaded\n");
-}
-
-module_init(init_zpool);
-module_exit(exit_zpool);
-
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Dan Streetman <ddstreet@ieee.org>");
 MODULE_DESCRIPTION("Common API for compressed memory storage");

mm/zsmalloc.c

@@ -169,14 +169,12 @@ enum zs_stat_type {
 	NR_ZS_STAT_TYPE,
 };
 
-#ifdef CONFIG_ZSMALLOC_STAT
-
-static struct dentry *zs_stat_root;
-
 struct zs_size_stat {
 	unsigned long objs[NR_ZS_STAT_TYPE];
 };
 
+#ifdef CONFIG_ZSMALLOC_STAT
+static struct dentry *zs_stat_root;
 #endif
 
 /*
@@ -201,6 +199,8 @@ static int zs_size_classes;
 static const int fullness_threshold_frac = 4;
 
 struct size_class {
+	spinlock_t lock;
+	struct page *fullness_list[_ZS_NR_FULLNESS_GROUPS];
 	/*
 	 * Size of objects stored in this class. Must be multiple
 	 * of ZS_ALIGN.
@@ -210,16 +210,10 @@ struct size_class {
 
 	/* Number of PAGE_SIZE sized pages to combine to form a 'zspage' */
 	int pages_per_zspage;
-	/* huge object: pages_per_zspage == 1 && maxobj_per_zspage == 1 */
-	bool huge;
-
-#ifdef CONFIG_ZSMALLOC_STAT
 	struct zs_size_stat stats;
-#endif
-
-	spinlock_t lock;
 
-	struct page *fullness_list[_ZS_NR_FULLNESS_GROUPS];
+	/* huge object: pages_per_zspage == 1 && maxobj_per_zspage == 1 */
+	bool huge;
 };
 
 /*
@@ -251,6 +245,15 @@ struct zs_pool {
 	gfp_t flags;	/* allocation flags used when growing pool */
 	atomic_long_t pages_allocated;
 
+	struct zs_pool_stats stats;
+
+	/* Compact classes */
+	struct shrinker shrinker;
+	/*
+	 * To signify that register_shrinker() was successful
+	 * and unregister_shrinker() will not Oops.
+	 */
+	bool shrinker_enabled;
 #ifdef CONFIG_ZSMALLOC_STAT
 	struct dentry *stat_dentry;
 #endif
@@ -285,8 +288,7 @@ static int create_handle_cache(struct zs_pool *pool)
 
 static void destroy_handle_cache(struct zs_pool *pool)
 {
-	if (pool->handle_cachep)
-		kmem_cache_destroy(pool->handle_cachep);
+	kmem_cache_destroy(pool->handle_cachep);
 }
 
 static unsigned long alloc_handle(struct zs_pool *pool)
@@ -309,7 +311,8 @@ static void record_obj(unsigned long handle, unsigned long obj)
 
 #ifdef CONFIG_ZPOOL
 
-static void *zs_zpool_create(char *name, gfp_t gfp, struct zpool_ops *zpool_ops,
+static void *zs_zpool_create(char *name, gfp_t gfp,
+			     const struct zpool_ops *zpool_ops,
 			     struct zpool *zpool)
 {
 	return zs_create_pool(name, gfp);
@@ -441,8 +444,6 @@ static int get_size_class_index(int size)
 	return min(zs_size_classes - 1, idx);
 }
 
-#ifdef CONFIG_ZSMALLOC_STAT
-
 static inline void zs_stat_inc(struct size_class *class,
 				enum zs_stat_type type, unsigned long cnt)
 {
@@ -461,6 +462,8 @@ static inline unsigned long zs_stat_get(struct size_class *class,
 	return class->stats.objs[type];
 }
 
+#ifdef CONFIG_ZSMALLOC_STAT
+
 static int __init zs_stat_init(void)
 {
 	if (!debugfs_initialized())
@@ -576,23 +579,6 @@ static void zs_pool_stat_destroy(struct zs_pool *pool)
 }
 
