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;
 }