Fixed MTP to work with TWRP

mm/Kconfig

@@ -0,0 +1,695 @@
+config SELECT_MEMORY_MODEL
+	def_bool y
+	depends on ARCH_SELECT_MEMORY_MODEL
+
+choice
+	prompt "Memory model"
+	depends on SELECT_MEMORY_MODEL
+	default DISCONTIGMEM_MANUAL if ARCH_DISCONTIGMEM_DEFAULT
+	default SPARSEMEM_MANUAL if ARCH_SPARSEMEM_DEFAULT
+	default FLATMEM_MANUAL
+
+config FLATMEM_MANUAL
+	bool "Flat Memory"
+	depends on !(ARCH_DISCONTIGMEM_ENABLE || ARCH_SPARSEMEM_ENABLE) || ARCH_FLATMEM_ENABLE
+	help
+	  This option allows you to change some of the ways that
+	  Linux manages its memory internally.  Most users will
+	  only have one option here: FLATMEM.  This is normal
+	  and a correct option.
+
+	  Some users of more advanced features like NUMA and
+	  memory hotplug may have different options here.
+	  DISCONTIGMEM is a more mature, better tested system,
+	  but is incompatible with memory hotplug and may suffer
+	  decreased performance over SPARSEMEM.  If unsure between
+	  "Sparse Memory" and "Discontiguous Memory", choose
+	  "Discontiguous Memory".
+
+	  If unsure, choose this option (Flat Memory) over any other.
+
+config DISCONTIGMEM_MANUAL
+	bool "Discontiguous Memory"
+	depends on ARCH_DISCONTIGMEM_ENABLE
+	help
+	  This option provides enhanced support for discontiguous
+	  memory systems, over FLATMEM.  These systems have holes
+	  in their physical address spaces, and this option provides
+	  more efficient handling of these holes.  However, the vast
+	  majority of hardware has quite flat address spaces, and
+	  can have degraded performance from the extra overhead that
+	  this option imposes.
+
+	  Many NUMA configurations will have this as the only option.
+
+	  If unsure, choose "Flat Memory" over this option.
+
+config SPARSEMEM_MANUAL
+	bool "Sparse Memory"
+	depends on ARCH_SPARSEMEM_ENABLE
+	help
+	  This will be the only option for some systems, including
+	  memory hotplug systems.  This is normal.
+
+	  For many other systems, this will be an alternative to
+	  "Discontiguous Memory".  This option provides some potential
+	  performance benefits, along with decreased code complexity,
+	  but it is newer, and more experimental.
+
+	  If unsure, choose "Discontiguous Memory" or "Flat Memory"
+	  over this option.
+
+endchoice
+
+config DISCONTIGMEM
+	def_bool y
+	depends on (!SELECT_MEMORY_MODEL && ARCH_DISCONTIGMEM_ENABLE) || DISCONTIGMEM_MANUAL
+
+config SPARSEMEM
+	def_bool y
+	depends on (!SELECT_MEMORY_MODEL && ARCH_SPARSEMEM_ENABLE) || SPARSEMEM_MANUAL
+
+config FLATMEM
+	def_bool y
+	depends on (!DISCONTIGMEM && !SPARSEMEM) || FLATMEM_MANUAL
+
+config FLAT_NODE_MEM_MAP
+	def_bool y
+	depends on !SPARSEMEM
+
+#
+# Both the NUMA code and DISCONTIGMEM use arrays of pg_data_t's
+# to represent different areas of memory.  This variable allows
+# those dependencies to exist individually.
+#
+config NEED_MULTIPLE_NODES
+	def_bool y
+	depends on DISCONTIGMEM || NUMA
+
+config HAVE_MEMORY_PRESENT
+	def_bool y
+	depends on ARCH_HAVE_MEMORY_PRESENT || SPARSEMEM
+
+#
+# SPARSEMEM_EXTREME (which is the default) does some bootmem
+# allocations when memory_present() is called.  If this cannot
+# be done on your architecture, select this option.  However,
+# statically allocating the mem_section[] array can potentially
+# consume vast quantities of .bss, so be careful.
+#
+# This option will also potentially produce smaller runtime code
+# with gcc 3.4 and later.
+#
+config SPARSEMEM_STATIC
+	bool
+
+#
+# Architecture platforms which require a two level mem_section in SPARSEMEM
+# must select this option. This is usually for architecture platforms with
+# an extremely sparse physical address space.
+#
+config SPARSEMEM_EXTREME
+	def_bool y
+	depends on SPARSEMEM && !SPARSEMEM_STATIC
+
+config SPARSEMEM_VMEMMAP_ENABLE
+	bool
+
+config SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
+	def_bool y
+	depends on SPARSEMEM && X86_64
+
+config SPARSEMEM_VMEMMAP
+	bool "Sparse Memory virtual memmap"
+	depends on SPARSEMEM && SPARSEMEM_VMEMMAP_ENABLE
+	default y
+	help
+	 SPARSEMEM_VMEMMAP uses a virtually mapped memmap to optimise
+	 pfn_to_page and page_to_pfn operations.  This is the most
+	 efficient option when sufficient kernel resources are available.
+
+config HAVE_MEMBLOCK
+	boolean
+
+config HAVE_MEMBLOCK_NODE_MAP
+	boolean
+
+config HAVE_MEMBLOCK_PHYS_MAP
+	boolean
+
+config HAVE_GENERIC_RCU_GUP
+	boolean
+
+config ARCH_DISCARD_MEMBLOCK
+	boolean
+
+config NO_BOOTMEM
+	boolean
+
+config MEMORY_ISOLATION
+	boolean
+
+config MOVABLE_NODE
+	boolean "Enable to assign a node which has only movable memory"
+	depends on HAVE_MEMBLOCK
+	depends on NO_BOOTMEM
+	depends on X86_64
+	depends on NUMA
+	default n
+	help
+	  Allow a node to have only movable memory.  Pages used by the kernel,
+	  such as direct mapping pages cannot be migrated.  So the corresponding
+	  memory device cannot be hotplugged.  This option allows the following
+	  two things:
+	  - When the system is booting, node full of hotpluggable memory can
+	  be arranged to have only movable memory so that the whole node can
+	  be hot-removed. (need movable_node boot option specified).
+	  - After the system is up, the option allows users to online all the
+	  memory of a node as movable memory so that the whole node can be
+	  hot-removed.
+
+	  Users who don't use the memory hotplug feature are fine with this
+	  option on since they don't specify movable_node boot option or they
+	  don't online memory as movable.
+
+	  Say Y here if you want to hotplug a whole node.
+	  Say N here if you want kernel to use memory on all nodes evenly.
+
+#
+# Only be set on architectures that have completely implemented memory hotplug
+# feature. If you are not sure, don't touch it.
+#
+config HAVE_BOOTMEM_INFO_NODE
+	def_bool n
+
+# eventually, we can have this option just 'select SPARSEMEM'
+config MEMORY_HOTPLUG
+	bool "Allow for memory hot-add"
+	depends on SPARSEMEM || X86_64_ACPI_NUMA
+	depends on ARCH_ENABLE_MEMORY_HOTPLUG
+	depends on (IA64 || X86 || PPC_BOOK3S_64 || SUPERH || S390)
+
+config MEMORY_HOTPLUG_SPARSE
+	def_bool y
+	depends on SPARSEMEM && MEMORY_HOTPLUG
+
+config MEMORY_HOTREMOVE
+	bool "Allow for memory hot remove"
+	select MEMORY_ISOLATION
+	select HAVE_BOOTMEM_INFO_NODE if (X86_64 || PPC64)
+	depends on MEMORY_HOTPLUG && ARCH_ENABLE_MEMORY_HOTREMOVE
+	depends on MIGRATION
+
+#
+# If we have space for more page flags then we can enable additional
+# optimizations and functionality.
+#
+# Regular Sparsemem takes page flag bits for the sectionid if it does not
+# use a virtual memmap. Disable extended page flags for 32 bit platforms
+# that require the use of a sectionid in the page flags.
+#
+config PAGEFLAGS_EXTENDED
+	def_bool y
+	depends on 64BIT || SPARSEMEM_VMEMMAP || !SPARSEMEM
+
+# Heavily threaded applications may benefit from splitting the mm-wide
+# page_table_lock, so that faults on different parts of the user address
+# space can be handled with less contention: split it at this NR_CPUS.
+# Default to 4 for wider testing, though 8 might be more appropriate.
+# ARM's adjust_pte (unused if VIPT) depends on mm-wide page_table_lock.
+# PA-RISC 7xxx's spinlock_t would enlarge struct page from 32 to 44 bytes.
+# DEBUG_SPINLOCK and DEBUG_LOCK_ALLOC spinlock_t also enlarge struct page.
+#
+config SPLIT_PTLOCK_CPUS
+	int
+	default "999999" if !MMU
+	default "999999" if ARM && !CPU_CACHE_VIPT
+	default "999999" if PARISC && !PA20
+	default "4"
+
+config ARCH_ENABLE_SPLIT_PMD_PTLOCK
+	boolean
+
+#
+# support for memory balloon
+config MEMORY_BALLOON
+	boolean
+
+#
+# support for memory balloon compaction
+config BALLOON_COMPACTION
+	bool "Allow for balloon memory compaction/migration"
+	def_bool y
+	depends on COMPACTION && MEMORY_BALLOON
+	help
+	  Memory fragmentation introduced by ballooning might reduce
+	  significantly the number of 2MB contiguous memory blocks that can be
+	  used within a guest, thus imposing performance penalties associated
+	  with the reduced number of transparent huge pages that could be used
+	  by the guest workload. Allowing the compaction & migration for memory
+	  pages enlisted as being part of memory balloon devices avoids the
+	  scenario aforementioned and helps improving memory defragmentation.
+
+#
+# support for memory compaction
+config COMPACTION
+	bool "Allow for memory compaction"
+	def_bool y
+	select MIGRATION
+	depends on MMU
+	help
+	  Allows the compaction of memory for the allocation of huge pages.
+
+#
+# support for page migration
+#
+config MIGRATION
+	bool "Page migration"
+	def_bool y
+	depends on (NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE || COMPACTION || CMA) && MMU
+	help
+	  Allows the migration of the physical location of pages of processes
+	  while the virtual addresses are not changed. This is useful in
+	  two situations. The first is on NUMA systems to put pages nearer
+	  to the processors accessing. The second is when allocating huge
+	  pages as migration can relocate pages to satisfy a huge page
+	  allocation instead of reclaiming.
+
+config ARCH_ENABLE_HUGEPAGE_MIGRATION
+	boolean
+
+config PHYS_ADDR_T_64BIT
+	def_bool 64BIT || ARCH_PHYS_ADDR_T_64BIT
+
+config ZONE_DMA_FLAG
+	int
+	default "0" if !ZONE_DMA
+	default "1"
+
+config BOUNCE
+	bool "Enable bounce buffers"
+	default y
+	depends on BLOCK && MMU && (ZONE_DMA || HIGHMEM)
+	help
+	  Enable bounce buffers for devices that cannot access
+	  the full range of memory available to the CPU. Enabled
+	  by default when ZONE_DMA or HIGHMEM is selected, but you
+	  may say n to override this.
+
+# On the 'tile' arch, USB OHCI needs the bounce pool since tilegx will often
+# have more than 4GB of memory, but we don't currently use the IOTLB to present
+# a 32-bit address to OHCI.  So we need to use a bounce pool instead.
+#
+# We also use the bounce pool to provide stable page writes for jbd.  jbd
+# initiates buffer writeback without locking the page or setting PG_writeback,
+# and fixing that behavior (a second time; jbd2 doesn't have this problem) is
+# a major rework effort.  Instead, use the bounce buffer to snapshot pages
+# (until jbd goes away).  The only jbd user is ext3.
+config NEED_BOUNCE_POOL
+	bool
+	default y if (TILE && USB_OHCI_HCD) || (BLK_DEV_INTEGRITY && JBD)
+
+config NR_QUICK
+	int
+	depends on QUICKLIST
+	default "2" if AVR32
+	default "1"
+
+config VIRT_TO_BUS
+	bool
+	help
+	  An architecture should select this if it implements the
+	  deprecated interface virt_to_bus().  All new architectures
+	  should probably not select this.
+
+
+config MMU_NOTIFIER
+	bool
+
+config KSM
+	bool "Enable KSM for page merging"
+	depends on MMU
+	help
+	  Enable Kernel Samepage Merging: KSM periodically scans those areas
+	  of an application's address space that an app has advised may be
+	  mergeable.  When it finds pages of identical content, it replaces
+	  the many instances by a single page with that content, so
+	  saving memory until one or another app needs to modify the content.
+	  Recommended for use with KVM, or with other duplicative applications.
+	  See Documentation/vm/ksm.txt for more information: KSM is inactive
+	  until a program has madvised that an area is MADV_MERGEABLE, and
+	  root has set /sys/kernel/mm/ksm/run to 1 (if CONFIG_SYSFS is set).
+
+config DEFAULT_MMAP_MIN_ADDR
+        int "Low address space to protect from user allocation"
+	depends on MMU
+        default 4096
+        help
+	  This is the portion of low virtual memory which should be protected
+	  from userspace allocation.  Keeping a user from writing to low pages
+	  can help reduce the impact of kernel NULL pointer bugs.
+
+	  For most ia64, ppc64 and x86 users with lots of address space
+	  a value of 65536 is reasonable and should cause no problems.
+	  On arm and other archs it should not be higher than 32768.
+	  Programs which use vm86 functionality or have some need to map
+	  this low address space will need CAP_SYS_RAWIO or disable this
+	  protection by setting the value to 0.
+
+	  This value can be changed after boot using the
+	  /proc/sys/vm/mmap_min_addr tunable.
+
+config ARCH_SUPPORTS_MEMORY_FAILURE
+	bool
+
+config MEMORY_FAILURE
+	depends on MMU
+	depends on ARCH_SUPPORTS_MEMORY_FAILURE
+	bool "Enable recovery from hardware memory errors"
+	select MEMORY_ISOLATION
+	help
+	  Enables code to recover from some memory failures on systems
+	  with MCA recovery. This allows a system to continue running
+	  even when some of its memory has uncorrected errors. This requires
+	  special hardware support and typically ECC memory.
+
+config HWPOISON_INJECT
+	tristate "HWPoison pages injector"
+	depends on MEMORY_FAILURE && DEBUG_KERNEL && PROC_FS
+	select PROC_PAGE_MONITOR
+
+config NOMMU_INITIAL_TRIM_EXCESS
+	int "Turn on mmap() excess space trimming before booting"
+	depends on !MMU
+	default 1
+	help
+	  The NOMMU mmap() frequently needs to allocate large contiguous chunks
+	  of memory on which to store mappings, but it can only ask the system
+	  allocator for chunks in 2^N*PAGE_SIZE amounts - which is frequently
+	  more than it requires.  To deal with this, mmap() is able to trim off
+	  the excess and return it to the allocator.
+
+	  If trimming is enabled, the excess is trimmed off and returned to the
+	  system allocator, which can cause extra fragmentation, particularly
+	  if there are a lot of transient processes.
+
+	  If trimming is disabled, the excess is kept, but not used, which for
+	  long-term mappings means that the space is wasted.
+
+	  Trimming can be dynamically controlled through a sysctl option
+	  (/proc/sys/vm/nr_trim_pages) which specifies the minimum number of
+	  excess pages there must be before trimming should occur, or zero if
+	  no trimming is to occur.
+
+	  This option specifies the initial value of this option.  The default
+	  of 1 says that all excess pages should be trimmed.
+
+	  See Documentation/nommu-mmap.txt for more information.
+
+config TRANSPARENT_HUGEPAGE
+	bool "Transparent Hugepage Support"
+	depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE
+	select COMPACTION
+	help
+	  Transparent Hugepages allows the kernel to use huge pages and
+	  huge tlb transparently to the applications whenever possible.
+	  This feature can improve computing performance to certain
+	  applications by speeding up page faults during memory
+	  allocation, by reducing the number of tlb misses and by speeding
+	  up the pagetable walking.
+
+	  If memory constrained on embedded, you may want to say N.
+
+choice
+	prompt "Transparent Hugepage Support sysfs defaults"
+	depends on TRANSPARENT_HUGEPAGE
+	default TRANSPARENT_HUGEPAGE_ALWAYS
+	help
+	  Selects the sysfs defaults for Transparent Hugepage Support.
+
+	config TRANSPARENT_HUGEPAGE_ALWAYS
+		bool "always"
+	help
+	  Enabling Transparent Hugepage always, can increase the
+	  memory footprint of applications without a guaranteed
+	  benefit but it will work automatically for all applications.
+
+	config TRANSPARENT_HUGEPAGE_MADVISE
+		bool "madvise"
+	help
+	  Enabling Transparent Hugepage madvise, will only provide a
+	  performance improvement benefit to the applications using
+	  madvise(MADV_HUGEPAGE) but it won't risk to increase the
+	  memory footprint of applications without a guaranteed
+	  benefit.
+endchoice
+
+#
+# UP and nommu archs use km based percpu allocator
+#
+config NEED_PER_CPU_KM
+	depends on !SMP
+	bool
+	default y
+
+config CLEANCACHE
+	bool "Enable cleancache driver to cache clean pages if tmem is present"
+	default n
+	help
+	  Cleancache can be thought of as a page-granularity victim cache
+	  for clean pages that the kernel's pageframe replacement algorithm
+	  (PFRA) would like to keep around, but can't since there isn't enough
+	  memory.  So when the PFRA "evicts" a page, it first attempts to use
+	  cleancache code to put the data contained in that page into
+	  "transcendent memory", memory that is not directly accessible or
+	  addressable by the kernel and is of unknown and possibly
+	  time-varying size.  And when a cleancache-enabled
+	  filesystem wishes to access a page in a file on disk, it first
+	  checks cleancache to see if it already contains it; if it does,
+	  the page is copied into the kernel and a disk access is avoided.
+	  When a transcendent memory driver is available (such as zcache or
+	  Xen transcendent memory), a significant I/O reduction
+	  may be achieved.  When none is available, all cleancache calls
+	  are reduced to a single pointer-compare-against-NULL resulting
+	  in a negligible performance hit.
+
+	  If unsure, say Y to enable cleancache
+
+config FRONTSWAP
+	bool "Enable frontswap to cache swap pages if tmem is present"
+	depends on SWAP
+	default n
+	help
+	  Frontswap is so named because it can be thought of as the opposite
+	  of a "backing" store for a swap device.  The data is stored into
+	  "transcendent memory", memory that is not directly accessible or
+	  addressable by the kernel and is of unknown and possibly
+	  time-varying size.  When space in transcendent memory is available,
+	  a significant swap I/O reduction may be achieved.  When none is
+	  available, all frontswap calls are reduced to a single pointer-
+	  compare-against-NULL resulting in a negligible performance hit
+	  and swap data is stored as normal on the matching swap device.
+
+	  If unsure, say Y to enable frontswap.
+
+config CMA
+	bool "Contiguous Memory Allocator"
+	depends on HAVE_MEMBLOCK && MMU
+	select MIGRATION
+	select MEMORY_ISOLATION
+	help
+	  This enables the Contiguous Memory Allocator which allows other
+	  subsystems to allocate big physically-contiguous blocks of memory.
+	  CMA reserves a region of memory and allows only movable pages to
+	  be allocated from it. This way, the kernel can use the memory for
+	  pagecache and when a subsystem requests for contiguous area, the
+	  allocated pages are migrated away to serve the contiguous request.
+
+	  If unsure, say "n".
+
+config CMA_DEBUG
+	bool "CMA debug messages (DEVELOPMENT)"
+	depends on DEBUG_KERNEL && CMA
+	help
+	  Turns on debug messages in CMA.  This produces KERN_DEBUG
+	  messages for every CMA call as well as various messages while
+	  processing calls such as dma_alloc_from_contiguous().
+	  This option does not affect warning and error messages.
+
+config CMA_PINPAGE_MIGRATION
+	bool "CMA pinned page migration (EXPERIMENTAL)"
+	depends on CMA
+	default n
+	help
+	  Turns on cma page migration for pinned page.
+
+config CMA_AREAS
+	int "Maximum count of the CMA areas"
+	depends on CMA
+	default 7
+	help
+	  CMA allows to create CMA areas for particular purpose, mainly,
+	  used as device private area. This parameter sets the maximum
+	  number of CMA area in the system.
+
+	  If unsure, leave the default value "7".
+
+config MEM_SOFT_DIRTY
+	bool "Track memory changes"
+	depends on CHECKPOINT_RESTORE && HAVE_ARCH_SOFT_DIRTY && PROC_FS
+	select PROC_PAGE_MONITOR
+	help
+	  This option enables memory changes tracking by introducing a
+	  soft-dirty bit on pte-s. This bit it set when someone writes
+	  into a page just as regular dirty bit, but unlike the latter
+	  it can be cleared by hands.
+
+	  See Documentation/vm/soft-dirty.txt for more details.
+
+config ZSWAP
+	bool "Compressed cache for swap pages (EXPERIMENTAL)"
+	depends on FRONTSWAP && CRYPTO=y
+	select CRYPTO_LZO
+	select CRYPTO_LZ4
+	select ZPOOL
+	default n
+	help
+	  A lightweight compressed cache for swap pages.  It takes
+	  pages that are in the process of being swapped out and attempts to
+	  compress them into a dynamically allocated RAM-based memory pool.
+	  This can result in a significant I/O reduction on swap device and,
+	  in the case where decompressing from RAM is faster that swap device
+	  reads, can also improve workload performance.
+
+	  This is marked experimental because it is a new feature (as of
+	  v3.11) that interacts heavily with memory reclaim.  While these
+	  interactions don't cause any known issues on simple memory setups,
+	  they have not be fully explored on the large set of potential
+	  configurations and workloads that exist.
+
+config ZSWAP_COMPACTION
+	bool "Enable runtime zswap compaction"
+	depends on ZSWAP && ZPOOL && ZSMALLOC
+	default n
+
+config ZSWAP_ENABLE_WRITEBACK
+	bool "Enable zswap writeback"
+	depends on ZSWAP
+	default n
+
+config ZPOOL
+	tristate "Common API for compressed memory storage"
+	default n
+	help
+	  Compressed memory storage API.  This allows using either zbud or
+	  zsmalloc.
+
+config ZBUD
+	tristate "Low density storage for compressed pages"
+	default n
+	help
+	  A special purpose allocator for storing compressed pages.
+	  It is designed to store up to two compressed pages per physical
+	  page.  While this design limits storage density, it has simple and
+	  deterministic reclaim properties that make it preferable to a higher
+	  density approach when reclaim will be used.
+
+config ZSMALLOC
+	tristate "Memory allocator for compressed pages"
+	depends on MMU
+	default n
+	help
+	  zsmalloc is a slab-based memory allocator designed to store
+	  compressed RAM pages.  zsmalloc uses virtual memory mapping
+	  in order to reduce fragmentation.  However, this results in a
+	  non-standard allocator interface where a handle, not a pointer, is
+	  returned by an alloc().  This handle must be mapped in order to
+	  access the allocated space.
+
+config PGTABLE_MAPPING
+	bool "Use page table mapping to access object in zsmalloc"
+	depends on ZSMALLOC
+	help
+	  By default, zsmalloc uses a copy-based object mapping method to
+	  access allocations that span two pages. However, if a particular
+	  architecture (ex, ARM) performs VM mapping faster than copying,
+	  then you should select this. This causes zsmalloc to use page table
+	  mapping rather than copying for object mapping.
+
+	  You can check speed with zsmalloc benchmark:
+	  https://github.com/spartacus06/zsmapbench
+
+config ZSMALLOC_STAT
+	bool "Export zsmalloc statistics"
+	depends on ZSMALLOC
+	select DEBUG_FS
+	help
+	  This option enables code in the zsmalloc to collect various
+	  statistics about whats happening in zsmalloc and exports that
+	  information to userspace via debugfs.
+	  If unsure, say N.
+
+config ZSMALLOC_OBJ_SEQ
+	bool "Record the sequence number of each object in itself"
+	depends on ZSMALLOC
+	default n
+	help
+	  This option records the sequence number of each zs object in the object.
+	  The recorded number will be used for reclaim_zspage.
+	  If unsure, say N.
+
+config DIRECT_RECLAIM_FILE_PAGES_ONLY
+	bool "Reclaim file pages only on direct reclaim path"
+	depends on ZSWAP
+	default n
+
+config INCREASE_MAXIMUM_SWAPPINESS
+	bool "Allow swappiness to be set up to 200"
+	depends on ZSWAP
+	default n
+
+config FIX_INACTIVE_RATIO
+	bool "Fix active:inactive anon ratio to 1:1"
+	depends on ZSWAP
+	default n
+
+config TIGHT_PGDAT_BALANCE
+	bool "Set more tight balanced condition to kswapd"
+	depends on ZSWAP
+	default n
+
+config SWAP_ENABLE_READAHEAD
+	bool "Enable readahead on page swap in"
+	depends on SWAP
+	default y
+	help
+	  When a page fault occurs, adjacent pages of SWAP_CLUSTER_MAX are
+	  also paged in expecting those pages will be used in near future.
+	  This behaviour is good at disk-based system, but not on in-memory
+	  compression (e.g. zram).
+
+config GENERIC_EARLY_IOREMAP
+	bool
+
+config MAX_STACK_SIZE_MB
+	int "Maximum user stack size for 32-bit processes (MB)"
+	default 80
+	range 8 256 if METAG
+	range 8 2048
+	depends on STACK_GROWSUP && (!64BIT || COMPAT)
+	help
+	  This is the maximum stack size in Megabytes in the VM layout of 32-bit
+	  user processes when the stack grows upwards (currently only on parisc
+	  and metag arch). The stack will be located at the highest memory
+	  address minus the given value, unless the RLIMIT_STACK hard limit is
+	  changed to a smaller value in which case that is used.
+
+	  A sane initial value is 80 MB.
+
+config MMAP_READAROUND_LIMIT
+	int "Limit mmap readaround upperbound"
+	default 0
+	help
+	  Inappropriate mmap readaround size can hurt device performance
+	  during the sluggish situation. Add the hard upper-limit for
+	  mmap readaround.

