Merge branch 'akpm' (patches from Andrew)

Merge updates from Andrew Morton:

 - various misc bits

 - DAX updates

 - OCFS2

 - most of MM

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (119 commits)
  mm,fork: introduce MADV_WIPEONFORK
  x86,mpx: make mpx depend on x86-64 to free up VMA flag
  mm: add /proc/pid/smaps_rollup
  mm: hugetlb: clear target sub-page last when clearing huge page
  mm: oom: let oom_reap_task and exit_mmap run concurrently
  swap: choose swap device according to numa node
  mm: replace TIF_MEMDIE checks by tsk_is_oom_victim
  mm, oom: do not rely on TIF_MEMDIE for memory reserves access
  z3fold: use per-cpu unbuddied lists
  mm, swap: don't use VMA based swap readahead if HDD is used as swap
  mm, swap: add sysfs interface for VMA based swap readahead
  mm, swap: VMA based swap readahead
  mm, swap: fix swap readahead marking
  mm, swap: add swap readahead hit statistics
  mm/vmalloc.c: don't reinvent the wheel but use existing llist API
  mm/vmstat.c: fix wrong comment
  selftests/memfd: add memfd_create hugetlbfs selftest
  mm/shmem: add hugetlbfs support to memfd_create()
  mm, devm_memremap_pages: use multi-order radix for ZONE_DEVICE lookups
  mm/vmalloc.c: halve the number of comparisons performed in pcpu_get_vm_areas()
  ...

Documentation/ABI/testing/procfs-smaps_rollup

@@ -0,0 +1,31 @@
+What:		/proc/pid/smaps_rollup
+Date:		August 2017
+Contact:	Daniel Colascione <dancol@google.com>
+Description:
+		This file provides pre-summed memory information for a
+		process.  The format is identical to /proc/pid/smaps,
+		except instead of an entry for each VMA in a process,
+		smaps_rollup has a single entry (tagged "[rollup]")
+		for which each field is the sum of the corresponding
+		fields from all the maps in /proc/pid/smaps.
+		For more details, see the procfs man page.
+
+		Typical output looks like this:
+
+		00100000-ff709000 ---p 00000000 00:00 0		 [rollup]
+		Rss:		     884 kB
+		Pss:		     385 kB
+		Shared_Clean:	     696 kB
+		Shared_Dirty:	       0 kB
+		Private_Clean:	     120 kB
+		Private_Dirty:	      68 kB
+		Referenced:	     884 kB
+		Anonymous:	      68 kB
+		LazyFree:	       0 kB
+		AnonHugePages:	       0 kB
+		ShmemPmdMapped:	       0 kB
+		Shared_Hugetlb:	       0 kB
+		Private_Hugetlb:       0 kB
+		Swap:		       0 kB
+		SwapPss:	       0 kB
+		Locked:		     385 kB

Documentation/ABI/testing/sysfs-block-zram

@@ -90,3 +90,11 @@ Description:
 		device's debugging info useful for kernel developers. Its
 		format is not documented intentionally and may change
 		anytime without any notice.
+
+What:		/sys/block/zram<id>/backing_dev
+Date:		June 2017
+Contact:	Minchan Kim <minchan@kernel.org>
+Description:
+		The backing_dev file is read-write and set up backing
+		device for zram to write incompressible pages.
+		For using, user should enable CONFIG_ZRAM_WRITEBACK.

Documentation/ABI/testing/sysfs-kernel-mm-swap

@@ -0,0 +1,26 @@
+What:		/sys/kernel/mm/swap/
+Date:		August 2017
+Contact:	Linux memory management mailing list <linux-mm@kvack.org>
+Description:	Interface for swapping
+
+What:		/sys/kernel/mm/swap/vma_ra_enabled
+Date:		August 2017
+Contact:	Linux memory management mailing list <linux-mm@kvack.org>
+Description:	Enable/disable VMA based swap readahead.
+
+		If set to true, the VMA based swap readahead algorithm
+		will be used for swappable anonymous pages mapped in a
+		VMA, and the global swap readahead algorithm will be
+		still used for tmpfs etc. other users.  If set to
+		false, the global swap readahead algorithm will be
+		used for all swappable pages.
+
+What:		/sys/kernel/mm/swap/vma_ra_max_order
+Date:		August 2017
+Contact:	Linux memory management mailing list <linux-mm@kvack.org>
+Description:	The max readahead size in order for VMA based swap readahead
+
+		VMA based swap readahead algorithm will readahead at
+		most 1 << max_order pages for each readahead.  The
+		real readahead size for each readahead will be scaled
+		according to the estimation algorithm.

Documentation/admin-guide/kernel-parameters.txt

@@ -2783,7 +2783,7 @@
 			Allowed values are enable and disable
 
 	numa_zonelist_order= [KNL, BOOT] Select zonelist order for NUMA.
-			one of ['zone', 'node', 'default'] can be specified
+			'node', 'default' can be specified
 			This can be set from sysctl after boot.
 			See Documentation/sysctl/vm.txt for details.
 

Documentation/blockdev/zram.txt

@@ -168,6 +168,7 @@ max_comp_streams  RW    the number of possible concurrent compress operations
 comp_algorithm    RW    show and change the compression algorithm
 compact           WO    trigger memory compaction
 debug_stat        RO    this file is used for zram debugging purposes
+backing_dev	  RW	set up backend storage for zram to write out
 
 
 User space is advised to use the following files to read the device statistics.
@@ -231,5 +232,15 @@ line of text and contains the following stats separated by whitespace:
 	resets the disksize to zero. You must set the disksize again
 	before reusing the device.
 
+* Optional Feature
+
+= writeback
+
+With incompressible pages, there is no memory saving with zram.
+Instead, with CONFIG_ZRAM_WRITEBACK, zram can write incompressible page
+to backing storage rather than keeping it in memory.
+User should set up backing device via /sys/block/zramX/backing_dev
+before disksize setting.
+
 Nitin Gupta
 ngupta@vflare.org

Documentation/filesystems/caching/netfs-api.txt

@@ -151,8 +151,6 @@ To define an object, a structure of the following type should be filled out:
 		void (*mark_pages_cached)(void *cookie_netfs_data,
 					  struct address_space *mapping,
 					  struct pagevec *cached_pvec);
-
-		void (*now_uncached)(void *cookie_netfs_data);
 	};
 
 This has the following fields:

Documentation/filesystems/dax.txt

@@ -63,9 +63,8 @@ Filesystem support consists of
 - implementing an mmap file operation for DAX files which sets the
   VM_MIXEDMAP and VM_HUGEPAGE flags on the VMA, and setting the vm_ops to
   include handlers for fault, pmd_fault, page_mkwrite, pfn_mkwrite. These
-  handlers should probably call dax_iomap_fault() (for fault and page_mkwrite
-  handlers), dax_iomap_pmd_fault(), dax_pfn_mkwrite() passing the appropriate
-  iomap operations.
+  handlers should probably call dax_iomap_fault() passing the appropriate
+  fault size and iomap operations.
 - calling iomap_zero_range() passing appropriate iomap operations instead of
   block_truncate_page() for DAX files
 - ensuring that there is sufficient locking between reads, writes,

Documentation/sysctl/vm.txt

@@ -572,7 +572,9 @@ See Documentation/nommu-mmap.txt for more information.
 
 numa_zonelist_order
 
-This sysctl is only for NUMA.
+This sysctl is only for NUMA and it is deprecated. Anything but
+Node order will fail!
+
 'where the memory is allocated from' is controlled by zonelists.
 (This documentation ignores ZONE_HIGHMEM/ZONE_DMA32 for simple explanation.
  you may be able to read ZONE_DMA as ZONE_DMA32...)

Documentation/vm/numa

@@ -79,11 +79,8 @@ memory, Linux must decide whether to order the zonelists such that allocations
 fall back to the same zone type on a different node, or to a different zone
 type on the same node.  This is an important consideration because some zones,
 such as DMA or DMA32, represent relatively scarce resources.  Linux chooses
-a default zonelist order based on the sizes of the various zone types relative
-to the total memory of the node and the total memory of the system.  The
-default zonelist order may be overridden using the numa_zonelist_order kernel
-boot parameter or sysctl.  [see Documentation/admin-guide/kernel-parameters.rst and
-Documentation/sysctl/vm.txt]
+a default Node ordered zonelist. This means it tries to fallback to other zones
+from the same node before using remote nodes which are ordered by NUMA distance.
 
 By default, Linux will attempt to satisfy memory allocation requests from the
 node to which the CPU that executes the request is assigned.  Specifically,

Documentation/vm/swap_numa.txt

@@ -0,0 +1,69 @@
+Automatically bind swap device to numa node
+-------------------------------------------
+
+If the system has more than one swap device and swap device has the node
+information, we can make use of this information to decide which swap
+device to use in get_swap_pages() to get better performance.
+
+
+How to use this feature
+-----------------------
+
+Swap device has priority and that decides the order of it to be used. To make
+use of automatically binding, there is no need to manipulate priority settings
+for swap devices. e.g. on a 2 node machine, assume 2 swap devices swapA and
+swapB, with swapA attached to node 0 and swapB attached to node 1, are going
+to be swapped on. Simply swapping them on by doing:
+# swapon /dev/swapA
+# swapon /dev/swapB
+
+Then node 0 will use the two swap devices in the order of swapA then swapB and
+node 1 will use the two swap devices in the order of swapB then swapA. Note
+that the order of them being swapped on doesn't matter.
+
+A more complex example on a 4 node machine. Assume 6 swap devices are going to
+be swapped on: swapA and swapB are attached to node 0, swapC is attached to
+node 1, swapD and swapE are attached to node 2 and swapF is attached to node3.
+The way to swap them on is the same as above:
+# swapon /dev/swapA
+# swapon /dev/swapB
+# swapon /dev/swapC
+# swapon /dev/swapD
+# swapon /dev/swapE
+# swapon /dev/swapF
+
+Then node 0 will use them in the order of:
+swapA/swapB -> swapC -> swapD -> swapE -> swapF
+swapA and swapB will be used in a round robin mode before any other swap device.
+
+node 1 will use them in the order of:
+swapC -> swapA -> swapB -> swapD -> swapE -> swapF
+
+node 2 will use them in the order of:
+swapD/swapE -> swapA -> swapB -> swapC -> swapF
+Similaly, swapD and swapE will be used in a round robin mode before any
+other swap devices.
+
+node 3 will use them in the order of:
+swapF -> swapA -> swapB -> swapC -> swapD -> swapE
+
+
+Implementation details
+----------------------
+
+The current code uses a priority based list, swap_avail_list, to decide
+which swap device to use and if multiple swap devices share the same
+priority, they are used round robin. This change here replaces the single
+global swap_avail_list with a per-numa-node list, i.e. for each numa node,
+it sees its own priority based list of available swap devices. Swap
+device's priority can be promoted on its matching node's swap_avail_list.
+
+The current swap device's priority is set as: user can set a >=0 value,
+or the system will pick one starting from -1 then downwards. The priority
+value in the swap_avail_list is the negated value of the swap device's
+due to plist being sorted from low to high. The new policy doesn't change
+the semantics for priority >=0 cases, the previous starting from -1 then
+downwards now becomes starting from -2 then downwards and -1 is reserved
+as the promoted value. So if multiple swap devices are attached to the same
+node, they will all be promoted to priority -1 on that node's plist and will
+be used round robin before any other swap devices.

arch/alpha/include/uapi/asm/mman.h

@@ -64,20 +64,12 @@
 					   overrides the coredump filter bits */
 #define MADV_DODUMP	17		/* Clear the MADV_NODUMP flag */
 
+#define MADV_WIPEONFORK 18		/* Zero memory on fork, child only */
+#define MADV_KEEPONFORK 19		/* Undo MADV_WIPEONFORK */
+
 /* compatibility flags */
 #define MAP_FILE	0
 
-/*
- * When MAP_HUGETLB is set bits [26:31] encode the log2 of the huge page size.
- * This gives us 6 bits, which is enough until someone invents 128 bit address
- * spaces.
- *
- * Assume these are all power of twos.
- * When 0 use the default page size.
- */
-#define MAP_HUGE_SHIFT	26
-#define MAP_HUGE_MASK	0x3f
-
 #define PKEY_DISABLE_ACCESS	0x1
 #define PKEY_DISABLE_WRITE	0x2
 #define PKEY_ACCESS_MASK	(PKEY_DISABLE_ACCESS |\

arch/metag/include/asm/topology.h

@@ -4,7 +4,6 @@
 #ifdef CONFIG_NUMA
 
 #define cpu_to_node(cpu)	((void)(cpu), 0)
-#define parent_node(node)	((void)(node), 0)
 
 #define cpumask_of_node(node)	((void)node, cpu_online_mask)
 

arch/mips/include/uapi/asm/mman.h

@@ -91,20 +91,12 @@
 					   overrides the coredump filter bits */
 #define MADV_DODUMP	17		/* Clear the MADV_NODUMP flag */
 
+#define MADV_WIPEONFORK 18		/* Zero memory on fork, child only */
+#define MADV_KEEPONFORK 19		/* Undo MADV_WIPEONFORK */
+
 /* compatibility flags */
 #define MAP_FILE	0
 
-/*
- * When MAP_HUGETLB is set bits [26:31] encode the log2 of the huge page size.
- * This gives us 6 bits, which is enough until someone invents 128 bit address
- * spaces.
- *
- * Assume these are all power of twos.
- * When 0 use the default page size.
- */
-#define MAP_HUGE_SHIFT	26
-#define MAP_HUGE_MASK	0x3f
-
 #define PKEY_DISABLE_ACCESS	0x1
 #define PKEY_DISABLE_WRITE	0x2
 #define PKEY_ACCESS_MASK	(PKEY_DISABLE_ACCESS |\

arch/parisc/include/uapi/asm/mman.h

@@ -57,6 +57,9 @@
 					   overrides the coredump filter bits */
 #define MADV_DODUMP	70		/* Clear the MADV_NODUMP flag */
 
+#define MADV_WIPEONFORK 71		/* Zero memory on fork, child only */
+#define MADV_KEEPONFORK 72		/* Undo MADV_WIPEONFORK */
+
 #define MADV_HWPOISON     100		/* poison a page for testing */
 #define MADV_SOFT_OFFLINE 101		/* soft offline page for testing */
 
@@ -64,17 +67,6 @@
 #define MAP_FILE	0
 #define MAP_VARIABLE	0
 
-/*
- * When MAP_HUGETLB is set bits [26:31] encode the log2 of the huge page size.
- * This gives us 6 bits, which is enough until someone invents 128 bit address
- * spaces.
- *
- * Assume these are all power of twos.
- * When 0 use the default page size.
- */
-#define MAP_HUGE_SHIFT	26
-#define MAP_HUGE_MASK	0x3f
-
 #define PKEY_DISABLE_ACCESS	0x1
 #define PKEY_DISABLE_WRITE	0x2
 #define PKEY_ACCESS_MASK	(PKEY_DISABLE_ACCESS |\

arch/powerpc/include/uapi/asm/mman.h

@@ -29,20 +29,4 @@
 #define MAP_STACK	0x20000		/* give out an address that is best suited for process/thread stacks */
 #define MAP_HUGETLB	0x40000		/* create a huge page mapping */
 
-/*
- * When MAP_HUGETLB is set, bits [26:31] of the flags argument to mmap(2),
- * encode the log2 of the huge page size. A value of zero indicates that the
- * default huge page size should be used. To use a non-default huge page size,
- * one of these defines can be used, or the size can be encoded by hand. Note
- * that on most systems only a subset, or possibly none, of these sizes will be
- * available.
- */
-#define MAP_HUGE_512KB	(19 << MAP_HUGE_SHIFT)	/* 512KB HugeTLB Page */
-#define MAP_HUGE_1MB	(20 << MAP_HUGE_SHIFT)	/* 1MB   HugeTLB Page */
-#define MAP_HUGE_2MB	(21 << MAP_HUGE_SHIFT)	/* 2MB   HugeTLB Page */
-#define MAP_HUGE_8MB	(23 << MAP_HUGE_SHIFT)	/* 8MB   HugeTLB Page */
-#define MAP_HUGE_16MB	(24 << MAP_HUGE_SHIFT)	/* 16MB  HugeTLB Page */
-#define MAP_HUGE_1GB	(30 << MAP_HUGE_SHIFT)	/* 1GB   HugeTLB Page */
-#define MAP_HUGE_16GB	(34 << MAP_HUGE_SHIFT)	/* 16GB  HugeTLB Page */
-
 #endif /* _UAPI_ASM_POWERPC_MMAN_H */

arch/x86/Kconfig

@@ -1806,7 +1806,9 @@ config X86_SMAP
 config X86_INTEL_MPX
 	prompt "Intel MPX (Memory Protection Extensions)"
 	def_bool n
-	depends on CPU_SUP_INTEL
+	# Note: only available in 64-bit mode due to VMA flags shortage
+	depends on CPU_SUP_INTEL && X86_64
+	select ARCH_USES_HIGH_VMA_FLAGS
 	---help---
 	  MPX provides hardware features that can be used in
 	  conjunction with compiler-instrumented code to check

arch/x86/include/uapi/asm/mman.h

@@ -3,9 +3,6 @@
 
 #define MAP_32BIT	0x40		/* only give out 32bit addresses */
 
-#define MAP_HUGE_2MB    (21 << MAP_HUGE_SHIFT)
-#define MAP_HUGE_1GB    (30 << MAP_HUGE_SHIFT)
-
 #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
 /*
  * Take the 4 protection key bits out of the vma->vm_flags

arch/xtensa/include/uapi/asm/mman.h

@@ -103,20 +103,12 @@
 					   overrides the coredump filter bits */
 #define MADV_DODUMP	17		/* Clear the MADV_NODUMP flag */
 
+#define MADV_WIPEONFORK 18		/* Zero memory on fork, child only */
+#define MADV_KEEPONFORK 19		/* Undo MADV_WIPEONFORK */
+
 /* compatibility flags */
 #define MAP_FILE	0
 
-/*
- * When MAP_HUGETLB is set bits [26:31] encode the log2 of the huge page size.
- * This gives us 6 bits, which is enough until someone invents 128 bit address
- * spaces.
- *
- * Assume these are all power of twos.
- * When 0 use the default page size.
- */
-#define MAP_HUGE_SHIFT	26
-#define MAP_HUGE_MASK	0x3f
-
 #define PKEY_DISABLE_ACCESS	0x1
 #define PKEY_DISABLE_WRITE	0x2
 #define PKEY_ACCESS_MASK	(PKEY_DISABLE_ACCESS |\

drivers/base/memory.c

@@ -388,6 +388,19 @@ static ssize_t show_phys_device(struct device *dev,
 }
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
+static void print_allowed_zone(char *buf, int nid, unsigned long start_pfn,
+		unsigned long nr_pages, int online_type,
+		struct zone *default_zone)
+{
+	struct zone *zone;
+
+	zone = zone_for_pfn_range(online_type, nid, start_pfn, nr_pages);
+	if (zone != default_zone) {
+		strcat(buf, " ");
+		strcat(buf, zone->name);
+	}
+}
+
 static ssize_t show_valid_zones(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
@@ -395,7 +408,7 @@ static ssize_t show_valid_zones(struct device *dev,
 	unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr);
 	unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
 	unsigned long valid_start_pfn, valid_end_pfn;
-	bool append = false;
+	struct zone *default_zone;
 	int nid;
 
 	/*
@@ -418,16 +431,13 @@ static ssize_t show_valid_zones(struct device *dev,
 	}
 
 	nid = pfn_to_nid(start_pfn);
-	if (allow_online_pfn_range(nid, start_pfn, nr_pages, MMOP_ONLINE_KERNEL)) {
-		strcat(buf, default_zone_for_pfn(nid, start_pfn, nr_pages)->name);
-		append = true;
-	}
+	default_zone = zone_for_pfn_range(MMOP_ONLINE_KEEP, nid, start_pfn, nr_pages);
+	strcat(buf, default_zone->name);
 
-	if (allow_online_pfn_range(nid, start_pfn, nr_pages, MMOP_ONLINE_MOVABLE)) {
-		if (append)
-			strcat(buf, " ");
-		strcat(buf, NODE_DATA(nid)->node_zones[ZONE_MOVABLE].name);
-	}
+	print_allowed_zone(buf, nid, start_pfn, nr_pages, MMOP_ONLINE_KERNEL,
+			default_zone);
+	print_allowed_zone(buf, nid, start_pfn, nr_pages, MMOP_ONLINE_MOVABLE,
+			default_zone);
 out:
 	strcat(buf, "\n");
 

drivers/block/brd.c

@@ -326,7 +326,11 @@ static int brd_rw_page(struct block_device *bdev, sector_t sector,
 		       struct page *page, bool is_write)
 {
 	struct brd_device *brd = bdev->bd_disk->private_data;
-	int err = brd_do_bvec(brd, page, PAGE_SIZE, 0, is_write, sector);
+	int err;
+
+	if (PageTransHuge(page))
+		return -ENOTSUPP;
+	err = brd_do_bvec(brd, page, PAGE_SIZE, 0, is_write, sector);
 	page_endio(page, is_write, err);
 	return err;
 }

drivers/block/zram/Kconfig

@@ -13,3 +13,15 @@ config ZRAM
 	  disks and maybe many more.
 