 #else /* CONFIG_ZSMALLOC_STAT */
-
-static inline void zs_stat_inc(struct size_class *class,
-				enum zs_stat_type type, unsigned long cnt)
-{
-}
-
-static inline void zs_stat_dec(struct size_class *class,
-				enum zs_stat_type type, unsigned long cnt)
-{
-}
-
-static inline unsigned long zs_stat_get(struct size_class *class,
-				enum zs_stat_type type)
-{
-	return 0;
-}
-
 static int __init zs_stat_init(void)
 {
 	return 0;
@@ -610,7 +596,6 @@ static inline int zs_pool_stat_create(char *name, struct zs_pool *pool)
 static inline void zs_pool_stat_destroy(struct zs_pool *pool)
 {
 }
-
 #endif
 
 
@@ -658,13 +643,22 @@ static void insert_zspage(struct page *page, struct size_class *class,
 	if (fullness >= _ZS_NR_FULLNESS_GROUPS)
 		return;
 
-	head = &class->fullness_list[fullness];
-	if (*head)
-		list_add_tail(&page->lru, &(*head)->lru);
-
-	*head = page;
 	zs_stat_inc(class, fullness == ZS_ALMOST_EMPTY ?
 			CLASS_ALMOST_EMPTY : CLASS_ALMOST_FULL, 1);
+
+	head = &class->fullness_list[fullness];
+	if (!*head) {
+		*head = page;
+		return;
+	}
+
+	/*
+	 * We want to see more ZS_FULL pages and less almost
+	 * empty/full. Put pages with higher ->inuse first.
+	 */
+	list_add_tail(&page->lru, &(*head)->lru);
+	if (page->inuse >= (*head)->inuse)
+		*head = page;
 }
 
 /*
@@ -1495,7 +1489,7 @@ void zs_free(struct zs_pool *pool, unsigned long handle)
 }
 EXPORT_SYMBOL_GPL(zs_free);
 
-static void zs_object_copy(unsigned long src, unsigned long dst,
+static void zs_object_copy(unsigned long dst, unsigned long src,
 				struct size_class *class)
 {
 	struct page *s_page, *d_page;
@@ -1602,8 +1596,6 @@ struct zs_compact_control {
 	 /* Starting object index within @s_page which used for live object
 	  * in the subpage. */
 	int index;
-	/* how many of objects are migrated */
-	int nr_migrated;
 };
 
 static int migrate_zspage(struct zs_pool *pool, struct size_class *class,
@@ -1614,7 +1606,6 @@ static int migrate_zspage(struct zs_pool *pool, struct size_class *class,
 	struct page *s_page = cc->s_page;
 	struct page *d_page = cc->d_page;
 	unsigned long index = cc->index;
-	int nr_migrated = 0;
 	int ret = 0;
 
 	while (1) {
@@ -1636,23 +1627,21 @@ static int migrate_zspage(struct zs_pool *pool, struct size_class *class,
 
 		used_obj = handle_to_obj(handle);
 		free_obj = obj_malloc(d_page, class, handle);
-		zs_object_copy(used_obj, free_obj, class);
+		zs_object_copy(free_obj, used_obj, class);
 		index++;
 		record_obj(handle, free_obj);
 		unpin_tag(handle);
 		obj_free(pool, class, used_obj);
-		nr_migrated++;
 	}
 
 	/* Remember last position in this iteration */
 	cc->s_page = s_page;
 	cc->index = index;
-	cc->nr_migrated = nr_migrated;
 
 	return ret;
 }
 
-static struct page *alloc_target_page(struct size_class *class)
+static struct page *isolate_target_page(struct size_class *class)
 {
 	int i;
 	struct page *page;
@@ -1668,8 +1657,17 @@ static struct page *alloc_target_page(struct size_class *class)
 	return page;
 }
 
-static void putback_zspage(struct zs_pool *pool, struct size_class *class,
-				struct page *first_page)
+/*
+ * putback_zspage - add @first_page into right class's fullness list
+ * @pool: target pool
+ * @class: destination class
+ * @first_page: target page
+ *
+ * Return @fist_page's fullness_group
+ */
+static enum fullness_group putback_zspage(struct zs_pool *pool,
+			struct size_class *class,
+			struct page *first_page)
 {
 	enum fullness_group fullness;
 
@@ -1687,50 +1685,72 @@ static void putback_zspage(struct zs_pool *pool, struct size_class *class,
 
 		free_zspage(first_page);
 	}
+
+	return fullness;
 }
 
 static struct page *isolate_source_page(struct size_class *class)
 {
-	struct page *page;
+	int i;
+	struct page *page = NULL;
 