mm/Kconfig.debug

@@ -0,0 +1,29 @@
+config DEBUG_PAGEALLOC
+	bool "Debug page memory allocations"
+	depends on DEBUG_KERNEL
+	depends on !HIBERNATION || ARCH_SUPPORTS_DEBUG_PAGEALLOC && !PPC && !SPARC
+	depends on !KMEMCHECK
+	select PAGE_POISONING if !ARCH_SUPPORTS_DEBUG_PAGEALLOC
+	select PAGE_GUARD if ARCH_SUPPORTS_DEBUG_PAGEALLOC
+	---help---
+	  Unmap pages from the kernel linear mapping after free_pages().
+	  This results in a large slowdown, but helps to find certain types
+	  of memory corruption.
+
+	  For architectures which don't enable ARCH_SUPPORTS_DEBUG_PAGEALLOC,
+	  fill the pages with poison patterns after free_pages() and verify
+	  the patterns before alloc_pages().  Additionally,
+	  this option cannot be enabled in combination with hibernation as
+	  that would result in incorrect warnings of memory corruption after
+	  a resume because free pages are not saved to the suspend image.
+
+config WANT_PAGE_DEBUG_FLAGS
+	bool
+
+config PAGE_POISONING
+	bool
+	select WANT_PAGE_DEBUG_FLAGS
+
+config PAGE_GUARD
+	bool
+	select WANT_PAGE_DEBUG_FLAGS

mm/Makefile

@@ -0,0 +1,71 @@
+#
+# Makefile for the linux memory manager.
+#
+
+mmu-y			:= nommu.o
+mmu-$(CONFIG_MMU)	:= fremap.o gup.o highmem.o memory.o mincore.o \
+			   mlock.o mmap.o mprotect.o mremap.o msync.o rmap.o \
+			   vmalloc.o pagewalk.o pgtable-generic.o
+
+ifdef CONFIG_CROSS_MEMORY_ATTACH
+mmu-$(CONFIG_MMU)	+= process_vm_access.o
+endif
+
+obj-y			:= filemap.o mempool.o oom_kill.o \
+			   maccess.o page_alloc.o page-writeback.o \
+			   readahead.o swap.o truncate.o vmscan.o shmem.o \
+			   util.o mmzone.o vmstat.o backing-dev.o \
+			   mm_init.o mmu_context.o percpu.o slab_common.o \
+			   compaction.o vmacache.o \
+			   interval_tree.o list_lru.o workingset.o \
+			   iov_iter.o debug.o $(mmu-y)
+
+obj-y += init-mm.o
+
+ifdef CONFIG_NO_BOOTMEM
+	obj-y		+= nobootmem.o
+else
+	obj-y		+= bootmem.o
+endif
+
+obj-$(CONFIG_ADVISE_SYSCALLS)	+= fadvise.o
+ifdef CONFIG_MMU
+	obj-$(CONFIG_ADVISE_SYSCALLS)	+= madvise.o
+endif
+obj-$(CONFIG_HAVE_MEMBLOCK) += memblock.o
+
+obj-$(CONFIG_SWAP)	+= page_io.o swap_state.o swapfile.o
+obj-$(CONFIG_FRONTSWAP)	+= frontswap.o
+obj-$(CONFIG_ZSWAP)	+= zswap.o
+obj-$(CONFIG_HAS_DMA)	+= dmapool.o
+obj-$(CONFIG_HUGETLBFS)	+= hugetlb.o
+obj-$(CONFIG_NUMA) 	+= mempolicy.o
+obj-$(CONFIG_SPARSEMEM)	+= sparse.o
+obj-$(CONFIG_SPARSEMEM_VMEMMAP) += sparse-vmemmap.o
+obj-$(CONFIG_SLOB) += slob.o
+obj-$(CONFIG_MMU_NOTIFIER) += mmu_notifier.o
+obj-$(CONFIG_KSM) += ksm.o
+obj-$(CONFIG_PAGE_POISONING) += debug-pagealloc.o
+obj-$(CONFIG_SLAB) += slab.o
+obj-$(CONFIG_SLUB) += slub.o
+obj-$(CONFIG_KMEMCHECK) += kmemcheck.o
+obj-$(CONFIG_FAILSLAB) += failslab.o
+obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o
+obj-$(CONFIG_FS_XIP) += filemap_xip.o
+obj-$(CONFIG_MIGRATION) += migrate.o
+obj-$(CONFIG_QUICKLIST) += quicklist.o
+obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += huge_memory.o
+obj-$(CONFIG_MEMCG) += memcontrol.o page_cgroup.o vmpressure.o
+obj-$(CONFIG_CGROUP_HUGETLB) += hugetlb_cgroup.o
+obj-$(CONFIG_MEMORY_FAILURE) += memory-failure.o
+obj-$(CONFIG_HWPOISON_INJECT) += hwpoison-inject.o
+obj-$(CONFIG_DEBUG_KMEMLEAK) += kmemleak.o
+obj-$(CONFIG_DEBUG_KMEMLEAK_TEST) += kmemleak-test.o
+obj-$(CONFIG_CLEANCACHE) += cleancache.o
+obj-$(CONFIG_MEMORY_ISOLATION) += page_isolation.o
+obj-$(CONFIG_ZPOOL)	+= zpool.o
+obj-$(CONFIG_ZBUD)	+= zbud.o
+obj-$(CONFIG_ZSMALLOC)	+= zsmalloc.o
+obj-$(CONFIG_GENERIC_EARLY_IOREMAP) += early_ioremap.o
+obj-$(CONFIG_CMA)	+= cma.o
+obj-$(CONFIG_MEMORY_BALLOON) += balloon_compaction.o