 	  See zram.txt for more information.
+
+config ZRAM_WRITEBACK
+       bool "Write back incompressible page to backing device"
+       depends on ZRAM
+       default n
+       help
+	 With incompressible page, there is no memory saving to keep it
+	 in memory. Instead, write it out to backing device.
+	 For this feature, admin should set up backing device via
+	 /sys/block/zramX/backing_dev.
+
+	 See zram.txt for more infomration.

drivers/block/zram/zram_drv.c

@@ -270,6 +270,349 @@ static ssize_t mem_used_max_store(struct device *dev,
 	return len;
 }
 
+#ifdef CONFIG_ZRAM_WRITEBACK
+static bool zram_wb_enabled(struct zram *zram)
+{
+	return zram->backing_dev;
+}
+
+static void reset_bdev(struct zram *zram)
+{
+	struct block_device *bdev;
+
+	if (!zram_wb_enabled(zram))
+		return;
+
+	bdev = zram->bdev;
+	if (zram->old_block_size)
+		set_blocksize(bdev, zram->old_block_size);
+	blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
+	/* hope filp_close flush all of IO */
+	filp_close(zram->backing_dev, NULL);
+	zram->backing_dev = NULL;
+	zram->old_block_size = 0;
+	zram->bdev = NULL;
+
+	kvfree(zram->bitmap);
+	zram->bitmap = NULL;
+}
+
+static ssize_t backing_dev_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct zram *zram = dev_to_zram(dev);
+	struct file *file = zram->backing_dev;
+	char *p;
+	ssize_t ret;
+
+	down_read(&zram->init_lock);
+	if (!zram_wb_enabled(zram)) {
+		memcpy(buf, "none\n", 5);
+		up_read(&zram->init_lock);
+		return 5;
+	}
+
+	p = file_path(file, buf, PAGE_SIZE - 1);
+	if (IS_ERR(p)) {
+		ret = PTR_ERR(p);
+		goto out;
+	}
+
+	ret = strlen(p);
+	memmove(buf, p, ret);
+	buf[ret++] = '\n';
+out:
+	up_read(&zram->init_lock);
+	return ret;
+}
+
+static ssize_t backing_dev_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t len)
+{
+	char *file_name;
+	struct file *backing_dev = NULL;
+	struct inode *inode;
+	struct address_space *mapping;
+	unsigned int bitmap_sz, old_block_size = 0;
+	unsigned long nr_pages, *bitmap = NULL;
+	struct block_device *bdev = NULL;
+	int err;
+	struct zram *zram = dev_to_zram(dev);
+
+	file_name = kmalloc(PATH_MAX, GFP_KERNEL);
+	if (!file_name)
+		return -ENOMEM;
+
+	down_write(&zram->init_lock);
+	if (init_done(zram)) {
+		pr_info("Can't setup backing device for initialized device\n");
+		err = -EBUSY;
+		goto out;
+	}
+
+	strlcpy(file_name, buf, len);
+
+	backing_dev = filp_open(file_name, O_RDWR|O_LARGEFILE, 0);
+	if (IS_ERR(backing_dev)) {
+		err = PTR_ERR(backing_dev);
+		backing_dev = NULL;
+		goto out;
+	}
+
+	mapping = backing_dev->f_mapping;
+	inode = mapping->host;
+
+	/* Support only block device in this moment */
+	if (!S_ISBLK(inode->i_mode)) {
+		err = -ENOTBLK;
+		goto out;
+	}
+
+	bdev = bdgrab(I_BDEV(inode));
+	err = blkdev_get(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL, zram);
+	if (err < 0)
+		goto out;
+
+	nr_pages = i_size_read(inode) >> PAGE_SHIFT;
+	bitmap_sz = BITS_TO_LONGS(nr_pages) * sizeof(long);
+	bitmap = kvzalloc(bitmap_sz, GFP_KERNEL);
+	if (!bitmap) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	old_block_size = block_size(bdev);
+	err = set_blocksize(bdev, PAGE_SIZE);
+	if (err)
+		goto out;
+
+	reset_bdev(zram);
+	spin_lock_init(&zram->bitmap_lock);
+
+	zram->old_block_size = old_block_size;
+	zram->bdev = bdev;
+	zram->backing_dev = backing_dev;
+	zram->bitmap = bitmap;
+	zram->nr_pages = nr_pages;
+	up_write(&zram->init_lock);
+
+	pr_info("setup backing device %s\n", file_name);
+	kfree(file_name);
+
+	return len;
+out:
+	if (bitmap)
+		kvfree(bitmap);
+
+	if (bdev)
+		blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL);
+
+	if (backing_dev)
+		filp_close(backing_dev, NULL);
+
+	up_write(&zram->init_lock);
+
+	kfree(file_name);
+
+	return err;
+}
+
+static unsigned long get_entry_bdev(struct zram *zram)
+{
+	unsigned long entry;
+
+	spin_lock(&zram->bitmap_lock);
+	/* skip 0 bit to confuse zram.handle = 0 */
+	entry = find_next_zero_bit(zram->bitmap, zram->nr_pages, 1);
+	if (entry == zram->nr_pages) {
+		spin_unlock(&zram->bitmap_lock);
+		return 0;
+	}
+
+	set_bit(entry, zram->bitmap);
+	spin_unlock(&zram->bitmap_lock);
+
+	return entry;
+}
+
+static void put_entry_bdev(struct zram *zram, unsigned long entry)
+{
+	int was_set;
+
+	spin_lock(&zram->bitmap_lock);
+	was_set = test_and_clear_bit(entry, zram->bitmap);
+	spin_unlock(&zram->bitmap_lock);
+	WARN_ON_ONCE(!was_set);
+}
+
+void zram_page_end_io(struct bio *bio)
+{
+	struct page *page = bio->bi_io_vec[0].bv_page;
+
+	page_endio(page, op_is_write(bio_op(bio)),
+			blk_status_to_errno(bio->bi_status));
+	bio_put(bio);
+}
+
+/*
+ * Returns 1 if the submission is successful.
+ */
+static int read_from_bdev_async(struct zram *zram, struct bio_vec *bvec,
+			unsigned long entry, struct bio *parent)
+{
+	struct bio *bio;
+
+	bio = bio_alloc(GFP_ATOMIC, 1);
+	if (!bio)
+		return -ENOMEM;
+
+	bio->bi_iter.bi_sector = entry * (PAGE_SIZE >> 9);
+	bio->bi_bdev = zram->bdev;
+	if (!bio_add_page(bio, bvec->bv_page, bvec->bv_len, bvec->bv_offset)) {
+		bio_put(bio);
+		return -EIO;
+	}
+
+	if (!parent) {
+		bio->bi_opf = REQ_OP_READ;
+		bio->bi_end_io = zram_page_end_io;
+	} else {
+		bio->bi_opf = parent->bi_opf;
+		bio_chain(bio, parent);
+	}
+
+	submit_bio(bio);
+	return 1;
+}
+
+struct zram_work {
+	struct work_struct work;
+	struct zram *zram;
+	unsigned long entry;
+	struct bio *bio;
+};
+
+#if PAGE_SIZE != 4096
+static void zram_sync_read(struct work_struct *work)
+{
+	struct bio_vec bvec;
+	struct zram_work *zw = container_of(work, struct zram_work, work);
+	struct zram *zram = zw->zram;
+	unsigned long entry = zw->entry;
+	struct bio *bio = zw->bio;
+
+	read_from_bdev_async(zram, &bvec, entry, bio);
+}
+
+/*
+ * Block layer want one ->make_request_fn to be active at a time
+ * so if we use chained IO with parent IO in same context,
+ * it's a deadlock. To avoid, it, it uses worker thread context.
+ */
+static int read_from_bdev_sync(struct zram *zram, struct bio_vec *bvec,
+				unsigned long entry, struct bio *bio)
+{
+	struct zram_work work;
+
+	work.zram = zram;
+	work.entry = entry;
+	work.bio = bio;
+
+	INIT_WORK_ONSTACK(&work.work, zram_sync_read);
+	queue_work(system_unbound_wq, &work.work);
+	flush_work(&work.work);
+	destroy_work_on_stack(&work.work);
+
+	return 1;
+}
+#else
+static int read_from_bdev_sync(struct zram *zram, struct bio_vec *bvec,
+				unsigned long entry, struct bio *bio)
+{
+	WARN_ON(1);
+	return -EIO;
+}
+#endif
+
+static int read_from_bdev(struct zram *zram, struct bio_vec *bvec,
+			unsigned long entry, struct bio *parent, bool sync)
+{
+	if (sync)
+		return read_from_bdev_sync(zram, bvec, entry, parent);
+	else
+		return read_from_bdev_async(zram, bvec, entry, parent);
+}
+
+static int write_to_bdev(struct zram *zram, struct bio_vec *bvec,
+					u32 index, struct bio *parent,
+					unsigned long *pentry)
+{
+	struct bio *bio;
+	unsigned long entry;
+
+	bio = bio_alloc(GFP_ATOMIC, 1);
+	if (!bio)
+		return -ENOMEM;
+
+	entry = get_entry_bdev(zram);
+	if (!entry) {
+		bio_put(bio);
+		return -ENOSPC;
+	}
+
+	bio->bi_iter.bi_sector = entry * (PAGE_SIZE >> 9);
+	bio->bi_bdev = zram->bdev;
+	if (!bio_add_page(bio, bvec->bv_page, bvec->bv_len,
+					bvec->bv_offset)) {
+		bio_put(bio);
+		put_entry_bdev(zram, entry);
+		return -EIO;
+	}
+
+	if (!parent) {
+		bio->bi_opf = REQ_OP_WRITE | REQ_SYNC;
+		bio->bi_end_io = zram_page_end_io;
+	} else {
+		bio->bi_opf = parent->bi_opf;
+		bio_chain(bio, parent);
+	}
+
+	submit_bio(bio);
+	*pentry = entry;
+
+	return 0;
+}
+
+static void zram_wb_clear(struct zram *zram, u32 index)
+{
+	unsigned long entry;
+
+	zram_clear_flag(zram, index, ZRAM_WB);
+	entry = zram_get_element(zram, index);
+	zram_set_element(zram, index, 0);
+	put_entry_bdev(zram, entry);
+}
+
+#else
+static bool zram_wb_enabled(struct zram *zram) { return false; }
+static inline void reset_bdev(struct zram *zram) {};
+static int write_to_bdev(struct zram *zram, struct bio_vec *bvec,
+					u32 index, struct bio *parent,
+					unsigned long *pentry)
+
+{
+	return -EIO;
+}
+
+static int read_from_bdev(struct zram *zram, struct bio_vec *bvec,
+			unsigned long entry, struct bio *parent, bool sync)
+{
+	return -EIO;
+}
+static void zram_wb_clear(struct zram *zram, u32 index) {}
+#endif
+
+
 /*
  * We switched to per-cpu streams and this attr is not needed anymore.
  * However, we will keep it around for some time, because:
@@ -453,30 +796,6 @@ static bool zram_same_page_read(struct zram *zram, u32 index,
 	return false;
 }
 
-static bool zram_same_page_write(struct zram *zram, u32 index,
-					struct page *page)
-{
-	unsigned long element;
-	void *mem = kmap_atomic(page);
-
-	if (page_same_filled(mem, &element)) {
-		kunmap_atomic(mem);
-		/* Free memory associated with this sector now. */
-		zram_slot_lock(zram, index);
-		zram_free_page(zram, index);
-		zram_set_flag(zram, index, ZRAM_SAME);
-		zram_set_element(zram, index, element);
-		zram_slot_unlock(zram, index);
-
-		atomic64_inc(&zram->stats.same_pages);
-		atomic64_inc(&zram->stats.pages_stored);
-		return true;
-	}
-	kunmap_atomic(mem);
-
-	return false;
-}
-
 static void zram_meta_free(struct zram *zram, u64 disksize)
 {
 	size_t num_pages = disksize >> PAGE_SHIFT;
@@ -515,7 +834,13 @@ static bool zram_meta_alloc(struct zram *zram, u64 disksize)
  */
 static void zram_free_page(struct zram *zram, size_t index)
 {
-	unsigned long handle = zram_get_handle(zram, index);
+	unsigned long handle;
+
+	if (zram_wb_enabled(zram) && zram_test_flag(zram, index, ZRAM_WB)) {
+		zram_wb_clear(zram, index);
+		atomic64_dec(&zram->stats.pages_stored);
+		return;
+	}
 
 	/*
 	 * No memory is allocated for same element filled pages.
@@ -529,6 +854,7 @@ static void zram_free_page(struct zram *zram, size_t index)
 		return;
 	}
 
+	handle = zram_get_handle(zram, index);
 	if (!handle)
 		return;
 
@@ -542,13 +868,31 @@ static void zram_free_page(struct zram *zram, size_t index)
 	zram_set_obj_size(zram, index, 0);
 }
 
-static int zram_decompress_page(struct zram *zram, struct page *page, u32 index)
+static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index,
+				struct bio *bio, bool partial_io)
 {
 	int ret;
 	unsigned long handle;
 	unsigned int size;
 	void *src, *dst;
 
+	if (zram_wb_enabled(zram)) {
+		zram_slot_lock(zram, index);
+		if (zram_test_flag(zram, index, ZRAM_WB)) {
+			struct bio_vec bvec;
+
+			zram_slot_unlock(zram, index);
+
+			bvec.bv_page = page;
+			bvec.bv_len = PAGE_SIZE;
+			bvec.bv_offset = 0;
+			return read_from_bdev(zram, &bvec,
+					zram_get_element(zram, index),
+					bio, partial_io);
+		}
+		zram_slot_unlock(zram, index);
+	}
+
 	if (zram_same_page_read(zram, index, page, 0, PAGE_SIZE))
 		return 0;
 
@@ -581,7 +925,7 @@ static int zram_decompress_page(struct zram *zram, struct page *page, u32 index)
 }
 
 static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
-				u32 index, int offset)
+				u32 index, int offset, struct bio *bio)
 {
 	int ret;
 	struct page *page;
@@ -594,7 +938,7 @@ static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
 			return -ENOMEM;
 	}
 
-	ret = zram_decompress_page(zram, page, index);
+	ret = __zram_bvec_read(zram, page, index, bio, is_partial_io(bvec));
 	if (unlikely(ret))
 		goto out;
 
@@ -613,30 +957,57 @@ out:
 	return ret;
 }
 
-static int zram_compress(struct zram *zram, struct zcomp_strm **zstrm,
-			struct page *page,
-			unsigned long *out_handle, unsigned int *out_comp_len)
+static int __zram_bvec_write(struct zram *zram, struct bio_vec *bvec,
+				u32 index, struct bio *bio)
 {
-	int ret;
-	unsigned int comp_len;
-	void *src;
+	int ret = 0;
 	unsigned long alloced_pages;
 	unsigned long handle = 0;
+	unsigned int comp_len = 0;
+	void *src, *dst, *mem;
+	struct zcomp_strm *zstrm;
+	struct page *page = bvec->bv_page;
+	unsigned long element = 0;
+	enum zram_pageflags flags = 0;
+	bool allow_wb = true;
+
+	mem = kmap_atomic(page);
+	if (page_same_filled(mem, &element)) {
+		kunmap_atomic(mem);
+		/* Free memory associated with this sector now. */
+		flags = ZRAM_SAME;
+		atomic64_inc(&zram->stats.same_pages);
+		goto out;
+	}
+	kunmap_atomic(mem);
 
 compress_again:
+	zstrm = zcomp_stream_get(zram->comp);
 	src = kmap_atomic(page);
-	ret = zcomp_compress(*zstrm, src, &comp_len);
+	ret = zcomp_compress(zstrm, src, &comp_len);
 	kunmap_atomic(src);
 
 	if (unlikely(ret)) {
+		zcomp_stream_put(zram->comp);
 		pr_err("Compression failed! err=%d\n", ret);
-		if (handle)
-			zs_free(zram->mem_pool, handle);
+		zs_free(zram->mem_pool, handle);
 		return ret;
 	}
 
-	if (unlikely(comp_len > max_zpage_size))
+	if (unlikely(comp_len > max_zpage_size)) {
+		if (zram_wb_enabled(zram) && allow_wb) {
+			zcomp_stream_put(zram->comp);
+			ret = write_to_bdev(zram, bvec, index, bio, &element);
+			if (!ret) {
+				flags = ZRAM_WB;
+				ret = 1;
+				goto out;
+			}
+			allow_wb = false;
+			goto compress_again;
+		}
 		comp_len = PAGE_SIZE;
+	}
 
 	/*
 	 * handle allocation has 2 paths:
@@ -663,7 +1034,6 @@ compress_again:
 		handle = zs_malloc(zram->mem_pool, comp_len,
 				GFP_NOIO | __GFP_HIGHMEM |
 				__GFP_MOVABLE);
-		*zstrm = zcomp_stream_get(zram->comp);
 		if (handle)
 			goto compress_again;
 		return -ENOMEM;
@@ -673,34 +1043,11 @@ compress_again:
 	update_used_max(zram, alloced_pages);
 
 	if (zram->limit_pages && alloced_pages > zram->limit_pages) {
+		zcomp_stream_put(zram->comp);
 		zs_free(zram->mem_pool, handle);
 		return -ENOMEM;
 	}
 
-	*out_handle = handle;
-	*out_comp_len = comp_len;
-	return 0;
-}
-
-static int __zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index)
-{
-	int ret;
-	unsigned long handle;
-	unsigned int comp_len;
-	void *src, *dst;
-	struct zcomp_strm *zstrm;
-	struct page *page = bvec->bv_page;
-
-	if (zram_same_page_write(zram, index, page))
-		return 0;
-
-	zstrm = zcomp_stream_get(zram->comp);
-	ret = zram_compress(zram, &zstrm, page, &handle, &comp_len);
-	if (ret) {
-		zcomp_stream_put(zram->comp);
-		return ret;
-	}
-
 	dst = zs_map_object(zram->mem_pool, handle, ZS_MM_WO);
 
 	src = zstrm->buffer;
@@ -712,25 +1059,31 @@ static int __zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index)
 
 	zcomp_stream_put(zram->comp);
 	zs_unmap_object(zram->mem_pool, handle);
-
+	atomic64_add(comp_len, &zram->stats.compr_data_size);
+out:
 	/*
 	 * Free memory associated with this sector
 	 * before overwriting unused sectors.
 	 */
 	zram_slot_lock(zram, index);
 	zram_free_page(zram, index);
-	zram_set_handle(zram, index, handle);
-	zram_set_obj_size(zram, index, comp_len);
+
+	if (flags) {
+		zram_set_flag(zram, index, flags);
+		zram_set_element(zram, index, element);
+	}  else {
+		zram_set_handle(zram, index, handle);
+		zram_set_obj_size(zram, index, comp_len);
+	}
 	zram_slot_unlock(zram, index);
 
 	/* Update stats */
-	atomic64_add(comp_len, &zram->stats.compr_data_size);
 	atomic64_inc(&zram->stats.pages_stored);
-	return 0;
+	return ret;
 }
 
 static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec,
-				u32 index, int offset)
+				u32 index, int offset, struct bio *bio)
 {
 	int ret;
 	struct page *page = NULL;
@@ -748,7 +1101,7 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec,
 		if (!page)
 			return -ENOMEM;
 
-		ret = zram_decompress_page(zram, page, index);
+		ret = __zram_bvec_read(zram, page, index, bio, true);
 		if (ret)
 			goto out;
 
@@ -763,7 +1116,7 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec,
 		vec.bv_offset = 0;
 	}
 
-	ret = __zram_bvec_write(zram, &vec, index);
+	ret = __zram_bvec_write(zram, &vec, index, bio);
 out:
 	if (is_partial_io(bvec))
 		__free_page(page);
@@ -808,8 +1161,13 @@ static void zram_bio_discard(struct zram *zram, u32 index,
 	}
 }
 
+/*
+ * Returns errno if it has some problem. Otherwise return 0 or 1.
+ * Returns 0 if IO request was done synchronously
+ * Returns 1 if IO request was successfully submitted.
+ */
 static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index,
-			int offset, bool is_write)
+			int offset, bool is_write, struct bio *bio)
 {
 	unsigned long start_time = jiffies;
 	int rw_acct = is_write ? REQ_OP_WRITE : REQ_OP_READ;
@@ -820,16 +1178,16 @@ static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index,
 
 	if (!is_write) {
 		atomic64_inc(&zram->stats.num_reads);
-		ret = zram_bvec_read(zram, bvec, index, offset);
+		ret = zram_bvec_read(zram, bvec, index, offset, bio);
 		flush_dcache_page(bvec->bv_page);
 	} else {
 		atomic64_inc(&zram->stats.num_writes);
-		ret = zram_bvec_write(zram, bvec, index, offset);
+		ret = zram_bvec_write(zram, bvec, index, offset, bio);
 	}
 
 	generic_end_io_acct(rw_acct, &zram->disk->part0, start_time);
 
-	if (unlikely(ret)) {
+	if (unlikely(ret < 0)) {
 		if (!is_write)
 			atomic64_inc(&zram->stats.failed_reads);
 		else
@@ -868,7 +1226,7 @@ static void __zram_make_request(struct zram *zram, struct bio *bio)
 			bv.bv_len = min_t(unsigned int, PAGE_SIZE - offset,
 							unwritten);
 			if (zram_bvec_rw(zram, &bv, index, offset,
-					op_is_write(bio_op(bio))) < 0)
+					op_is_write(bio_op(bio)), bio) < 0)
 				goto out;
 
 			bv.bv_offset += bv.bv_len;
@@ -922,16 +1280,18 @@ static void zram_slot_free_notify(struct block_device *bdev,
 static int zram_rw_page(struct block_device *bdev, sector_t sector,
 		       struct page *page, bool is_write)
 {
-	int offset, err = -EIO;
+	int offset, ret;
 	u32 index;
 	struct zram *zram;
 	struct bio_vec bv;
 
+	if (PageTransHuge(page))
+		return -ENOTSUPP;
 	zram = bdev->bd_disk->private_data;
 
 	if (!valid_io_request(zram, sector, PAGE_SIZE)) {
 		atomic64_inc(&zram->stats.invalid_io);
-		err = -EINVAL;
+		ret = -EINVAL;
 		goto out;
 	}
 
@@ -942,7 +1302,7 @@ static int zram_rw_page(struct block_device *bdev, sector_t sector,
 	bv.bv_len = PAGE_SIZE;
 	bv.bv_offset = 0;
 
-	err = zram_bvec_rw(zram, &bv, index, offset, is_write);
+	ret = zram_bvec_rw(zram, &bv, index, offset, is_write, NULL);
 out:
 	/*
 	 * If I/O fails, just return error(ie, non-zero) without
@@ -952,9 +1312,20 @@ out:
 	 * bio->bi_end_io does things to handle the error
 	 * (e.g., SetPageError, set_page_dirty and extra works).
 	 */
-	if (err == 0)
+	if (unlikely(ret < 0))
+		return ret;
+
+	switch (ret) {
+	case 0:
 		page_endio(page, is_write, 0);
-	return err;
+		break;
+	case 1:
+		ret = 0;
+		break;
+	default:
+		WARN_ON(1);
+	}
+	return ret;
 }
 
 static void zram_reset_device(struct zram *zram)
@@ -983,6 +1354,7 @@ static void zram_reset_device(struct zram *zram)
 	zram_meta_free(zram, disksize);
 	memset(&zram->stats, 0, sizeof(zram->stats));
 	zcomp_destroy(comp);
+	reset_bdev(zram);
 }
 
 static ssize_t disksize_store(struct device *dev,
@@ -1108,6 +1480,9 @@ static DEVICE_ATTR_WO(mem_limit);
 static DEVICE_ATTR_WO(mem_used_max);
 static DEVICE_ATTR_RW(max_comp_streams);
 static DEVICE_ATTR_RW(comp_algorithm);
+#ifdef CONFIG_ZRAM_WRITEBACK
+static DEVICE_ATTR_RW(backing_dev);
+#endif
 
 static struct attribute *zram_disk_attrs[] = {
 	&dev_attr_disksize.attr,
@@ -1118,6 +1493,9 @@ static struct attribute *zram_disk_attrs[] = {
 	&dev_attr_mem_used_max.attr,
 	&dev_attr_max_comp_streams.attr,
 	&dev_attr_comp_algorithm.attr,
+#ifdef CONFIG_ZRAM_WRITEBACK
+	&dev_attr_backing_dev.attr,
+#endif
 	&dev_attr_io_stat.attr,
 	&dev_attr_mm_stat.attr,
 	&dev_attr_debug_stat.attr,

drivers/block/zram/zram_drv.h

@@ -60,9 +60,10 @@ static const size_t max_zpage_size = PAGE_SIZE / 4 * 3;
 
 /* Flags for zram pages (table[page_no].value) */
 enum zram_pageflags {
-	/* Page consists entirely of zeros */
+	/* Page consists the same element */
 	ZRAM_SAME = ZRAM_FLAG_SHIFT,
 	ZRAM_ACCESS,	/* page is now accessed */
+	ZRAM_WB,	/* page is stored on backing_device */
 
 	__NR_ZRAM_PAGEFLAGS,
 };
@@ -115,5 +116,13 @@ struct zram {
 	 * zram is claimed so open request will be failed
 	 */
 	bool claim; /* Protected by bdev->bd_mutex */
+#ifdef CONFIG_ZRAM_WRITEBACK
+	struct file *backing_dev;
+	struct block_device *bdev;
+	unsigned int old_block_size;
+	unsigned long *bitmap;
+	unsigned long nr_pages;
+	spinlock_t bitmap_lock;
+#endif
 };
 #endif

drivers/gpu/drm/i915/i915_debugfs.c

@@ -4308,10 +4308,10 @@ i915_drop_caches_set(void *data, u64 val)
 
 	fs_reclaim_acquire(GFP_KERNEL);
 	if (val & DROP_BOUND)
-		i915_gem_shrink(dev_priv, LONG_MAX, I915_SHRINK_BOUND);
+		i915_gem_shrink(dev_priv, LONG_MAX, NULL, I915_SHRINK_BOUND);
 
 	if (val & DROP_UNBOUND)
-		i915_gem_shrink(dev_priv, LONG_MAX, I915_SHRINK_UNBOUND);
+		i915_gem_shrink(dev_priv, LONG_MAX, NULL, I915_SHRINK_UNBOUND);
 
 	if (val & DROP_SHRINK_ALL)
 		i915_gem_shrink_all(dev_priv);

drivers/gpu/drm/i915/i915_drv.h

@@ -3742,6 +3742,7 @@ i915_gem_object_create_internal(struct drm_i915_private *dev_priv,
 /* i915_gem_shrinker.c */
 unsigned long i915_gem_shrink(struct drm_i915_private *dev_priv,
 			      unsigned long target,
+			      unsigned long *nr_scanned,
 			      unsigned flags);
 #define I915_SHRINK_PURGEABLE 0x1
 #define I915_SHRINK_UNBOUND 0x2

drivers/gpu/drm/i915/i915_gem.c

@@ -2354,7 +2354,7 @@ rebuild_st:
 				goto err_sg;
 			}
 
-			i915_gem_shrink(dev_priv, 2 * page_count, *s++);
+			i915_gem_shrink(dev_priv, 2 * page_count, NULL, *s++);
 			cond_resched();
 