-	page = class->fullness_list[ZS_ALMOST_EMPTY];
-	if (page)
-		remove_zspage(page, class, ZS_ALMOST_EMPTY);
+	for (i = ZS_ALMOST_EMPTY; i >= ZS_ALMOST_FULL; i--) {
+		page = class->fullness_list[i];
+		if (!page)
+			continue;
+
+		remove_zspage(page, class, i);
+		break;
+	}
 
 	return page;
 }
 
-static unsigned long __zs_compact(struct zs_pool *pool,
-				struct size_class *class)
+/*
+ *
+ * Based on the number of unused allocated objects calculate
+ * and return the number of pages that we can free.
+ */
+static unsigned long zs_can_compact(struct size_class *class)
+{
+	unsigned long obj_wasted;
+
+	obj_wasted = zs_stat_get(class, OBJ_ALLOCATED) -
+		zs_stat_get(class, OBJ_USED);
+
+	obj_wasted /= get_maxobj_per_zspage(class->size,
+			class->pages_per_zspage);
+
+	return obj_wasted * class->pages_per_zspage;
+}
+
+static void __zs_compact(struct zs_pool *pool, struct size_class *class)
 {
-	int nr_to_migrate;
 	struct zs_compact_control cc;
 	struct page *src_page;
 	struct page *dst_page = NULL;
-	unsigned long nr_total_migrated = 0;
 
 	spin_lock(&class->lock);
 	while ((src_page = isolate_source_page(class))) {
 
 		BUG_ON(!is_first_page(src_page));
 
-		/* The goal is to migrate all live objects in source page */
-		nr_to_migrate = src_page->inuse;
+		if (!zs_can_compact(class))
+			break;
+
 		cc.index = 0;
 		cc.s_page = src_page;
 
-		while ((dst_page = alloc_target_page(class))) {
+		while ((dst_page = isolate_target_page(class))) {
 			cc.d_page = dst_page;
 			/*
-			 * If there is no more space in dst_page, try to
-			 * allocate another zspage.
+			 * If there is no more space in dst_page, resched
+			 * and see if anyone had allocated another zspage.
 			 */
 			if (!migrate_zspage(pool, class, &cc))
 				break;
 
 			putback_zspage(pool, class, dst_page);
-			nr_total_migrated += cc.nr_migrated;
-			nr_to_migrate -= cc.nr_migrated;
 		}
 
 		/* Stop if we couldn't find slot */
@@ -1738,9 +1758,9 @@ static unsigned long __zs_compact(struct zs_pool *pool,
 			break;
 
 		putback_zspage(pool, class, dst_page);
-		putback_zspage(pool, class, src_page);
+		if (putback_zspage(pool, class, src_page) == ZS_EMPTY)
+			pool->stats.pages_compacted += class->pages_per_zspage;
 		spin_unlock(&class->lock);
-		nr_total_migrated += cc.nr_migrated;
 		cond_resched();
 		spin_lock(&class->lock);
 	}
@@ -1749,14 +1769,11 @@ static unsigned long __zs_compact(struct zs_pool *pool,
 		putback_zspage(pool, class, src_page);
 
 	spin_unlock(&class->lock);
-
-	return nr_total_migrated;
 }
 
 unsigned long zs_compact(struct zs_pool *pool)
 {
 	int i;
-	unsigned long nr_migrated = 0;
 	struct size_class *class;
 
 	for (i = zs_size_classes - 1; i >= 0; i--) {
@@ -1765,13 +1782,80 @@ unsigned long zs_compact(struct zs_pool *pool)
 			continue;
 		if (class->index != i)
 			continue;
-		nr_migrated += __zs_compact(pool, class);
+		__zs_compact(pool, class);
 	}
 
-	return nr_migrated;
+	return pool->stats.pages_compacted;
 }
 EXPORT_SYMBOL_GPL(zs_compact);
 