mm/backing-dev.c

@@ -0,0 +1,668 @@
+
+#include <linux/wait.h>
+#include <linux/backing-dev.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
+#include <linux/fs.h>
+#include <linux/pagemap.h>
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <linux/module.h>
+#include <linux/writeback.h>
+#include <linux/device.h>
+#include <trace/events/writeback.h>
+
+static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0);
+
+struct backing_dev_info default_backing_dev_info = {
+	.name		= "default",
+	.ra_pages	= VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE,
+	.state		= 0,
+	.capabilities	= BDI_CAP_MAP_COPY,
+};
+EXPORT_SYMBOL_GPL(default_backing_dev_info);
+
+struct backing_dev_info noop_backing_dev_info = {
+	.name		= "noop",
+	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
+};
+EXPORT_SYMBOL_GPL(noop_backing_dev_info);
+
+static struct class *bdi_class;
+
+/*
+ * bdi_lock protects updates to bdi_list. bdi_list has RCU reader side
+ * locking.
+ */
+DEFINE_SPINLOCK(bdi_lock);
+LIST_HEAD(bdi_list);
+
+/* bdi_wq serves all asynchronous writeback tasks */
+struct workqueue_struct *bdi_wq;
+
+static void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2)
+{
+	if (wb1 < wb2) {
+		spin_lock(&wb1->list_lock);
+		spin_lock_nested(&wb2->list_lock, 1);
+	} else {
+		spin_lock(&wb2->list_lock);
+		spin_lock_nested(&wb1->list_lock, 1);
+	}
+}
+
+#ifdef CONFIG_DEBUG_FS
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+
+static struct dentry *bdi_debug_root;
+
+static void bdi_debug_init(void)
+{
+	bdi_debug_root = debugfs_create_dir("bdi", NULL);
+}
+
+static int bdi_debug_stats_show(struct seq_file *m, void *v)
+{
+	struct backing_dev_info *bdi = m->private;
+	struct bdi_writeback *wb = &bdi->wb;
+	unsigned long background_thresh;
+	unsigned long dirty_thresh;
+	unsigned long bdi_thresh;
+	unsigned long nr_dirty, nr_io, nr_more_io;
+	struct inode *inode;
+
+	nr_dirty = nr_io = nr_more_io = 0;
+	spin_lock(&wb->list_lock);
+	list_for_each_entry(inode, &wb->b_dirty, i_wb_list)
+		nr_dirty++;
+	list_for_each_entry(inode, &wb->b_io, i_wb_list)
+		nr_io++;
+	list_for_each_entry(inode, &wb->b_more_io, i_wb_list)
+		nr_more_io++;
+	spin_unlock(&wb->list_lock);
+
+	global_dirty_limits(&background_thresh, &dirty_thresh);
+	bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh);
+
+#define K(x) ((x) << (PAGE_SHIFT - 10))
+	seq_printf(m,
+		   "BdiWriteback:       %10lu kB\n"
+		   "BdiReclaimable:     %10lu kB\n"
+		   "BdiDirtyThresh:     %10lu kB\n"
+		   "DirtyThresh:        %10lu kB\n"
+		   "BackgroundThresh:   %10lu kB\n"
+		   "BdiDirtied:         %10lu kB\n"
+		   "BdiWritten:         %10lu kB\n"
+		   "BdiWriteBandwidth:  %10lu kBps\n"
+		   "b_dirty:            %10lu\n"
+		   "b_io:               %10lu\n"
+		   "b_more_io:          %10lu\n"
+		   "bdi_list:           %10u\n"
+		   "state:              %10lx\n",
+		   (unsigned long) K(bdi_stat(bdi, BDI_WRITEBACK)),
+		   (unsigned long) K(bdi_stat(bdi, BDI_RECLAIMABLE)),
+		   K(bdi_thresh),
+		   K(dirty_thresh),
+		   K(background_thresh),
+		   (unsigned long) K(bdi_stat(bdi, BDI_DIRTIED)),
+		   (unsigned long) K(bdi_stat(bdi, BDI_WRITTEN)),
+		   (unsigned long) K(bdi->write_bandwidth),
+		   nr_dirty,
+		   nr_io,
+		   nr_more_io,
+		   !list_empty(&bdi->bdi_list), bdi->state);
+#undef K
+
+	return 0;
+}
+
+static int bdi_debug_stats_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, bdi_debug_stats_show, inode->i_private);
+}
+
+static const struct file_operations bdi_debug_stats_fops = {
+	.open		= bdi_debug_stats_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static void bdi_debug_register(struct backing_dev_info *bdi, const char *name)
+{
+	bdi->debug_dir = debugfs_create_dir(name, bdi_debug_root);
+	bdi->debug_stats = debugfs_create_file("stats", 0444, bdi->debug_dir,
+					       bdi, &bdi_debug_stats_fops);
+}
+
+static void bdi_debug_unregister(struct backing_dev_info *bdi)
+{
+	debugfs_remove(bdi->debug_stats);
+	debugfs_remove(bdi->debug_dir);
+}
+#else
+static inline void bdi_debug_init(void)
+{
+}
+static inline void bdi_debug_register(struct backing_dev_info *bdi,
+				      const char *name)
+{
+}
+static inline void bdi_debug_unregister(struct backing_dev_info *bdi)
+{
+}
+#endif
+
+static ssize_t read_ahead_kb_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t count)
+{
+	struct backing_dev_info *bdi = dev_get_drvdata(dev);
+	unsigned long read_ahead_kb;
+	ssize_t ret;
+
+	ret = kstrtoul(buf, 10, &read_ahead_kb);
+	if (ret < 0)
+		return ret;
+
+	bdi->ra_pages = read_ahead_kb >> (PAGE_SHIFT - 10);
+
+	return count;
+}
+
+#define K(pages) ((pages) << (PAGE_SHIFT - 10))
+
+#define BDI_SHOW(name, expr)						\
+static ssize_t name##_show(struct device *dev,				\
+			   struct device_attribute *attr, char *page)	\
+{									\
+	struct backing_dev_info *bdi = dev_get_drvdata(dev);		\
+									\
+	return snprintf(page, PAGE_SIZE-1, "%lld\n", (long long)expr);	\
+}									\
+static DEVICE_ATTR_RW(name);
+
+BDI_SHOW(read_ahead_kb, K(bdi->ra_pages))
+
+static ssize_t min_ratio_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct backing_dev_info *bdi = dev_get_drvdata(dev);
+	unsigned int ratio;
+	ssize_t ret;
+
+	ret = kstrtouint(buf, 10, &ratio);
+	if (ret < 0)
+		return ret;
+
+	ret = bdi_set_min_ratio(bdi, ratio);
+	if (!ret)
+		ret = count;
+
+	return ret;
+}
+BDI_SHOW(min_ratio, bdi->min_ratio)
+
+static ssize_t max_ratio_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct backing_dev_info *bdi = dev_get_drvdata(dev);
+	unsigned int ratio;
+	ssize_t ret;
+
+	ret = kstrtouint(buf, 10, &ratio);
+	if (ret < 0)
+		return ret;
+
+	ret = bdi_set_max_ratio(bdi, ratio);
+	if (!ret)
+		ret = count;
+
+	return ret;
+}
+BDI_SHOW(max_ratio, bdi->max_ratio)
+
+static ssize_t stable_pages_required_show(struct device *dev,
+					  struct device_attribute *attr,
+					  char *page)
+{
+	struct backing_dev_info *bdi = dev_get_drvdata(dev);
+
+	return snprintf(page, PAGE_SIZE-1, "%d\n",
+			bdi_cap_stable_pages_required(bdi) ? 1 : 0);
+}
+static DEVICE_ATTR_RO(stable_pages_required);
+
+static struct attribute *bdi_dev_attrs[] = {
+	&dev_attr_read_ahead_kb.attr,
+	&dev_attr_min_ratio.attr,
+	&dev_attr_max_ratio.attr,
+	&dev_attr_stable_pages_required.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(bdi_dev);
+
+static __init int bdi_class_init(void)
+{
+	bdi_class = class_create(THIS_MODULE, "bdi");
+	if (IS_ERR(bdi_class))
+		return PTR_ERR(bdi_class);
+
+	bdi_class->dev_groups = bdi_dev_groups;
+	bdi_debug_init();
+	return 0;
+}
+postcore_initcall(bdi_class_init);
+
+static int __init default_bdi_init(void)
+{
+	int err;
+
+	bdi_wq = alloc_workqueue("writeback", WQ_MEM_RECLAIM | WQ_FREEZABLE |
+					      WQ_UNBOUND | WQ_SYSFS, 0);
+	if (!bdi_wq)
+		return -ENOMEM;
+
+	err = bdi_init(&default_backing_dev_info);
+	if (!err)
+		bdi_register(&default_backing_dev_info, NULL, "default");
+	err = bdi_init(&noop_backing_dev_info);
+
+	return err;
+}
+subsys_initcall(default_bdi_init);
+
+int bdi_has_dirty_io(struct backing_dev_info *bdi)
+{
+	return wb_has_dirty_io(&bdi->wb);
+}
+
+/*
+ * This function is used when the first inode for this bdi is marked dirty. It
+ * wakes-up the corresponding bdi thread which should then take care of the
+ * periodic background write-out of dirty inodes. Since the write-out would
+ * starts only 'dirty_writeback_interval' centisecs from now anyway, we just
+ * set up a timer which wakes the bdi thread up later.
+ *
+ * Note, we wouldn't bother setting up the timer, but this function is on the
+ * fast-path (used by '__mark_inode_dirty()'), so we save few context switches
+ * by delaying the wake-up.
+ *
+ * We have to be careful not to postpone flush work if it is scheduled for
+ * earlier. Thus we use queue_delayed_work().
+ */
+void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi)
+{
+	unsigned long timeout;
+
+	timeout = msecs_to_jiffies(dirty_writeback_interval * 10);
+	spin_lock_bh(&bdi->wb_lock);
+	if (test_bit(BDI_registered, &bdi->state))
+		queue_delayed_work(bdi_wq, &bdi->wb.dwork, timeout);
+	spin_unlock_bh(&bdi->wb_lock);
+}
+
+/*
+ * Remove bdi from bdi_list, and ensure that it is no longer visible
+ */
+static void bdi_remove_from_list(struct backing_dev_info *bdi)
+{
+	spin_lock_bh(&bdi_lock);
+	list_del_rcu(&bdi->bdi_list);
+	spin_unlock_bh(&bdi_lock);
+
+	synchronize_rcu_expedited();
+}
+
+int bdi_register(struct backing_dev_info *bdi, struct device *parent,
+		const char *fmt, ...)
+{
+	va_list args;
+	struct device *dev;
+
+	if (bdi->dev)	/* The driver needs to use separate queues per device */
+		return 0;
+
+	va_start(args, fmt);
+	dev = device_create_vargs(bdi_class, parent, MKDEV(0, 0), bdi, fmt, args);
+	va_end(args);
+	if (IS_ERR(dev))
+		return PTR_ERR(dev);
+
+	bdi->dev = dev;
+
+	bdi_debug_register(bdi, dev_name(dev));
+	set_bit(BDI_registered, &bdi->state);
+
+	spin_lock_bh(&bdi_lock);
+	list_add_tail_rcu(&bdi->bdi_list, &bdi_list);
+	spin_unlock_bh(&bdi_lock);
+
+	trace_writeback_bdi_register(bdi);
+	return 0;
+}
+EXPORT_SYMBOL(bdi_register);
+
+int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev)
+{
+	return bdi_register(bdi, NULL, "%u:%u", MAJOR(dev), MINOR(dev));
+}
+EXPORT_SYMBOL(bdi_register_dev);
+
+/*
+ * Remove bdi from the global list and shutdown any threads we have running
+ */
+static void bdi_wb_shutdown(struct backing_dev_info *bdi)
+{
+	if (!bdi_cap_writeback_dirty(bdi))
+		return;
+
+	/*
+	 * Make sure nobody finds us on the bdi_list anymore
+	 */
+	bdi_remove_from_list(bdi);
+
+	/* Make sure nobody queues further work */
+	spin_lock_bh(&bdi->wb_lock);
+	clear_bit(BDI_registered, &bdi->state);
+	spin_unlock_bh(&bdi->wb_lock);
+
+	/*
+	 * Drain work list and shutdown the delayed_work.  At this point,
+	 * @bdi->bdi_list is empty telling bdi_Writeback_workfn() that @bdi
+	 * is dying and its work_list needs to be drained no matter what.
+	 */
+	mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
+	flush_delayed_work(&bdi->wb.dwork);
+	WARN_ON(!list_empty(&bdi->work_list));
+	WARN_ON(delayed_work_pending(&bdi->wb.dwork));
+}
+
+/*
+ * This bdi is going away now, make sure that no super_blocks point to it
+ */
+static void bdi_prune_sb(struct backing_dev_info *bdi)
+{
+	struct super_block *sb;
+
+	spin_lock(&sb_lock);
+	list_for_each_entry(sb, &super_blocks, s_list) {
+		if (sb->s_bdi == bdi)
+			sb->s_bdi = &default_backing_dev_info;
+	}
+	spin_unlock(&sb_lock);
+}
+
+void bdi_unregister(struct backing_dev_info *bdi)
+{
+	if (bdi->dev) {
+		bdi_set_min_ratio(bdi, 0);
+		trace_writeback_bdi_unregister(bdi);
+		bdi_prune_sb(bdi);
+
+		bdi_wb_shutdown(bdi);
+		bdi_debug_unregister(bdi);
+		device_unregister(bdi->dev);
+		bdi->dev = NULL;
+	}
+}
+EXPORT_SYMBOL(bdi_unregister);
+
+static void bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi)
+{
+	memset(wb, 0, sizeof(*wb));
+
+	wb->bdi = bdi;
+	wb->last_old_flush = jiffies;
+	INIT_LIST_HEAD(&wb->b_dirty);
+	INIT_LIST_HEAD(&wb->b_io);
+	INIT_LIST_HEAD(&wb->b_more_io);
+	spin_lock_init(&wb->list_lock);
+	INIT_DELAYED_WORK(&wb->dwork, bdi_writeback_workfn);
+}
+
+/*
+ * Initial write bandwidth: 100 MB/s
+ */
+#define INIT_BW		(100 << (20 - PAGE_SHIFT))
+
+int bdi_init(struct backing_dev_info *bdi)
+{
+	int i, err;
+
+	bdi->dev = NULL;
+
+	bdi->min_ratio = 0;
+	bdi->max_ratio = 100;
+	bdi->max_prop_frac = FPROP_FRAC_BASE;
+	spin_lock_init(&bdi->wb_lock);
+	INIT_LIST_HEAD(&bdi->bdi_list);
+	INIT_LIST_HEAD(&bdi->work_list);
+
+	bdi_wb_init(&bdi->wb, bdi);
+
+	for (i = 0; i < NR_BDI_STAT_ITEMS; i++) {
+		err = percpu_counter_init(&bdi->bdi_stat[i], 0, GFP_KERNEL);
+		if (err)
+			goto err;
+	}
+
+	bdi->dirty_exceeded = 0;
+
+	bdi->bw_time_stamp = jiffies;
+	bdi->written_stamp = 0;
+
+	bdi->balanced_dirty_ratelimit = INIT_BW;
+	bdi->dirty_ratelimit = INIT_BW;
+	bdi->write_bandwidth = INIT_BW;
+	bdi->avg_write_bandwidth = INIT_BW;
+
+	err = fprop_local_init_percpu(&bdi->completions, GFP_KERNEL);
+
+	if (err) {
+err:
+		while (i--)
+			percpu_counter_destroy(&bdi->bdi_stat[i]);
+	}
+
+	return err;
+}
+EXPORT_SYMBOL(bdi_init);
+
+void bdi_destroy(struct backing_dev_info *bdi)
+{
+	int i;
+
+	/*
+	 * Splice our entries to the default_backing_dev_info.  This
+	 * condition shouldn't happen.  @wb must be empty at this point and
+	 * dirty inodes on it might cause other issues.  This workaround is
+	 * added by ce5f8e779519 ("writeback: splice dirty inode entries to
+	 * default bdi on bdi_destroy()") without root-causing the issue.
+	 *
+	 * http://lkml.kernel.org/g/1253038617-30204-11-git-send-email-jens.axboe@oracle.com
+	 * http://thread.gmane.org/gmane.linux.file-systems/35341/focus=35350
+	 *
+	 * We should probably add WARN_ON() to find out whether it still
+	 * happens and track it down if so.
+	 */
+	if (bdi_has_dirty_io(bdi)) {
+		struct bdi_writeback *dst = &default_backing_dev_info.wb;
+
+		bdi_lock_two(&bdi->wb, dst);
+		list_splice(&bdi->wb.b_dirty, &dst->b_dirty);
+		list_splice(&bdi->wb.b_io, &dst->b_io);
+		list_splice(&bdi->wb.b_more_io, &dst->b_more_io);
+		spin_unlock(&bdi->wb.list_lock);
+		spin_unlock(&dst->list_lock);
+	}
+
+	bdi_unregister(bdi);
+
+	WARN_ON(delayed_work_pending(&bdi->wb.dwork));
+
+	for (i = 0; i < NR_BDI_STAT_ITEMS; i++)
+		percpu_counter_destroy(&bdi->bdi_stat[i]);
+
+	fprop_local_destroy_percpu(&bdi->completions);
+}
+EXPORT_SYMBOL(bdi_destroy);
+
+/*
+ * For use from filesystems to quickly init and register a bdi associated
+ * with dirty writeback
+ */
+int bdi_setup_and_register(struct backing_dev_info *bdi, char *name,
+			   unsigned int cap)
+{
+	int err;
+
+	bdi->name = name;
+	bdi->capabilities = cap;
+	err = bdi_init(bdi);
+	if (err)
+		return err;
+
+	err = bdi_register(bdi, NULL, "%.28s-%ld", name,
+			   atomic_long_inc_return(&bdi_seq));
+	if (err) {
+		bdi_destroy(bdi);
+		return err;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(bdi_setup_and_register);
+
+static wait_queue_head_t congestion_wqh[2] = {
+		__WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[0]),
+		__WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1])
+	};
+static atomic_t nr_bdi_congested[2];
+
+void clear_bdi_congested(struct backing_dev_info *bdi, int sync)
+{
+	enum bdi_state bit;
+	wait_queue_head_t *wqh = &congestion_wqh[sync];
+
+	bit = sync ? BDI_sync_congested : BDI_async_congested;
+	if (test_and_clear_bit(bit, &bdi->state))
+		atomic_dec(&nr_bdi_congested[sync]);
+	smp_mb__after_atomic();
+	if (waitqueue_active(wqh))
+		wake_up(wqh);
+}
+EXPORT_SYMBOL(clear_bdi_congested);
+
+void set_bdi_congested(struct backing_dev_info *bdi, int sync)
+{
+	enum bdi_state bit;
+
+	bit = sync ? BDI_sync_congested : BDI_async_congested;
+	if (!test_and_set_bit(bit, &bdi->state))
+		atomic_inc(&nr_bdi_congested[sync]);
+}
+EXPORT_SYMBOL(set_bdi_congested);
+
+/**
+ * congestion_wait - wait for a backing_dev to become uncongested
+ * @sync: SYNC or ASYNC IO
+ * @timeout: timeout in jiffies
+ *
+ * Waits for up to @timeout jiffies for a backing_dev (any backing_dev) to exit
+ * write congestion.  If no backing_devs are congested then just wait for the
+ * next write to be completed.
+ */
+long congestion_wait(int sync, long timeout)
+{
+	long ret;
+	unsigned long start = jiffies;
+	DEFINE_WAIT(wait);
+	wait_queue_head_t *wqh = &congestion_wqh[sync];
+
+	prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
+	ret = io_schedule_timeout(timeout);
+	finish_wait(wqh, &wait);
+
+	trace_writeback_congestion_wait(jiffies_to_usecs(timeout),
+					jiffies_to_usecs(jiffies - start));
+
+	return ret;
+}
+EXPORT_SYMBOL(congestion_wait);
+
+/**
+ * wait_iff_congested - Conditionally wait for a backing_dev to become uncongested or a zone to complete writes
+ * @zone: A zone to check if it is heavily congested
+ * @sync: SYNC or ASYNC IO
+ * @timeout: timeout in jiffies
+ *
+ * In the event of a congested backing_dev (any backing_dev) and the given
+ * @zone has experienced recent congestion, this waits for up to @timeout
+ * jiffies for either a BDI to exit congestion of the given @sync queue
+ * or a write to complete.
+ *
+ * In the absence of zone congestion, cond_resched() is called to yield
+ * the processor if necessary but otherwise does not sleep.
+ *
+ * The return value is 0 if the sleep is for the full timeout. Otherwise,
+ * it is the number of jiffies that were still remaining when the function
+ * returned. return_value == timeout implies the function did not sleep.
+ */
+long wait_iff_congested(struct zone *zone, int sync, long timeout)
+{
+	long ret;
+	unsigned long start = jiffies;
+	DEFINE_WAIT(wait);
+	wait_queue_head_t *wqh = &congestion_wqh[sync];
+
+	/*
+	 * If there is no congestion, or heavy congestion is not being
+	 * encountered in the current zone, yield if necessary instead
+	 * of sleeping on the congestion queue
+	 */
+	if (atomic_read(&nr_bdi_congested[sync]) == 0 ||
+	    !test_bit(ZONE_CONGESTED, &zone->flags)) {
+		cond_resched();
+
+		/* In case we scheduled, work out time remaining */
+		ret = timeout - (jiffies - start);
+		if (ret < 0)
+			ret = 0;
+
+		goto out;
+	}
+
+	/* Sleep until uncongested or a write happens */
+	prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
+	ret = io_schedule_timeout(timeout);
+	finish_wait(wqh, &wait);
+
+out:
+	trace_writeback_wait_iff_congested(jiffies_to_usecs(timeout),
+					jiffies_to_usecs(jiffies - start));
+
+	return ret;
+}
+EXPORT_SYMBOL(wait_iff_congested);
+
+int pdflush_proc_obsolete(struct ctl_table *table, int write,
+			void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	char kbuf[] = "0\n";
+
+	if (*ppos || *lenp < sizeof(kbuf)) {
+		*lenp = 0;
+		return 0;
+	}
+
+	if (copy_to_user(buffer, kbuf, sizeof(kbuf)))
+		return -EFAULT;
+	printk_once(KERN_WARNING "%s exported in /proc is scheduled for removal\n",
+			table->procname);
+
+	*lenp = 2;
+	*ppos += *lenp;
+	return 2;
+}

mm/balloon_compaction.c

@@ -0,0 +1,221 @@
+/*
+ * mm/balloon_compaction.c
+ *
+ * Common interface for making balloon pages movable by compaction.
+ *
+ * Copyright (C) 2012, Red Hat, Inc.  Rafael Aquini <aquini@redhat.com>
+ */
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/export.h>
+#include <linux/balloon_compaction.h>
+
+/*
+ * balloon_page_enqueue - allocates a new page and inserts it into the balloon
+ *			  page list.
+ * @b_dev_info: balloon device decriptor where we will insert a new page to
+ *
+ * Driver must call it to properly allocate a new enlisted balloon page
+ * before definetively removing it from the guest system.
+ * This function returns the page address for the recently enqueued page or
+ * NULL in the case we fail to allocate a new page this turn.
+ */
+struct page *balloon_page_enqueue(struct balloon_dev_info *b_dev_info)
+{
+	unsigned long flags;
+	struct page *page = alloc_page(balloon_mapping_gfp_mask() |
+					__GFP_NOMEMALLOC | __GFP_NORETRY);
+	if (!page)
+		return NULL;
+
+	/*
+	 * Block others from accessing the 'page' when we get around to
+	 * establishing additional references. We should be the only one
+	 * holding a reference to the 'page' at this point.
+	 */
+	BUG_ON(!trylock_page(page));
+	spin_lock_irqsave(&b_dev_info->pages_lock, flags);
+	balloon_page_insert(b_dev_info, page);
+	__count_vm_event(BALLOON_INFLATE);
+	spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
+	unlock_page(page);
+	return page;
+}
+EXPORT_SYMBOL_GPL(balloon_page_enqueue);
+
+/*
+ * balloon_page_dequeue - removes a page from balloon's page list and returns
+ *			  the its address to allow the driver release the page.
+ * @b_dev_info: balloon device decriptor where we will grab a page from.
+ *
+ * Driver must call it to properly de-allocate a previous enlisted balloon page
+ * before definetively releasing it back to the guest system.
+ * This function returns the page address for the recently dequeued page or
+ * NULL in the case we find balloon's page list temporarily empty due to
+ * compaction isolated pages.
+ */
+struct page *balloon_page_dequeue(struct balloon_dev_info *b_dev_info)
+{
+	struct page *page, *tmp;
+	unsigned long flags;
+	bool dequeued_page;
+
+	dequeued_page = false;
+	list_for_each_entry_safe(page, tmp, &b_dev_info->pages, lru) {
+		/*
+		 * Block others from accessing the 'page' while we get around
+		 * establishing additional references and preparing the 'page'
+		 * to be released by the balloon driver.
+		 */
+		if (trylock_page(page)) {
+#ifdef CONFIG_BALLOON_COMPACTION
+			if (!PagePrivate(page)) {
+				/* raced with isolation */
+				unlock_page(page);
+				continue;
+			}
+#endif
+			spin_lock_irqsave(&b_dev_info->pages_lock, flags);
+			balloon_page_delete(page);
+			__count_vm_event(BALLOON_DEFLATE);
+			spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
+			unlock_page(page);
+			dequeued_page = true;
+			break;
+		}
+	}
+
+	if (!dequeued_page) {
+		/*
+		 * If we are unable to dequeue a balloon page because the page
+		 * list is empty and there is no isolated pages, then something
+		 * went out of track and some balloon pages are lost.
+		 * BUG() here, otherwise the balloon driver may get stuck into
+		 * an infinite loop while attempting to release all its pages.
+		 */
+		spin_lock_irqsave(&b_dev_info->pages_lock, flags);
+		if (unlikely(list_empty(&b_dev_info->pages) &&
+			     !b_dev_info->isolated_pages))
+			BUG();
+		spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
+		page = NULL;
+	}
+	return page;
+}
+EXPORT_SYMBOL_GPL(balloon_page_dequeue);
+
+#ifdef CONFIG_BALLOON_COMPACTION
+
+static inline void __isolate_balloon_page(struct page *page)
+{
+	struct balloon_dev_info *b_dev_info = balloon_page_device(page);
+	unsigned long flags;
+
+	spin_lock_irqsave(&b_dev_info->pages_lock, flags);
+	ClearPagePrivate(page);
+	list_del(&page->lru);
+	b_dev_info->isolated_pages++;
+	spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
+}
+
+static inline void __putback_balloon_page(struct page *page)
+{
+	struct balloon_dev_info *b_dev_info = balloon_page_device(page);
+	unsigned long flags;
+
+	spin_lock_irqsave(&b_dev_info->pages_lock, flags);
+	SetPagePrivate(page);
+	list_add(&page->lru, &b_dev_info->pages);
+	b_dev_info->isolated_pages--;
+	spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
+}
+
+/* __isolate_lru_page() counterpart for a ballooned page */
+bool balloon_page_isolate(struct page *page)
+{
+	/*
+	 * Avoid burning cycles with pages that are yet under __free_pages(),
+	 * or just got freed under us.
+	 *
+	 * In case we 'win' a race for a balloon page being freed under us and
+	 * raise its refcount preventing __free_pages() from doing its job
+	 * the put_page() at the end of this block will take care of
+	 * release this page, thus avoiding a nasty leakage.
+	 */
+	if (likely(get_page_unless_zero(page))) {
+		/*
+		 * As balloon pages are not isolated from LRU lists, concurrent
+		 * compaction threads can race against page migration functions
+		 * as well as race against the balloon driver releasing a page.
+		 *
+		 * In order to avoid having an already isolated balloon page
+		 * being (wrongly) re-isolated while it is under migration,
+		 * or to avoid attempting to isolate pages being released by
+		 * the balloon driver, lets be sure we have the page lock
+		 * before proceeding with the balloon page isolation steps.
+		 */
+		if (likely(trylock_page(page))) {
+			/*
+			 * A ballooned page, by default, has PagePrivate set.
+			 * Prevent concurrent compaction threads from isolating
+			 * an already isolated balloon page by clearing it.
+			 */
+			if (balloon_page_movable(page)) {
+				__isolate_balloon_page(page);
+				unlock_page(page);
+				return true;
+			}
+			unlock_page(page);
+		}
+		put_page(page);
+	}
+	return false;
+}
+
+/* putback_lru_page() counterpart for a ballooned page */
+void balloon_page_putback(struct page *page)
+{
+	/*
+	 * 'lock_page()' stabilizes the page and prevents races against
+	 * concurrent isolation threads attempting to re-isolate it.
+	 */
+	lock_page(page);
+
+	if (__is_movable_balloon_page(page)) {
+		__putback_balloon_page(page);
+		/* drop the extra ref count taken for page isolation */
+		put_page(page);
+	} else {
+		WARN_ON(1);
+		dump_page(page, "not movable balloon page");
+	}
+	unlock_page(page);
+}
+
+/* move_to_new_page() counterpart for a ballooned page */
+int balloon_page_migrate(struct page *newpage,
+			 struct page *page, enum migrate_mode mode)
+{
+	struct balloon_dev_info *balloon = balloon_page_device(page);
+	int rc = -EAGAIN;
+
+	/*
+	 * Block others from accessing the 'newpage' when we get around to
+	 * establishing additional references. We should be the only one
+	 * holding a reference to the 'newpage' at this point.
+	 */
+	BUG_ON(!trylock_page(newpage));
+
+	if (WARN_ON(!__is_movable_balloon_page(page))) {
+		dump_page(page, "not movable balloon page");
+		unlock_page(newpage);
+		return rc;
+	}
+
+	if (balloon && balloon->migratepage)
+		rc = balloon->migratepage(balloon, newpage, page, mode);
+
+	unlock_page(newpage);
+	return rc;
+}
+#endif /* CONFIG_BALLOON_COMPACTION */