 			/* We've tried hard to allocate the memory by reaping
@@ -5015,7 +5015,7 @@ int i915_gem_freeze_late(struct drm_i915_private *dev_priv)
 	 * the objects as well, see i915_gem_freeze()
 	 */
 
-	i915_gem_shrink(dev_priv, -1UL, I915_SHRINK_UNBOUND);
+	i915_gem_shrink(dev_priv, -1UL, NULL, I915_SHRINK_UNBOUND);
 	i915_gem_drain_freed_objects(dev_priv);
 
 	mutex_lock(&dev_priv->drm.struct_mutex);

drivers/gpu/drm/i915/i915_gem_gtt.c

@@ -2062,7 +2062,7 @@ int i915_gem_gtt_prepare_pages(struct drm_i915_gem_object *obj,
 		 */
 		GEM_BUG_ON(obj->mm.pages == pages);
 	} while (i915_gem_shrink(to_i915(obj->base.dev),
-				 obj->base.size >> PAGE_SHIFT,
+				 obj->base.size >> PAGE_SHIFT, NULL,
 				 I915_SHRINK_BOUND |
 				 I915_SHRINK_UNBOUND |
 				 I915_SHRINK_ACTIVE));

drivers/gpu/drm/i915/i915_gem_shrinker.c

@@ -136,6 +136,7 @@ static bool unsafe_drop_pages(struct drm_i915_gem_object *obj)
  * i915_gem_shrink - Shrink buffer object caches
  * @dev_priv: i915 device
  * @target: amount of memory to make available, in pages
+ * @nr_scanned: optional output for number of pages scanned (incremental)
  * @flags: control flags for selecting cache types
  *
  * This function is the main interface to the shrinker. It will try to release
@@ -158,7 +159,9 @@ static bool unsafe_drop_pages(struct drm_i915_gem_object *obj)
  */
 unsigned long
 i915_gem_shrink(struct drm_i915_private *dev_priv,
-		unsigned long target, unsigned flags)
+		unsigned long target,
+		unsigned long *nr_scanned,
+		unsigned flags)
 {
 	const struct {
 		struct list_head *list;
@@ -169,6 +172,7 @@ i915_gem_shrink(struct drm_i915_private *dev_priv,
 		{ NULL, 0 },
 	}, *phase;
 	unsigned long count = 0;
+	unsigned long scanned = 0;
 	bool unlock;
 
 	if (!shrinker_lock(dev_priv, &unlock))
@@ -249,6 +253,7 @@ i915_gem_shrink(struct drm_i915_private *dev_priv,
 					count += obj->base.size >> PAGE_SHIFT;
 				}
 				mutex_unlock(&obj->mm.lock);
+				scanned += obj->base.size >> PAGE_SHIFT;
 			}
 		}
 		list_splice_tail(&still_in_list, phase->list);
@@ -261,6 +266,8 @@ i915_gem_shrink(struct drm_i915_private *dev_priv,
 
 	shrinker_unlock(dev_priv, unlock);
 
+	if (nr_scanned)
+		*nr_scanned += scanned;
 	return count;
 }
 
@@ -283,7 +290,7 @@ unsigned long i915_gem_shrink_all(struct drm_i915_private *dev_priv)
 	unsigned long freed;
 
 	intel_runtime_pm_get(dev_priv);
-	freed = i915_gem_shrink(dev_priv, -1UL,
+	freed = i915_gem_shrink(dev_priv, -1UL, NULL,
 				I915_SHRINK_BOUND |
 				I915_SHRINK_UNBOUND |
 				I915_SHRINK_ACTIVE);
@@ -329,23 +336,28 @@ i915_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc)
 	unsigned long freed;
 	bool unlock;
 
+	sc->nr_scanned = 0;
+
 	if (!shrinker_lock(dev_priv, &unlock))
 		return SHRINK_STOP;
 
 	freed = i915_gem_shrink(dev_priv,
 				sc->nr_to_scan,
+				&sc->nr_scanned,
 				I915_SHRINK_BOUND |
 				I915_SHRINK_UNBOUND |
 				I915_SHRINK_PURGEABLE);
 	if (freed < sc->nr_to_scan)
 		freed += i915_gem_shrink(dev_priv,
-					 sc->nr_to_scan - freed,
+					 sc->nr_to_scan - sc->nr_scanned,
+					 &sc->nr_scanned,
 					 I915_SHRINK_BOUND |
 					 I915_SHRINK_UNBOUND);
 	if (freed < sc->nr_to_scan && current_is_kswapd()) {
 		intel_runtime_pm_get(dev_priv);
 		freed += i915_gem_shrink(dev_priv,
-					 sc->nr_to_scan - freed,
+					 sc->nr_to_scan - sc->nr_scanned,
+					 &sc->nr_scanned,
 					 I915_SHRINK_ACTIVE |
 					 I915_SHRINK_BOUND |
 					 I915_SHRINK_UNBOUND);
@@ -354,7 +366,7 @@ i915_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc)
 
 	shrinker_unlock(dev_priv, unlock);
 
-	return freed;
+	return sc->nr_scanned ? freed : SHRINK_STOP;
 }
 
 static bool
@@ -453,7 +465,7 @@ i915_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr
 		goto out;
 
 	intel_runtime_pm_get(dev_priv);
-	freed_pages += i915_gem_shrink(dev_priv, -1UL,
+	freed_pages += i915_gem_shrink(dev_priv, -1UL, NULL,
 				       I915_SHRINK_BOUND |
 				       I915_SHRINK_UNBOUND |
 				       I915_SHRINK_ACTIVE |

drivers/nvdimm/btt.c

@@ -1241,8 +1241,10 @@ static int btt_rw_page(struct block_device *bdev, sector_t sector,
 {
 	struct btt *btt = bdev->bd_disk->private_data;
 	int rc;
+	unsigned int len;
 
-	rc = btt_do_bvec(btt, NULL, page, PAGE_SIZE, 0, is_write, sector);
+	len = hpage_nr_pages(page) * PAGE_SIZE;
+	rc = btt_do_bvec(btt, NULL, page, len, 0, is_write, sector);
 	if (rc == 0)
 		page_endio(page, is_write, 0);
 

drivers/nvdimm/pmem.c

@@ -80,22 +80,40 @@ static blk_status_t pmem_clear_poison(struct pmem_device *pmem,
 static void write_pmem(void *pmem_addr, struct page *page,
 		unsigned int off, unsigned int len)
 {
-	void *mem = kmap_atomic(page);
-
-	memcpy_flushcache(pmem_addr, mem + off, len);
-	kunmap_atomic(mem);
+	unsigned int chunk;
+	void *mem;
+
+	while (len) {
+		mem = kmap_atomic(page);
+		chunk = min_t(unsigned int, len, PAGE_SIZE);
+		memcpy_flushcache(pmem_addr, mem + off, chunk);
+		kunmap_atomic(mem);
+		len -= chunk;
+		off = 0;
+		page++;
+		pmem_addr += PAGE_SIZE;
+	}
 }
 
 static blk_status_t read_pmem(struct page *page, unsigned int off,
 		void *pmem_addr, unsigned int len)
 {
+	unsigned int chunk;
 	int rc;
-	void *mem = kmap_atomic(page);
-
-	rc = memcpy_mcsafe(mem + off, pmem_addr, len);
-	kunmap_atomic(mem);
-	if (rc)
-		return BLK_STS_IOERR;
+	void *mem;
+
+	while (len) {
+		mem = kmap_atomic(page);
+		chunk = min_t(unsigned int, len, PAGE_SIZE);
+		rc = memcpy_mcsafe(mem + off, pmem_addr, chunk);
+		kunmap_atomic(mem);
+		if (rc)
+			return BLK_STS_IOERR;
+		len -= chunk;
+		off = 0;
+		page++;
+		pmem_addr += PAGE_SIZE;
+	}
 	return BLK_STS_OK;
 }
 
@@ -188,7 +206,8 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector,
 	struct pmem_device *pmem = bdev->bd_queue->queuedata;
 	blk_status_t rc;
 
-	rc = pmem_do_bvec(pmem, page, PAGE_SIZE, 0, is_write, sector);
+	rc = pmem_do_bvec(pmem, page, hpage_nr_pages(page) * PAGE_SIZE,
+			  0, is_write, sector);
 
 	/*
 	 * The ->rw_page interface is subtle and tricky.  The core

fs/9p/cache.c

@@ -151,34 +151,6 @@ fscache_checkaux v9fs_cache_inode_check_aux(void *cookie_netfs_data,
 	return FSCACHE_CHECKAUX_OKAY;
 }
 
-static void v9fs_cache_inode_now_uncached(void *cookie_netfs_data)
-{
-	struct v9fs_inode *v9inode = cookie_netfs_data;
-	struct pagevec pvec;
-	pgoff_t first;
-	int loop, nr_pages;
-
-	pagevec_init(&pvec, 0);
-	first = 0;
-
-	for (;;) {
-		nr_pages = pagevec_lookup(&pvec, v9inode->vfs_inode.i_mapping,
-					  first,
-					  PAGEVEC_SIZE - pagevec_count(&pvec));
-		if (!nr_pages)
-			break;
-
-		for (loop = 0; loop < nr_pages; loop++)
-			ClearPageFsCache(pvec.pages[loop]);
-
-		first = pvec.pages[nr_pages - 1]->index + 1;
-
-		pvec.nr = nr_pages;
-		pagevec_release(&pvec);
-		cond_resched();
-	}
-}
-
 const struct fscache_cookie_def v9fs_cache_inode_index_def = {
 	.name		= "9p.inode",
 	.type		= FSCACHE_COOKIE_TYPE_DATAFILE,
@@ -186,7 +158,6 @@ const struct fscache_cookie_def v9fs_cache_inode_index_def = {
 	.get_attr	= v9fs_cache_inode_get_attr,
 	.get_aux	= v9fs_cache_inode_get_aux,
 	.check_aux	= v9fs_cache_inode_check_aux,
-	.now_uncached	= v9fs_cache_inode_now_uncached,
 };
 
 void v9fs_cache_inode_get_cookie(struct inode *inode)

fs/afs/cache.c

@@ -39,7 +39,6 @@ static uint16_t afs_vnode_cache_get_aux(const void *cookie_netfs_data,
 static enum fscache_checkaux afs_vnode_cache_check_aux(void *cookie_netfs_data,
 						       const void *buffer,
 						       uint16_t buflen);
-static void afs_vnode_cache_now_uncached(void *cookie_netfs_data);
 
 struct fscache_netfs afs_cache_netfs = {
 	.name			= "afs",
@@ -75,7 +74,6 @@ struct fscache_cookie_def afs_vnode_cache_index_def = {
 	.get_attr		= afs_vnode_cache_get_attr,
 	.get_aux		= afs_vnode_cache_get_aux,
 	.check_aux		= afs_vnode_cache_check_aux,
-	.now_uncached		= afs_vnode_cache_now_uncached,
 };
 
 /*
@@ -359,44 +357,3 @@ static enum fscache_checkaux afs_vnode_cache_check_aux(void *cookie_netfs_data,
 	_leave(" = SUCCESS");
 	return FSCACHE_CHECKAUX_OKAY;
 }
-
-/*
- * indication the cookie is no longer uncached
- * - this function is called when the backing store currently caching a cookie
- *   is removed
- * - the netfs should use this to clean up any markers indicating cached pages
- * - this is mandatory for any object that may have data
- */
-static void afs_vnode_cache_now_uncached(void *cookie_netfs_data)
-{
-	struct afs_vnode *vnode = cookie_netfs_data;
-	struct pagevec pvec;
-	pgoff_t first;
-	int loop, nr_pages;
-
-	_enter("{%x,%x,%Lx}",
-	       vnode->fid.vnode, vnode->fid.unique, vnode->status.data_version);
-
-	pagevec_init(&pvec, 0);
-	first = 0;
-
-	for (;;) {
-		/* grab a bunch of pages to clean */
-		nr_pages = pagevec_lookup(&pvec, vnode->vfs_inode.i_mapping,
-					  first,
-					  PAGEVEC_SIZE - pagevec_count(&pvec));
-		if (!nr_pages)
-			break;
-
-		for (loop = 0; loop < nr_pages; loop++)
-			ClearPageFsCache(pvec.pages[loop]);
-
-		first = pvec.pages[nr_pages - 1]->index + 1;
-
-		pvec.nr = nr_pages;
-		pagevec_release(&pvec);
-		cond_resched();
-	}
-
-	_leave("");
-}

fs/buffer.c

@@ -1627,20 +1627,17 @@ void clean_bdev_aliases(struct block_device *bdev, sector_t block, sector_t len)
 	struct pagevec pvec;
 	pgoff_t index = block >> (PAGE_SHIFT - bd_inode->i_blkbits);
 	pgoff_t end;
-	int i;
+	int i, count;
 	struct buffer_head *bh;
 	struct buffer_head *head;
 
 	end = (block + len - 1) >> (PAGE_SHIFT - bd_inode->i_blkbits);
 	pagevec_init(&pvec, 0);
-	while (index <= end && pagevec_lookup(&pvec, bd_mapping, index,
-			min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) {
-		for (i = 0; i < pagevec_count(&pvec); i++) {
+	while (pagevec_lookup_range(&pvec, bd_mapping, &index, end)) {
+		count = pagevec_count(&pvec);
+		for (i = 0; i < count; i++) {
 			struct page *page = pvec.pages[i];
 
-			index = page->index;
-			if (index > end)
-				break;
 			if (!page_has_buffers(page))
 				continue;
 			/*
@@ -1670,7 +1667,9 @@ unlock_page:
 		}
 		pagevec_release(&pvec);
 		cond_resched();
-		index++;
+		/* End of range already reached? */
+		if (index > end || !index)
+			break;
 	}
 }
 EXPORT_SYMBOL(clean_bdev_aliases);
@@ -3549,10 +3548,10 @@ page_cache_seek_hole_data(struct inode *inode, loff_t offset, loff_t length,
 	pagevec_init(&pvec, 0);
 
 	do {
-		unsigned want, nr_pages, i;
+		unsigned nr_pages, i;
 
-		want = min_t(unsigned, end - index, PAGEVEC_SIZE);
-		nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index, want);
+		nr_pages = pagevec_lookup_range(&pvec, inode->i_mapping, &index,
+						end - 1);
 		if (nr_pages == 0)
 			break;
 
@@ -3573,10 +3572,6 @@ page_cache_seek_hole_data(struct inode *inode, loff_t offset, loff_t length,
 			    lastoff < page_offset(page))
 				goto check_range;
 
-			/* Searching done if the page index is out of range. */
-			if (page->index >= end)
-				goto not_found;
-
 			lock_page(page);
 			if (likely(page->mapping == inode->i_mapping) &&
 			    page_has_buffers(page)) {
@@ -3589,12 +3584,6 @@ page_cache_seek_hole_data(struct inode *inode, loff_t offset, loff_t length,
 			unlock_page(page);
 			lastoff = page_offset(page) + PAGE_SIZE;
 		}
-
-		/* Searching done if fewer pages returned than wanted. */
-		if (nr_pages < want)
-			break;
-
-		index = pvec.pages[i - 1]->index + 1;
 		pagevec_release(&pvec);
 	} while (index < end);
 

fs/ceph/cache.c

@@ -194,36 +194,6 @@ static enum fscache_checkaux ceph_fscache_inode_check_aux(
 	return FSCACHE_CHECKAUX_OKAY;
 }
 
-static void ceph_fscache_inode_now_uncached(void* cookie_netfs_data)
-{
-	struct ceph_inode_info* ci = cookie_netfs_data;
-	struct pagevec pvec;
-	pgoff_t first;
-	int loop, nr_pages;
-
-	pagevec_init(&pvec, 0);
-	first = 0;
-
-	dout("ceph inode 0x%p now uncached", ci);
-
-	while (1) {
-		nr_pages = pagevec_lookup(&pvec, ci->vfs_inode.i_mapping, first,
-					  PAGEVEC_SIZE - pagevec_count(&pvec));
-
-		if (!nr_pages)
-			break;
-
-		for (loop = 0; loop < nr_pages; loop++)
-			ClearPageFsCache(pvec.pages[loop]);
-
-		first = pvec.pages[nr_pages - 1]->index + 1;
-
-		pvec.nr = nr_pages;
-		pagevec_release(&pvec);
-		cond_resched();
-	}
-}
-
 static const struct fscache_cookie_def ceph_fscache_inode_object_def = {
 	.name		= "CEPH.inode",
 	.type		= FSCACHE_COOKIE_TYPE_DATAFILE,
@@ -231,7 +201,6 @@ static const struct fscache_cookie_def ceph_fscache_inode_object_def = {
 	.get_attr	= ceph_fscache_inode_get_attr,
 	.get_aux	= ceph_fscache_inode_get_aux,
 	.check_aux	= ceph_fscache_inode_check_aux,
-	.now_uncached	= ceph_fscache_inode_now_uncached,
 };
 
 void ceph_fscache_register_inode_cookie(struct inode *inode)

fs/cifs/cache.c

@@ -292,36 +292,6 @@ fscache_checkaux cifs_fscache_inode_check_aux(void *cookie_netfs_data,
 	return FSCACHE_CHECKAUX_OKAY;
 }
 
-static void cifs_fscache_inode_now_uncached(void *cookie_netfs_data)
-{
-	struct cifsInodeInfo *cifsi = cookie_netfs_data;
-	struct pagevec pvec;
-	pgoff_t first;
-	int loop, nr_pages;
-
-	pagevec_init(&pvec, 0);
-	first = 0;
-
-	cifs_dbg(FYI, "%s: cifs inode 0x%p now uncached\n", __func__, cifsi);
-
-	for (;;) {
-		nr_pages = pagevec_lookup(&pvec,
-					  cifsi->vfs_inode.i_mapping, first,
-					  PAGEVEC_SIZE - pagevec_count(&pvec));
-		if (!nr_pages)
-			break;
-
-		for (loop = 0; loop < nr_pages; loop++)
-			ClearPageFsCache(pvec.pages[loop]);
-
-		first = pvec.pages[nr_pages - 1]->index + 1;
-
-		pvec.nr = nr_pages;
-		pagevec_release(&pvec);
-		cond_resched();
-	}
-}
-
 const struct fscache_cookie_def cifs_fscache_inode_object_def = {
 	.name		= "CIFS.uniqueid",
 	.type		= FSCACHE_COOKIE_TYPE_DATAFILE,
@@ -329,5 +299,4 @@ const struct fscache_cookie_def cifs_fscache_inode_object_def = {
 	.get_attr	= cifs_fscache_inode_get_attr,
 	.get_aux	= cifs_fscache_inode_get_aux,
 	.check_aux	= cifs_fscache_inode_check_aux,
-	.now_uncached	= cifs_fscache_inode_now_uncached,
 };

fs/dax.c

@@ -42,6 +42,9 @@
 #define DAX_WAIT_TABLE_BITS 12
 #define DAX_WAIT_TABLE_ENTRIES (1 << DAX_WAIT_TABLE_BITS)
 
+/* The 'colour' (ie low bits) within a PMD of a page offset.  */
+#define PG_PMD_COLOUR	((PMD_SIZE >> PAGE_SHIFT) - 1)
+
 static wait_queue_head_t wait_table[DAX_WAIT_TABLE_ENTRIES];
 
 static int __init init_dax_wait_table(void)
@@ -54,6 +57,40 @@ static int __init init_dax_wait_table(void)
 }
 fs_initcall(init_dax_wait_table);
 
+/*
+ * We use lowest available bit in exceptional entry for locking, one bit for
+ * the entry size (PMD) and two more to tell us if the entry is a zero page or
+ * an empty entry that is just used for locking.  In total four special bits.
+ *
+ * If the PMD bit isn't set the entry has size PAGE_SIZE, and if the ZERO_PAGE
+ * and EMPTY bits aren't set the entry is a normal DAX entry with a filesystem
+ * block allocation.
+ */
+#define RADIX_DAX_SHIFT		(RADIX_TREE_EXCEPTIONAL_SHIFT + 4)
+#define RADIX_DAX_ENTRY_LOCK	(1 << RADIX_TREE_EXCEPTIONAL_SHIFT)
+#define RADIX_DAX_PMD		(1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 1))
+#define RADIX_DAX_ZERO_PAGE	(1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 2))
+#define RADIX_DAX_EMPTY		(1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 3))
+
+static unsigned long dax_radix_sector(void *entry)
+{
+	return (unsigned long)entry >> RADIX_DAX_SHIFT;
+}
+
+static void *dax_radix_locked_entry(sector_t sector, unsigned long flags)
+{
+	return (void *)(RADIX_TREE_EXCEPTIONAL_ENTRY | flags |
+			((unsigned long)sector << RADIX_DAX_SHIFT) |
+			RADIX_DAX_ENTRY_LOCK);
+}
+
+static unsigned int dax_radix_order(void *entry)
+{
+	if ((unsigned long)entry & RADIX_DAX_PMD)
+		return PMD_SHIFT - PAGE_SHIFT;
+	return 0;
+}
+
 static int dax_is_pmd_entry(void *entry)
 {
 	return (unsigned long)entry & RADIX_DAX_PMD;
@@ -66,7 +103,7 @@ static int dax_is_pte_entry(void *entry)
 
 static int dax_is_zero_entry(void *entry)
 {
-	return (unsigned long)entry & RADIX_DAX_HZP;
+	return (unsigned long)entry & RADIX_DAX_ZERO_PAGE;
 }
 
 static int dax_is_empty_entry(void *entry)
@@ -98,7 +135,7 @@ static wait_queue_head_t *dax_entry_waitqueue(struct address_space *mapping,
 	 * the range covered by the PMD map to the same bit lock.
 	 */
 	if (dax_is_pmd_entry(entry))
-		index &= ~((1UL << (PMD_SHIFT - PAGE_SHIFT)) - 1);
+		index &= ~PG_PMD_COLOUR;
 
 	key->mapping = mapping;
 	key->entry_start = index;
@@ -120,6 +157,31 @@ static int wake_exceptional_entry_func(wait_queue_entry_t *wait, unsigned int mo
 	return autoremove_wake_function(wait, mode, sync, NULL);
 }
 
+/*
+ * We do not necessarily hold the mapping->tree_lock when we call this
+ * function so it is possible that 'entry' is no longer a valid item in the
+ * radix tree.  This is okay because all we really need to do is to find the
+ * correct waitqueue where tasks might be waiting for that old 'entry' and
+ * wake them.
+ */
+static void dax_wake_mapping_entry_waiter(struct address_space *mapping,
+		pgoff_t index, void *entry, bool wake_all)
+{
+	struct exceptional_entry_key key;
+	wait_queue_head_t *wq;
+
+	wq = dax_entry_waitqueue(mapping, index, entry, &key);
+
+	/*
+	 * Checking for locked entry and prepare_to_wait_exclusive() happens
+	 * under mapping->tree_lock, ditto for entry handling in our callers.
+	 * So at this point all tasks that could have seen our entry locked
+	 * must be in the waitqueue and the following check will see them.
+	 */
+	if (waitqueue_active(wq))
+		__wake_up(wq, TASK_NORMAL, wake_all ? 0 : 1, &key);
+}
+
 /*
  * Check whether the given slot is locked. The function must be called with
  * mapping->tree_lock held
@@ -181,7 +243,8 @@ static void *get_unlocked_mapping_entry(struct address_space *mapping,
 	for (;;) {
 		entry = __radix_tree_lookup(&mapping->page_tree, index, NULL,
 					  &slot);
-		if (!entry || !radix_tree_exceptional_entry(entry) ||
+		if (!entry ||
+		    WARN_ON_ONCE(!radix_tree_exceptional_entry(entry)) ||
 		    !slot_locked(mapping, slot)) {
 			if (slotp)
 				*slotp = slot;
@@ -216,14 +279,9 @@ static void dax_unlock_mapping_entry(struct address_space *mapping,
 }
 
 static void put_locked_mapping_entry(struct address_space *mapping,
-				     pgoff_t index, void *entry)
+		pgoff_t index)
 {
-	if (!radix_tree_exceptional_entry(entry)) {
-		unlock_page(entry);
-		put_page(entry);
-	} else {
-		dax_unlock_mapping_entry(mapping, index);
-	}
+	dax_unlock_mapping_entry(mapping, index);
 }
 