+void zs_pool_stats(struct zs_pool *pool, struct zs_pool_stats *stats)
+{
+	memcpy(stats, &pool->stats, sizeof(struct zs_pool_stats));
+}
+EXPORT_SYMBOL_GPL(zs_pool_stats);
+
+static unsigned long zs_shrinker_scan(struct shrinker *shrinker,
+		struct shrink_control *sc)
+{
+	unsigned long pages_freed;
+	struct zs_pool *pool = container_of(shrinker, struct zs_pool,
+			shrinker);
+
+	pages_freed = pool->stats.pages_compacted;
+	/*
+	 * Compact classes and calculate compaction delta.
+	 * Can run concurrently with a manually triggered
+	 * (by user) compaction.
+	 */
+	pages_freed = zs_compact(pool) - pages_freed;
+
+	return pages_freed ? pages_freed : SHRINK_STOP;
+}
+
+static unsigned long zs_shrinker_count(struct shrinker *shrinker,
+		struct shrink_control *sc)
+{
+	int i;
+	struct size_class *class;
+	unsigned long pages_to_free = 0;
+	struct zs_pool *pool = container_of(shrinker, struct zs_pool,
+			shrinker);
+
+	if (!pool->shrinker_enabled)
+		return 0;
+
+	for (i = zs_size_classes - 1; i >= 0; i--) {
+		class = pool->size_class[i];
+		if (!class)
+			continue;
+		if (class->index != i)
+			continue;
+
+		pages_to_free += zs_can_compact(class);
+	}
+
+	return pages_to_free;
+}
+
+static void zs_unregister_shrinker(struct zs_pool *pool)
+{
+	if (pool->shrinker_enabled) {
+		unregister_shrinker(&pool->shrinker);
+		pool->shrinker_enabled = false;
+	}
+}
+
+static int zs_register_shrinker(struct zs_pool *pool)
+{
+	pool->shrinker.scan_objects = zs_shrinker_scan;
+	pool->shrinker.count_objects = zs_shrinker_count;
+	pool->shrinker.batch = 0;
+	pool->shrinker.seeks = DEFAULT_SEEKS;
+
+	return register_shrinker(&pool->shrinker);
+}
+
 /**
  * zs_create_pool - Creates an allocation pool to work from.
  * @flags: allocation flags used to allocate pool metadata
@@ -1857,6 +1941,12 @@ struct zs_pool *zs_create_pool(char *name, gfp_t flags)
 	if (zs_pool_stat_create(name, pool))
 		goto err;
 
+	/*
+	 * Not critical, we still can use the pool
+	 * and user can trigger compaction manually.
+	 */
+	if (zs_register_shrinker(pool) == 0)
+		pool->shrinker_enabled = true;
 	return pool;
 
 err:
@@ -1869,6 +1959,7 @@ void zs_destroy_pool(struct zs_pool *pool)
 {
 	int i;
 
+	zs_unregister_shrinker(pool);
 	zs_pool_stat_destroy(pool);
 
 	for (i = 0; i < zs_size_classes; i++) {

mm/zswap.c

@@ -446,75 +446,14 @@ enum zswap_get_swap_ret {
 static int zswap_get_swap_cache_page(swp_entry_t entry,
 				struct page **retpage)
 {
-	struct page *found_page, *new_page = NULL;
-	struct address_space *swapper_space = swap_address_space(entry);
-	int err;
+	bool page_was_allocated;
 
-	*retpage = NULL;
-	do {
-		/*
-		 * First check the swap cache.  Since this is normally
-		 * called after lookup_swap_cache() failed, re-calling
-		 * that would confuse statistics.
-		 */
-		found_page = find_get_page(swapper_space, entry.val);
-		if (found_page)
-			break;
-
-		/*
-		 * Get a new page to read into from swap.
-		 */
-		if (!new_page) {
-			new_page = alloc_page(GFP_KERNEL);
-			if (!new_page)
-				break; /* Out of memory */
-		}
-
-		/*
-		 * call radix_tree_preload() while we can wait.
-		 */
-		err = radix_tree_preload(GFP_KERNEL);
-		if (err)
-			break;
-
-		/*
-		 * Swap entry may have been freed since our caller observed it.
-		 */
-		err = swapcache_prepare(entry);
-		if (err == -EEXIST) { /* seems racy */
-			radix_tree_preload_end();
-			continue;
-		}
-		if (err) { /* swp entry is obsolete ? */
-			radix_tree_preload_end();
-			break;
-		}
-
-		/* May fail (-ENOMEM) if radix-tree node allocation failed. */
-		__set_page_locked(new_page);
-		SetPageSwapBacked(new_page);
-		err = __add_to_swap_cache(new_page, entry);
-		if (likely(!err)) {
-			radix_tree_preload_end();
-			lru_cache_add_anon(new_page);
-			*retpage = new_page;
-			return ZSWAP_SWAPCACHE_NEW;
-		}
-		radix_tree_preload_end();
-		ClearPageSwapBacked(new_page);
-		__clear_page_locked(new_page);
-		/*
-		 * add_to_swap_cache() doesn't return -EEXIST, so we can safely
-		 * clear SWAP_HAS_CACHE flag.
-		 */
-		swapcache_free(entry);
-	} while (err != -ENOMEM);
-
-	if (new_page)
-		page_cache_release(new_page);
-	if (!found_page)
+	*retpage = __read_swap_cache_async(entry, GFP_KERNEL,
+			NULL, 0, &page_was_allocated);
+	if (page_was_allocated)
+		return ZSWAP_SWAPCACHE_NEW;
+	if (!*retpage)
 		return ZSWAP_SWAPCACHE_FAIL;
-	*retpage = found_page;
 	return ZSWAP_SWAPCACHE_EXIST;
 }
 