mm/bootmem.c

@@ -0,0 +1,861 @@
+/*
+ *  bootmem - A boot-time physical memory allocator and configurator
+ *
+ *  Copyright (C) 1999 Ingo Molnar
+ *                1999 Kanoj Sarcar, SGI
+ *                2008 Johannes Weiner
+ *
+ * Access to this subsystem has to be serialized externally (which is true
+ * for the boot process anyway).
+ */
+#include <linux/init.h>
+#include <linux/pfn.h>
+#include <linux/slab.h>
+#include <linux/bootmem.h>
+#include <linux/export.h>
+#include <linux/kmemleak.h>
+#include <linux/range.h>
+#include <linux/memblock.h>
+#include <linux/bug.h>
+#include <linux/io.h>
+
+#include <asm/processor.h>
+
+#include "internal.h"
+
+#ifndef CONFIG_NEED_MULTIPLE_NODES
+struct pglist_data __refdata contig_page_data = {
+	.bdata = &bootmem_node_data[0]
+};
+EXPORT_SYMBOL(contig_page_data);
+#endif
+
+unsigned long max_low_pfn;
+unsigned long min_low_pfn;
+unsigned long max_pfn;
+
+bootmem_data_t bootmem_node_data[MAX_NUMNODES] __initdata;
+
+static struct list_head bdata_list __initdata = LIST_HEAD_INIT(bdata_list);
+
+static int bootmem_debug;
+
+static int __init bootmem_debug_setup(char *buf)
+{
+	bootmem_debug = 1;
+	return 0;
+}
+early_param("bootmem_debug", bootmem_debug_setup);
+
+#define bdebug(fmt, args...) ({				\
+	if (unlikely(bootmem_debug))			\
+		printk(KERN_INFO			\
+			"bootmem::%s " fmt,		\
+			__func__, ## args);		\
+})
+
+static unsigned long __init bootmap_bytes(unsigned long pages)
+{
+	unsigned long bytes = DIV_ROUND_UP(pages, 8);
+
+	return ALIGN(bytes, sizeof(long));
+}
+
+/**
+ * bootmem_bootmap_pages - calculate bitmap size in pages
+ * @pages: number of pages the bitmap has to represent
+ */
+unsigned long __init bootmem_bootmap_pages(unsigned long pages)
+{
+	unsigned long bytes = bootmap_bytes(pages);
+
+	return PAGE_ALIGN(bytes) >> PAGE_SHIFT;
+}
+
+/*
+ * link bdata in order
+ */
+static void __init link_bootmem(bootmem_data_t *bdata)
+{
+	bootmem_data_t *ent;
+
+	list_for_each_entry(ent, &bdata_list, list) {
+		if (bdata->node_min_pfn < ent->node_min_pfn) {
+			list_add_tail(&bdata->list, &ent->list);
+			return;
+		}
+	}
+
+	list_add_tail(&bdata->list, &bdata_list);
+}
+
+/*
+ * Called once to set up the allocator itself.
+ */
+static unsigned long __init init_bootmem_core(bootmem_data_t *bdata,
+	unsigned long mapstart, unsigned long start, unsigned long end)
+{
+	unsigned long mapsize;
+
+	mminit_validate_memmodel_limits(&start, &end);
+	bdata->node_bootmem_map = phys_to_virt(PFN_PHYS(mapstart));
+	bdata->node_min_pfn = start;
+	bdata->node_low_pfn = end;
+	link_bootmem(bdata);
+
+	/*
+	 * Initially all pages are reserved - setup_arch() has to
+	 * register free RAM areas explicitly.
+	 */
+	mapsize = bootmap_bytes(end - start);
+	memset(bdata->node_bootmem_map, 0xff, mapsize);
+
+	bdebug("nid=%td start=%lx map=%lx end=%lx mapsize=%lx\n",
+		bdata - bootmem_node_data, start, mapstart, end, mapsize);
+
+	return mapsize;
+}
+
+/**
+ * init_bootmem_node - register a node as boot memory
+ * @pgdat: node to register
+ * @freepfn: pfn where the bitmap for this node is to be placed
+ * @startpfn: first pfn on the node
+ * @endpfn: first pfn after the node
+ *
+ * Returns the number of bytes needed to hold the bitmap for this node.
+ */
+unsigned long __init init_bootmem_node(pg_data_t *pgdat, unsigned long freepfn,
+				unsigned long startpfn, unsigned long endpfn)
+{
+	return init_bootmem_core(pgdat->bdata, freepfn, startpfn, endpfn);
+}
+
+/**
+ * init_bootmem - register boot memory
+ * @start: pfn where the bitmap is to be placed
+ * @pages: number of available physical pages
+ *
+ * Returns the number of bytes needed to hold the bitmap.
+ */
+unsigned long __init init_bootmem(unsigned long start, unsigned long pages)
+{
+	max_low_pfn = pages;
+	min_low_pfn = start;
+	return init_bootmem_core(NODE_DATA(0)->bdata, start, 0, pages);
+}
+
+/*
+ * free_bootmem_late - free bootmem pages directly to page allocator
+ * @addr: starting physical address of the range
+ * @size: size of the range in bytes
+ *
+ * This is only useful when the bootmem allocator has already been torn
+ * down, but we are still initializing the system.  Pages are given directly
+ * to the page allocator, no bootmem metadata is updated because it is gone.
+ */
+void __init free_bootmem_late(unsigned long physaddr, unsigned long size)
+{
+	unsigned long cursor, end;
+
+	kmemleak_free_part(__va(physaddr), size);
+
+	cursor = PFN_UP(physaddr);
+	end = PFN_DOWN(physaddr + size);
+
+	for (; cursor < end; cursor++) {
+		__free_pages_bootmem(pfn_to_page(cursor), 0);
+		totalram_pages++;
+	}
+}
+
+static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
+{
+	struct page *page;
+	unsigned long *map, start, end, pages, count = 0;
+
+	if (!bdata->node_bootmem_map)
+		return 0;
+
+	map = bdata->node_bootmem_map;
+	start = bdata->node_min_pfn;
+	end = bdata->node_low_pfn;
+
+	bdebug("nid=%td start=%lx end=%lx\n",
+		bdata - bootmem_node_data, start, end);
+
+	while (start < end) {
+		unsigned long idx, vec;
+		unsigned shift;
+
+		idx = start - bdata->node_min_pfn;
+		shift = idx & (BITS_PER_LONG - 1);
+		/*
+		 * vec holds at most BITS_PER_LONG map bits,
+		 * bit 0 corresponds to start.
+		 */
+		vec = ~map[idx / BITS_PER_LONG];
+
+		if (shift) {
+			vec >>= shift;
+			if (end - start >= BITS_PER_LONG)
+				vec |= ~map[idx / BITS_PER_LONG + 1] <<
+					(BITS_PER_LONG - shift);
+		}
+		/*
+		 * If we have a properly aligned and fully unreserved
+		 * BITS_PER_LONG block of pages in front of us, free
+		 * it in one go.
+		 */
+		if (IS_ALIGNED(start, BITS_PER_LONG) && vec == ~0UL) {
+			int order = ilog2(BITS_PER_LONG);
+
+			__free_pages_bootmem(pfn_to_page(start), order);
+			count += BITS_PER_LONG;
+			start += BITS_PER_LONG;
+		} else {
+			unsigned long cur = start;
+
+			start = ALIGN(start + 1, BITS_PER_LONG);
+			while (vec && cur != start) {
+				if (vec & 1) {
+					page = pfn_to_page(cur);
+					__free_pages_bootmem(page, 0);
+					count++;
+				}
+				vec >>= 1;
+				++cur;
+			}
+		}
+	}
+
+	page = virt_to_page(bdata->node_bootmem_map);
+	pages = bdata->node_low_pfn - bdata->node_min_pfn;
+	pages = bootmem_bootmap_pages(pages);
+	count += pages;
+	while (pages--)
+		__free_pages_bootmem(page++, 0);
+
+	bdebug("nid=%td released=%lx\n", bdata - bootmem_node_data, count);
+
+	return count;
+}
+
+static int reset_managed_pages_done __initdata;
+
+void reset_node_managed_pages(pg_data_t *pgdat)
+{
+	struct zone *z;
+
+	for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++)
+		z->managed_pages = 0;
+}
+
+void __init reset_all_zones_managed_pages(void)
+{
+	struct pglist_data *pgdat;
+
+	if (reset_managed_pages_done)
+		return;
+
+	for_each_online_pgdat(pgdat)
+		reset_node_managed_pages(pgdat);
+
+	reset_managed_pages_done = 1;
+}
+
+/**
+ * free_all_bootmem - release free pages to the buddy allocator
+ *
+ * Returns the number of pages actually released.
+ */
+unsigned long __init free_all_bootmem(void)
+{
+	unsigned long total_pages = 0;
+	bootmem_data_t *bdata;
+
+	reset_all_zones_managed_pages();
+
+	list_for_each_entry(bdata, &bdata_list, list)
+		total_pages += free_all_bootmem_core(bdata);
+
+	totalram_pages += total_pages;
+
+	return total_pages;
+}
+
+static void __init __free(bootmem_data_t *bdata,
+			unsigned long sidx, unsigned long eidx)
+{
+	unsigned long idx;
+
+	bdebug("nid=%td start=%lx end=%lx\n", bdata - bootmem_node_data,
+		sidx + bdata->node_min_pfn,
+		eidx + bdata->node_min_pfn);
+
+	if (bdata->hint_idx > sidx)
+		bdata->hint_idx = sidx;
+
+	for (idx = sidx; idx < eidx; idx++)
+		if (!test_and_clear_bit(idx, bdata->node_bootmem_map))
+			BUG();
+}
+
+static int __init __reserve(bootmem_data_t *bdata, unsigned long sidx,
+			unsigned long eidx, int flags)
+{
+	unsigned long idx;
+	int exclusive = flags & BOOTMEM_EXCLUSIVE;
+
+	bdebug("nid=%td start=%lx end=%lx flags=%x\n",
+		bdata - bootmem_node_data,
+		sidx + bdata->node_min_pfn,
+		eidx + bdata->node_min_pfn,
+		flags);
+
+	for (idx = sidx; idx < eidx; idx++)
+		if (test_and_set_bit(idx, bdata->node_bootmem_map)) {
+			if (exclusive) {
+				__free(bdata, sidx, idx);
+				return -EBUSY;
+			}
+			bdebug("silent double reserve of PFN %lx\n",
+				idx + bdata->node_min_pfn);
+		}
+	return 0;
+}
+
+static int __init mark_bootmem_node(bootmem_data_t *bdata,
+				unsigned long start, unsigned long end,
+				int reserve, int flags)
+{
+	unsigned long sidx, eidx;
+
+	bdebug("nid=%td start=%lx end=%lx reserve=%d flags=%x\n",
+		bdata - bootmem_node_data, start, end, reserve, flags);
+
+	BUG_ON(start < bdata->node_min_pfn);
+	BUG_ON(end > bdata->node_low_pfn);
+
+	sidx = start - bdata->node_min_pfn;
+	eidx = end - bdata->node_min_pfn;
+
+	if (reserve)
+		return __reserve(bdata, sidx, eidx, flags);
+	else
+		__free(bdata, sidx, eidx);
+	return 0;
+}
+
+static int __init mark_bootmem(unsigned long start, unsigned long end,
+				int reserve, int flags)
+{
+	unsigned long pos;
+	bootmem_data_t *bdata;
+
+	pos = start;
+	list_for_each_entry(bdata, &bdata_list, list) {
+		int err;
+		unsigned long max;
+
+		if (pos < bdata->node_min_pfn ||
+		    pos >= bdata->node_low_pfn) {
+			BUG_ON(pos != start);
+			continue;
+		}
+
+		max = min(bdata->node_low_pfn, end);
+
+		err = mark_bootmem_node(bdata, pos, max, reserve, flags);
+		if (reserve && err) {
+			mark_bootmem(start, pos, 0, 0);
+			return err;
+		}
+
+		if (max == end)
+			return 0;
+		pos = bdata->node_low_pfn;
+	}
+	BUG();
+}
+
+/**
+ * free_bootmem_node - mark a page range as usable
+ * @pgdat: node the range resides on
+ * @physaddr: starting address of the range
+ * @size: size of the range in bytes
+ *
+ * Partial pages will be considered reserved and left as they are.
+ *
+ * The range must reside completely on the specified node.
+ */
+void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
+			      unsigned long size)
+{
+	unsigned long start, end;
+
+	kmemleak_free_part(__va(physaddr), size);
+
+	start = PFN_UP(physaddr);
+	end = PFN_DOWN(physaddr + size);
+
+	mark_bootmem_node(pgdat->bdata, start, end, 0, 0);
+}
+
+/**
+ * free_bootmem - mark a page range as usable
+ * @addr: starting physical address of the range
+ * @size: size of the range in bytes
+ *
+ * Partial pages will be considered reserved and left as they are.
+ *
+ * The range must be contiguous but may span node boundaries.
+ */
+void __init free_bootmem(unsigned long physaddr, unsigned long size)
+{
+	unsigned long start, end;
+
+	kmemleak_free_part(__va(physaddr), size);
+
+	start = PFN_UP(physaddr);
+	end = PFN_DOWN(physaddr + size);
+
+	mark_bootmem(start, end, 0, 0);
+}
+
+/**
+ * reserve_bootmem_node - mark a page range as reserved
+ * @pgdat: node the range resides on
+ * @physaddr: starting address of the range
+ * @size: size of the range in bytes
+ * @flags: reservation flags (see linux/bootmem.h)
+ *
+ * Partial pages will be reserved.
+ *
+ * The range must reside completely on the specified node.
+ */
+int __init reserve_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
+				 unsigned long size, int flags)
+{
+	unsigned long start, end;
+
+	start = PFN_DOWN(physaddr);
+	end = PFN_UP(physaddr + size);
+
+	return mark_bootmem_node(pgdat->bdata, start, end, 1, flags);
+}
+
+/**
+ * reserve_bootmem - mark a page range as reserved
+ * @addr: starting address of the range
+ * @size: size of the range in bytes
+ * @flags: reservation flags (see linux/bootmem.h)
+ *
+ * Partial pages will be reserved.
+ *
+ * The range must be contiguous but may span node boundaries.
+ */
+int __init reserve_bootmem(unsigned long addr, unsigned long size,
+			    int flags)
+{
+	unsigned long start, end;
+
+	start = PFN_DOWN(addr);
+	end = PFN_UP(addr + size);
+
+	return mark_bootmem(start, end, 1, flags);
+}
+
+static unsigned long __init align_idx(struct bootmem_data *bdata,
+				      unsigned long idx, unsigned long step)
+{
+	unsigned long base = bdata->node_min_pfn;
+
+	/*
+	 * Align the index with respect to the node start so that the
+	 * combination of both satisfies the requested alignment.
+	 */
+
+	return ALIGN(base + idx, step) - base;
+}
+
+static unsigned long __init align_off(struct bootmem_data *bdata,
+				      unsigned long off, unsigned long align)
+{
+	unsigned long base = PFN_PHYS(bdata->node_min_pfn);
+
+	/* Same as align_idx for byte offsets */
+
+	return ALIGN(base + off, align) - base;
+}
+
+static void * __init alloc_bootmem_bdata(struct bootmem_data *bdata,
+					unsigned long size, unsigned long align,
+					unsigned long goal, unsigned long limit)
+{
+	unsigned long fallback = 0;
+	unsigned long min, max, start, sidx, midx, step;
+
+	bdebug("nid=%td size=%lx [%lu pages] align=%lx goal=%lx limit=%lx\n",
+		bdata - bootmem_node_data, size, PAGE_ALIGN(size) >> PAGE_SHIFT,
+		align, goal, limit);
+
+	BUG_ON(!size);
+	BUG_ON(align & (align - 1));
+	BUG_ON(limit && goal + size > limit);
+
+	if (!bdata->node_bootmem_map)
+		return NULL;
+
+	min = bdata->node_min_pfn;
+	max = bdata->node_low_pfn;
+
+	goal >>= PAGE_SHIFT;
+	limit >>= PAGE_SHIFT;
+
+	if (limit && max > limit)
+		max = limit;
+	if (max <= min)
+		return NULL;
+
+	step = max(align >> PAGE_SHIFT, 1UL);
+
+	if (goal && min < goal && goal < max)
+		start = ALIGN(goal, step);
+	else
+		start = ALIGN(min, step);
+
+	sidx = start - bdata->node_min_pfn;
+	midx = max - bdata->node_min_pfn;
+
+	if (bdata->hint_idx > sidx) {
+		/*
+		 * Handle the valid case of sidx being zero and still
+		 * catch the fallback below.
+		 */
+		fallback = sidx + 1;
+		sidx = align_idx(bdata, bdata->hint_idx, step);
+	}
+
+	while (1) {
+		int merge;
+		void *region;
+		unsigned long eidx, i, start_off, end_off;
+find_block:
+		sidx = find_next_zero_bit(bdata->node_bootmem_map, midx, sidx);
+		sidx = align_idx(bdata, sidx, step);
+		eidx = sidx + PFN_UP(size);
+
+		if (sidx >= midx || eidx > midx)
+			break;
+
+		for (i = sidx; i < eidx; i++)
+			if (test_bit(i, bdata->node_bootmem_map)) {
+				sidx = align_idx(bdata, i, step);
+				if (sidx == i)
+					sidx += step;
+				goto find_block;
+			}
+
+		if (bdata->last_end_off & (PAGE_SIZE - 1) &&
+				PFN_DOWN(bdata->last_end_off) + 1 == sidx)
+			start_off = align_off(bdata, bdata->last_end_off, align);
+		else
+			start_off = PFN_PHYS(sidx);
+
+		merge = PFN_DOWN(start_off) < sidx;
+		end_off = start_off + size;
+
+		bdata->last_end_off = end_off;
+		bdata->hint_idx = PFN_UP(end_off);
+
+		/*
+		 * Reserve the area now:
+		 */
+		if (__reserve(bdata, PFN_DOWN(start_off) + merge,
+				PFN_UP(end_off), BOOTMEM_EXCLUSIVE))
+			BUG();
+
+		region = phys_to_virt(PFN_PHYS(bdata->node_min_pfn) +
+				start_off);
+		memset(region, 0, size);
+		/*
+		 * The min_count is set to 0 so that bootmem allocated blocks
+		 * are never reported as leaks.
+		 */
+		kmemleak_alloc(region, size, 0, 0);
+		return region;
+	}
+
+	if (fallback) {
+		sidx = align_idx(bdata, fallback - 1, step);
+		fallback = 0;
+		goto find_block;
+	}
+
+	return NULL;
+}
+
+static void * __init alloc_bootmem_core(unsigned long size,
+					unsigned long align,
+					unsigned long goal,
+					unsigned long limit)
+{
+	bootmem_data_t *bdata;
+	void *region;
+
+	if (WARN_ON_ONCE(slab_is_available()))
+		return kzalloc(size, GFP_NOWAIT);
+
+	list_for_each_entry(bdata, &bdata_list, list) {
+		if (goal && bdata->node_low_pfn <= PFN_DOWN(goal))
+			continue;
+		if (limit && bdata->node_min_pfn >= PFN_DOWN(limit))
+			break;
+
+		region = alloc_bootmem_bdata(bdata, size, align, goal, limit);
+		if (region)
+			return region;
+	}
+
+	return NULL;
+}
+
+static void * __init ___alloc_bootmem_nopanic(unsigned long size,
+					      unsigned long align,
+					      unsigned long goal,
+					      unsigned long limit)
+{
+	void *ptr;
+
+restart:
+	ptr = alloc_bootmem_core(size, align, goal, limit);
+	if (ptr)
+		return ptr;
+	if (goal) {
+		goal = 0;
+		goto restart;
+	}
+
+	return NULL;
+}
+
+/**
+ * __alloc_bootmem_nopanic - allocate boot memory without panicking
+ * @size: size of the request in bytes
+ * @align: alignment of the region
+ * @goal: preferred starting address of the region
+ *
+ * The goal is dropped if it can not be satisfied and the allocation will
+ * fall back to memory below @goal.
+ *
+ * Allocation may happen on any node in the system.
+ *
+ * Returns NULL on failure.
+ */
+void * __init __alloc_bootmem_nopanic(unsigned long size, unsigned long align,
+					unsigned long goal)
+{
+	unsigned long limit = 0;
+
+	return ___alloc_bootmem_nopanic(size, align, goal, limit);
+}
+
+static void * __init ___alloc_bootmem(unsigned long size, unsigned long align,
+					unsigned long goal, unsigned long limit)
+{
+	void *mem = ___alloc_bootmem_nopanic(size, align, goal, limit);
+
+	if (mem)
+		return mem;
+	/*
+	 * Whoops, we cannot satisfy the allocation request.
+	 */
+	printk(KERN_ALERT "bootmem alloc of %lu bytes failed!\n", size);
+	panic("Out of memory");
+	return NULL;
+}
+
+/**
+ * __alloc_bootmem - allocate boot memory
+ * @size: size of the request in bytes
+ * @align: alignment of the region
+ * @goal: preferred starting address of the region
+ *
+ * The goal is dropped if it can not be satisfied and the allocation will
+ * fall back to memory below @goal.
+ *
+ * Allocation may happen on any node in the system.
+ *
+ * The function panics if the request can not be satisfied.
+ */
+void * __init __alloc_bootmem(unsigned long size, unsigned long align,
+			      unsigned long goal)
+{
+	unsigned long limit = 0;
+
+	return ___alloc_bootmem(size, align, goal, limit);
+}
+
+void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat,
+				unsigned long size, unsigned long align,
+				unsigned long goal, unsigned long limit)
+{
+	void *ptr;
+
+	if (WARN_ON_ONCE(slab_is_available()))
+		return kzalloc(size, GFP_NOWAIT);
+again:
+
+	/* do not panic in alloc_bootmem_bdata() */
+	if (limit && goal + size > limit)
+		limit = 0;
+
+	ptr = alloc_bootmem_bdata(pgdat->bdata, size, align, goal, limit);
+	if (ptr)
+		return ptr;
+
+	ptr = alloc_bootmem_core(size, align, goal, limit);
+	if (ptr)
+		return ptr;
+
+	if (goal) {
+		goal = 0;
+		goto again;
+	}
+
+	return NULL;
+}
+
+void * __init __alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size,
+				   unsigned long align, unsigned long goal)
+{
+	if (WARN_ON_ONCE(slab_is_available()))
+		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
+
+	return ___alloc_bootmem_node_nopanic(pgdat, size, align, goal, 0);
+}
+
+void * __init ___alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
+				    unsigned long align, unsigned long goal,
+				    unsigned long limit)
+{
+	void *ptr;
+
+	ptr = ___alloc_bootmem_node_nopanic(pgdat, size, align, goal, 0);
+	if (ptr)
+		return ptr;
+
+	printk(KERN_ALERT "bootmem alloc of %lu bytes failed!\n", size);
+	panic("Out of memory");
+	return NULL;
+}
+
+/**
+ * __alloc_bootmem_node - allocate boot memory from a specific node
+ * @pgdat: node to allocate from
+ * @size: size of the request in bytes
+ * @align: alignment of the region
+ * @goal: preferred starting address of the region
+ *
+ * The goal is dropped if it can not be satisfied and the allocation will
+ * fall back to memory below @goal.
+ *
+ * Allocation may fall back to any node in the system if the specified node
+ * can not hold the requested memory.
+ *
+ * The function panics if the request can not be satisfied.
+ */
+void * __init __alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
+				   unsigned long align, unsigned long goal)
+{
+	if (WARN_ON_ONCE(slab_is_available()))
+		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
+
+	return  ___alloc_bootmem_node(pgdat, size, align, goal, 0);
+}
+
+void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size,
+				   unsigned long align, unsigned long goal)
+{
+#ifdef MAX_DMA32_PFN
+	unsigned long end_pfn;
+
+	if (WARN_ON_ONCE(slab_is_available()))
+		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
+
+	/* update goal according ...MAX_DMA32_PFN */
+	end_pfn = pgdat_end_pfn(pgdat);
+
+	if (end_pfn > MAX_DMA32_PFN + (128 >> (20 - PAGE_SHIFT)) &&
+	    (goal >> PAGE_SHIFT) < MAX_DMA32_PFN) {
+		void *ptr;
+		unsigned long new_goal;
+
+		new_goal = MAX_DMA32_PFN << PAGE_SHIFT;
+		ptr = alloc_bootmem_bdata(pgdat->bdata, size, align,
+						 new_goal, 0);
+		if (ptr)
+			return ptr;
+	}
+#endif
+
+	return __alloc_bootmem_node(pgdat, size, align, goal);
+
+}
+
+#ifndef ARCH_LOW_ADDRESS_LIMIT
+#define ARCH_LOW_ADDRESS_LIMIT	0xffffffffUL
+#endif
+
+/**
+ * __alloc_bootmem_low - allocate low boot memory
+ * @size: size of the request in bytes
+ * @align: alignment of the region
+ * @goal: preferred starting address of the region
+ *
+ * The goal is dropped if it can not be satisfied and the allocation will
+ * fall back to memory below @goal.
+ *
+ * Allocation may happen on any node in the system.
+ *
+ * The function panics if the request can not be satisfied.
+ */
+void * __init __alloc_bootmem_low(unsigned long size, unsigned long align,
+				  unsigned long goal)
+{
+	return ___alloc_bootmem(size, align, goal, ARCH_LOW_ADDRESS_LIMIT);
+}
+
+void * __init __alloc_bootmem_low_nopanic(unsigned long size,
+					  unsigned long align,
+					  unsigned long goal)
+{
+	return ___alloc_bootmem_nopanic(size, align, goal,
+					ARCH_LOW_ADDRESS_LIMIT);
+}
+
+/**
+ * __alloc_bootmem_low_node - allocate low boot memory from a specific node
+ * @pgdat: node to allocate from
+ * @size: size of the request in bytes
+ * @align: alignment of the region
+ * @goal: preferred starting address of the region
+ *
+ * The goal is dropped if it can not be satisfied and the allocation will
+ * fall back to memory below @goal.
+ *
+ * Allocation may fall back to any node in the system if the specified node
+ * can not hold the requested memory.
+ *
+ * The function panics if the request can not be satisfied.
+ */
+void * __init __alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long size,
+				       unsigned long align, unsigned long goal)
+{
+	if (WARN_ON_ONCE(slab_is_available()))
+		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
+
+	return ___alloc_bootmem_node(pgdat, size, align,
+				     goal, ARCH_LOW_ADDRESS_LIMIT);
+}