 /*
@@ -233,7 +291,7 @@ static void put_locked_mapping_entry(struct address_space *mapping,
 static void put_unlocked_mapping_entry(struct address_space *mapping,
 				       pgoff_t index, void *entry)
 {
-	if (!radix_tree_exceptional_entry(entry))
+	if (!entry)
 		return;
 
 	/* We have to wake up next waiter for the radix tree entry lock */
@@ -241,15 +299,15 @@ static void put_unlocked_mapping_entry(struct address_space *mapping,
 }
 
 /*
- * Find radix tree entry at given index. If it points to a page, return with
- * the page locked. If it points to the exceptional entry, return with the
- * radix tree entry locked. If the radix tree doesn't contain given index,
- * create empty exceptional entry for the index and return with it locked.
+ * Find radix tree entry at given index. If it points to an exceptional entry,
+ * return it with the radix tree entry locked. If the radix tree doesn't
+ * contain given index, create an empty exceptional entry for the index and
+ * return with it locked.
  *
  * When requesting an entry with size RADIX_DAX_PMD, grab_mapping_entry() will
  * either return that locked entry or will return an error.  This error will
- * happen if there are any 4k entries (either zero pages or DAX entries)
- * within the 2MiB range that we are requesting.
+ * happen if there are any 4k entries within the 2MiB range that we are
+ * requesting.
  *
  * We always favor 4k entries over 2MiB entries. There isn't a flow where we
  * evict 4k entries in order to 'upgrade' them to a 2MiB entry.  A 2MiB
@@ -276,18 +334,21 @@ restart:
 	spin_lock_irq(&mapping->tree_lock);
 	entry = get_unlocked_mapping_entry(mapping, index, &slot);
 
+	if (WARN_ON_ONCE(entry && !radix_tree_exceptional_entry(entry))) {
+		entry = ERR_PTR(-EIO);
+		goto out_unlock;
+	}
+
 	if (entry) {
 		if (size_flag & RADIX_DAX_PMD) {
-			if (!radix_tree_exceptional_entry(entry) ||
-			    dax_is_pte_entry(entry)) {
+			if (dax_is_pte_entry(entry)) {
 				put_unlocked_mapping_entry(mapping, index,
 						entry);
 				entry = ERR_PTR(-EEXIST);
 				goto out_unlock;
 			}
 		} else { /* trying to grab a PTE entry */
-			if (radix_tree_exceptional_entry(entry) &&
-			    dax_is_pmd_entry(entry) &&
+			if (dax_is_pmd_entry(entry) &&
 			    (dax_is_zero_entry(entry) ||
 			     dax_is_empty_entry(entry))) {
 				pmd_downgrade = true;
@@ -321,7 +382,7 @@ restart:
 				mapping_gfp_mask(mapping) & ~__GFP_HIGHMEM);
 		if (err) {
 			if (pmd_downgrade)
-				put_locked_mapping_entry(mapping, index, entry);
+				put_locked_mapping_entry(mapping, index);
 			return ERR_PTR(err);
 		}
 		spin_lock_irq(&mapping->tree_lock);
@@ -371,52 +432,12 @@ restart:
 		spin_unlock_irq(&mapping->tree_lock);
 		return entry;
 	}
-	/* Normal page in radix tree? */
-	if (!radix_tree_exceptional_entry(entry)) {
-		struct page *page = entry;
-
-		get_page(page);
-		spin_unlock_irq(&mapping->tree_lock);
-		lock_page(page);
-		/* Page got truncated? Retry... */
-		if (unlikely(page->mapping != mapping)) {
-			unlock_page(page);
-			put_page(page);
-			goto restart;
-		}
-		return page;
-	}
 	entry = lock_slot(mapping, slot);
  out_unlock:
 	spin_unlock_irq(&mapping->tree_lock);
 	return entry;
 }
 
-/*
- * We do not necessarily hold the mapping->tree_lock when we call this
- * function so it is possible that 'entry' is no longer a valid item in the
- * radix tree.  This is okay because all we really need to do is to find the
- * correct waitqueue where tasks might be waiting for that old 'entry' and
- * wake them.
- */
-void dax_wake_mapping_entry_waiter(struct address_space *mapping,
-		pgoff_t index, void *entry, bool wake_all)
-{
-	struct exceptional_entry_key key;
-	wait_queue_head_t *wq;
-
-	wq = dax_entry_waitqueue(mapping, index, entry, &key);
-
-	/*
-	 * Checking for locked entry and prepare_to_wait_exclusive() happens
-	 * under mapping->tree_lock, ditto for entry handling in our callers.
-	 * So at this point all tasks that could have seen our entry locked
-	 * must be in the waitqueue and the following check will see them.
-	 */
-	if (waitqueue_active(wq))
-		__wake_up(wq, TASK_NORMAL, wake_all ? 0 : 1, &key);
-}
-
 static int __dax_invalidate_mapping_entry(struct address_space *mapping,
 					  pgoff_t index, bool trunc)
 {
@@ -426,7 +447,7 @@ static int __dax_invalidate_mapping_entry(struct address_space *mapping,
 
 	spin_lock_irq(&mapping->tree_lock);
 	entry = get_unlocked_mapping_entry(mapping, index, NULL);
-	if (!entry || !radix_tree_exceptional_entry(entry))
+	if (!entry || WARN_ON_ONCE(!radix_tree_exceptional_entry(entry)))
 		goto out;
 	if (!trunc &&
 	    (radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_DIRTY) ||
@@ -468,50 +489,6 @@ int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
 	return __dax_invalidate_mapping_entry(mapping, index, false);
 }
 
-/*
- * The user has performed a load from a hole in the file.  Allocating
- * a new page in the file would cause excessive storage usage for
- * workloads with sparse files.  We allocate a page cache page instead.
- * We'll kick it out of the page cache if it's ever written to,
- * otherwise it will simply fall out of the page cache under memory
- * pressure without ever having been dirtied.
- */
-static int dax_load_hole(struct address_space *mapping, void **entry,
-			 struct vm_fault *vmf)
-{
-	struct inode *inode = mapping->host;
-	struct page *page;
-	int ret;
-
-	/* Hole page already exists? Return it...  */
-	if (!radix_tree_exceptional_entry(*entry)) {
-		page = *entry;
-		goto finish_fault;
-	}
-
-	/* This will replace locked radix tree entry with a hole page */
-	page = find_or_create_page(mapping, vmf->pgoff,
-				   vmf->gfp_mask | __GFP_ZERO);
-	if (!page) {
-		ret = VM_FAULT_OOM;
-		goto out;
-	}
-
-finish_fault:
-	vmf->page = page;
-	ret = finish_fault(vmf);
-	vmf->page = NULL;
-	*entry = page;
-	if (!ret) {
-		/* Grab reference for PTE that is now referencing the page */
-		get_page(page);
-		ret = VM_FAULT_NOPAGE;
-	}
-out:
-	trace_dax_load_hole(inode, vmf, ret);
-	return ret;
-}
-
 static int copy_user_dax(struct block_device *bdev, struct dax_device *dax_dev,
 		sector_t sector, size_t size, struct page *to,
 		unsigned long vaddr)
@@ -552,47 +529,27 @@ static void *dax_insert_mapping_entry(struct address_space *mapping,
 				      unsigned long flags)
 {
 	struct radix_tree_root *page_tree = &mapping->page_tree;
-	int error = 0;
-	bool hole_fill = false;
 	void *new_entry;
 	pgoff_t index = vmf->pgoff;
 
 	if (vmf->flags & FAULT_FLAG_WRITE)
 		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
 
-	/* Replacing hole page with block mapping? */
-	if (!radix_tree_exceptional_entry(entry)) {
-		hole_fill = true;
-		/*
-		 * Unmap the page now before we remove it from page cache below.
-		 * The page is locked so it cannot be faulted in again.
-		 */
-		unmap_mapping_range(mapping, vmf->pgoff << PAGE_SHIFT,
-				    PAGE_SIZE, 0);
-		error = radix_tree_preload(vmf->gfp_mask & ~__GFP_HIGHMEM);
-		if (error)
-			return ERR_PTR(error);
-	} else if (dax_is_zero_entry(entry) && !(flags & RADIX_DAX_HZP)) {
-		/* replacing huge zero page with PMD block mapping */
-		unmap_mapping_range(mapping,
-			(vmf->pgoff << PAGE_SHIFT) & PMD_MASK, PMD_SIZE, 0);
+	if (dax_is_zero_entry(entry) && !(flags & RADIX_DAX_ZERO_PAGE)) {
+		/* we are replacing a zero page with block mapping */
+		if (dax_is_pmd_entry(entry))
+			unmap_mapping_range(mapping,
+					(vmf->pgoff << PAGE_SHIFT) & PMD_MASK,
+					PMD_SIZE, 0);
+		else /* pte entry */
+			unmap_mapping_range(mapping, vmf->pgoff << PAGE_SHIFT,
+					PAGE_SIZE, 0);
 	}
 
 	spin_lock_irq(&mapping->tree_lock);
 	new_entry = dax_radix_locked_entry(sector, flags);
 
-	if (hole_fill) {
-		__delete_from_page_cache(entry, NULL);
-		/* Drop pagecache reference */
-		put_page(entry);
-		error = __radix_tree_insert(page_tree, index,
-				dax_radix_order(new_entry), new_entry);
-		if (error) {
-			new_entry = ERR_PTR(error);
-			goto unlock;
-		}
-		mapping->nrexceptional++;
-	} else if (dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) {
+	if (dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) {
 		/*
 		 * Only swap our new entry into the radix tree if the current
 		 * entry is a zero page or an empty entry.  If a normal PTE or
@@ -609,23 +566,14 @@ static void *dax_insert_mapping_entry(struct address_space *mapping,
 		WARN_ON_ONCE(ret != entry);
 		__radix_tree_replace(page_tree, node, slot,
 				     new_entry, NULL, NULL);
+		entry = new_entry;
 	}
+
 	if (vmf->flags & FAULT_FLAG_WRITE)
 		radix_tree_tag_set(page_tree, index, PAGECACHE_TAG_DIRTY);
- unlock:
+
 	spin_unlock_irq(&mapping->tree_lock);
-	if (hole_fill) {
-		radix_tree_preload_end();
-		/*
-		 * We don't need hole page anymore, it has been replaced with
-		 * locked radix tree entry now.
-		 */
-		if (mapping->a_ops->freepage)
-			mapping->a_ops->freepage(entry);
-		unlock_page(entry);
-		put_page(entry);
-	}
-	return new_entry;
+	return entry;
 }
 
 static inline unsigned long
@@ -727,7 +675,7 @@ static int dax_writeback_one(struct block_device *bdev,
 	spin_lock_irq(&mapping->tree_lock);
 	entry2 = get_unlocked_mapping_entry(mapping, index, &slot);
 	/* Entry got punched out / reallocated? */
-	if (!entry2 || !radix_tree_exceptional_entry(entry2))
+	if (!entry2 || WARN_ON_ONCE(!radix_tree_exceptional_entry(entry2)))
 		goto put_unlocked;
 	/*
 	 * Entry got reallocated elsewhere? No need to writeback. We have to
@@ -799,7 +747,7 @@ static int dax_writeback_one(struct block_device *bdev,
 	trace_dax_writeback_one(mapping->host, index, size >> PAGE_SHIFT);
  dax_unlock:
 	dax_read_unlock(id);
-	put_locked_mapping_entry(mapping, index, entry);
+	put_locked_mapping_entry(mapping, index);
 	return ret;
 
  put_unlocked:
@@ -874,11 +822,10 @@ EXPORT_SYMBOL_GPL(dax_writeback_mapping_range);
 
 static int dax_insert_mapping(struct address_space *mapping,
 		struct block_device *bdev, struct dax_device *dax_dev,
-		sector_t sector, size_t size, void **entryp,
+		sector_t sector, size_t size, void *entry,
 		struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	unsigned long vaddr = vmf->address;
-	void *entry = *entryp;
 	void *ret, *kaddr;
 	pgoff_t pgoff;
 	int id, rc;
@@ -899,47 +846,48 @@ static int dax_insert_mapping(struct address_space *mapping,
 	ret = dax_insert_mapping_entry(mapping, vmf, entry, sector, 0);
 	if (IS_ERR(ret))
 		return PTR_ERR(ret);
-	*entryp = ret;
 
 	trace_dax_insert_mapping(mapping->host, vmf, ret);
-	return vm_insert_mixed(vma, vaddr, pfn);
+	if (vmf->flags & FAULT_FLAG_WRITE)
+		return vm_insert_mixed_mkwrite(vma, vaddr, pfn);
+	else
+		return vm_insert_mixed(vma, vaddr, pfn);
 }
 
-/**
- * dax_pfn_mkwrite - handle first write to DAX page
- * @vmf: The description of the fault
+/*
+ * The user has performed a load from a hole in the file.  Allocating a new
+ * page in the file would cause excessive storage usage for workloads with
+ * sparse files.  Instead we insert a read-only mapping of the 4k zero page.
+ * If this page is ever written to we will re-fault and change the mapping to
+ * point to real DAX storage instead.
  */
-int dax_pfn_mkwrite(struct vm_fault *vmf)
+static int dax_load_hole(struct address_space *mapping, void *entry,
+			 struct vm_fault *vmf)
 {
-	struct file *file = vmf->vma->vm_file;
-	struct address_space *mapping = file->f_mapping;
 	struct inode *inode = mapping->host;
-	void *entry, **slot;
-	pgoff_t index = vmf->pgoff;
+	unsigned long vaddr = vmf->address;
+	int ret = VM_FAULT_NOPAGE;
+	struct page *zero_page;
+	void *entry2;
 
-	spin_lock_irq(&mapping->tree_lock);
-	entry = get_unlocked_mapping_entry(mapping, index, &slot);
-	if (!entry || !radix_tree_exceptional_entry(entry)) {
-		if (entry)
-			put_unlocked_mapping_entry(mapping, index, entry);
-		spin_unlock_irq(&mapping->tree_lock);
-		trace_dax_pfn_mkwrite_no_entry(inode, vmf, VM_FAULT_NOPAGE);
-		return VM_FAULT_NOPAGE;
+	zero_page = ZERO_PAGE(0);
+	if (unlikely(!zero_page)) {
+		ret = VM_FAULT_OOM;
+		goto out;
 	}
-	radix_tree_tag_set(&mapping->page_tree, index, PAGECACHE_TAG_DIRTY);
-	entry = lock_slot(mapping, slot);
-	spin_unlock_irq(&mapping->tree_lock);
-	/*
-	 * If we race with somebody updating the PTE and finish_mkwrite_fault()
-	 * fails, we don't care. We need to return VM_FAULT_NOPAGE and retry
-	 * the fault in either case.
-	 */
-	finish_mkwrite_fault(vmf);
-	put_locked_mapping_entry(mapping, index, entry);
-	trace_dax_pfn_mkwrite(inode, vmf, VM_FAULT_NOPAGE);
-	return VM_FAULT_NOPAGE;
+
+	entry2 = dax_insert_mapping_entry(mapping, vmf, entry, 0,
+			RADIX_DAX_ZERO_PAGE);
+	if (IS_ERR(entry2)) {
+		ret = VM_FAULT_SIGBUS;
+		goto out;
+	}
+
+	vm_insert_mixed(vmf->vma, vaddr, page_to_pfn_t(zero_page));
+out:
+	trace_dax_load_hole(inode, vmf, ret);
+	return ret;
 }
-EXPORT_SYMBOL_GPL(dax_pfn_mkwrite);
 
 static bool dax_range_is_aligned(struct block_device *bdev,
 				 unsigned int offset, unsigned int length)
@@ -1059,6 +1007,11 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 		if (map_len > end - pos)
 			map_len = end - pos;
 
+		/*
+		 * The userspace address for the memory copy has already been
+		 * validated via access_ok() in either vfs_read() or
+		 * vfs_write(), depending on which operation we are doing.
+		 */
 		if (iov_iter_rw(iter) == WRITE)
 			map_len = dax_copy_from_iter(dax_dev, pgoff, kaddr,
 					map_len, iter);
@@ -1223,7 +1176,7 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf,
 			major = VM_FAULT_MAJOR;
 		}
 		error = dax_insert_mapping(mapping, iomap.bdev, iomap.dax_dev,
-				sector, PAGE_SIZE, &entry, vmf->vma, vmf);
+				sector, PAGE_SIZE, entry, vmf->vma, vmf);
 		/* -EBUSY is fine, somebody else faulted on the same PTE */
 		if (error == -EBUSY)
 			error = 0;
@@ -1231,7 +1184,7 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf,
 	case IOMAP_UNWRITTEN:
 	case IOMAP_HOLE:
 		if (!(vmf->flags & FAULT_FLAG_WRITE)) {
-			vmf_ret = dax_load_hole(mapping, &entry, vmf);
+			vmf_ret = dax_load_hole(mapping, entry, vmf);
 			goto finish_iomap;
 		}
 		/*FALLTHRU*/
@@ -1258,21 +1211,15 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf,
 		ops->iomap_end(inode, pos, PAGE_SIZE, copied, flags, &iomap);
 	}
  unlock_entry:
-	put_locked_mapping_entry(mapping, vmf->pgoff, entry);
+	put_locked_mapping_entry(mapping, vmf->pgoff);
  out:
 	trace_dax_pte_fault_done(inode, vmf, vmf_ret);
 	return vmf_ret;
 }
 
 #ifdef CONFIG_FS_DAX_PMD
-/*
- * The 'colour' (ie low bits) within a PMD of a page offset.  This comes up
- * more often than one might expect in the below functions.
- */
-#define PG_PMD_COLOUR	((PMD_SIZE >> PAGE_SHIFT) - 1)
-
 static int dax_pmd_insert_mapping(struct vm_fault *vmf, struct iomap *iomap,
-		loff_t pos, void **entryp)
+		loff_t pos, void *entry)
 {
 	struct address_space *mapping = vmf->vma->vm_file->f_mapping;
 	const sector_t sector = dax_iomap_sector(iomap, pos);
@@ -1283,7 +1230,7 @@ static int dax_pmd_insert_mapping(struct vm_fault *vmf, struct iomap *iomap,
 	void *ret = NULL, *kaddr;
 	long length = 0;
 	pgoff_t pgoff;
-	pfn_t pfn;
+	pfn_t pfn = {};
 	int id;
 
 	if (bdev_dax_pgoff(bdev, sector, size, &pgoff) != 0)
@@ -1303,11 +1250,10 @@ static int dax_pmd_insert_mapping(struct vm_fault *vmf, struct iomap *iomap,
 		goto unlock_fallback;
 	dax_read_unlock(id);
 
-	ret = dax_insert_mapping_entry(mapping, vmf, *entryp, sector,
+	ret = dax_insert_mapping_entry(mapping, vmf, entry, sector,
 			RADIX_DAX_PMD);
 	if (IS_ERR(ret))
 		goto fallback;
-	*entryp = ret;
 
 	trace_dax_pmd_insert_mapping(inode, vmf, length, pfn, ret);
 	return vmf_insert_pfn_pmd(vmf->vma, vmf->address, vmf->pmd,
@@ -1321,7 +1267,7 @@ fallback:
 }
 
 static int dax_pmd_load_hole(struct vm_fault *vmf, struct iomap *iomap,
-		void **entryp)
+		void *entry)
 {
 	struct address_space *mapping = vmf->vma->vm_file->f_mapping;
 	unsigned long pmd_addr = vmf->address & PMD_MASK;
@@ -1336,11 +1282,10 @@ static int dax_pmd_load_hole(struct vm_fault *vmf, struct iomap *iomap,
 	if (unlikely(!zero_page))
 		goto fallback;
 
-	ret = dax_insert_mapping_entry(mapping, vmf, *entryp, 0,
-			RADIX_DAX_PMD | RADIX_DAX_HZP);
+	ret = dax_insert_mapping_entry(mapping, vmf, entry, 0,
+			RADIX_DAX_PMD | RADIX_DAX_ZERO_PAGE);
 	if (IS_ERR(ret))
 		goto fallback;
-	*entryp = ret;
 
 	ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd);
 	if (!pmd_none(*(vmf->pmd))) {
@@ -1416,10 +1361,10 @@ static int dax_iomap_pmd_fault(struct vm_fault *vmf,
 		goto fallback;
 
 	/*
-	 * grab_mapping_entry() will make sure we get a 2M empty entry, a DAX
-	 * PMD or a HZP entry.  If it can't (because a 4k page is already in
-	 * the tree, for instance), it will return -EEXIST and we just fall
-	 * back to 4k entries.
+	 * grab_mapping_entry() will make sure we get a 2MiB empty entry, a
+	 * 2MiB zero page entry or a DAX PMD.  If it can't (because a 4k page
+	 * is already in the tree, for instance), it will return -EEXIST and
+	 * we just fall back to 4k entries.
 	 */
 	entry = grab_mapping_entry(mapping, pgoff, RADIX_DAX_PMD);
 	if (IS_ERR(entry))
@@ -1452,13 +1397,13 @@ static int dax_iomap_pmd_fault(struct vm_fault *vmf,
 
 	switch (iomap.type) {
 	case IOMAP_MAPPED:
-		result = dax_pmd_insert_mapping(vmf, &iomap, pos, &entry);
+		result = dax_pmd_insert_mapping(vmf, &iomap, pos, entry);
 		break;
 	case IOMAP_UNWRITTEN:
 	case IOMAP_HOLE:
 		if (WARN_ON_ONCE(write))
 			break;
-		result = dax_pmd_load_hole(vmf, &iomap, &entry);
+		result = dax_pmd_load_hole(vmf, &iomap, entry);
 		break;
 	default:
 		WARN_ON_ONCE(1);
@@ -1481,7 +1426,7 @@ static int dax_iomap_pmd_fault(struct vm_fault *vmf,
 				&iomap);
 	}
  unlock_entry:
-	put_locked_mapping_entry(mapping, pgoff, entry);
+	put_locked_mapping_entry(mapping, pgoff);
  fallback:
 	if (result == VM_FAULT_FALLBACK) {
 		split_huge_pmd(vma, vmf->pmd, vmf->address);

fs/ext2/file.c

@@ -107,29 +107,6 @@ static int ext2_dax_fault(struct vm_fault *vmf)
 	return ret;
 }
 
-static int ext2_dax_pfn_mkwrite(struct vm_fault *vmf)
-{
-	struct inode *inode = file_inode(vmf->vma->vm_file);
-	struct ext2_inode_info *ei = EXT2_I(inode);
-	loff_t size;
-	int ret;
-
-	sb_start_pagefault(inode->i_sb);
-	file_update_time(vmf->vma->vm_file);
-	down_read(&ei->dax_sem);
-
-	/* check that the faulting page hasn't raced with truncate */
-	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	if (vmf->pgoff >= size)
-		ret = VM_FAULT_SIGBUS;
-	else
-		ret = dax_pfn_mkwrite(vmf);
-
-	up_read(&ei->dax_sem);
-	sb_end_pagefault(inode->i_sb);
-	return ret;
-}
-
 static const struct vm_operations_struct ext2_dax_vm_ops = {
 	.fault		= ext2_dax_fault,
 	/*
@@ -138,7 +115,7 @@ static const struct vm_operations_struct ext2_dax_vm_ops = {
 	 * will always fail and fail back to regular faults.
 	 */
 	.page_mkwrite	= ext2_dax_fault,
-	.pfn_mkwrite	= ext2_dax_pfn_mkwrite,
+	.pfn_mkwrite	= ext2_dax_fault,
 };
 
 static int ext2_file_mmap(struct file *file, struct vm_area_struct *vma)

fs/ext4/file.c

@@ -324,41 +324,11 @@ static int ext4_dax_fault(struct vm_fault *vmf)
 	return ext4_dax_huge_fault(vmf, PE_SIZE_PTE);
 }
 