@@ -816,7 +755,7 @@ static void zswap_frontswap_invalidate_area(unsigned type)
 	zswap_trees[type] = NULL;
 }
 
-static struct zpool_ops zswap_zpool_ops = {
+static const struct zpool_ops zswap_zpool_ops = {
 	.evict = zswap_writeback_entry
 };
 

scripts/coccinelle/api/alloc/pool_zalloc-simple.cocci

@@ -0,0 +1,84 @@
+///
+/// Use *_pool_zalloc rather than *_pool_alloc followed by memset with 0
+///
+// Copyright: (C) 2015 Intel Corp.  GPLv2.
+// Options: --no-includes --include-headers
+//
+// Keywords: dma_pool_zalloc, pci_pool_zalloc
+//
+
+virtual context
+virtual patch
+virtual org
+virtual report
+
+//----------------------------------------------------------
+//  For context mode
+//----------------------------------------------------------
+
+@depends on context@
+expression x;
+statement S;
+@@
+
+* x = \(dma_pool_alloc\|pci_pool_alloc\)(...);
+  if ((x==NULL) || ...) S
+* memset(x,0, ...);
+
+//----------------------------------------------------------
+//  For patch mode
+//----------------------------------------------------------
+
+@depends on patch@
+expression x;
+expression a,b,c;
+statement S;
+@@
+
+- x = dma_pool_alloc(a,b,c);
++ x = dma_pool_zalloc(a,b,c);
+  if ((x==NULL) || ...) S
+- memset(x,0,...);
+
+@depends on patch@
+expression x;
+expression a,b,c;
+statement S;
+@@
+
+- x = pci_pool_alloc(a,b,c);
++ x = pci_pool_zalloc(a,b,c);
+  if ((x==NULL) || ...) S
+- memset(x,0,...);
+
+//----------------------------------------------------------
+//  For org and report mode
+//----------------------------------------------------------
+
+@r depends on org || report@
+expression x;
+expression a,b,c;
+statement S;
+position p;
+@@
+
+ x = @p\(dma_pool_alloc\|pci_pool_alloc\)(a,b,c);
+ if ((x==NULL) || ...) S
+ memset(x,0, ...);
+
+@script:python depends on org@
+p << r.p;
+x << r.x;
+@@
+
+msg="%s" % (x)
+msg_safe=msg.replace("[","@(").replace("]",")")
+coccilib.org.print_todo(p[0], msg_safe)
+
+@script:python depends on report@
+p << r.p;
+x << r.x;
+@@
+
+msg="WARNING: *_pool_zalloc should be used for %s, instead of *_pool_alloc/memset" % (x)
+coccilib.report.print_report(p[0], msg)

tools/testing/selftests/vm/Makefile

@@ -4,7 +4,6 @@ CFLAGS = -Wall
 BINARIES = compaction_test
 BINARIES += hugepage-mmap
 BINARIES += hugepage-shm
-BINARIES += hugetlbfstest
 BINARIES += map_hugetlb
 BINARIES += thuge-gen
 BINARIES += transhuge-stress