mm/cleancache.c

@@ -0,0 +1,409 @@
+/*
+ * Cleancache frontend
+ *
+ * This code provides the generic "frontend" layer to call a matching
+ * "backend" driver implementation of cleancache.  See
+ * Documentation/vm/cleancache.txt for more information.
+ *
+ * Copyright (C) 2009-2010 Oracle Corp. All rights reserved.
+ * Author: Dan Magenheimer
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ */
+
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/exportfs.h>
+#include <linux/mm.h>
+#include <linux/debugfs.h>
+#include <linux/cleancache.h>
+
+/*
+ * cleancache_ops is set by cleancache_ops_register to contain the pointers
+ * to the cleancache "backend" implementation functions.
+ */
+static struct cleancache_ops *cleancache_ops __read_mostly;
+
+/*
+ * Counters available via /sys/kernel/debug/frontswap (if debugfs is
+ * properly configured.  These are for information only so are not protected
+ * against increment races.
+ */
+static u64 cleancache_succ_gets;
+static u64 cleancache_failed_gets;
+static u64 cleancache_puts;
+static u64 cleancache_invalidates;
+
+/*
+ * When no backend is registered all calls to init_fs and init_shared_fs
+ * are registered and fake poolids (FAKE_FS_POOLID_OFFSET or
+ * FAKE_SHARED_FS_POOLID_OFFSET, plus offset in the respective array
+ * [shared_|]fs_poolid_map) are given to the respective super block
+ * (sb->cleancache_poolid) and no tmem_pools are created. When a backend
+ * registers with cleancache the previous calls to init_fs and init_shared_fs
+ * are executed to create tmem_pools and set the respective poolids. While no
+ * backend is registered all "puts", "gets" and "flushes" are ignored or failed.
+ */
+#define MAX_INITIALIZABLE_FS 32
+#define FAKE_FS_POOLID_OFFSET 1000
+#define FAKE_SHARED_FS_POOLID_OFFSET 2000
+
+#define FS_NO_BACKEND (-1)
+#define FS_UNKNOWN (-2)
+static int fs_poolid_map[MAX_INITIALIZABLE_FS];
+static int shared_fs_poolid_map[MAX_INITIALIZABLE_FS];
+static char *uuids[MAX_INITIALIZABLE_FS];
+/*
+ * Mutex for the [shared_|]fs_poolid_map to guard against multiple threads
+ * invoking umount (and ending in __cleancache_invalidate_fs) and also multiple
+ * threads calling mount (and ending up in __cleancache_init_[shared|]fs).
+ */
+static DEFINE_MUTEX(poolid_mutex);
+/*
+ * When set to false (default) all calls to the cleancache functions, except
+ * the __cleancache_invalidate_fs and __cleancache_init_[shared|]fs are guarded
+ * by the if (!cleancache_ops) return. This means multiple threads (from
+ * different filesystems) will be checking cleancache_ops. The usage of a
+ * bool instead of a atomic_t or a bool guarded by a spinlock is OK - we are
+ * OK if the time between the backend's have been initialized (and
+ * cleancache_ops has been set to not NULL) and when the filesystems start
+ * actually calling the backends. The inverse (when unloading) is obviously
+ * not good - but this shim does not do that (yet).
+ */
+
+/*
+ * The backends and filesystems work all asynchronously. This is b/c the
+ * backends can be built as modules.
+ * The usual sequence of events is:
+ *	a) mount /	-> __cleancache_init_fs is called. We set the
+ *		[shared_|]fs_poolid_map and uuids for.
+ *
+ *	b). user does I/Os -> we call the rest of __cleancache_* functions
+ *		which return immediately as cleancache_ops is false.
+ *
+ *	c). modprobe zcache -> cleancache_register_ops. We init the backend
+ *		and set cleancache_ops to true, and for any fs_poolid_map
+ *		(which is set by __cleancache_init_fs) we initialize the poolid.
+ *
+ *	d). user does I/Os -> now that cleancache_ops is true all the
+ *		__cleancache_* functions can call the backend. They all check
+ *		that fs_poolid_map is valid and if so invoke the backend.
+ *
+ *	e). umount /	-> __cleancache_invalidate_fs, the fs_poolid_map is
+ *		reset (which is the second check in the __cleancache_* ops
+ *		to call the backend).
+ *
+ * The sequence of event could also be c), followed by a), and d). and e). The
+ * c) would not happen anymore. There is also the chance of c), and one thread
+ * doing a) + d), and another doing e). For that case we depend on the
+ * filesystem calling __cleancache_invalidate_fs in the proper sequence (so
+ * that it handles all I/Os before it invalidates the fs (which is last part
+ * of unmounting process).
+ *
+ * Note: The acute reader will notice that there is no "rmmod zcache" case.
+ * This is b/c the functionality for that is not yet implemented and when
+ * done, will require some extra locking not yet devised.
+ */
+
+/*
+ * Register operations for cleancache, returning previous thus allowing
+ * detection of multiple backends and possible nesting.
+ */
+struct cleancache_ops *cleancache_register_ops(struct cleancache_ops *ops)
+{
+	struct cleancache_ops *old = cleancache_ops;
+	int i;
+
+	mutex_lock(&poolid_mutex);
+	for (i = 0; i < MAX_INITIALIZABLE_FS; i++) {
+		if (fs_poolid_map[i] == FS_NO_BACKEND)
+			fs_poolid_map[i] = ops->init_fs(PAGE_SIZE);
+		if (shared_fs_poolid_map[i] == FS_NO_BACKEND)
+			shared_fs_poolid_map[i] = ops->init_shared_fs
+					(uuids[i], PAGE_SIZE);
+	}
+	/*
+	 * We MUST set cleancache_ops _after_ we have called the backends
+	 * init_fs or init_shared_fs functions. Otherwise the compiler might
+	 * re-order where cleancache_ops is set in this function.
+	 */
+	barrier();
+	cleancache_ops = ops;
+	mutex_unlock(&poolid_mutex);
+	return old;
+}
+EXPORT_SYMBOL(cleancache_register_ops);
+
+/* Called by a cleancache-enabled filesystem at time of mount */
+void __cleancache_init_fs(struct super_block *sb)
+{
+	int i;
+
+	mutex_lock(&poolid_mutex);
+	for (i = 0; i < MAX_INITIALIZABLE_FS; i++) {
+		if (fs_poolid_map[i] == FS_UNKNOWN) {
+			sb->cleancache_poolid = i + FAKE_FS_POOLID_OFFSET;
+			if (cleancache_ops)
+				fs_poolid_map[i] = cleancache_ops->init_fs(PAGE_SIZE);
+			else
+				fs_poolid_map[i] = FS_NO_BACKEND;
+			break;
+		}
+	}
+	mutex_unlock(&poolid_mutex);
+}
+EXPORT_SYMBOL(__cleancache_init_fs);
+
+/* Called by a cleancache-enabled clustered filesystem at time of mount */
+void __cleancache_init_shared_fs(char *uuid, struct super_block *sb)
+{
+	int i;
+
+	mutex_lock(&poolid_mutex);
+	for (i = 0; i < MAX_INITIALIZABLE_FS; i++) {
+		if (shared_fs_poolid_map[i] == FS_UNKNOWN) {
+			sb->cleancache_poolid = i + FAKE_SHARED_FS_POOLID_OFFSET;
+			uuids[i] = uuid;
+			if (cleancache_ops)
+				shared_fs_poolid_map[i] = cleancache_ops->init_shared_fs
+						(uuid, PAGE_SIZE);
+			else
+				shared_fs_poolid_map[i] = FS_NO_BACKEND;
+			break;
+		}
+	}
+	mutex_unlock(&poolid_mutex);
+}
+EXPORT_SYMBOL(__cleancache_init_shared_fs);
+
+/*
+ * If the filesystem uses exportable filehandles, use the filehandle as
+ * the key, else use the inode number.
+ */
+static int cleancache_get_key(struct inode *inode,
+			      struct cleancache_filekey *key)
+{
+	int (*fhfn)(struct inode *, __u32 *fh, int *, struct inode *);
+	int len = 0, maxlen = CLEANCACHE_KEY_MAX;
+	struct super_block *sb = inode->i_sb;
+
+	key->u.ino = inode->i_ino;
+	if (sb->s_export_op != NULL) {
+		fhfn = sb->s_export_op->encode_fh;
+		if  (fhfn) {
+			len = (*fhfn)(inode, &key->u.fh[0], &maxlen, NULL);
+			if (len <= FILEID_ROOT || len == FILEID_INVALID)
+				return -1;
+			if (maxlen > CLEANCACHE_KEY_MAX)
+				return -1;
+		}
+	}
+	return 0;
+}
+
+/*
+ * Returns a pool_id that is associated with a given fake poolid.
+ */
+static int get_poolid_from_fake(int fake_pool_id)
+{
+	if (fake_pool_id >= FAKE_SHARED_FS_POOLID_OFFSET)
+		return shared_fs_poolid_map[fake_pool_id -
+			FAKE_SHARED_FS_POOLID_OFFSET];
+	else if (fake_pool_id >= FAKE_FS_POOLID_OFFSET)
+		return fs_poolid_map[fake_pool_id - FAKE_FS_POOLID_OFFSET];
+	return FS_NO_BACKEND;
+}
+
+/*
+ * "Get" data from cleancache associated with the poolid/inode/index
+ * that were specified when the data was put to cleanache and, if
+ * successful, use it to fill the specified page with data and return 0.
+ * The pageframe is unchanged and returns -1 if the get fails.
+ * Page must be locked by caller.
+ *
+ * The function has two checks before any action is taken - whether
+ * a backend is registered and whether the sb->cleancache_poolid
+ * is correct.
+ */
+int __cleancache_get_page(struct page *page)
+{
+	int ret = -1;
+	int pool_id;
+	int fake_pool_id;
+	struct cleancache_filekey key = { .u.key = { 0 } };
+
+	if (!cleancache_ops) {
+		cleancache_failed_gets++;
+		goto out;
+	}
+
+	VM_BUG_ON_PAGE(!PageLocked(page), page);
+	fake_pool_id = page->mapping->host->i_sb->cleancache_poolid;
+	if (fake_pool_id < 0)
+		goto out;
+	pool_id = get_poolid_from_fake(fake_pool_id);
+
+	if (cleancache_get_key(page->mapping->host, &key) < 0)
+		goto out;
+
+	if (pool_id >= 0)
+		ret = cleancache_ops->get_page(pool_id,
+				key, page->index, page);
+	if (ret == 0)
+		cleancache_succ_gets++;
+	else
+		cleancache_failed_gets++;
+out:
+	return ret;
+}
+EXPORT_SYMBOL(__cleancache_get_page);
+
+/*
+ * "Put" data from a page to cleancache and associate it with the
+ * (previously-obtained per-filesystem) poolid and the page's,
+ * inode and page index.  Page must be locked.  Note that a put_page
+ * always "succeeds", though a subsequent get_page may succeed or fail.
+ *
+ * The function has two checks before any action is taken - whether
+ * a backend is registered and whether the sb->cleancache_poolid
+ * is correct.
+ */
+void __cleancache_put_page(struct page *page)
+{
+	int pool_id;
+	int fake_pool_id;
+	struct cleancache_filekey key = { .u.key = { 0 } };
+
+	if (!cleancache_ops) {
+		cleancache_puts++;
+		return;
+	}
+
+	VM_BUG_ON_PAGE(!PageLocked(page), page);
+	fake_pool_id = page->mapping->host->i_sb->cleancache_poolid;
+	if (fake_pool_id < 0)
+		return;
+
+	pool_id = get_poolid_from_fake(fake_pool_id);
+
+	if (pool_id >= 0 &&
+		cleancache_get_key(page->mapping->host, &key) >= 0) {
+		cleancache_ops->put_page(pool_id, key, page->index, page);
+		cleancache_puts++;
+	}
+}
+EXPORT_SYMBOL(__cleancache_put_page);
+
+/*
+ * Invalidate any data from cleancache associated with the poolid and the
+ * page's inode and page index so that a subsequent "get" will fail.
+ *
+ * The function has two checks before any action is taken - whether
+ * a backend is registered and whether the sb->cleancache_poolid
+ * is correct.
+ */
+void __cleancache_invalidate_page(struct address_space *mapping,
+					struct page *page)
+{
+	/* careful... page->mapping is NULL sometimes when this is called */
+	int pool_id;
+	int fake_pool_id = mapping->host->i_sb->cleancache_poolid;
+	struct cleancache_filekey key = { .u.key = { 0 } };
+
+	if (!cleancache_ops)
+		return;
+
+	if (fake_pool_id >= 0) {
+		pool_id = get_poolid_from_fake(fake_pool_id);
+		if (pool_id < 0)
+			return;
+
+		VM_BUG_ON_PAGE(!PageLocked(page), page);
+		if (cleancache_get_key(mapping->host, &key) >= 0) {
+			cleancache_ops->invalidate_page(pool_id,
+					key, page->index);
+			cleancache_invalidates++;
+		}
+	}
+}
+EXPORT_SYMBOL(__cleancache_invalidate_page);
+
+/*
+ * Invalidate all data from cleancache associated with the poolid and the
+ * mappings's inode so that all subsequent gets to this poolid/inode
+ * will fail.
+ *
+ * The function has two checks before any action is taken - whether
+ * a backend is registered and whether the sb->cleancache_poolid
+ * is correct.
+ */
+void __cleancache_invalidate_inode(struct address_space *mapping)
+{
+	int pool_id;
+	int fake_pool_id = mapping->host->i_sb->cleancache_poolid;
+	struct cleancache_filekey key = { .u.key = { 0 } };
+
+	if (!cleancache_ops)
+		return;
+
+	if (fake_pool_id < 0)
+		return;
+
+	pool_id = get_poolid_from_fake(fake_pool_id);
+
+	if (pool_id >= 0 && cleancache_get_key(mapping->host, &key) >= 0)
+		cleancache_ops->invalidate_inode(pool_id, key);
+}
+EXPORT_SYMBOL(__cleancache_invalidate_inode);
+
+/*
+ * Called by any cleancache-enabled filesystem at time of unmount;
+ * note that pool_id is surrendered and may be returned by a subsequent
+ * cleancache_init_fs or cleancache_init_shared_fs.
+ */
+void __cleancache_invalidate_fs(struct super_block *sb)
+{
+	int index;
+	int fake_pool_id = sb->cleancache_poolid;
+	int old_poolid = fake_pool_id;
+
+	mutex_lock(&poolid_mutex);
+	if (fake_pool_id >= FAKE_SHARED_FS_POOLID_OFFSET) {
+		index = fake_pool_id - FAKE_SHARED_FS_POOLID_OFFSET;
+		old_poolid = shared_fs_poolid_map[index];
+		shared_fs_poolid_map[index] = FS_UNKNOWN;
+		uuids[index] = NULL;
+	} else if (fake_pool_id >= FAKE_FS_POOLID_OFFSET) {
+		index = fake_pool_id - FAKE_FS_POOLID_OFFSET;
+		old_poolid = fs_poolid_map[index];
+		fs_poolid_map[index] = FS_UNKNOWN;
+	}
+	sb->cleancache_poolid = -1;
+	if (cleancache_ops)
+		cleancache_ops->invalidate_fs(old_poolid);
+	mutex_unlock(&poolid_mutex);
+}
+EXPORT_SYMBOL(__cleancache_invalidate_fs);
+
+static int __init init_cleancache(void)
+{
+	int i;
+
+#ifdef CONFIG_DEBUG_FS
+	struct dentry *root = debugfs_create_dir("cleancache", NULL);
+	if (root == NULL)
+		return -ENXIO;
+	debugfs_create_u64("succ_gets", S_IRUGO, root, &cleancache_succ_gets);
+	debugfs_create_u64("failed_gets", S_IRUGO,
+				root, &cleancache_failed_gets);
+	debugfs_create_u64("puts", S_IRUGO, root, &cleancache_puts);
+	debugfs_create_u64("invalidates", S_IRUGO,
+				root, &cleancache_invalidates);
+#endif
+	for (i = 0; i < MAX_INITIALIZABLE_FS; i++) {
+		fs_poolid_map[i] = FS_UNKNOWN;
+		shared_fs_poolid_map[i] = FS_UNKNOWN;
+	}
+	return 0;
+}
+module_init(init_cleancache)