-/*
- * Handle write fault for VM_MIXEDMAP mappings. Similarly to ext4_dax_fault()
- * handler we check for races agaist truncate. Note that since we cycle through
- * i_mmap_sem, we are sure that also any hole punching that began before we
- * were called is finished by now and so if it included part of the file we
- * are working on, our pte will get unmapped and the check for pte_same() in
- * wp_pfn_shared() fails. Thus fault gets retried and things work out as
- * desired.
- */
-static int ext4_dax_pfn_mkwrite(struct vm_fault *vmf)
-{
-	struct inode *inode = file_inode(vmf->vma->vm_file);
-	struct super_block *sb = inode->i_sb;
-	loff_t size;
-	int ret;
-
-	sb_start_pagefault(sb);
-	file_update_time(vmf->vma->vm_file);
-	down_read(&EXT4_I(inode)->i_mmap_sem);
-	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	if (vmf->pgoff >= size)
-		ret = VM_FAULT_SIGBUS;
-	else
-		ret = dax_pfn_mkwrite(vmf);
-	up_read(&EXT4_I(inode)->i_mmap_sem);
-	sb_end_pagefault(sb);
-
-	return ret;
-}
-
 static const struct vm_operations_struct ext4_dax_vm_ops = {
 	.fault		= ext4_dax_fault,
 	.huge_fault	= ext4_dax_huge_fault,
 	.page_mkwrite	= ext4_dax_fault,
-	.pfn_mkwrite	= ext4_dax_pfn_mkwrite,
+	.pfn_mkwrite	= ext4_dax_fault,
 };
 #else
 #define ext4_dax_vm_ops	ext4_file_vm_ops
@@ -507,12 +477,11 @@ static int ext4_find_unwritten_pgoff(struct inode *inode,
 
 	pagevec_init(&pvec, 0);
 	do {
-		int i, num;
+		int i;
 		unsigned long nr_pages;
 
-		num = min_t(pgoff_t, end - index, PAGEVEC_SIZE - 1) + 1;
-		nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index,
-					  (pgoff_t)num);
+		nr_pages = pagevec_lookup_range(&pvec, inode->i_mapping,
+					&index, end);
 		if (nr_pages == 0)
 			break;
 
@@ -531,9 +500,6 @@ static int ext4_find_unwritten_pgoff(struct inode *inode,
 				goto out;
 			}
 
-			if (page->index > end)
-				goto out;
-
 			lock_page(page);
 
 			if (unlikely(page->mapping != inode->i_mapping)) {
@@ -576,14 +542,10 @@ next:
 			unlock_page(page);
 		}
 
-		/* The no. of pages is less than our desired, we are done. */
-		if (nr_pages < num)
-			break;
-
-		index = pvec.pages[i - 1]->index + 1;
 		pagevec_release(&pvec);
 	} while (index <= end);
 
+	/* There are no pages upto endoff - that would be a hole in there. */
 	if (whence == SEEK_HOLE && lastoff < endoff) {
 		found = 1;
 		*offset = lastoff;

fs/ext4/inode.c

@@ -1720,13 +1720,12 @@ static void mpage_release_unused_pages(struct mpage_da_data *mpd,
 
 	pagevec_init(&pvec, 0);
 	while (index <= end) {
-		nr_pages = pagevec_lookup(&pvec, mapping, index, PAGEVEC_SIZE);
+		nr_pages = pagevec_lookup_range(&pvec, mapping, &index, end);
 		if (nr_pages == 0)
 			break;
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
-			if (page->index > end)
-				break;
+
 			BUG_ON(!PageLocked(page));
 			BUG_ON(PageWriteback(page));
 			if (invalidate) {
@@ -1737,7 +1736,6 @@ static void mpage_release_unused_pages(struct mpage_da_data *mpd,
 			}
 			unlock_page(page);
 		}
-		index = pvec.pages[nr_pages - 1]->index + 1;
 		pagevec_release(&pvec);
 	}
 }
@@ -2348,17 +2346,13 @@ static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd)
 
 	pagevec_init(&pvec, 0);
 	while (start <= end) {
-		nr_pages = pagevec_lookup(&pvec, inode->i_mapping, start,
-					  PAGEVEC_SIZE);
+		nr_pages = pagevec_lookup_range(&pvec, inode->i_mapping,
+						&start, end);
 		if (nr_pages == 0)
 			break;
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
 
-			if (page->index > end)
-				break;
-			/* Up to 'end' pages must be contiguous */
-			BUG_ON(page->index != start);
 			bh = head = page_buffers(page);
 			do {
 				if (lblk < mpd->map.m_lblk)
@@ -2403,7 +2397,6 @@ static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd)
 				pagevec_release(&pvec);
 				return err;
 			}
-			start++;
 		}
 		pagevec_release(&pvec);
 	}

fs/fscache/page.c

@@ -1178,11 +1178,10 @@ void __fscache_uncache_all_inode_pages(struct fscache_cookie *cookie,
 	pagevec_init(&pvec, 0);
 	next = 0;
 	do {
-		if (!pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE))
+		if (!pagevec_lookup(&pvec, mapping, &next))
 			break;
 		for (i = 0; i < pagevec_count(&pvec); i++) {
 			struct page *page = pvec.pages[i];
-			next = page->index;
 			if (PageFsCache(page)) {
 				__fscache_wait_on_page_write(cookie, page);
 				__fscache_uncache_page(cookie, page);
@@ -1190,7 +1189,7 @@ void __fscache_uncache_all_inode_pages(struct fscache_cookie *cookie,
 		}
 		pagevec_release(&pvec);
 		cond_resched();
-	} while (++next);
+	} while (next);
 
 	_leave("");
 }

fs/hugetlbfs/inode.c

@@ -401,9 +401,8 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
 	const pgoff_t end = lend >> huge_page_shift(h);
 	struct vm_area_struct pseudo_vma;
 	struct pagevec pvec;
-	pgoff_t next;
+	pgoff_t next, index;
 	int i, freed = 0;
-	long lookup_nr = PAGEVEC_SIZE;
 	bool truncate_op = (lend == LLONG_MAX);
 
 	memset(&pseudo_vma, 0, sizeof(struct vm_area_struct));
@@ -411,34 +410,20 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
 	pagevec_init(&pvec, 0);
 	next = start;
 	while (next < end) {
-		/*
-		 * Don't grab more pages than the number left in the range.
-		 */
-		if (end - next < lookup_nr)
-			lookup_nr = end - next;
-
 		/*
 		 * When no more pages are found, we are done.
 		 */
-		if (!pagevec_lookup(&pvec, mapping, next, lookup_nr))
+		if (!pagevec_lookup_range(&pvec, mapping, &next, end - 1))
 			break;
 
 		for (i = 0; i < pagevec_count(&pvec); ++i) {
 			struct page *page = pvec.pages[i];
 			u32 hash;
 
-			/*
-			 * The page (index) could be beyond end.  This is
-			 * only possible in the punch hole case as end is
-			 * max page offset in the truncate case.
-			 */
-			next = page->index;
-			if (next >= end)
-				break;
-
+			index = page->index;
 			hash = hugetlb_fault_mutex_hash(h, current->mm,
 							&pseudo_vma,
-							mapping, next, 0);
+							mapping, index, 0);
 			mutex_lock(&hugetlb_fault_mutex_table[hash]);
 
 			/*
@@ -455,8 +440,8 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
 
 				i_mmap_lock_write(mapping);
 				hugetlb_vmdelete_list(&mapping->i_mmap,
-					next * pages_per_huge_page(h),
-					(next + 1) * pages_per_huge_page(h));
+					index * pages_per_huge_page(h),
+					(index + 1) * pages_per_huge_page(h));
 				i_mmap_unlock_write(mapping);
 			}
 
@@ -475,14 +460,13 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
 			freed++;
 			if (!truncate_op) {
 				if (unlikely(hugetlb_unreserve_pages(inode,
-							next, next + 1, 1)))
+							index, index + 1, 1)))
 					hugetlb_fix_reserve_counts(inode);
 			}
 
 			unlock_page(page);
 			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 		}
-		++next;
 		huge_pagevec_release(&pvec);
 		cond_resched();
 	}

fs/nfs/fscache-index.c

@@ -251,45 +251,6 @@ enum fscache_checkaux nfs_fscache_inode_check_aux(void *cookie_netfs_data,
 	return FSCACHE_CHECKAUX_OKAY;
 }
 
-/*
- * Indication from FS-Cache that the cookie is no longer cached
- * - This function is called when the backing store currently caching a cookie
- *   is removed
- * - The netfs should use this to clean up any markers indicating cached pages
- * - This is mandatory for any object that may have data
- */
-static void nfs_fscache_inode_now_uncached(void *cookie_netfs_data)
-{
-	struct nfs_inode *nfsi = cookie_netfs_data;
-	struct pagevec pvec;
-	pgoff_t first;
-	int loop, nr_pages;
-
-	pagevec_init(&pvec, 0);
-	first = 0;
-
-	dprintk("NFS: nfs_inode_now_uncached: nfs_inode 0x%p\n", nfsi);
-
-	for (;;) {
-		/* grab a bunch of pages to unmark */
-		nr_pages = pagevec_lookup(&pvec,
-					  nfsi->vfs_inode.i_mapping,
-					  first,
-					  PAGEVEC_SIZE - pagevec_count(&pvec));
-		if (!nr_pages)
-			break;
-
-		for (loop = 0; loop < nr_pages; loop++)
-			ClearPageFsCache(pvec.pages[loop]);
-
-		first = pvec.pages[nr_pages - 1]->index + 1;
-
-		pvec.nr = nr_pages;
-		pagevec_release(&pvec);
-		cond_resched();
-	}
-}
-
 /*
  * Get an extra reference on a read context.
  * - This function can be absent if the completion function doesn't require a
@@ -330,7 +291,6 @@ const struct fscache_cookie_def nfs_fscache_inode_object_def = {
 	.get_attr	= nfs_fscache_inode_get_attr,
 	.get_aux	= nfs_fscache_inode_get_aux,
 	.check_aux	= nfs_fscache_inode_check_aux,
-	.now_uncached	= nfs_fscache_inode_now_uncached,
 	.get_context	= nfs_fh_get_context,
 	.put_context	= nfs_fh_put_context,
 };

fs/nilfs2/page.c

@@ -312,10 +312,9 @@ void nilfs_copy_back_pages(struct address_space *dmap,
 
 	pagevec_init(&pvec, 0);
 repeat:
-	n = pagevec_lookup(&pvec, smap, index, PAGEVEC_SIZE);
+	n = pagevec_lookup(&pvec, smap, &index);
 	if (!n)
 		return;
-	index = pvec.pages[n - 1]->index + 1;
 
 	for (i = 0; i < pagevec_count(&pvec); i++) {
 		struct page *page = pvec.pages[i], *dpage;

fs/ocfs2/acl.c

@@ -221,7 +221,7 @@ out:
 /*
  * Set the access or default ACL of an inode.
  */
-int ocfs2_set_acl(handle_t *handle,
+static int ocfs2_set_acl(handle_t *handle,
 			 struct inode *inode,
 			 struct buffer_head *di_bh,
 			 int type,

fs/ocfs2/acl.h

@@ -28,13 +28,6 @@ struct ocfs2_acl_entry {
 
 struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, int type);
 int ocfs2_iop_set_acl(struct inode *inode, struct posix_acl *acl, int type);
-int ocfs2_set_acl(handle_t *handle,
-			 struct inode *inode,
-			 struct buffer_head *di_bh,
-			 int type,
-			 struct posix_acl *acl,
-			 struct ocfs2_alloc_context *meta_ac,
-			 struct ocfs2_alloc_context *data_ac);
 extern int ocfs2_acl_chmod(struct inode *, struct buffer_head *);
 extern int ocfs2_init_acl(handle_t *, struct inode *, struct inode *,
 			  struct buffer_head *, struct buffer_head *,

fs/ocfs2/alloc.c

@@ -955,8 +955,7 @@ int ocfs2_read_extent_block(struct ocfs2_caching_info *ci, u64 eb_blkno,
 /*
  * How many free extents have we got before we need more meta data?
  */
-int ocfs2_num_free_extents(struct ocfs2_super *osb,
-			   struct ocfs2_extent_tree *et)
+int ocfs2_num_free_extents(struct ocfs2_extent_tree *et)
 {
 	int retval;
 	struct ocfs2_extent_list *el = NULL;
@@ -1933,14 +1932,12 @@ out:
  * the new changes.
  *
  * left_rec: the record on the left.
- * left_child_el: is the child list pointed to by left_rec
  * right_rec: the record to the right of left_rec
  * right_child_el: is the child list pointed to by right_rec
  *
  * By definition, this only works on interior nodes.
  */
 static void ocfs2_adjust_adjacent_records(struct ocfs2_extent_rec *left_rec,
-				  struct ocfs2_extent_list *left_child_el,
 				  struct ocfs2_extent_rec *right_rec,
 				  struct ocfs2_extent_list *right_child_el)
 {
@@ -2003,7 +2000,7 @@ static void ocfs2_adjust_root_records(struct ocfs2_extent_list *root_el,
 	 */
 	BUG_ON(i >= (le16_to_cpu(root_el->l_next_free_rec) - 1));
 
-	ocfs2_adjust_adjacent_records(&root_el->l_recs[i], left_el,
+	ocfs2_adjust_adjacent_records(&root_el->l_recs[i],
 				      &root_el->l_recs[i + 1], right_el);
 }
 
@@ -2060,8 +2057,7 @@ static void ocfs2_complete_edge_insert(handle_t *handle,
 		el = right_path->p_node[i].el;
 		right_rec = &el->l_recs[0];
 
-		ocfs2_adjust_adjacent_records(left_rec, left_el, right_rec,
-					      right_el);
+		ocfs2_adjust_adjacent_records(left_rec, right_rec, right_el);
 
 		ocfs2_journal_dirty(handle, left_path->p_node[i].bh);
 		ocfs2_journal_dirty(handle, right_path->p_node[i].bh);
@@ -2509,7 +2505,7 @@ out_ret_path:
 
 static int ocfs2_update_edge_lengths(handle_t *handle,
 				     struct ocfs2_extent_tree *et,
-				     int subtree_index, struct ocfs2_path *path)
+				     struct ocfs2_path *path)
 {
 	int i, idx, ret;
 	struct ocfs2_extent_rec *rec;
@@ -2755,8 +2751,7 @@ static int ocfs2_rotate_subtree_left(handle_t *handle,
 	if (del_right_subtree) {
 		ocfs2_unlink_subtree(handle, et, left_path, right_path,
 				     subtree_index, dealloc);
-		ret = ocfs2_update_edge_lengths(handle, et, subtree_index,
-						left_path);
+		ret = ocfs2_update_edge_lengths(handle, et, left_path);
 		if (ret) {
 			mlog_errno(ret);
 			goto out;
@@ -3060,8 +3055,7 @@ static int ocfs2_remove_rightmost_path(handle_t *handle,
 
 		ocfs2_unlink_subtree(handle, et, left_path, path,
 				     subtree_index, dealloc);
-		ret = ocfs2_update_edge_lengths(handle, et, subtree_index,
-						left_path);
+		ret = ocfs2_update_edge_lengths(handle, et, left_path);
 		if (ret) {
 			mlog_errno(ret);
 			goto out;
@@ -4790,7 +4784,7 @@ int ocfs2_add_clusters_in_btree(handle_t *handle,
 	if (mark_unwritten)
 		flags = OCFS2_EXT_UNWRITTEN;
 
-	free_extents = ocfs2_num_free_extents(osb, et);
+	free_extents = ocfs2_num_free_extents(et);
 	if (free_extents < 0) {
 		status = free_extents;
 		mlog_errno(status);
@@ -5668,7 +5662,7 @@ static int ocfs2_reserve_blocks_for_rec_trunc(struct inode *inode,
 
 	*ac = NULL;
 
-	num_free_extents = ocfs2_num_free_extents(osb, et);
+	num_free_extents = ocfs2_num_free_extents(et);
 	if (num_free_extents < 0) {
 		ret = num_free_extents;
 		mlog_errno(ret);

fs/ocfs2/alloc.h

@@ -144,8 +144,7 @@ int ocfs2_remove_btree_range(struct inode *inode,
 			     struct ocfs2_cached_dealloc_ctxt *dealloc,
 			     u64 refcount_loc, bool refcount_tree_locked);
 
-int ocfs2_num_free_extents(struct ocfs2_super *osb,
-			   struct ocfs2_extent_tree *et);
+int ocfs2_num_free_extents(struct ocfs2_extent_tree *et);
 
 /*
  * how many new metadata chunks would an allocation need at maximum?

fs/ocfs2/cluster/heartbeat.c

@@ -505,8 +505,7 @@ static inline void o2hb_bio_wait_dec(struct o2hb_bio_wait_ctxt *wc,
 	}
 }
 
-static void o2hb_wait_on_io(struct o2hb_region *reg,
-			    struct o2hb_bio_wait_ctxt *wc)
+static void o2hb_wait_on_io(struct o2hb_bio_wait_ctxt *wc)
 {
 	o2hb_bio_wait_dec(wc, 1);
 	wait_for_completion(&wc->wc_io_complete);
@@ -608,7 +607,7 @@ static int o2hb_read_slots(struct o2hb_region *reg,
 	status = 0;
 
 bail_and_wait:
-	o2hb_wait_on_io(reg, &wc);
+	o2hb_wait_on_io(&wc);
 	if (wc.wc_error && !status)
 		status = wc.wc_error;
 
@@ -1162,7 +1161,7 @@ static int o2hb_do_disk_heartbeat(struct o2hb_region *reg)
 	 * before we can go to steady state.  This ensures that
 	 * people we find in our steady state have seen us.
 	 */
-	o2hb_wait_on_io(reg, &write_wc);
+	o2hb_wait_on_io(&write_wc);
 	if (write_wc.wc_error) {
 		/* Do not re-arm the write timeout on I/O error - we
 		 * can't be sure that the new block ever made it to
@@ -1275,7 +1274,7 @@ static int o2hb_thread(void *data)
 		o2hb_prepare_block(reg, 0);
 		ret = o2hb_issue_node_write(reg, &write_wc);
 		if (ret == 0)
-			o2hb_wait_on_io(reg, &write_wc);
+			o2hb_wait_on_io(&write_wc);
 		else
 			mlog_errno(ret);
 	}
@@ -2576,22 +2575,6 @@ void o2hb_unregister_callback(const char *region_uuid,
 }
 EXPORT_SYMBOL_GPL(o2hb_unregister_callback);
 
-int o2hb_check_node_heartbeating(u8 node_num)
-{
-	unsigned long testing_map[BITS_TO_LONGS(O2NM_MAX_NODES)];
-
-	o2hb_fill_node_map(testing_map, sizeof(testing_map));
-	if (!test_bit(node_num, testing_map)) {
-		mlog(ML_HEARTBEAT,
-		     "node (%u) does not have heartbeating enabled.\n",
-		     node_num);
-		return 0;
-	}
-
-	return 1;
-}
-EXPORT_SYMBOL_GPL(o2hb_check_node_heartbeating);
-
 int o2hb_check_node_heartbeating_no_sem(u8 node_num)
 {
 	unsigned long testing_map[BITS_TO_LONGS(O2NM_MAX_NODES)];
@@ -2626,23 +2609,6 @@ int o2hb_check_node_heartbeating_from_callback(u8 node_num)
 }
 EXPORT_SYMBOL_GPL(o2hb_check_node_heartbeating_from_callback);
 
-/* Makes sure our local node is configured with a node number, and is
- * heartbeating. */
-int o2hb_check_local_node_heartbeating(void)
-{
-	u8 node_num;
-
-	/* if this node was set then we have networking */
-	node_num = o2nm_this_node();
-	if (node_num == O2NM_MAX_NODES) {
-		mlog(ML_HEARTBEAT, "this node has not been configured.\n");
-		return 0;
-	}
-
-	return o2hb_check_node_heartbeating(node_num);
-}
-EXPORT_SYMBOL_GPL(o2hb_check_local_node_heartbeating);
-
 /*
  * this is just a hack until we get the plumbing which flips file systems
  * read only and drops the hb ref instead of killing the node dead.

fs/ocfs2/dir.c

@@ -3249,7 +3249,7 @@ static int ocfs2_extend_dir(struct ocfs2_super *osb,
 		spin_unlock(&OCFS2_I(dir)->ip_lock);
 		ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(dir),
 					      parent_fe_bh);
-		num_free_extents = ocfs2_num_free_extents(osb, &et);
+		num_free_extents = ocfs2_num_free_extents(&et);
 		if (num_free_extents < 0) {
 			status = num_free_extents;
 			mlog_errno(status);

fs/ocfs2/file.c

@@ -713,13 +713,6 @@ leave:
 	return status;
 }
 
-int ocfs2_extend_allocation(struct inode *inode, u32 logical_start,
-		u32 clusters_to_add, int mark_unwritten)
-{
-	return __ocfs2_extend_allocation(inode, logical_start,
-			clusters_to_add, mark_unwritten);
-}
-
 /*
  * While a write will already be ordering the data, a truncate will not.
  * Thus, we need to explicitly order the zeroed pages.

fs/ocfs2/journal.c

@@ -1348,7 +1348,6 @@ void ocfs2_complete_mount_recovery(struct ocfs2_super *osb)
 	ocfs2_schedule_truncate_log_flush(osb, 0);
 
 	osb->local_alloc_copy = NULL;
-	osb->dirty = 0;
 
 	/* queue to recover orphan slots for all offline slots */
 	ocfs2_replay_map_set_state(osb, REPLAY_NEEDED);

fs/ocfs2/move_extents.c

@@ -175,7 +175,7 @@ static int ocfs2_lock_allocators_move_extents(struct inode *inode,
 	unsigned int max_recs_needed = 2 * extents_to_split + clusters_to_move;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 
-	num_free_extents = ocfs2_num_free_extents(osb, et);
+	num_free_extents = ocfs2_num_free_extents(et);
 	if (num_free_extents < 0) {
 		ret = num_free_extents;
 		mlog_errno(ret);

fs/ocfs2/ocfs2.h

@@ -320,7 +320,6 @@ struct ocfs2_super
 	u64 system_dir_blkno;
 	u64 bitmap_blkno;
 	u32 bitmap_cpg;
-	u8 *uuid;
 	char *uuid_str;
 	u32 uuid_hash;
 	u8 *vol_label;
@@ -388,9 +387,8 @@ struct ocfs2_super
 	unsigned int	osb_resv_level;
 	unsigned int	osb_dir_resv_level;
 
-	/* Next three fields are for local node slot recovery during
+	/* Next two fields are for local node slot recovery during
 	 * mount. */
-	int dirty;
 	struct ocfs2_dinode *local_alloc_copy;
 	struct ocfs2_quota_recovery *quota_rec;
 

fs/ocfs2/refcounttree.c

@@ -2851,7 +2851,7 @@ static int ocfs2_lock_refcount_allocators(struct super_block *sb,
 					int *credits)
 {
 	int ret = 0, meta_add = 0;
-	int num_free_extents = ocfs2_num_free_extents(OCFS2_SB(sb), et);
+	int num_free_extents = ocfs2_num_free_extents(et);
 
 	if (num_free_extents < 0) {
 		ret = num_free_extents;

fs/ocfs2/suballoc.c

@@ -2700,7 +2700,7 @@ int ocfs2_lock_allocators(struct inode *inode,
 
 	BUG_ON(clusters_to_add != 0 && data_ac == NULL);
 
-	num_free_extents = ocfs2_num_free_extents(osb, et);
+	num_free_extents = ocfs2_num_free_extents(et);
 	if (num_free_extents < 0) {
 		ret = num_free_extents;
 		mlog_errno(ret);

fs/ocfs2/super.c

@@ -2486,7 +2486,6 @@ static int ocfs2_check_volume(struct ocfs2_super *osb)
 	if (dirty) {
 		/* Recovery will be completed after we've mounted the
 		 * rest of the volume. */
-		osb->dirty = 1;
 		osb->local_alloc_copy = local_alloc;
 		local_alloc = NULL;
 	}

fs/ocfs2/xattr.c

@@ -6800,7 +6800,7 @@ static int ocfs2_lock_reflink_xattr_rec_allocators(
 		*credits += 1;
 