tools/testing/selftests/vm/hugetlbfstest.c

@@ -1,86 +0,0 @@
-#define _GNU_SOURCE
-#include <assert.h>
-#include <fcntl.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <sys/mman.h>
-#include <sys/stat.h>
-#include <sys/types.h>
-#include <unistd.h>
-
-typedef unsigned long long u64;
-
-static size_t length = 1 << 24;
-
-static u64 read_rss(void)
-{
-	char buf[4096], *s = buf;
-	int i, fd;
-	u64 rss;
-
-	fd = open("/proc/self/statm", O_RDONLY);
-	assert(fd > 2);
-	memset(buf, 0, sizeof(buf));
-	read(fd, buf, sizeof(buf) - 1);
-	for (i = 0; i < 1; i++)
-		s = strchr(s, ' ') + 1;
-	rss = strtoull(s, NULL, 10);
-	return rss << 12; /* assumes 4k pagesize */
-}
-
-static void do_mmap(int fd, int extra_flags, int unmap)
-{
-	int *p;
-	int flags = MAP_PRIVATE | MAP_POPULATE | extra_flags;
-	u64 before, after;
-	int ret;
-
-	before = read_rss();
-	p = mmap(NULL, length, PROT_READ | PROT_WRITE, flags, fd, 0);
-	assert(p != MAP_FAILED ||
-			!"mmap returned an unexpected error");
-	after = read_rss();
-	assert(llabs(after - before - length) < 0x40000 ||
-			!"rss didn't grow as expected");
-	if (!unmap)
-		return;
-	ret = munmap(p, length);
-	assert(!ret || !"munmap returned an unexpected error");
-	after = read_rss();
-	assert(llabs(after - before) < 0x40000 ||
-			!"rss didn't shrink as expected");
-}
-
-static int open_file(const char *path)
-{
-	int fd, err;
-
-	unlink(path);
-	fd = open(path, O_CREAT | O_RDWR | O_TRUNC | O_EXCL
-			| O_LARGEFILE | O_CLOEXEC, 0600);
-	assert(fd > 2);
-	unlink(path);
-	err = ftruncate(fd, length);
-	assert(!err);
-	return fd;
-}
-
-int main(void)
-{
-	int hugefd, fd;
-
-	fd = open_file("/dev/shm/hugetlbhog");
-	hugefd = open_file("/hugepages/hugetlbhog");
-
-	system("echo 100 > /proc/sys/vm/nr_hugepages");
-	do_mmap(-1, MAP_ANONYMOUS, 1);
-	do_mmap(fd, 0, 1);
-	do_mmap(-1, MAP_ANONYMOUS | MAP_HUGETLB, 1);
-	do_mmap(hugefd, 0, 1);
-	do_mmap(hugefd, MAP_HUGETLB, 1);
-	/* Leak the last one to test do_exit() */
-	do_mmap(-1, MAP_ANONYMOUS | MAP_HUGETLB, 0);
-	printf("oll korrekt.\n");
-	return 0;
-}

tools/testing/selftests/vm/run_vmtests

@@ -75,16 +75,9 @@ else
 	echo "[PASS]"
 fi
 
-echo "--------------------"
-echo "running hugetlbfstest"
-echo "--------------------"
-./hugetlbfstest
-if [ $? -ne 0 ]; then
-	echo "[FAIL]"
-	exitcode=1
-else
-	echo "[PASS]"
-fi
+echo "NOTE: The above hugetlb tests provide minimal coverage.  Use"
+echo "      https://github.com/libhugetlbfs/libhugetlbfs.git for"
+echo "      hugetlb regression testing."
 
 echo "--------------------"
 echo "running userfaultfd"