mm/cma.c

@@ -0,0 +1,430 @@
+/*
+ * Contiguous Memory Allocator
+ *
+ * Copyright (c) 2010-2011 by Samsung Electronics.
+ * Copyright IBM Corporation, 2013
+ * Copyright LG Electronics Inc., 2014
+ * Written by:
+ *	Marek Szyprowski <m.szyprowski@samsung.com>
+ *	Michal Nazarewicz <mina86@mina86.com>
+ *	Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
+ *	Joonsoo Kim <iamjoonsoo.kim@lge.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of the
+ * License or (at your optional) any later version of the license.
+ */
+
+#define pr_fmt(fmt) "cma: " fmt
+
+#ifdef CONFIG_CMA_DEBUG
+#ifndef DEBUG
+#  define DEBUG
+#endif
+#endif
+
+#include <linux/memblock.h>
+#include <linux/err.h>
+#include <linux/mm.h>
+#include <linux/mutex.h>
+#include <linux/sizes.h>
+#include <linux/slab.h>
+#include <linux/log2.h>
+#include <linux/cma.h>
+#include <linux/highmem.h>
+
+struct cma {
+	unsigned long	base_pfn;
+	unsigned long	count;
+	unsigned long	*bitmap;
+	unsigned int order_per_bit; /* Order of pages represented by one bit */
+	struct mutex	lock;
+};
+
+static struct cma cma_areas[MAX_CMA_AREAS];
+static unsigned cma_area_count;
+static DEFINE_MUTEX(cma_mutex);
+
+phys_addr_t cma_get_base(struct cma *cma)
+{
+	return PFN_PHYS(cma->base_pfn);
+}
+
+unsigned long cma_get_size(struct cma *cma)
+{
+	return cma->count << PAGE_SHIFT;
+}
+
+static unsigned long cma_bitmap_aligned_mask(struct cma *cma, int align_order)
+{
+	if (align_order <= cma->order_per_bit)
+		return 0;
+	return (1UL << (align_order - cma->order_per_bit)) - 1;
+}
+
+static unsigned long cma_bitmap_maxno(struct cma *cma)
+{
+	return cma->count >> cma->order_per_bit;
+}
+
+static unsigned long cma_bitmap_pages_to_bits(struct cma *cma,
+						unsigned long pages)
+{
+	return ALIGN(pages, 1UL << cma->order_per_bit) >> cma->order_per_bit;
+}
+
+static void cma_clear_bitmap(struct cma *cma, unsigned long pfn, int count)
+{
+	unsigned long bitmap_no, bitmap_count;
+
+	bitmap_no = (pfn - cma->base_pfn) >> cma->order_per_bit;
+	bitmap_count = cma_bitmap_pages_to_bits(cma, count);
+
+	mutex_lock(&cma->lock);
+	bitmap_clear(cma->bitmap, bitmap_no, bitmap_count);
+	mutex_unlock(&cma->lock);
+}
+
+static int __init cma_activate_area(struct cma *cma)
+{
+	int bitmap_size = BITS_TO_LONGS(cma_bitmap_maxno(cma)) * sizeof(long);
+	unsigned long base_pfn = cma->base_pfn, pfn = base_pfn;
+	unsigned i = cma->count >> pageblock_order;
+	struct zone *zone;
+
+	cma->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
+
+	if (!cma->bitmap)
+		return -ENOMEM;
+
+	WARN_ON_ONCE(!pfn_valid(pfn));
+	zone = page_zone(pfn_to_page(pfn));
+
+	do {
+		unsigned j;
+
+		base_pfn = pfn;
+		for (j = pageblock_nr_pages; j; --j, pfn++) {
+			WARN_ON_ONCE(!pfn_valid(pfn));
+			/*
+			 * alloc_contig_range requires the pfn range
+			 * specified to be in the same zone. Make this
+			 * simple by forcing the entire CMA resv range
+			 * to be in the same zone.
+			 */
+			if (page_zone(pfn_to_page(pfn)) != zone)
+				goto err;
+		}
+		init_cma_reserved_pageblock(pfn_to_page(base_pfn));
+	} while (--i);
+
+	mutex_init(&cma->lock);
+	return 0;
+
+err:
+	kfree(cma->bitmap);
+	cma->count = 0;
+	return -EINVAL;
+}
+
+static int __init cma_init_reserved_areas(void)
+{
+	int i;
+
+	for (i = 0; i < cma_area_count; i++) {
+		int ret = cma_activate_area(&cma_areas[i]);
+
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+core_initcall(cma_init_reserved_areas);
+
+/**
+ * cma_init_reserved_mem() - create custom contiguous area from reserved memory
+ * @base: Base address of the reserved area
+ * @size: Size of the reserved area (in bytes),
+ * @order_per_bit: Order of pages represented by one bit on bitmap.
+ * @res_cma: Pointer to store the created cma region.
+ *
+ * This function creates custom contiguous area from already reserved memory.
+ */
+int __init cma_init_reserved_mem(phys_addr_t base, phys_addr_t size,
+				 int order_per_bit, struct cma **res_cma)
+{
+	struct cma *cma;
+	phys_addr_t alignment;
+
+	/* Sanity checks */
+	if (cma_area_count == ARRAY_SIZE(cma_areas)) {
+		pr_err("Not enough slots for CMA reserved regions!\n");
+		return -ENOSPC;
+	}
+
+	if (!size || !memblock_is_region_reserved(base, size))
+		return -EINVAL;
+
+	/* ensure minimal alignment requied by mm core */
+	alignment = PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order);
+
+	/* alignment should be aligned with order_per_bit */
+	if (!IS_ALIGNED(alignment >> PAGE_SHIFT, 1 << order_per_bit))
+		return -EINVAL;
+
+	if (ALIGN(base, alignment) != base || ALIGN(size, alignment) != size)
+		return -EINVAL;
+
+	/*
+	 * Each reserved area must be initialised later, when more kernel
+	 * subsystems (like slab allocator) are available.
+	 */
+	cma = &cma_areas[cma_area_count];
+	cma->base_pfn = PFN_DOWN(base);
+	cma->count = size >> PAGE_SHIFT;
+	cma->order_per_bit = order_per_bit;
+	*res_cma = cma;
+	cma_area_count++;
+
+	return 0;
+}
+
+/**
+ * cma_declare_contiguous() - reserve custom contiguous area
+ * @base: Base address of the reserved area optional, use 0 for any
+ * @size: Size of the reserved area (in bytes),
+ * @limit: End address of the reserved memory (optional, 0 for any).
+ * @alignment: Alignment for the CMA area, should be power of 2 or zero
+ * @order_per_bit: Order of pages represented by one bit on bitmap.
+ * @fixed: hint about where to place the reserved area
+ * @res_cma: Pointer to store the created cma region.
+ *
+ * This function reserves memory from early allocator. It should be
+ * called by arch specific code once the early allocator (memblock or bootmem)
+ * has been activated and all other subsystems have already allocated/reserved
+ * memory. This function allows to create custom reserved areas.
+ *
+ * If @fixed is true, reserve contiguous area at exactly @base.  If false,
+ * reserve in range from @base to @limit.
+ */
+int __init cma_declare_contiguous(phys_addr_t base,
+			phys_addr_t size, phys_addr_t limit,
+			phys_addr_t alignment, unsigned int order_per_bit,
+			bool fixed, struct cma **res_cma)
+{
+	phys_addr_t memblock_end = memblock_end_of_DRAM();
+	phys_addr_t highmem_start;
+	int ret = 0;
+
+#ifdef CONFIG_X86
+	/*
+	 * high_memory isn't direct mapped memory so retrieving its physical
+	 * address isn't appropriate.  But it would be useful to check the
+	 * physical address of the highmem boundary so it's justfiable to get
+	 * the physical address from it.  On x86 there is a validation check for
+	 * this case, so the following workaround is needed to avoid it.
+	 */
+	highmem_start = __pa_nodebug(high_memory);
+#else
+	highmem_start = __pa(high_memory);
+#endif
+	pr_debug("%s(size %pa, base %pa, limit %pa alignment %pa)\n",
+		__func__, &size, &base, &limit, &alignment);
+
+	if (cma_area_count == ARRAY_SIZE(cma_areas)) {
+		pr_err("Not enough slots for CMA reserved regions!\n");
+		return -ENOSPC;
+	}
+
+	if (!size)
+		return -EINVAL;
+
+	if (alignment && !is_power_of_2(alignment))
+		return -EINVAL;
+
+	/*
+	 * Sanitise input arguments.
+	 * Pages both ends in CMA area could be merged into adjacent unmovable
+	 * migratetype page by page allocator's buddy algorithm. In the case,
+	 * you couldn't get a contiguous memory, which is not what we want.
+	 */
+	alignment = max(alignment,
+		(phys_addr_t)PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order));
+	base = ALIGN(base, alignment);
+	size = ALIGN(size, alignment);
+	limit &= ~(alignment - 1);
+
+	if (!base)
+		fixed = false;
+
+	/* size should be aligned with order_per_bit */
+	if (!IS_ALIGNED(size >> PAGE_SHIFT, 1 << order_per_bit))
+		return -EINVAL;
+
+	/*
+	 * If allocating at a fixed base the request region must not cross the
+	 * low/high memory boundary.
+	 */
+	if (fixed && base < highmem_start && base + size > highmem_start) {
+		ret = -EINVAL;
+		pr_err("Region at %pa defined on low/high memory boundary (%pa)\n",
+			&base, &highmem_start);
+		goto err;
+	}
+
+	/*
+	 * If the limit is unspecified or above the memblock end, its effective
+	 * value will be the memblock end. Set it explicitly to simplify further
+	 * checks.
+	 */
+	if (limit == 0 || limit > memblock_end)
+		limit = memblock_end;
+
+	/* Reserve memory */
+	if (fixed) {
+		if (memblock_is_region_reserved(base, size) ||
+		    memblock_reserve(base, size) < 0) {
+			ret = -EBUSY;
+			goto err;
+		}
+	} else {
+		phys_addr_t addr = 0;
+
+		/*
+		 * All pages in the reserved area must come from the same zone.
+		 * If the requested region crosses the low/high memory boundary,
+		 * try allocating from high memory first and fall back to low
+		 * memory in case of failure.
+		 */
+		if (base < highmem_start && limit > highmem_start) {
+			addr = memblock_alloc_range(size, alignment,
+						    highmem_start, limit);
+			limit = highmem_start;
+		}
+
+		if (!addr) {
+			addr = memblock_alloc_range(size, alignment, base,
+						    limit);
+			if (!addr) {
+				ret = -ENOMEM;
+				goto err;
+			}
+		}
+
+		base = addr;
+	}
+
+	ret = cma_init_reserved_mem(base, size, order_per_bit, res_cma);
+	if (ret)
+		goto err;
+
+	pr_info("Reserved %ld MiB at %pa\n", (unsigned long)size / SZ_1M,
+		&base);
+	return 0;
+
+err:
+	pr_err("Failed to reserve %ld MiB\n", (unsigned long)size / SZ_1M);
+	return ret;
+}
+
+/**
+ * cma_alloc() - allocate pages from contiguous area
+ * @cma:   Contiguous memory region for which the allocation is performed.
+ * @count: Requested number of pages.
+ * @align: Requested alignment of pages (in PAGE_SIZE order).
+ *
+ * This function allocates part of contiguous memory on specific
+ * contiguous memory area.
+ */
+struct page *cma_alloc(struct cma *cma, int count, unsigned int align)
+{
+	unsigned long mask, pfn, start = 0;
+	unsigned long bitmap_maxno, bitmap_no, bitmap_count;
+	struct page *page = NULL;
+	int ret;
+
+	if (!cma || !cma->count)
+		return NULL;
+
+	pr_debug("%s(cma %p, count %d, align %d)\n", __func__, (void *)cma,
+		 count, align);
+
+	if (!count)
+		return NULL;
+
+	mask = cma_bitmap_aligned_mask(cma, align);
+	bitmap_maxno = cma_bitmap_maxno(cma);
+	bitmap_count = cma_bitmap_pages_to_bits(cma, count);
+
+	for (;;) {
+		mutex_lock(&cma->lock);
+		bitmap_no = bitmap_find_next_zero_area(cma->bitmap,
+				bitmap_maxno, start, bitmap_count, mask);
+		if (bitmap_no >= bitmap_maxno) {
+			mutex_unlock(&cma->lock);
+			break;
+		}
+		bitmap_set(cma->bitmap, bitmap_no, bitmap_count);
+		/*
+		 * It's safe to drop the lock here. We've marked this region for
+		 * our exclusive use. If the migration fails we will take the
+		 * lock again and unmark it.
+		 */
+		mutex_unlock(&cma->lock);
+
+		pfn = cma->base_pfn + (bitmap_no << cma->order_per_bit);
+		mutex_lock(&cma_mutex);
+		ret = alloc_contig_range(pfn, pfn + count, MIGRATE_CMA);
+		mutex_unlock(&cma_mutex);
+		if (ret == 0) {
+			page = pfn_to_page(pfn);
+			break;
+		}
+
+		cma_clear_bitmap(cma, pfn, count);
+		if (ret != -EBUSY)
+			break;
+
+		pr_debug("%s(): memory range at %p is busy, retrying\n",
+			 __func__, pfn_to_page(pfn));
+		/* try again with a bit different memory target */
+		start = bitmap_no + mask + 1;
+	}
+
+	pr_debug("%s(): returned %p\n", __func__, page);
+	return page;
+}
+
+/**
+ * cma_release() - release allocated pages
+ * @cma:   Contiguous memory region for which the allocation is performed.
+ * @pages: Allocated pages.
+ * @count: Number of allocated pages.
+ *
+ * This function releases memory allocated by alloc_cma().
+ * It returns false when provided pages do not belong to contiguous area and
+ * true otherwise.
+ */
+bool cma_release(struct cma *cma, struct page *pages, int count)
+{
+	unsigned long pfn;
+
+	if (!cma || !pages)
+		return false;
+
+	pr_debug("%s(page %p)\n", __func__, (void *)pages);
+
+	pfn = page_to_pfn(pages);
+
+	if (pfn < cma->base_pfn || pfn >= cma->base_pfn + cma->count)
+		return false;
+
+	VM_BUG_ON(pfn + count > cma->base_pfn + cma->count);
+
+	free_contig_range(pfn, count);
+	cma_clear_bitmap(cma, pfn, count);
+
+	return true;
+}