 	/* count in the xattr tree change. */
-	num_free_extents = ocfs2_num_free_extents(osb, xt_et);
+	num_free_extents = ocfs2_num_free_extents(xt_et);
 	if (num_free_extents < 0) {
 		ret = num_free_extents;
 		mlog_errno(ret);

fs/proc/base.c

@@ -2931,6 +2931,7 @@ static const struct pid_entry tgid_base_stuff[] = {
 #ifdef CONFIG_PROC_PAGE_MONITOR
 	REG("clear_refs", S_IWUSR, proc_clear_refs_operations),
 	REG("smaps",      S_IRUGO, proc_pid_smaps_operations),
+	REG("smaps_rollup", S_IRUGO, proc_pid_smaps_rollup_operations),
 	REG("pagemap",    S_IRUSR, proc_pagemap_operations),
 #endif
 #ifdef CONFIG_SECURITY
@@ -3324,6 +3325,7 @@ static const struct pid_entry tid_base_stuff[] = {
 #ifdef CONFIG_PROC_PAGE_MONITOR
 	REG("clear_refs", S_IWUSR, proc_clear_refs_operations),
 	REG("smaps",     S_IRUGO, proc_tid_smaps_operations),
+	REG("smaps_rollup", S_IRUGO, proc_pid_smaps_rollup_operations),
 	REG("pagemap",    S_IRUSR, proc_pagemap_operations),
 #endif
 #ifdef CONFIG_SECURITY

fs/proc/internal.h

@@ -269,10 +269,12 @@ extern int proc_remount(struct super_block *, int *, char *);
 /*
  * task_[no]mmu.c
  */
+struct mem_size_stats;
 struct proc_maps_private {
 	struct inode *inode;
 	struct task_struct *task;
 	struct mm_struct *mm;
+	struct mem_size_stats *rollup;
 #ifdef CONFIG_MMU
 	struct vm_area_struct *tail_vma;
 #endif
@@ -288,6 +290,7 @@ extern const struct file_operations proc_tid_maps_operations;
 extern const struct file_operations proc_pid_numa_maps_operations;
 extern const struct file_operations proc_tid_numa_maps_operations;
 extern const struct file_operations proc_pid_smaps_operations;
+extern const struct file_operations proc_pid_smaps_rollup_operations;
 extern const struct file_operations proc_tid_smaps_operations;
 extern const struct file_operations proc_clear_refs_operations;
 extern const struct file_operations proc_pagemap_operations;

fs/proc/meminfo.c

@@ -80,7 +80,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 	show_val_kb(m, "Active(file):   ", pages[LRU_ACTIVE_FILE]);
 	show_val_kb(m, "Inactive(file): ", pages[LRU_INACTIVE_FILE]);
 	show_val_kb(m, "Unevictable:    ", pages[LRU_UNEVICTABLE]);
-	show_val_kb(m, "Mlocked:        ", global_page_state(NR_MLOCK));
+	show_val_kb(m, "Mlocked:        ", global_zone_page_state(NR_MLOCK));
 
 #ifdef CONFIG_HIGHMEM
 	show_val_kb(m, "HighTotal:      ", i.totalhigh);
@@ -114,9 +114,9 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 	show_val_kb(m, "SUnreclaim:     ",
 		    global_node_page_state(NR_SLAB_UNRECLAIMABLE));
 	seq_printf(m, "KernelStack:    %8lu kB\n",
-		   global_page_state(NR_KERNEL_STACK_KB));
+		   global_zone_page_state(NR_KERNEL_STACK_KB));
 	show_val_kb(m, "PageTables:     ",
-		    global_page_state(NR_PAGETABLE));
+		    global_zone_page_state(NR_PAGETABLE));
 #ifdef CONFIG_QUICKLIST
 	show_val_kb(m, "Quicklists:     ", quicklist_total_size());
 #endif
@@ -124,7 +124,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 	show_val_kb(m, "NFS_Unstable:   ",
 		    global_node_page_state(NR_UNSTABLE_NFS));
 	show_val_kb(m, "Bounce:         ",
-		    global_page_state(NR_BOUNCE));
+		    global_zone_page_state(NR_BOUNCE));
 	show_val_kb(m, "WritebackTmp:   ",
 		    global_node_page_state(NR_WRITEBACK_TEMP));
 	show_val_kb(m, "CommitLimit:    ", vm_commit_limit());
@@ -151,7 +151,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 #ifdef CONFIG_CMA
 	show_val_kb(m, "CmaTotal:       ", totalcma_pages);
 	show_val_kb(m, "CmaFree:        ",
-		    global_page_state(NR_FREE_CMA_PAGES));
+		    global_zone_page_state(NR_FREE_CMA_PAGES));
 #endif
 
 	hugetlb_report_meminfo(m);

fs/proc/task_mmu.c

@@ -253,6 +253,7 @@ static int proc_map_release(struct inode *inode, struct file *file)
 	if (priv->mm)
 		mmdrop(priv->mm);
 
+	kfree(priv->rollup);
 	return seq_release_private(inode, file);
 }
 
@@ -279,6 +280,23 @@ static int is_stack(struct proc_maps_private *priv,
 		vma->vm_end >= vma->vm_mm->start_stack;
 }
 
+static void show_vma_header_prefix(struct seq_file *m,
+				   unsigned long start, unsigned long end,
+				   vm_flags_t flags, unsigned long long pgoff,
+				   dev_t dev, unsigned long ino)
+{
+	seq_setwidth(m, 25 + sizeof(void *) * 6 - 1);
+	seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu ",
+		   start,
+		   end,
+		   flags & VM_READ ? 'r' : '-',
+		   flags & VM_WRITE ? 'w' : '-',
+		   flags & VM_EXEC ? 'x' : '-',
+		   flags & VM_MAYSHARE ? 's' : 'p',
+		   pgoff,
+		   MAJOR(dev), MINOR(dev), ino);
+}
+
 static void
 show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
 {
@@ -301,17 +319,7 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
 
 	start = vma->vm_start;
 	end = vma->vm_end;
-
-	seq_setwidth(m, 25 + sizeof(void *) * 6 - 1);
-	seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu ",
-			start,
-			end,
-			flags & VM_READ ? 'r' : '-',
-			flags & VM_WRITE ? 'w' : '-',
-			flags & VM_EXEC ? 'x' : '-',
-			flags & VM_MAYSHARE ? 's' : 'p',
-			pgoff,
-			MAJOR(dev), MINOR(dev), ino);
+	show_vma_header_prefix(m, start, end, flags, pgoff, dev, ino);
 
 	/*
 	 * Print the dentry name for named mappings, and a
@@ -430,6 +438,7 @@ const struct file_operations proc_tid_maps_operations = {
 
 #ifdef CONFIG_PROC_PAGE_MONITOR
 struct mem_size_stats {
+	bool first;
 	unsigned long resident;
 	unsigned long shared_clean;
 	unsigned long shared_dirty;
@@ -443,7 +452,9 @@ struct mem_size_stats {
 	unsigned long swap;
 	unsigned long shared_hugetlb;
 	unsigned long private_hugetlb;
+	unsigned long first_vma_start;
 	u64 pss;
+	u64 pss_locked;
 	u64 swap_pss;
 	bool check_shmem_swap;
 };
@@ -652,6 +663,7 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
 		[ilog2(VM_NORESERVE)]	= "nr",
 		[ilog2(VM_HUGETLB)]	= "ht",
 		[ilog2(VM_ARCH_1)]	= "ar",
+		[ilog2(VM_WIPEONFORK)]	= "wf",
 		[ilog2(VM_DONTDUMP)]	= "dd",
 #ifdef CONFIG_MEM_SOFT_DIRTY
 		[ilog2(VM_SOFTDIRTY)]	= "sd",
@@ -719,18 +731,36 @@ void __weak arch_show_smap(struct seq_file *m, struct vm_area_struct *vma)
 
 static int show_smap(struct seq_file *m, void *v, int is_pid)
 {
+	struct proc_maps_private *priv = m->private;
 	struct vm_area_struct *vma = v;
-	struct mem_size_stats mss;
+	struct mem_size_stats mss_stack;
+	struct mem_size_stats *mss;
 	struct mm_walk smaps_walk = {
 		.pmd_entry = smaps_pte_range,
 #ifdef CONFIG_HUGETLB_PAGE
 		.hugetlb_entry = smaps_hugetlb_range,
 #endif
 		.mm = vma->vm_mm,
-		.private = &mss,
 	};
+	int ret = 0;
+	bool rollup_mode;
+	bool last_vma;
+
+	if (priv->rollup) {
+		rollup_mode = true;
+		mss = priv->rollup;
+		if (mss->first) {
+			mss->first_vma_start = vma->vm_start;
+			mss->first = false;
+		}
+		last_vma = !m_next_vma(priv, vma);
+	} else {
+		rollup_mode = false;
+		memset(&mss_stack, 0, sizeof(mss_stack));
+		mss = &mss_stack;
+	}
 
-	memset(&mss, 0, sizeof mss);
+	smaps_walk.private = mss;
 
 #ifdef CONFIG_SHMEM
 	if (vma->vm_file && shmem_mapping(vma->vm_file->f_mapping)) {
@@ -748,9 +778,9 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
 
 		if (!shmem_swapped || (vma->vm_flags & VM_SHARED) ||
 					!(vma->vm_flags & VM_WRITE)) {
-			mss.swap = shmem_swapped;
+			mss->swap = shmem_swapped;
 		} else {
-			mss.check_shmem_swap = true;
+			mss->check_shmem_swap = true;
 			smaps_walk.pte_hole = smaps_pte_hole;
 		}
 	}
@@ -758,54 +788,71 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
 
 	/* mmap_sem is held in m_start */
 	walk_page_vma(vma, &smaps_walk);
+	if (vma->vm_flags & VM_LOCKED)
+		mss->pss_locked += mss->pss;
+
+	if (!rollup_mode) {
+		show_map_vma(m, vma, is_pid);
+	} else if (last_vma) {
+		show_vma_header_prefix(
+			m, mss->first_vma_start, vma->vm_end, 0, 0, 0, 0);
+		seq_pad(m, ' ');
+		seq_puts(m, "[rollup]\n");
+	} else {
+		ret = SEQ_SKIP;
+	}
 
-	show_map_vma(m, vma, is_pid);
-
-	seq_printf(m,
-		   "Size:           %8lu kB\n"
-		   "Rss:            %8lu kB\n"
-		   "Pss:            %8lu kB\n"
-		   "Shared_Clean:   %8lu kB\n"
-		   "Shared_Dirty:   %8lu kB\n"
-		   "Private_Clean:  %8lu kB\n"
-		   "Private_Dirty:  %8lu kB\n"
-		   "Referenced:     %8lu kB\n"
-		   "Anonymous:      %8lu kB\n"
-		   "LazyFree:       %8lu kB\n"
-		   "AnonHugePages:  %8lu kB\n"
-		   "ShmemPmdMapped: %8lu kB\n"
-		   "Shared_Hugetlb: %8lu kB\n"
-		   "Private_Hugetlb: %7lu kB\n"
-		   "Swap:           %8lu kB\n"
-		   "SwapPss:        %8lu kB\n"
-		   "KernelPageSize: %8lu kB\n"
-		   "MMUPageSize:    %8lu kB\n"
-		   "Locked:         %8lu kB\n",
-		   (vma->vm_end - vma->vm_start) >> 10,
-		   mss.resident >> 10,
-		   (unsigned long)(mss.pss >> (10 + PSS_SHIFT)),
-		   mss.shared_clean  >> 10,
-		   mss.shared_dirty  >> 10,
-		   mss.private_clean >> 10,
-		   mss.private_dirty >> 10,
-		   mss.referenced >> 10,
-		   mss.anonymous >> 10,
-		   mss.lazyfree >> 10,
-		   mss.anonymous_thp >> 10,
-		   mss.shmem_thp >> 10,
-		   mss.shared_hugetlb >> 10,
-		   mss.private_hugetlb >> 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) ?
-			(unsigned long)(mss.pss >> (10 + PSS_SHIFT)) : 0);
-
-	arch_show_smap(m, vma);
-	show_smap_vma_flags(m, vma);
+	if (!rollup_mode)
+		seq_printf(m,
+			   "Size:           %8lu kB\n"
+			   "KernelPageSize: %8lu kB\n"
+			   "MMUPageSize:    %8lu kB\n",
+			   (vma->vm_end - vma->vm_start) >> 10,
+			   vma_kernel_pagesize(vma) >> 10,
+			   vma_mmu_pagesize(vma) >> 10);
+
+
+	if (!rollup_mode || last_vma)
+		seq_printf(m,
+			   "Rss:            %8lu kB\n"
+			   "Pss:            %8lu kB\n"
+			   "Shared_Clean:   %8lu kB\n"
+			   "Shared_Dirty:   %8lu kB\n"
+			   "Private_Clean:  %8lu kB\n"
+			   "Private_Dirty:  %8lu kB\n"
+			   "Referenced:     %8lu kB\n"
+			   "Anonymous:      %8lu kB\n"
+			   "LazyFree:       %8lu kB\n"
+			   "AnonHugePages:  %8lu kB\n"
+			   "ShmemPmdMapped: %8lu kB\n"
+			   "Shared_Hugetlb: %8lu kB\n"
+			   "Private_Hugetlb: %7lu kB\n"
+			   "Swap:           %8lu kB\n"
+			   "SwapPss:        %8lu kB\n"
+			   "Locked:         %8lu kB\n",
+			   mss->resident >> 10,
+			   (unsigned long)(mss->pss >> (10 + PSS_SHIFT)),
+			   mss->shared_clean  >> 10,
+			   mss->shared_dirty  >> 10,
+			   mss->private_clean >> 10,
+			   mss->private_dirty >> 10,
+			   mss->referenced >> 10,
+			   mss->anonymous >> 10,
+			   mss->lazyfree >> 10,
+			   mss->anonymous_thp >> 10,
+			   mss->shmem_thp >> 10,
+			   mss->shared_hugetlb >> 10,
+			   mss->private_hugetlb >> 10,
+			   mss->swap >> 10,
+			   (unsigned long)(mss->swap_pss >> (10 + PSS_SHIFT)),
+			   (unsigned long)(mss->pss >> (10 + PSS_SHIFT)));
+
+	if (!rollup_mode) {
+		arch_show_smap(m, vma);
+		show_smap_vma_flags(m, vma);
+	}
 	m_cache_vma(m, vma);
-	return 0;
+	return ret;
 }
 
 static int show_pid_smap(struct seq_file *m, void *v)
@@ -837,6 +884,25 @@ static int pid_smaps_open(struct inode *inode, struct file *file)
 	return do_maps_open(inode, file, &proc_pid_smaps_op);
 }
 
+static int pid_smaps_rollup_open(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq;
+	struct proc_maps_private *priv;
+	int ret = do_maps_open(inode, file, &proc_pid_smaps_op);
+
+	if (ret < 0)
+		return ret;
+	seq = file->private_data;
+	priv = seq->private;
+	priv->rollup = kzalloc(sizeof(*priv->rollup), GFP_KERNEL);
+	if (!priv->rollup) {
+		proc_map_release(inode, file);
+		return -ENOMEM;
+	}
+	priv->rollup->first = true;
+	return 0;
+}
+
 static int tid_smaps_open(struct inode *inode, struct file *file)
 {
 	return do_maps_open(inode, file, &proc_tid_smaps_op);
@@ -849,6 +915,13 @@ const struct file_operations proc_pid_smaps_operations = {
 	.release	= proc_map_release,
 };
 
+const struct file_operations proc_pid_smaps_rollup_operations = {
+	.open		= pid_smaps_rollup_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= proc_map_release,
+};
+
 const struct file_operations proc_tid_smaps_operations = {
 	.open		= tid_smaps_open,
 	.read		= seq_read,

fs/ramfs/file-nommu.c

@@ -228,7 +228,7 @@ static unsigned long ramfs_nommu_get_unmapped_area(struct file *file,
 	if (!pages)
 		goto out_free;
 
-	nr = find_get_pages(inode->i_mapping, pgoff, lpages, pages);
+	nr = find_get_pages(inode->i_mapping, &pgoff, lpages, pages);
 	if (nr != lpages)
 		goto out_free_pages; /* leave if some pages were missing */
 

fs/sync.c

@@ -335,11 +335,6 @@ SYSCALL_DEFINE4(sync_file_range, int, fd, loff_t, offset, loff_t, nbytes,
 		goto out_put;
 
 	mapping = f.file->f_mapping;
-	if (!mapping) {
-		ret = -EINVAL;
-		goto out_put;
-	}
-
 	ret = 0;
 	if (flags & SYNC_FILE_RANGE_WAIT_BEFORE) {
 		ret = file_fdatawait_range(f.file, offset, endbyte);

fs/userfaultfd.c

@@ -178,7 +178,8 @@ static inline void msg_init(struct uffd_msg *msg)
 
 static inline struct uffd_msg userfault_msg(unsigned long address,
 					    unsigned int flags,
-					    unsigned long reason)
+					    unsigned long reason,
+					    unsigned int features)
 {
 	struct uffd_msg msg;
 	msg_init(&msg);
@@ -202,6 +203,8 @@ static inline struct uffd_msg userfault_msg(unsigned long address,
 		 * write protect fault.
 		 */
 		msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WP;
+	if (features & UFFD_FEATURE_THREAD_ID)
+		msg.arg.pagefault.feat.ptid = task_pid_vnr(current);
 	return msg;
 }
 
@@ -370,6 +373,9 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason)
 	VM_BUG_ON(reason & ~(VM_UFFD_MISSING|VM_UFFD_WP));
 	VM_BUG_ON(!(reason & VM_UFFD_MISSING) ^ !!(reason & VM_UFFD_WP));
 
+	if (ctx->features & UFFD_FEATURE_SIGBUS)
+		goto out;
+
 	/*
 	 * If it's already released don't get it. This avoids to loop
 	 * in __get_user_pages if userfaultfd_release waits on the
@@ -419,7 +425,8 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason)
 
 	init_waitqueue_func_entry(&uwq.wq, userfaultfd_wake_function);
 	uwq.wq.private = current;
-	uwq.msg = userfault_msg(vmf->address, vmf->flags, reason);
+	uwq.msg = userfault_msg(vmf->address, vmf->flags, reason,
+			ctx->features);
 	uwq.ctx = ctx;
 	uwq.waken = false;
 
@@ -1194,7 +1201,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 	struct uffdio_register __user *user_uffdio_register;
 	unsigned long vm_flags, new_flags;
 	bool found;
-	bool non_anon_pages;
+	bool basic_ioctls;
 	unsigned long start, end, vma_end;
 
 	user_uffdio_register = (struct uffdio_register __user *) arg;
@@ -1260,7 +1267,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 	 * Search for not compatible vmas.
 	 */
 	found = false;
-	non_anon_pages = false;
+	basic_ioctls = false;
 	for (cur = vma; cur && cur->vm_start < end; cur = cur->vm_next) {
 		cond_resched();
 
@@ -1299,8 +1306,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 		/*
 		 * Note vmas containing huge pages
 		 */
-		if (is_vm_hugetlb_page(cur) || vma_is_shmem(cur))
-			non_anon_pages = true;
+		if (is_vm_hugetlb_page(cur))
+			basic_ioctls = true;
 
 		found = true;
 	}
@@ -1371,7 +1378,7 @@ out_unlock:
 		 * userland which ioctls methods are guaranteed to
 		 * succeed on this range.
 		 */
-		if (put_user(non_anon_pages ? UFFD_API_RANGE_IOCTLS_BASIC :
+		if (put_user(basic_ioctls ? UFFD_API_RANGE_IOCTLS_BASIC :
 			     UFFD_API_RANGE_IOCTLS,
 			     &user_uffdio_register->ioctls))
 			ret = -EFAULT;

fs/xfs/xfs_file.c

@@ -1101,7 +1101,7 @@ xfs_filemap_pfn_mkwrite(
 	if (vmf->pgoff >= size)
 		ret = VM_FAULT_SIGBUS;
 	else if (IS_DAX(inode))
-		ret = dax_pfn_mkwrite(vmf);
+		ret = dax_iomap_fault(vmf, PE_SIZE_PTE, &xfs_iomap_ops);
 	xfs_iunlock(ip, XFS_MMAPLOCK_SHARED);
 	sb_end_pagefault(inode->i_sb);
 	return ret;

include/linux/bio.h

@@ -38,7 +38,15 @@
 #define BIO_BUG_ON
 #endif
 
+#ifdef CONFIG_THP_SWAP
+#if HPAGE_PMD_NR > 256
+#define BIO_MAX_PAGES		HPAGE_PMD_NR
+#else
 #define BIO_MAX_PAGES		256
+#endif
+#else
+#define BIO_MAX_PAGES		256
+#endif
 
 #define bio_prio(bio)			(bio)->bi_ioprio
 #define bio_set_prio(bio, prio)		((bio)->bi_ioprio = prio)

include/linux/dax.h

@@ -89,34 +89,6 @@ void dax_flush(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
 void dax_write_cache(struct dax_device *dax_dev, bool wc);
 bool dax_write_cache_enabled(struct dax_device *dax_dev);
 
-/*
- * We use lowest available bit in exceptional entry for locking, one bit for
- * the entry size (PMD) and two more to tell us if the entry is a huge zero
- * page (HZP) or an empty entry that is just used for locking.  In total four
- * special bits.
- *
- * If the PMD bit isn't set the entry has size PAGE_SIZE, and if the HZP and
- * EMPTY bits aren't set the entry is a normal DAX entry with a filesystem
- * block allocation.
- */
-#define RADIX_DAX_SHIFT	(RADIX_TREE_EXCEPTIONAL_SHIFT + 4)
-#define RADIX_DAX_ENTRY_LOCK (1 << RADIX_TREE_EXCEPTIONAL_SHIFT)
-#define RADIX_DAX_PMD (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 1))
-#define RADIX_DAX_HZP (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 2))
-#define RADIX_DAX_EMPTY (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 3))
-
-static inline unsigned long dax_radix_sector(void *entry)
-{
-	return (unsigned long)entry >> RADIX_DAX_SHIFT;
-}
-
-static inline void *dax_radix_locked_entry(sector_t sector, unsigned long flags)
-{
-	return (void *)(RADIX_TREE_EXCEPTIONAL_ENTRY | flags |
-			((unsigned long)sector << RADIX_DAX_SHIFT) |
-			RADIX_DAX_ENTRY_LOCK);
-}
-
 ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops);
 int dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size,
@@ -124,8 +96,6 @@ int dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size,
 int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
 int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
 				      pgoff_t index);
-void dax_wake_mapping_entry_waiter(struct address_space *mapping,
-		pgoff_t index, void *entry, bool wake_all);
 
 #ifdef CONFIG_FS_DAX
 int __dax_zero_page_range(struct block_device *bdev,
@@ -140,21 +110,6 @@ static inline int __dax_zero_page_range(struct block_device *bdev,
 }
 #endif
 
-#ifdef CONFIG_FS_DAX_PMD
-static inline unsigned int dax_radix_order(void *entry)
-{
-	if ((unsigned long)entry & RADIX_DAX_PMD)
-		return PMD_SHIFT - PAGE_SHIFT;
-	return 0;
-}
-#else
-static inline unsigned int dax_radix_order(void *entry)
-{
-	return 0;
-}
-#endif
-int dax_pfn_mkwrite(struct vm_fault *vmf);
-
 static inline bool dax_mapping(struct address_space *mapping)
 {
 	return mapping->host && IS_DAX(mapping->host);

include/linux/fs.h

@@ -1269,8 +1269,6 @@ extern void f_delown(struct file *filp);
 extern pid_t f_getown(struct file *filp);
 extern int send_sigurg(struct fown_struct *fown);
 
-struct mm_struct;
-
 /*
  *	Umount options
  */

include/linux/fscache.h

@@ -143,15 +143,6 @@ struct fscache_cookie_def {
 	void (*mark_page_cached)(void *cookie_netfs_data,
 				 struct address_space *mapping,
 				 struct page *page);
-
-	/* indicate the cookie is no longer cached
-	 * - this function is called when the backing store currently caching
-	 *   a cookie is removed
-	 * - the netfs should use this to clean up any markers indicating
-	 *   cached pages
-	 * - this is mandatory for any object that may have data
-	 */
-	void (*now_uncached)(void *cookie_netfs_data);
 };
 