tools/testing/selftests/vm/userfaultfd.c

@@ -147,7 +147,8 @@ static void *locking_thread(void *arg)
 			if (sizeof(page_nr) > sizeof(rand_nr)) {
 				if (random_r(&rand, &rand_nr))
 					fprintf(stderr, "random_r 2 error\n"), exit(1);
-				page_nr |= ((unsigned long) rand_nr) << 32;
+				page_nr |= (((unsigned long) rand_nr) << 16) <<
+					   16;
 			}
 		} else
 			page_nr += 1;
@@ -290,7 +291,8 @@ static void *uffd_poll_thread(void *arg)
 				msg.event), exit(1);
 		if (msg.arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE)
 			fprintf(stderr, "unexpected write fault\n"), exit(1);
-		offset = (char *)msg.arg.pagefault.address - area_dst;
+		offset = (char *)(unsigned long)msg.arg.pagefault.address -
+			 area_dst;
 		offset &= ~(page_size-1);
 		if (copy_page(offset))
 			userfaults++;
@@ -327,7 +329,8 @@ static void *uffd_read_thread(void *arg)
 		if (bounces & BOUNCE_VERIFY &&
 		    msg.arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE)
 			fprintf(stderr, "unexpected write fault\n"), exit(1);
-		offset = (char *)msg.arg.pagefault.address - area_dst;
+		offset = (char *)(unsigned long)msg.arg.pagefault.address -
+			 area_dst;
 		offset &= ~(page_size-1);
 		if (copy_page(offset))
 			(*this_cpu_userfaults)++;

tools/vm/page-types.c

@@ -57,23 +57,15 @@
  * pagemap kernel ABI bits
  */
 
-#define PM_ENTRY_BYTES      sizeof(uint64_t)
-#define PM_STATUS_BITS      3
-#define PM_STATUS_OFFSET    (64 - PM_STATUS_BITS)
-#define PM_STATUS_MASK      (((1LL << PM_STATUS_BITS) - 1) << PM_STATUS_OFFSET)
-#define PM_STATUS(nr)       (((nr) << PM_STATUS_OFFSET) & PM_STATUS_MASK)
-#define PM_PSHIFT_BITS      6
-#define PM_PSHIFT_OFFSET    (PM_STATUS_OFFSET - PM_PSHIFT_BITS)
-#define PM_PSHIFT_MASK      (((1LL << PM_PSHIFT_BITS) - 1) << PM_PSHIFT_OFFSET)
-#define __PM_PSHIFT(x)      (((uint64_t) (x) << PM_PSHIFT_OFFSET) & PM_PSHIFT_MASK)
-#define PM_PFRAME_MASK      ((1LL << PM_PSHIFT_OFFSET) - 1)
-#define PM_PFRAME(x)        ((x) & PM_PFRAME_MASK)
-
-#define __PM_SOFT_DIRTY      (1LL)
-#define PM_PRESENT          PM_STATUS(4LL)
-#define PM_SWAP             PM_STATUS(2LL)
-#define PM_SOFT_DIRTY       __PM_PSHIFT(__PM_SOFT_DIRTY)
-
+#define PM_ENTRY_BYTES		8
+#define PM_PFRAME_BITS		55
+#define PM_PFRAME_MASK		((1LL << PM_PFRAME_BITS) - 1)
+#define PM_PFRAME(x)		((x) & PM_PFRAME_MASK)
+#define PM_SOFT_DIRTY		(1ULL << 55)
+#define PM_MMAP_EXCLUSIVE	(1ULL << 56)
+#define PM_FILE			(1ULL << 61)
+#define PM_SWAP			(1ULL << 62)
+#define PM_PRESENT		(1ULL << 63)
 
 /*
  * kernel page flags
@@ -100,6 +92,8 @@
 #define KPF_SLOB_FREE		49
 #define KPF_SLUB_FROZEN		50
 #define KPF_SLUB_DEBUG		51
+#define KPF_FILE		62
+#define KPF_MMAP_EXCLUSIVE	63
 
 #define KPF_ALL_BITS		((uint64_t)~0ULL)
 #define KPF_HACKERS_BITS	(0xffffULL << 32)
@@ -149,6 +143,9 @@ static const char * const page_flag_names[] = {
 	[KPF_SLOB_FREE]		= "P:slob_free",
 	[KPF_SLUB_FROZEN]	= "A:slub_frozen",
 	[KPF_SLUB_DEBUG]	= "E:slub_debug",
+
+	[KPF_FILE]		= "F:file",
+	[KPF_MMAP_EXCLUSIVE]	= "1:mmap_exclusive",
 };
 
 
@@ -452,6 +449,10 @@ static uint64_t expand_overloaded_flags(uint64_t flags, uint64_t pme)
 
 	if (pme & PM_SOFT_DIRTY)
 		flags |= BIT(SOFTDIRTY);
+	if (pme & PM_FILE)
+		flags |= BIT(FILE);
+	if (pme & PM_MMAP_EXCLUSIVE)
+		flags |= BIT(MMAP_EXCLUSIVE);
 
 	return flags;
 }