mm/debug-pagealloc.c

@@ -0,0 +1,102 @@
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/mm.h>
+#include <linux/highmem.h>
+#include <linux/page-debug-flags.h>
+#include <linux/poison.h>
+#include <linux/ratelimit.h>
+
+static inline void set_page_poison(struct page *page)
+{
+	__set_bit(PAGE_DEBUG_FLAG_POISON, &page->debug_flags);
+}
+
+static inline void clear_page_poison(struct page *page)
+{
+	__clear_bit(PAGE_DEBUG_FLAG_POISON, &page->debug_flags);
+}
+
+static inline bool page_poison(struct page *page)
+{
+	return test_bit(PAGE_DEBUG_FLAG_POISON, &page->debug_flags);
+}
+
+static void poison_page(struct page *page)
+{
+	void *addr = kmap_atomic(page);
+
+	set_page_poison(page);
+	memset(addr, PAGE_POISON, PAGE_SIZE);
+	kunmap_atomic(addr);
+}
+
+static void poison_pages(struct page *page, int n)
+{
+	int i;
+
+	for (i = 0; i < n; i++)
+		poison_page(page + i);
+}
+
+static bool single_bit_flip(unsigned char a, unsigned char b)
+{
+	unsigned char error = a ^ b;
+
+	return error && !(error & (error - 1));
+}
+
+static void check_poison_mem(unsigned char *mem, size_t bytes)
+{
+	static DEFINE_RATELIMIT_STATE(ratelimit, 5 * HZ, 10);
+	unsigned char *start;
+	unsigned char *end;
+
+	start = memchr_inv(mem, PAGE_POISON, bytes);
+	if (!start)
+		return;
+
+	for (end = mem + bytes - 1; end > start; end--) {
+		if (*end != PAGE_POISON)
+			break;
+	}
+
+	if (!__ratelimit(&ratelimit))
+		return;
+	else if (start == end && single_bit_flip(*start, PAGE_POISON))
+		printk(KERN_ERR "pagealloc: single bit error\n");
+	else
+		printk(KERN_ERR "pagealloc: memory corruption\n");
+
+	print_hex_dump(KERN_ERR, "", DUMP_PREFIX_ADDRESS, 16, 1, start,
+			end - start + 1, 1);
+	dump_stack();
+}
+
+static void unpoison_page(struct page *page)
+{
+	void *addr;
+
+	if (!page_poison(page))
+		return;
+
+	addr = kmap_atomic(page);
+	check_poison_mem(addr, PAGE_SIZE);
+	clear_page_poison(page);
+	kunmap_atomic(addr);
+}
+
+static void unpoison_pages(struct page *page, int n)
+{
+	int i;
+
+	for (i = 0; i < n; i++)
+		unpoison_page(page + i);
+}
+
+void kernel_map_pages(struct page *page, int numpages, int enable)
+{
+	if (enable)
+		unpoison_pages(page, numpages);
+	else
+		poison_pages(page, numpages);
+}

mm/debug.c

@@ -0,0 +1,237 @@
+/*
+ * mm/debug.c
+ *
+ * mm/ specific debug routines.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/ftrace_event.h>
+#include <linux/memcontrol.h>
+
+static const struct trace_print_flags pageflag_names[] = {
+	{1UL << PG_locked,		"locked"	},
+	{1UL << PG_error,		"error"		},
+	{1UL << PG_referenced,		"referenced"	},
+	{1UL << PG_uptodate,		"uptodate"	},
+	{1UL << PG_dirty,		"dirty"		},
+	{1UL << PG_lru,			"lru"		},
+	{1UL << PG_active,		"active"	},
+	{1UL << PG_slab,		"slab"		},
+	{1UL << PG_owner_priv_1,	"owner_priv_1"	},
+	{1UL << PG_arch_1,		"arch_1"	},
+	{1UL << PG_reserved,		"reserved"	},
+	{1UL << PG_private,		"private"	},
+	{1UL << PG_private_2,		"private_2"	},
+	{1UL << PG_writeback,		"writeback"	},
+#ifdef CONFIG_PAGEFLAGS_EXTENDED
+	{1UL << PG_head,		"head"		},
+	{1UL << PG_tail,		"tail"		},
+#else
+	{1UL << PG_compound,		"compound"	},
+#endif
+	{1UL << PG_swapcache,		"swapcache"	},
+	{1UL << PG_mappedtodisk,	"mappedtodisk"	},
+	{1UL << PG_reclaim,		"reclaim"	},
+	{1UL << PG_swapbacked,		"swapbacked"	},
+	{1UL << PG_unevictable,		"unevictable"	},
+#ifdef CONFIG_MMU
+	{1UL << PG_mlocked,		"mlocked"	},
+#endif
+#ifdef CONFIG_ARCH_USES_PG_UNCACHED
+	{1UL << PG_uncached,		"uncached"	},
+#endif
+#ifdef CONFIG_MEMORY_FAILURE
+	{1UL << PG_hwpoison,		"hwpoison"	},
+#endif
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	{1UL << PG_compound_lock,	"compound_lock"	},
+#endif
+};
+
+static void dump_flags(unsigned long flags,
+			const struct trace_print_flags *names, int count)
+{
+	const char *delim = "";
+	unsigned long mask;
+	int i;
+
+	pr_emerg("flags: %#lx(", flags);
+
+	/* remove zone id */
+	flags &= (1UL << NR_PAGEFLAGS) - 1;
+
+	for (i = 0; i < count && flags; i++) {
+
+		mask = names[i].mask;
+		if ((flags & mask) != mask)
+			continue;
+
+		flags &= ~mask;
+		pr_cont("%s%s", delim, names[i].name);
+		delim = "|";
+	}
+
+	/* check for left over flags */
+	if (flags)
+		pr_cont("%s%#lx", delim, flags);
+
+	pr_cont(")\n");
+}
+
+void dump_page_badflags(struct page *page, const char *reason,
+		unsigned long badflags)
+{
+	pr_emerg("page:%p count:%d mapcount:%d mapping:%p index:%#lx\n",
+		  page, atomic_read(&page->_count), page_mapcount(page),
+		  page->mapping, page->index);
+	BUILD_BUG_ON(ARRAY_SIZE(pageflag_names) != __NR_PAGEFLAGS);
+	dump_flags(page->flags, pageflag_names, ARRAY_SIZE(pageflag_names));
+	if (reason)
+		pr_alert("page dumped because: %s\n", reason);
+	if (page->flags & badflags) {
+		pr_alert("bad because of flags:\n");
+		dump_flags(page->flags & badflags,
+				pageflag_names, ARRAY_SIZE(pageflag_names));
+	}
+	mem_cgroup_print_bad_page(page);
+}
+
+void dump_page(struct page *page, const char *reason)
+{
+	dump_page_badflags(page, reason, 0);
+}
+EXPORT_SYMBOL(dump_page);
+
+#ifdef CONFIG_DEBUG_VM
+
+static const struct trace_print_flags vmaflags_names[] = {
+	{VM_READ,			"read"		},
+	{VM_WRITE,			"write"		},
+	{VM_EXEC,			"exec"		},
+	{VM_SHARED,			"shared"	},
+	{VM_MAYREAD,			"mayread"	},
+	{VM_MAYWRITE,			"maywrite"	},
+	{VM_MAYEXEC,			"mayexec"	},
+	{VM_MAYSHARE,			"mayshare"	},
+	{VM_GROWSDOWN,			"growsdown"	},
+	{VM_PFNMAP,			"pfnmap"	},
+	{VM_DENYWRITE,			"denywrite"	},
+	{VM_LOCKED,			"locked"	},
+	{VM_IO,				"io"		},
+	{VM_SEQ_READ,			"seqread"	},
+	{VM_RAND_READ,			"randread"	},
+	{VM_DONTCOPY,			"dontcopy"	},
+	{VM_DONTEXPAND,			"dontexpand"	},
+	{VM_ACCOUNT,			"account"	},
+	{VM_NORESERVE,			"noreserve"	},
+	{VM_HUGETLB,			"hugetlb"	},
+	{VM_NONLINEAR,			"nonlinear"	},
+#if defined(CONFIG_X86)
+	{VM_PAT,			"pat"		},
+#elif defined(CONFIG_PPC)
+	{VM_SAO,			"sao"		},
+#elif defined(CONFIG_PARISC) || defined(CONFIG_METAG) || defined(CONFIG_IA64)
+	{VM_GROWSUP,			"growsup"	},
+#elif !defined(CONFIG_MMU)
+	{VM_MAPPED_COPY,		"mappedcopy"	},
+#else
+	{VM_ARCH_1,			"arch_1"	},
+#endif
+	{VM_DONTDUMP,			"dontdump"	},
+#ifdef CONFIG_MEM_SOFT_DIRTY
+	{VM_SOFTDIRTY,			"softdirty"	},
+#endif
+	{VM_MIXEDMAP,			"mixedmap"	},
+	{VM_HUGEPAGE,			"hugepage"	},
+	{VM_NOHUGEPAGE,			"nohugepage"	},
+	{VM_MERGEABLE,			"mergeable"	},
+};
+
+void dump_vma(const struct vm_area_struct *vma)
+{
+	pr_emerg("vma %p start %p end %p\n"
+		"next %p prev %p mm %p\n"
+		"prot %lx anon_vma %p vm_ops %p\n"
+		"pgoff %lx file %p private_data %p\n",
+		vma, (void *)vma->vm_start, (void *)vma->vm_end, vma->vm_next,
+		vma->vm_prev, vma->vm_mm,
+		(unsigned long)pgprot_val(vma->vm_page_prot),
+		vma->anon_vma, vma->vm_ops, vma->vm_pgoff,
+		vma->vm_file, vma->vm_private_data);
+	dump_flags(vma->vm_flags, vmaflags_names, ARRAY_SIZE(vmaflags_names));
+}
+EXPORT_SYMBOL(dump_vma);
+
+void dump_mm(const struct mm_struct *mm)
+{
+	pr_emerg("mm %p mmap %p seqnum %d task_size %lu\n"
+#ifdef CONFIG_MMU
+		"get_unmapped_area %p\n"
+#endif
+		"mmap_base %lu mmap_legacy_base %lu highest_vm_end %lu\n"
+		"pgd %p mm_users %d mm_count %d nr_ptes %lu map_count %d\n"
+		"hiwater_rss %lx hiwater_vm %lx total_vm %lx locked_vm %lx\n"
+		"pinned_vm %lx shared_vm %lx exec_vm %lx stack_vm %lx\n"
+		"start_code %lx end_code %lx start_data %lx end_data %lx\n"
+		"start_brk %lx brk %lx start_stack %lx\n"
+		"arg_start %lx arg_end %lx env_start %lx env_end %lx\n"
+		"binfmt %p flags %lx core_state %p\n"
+#ifdef CONFIG_AIO
+		"ioctx_table %p\n"
+#endif
+#ifdef CONFIG_MEMCG
+		"owner %p "
+#endif
+		"exe_file %p\n"
+#ifdef CONFIG_MMU_NOTIFIER
+		"mmu_notifier_mm %p\n"
+#endif
+#ifdef CONFIG_NUMA_BALANCING
+		"numa_next_scan %lu numa_scan_offset %lu numa_scan_seq %d\n"
+#endif
+#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION)
+		"tlb_flush_pending %d\n"
+#endif
+		"%s",	/* This is here to hold the comma */
+
+		mm, mm->mmap, mm->vmacache_seqnum, mm->task_size,
+#ifdef CONFIG_MMU
+		mm->get_unmapped_area,
+#endif
+		mm->mmap_base, mm->mmap_legacy_base, mm->highest_vm_end,
+		mm->pgd, atomic_read(&mm->mm_users),
+		atomic_read(&mm->mm_count),
+		atomic_long_read((atomic_long_t *)&mm->nr_ptes),
+		mm->map_count,
+		mm->hiwater_rss, mm->hiwater_vm, mm->total_vm, mm->locked_vm,
+		mm->pinned_vm, mm->shared_vm, mm->exec_vm, mm->stack_vm,
+		mm->start_code, mm->end_code, mm->start_data, mm->end_data,
+		mm->start_brk, mm->brk, mm->start_stack,
+		mm->arg_start, mm->arg_end, mm->env_start, mm->env_end,
+		mm->binfmt, mm->flags, mm->core_state,
+#ifdef CONFIG_AIO
+		mm->ioctx_table,
+#endif
+#ifdef CONFIG_MEMCG
+		mm->owner,
+#endif
+		mm->exe_file,
+#ifdef CONFIG_MMU_NOTIFIER
+		mm->mmu_notifier_mm,
+#endif
+#ifdef CONFIG_NUMA_BALANCING
+		mm->numa_next_scan, mm->numa_scan_offset, mm->numa_scan_seq,
+#endif
+#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION)
+		mm->tlb_flush_pending,
+#endif
+		""		/* This is here to not have a comma! */
+		);
+
+		dump_flags(mm->def_flags, vmaflags_names,
+				ARRAY_SIZE(vmaflags_names));
+}
+
+#endif		/* CONFIG_DEBUG_VM */