 /*

include/linux/memcontrol.h

@@ -488,8 +488,9 @@ struct mem_cgroup *lock_page_memcg(struct page *page);
 void __unlock_page_memcg(struct mem_cgroup *memcg);
 void unlock_page_memcg(struct page *page);
 
+/* idx can be of type enum memcg_stat_item or node_stat_item */
 static inline unsigned long memcg_page_state(struct mem_cgroup *memcg,
-					     enum memcg_stat_item idx)
+					     int idx)
 {
 	long val = 0;
 	int cpu;
@@ -503,15 +504,17 @@ static inline unsigned long memcg_page_state(struct mem_cgroup *memcg,
 	return val;
 }
 
+/* idx can be of type enum memcg_stat_item or node_stat_item */
 static inline void __mod_memcg_state(struct mem_cgroup *memcg,
-				     enum memcg_stat_item idx, int val)
+				     int idx, int val)
 {
 	if (!mem_cgroup_disabled())
 		__this_cpu_add(memcg->stat->count[idx], val);
 }
 
+/* idx can be of type enum memcg_stat_item or node_stat_item */
 static inline void mod_memcg_state(struct mem_cgroup *memcg,
-				   enum memcg_stat_item idx, int val)
+				   int idx, int val)
 {
 	if (!mem_cgroup_disabled())
 		this_cpu_add(memcg->stat->count[idx], val);
@@ -535,14 +538,14 @@ static inline void mod_memcg_state(struct mem_cgroup *memcg,
  * Kernel pages are an exception to this, since they'll never move.
  */
 static inline void __mod_memcg_page_state(struct page *page,
-					  enum memcg_stat_item idx, int val)
+					  int idx, int val)
 {
 	if (page->mem_cgroup)
 		__mod_memcg_state(page->mem_cgroup, idx, val);
 }
 
 static inline void mod_memcg_page_state(struct page *page,
-					enum memcg_stat_item idx, int val)
+					int idx, int val)
 {
 	if (page->mem_cgroup)
 		mod_memcg_state(page->mem_cgroup, idx, val);
@@ -632,8 +635,9 @@ static inline void count_memcg_events(struct mem_cgroup *memcg,
 		this_cpu_add(memcg->stat->events[idx], count);
 }
 
+/* idx can be of type enum memcg_stat_item or node_stat_item */
 static inline void count_memcg_page_event(struct page *page,
-					  enum memcg_stat_item idx)
+					  int idx)
 {
 	if (page->mem_cgroup)
 		count_memcg_events(page->mem_cgroup, idx, 1);
@@ -846,31 +850,31 @@ static inline bool mem_cgroup_oom_synchronize(bool wait)
 }
 
 static inline unsigned long memcg_page_state(struct mem_cgroup *memcg,
-					     enum memcg_stat_item idx)
+					     int idx)
 {
 	return 0;
 }
 
 static inline void __mod_memcg_state(struct mem_cgroup *memcg,
-				     enum memcg_stat_item idx,
+				     int idx,
 				     int nr)
 {
 }
 
 static inline void mod_memcg_state(struct mem_cgroup *memcg,
-				   enum memcg_stat_item idx,
+				   int idx,
 				   int nr)
 {
 }
 
 static inline void __mod_memcg_page_state(struct page *page,
-					  enum memcg_stat_item idx,
+					  int idx,
 					  int nr)
 {
 }
 
 static inline void mod_memcg_page_state(struct page *page,
-					enum memcg_stat_item idx,
+					int idx,
 					int nr)
 {
 }
@@ -924,7 +928,7 @@ static inline void count_memcg_events(struct mem_cgroup *memcg,
 }
 
 static inline void count_memcg_page_event(struct page *page,
-					  enum memcg_stat_item idx)
+					  int idx)
 {
 }
 
@@ -934,26 +938,30 @@ void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx)
 }
 #endif /* CONFIG_MEMCG */
 
+/* idx can be of type enum memcg_stat_item or node_stat_item */
 static inline void __inc_memcg_state(struct mem_cgroup *memcg,
-				     enum memcg_stat_item idx)
+				     int idx)
 {
 	__mod_memcg_state(memcg, idx, 1);
 }
 
+/* idx can be of type enum memcg_stat_item or node_stat_item */
 static inline void __dec_memcg_state(struct mem_cgroup *memcg,
-				     enum memcg_stat_item idx)
+				     int idx)
 {
 	__mod_memcg_state(memcg, idx, -1);
 }
 
+/* idx can be of type enum memcg_stat_item or node_stat_item */
 static inline void __inc_memcg_page_state(struct page *page,
-					  enum memcg_stat_item idx)
+					  int idx)
 {
 	__mod_memcg_page_state(page, idx, 1);
 }
 
+/* idx can be of type enum memcg_stat_item or node_stat_item */
 static inline void __dec_memcg_page_state(struct page *page,
-					  enum memcg_stat_item idx)
+					  int idx)
 {
 	__mod_memcg_page_state(page, idx, -1);
 }
@@ -982,26 +990,30 @@ static inline void __dec_lruvec_page_state(struct page *page,
 	__mod_lruvec_page_state(page, idx, -1);
 }
 
+/* idx can be of type enum memcg_stat_item or node_stat_item */
 static inline void inc_memcg_state(struct mem_cgroup *memcg,
-				   enum memcg_stat_item idx)
+				   int idx)
 {
 	mod_memcg_state(memcg, idx, 1);
 }
 
+/* idx can be of type enum memcg_stat_item or node_stat_item */
 static inline void dec_memcg_state(struct mem_cgroup *memcg,
-				   enum memcg_stat_item idx)
+				   int idx)
 {
 	mod_memcg_state(memcg, idx, -1);
 }
 
+/* idx can be of type enum memcg_stat_item or node_stat_item */
 static inline void inc_memcg_page_state(struct page *page,
-					enum memcg_stat_item idx)
+					int idx)
 {
 	mod_memcg_page_state(page, idx, 1);
 }
 
+/* idx can be of type enum memcg_stat_item or node_stat_item */
 static inline void dec_memcg_page_state(struct page *page,
-					enum memcg_stat_item idx)
+					int idx)
 {
 	mod_memcg_page_state(page, idx, -1);
 }

include/linux/memory_hotplug.h

@@ -319,6 +319,6 @@ extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map,
 					  unsigned long pnum);
 extern bool allow_online_pfn_range(int nid, unsigned long pfn, unsigned long nr_pages,
 		int online_type);
-extern struct zone *default_zone_for_pfn(int nid, unsigned long pfn,
+extern struct zone *zone_for_pfn_range(int online_type, int nid, unsigned start_pfn,
 		unsigned long nr_pages);
 #endif /* __LINUX_MEMORY_HOTPLUG_H */

include/linux/mm.h

@@ -189,7 +189,7 @@ extern unsigned int kobjsize(const void *objp);
 #define VM_NORESERVE	0x00200000	/* should the VM suppress accounting */
 #define VM_HUGETLB	0x00400000	/* Huge TLB Page VM */
 #define VM_ARCH_1	0x01000000	/* Architecture-specific flag */
-#define VM_ARCH_2	0x02000000
+#define VM_WIPEONFORK	0x02000000	/* Wipe VMA contents in child. */
 #define VM_DONTDUMP	0x04000000	/* Do not include in the core dump */
 
 #ifdef CONFIG_MEM_SOFT_DIRTY
@@ -208,10 +208,12 @@ extern unsigned int kobjsize(const void *objp);
 #define VM_HIGH_ARCH_BIT_1	33	/* bit only usable on 64-bit architectures */
 #define VM_HIGH_ARCH_BIT_2	34	/* bit only usable on 64-bit architectures */
 #define VM_HIGH_ARCH_BIT_3	35	/* bit only usable on 64-bit architectures */
+#define VM_HIGH_ARCH_BIT_4	36	/* bit only usable on 64-bit architectures */
 #define VM_HIGH_ARCH_0	BIT(VM_HIGH_ARCH_BIT_0)
 #define VM_HIGH_ARCH_1	BIT(VM_HIGH_ARCH_BIT_1)
 #define VM_HIGH_ARCH_2	BIT(VM_HIGH_ARCH_BIT_2)
 #define VM_HIGH_ARCH_3	BIT(VM_HIGH_ARCH_BIT_3)
+#define VM_HIGH_ARCH_4	BIT(VM_HIGH_ARCH_BIT_4)
 #endif /* CONFIG_ARCH_USES_HIGH_VMA_FLAGS */
 
 #if defined(CONFIG_X86)
@@ -235,9 +237,11 @@ extern unsigned int kobjsize(const void *objp);
 # define VM_MAPPED_COPY	VM_ARCH_1	/* T if mapped copy of data (nommu mmap) */
 #endif
 
-#if defined(CONFIG_X86)
+#if defined(CONFIG_X86_INTEL_MPX)
 /* MPX specific bounds table or bounds directory */
-# define VM_MPX		VM_ARCH_2
+# define VM_MPX		VM_HIGH_ARCH_BIT_4
+#else
+# define VM_MPX		VM_NONE
 #endif
 
 #ifndef VM_GROWSUP
@@ -2294,6 +2298,8 @@ int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
 			unsigned long pfn, pgprot_t pgprot);
 int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
 			pfn_t pfn);
+int vm_insert_mixed_mkwrite(struct vm_area_struct *vma, unsigned long addr,
+			pfn_t pfn);
 int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len);
 
 
@@ -2506,7 +2512,7 @@ enum mf_action_page_type {
 
 #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS)
 extern void clear_huge_page(struct page *page,
-			    unsigned long addr,
+			    unsigned long addr_hint,
 			    unsigned int pages_per_huge_page);
 extern void copy_user_huge_page(struct page *dst, struct page *src,
 				unsigned long addr, struct vm_area_struct *vma,

include/linux/mm_types.h

@@ -335,6 +335,7 @@ struct vm_area_struct {
 	struct file * vm_file;		/* File we map to (can be NULL). */
 	void * vm_private_data;		/* was vm_pte (shared mem) */
 
+	atomic_long_t swap_readahead_info;
 #ifndef CONFIG_MMU
 	struct vm_region *vm_region;	/* NOMMU mapping region */
 #endif

include/linux/mmzone.h

@@ -770,8 +770,7 @@ static inline bool is_dev_zone(const struct zone *zone)
 
 #include <linux/memory_hotplug.h>
 
-extern struct mutex zonelists_mutex;
-void build_all_zonelists(pg_data_t *pgdat, struct zone *zone);
+void build_all_zonelists(pg_data_t *pgdat);
 void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx);
 bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
 			 int classzone_idx, unsigned int alloc_flags,
@@ -896,7 +895,7 @@ int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *, int,
 extern int numa_zonelist_order_handler(struct ctl_table *, int,
 			void __user *, size_t *, loff_t *);
 extern char numa_zonelist_order[];
-#define NUMA_ZONELIST_ORDER_LEN 16	/* string buffer size */
+#define NUMA_ZONELIST_ORDER_LEN	16
 
 #ifndef CONFIG_NEED_MULTIPLE_NODES
 

include/linux/page-flags.h

@@ -303,8 +303,8 @@ PAGEFLAG(OwnerPriv1, owner_priv_1, PF_ANY)
  * Only test-and-set exist for PG_writeback.  The unconditional operators are
  * risky: they bypass page accounting.
  */
-TESTPAGEFLAG(Writeback, writeback, PF_NO_COMPOUND)
-	TESTSCFLAG(Writeback, writeback, PF_NO_COMPOUND)
+TESTPAGEFLAG(Writeback, writeback, PF_NO_TAIL)
+	TESTSCFLAG(Writeback, writeback, PF_NO_TAIL)
 PAGEFLAG(MappedToDisk, mappedtodisk, PF_NO_TAIL)
 
 /* PG_readahead is only used for reads; PG_reclaim is only for writes */

include/linux/pagemap.h

@@ -353,8 +353,16 @@ struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset);
 unsigned find_get_entries(struct address_space *mapping, pgoff_t start,
 			  unsigned int nr_entries, struct page **entries,
 			  pgoff_t *indices);
-unsigned find_get_pages(struct address_space *mapping, pgoff_t start,
-			unsigned int nr_pages, struct page **pages);
+unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start,
+			pgoff_t end, unsigned int nr_pages,
+			struct page **pages);
+static inline unsigned find_get_pages(struct address_space *mapping,
+			pgoff_t *start, unsigned int nr_pages,
+			struct page **pages)
+{
+	return find_get_pages_range(mapping, start, (pgoff_t)-1, nr_pages,
+				    pages);
+}
 unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start,
 			       unsigned int nr_pages, struct page **pages);
 unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index,

include/linux/pagevec.h

@@ -27,8 +27,16 @@ unsigned pagevec_lookup_entries(struct pagevec *pvec,
 				pgoff_t start, unsigned nr_entries,
 				pgoff_t *indices);
 void pagevec_remove_exceptionals(struct pagevec *pvec);
-unsigned pagevec_lookup(struct pagevec *pvec, struct address_space *mapping,
-		pgoff_t start, unsigned nr_pages);
+unsigned pagevec_lookup_range(struct pagevec *pvec,
+			      struct address_space *mapping,
+			      pgoff_t *start, pgoff_t end);
+static inline unsigned pagevec_lookup(struct pagevec *pvec,
+				      struct address_space *mapping,
+				      pgoff_t *start)
+{
+	return pagevec_lookup_range(pvec, mapping, start, (pgoff_t)-1);
+}
+
 unsigned pagevec_lookup_tag(struct pagevec *pvec,
 		struct address_space *mapping, pgoff_t *index, int tag,
 		unsigned nr_pages);

include/linux/sched/mm.h

@@ -84,12 +84,6 @@ static inline bool mmget_not_zero(struct mm_struct *mm)
 
 /* mmput gets rid of the mappings and all user-space */
 extern void mmput(struct mm_struct *);
-#ifdef CONFIG_MMU
-/* same as above but performs the slow path from the async context. Can
- * be called from the atomic context as well
- */
-extern void mmput_async(struct mm_struct *);
-#endif
 
 /* Grab a reference to a task's mm, if it is not already going away */
 extern struct mm_struct *get_task_mm(struct task_struct *task);

include/linux/shm.h

@@ -27,23 +27,6 @@ struct shmid_kernel /* private to the kernel */
 /* shm_mode upper byte flags */
 #define	SHM_DEST	01000	/* segment will be destroyed on last detach */
 #define SHM_LOCKED      02000   /* segment will not be swapped */
-#define SHM_HUGETLB     04000   /* segment will use huge TLB pages */
-#define SHM_NORESERVE   010000  /* don't check for reservations */
-
-/* Bits [26:31] are reserved */
-
-/*
- * When SHM_HUGETLB is set bits [26:31] encode the log2 of the huge page size.
- * This gives us 6 bits, which is enough until someone invents 128 bit address
- * spaces.
- *
- * Assume these are all power of twos.
- * When 0 use the default page size.
- */
-#define SHM_HUGE_SHIFT  26
-#define SHM_HUGE_MASK   0x3f
-#define SHM_HUGE_2MB    (21 << SHM_HUGE_SHIFT)
-#define SHM_HUGE_1GB    (30 << SHM_HUGE_SHIFT)
 
 #ifdef CONFIG_SYSVIPC
 struct sysv_shm {

include/linux/shmem_fs.h

@@ -137,9 +137,15 @@ extern int shmem_mcopy_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd,
 				  unsigned long dst_addr,
 				  unsigned long src_addr,
 				  struct page **pagep);
+extern int shmem_mfill_zeropage_pte(struct mm_struct *dst_mm,
+				    pmd_t *dst_pmd,
+				    struct vm_area_struct *dst_vma,
+				    unsigned long dst_addr);
 #else
 #define shmem_mcopy_atomic_pte(dst_mm, dst_pte, dst_vma, dst_addr, \
 			       src_addr, pagep)        ({ BUG(); 0; })
+#define shmem_mfill_zeropage_pte(dst_mm, dst_pmd, dst_vma, \
+				 dst_addr)      ({ BUG(); 0; })
 #endif
 
 #endif

include/linux/shrinker.h

@@ -18,6 +18,13 @@ struct shrink_control {
 	 */
 	unsigned long nr_to_scan;
 
+	/*
+	 * How many objects did scan_objects process?
+	 * This defaults to nr_to_scan before every call, but the callee
+	 * should track its actual progress.
+	 */
+	unsigned long nr_scanned;
+
 	/* current node being shrunk (for NUMA aware shrinkers) */
 	int nid;
 

include/linux/slub_def.h

@@ -115,6 +115,10 @@ struct kmem_cache {
 #endif
 #endif
 
+#ifdef CONFIG_SLAB_FREELIST_HARDENED
+	unsigned long random;
+#endif
+
 #ifdef CONFIG_NUMA
 	/*
 	 * Defragmentation by allocating from a remote node.

include/linux/swap.h

@@ -188,6 +188,7 @@ struct swap_cluster_info {
 };
 #define CLUSTER_FLAG_FREE 1 /* This cluster is free */
 #define CLUSTER_FLAG_NEXT_NULL 2 /* This cluster has no next cluster */
+#define CLUSTER_FLAG_HUGE 4 /* This cluster is backing a transparent huge page */
 
 /*
  * We assign a cluster to each CPU, so each CPU can allocate swap entry from
@@ -211,7 +212,7 @@ struct swap_info_struct {
 	unsigned long	flags;		/* SWP_USED etc: see above */
 	signed short	prio;		/* swap priority of this type */
 	struct plist_node list;		/* entry in swap_active_head */
-	struct plist_node avail_list;	/* entry in swap_avail_head */
+	struct plist_node avail_lists[MAX_NUMNODES];/* entry in swap_avail_heads */
 	signed char	type;		/* strange name for an index */
 	unsigned int	max;		/* extent of the swap_map */
 	unsigned char *swap_map;	/* vmalloc'ed array of usage counts */
@@ -250,6 +251,25 @@ struct swap_info_struct {
 	struct swap_cluster_list discard_clusters; /* discard clusters list */
 };
 
+#ifdef CONFIG_64BIT
+#define SWAP_RA_ORDER_CEILING	5
+#else
+/* Avoid stack overflow, because we need to save part of page table */
+#define SWAP_RA_ORDER_CEILING	3
+#define SWAP_RA_PTE_CACHE_SIZE	(1 << SWAP_RA_ORDER_CEILING)
+#endif
+
+struct vma_swap_readahead {
+	unsigned short win;
+	unsigned short offset;
+	unsigned short nr_pte;
+#ifdef CONFIG_64BIT
+	pte_t *ptes;
+#else
+	pte_t ptes[SWAP_RA_PTE_CACHE_SIZE];
+#endif
+};
+
 /* linux/mm/workingset.c */
 void *workingset_eviction(struct address_space *mapping, struct page *page);
 bool workingset_refault(void *shadow);
@@ -262,8 +282,8 @@ extern unsigned long totalreserve_pages;
 extern unsigned long nr_free_buffer_pages(void);
 extern unsigned long nr_free_pagecache_pages(void);
 
-/* Definition of global_page_state not available yet */
-#define nr_free_pages() global_page_state(NR_FREE_PAGES)
+/* Definition of global_zone_page_state not available yet */
+#define nr_free_pages() global_zone_page_state(NR_FREE_PAGES)
 
 
 /* linux/mm/swap.c */
@@ -349,6 +369,7 @@ int generic_swapfile_activate(struct swap_info_struct *, struct file *,
 #define SWAP_ADDRESS_SPACE_SHIFT	14
 #define SWAP_ADDRESS_SPACE_PAGES	(1 << SWAP_ADDRESS_SPACE_SHIFT)
 extern struct address_space *swapper_spaces[];
+extern bool swap_vma_readahead;
 #define swap_address_space(entry)			    \
 	(&swapper_spaces[swp_type(entry)][swp_offset(entry) \
 		>> SWAP_ADDRESS_SPACE_SHIFT])
@@ -361,7 +382,9 @@ extern void __delete_from_swap_cache(struct page *);
 extern void delete_from_swap_cache(struct page *);
 extern void free_page_and_swap_cache(struct page *);
 extern void free_pages_and_swap_cache(struct page **, int);
-extern struct page *lookup_swap_cache(swp_entry_t);
+extern struct page *lookup_swap_cache(swp_entry_t entry,
+				      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 do_poll);
@@ -371,11 +394,23 @@ extern struct page *__read_swap_cache_async(swp_entry_t, gfp_t,
 extern struct page *swapin_readahead(swp_entry_t, gfp_t,
 			struct vm_area_struct *vma, unsigned long addr);
 
+extern struct page *swap_readahead_detect(struct vm_fault *vmf,
+					  struct vma_swap_readahead *swap_ra);
+extern struct page *do_swap_page_readahead(swp_entry_t fentry, gfp_t gfp_mask,
+					   struct vm_fault *vmf,
+					   struct vma_swap_readahead *swap_ra);
+
 /* linux/mm/swapfile.c */
 extern atomic_long_t nr_swap_pages;
 extern long total_swap_pages;
+extern atomic_t nr_rotate_swap;
 extern bool has_usable_swap(void);
 
+static inline bool swap_use_vma_readahead(void)
+{
+	return READ_ONCE(swap_vma_readahead) && !atomic_read(&nr_rotate_swap);
+}
+
 /* Swap 50% full? Release swapcache more aggressively.. */
 static inline bool vm_swap_full(void)
 {
@@ -465,12 +500,32 @@ static inline struct page *swapin_readahead(swp_entry_t swp, gfp_t gfp_mask,
 	return NULL;
 }
 
+static inline bool swap_use_vma_readahead(void)
+{
+	return false;
+}
+
+static inline struct page *swap_readahead_detect(
+	struct vm_fault *vmf, struct vma_swap_readahead *swap_ra)
+{
+	return NULL;
+}
+
+static inline struct page *do_swap_page_readahead(
+	swp_entry_t fentry, gfp_t gfp_mask,
+	struct vm_fault *vmf, struct vma_swap_readahead *swap_ra)
+{
+	return NULL;
+}
+
 static inline int swap_writepage(struct page *p, struct writeback_control *wbc)
 {
 	return 0;
 }
 
-static inline struct page *lookup_swap_cache(swp_entry_t swp)
+static inline struct page *lookup_swap_cache(swp_entry_t swp,
+					     struct vm_area_struct *vma,
+					     unsigned long addr)
 {
 	return NULL;
 }
@@ -509,8 +564,8 @@ static inline int swp_swapcount(swp_entry_t entry)
 	return 0;
 }
 
-#define reuse_swap_page(page, total_mapcount) \
-	(page_trans_huge_mapcount(page, total_mapcount) == 1)
+#define reuse_swap_page(page, total_map_swapcount) \
+	(page_trans_huge_mapcount(page, total_map_swapcount) == 1)
 
 static inline int try_to_free_swap(struct page *page)
 {
@@ -526,6 +581,15 @@ static inline swp_entry_t get_swap_page(struct page *page)
 
 #endif /* CONFIG_SWAP */
 
+#ifdef CONFIG_THP_SWAP
+extern int split_swap_cluster(swp_entry_t entry);
+#else
+static inline int split_swap_cluster(swp_entry_t entry)
+{
+	return 0;
+}
+#endif
+
 #ifdef CONFIG_MEMCG
 static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg)
 {

include/linux/vm_event_item.h

@@ -85,6 +85,8 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 #endif
 		THP_ZERO_PAGE_ALLOC,
 		THP_ZERO_PAGE_ALLOC_FAILED,
+		THP_SWPOUT,
+		THP_SWPOUT_FALLBACK,
 #endif
 #ifdef CONFIG_MEMORY_BALLOON
 		BALLOON_INFLATE,
@@ -103,6 +105,10 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		VMACACHE_FIND_CALLS,
 		VMACACHE_FIND_HITS,
 		VMACACHE_FULL_FLUSHES,
+#endif
+#ifdef CONFIG_SWAP
+		SWAP_RA,
+		SWAP_RA_HIT,
 #endif
 		NR_VM_EVENT_ITEMS
 };

include/linux/vmstat.h

@@ -123,7 +123,7 @@ static inline void node_page_state_add(long x, struct pglist_data *pgdat,
 	atomic_long_add(x, &vm_node_stat[item]);
 }
 
-static inline unsigned long global_page_state(enum zone_stat_item item)
+static inline unsigned long global_zone_page_state(enum zone_stat_item item)
 {
 	long x = atomic_long_read(&vm_zone_stat[item]);
 #ifdef CONFIG_SMP
@@ -199,7 +199,7 @@ extern unsigned long sum_zone_node_page_state(int node,
 extern unsigned long node_page_state(struct pglist_data *pgdat,
 						enum node_stat_item item);
 #else
-#define sum_zone_node_page_state(node, item) global_page_state(item)
+#define sum_zone_node_page_state(node, item) global_zone_page_state(item)
 #define node_page_state(node, item) global_node_page_state(item)
 #endif /* CONFIG_NUMA */
 

include/trace/events/fs_dax.h

@@ -190,8 +190,6 @@ DEFINE_EVENT(dax_pte_fault_class, name, \
 
 DEFINE_PTE_FAULT_EVENT(dax_pte_fault);
 DEFINE_PTE_FAULT_EVENT(dax_pte_fault_done);
-DEFINE_PTE_FAULT_EVENT(dax_pfn_mkwrite_no_entry);
-DEFINE_PTE_FAULT_EVENT(dax_pfn_mkwrite);
 DEFINE_PTE_FAULT_EVENT(dax_load_hole);
 
 TRACE_EVENT(dax_insert_mapping,

include/trace/events/mmflags.h

@@ -125,12 +125,6 @@ IF_HAVE_PG_IDLE(PG_idle,		"idle"		)
 #define __VM_ARCH_SPECIFIC_1 {VM_ARCH_1,	"arch_1"	}
 #endif
 
-#if defined(CONFIG_X86)
-#define __VM_ARCH_SPECIFIC_2 {VM_MPX,		"mpx"		}
-#else
-#define __VM_ARCH_SPECIFIC_2 {VM_ARCH_2,	"arch_2"	}
-#endif
-
 #ifdef CONFIG_MEM_SOFT_DIRTY
 #define IF_HAVE_VM_SOFTDIRTY(flag,name) {flag, name },
 #else
@@ -162,7 +156,7 @@ IF_HAVE_PG_IDLE(PG_idle,		"idle"		)
 	{VM_NORESERVE,			"noreserve"	},		\
 	{VM_HUGETLB,			"hugetlb"	},		\
 	__VM_ARCH_SPECIFIC_1				,		\
-	__VM_ARCH_SPECIFIC_2				,		\
+	{VM_WIPEONFORK,			"wipeonfork"	},		\
 	{VM_DONTDUMP,			"dontdump"	},		\
 IF_HAVE_VM_SOFTDIRTY(VM_SOFTDIRTY,	"softdirty"	)		\
 	{VM_MIXEDMAP,			"mixedmap"	},		\

include/uapi/asm-generic/hugetlb_encode.h

@@ -0,0 +1,34 @@
+#ifndef _ASM_GENERIC_HUGETLB_ENCODE_H_
+#define _ASM_GENERIC_HUGETLB_ENCODE_H_
+
+/*
+ * Several system calls take a flag to request "hugetlb" huge pages.
+ * Without further specification, these system calls will use the
+ * system's default huge page size.  If a system supports multiple
+ * huge page sizes, the desired huge page size can be specified in
+ * bits [26:31] of the flag arguments.  The value in these 6 bits
+ * will encode the log2 of the huge page size.
+ *
+ * The following definitions are associated with this huge page size
+ * encoding in flag arguments.  System call specific header files
+ * that use this encoding should include this file.  They can then
+ * provide definitions based on these with their own specific prefix.
+ * for example:
+ * #define MAP_HUGE_SHIFT HUGETLB_FLAG_ENCODE_SHIFT
+ */
+
+#define HUGETLB_FLAG_ENCODE_SHIFT	26
+#define HUGETLB_FLAG_ENCODE_MASK	0x3f
+
+#define HUGETLB_FLAG_ENCODE_64KB	(16 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_512KB	(19 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_1MB		(20 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_2MB		(21 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_8MB		(23 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_16MB	(24 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_256MB	(28 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_1GB		(30 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_2GB		(31 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_16GB	(34 << HUGETLB_FLAG_ENCODE_SHIFT)
+
+#endif /* _ASM_GENERIC_HUGETLB_ENCODE_H_ */

include/uapi/asm-generic/mman-common.h

@@ -58,20 +58,12 @@
 					   overrides the coredump filter bits */
 #define MADV_DODUMP	17		/* Clear the MADV_DONTDUMP flag */
 
+#define MADV_WIPEONFORK 18		/* Zero memory on fork, child only */
+#define MADV_KEEPONFORK 19		/* Undo MADV_WIPEONFORK */
+
 /* compatibility flags */
 #define MAP_FILE	0
 
-/*
- * When MAP_HUGETLB is set bits [26:31] encode the log2 of the huge page size.
- * This gives us 6 bits, which is enough until someone invents 128 bit address
- * spaces.
- *
- * Assume these are all power of twos.
- * When 0 use the default page size.
- */
-#define MAP_HUGE_SHIFT	26
-#define MAP_HUGE_MASK	0x3f
-
 #define PKEY_DISABLE_ACCESS	0x1
 #define PKEY_DISABLE_WRITE	0x2
 #define PKEY_ACCESS_MASK	(PKEY_DISABLE_ACCESS |\

include/uapi/linux/memfd.h

@@ -1,8 +1,32 @@
 #ifndef _UAPI_LINUX_MEMFD_H
 #define _UAPI_LINUX_MEMFD_H
 
+#include <asm-generic/hugetlb_encode.h>
+
 /* flags for memfd_create(2) (unsigned int) */
 #define MFD_CLOEXEC		0x0001U
 #define MFD_ALLOW_SEALING	0x0002U
+#define MFD_HUGETLB		0x0004U
+
+/*
+ * Huge page size encoding when MFD_HUGETLB is specified, and a huge page
+ * size other than the default is desired.  See hugetlb_encode.h.
+ * All known huge page size encodings are provided here.  It is the
+ * responsibility of the application to know which sizes are supported on
+ * the running system.  See mmap(2) man page for details.
+ */
+#define MFD_HUGE_SHIFT	HUGETLB_FLAG_ENCODE_SHIFT
+#define MFD_HUGE_MASK	HUGETLB_FLAG_ENCODE_MASK
+
+#define MFD_HUGE_64KB	HUGETLB_FLAG_ENCODE_64KB
+#define MFD_HUGE_512KB	HUGETLB_FLAG_ENCODE_512KB
+#define MFD_HUGE_1MB	HUGETLB_FLAG_ENCODE_1MB
+#define MFD_HUGE_2MB	HUGETLB_FLAG_ENCODE_2MB
+#define MFD_HUGE_8MB	HUGETLB_FLAG_ENCODE_8MB
+#define MFD_HUGE_16MB	HUGETLB_FLAG_ENCODE_16MB
+#define MFD_HUGE_256MB	HUGETLB_FLAG_ENCODE_256MB
+#define MFD_HUGE_1GB	HUGETLB_FLAG_ENCODE_1GB
+#define MFD_HUGE_2GB	HUGETLB_FLAG_ENCODE_2GB
+#define MFD_HUGE_16GB	HUGETLB_FLAG_ENCODE_16GB
 
 #endif /* _UAPI_LINUX_MEMFD_H */

include/uapi/linux/mman.h

@@ -2,6 +2,7 @@
 #define _UAPI_LINUX_MMAN_H
 
 #include <asm/mman.h>
+#include <asm-generic/hugetlb_encode.h>
 
 #define MREMAP_MAYMOVE	1
 #define MREMAP_FIXED	2
@@ -10,4 +11,25 @@
 #define OVERCOMMIT_ALWAYS		1
 #define OVERCOMMIT_NEVER		2
 
+/*
+ * Huge page size encoding when MAP_HUGETLB is specified, and a huge page
+ * size other than the default is desired.  See hugetlb_encode.h.
+ * All known huge page size encodings are provided here.  It is the
+ * responsibility of the application to know which sizes are supported on
+ * the running system.  See mmap(2) man page for details.
+ */
+#define MAP_HUGE_SHIFT	HUGETLB_FLAG_ENCODE_SHIFT
+#define MAP_HUGE_MASK	HUGETLB_FLAG_ENCODE_MASK
+
+#define MAP_HUGE_64KB	HUGETLB_FLAG_ENCODE_64KB
+#define MAP_HUGE_512KB	HUGETLB_FLAG_ENCODE_512KB
+#define MAP_HUGE_1MB	HUGETLB_FLAG_ENCODE_1MB
+#define MAP_HUGE_2MB	HUGETLB_FLAG_ENCODE_2MB
+#define MAP_HUGE_8MB	HUGETLB_FLAG_ENCODE_8MB
+#define MAP_HUGE_16MB	HUGETLB_FLAG_ENCODE_16MB
+#define MAP_HUGE_256MB	HUGETLB_FLAG_ENCODE_256MB
+#define MAP_HUGE_1GB	HUGETLB_FLAG_ENCODE_1GB
+#define MAP_HUGE_2GB	HUGETLB_FLAG_ENCODE_2GB
+#define MAP_HUGE_16GB	HUGETLB_FLAG_ENCODE_16GB
+
 #endif /* _UAPI_LINUX_MMAN_H */

include/uapi/linux/shm.h

@@ -3,6 +3,7 @@
 
 #include <linux/ipc.h>
 #include <linux/errno.h>
+#include <asm-generic/hugetlb_encode.h>
 #ifndef __KERNEL__
 #include <unistd.h>
 #endif
@@ -40,11 +41,37 @@ struct shmid_ds {
 /* Include the definition of shmid64_ds and shminfo64 */
 #include <asm/shmbuf.h>
 
-/* permission flag for shmget */
+/*
+ * shmget() shmflg values.
+ */
+/* The bottom nine bits are the same as open(2) mode flags */
 #define SHM_R		0400	/* or S_IRUGO from <linux/stat.h> */
 #define SHM_W		0200	/* or S_IWUGO from <linux/stat.h> */
+/* Bits 9 & 10 are IPC_CREAT and IPC_EXCL */
+#define SHM_HUGETLB	04000	/* segment will use huge TLB pages */
+#define SHM_NORESERVE	010000	/* don't check for reservations */
+
+/*
+ * Huge page size encoding when SHM_HUGETLB is specified, and a huge page
+ * size other than the default is desired.  See hugetlb_encode.h
+ */
+#define SHM_HUGE_SHIFT	HUGETLB_FLAG_ENCODE_SHIFT
+#define SHM_HUGE_MASK	HUGETLB_FLAG_ENCODE_MASK
+
+#define SHM_HUGE_64KB	HUGETLB_FLAG_ENCODE_64KB
+#define SHM_HUGE_512KB	HUGETLB_FLAG_ENCODE_512KB
+#define SHM_HUGE_1MB	HUGETLB_FLAG_ENCODE_1MB
+#define SHM_HUGE_2MB	HUGETLB_FLAG_ENCODE_2MB
+#define SHM_HUGE_8MB	HUGETLB_FLAG_ENCODE_8MB
+#define SHM_HUGE_16MB	HUGETLB_FLAG_ENCODE_16MB
+#define SHM_HUGE_256MB	HUGETLB_FLAG_ENCODE_256MB
+#define SHM_HUGE_1GB	HUGETLB_FLAG_ENCODE_1GB
+#define SHM_HUGE_2GB	HUGETLB_FLAG_ENCODE_2GB
+#define SHM_HUGE_16GB	HUGETLB_FLAG_ENCODE_16GB
 
-/* mode for attach */
+/*
+ * shmat() shmflg values
+ */
 #define	SHM_RDONLY	010000	/* read-only access */
 #define	SHM_RND		020000	/* round attach address to SHMLBA boundary */
 #define	SHM_REMAP	040000	/* take-over region on attach */

include/uapi/linux/userfaultfd.h

@@ -23,7 +23,9 @@
 			   UFFD_FEATURE_EVENT_REMOVE |	\
 			   UFFD_FEATURE_EVENT_UNMAP |		\
 			   UFFD_FEATURE_MISSING_HUGETLBFS |	\
-			   UFFD_FEATURE_MISSING_SHMEM)
+			   UFFD_FEATURE_MISSING_SHMEM |		\
+			   UFFD_FEATURE_SIGBUS |		\
+			   UFFD_FEATURE_THREAD_ID)
 #define UFFD_API_IOCTLS				\
 	((__u64)1 << _UFFDIO_REGISTER |		\
 	 (__u64)1 << _UFFDIO_UNREGISTER |	\
@@ -78,6 +80,9 @@ struct uffd_msg {
 		struct {
 			__u64	flags;
 			__u64	address;
+			union {
+				__u32 ptid;
+			} feat;
 		} pagefault;
 
 		struct {
@@ -153,6 +158,13 @@ struct uffdio_api {
 	 * UFFD_FEATURE_MISSING_SHMEM works the same as
 	 * UFFD_FEATURE_MISSING_HUGETLBFS, but it applies to shmem
 	 * (i.e. tmpfs and other shmem based APIs).
+	 *
+	 * UFFD_FEATURE_SIGBUS feature means no page-fault
+	 * (UFFD_EVENT_PAGEFAULT) event will be delivered, instead
+	 * a SIGBUS signal will be sent to the faulting process.
+	 *
+	 * UFFD_FEATURE_THREAD_ID pid of the page faulted task_struct will
+	 * be returned, if feature is not requested 0 will be returned.
 	 */
 #define UFFD_FEATURE_PAGEFAULT_FLAG_WP		(1<<0)
 #define UFFD_FEATURE_EVENT_FORK			(1<<1)
@@ -161,6 +173,8 @@ struct uffdio_api {
 #define UFFD_FEATURE_MISSING_HUGETLBFS		(1<<4)
 #define UFFD_FEATURE_MISSING_SHMEM		(1<<5)
 #define UFFD_FEATURE_EVENT_UNMAP		(1<<6)
+#define UFFD_FEATURE_SIGBUS			(1<<7)
+#define UFFD_FEATURE_THREAD_ID			(1<<8)
 	__u64 features;
 
 	__u64 ioctls;

init/Kconfig

@@ -1576,6 +1576,15 @@ config SLAB_FREELIST_RANDOM
 	  security feature reduces the predictability of the kernel slab
 	  allocator against heap overflows.
 
+config SLAB_FREELIST_HARDENED
+	bool "Harden slab freelist metadata"
+	depends on SLUB
+	help
+	  Many kernel heap attacks try to target slab cache metadata and
+	  other infrastructure. This options makes minor performance
+	  sacrifies to harden the kernel slab allocator against common
+	  freelist exploit methods.
+
 config SLUB_CPU_PARTIAL
 	default y
 	depends on SLUB && SMP

init/main.c

@@ -542,7 +542,7 @@ asmlinkage __visible void __init start_kernel(void)
 	boot_cpu_state_init();
 	smp_prepare_boot_cpu();	/* arch-specific boot-cpu hooks */
 
-	build_all_zonelists(NULL, NULL);
+	build_all_zonelists(NULL);
 	page_alloc_init();
 
 	pr_notice("Kernel command line: %s\n", boot_command_line);

kernel/cgroup/cgroup.c

@@ -4100,9 +4100,6 @@ static void offline_css(struct cgroup_subsys_state *css)
 	if (!(css->flags & CSS_ONLINE))
 		return;
 
-	if (ss->css_reset)
-		ss->css_reset(css);
-
 	if (ss->css_offline)
 		ss->css_offline(css);
 

kernel/cgroup/cpuset.c

@@ -56,6 +56,7 @@
 #include <linux/time64.h>
 #include <linux/backing-dev.h>
 #include <linux/sort.h>
+#include <linux/oom.h>
 
 #include <linux/uaccess.h>
 #include <linux/atomic.h>
@@ -2500,12 +2501,12 @@ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs)
  * If we're in interrupt, yes, we can always allocate.  If @node is set in
  * current's mems_allowed, yes.  If it's not a __GFP_HARDWALL request and this
  * node is set in the nearest hardwalled cpuset ancestor to current's cpuset,
- * yes.  If current has access to memory reserves due to TIF_MEMDIE, yes.
+ * yes.  If current has access to memory reserves as an oom victim, yes.
  * Otherwise, no.
  *
  * GFP_USER allocations are marked with the __GFP_HARDWALL bit,
  * and do not allow allocations outside the current tasks cpuset
- * unless the task has been OOM killed as is marked TIF_MEMDIE.
+ * unless the task has been OOM killed.
  * GFP_KERNEL allocations are not so marked, so can escape to the
  * nearest enclosing hardwalled ancestor cpuset.
  *
@@ -2528,7 +2529,7 @@ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs)
  * affect that:
  *	in_interrupt - any node ok (current task context irrelevant)
  *	GFP_ATOMIC   - any node ok
- *	TIF_MEMDIE   - any node ok
+ *	tsk_is_oom_victim   - any node ok
  *	GFP_KERNEL   - any node in enclosing hardwalled cpuset ok
  *	GFP_USER     - only nodes in current tasks mems allowed ok.
  */
@@ -2546,7 +2547,7 @@ bool __cpuset_node_allowed(int node, gfp_t gfp_mask)
 	 * Allow tasks that have access to memory reserves because they have
 	 * been OOM killed to get memory anywhere.
 	 */
-	if (unlikely(test_thread_flag(TIF_MEMDIE)))
+	if (unlikely(tsk_is_oom_victim(current)))
 		return true;
 	if (gfp_mask & __GFP_HARDWALL)	/* If hardwall request, stop here */
 		return false;

kernel/fork.c

@@ -657,7 +657,12 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 		retval = dup_userfaultfd(tmp, &uf);
 		if (retval)
 			goto fail_nomem_anon_vma_fork;
-		if (anon_vma_fork(tmp, mpnt))
+		if (tmp->vm_flags & VM_WIPEONFORK) {
+			/* VM_WIPEONFORK gets a clean slate in the child. */
+			tmp->anon_vma = NULL;
+			if (anon_vma_prepare(tmp))
+				goto fail_nomem_anon_vma_fork;
+		} else if (anon_vma_fork(tmp, mpnt))
 			goto fail_nomem_anon_vma_fork;
 		tmp->vm_flags &= ~(VM_LOCKED | VM_LOCKONFAULT);
 		tmp->vm_next = tmp->vm_prev = NULL;
@@ -701,7 +706,8 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 		rb_parent = &tmp->vm_rb;
 
 		mm->map_count++;
-		retval = copy_page_range(mm, oldmm, mpnt);
+		if (!(tmp->vm_flags & VM_WIPEONFORK))
+			retval = copy_page_range(mm, oldmm, mpnt);
 
 		if (tmp->vm_ops && tmp->vm_ops->open)
 			tmp->vm_ops->open(tmp);
@@ -922,7 +928,6 @@ static inline void __mmput(struct mm_struct *mm)
 	}
 	if (mm->binfmt)
 		module_put(mm->binfmt->module);
-	set_bit(MMF_OOM_SKIP, &mm->flags);
 	mmdrop(mm);
 }
 
@@ -938,22 +943,6 @@ void mmput(struct mm_struct *mm)
 }
 EXPORT_SYMBOL_GPL(mmput);
 
-#ifdef CONFIG_MMU
-static void mmput_async_fn(struct work_struct *work)
-{
-	struct mm_struct *mm = container_of(work, struct mm_struct, async_put_work);
-	__mmput(mm);
-}
-
-void mmput_async(struct mm_struct *mm)
-{
-	if (atomic_dec_and_test(&mm->mm_users)) {
-		INIT_WORK(&mm->async_put_work, mmput_async_fn);
-		schedule_work(&mm->async_put_work);
-	}
-}
-#endif
-
 /**
  * set_mm_exe_file - change a reference to the mm's executable file
  *

kernel/memremap.c

@@ -194,18 +194,41 @@ struct page_map {
 	struct vmem_altmap altmap;
 };
 
-static void pgmap_radix_release(struct resource *res)
+static unsigned long order_at(struct resource *res, unsigned long pgoff)
 {
-	resource_size_t key, align_start, align_size, align_end;
+	unsigned long phys_pgoff = PHYS_PFN(res->start) + pgoff;
+	unsigned long nr_pages, mask;
 
-	align_start = res->start & ~(SECTION_SIZE - 1);
-	align_size = ALIGN(resource_size(res), SECTION_SIZE);
-	align_end = align_start + align_size - 1;
+	nr_pages = PHYS_PFN(resource_size(res));
+	if (nr_pages == pgoff)
+		return ULONG_MAX;
+
+	/*
+	 * What is the largest aligned power-of-2 range available from
+	 * this resource pgoff to the end of the resource range,
+	 * considering the alignment of the current pgoff?
+	 */
+	mask = phys_pgoff | rounddown_pow_of_two(nr_pages - pgoff);
+	if (!mask)
+		return ULONG_MAX;
+
+	return find_first_bit(&mask, BITS_PER_LONG);
+}
+
+#define foreach_order_pgoff(res, order, pgoff) \
+	for (pgoff = 0, order = order_at((res), pgoff); order < ULONG_MAX; \
+			pgoff += 1UL << order, order = order_at((res), pgoff))
+
+static void pgmap_radix_release(struct resource *res)
+{
+	unsigned long pgoff, order;
 
 	mutex_lock(&pgmap_lock);
-	for (key = res->start; key <= res->end; key += SECTION_SIZE)
-		radix_tree_delete(&pgmap_radix, key >> PA_SECTION_SHIFT);
+	foreach_order_pgoff(res, order, pgoff)
+		radix_tree_delete(&pgmap_radix, PHYS_PFN(res->start) + pgoff);
 	mutex_unlock(&pgmap_lock);
+
+	synchronize_rcu();
 }
 
 static unsigned long pfn_first(struct page_map *page_map)
@@ -268,7 +291,7 @@ struct dev_pagemap *find_dev_pagemap(resource_size_t phys)
 
 	WARN_ON_ONCE(!rcu_read_lock_held());
 
-	page_map = radix_tree_lookup(&pgmap_radix, phys >> PA_SECTION_SHIFT);
+	page_map = radix_tree_lookup(&pgmap_radix, PHYS_PFN(phys));
 	return page_map ? &page_map->pgmap : NULL;
 }
 
@@ -293,12 +316,12 @@ struct dev_pagemap *find_dev_pagemap(resource_size_t phys)
 void *devm_memremap_pages(struct device *dev, struct resource *res,
 		struct percpu_ref *ref, struct vmem_altmap *altmap)
 {
-	resource_size_t key, align_start, align_size, align_end;
+	resource_size_t align_start, align_size, align_end;
+	unsigned long pfn, pgoff, order;
 	pgprot_t pgprot = PAGE_KERNEL;
 	struct dev_pagemap *pgmap;
 	struct page_map *page_map;
 	int error, nid, is_ram;
-	unsigned long pfn;
 
 	align_start = res->start & ~(SECTION_SIZE - 1);
 	align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE)
@@ -337,11 +360,12 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 	mutex_lock(&pgmap_lock);
 	error = 0;
 	align_end = align_start + align_size - 1;
-	for (key = align_start; key <= align_end; key += SECTION_SIZE) {
+
+	foreach_order_pgoff(res, order, pgoff) {
 		struct dev_pagemap *dup;
 
 		rcu_read_lock();
-		dup = find_dev_pagemap(key);
+		dup = find_dev_pagemap(res->start + PFN_PHYS(pgoff));
 		rcu_read_unlock();
 		if (dup) {
 			dev_err(dev, "%s: %pr collides with mapping for %s\n",
@@ -349,8 +373,8 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 			error = -EBUSY;
 			break;
 		}
-		error = radix_tree_insert(&pgmap_radix, key >> PA_SECTION_SHIFT,
-				page_map);
+		error = __radix_tree_insert(&pgmap_radix,
+				PHYS_PFN(res->start) + pgoff, order, page_map);
 		if (error) {
 			dev_err(dev, "%s: failed: %d\n", __func__, error);
 			break;

mm/Kconfig

@@ -678,6 +678,7 @@ config ZONE_DEVICE
 	depends on MEMORY_HOTREMOVE
 	depends on SPARSEMEM_VMEMMAP
 	depends on ARCH_HAS_ZONE_DEVICE
+	select RADIX_TREE_MULTIORDER
 
 	help
 	  Device memory hotplug support allows for establishing pmem,