mm/dmapool.c

@@ -0,0 +1,529 @@
+/*
+ * DMA Pool allocator
+ *
+ * Copyright 2001 David Brownell
+ * Copyright 2007 Intel Corporation
+ *   Author: Matthew Wilcox <willy@linux.intel.com>
+ *
+ * This software may be redistributed and/or modified under the terms of
+ * the GNU General Public License ("GPL") version 2 as published by the
+ * Free Software Foundation.
+ *
+ * This allocator returns small blocks of a given size which are DMA-able by
+ * the given device.  It uses the dma_alloc_coherent page allocator to get
+ * new pages, then splits them up into blocks of the required size.
+ * Many older drivers still have their own code to do this.
+ *
+ * The current design of this allocator is fairly simple.  The pool is
+ * represented by the 'struct dma_pool' which keeps a doubly-linked list of
+ * allocated pages.  Each page in the page_list is split into blocks of at
+ * least 'size' bytes.  Free blocks are tracked in an unsorted singly-linked
+ * list of free blocks within the page.  Used blocks aren't tracked, but we
+ * keep a count of how many are currently allocated from each page.
+ */
+
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmapool.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/export.h>
+#include <linux/mutex.h>
+#include <linux/poison.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/stat.h>
+#include <linux/spinlock.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/wait.h>
+
+#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_SLUB_DEBUG_ON)
+#define DMAPOOL_DEBUG 1
+#endif
+
+struct dma_pool {		/* the pool */
+	struct list_head page_list;
+	spinlock_t lock;
+	size_t size;
+	struct device *dev;
+	size_t allocation;
+	size_t boundary;
+	char name[32];
+	struct list_head pools;
+};
+
+struct dma_page {		/* cacheable header for 'allocation' bytes */
+	struct list_head page_list;
+	void *vaddr;
+	dma_addr_t dma;
+	unsigned int in_use;
+	unsigned int offset;
+};
+
+static DEFINE_MUTEX(pools_lock);
+static DEFINE_MUTEX(pools_reg_lock);
+
+static ssize_t
+show_pools(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	unsigned temp;
+	unsigned size;
+	char *next;
+	struct dma_page *page;
+	struct dma_pool *pool;
+
+	next = buf;
+	size = PAGE_SIZE;
+
+	temp = scnprintf(next, size, "poolinfo - 0.1\n");
+	size -= temp;
+	next += temp;
+
+	mutex_lock(&pools_lock);
+	list_for_each_entry(pool, &dev->dma_pools, pools) {
+		unsigned pages = 0;
+		unsigned blocks = 0;
+
+		spin_lock_irq(&pool->lock);
+		list_for_each_entry(page, &pool->page_list, page_list) {
+			pages++;
+			blocks += page->in_use;
+		}
+		spin_unlock_irq(&pool->lock);
+
+		/* per-pool info, no real statistics yet */
+		temp = scnprintf(next, size, "%-16s %4u %4Zu %4Zu %2u\n",
+				 pool->name, blocks,
+				 pages * (pool->allocation / pool->size),
+				 pool->size, pages);
+		size -= temp;
+		next += temp;
+	}
+	mutex_unlock(&pools_lock);
+
+	return PAGE_SIZE - size;
+}
+
+static DEVICE_ATTR(pools, S_IRUGO, show_pools, NULL);
+
+/**
+ * dma_pool_create - Creates a pool of consistent memory blocks, for dma.
+ * @name: name of pool, for diagnostics
+ * @dev: device that will be doing the DMA
+ * @size: size of the blocks in this pool.
+ * @align: alignment requirement for blocks; must be a power of two
+ * @boundary: returned blocks won't cross this power of two boundary
+ * Context: !in_interrupt()
+ *
+ * Returns a dma allocation pool with the requested characteristics, or
+ * null if one can't be created.  Given one of these pools, dma_pool_alloc()
+ * may be used to allocate memory.  Such memory will all have "consistent"
+ * DMA mappings, accessible by the device and its driver without using
+ * cache flushing primitives.  The actual size of blocks allocated may be
+ * larger than requested because of alignment.
+ *
+ * If @boundary is nonzero, objects returned from dma_pool_alloc() won't
+ * cross that size boundary.  This is useful for devices which have
+ * addressing restrictions on individual DMA transfers, such as not crossing
+ * boundaries of 4KBytes.
+ */
+struct dma_pool *dma_pool_create(const char *name, struct device *dev,
+				 size_t size, size_t align, size_t boundary)
+{
+	struct dma_pool *retval;
+	size_t allocation;
+	bool empty = false;
+
+	if (align == 0)
+		align = 1;
+	else if (align & (align - 1))
+		return NULL;
+
+	if (size == 0)
+		return NULL;
+	else if (size < 4)
+		size = 4;
+
+	if ((size % align) != 0)
+		size = ALIGN(size, align);
+
+	allocation = max_t(size_t, size, PAGE_SIZE);
+
+	if (!boundary)
+		boundary = allocation;
+	else if ((boundary < size) || (boundary & (boundary - 1)))
+		return NULL;
+
+	retval = kmalloc_node(sizeof(*retval), GFP_KERNEL, dev_to_node(dev));
+	if (!retval)
+		return retval;
+
+	strlcpy(retval->name, name, sizeof(retval->name));
+
+	retval->dev = dev;
+
+	INIT_LIST_HEAD(&retval->page_list);
+	spin_lock_init(&retval->lock);
+	retval->size = size;
+	retval->boundary = boundary;
+	retval->allocation = allocation;
+
+	INIT_LIST_HEAD(&retval->pools);
+
+	/*
+	 * pools_lock ensures that the ->dma_pools list does not get corrupted.
+	 * pools_reg_lock ensures that there is not a race between
+	 * dma_pool_create() and dma_pool_destroy() or within dma_pool_create()
+	 * when the first invocation of dma_pool_create() failed on
+	 * device_create_file() and the second assumes that it has been done (I
+	 * know it is a short window).
+	 */
+	mutex_lock(&pools_reg_lock);
+	mutex_lock(&pools_lock);
+	if (list_empty(&dev->dma_pools))
+		empty = true;
+	list_add(&retval->pools, &dev->dma_pools);
+	mutex_unlock(&pools_lock);
+	if (empty) {
+		int err;
+
+		err = device_create_file(dev, &dev_attr_pools);
+		if (err) {
+			mutex_lock(&pools_lock);
+			list_del(&retval->pools);
+			mutex_unlock(&pools_lock);
+			mutex_unlock(&pools_reg_lock);
+			kfree(retval);
+			return NULL;
+		}
+	}
+	mutex_unlock(&pools_reg_lock);
+	return retval;
+}
+EXPORT_SYMBOL(dma_pool_create);
+
+static void pool_initialise_page(struct dma_pool *pool, struct dma_page *page)
+{
+	unsigned int offset = 0;
+	unsigned int next_boundary = pool->boundary;
+
+	do {
+		unsigned int next = offset + pool->size;
+		if (unlikely((next + pool->size) >= next_boundary)) {
+			next = next_boundary;
+			next_boundary += pool->boundary;
+		}
+		*(int *)(page->vaddr + offset) = next;
+		offset = next;
+	} while (offset < pool->allocation);
+}
+
+static struct dma_page *pool_alloc_page(struct dma_pool *pool, gfp_t mem_flags)
+{
+	struct dma_page *page;
+
+	page = kmalloc(sizeof(*page), mem_flags);
+	if (!page)
+		return NULL;
+	page->vaddr = dma_alloc_coherent(pool->dev, pool->allocation,
+					 &page->dma, mem_flags);
+	if (page->vaddr) {
+#ifdef	DMAPOOL_DEBUG
+		memset(page->vaddr, POOL_POISON_FREED, pool->allocation);
+#endif
+		pool_initialise_page(pool, page);
+		page->in_use = 0;
+		page->offset = 0;
+	} else {
+		kfree(page);
+		page = NULL;
+	}
+	return page;
+}
+
+static inline int is_page_busy(struct dma_page *page)
+{
+	return page->in_use != 0;
+}
+
+static void pool_free_page(struct dma_pool *pool, struct dma_page *page)
+{
+	dma_addr_t dma = page->dma;
+
+#ifdef	DMAPOOL_DEBUG
+	memset(page->vaddr, POOL_POISON_FREED, pool->allocation);
+#endif
+	dma_free_coherent(pool->dev, pool->allocation, page->vaddr, dma);
+	list_del(&page->page_list);
+	kfree(page);
+}
+
+/**
+ * dma_pool_destroy - destroys a pool of dma memory blocks.
+ * @pool: dma pool that will be destroyed
+ * Context: !in_interrupt()
+ *
+ * Caller guarantees that no more memory from the pool is in use,
+ * and that nothing will try to use the pool after this call.
+ */
+void dma_pool_destroy(struct dma_pool *pool)
+{
+	bool empty = false;
+
+	mutex_lock(&pools_reg_lock);
+	mutex_lock(&pools_lock);
+	list_del(&pool->pools);
+	if (pool->dev && list_empty(&pool->dev->dma_pools))
+		empty = true;
+	mutex_unlock(&pools_lock);
+	if (empty)
+		device_remove_file(pool->dev, &dev_attr_pools);
+	mutex_unlock(&pools_reg_lock);
+
+	while (!list_empty(&pool->page_list)) {
+		struct dma_page *page;
+		page = list_entry(pool->page_list.next,
+				  struct dma_page, page_list);
+		if (is_page_busy(page)) {
+			if (pool->dev)
+				dev_err(pool->dev,
+					"dma_pool_destroy %s, %p busy\n",
+					pool->name, page->vaddr);
+			else
+				printk(KERN_ERR
+				       "dma_pool_destroy %s, %p busy\n",
+				       pool->name, page->vaddr);
+			/* leak the still-in-use consistent memory */
+			list_del(&page->page_list);
+			kfree(page);
+		} else
+			pool_free_page(pool, page);
+	}
+
+	kfree(pool);
+}
+EXPORT_SYMBOL(dma_pool_destroy);
+
+/**
+ * dma_pool_alloc - get a block of consistent memory
+ * @pool: dma pool that will produce the block
+ * @mem_flags: GFP_* bitmask
+ * @handle: pointer to dma address of block
+ *
+ * This returns the kernel virtual address of a currently unused block,
+ * and reports its dma address through the handle.
+ * If such a memory block can't be allocated, %NULL is returned.
+ */
+void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags,
+		     dma_addr_t *handle)
+{
+	unsigned long flags;
+	struct dma_page *page;
+	size_t offset;
+	void *retval;
+
+	might_sleep_if(mem_flags & __GFP_WAIT);
+
+	spin_lock_irqsave(&pool->lock, flags);
+	list_for_each_entry(page, &pool->page_list, page_list) {
+		if (page->offset < pool->allocation)
+			goto ready;
+	}
+
+	/* pool_alloc_page() might sleep, so temporarily drop &pool->lock */
+	spin_unlock_irqrestore(&pool->lock, flags);
+
+	page = pool_alloc_page(pool, mem_flags);
+	if (!page)
+		return NULL;
+
+	spin_lock_irqsave(&pool->lock, flags);
+
+	list_add(&page->page_list, &pool->page_list);
+ ready:
+	page->in_use++;
+	offset = page->offset;
+	page->offset = *(int *)(page->vaddr + offset);
+	retval = offset + page->vaddr;
+	*handle = offset + page->dma;
+#ifdef	DMAPOOL_DEBUG
+	{
+		int i;
+		u8 *data = retval;
+		/* page->offset is stored in first 4 bytes */
+		for (i = sizeof(page->offset); i < pool->size; i++) {
+			if (data[i] == POOL_POISON_FREED)
+				continue;
+			if (pool->dev)
+				dev_err(pool->dev,
+					"dma_pool_alloc %s, %p (corrupted)\n",
+					pool->name, retval);
+			else
+				pr_err("dma_pool_alloc %s, %p (corrupted)\n",
+					pool->name, retval);
+
+			/*
+			 * Dump the first 4 bytes even if they are not
+			 * POOL_POISON_FREED
+			 */
+			print_hex_dump(KERN_ERR, "", DUMP_PREFIX_OFFSET, 16, 1,
+					data, pool->size, 1);
+			break;
+		}
+	}
+	memset(retval, POOL_POISON_ALLOCATED, pool->size);
+#endif
+	spin_unlock_irqrestore(&pool->lock, flags);
+	return retval;
+}
+EXPORT_SYMBOL(dma_pool_alloc);
+
+static struct dma_page *pool_find_page(struct dma_pool *pool, dma_addr_t dma)
+{
+	struct dma_page *page;
+
+	list_for_each_entry(page, &pool->page_list, page_list) {
+		if (dma < page->dma)
+			continue;
+		if (dma < (page->dma + pool->allocation))
+			return page;
+	}
+	return NULL;
+}
+
+/**
+ * dma_pool_free - put block back into dma pool
+ * @pool: the dma pool holding the block
+ * @vaddr: virtual address of block
+ * @dma: dma address of block
+ *
+ * Caller promises neither device nor driver will again touch this block
+ * unless it is first re-allocated.
+ */
+void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t dma)
+{
+	struct dma_page *page;
+	unsigned long flags;
+	unsigned int offset;
+
+	spin_lock_irqsave(&pool->lock, flags);
+	page = pool_find_page(pool, dma);
+	if (!page) {
+		spin_unlock_irqrestore(&pool->lock, flags);
+		if (pool->dev)
+			dev_err(pool->dev,
+				"dma_pool_free %s, %p/%lx (bad dma)\n",
+				pool->name, vaddr, (unsigned long)dma);
+		else
+			printk(KERN_ERR "dma_pool_free %s, %p/%lx (bad dma)\n",
+			       pool->name, vaddr, (unsigned long)dma);
+		return;
+	}
+
+	offset = vaddr - page->vaddr;
+#ifdef	DMAPOOL_DEBUG
+	if ((dma - page->dma) != offset) {
+		spin_unlock_irqrestore(&pool->lock, flags);
+		if (pool->dev)
+			dev_err(pool->dev,
+				"dma_pool_free %s, %p (bad vaddr)/%Lx\n",
+				pool->name, vaddr, (unsigned long long)dma);
+		else
+			printk(KERN_ERR
+			       "dma_pool_free %s, %p (bad vaddr)/%Lx\n",
+			       pool->name, vaddr, (unsigned long long)dma);
+		return;
+	}
+	{
+		unsigned int chain = page->offset;
+		while (chain < pool->allocation) {
+			if (chain != offset) {
+				chain = *(int *)(page->vaddr + chain);
+				continue;
+			}
+			spin_unlock_irqrestore(&pool->lock, flags);
+			if (pool->dev)
+				dev_err(pool->dev, "dma_pool_free %s, dma %Lx "
+					"already free\n", pool->name,
+					(unsigned long long)dma);
+			else
+				printk(KERN_ERR "dma_pool_free %s, dma %Lx "
+					"already free\n", pool->name,
+					(unsigned long long)dma);
+			return;
+		}
+	}
+	memset(vaddr, POOL_POISON_FREED, pool->size);
+#endif
+
+	page->in_use--;
+	*(int *)vaddr = page->offset;
+	page->offset = offset;
+	/*
+	 * Resist a temptation to do
+	 *    if (!is_page_busy(page)) pool_free_page(pool, page);
+	 * Better have a few empty pages hang around.
+	 */
+	spin_unlock_irqrestore(&pool->lock, flags);
+}
+EXPORT_SYMBOL(dma_pool_free);
+
+/*
+ * Managed DMA pool
+ */
+static void dmam_pool_release(struct device *dev, void *res)
+{
+	struct dma_pool *pool = *(struct dma_pool **)res;
+
+	dma_pool_destroy(pool);
+}
+
+static int dmam_pool_match(struct device *dev, void *res, void *match_data)
+{
+	return *(struct dma_pool **)res == match_data;
+}
+
+/**
+ * dmam_pool_create - Managed dma_pool_create()
+ * @name: name of pool, for diagnostics
+ * @dev: device that will be doing the DMA
+ * @size: size of the blocks in this pool.
+ * @align: alignment requirement for blocks; must be a power of two
+ * @allocation: returned blocks won't cross this boundary (or zero)
+ *
+ * Managed dma_pool_create().  DMA pool created with this function is
+ * automatically destroyed on driver detach.
+ */
+struct dma_pool *dmam_pool_create(const char *name, struct device *dev,
+				  size_t size, size_t align, size_t allocation)
+{
+	struct dma_pool **ptr, *pool;
+
+	ptr = devres_alloc(dmam_pool_release, sizeof(*ptr), GFP_KERNEL);
+	if (!ptr)
+		return NULL;
+
+	pool = *ptr = dma_pool_create(name, dev, size, align, allocation);
+	if (pool)
+		devres_add(dev, ptr);
+	else
+		devres_free(ptr);
+
+	return pool;
+}
+EXPORT_SYMBOL(dmam_pool_create);
+
+/**
+ * dmam_pool_destroy - Managed dma_pool_destroy()
+ * @pool: dma pool that will be destroyed
+ *
+ * Managed dma_pool_destroy().
+ */
+void dmam_pool_destroy(struct dma_pool *pool)
+{
+	struct device *dev = pool->dev;
+
+	WARN_ON(devres_release(dev, dmam_pool_release, dmam_pool_match, pool));
+}
+EXPORT_SYMBOL(dmam_pool_destroy);

mm/early_ioremap.c

@@ -0,0 +1,245 @@
+/*
+ * Provide common bits of early_ioremap() support for architectures needing
+ * temporary mappings during boot before ioremap() is available.
+ *
+ * This is mostly a direct copy of the x86 early_ioremap implementation.
+ *
+ * (C) Copyright 1995 1996, 2014 Linus Torvalds
+ *
+ */
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
+#include <linux/vmalloc.h>
+#include <asm/fixmap.h>
+
+#ifdef CONFIG_MMU
+static int early_ioremap_debug __initdata;
+
+static int __init early_ioremap_debug_setup(char *str)
+{
+	early_ioremap_debug = 1;
+
+	return 0;
+}
+early_param("early_ioremap_debug", early_ioremap_debug_setup);
+
+static int after_paging_init __initdata;
+
+void __init __weak early_ioremap_shutdown(void)
+{
+}
+
+void __init early_ioremap_reset(void)
+{
+	early_ioremap_shutdown();
+	after_paging_init = 1;
+}
+
+/*
+ * Generally, ioremap() is available after paging_init() has been called.
+ * Architectures wanting to allow early_ioremap after paging_init() can
+ * define __late_set_fixmap and __late_clear_fixmap to do the right thing.
+ */
+#ifndef __late_set_fixmap
+static inline void __init __late_set_fixmap(enum fixed_addresses idx,
+					    phys_addr_t phys, pgprot_t prot)
+{
+	BUG();
+}
+#endif
+
+#ifndef __late_clear_fixmap
+static inline void __init __late_clear_fixmap(enum fixed_addresses idx)
+{
+	BUG();
+}
+#endif
+
+static void __iomem *prev_map[FIX_BTMAPS_SLOTS] __initdata;
+static unsigned long prev_size[FIX_BTMAPS_SLOTS] __initdata;
+static unsigned long slot_virt[FIX_BTMAPS_SLOTS] __initdata;
+
+void __init early_ioremap_setup(void)
+{
+	int i;
+
+	for (i = 0; i < FIX_BTMAPS_SLOTS; i++)
+		if (WARN_ON(prev_map[i]))
+			break;
+
+	for (i = 0; i < FIX_BTMAPS_SLOTS; i++)
+		slot_virt[i] = __fix_to_virt(FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*i);
+}
+
+static int __init check_early_ioremap_leak(void)
+{
+	int count = 0;
+	int i;
+
+	for (i = 0; i < FIX_BTMAPS_SLOTS; i++)
+		if (prev_map[i])
+			count++;
+
+	if (WARN(count, KERN_WARNING
+		 "Debug warning: early ioremap leak of %d areas detected.\n"
+		 "please boot with early_ioremap_debug and report the dmesg.\n",
+		 count))
+		return 1;
+	return 0;
+}
+late_initcall(check_early_ioremap_leak);
+
+static void __init __iomem *
+__early_ioremap(resource_size_t phys_addr, unsigned long size, pgprot_t prot)
+{
+	unsigned long offset;
+	resource_size_t last_addr;
+	unsigned int nrpages;
+	enum fixed_addresses idx;
+	int i, slot;
+
+	WARN_ON(system_state != SYSTEM_BOOTING);
+
+	slot = -1;
+	for (i = 0; i < FIX_BTMAPS_SLOTS; i++) {
+		if (!prev_map[i]) {
+			slot = i;
+			break;
+		}
+	}
+
+	if (WARN(slot < 0, "%s(%08llx, %08lx) not found slot\n",
+		 __func__, (u64)phys_addr, size))
+		return NULL;
+
+	/* Don't allow wraparound or zero size */
+	last_addr = phys_addr + size - 1;
+	if (WARN_ON(!size || last_addr < phys_addr))
+		return NULL;
+
+	prev_size[slot] = size;
+	/*
+	 * Mappings have to be page-aligned
+	 */
+	offset = phys_addr & ~PAGE_MASK;
+	phys_addr &= PAGE_MASK;
+	size = PAGE_ALIGN(last_addr + 1) - phys_addr;
+
+	/*
+	 * Mappings have to fit in the FIX_BTMAP area.
+	 */
+	nrpages = size >> PAGE_SHIFT;
+	if (WARN_ON(nrpages > NR_FIX_BTMAPS))
+		return NULL;
+
+	/*
+	 * Ok, go for it..
+	 */
+	idx = FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*slot;
+	while (nrpages > 0) {
+		if (after_paging_init)
+			__late_set_fixmap(idx, phys_addr, prot);
+		else
+			__early_set_fixmap(idx, phys_addr, prot);
+		phys_addr += PAGE_SIZE;
+		--idx;
+		--nrpages;
+	}
+	WARN(early_ioremap_debug, "%s(%08llx, %08lx) [%d] => %08lx + %08lx\n",
+	     __func__, (u64)phys_addr, size, slot, offset, slot_virt[slot]);
+
+	prev_map[slot] = (void __iomem *)(offset + slot_virt[slot]);
+	return prev_map[slot];
+}
+
+void __init early_iounmap(void __iomem *addr, unsigned long size)
+{
+	unsigned long virt_addr;
+	unsigned long offset;
+	unsigned int nrpages;
+	enum fixed_addresses idx;
+	int i, slot;
+
+	slot = -1;
+	for (i = 0; i < FIX_BTMAPS_SLOTS; i++) {
+		if (prev_map[i] == addr) {
+			slot = i;
+			break;
+		}
+	}
+
+	if (WARN(slot < 0, "early_iounmap(%p, %08lx) not found slot\n",
+		 addr, size))
+		return;
+
+	if (WARN(prev_size[slot] != size,
+		 "early_iounmap(%p, %08lx) [%d] size not consistent %08lx\n",
+		 addr, size, slot, prev_size[slot]))
+		return;
+
+	WARN(early_ioremap_debug, "early_iounmap(%p, %08lx) [%d]\n",
+	     addr, size, slot);
+
+	virt_addr = (unsigned long)addr;
+	if (WARN_ON(virt_addr < fix_to_virt(FIX_BTMAP_BEGIN)))
+		return;
+
+	offset = virt_addr & ~PAGE_MASK;
+	nrpages = PAGE_ALIGN(offset + size) >> PAGE_SHIFT;
+
+	idx = FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*slot;
+	while (nrpages > 0) {
+		if (after_paging_init)
+			__late_clear_fixmap(idx);
+		else
+			__early_set_fixmap(idx, 0, FIXMAP_PAGE_CLEAR);
+		--idx;
+		--nrpages;
+	}
+	prev_map[slot] = NULL;
+}
+
+/* Remap an IO device */
+void __init __iomem *
+early_ioremap(resource_size_t phys_addr, unsigned long size)
+{
+	return __early_ioremap(phys_addr, size, FIXMAP_PAGE_IO);
+}
+
+/* Remap memory */
+void __init *
+early_memremap(resource_size_t phys_addr, unsigned long size)
+{
+	return (__force void *)__early_ioremap(phys_addr, size,
+					       FIXMAP_PAGE_NORMAL);
+}
+#else /* CONFIG_MMU */
+
+void __init __iomem *
+early_ioremap(resource_size_t phys_addr, unsigned long size)
+{
+	return (__force void __iomem *)phys_addr;
+}
+
+/* Remap memory */
+void __init *
+early_memremap(resource_size_t phys_addr, unsigned long size)
+{
+	return (void *)phys_addr;
+}
+
+void __init early_iounmap(void __iomem *addr, unsigned long size)
+{
+}
+
+#endif /* CONFIG_MMU */
+
+
+void __init early_memunmap(void *addr, unsigned long size)
+{
+	early_iounmap((__force void __iomem *)addr, size);
+}

mm/fadvise.c

@@ -0,0 +1,156 @@
+/*
+ * mm/fadvise.c
+ *
+ * Copyright (C) 2002, Linus Torvalds
+ *
+ * 11Jan2003	Andrew Morton
+ *		Initial version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/pagemap.h>
+#include <linux/backing-dev.h>
+#include <linux/pagevec.h>
+#include <linux/fadvise.h>
+#include <linux/writeback.h>
+#include <linux/syscalls.h>
+#include <linux/swap.h>
+
+#include <asm/unistd.h>
+
+/*
+ * POSIX_FADV_WILLNEED could set PG_Referenced, and POSIX_FADV_NOREUSE could
+ * deactivate the pages and clear PG_Referenced.
+ */
+SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice)
+{
+	struct fd f = fdget(fd);
+	struct address_space *mapping;
+	struct backing_dev_info *bdi;
+	loff_t endbyte;			/* inclusive */
+	pgoff_t start_index;
+	pgoff_t end_index;
+	unsigned long nrpages;
+	int ret = 0;
+
+	if (!f.file)
+		return -EBADF;
+
+	if (S_ISFIFO(file_inode(f.file)->i_mode)) {
+		ret = -ESPIPE;
+		goto out;
+	}
+
+	mapping = f.file->f_mapping;
+	if (!mapping || len < 0) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (mapping->a_ops->get_xip_mem) {
+		switch (advice) {
+		case POSIX_FADV_NORMAL:
+		case POSIX_FADV_RANDOM:
+		case POSIX_FADV_SEQUENTIAL:
+		case POSIX_FADV_WILLNEED:
+		case POSIX_FADV_NOREUSE:
+		case POSIX_FADV_DONTNEED:
+			/* no bad return value, but ignore advice */
+			break;
+		default:
+			ret = -EINVAL;
+		}
+		goto out;
+	}
+
+	/* Careful about overflows. Len == 0 means "as much as possible" */
+	endbyte = offset + len;
+	if (!len || endbyte < len)
+		endbyte = -1;
+	else
+		endbyte--;		/* inclusive */
+
+	bdi = mapping->backing_dev_info;
+
+	switch (advice) {
+	case POSIX_FADV_NORMAL:
+		f.file->f_ra.ra_pages = bdi->ra_pages;
+		spin_lock(&f.file->f_lock);
+		f.file->f_mode &= ~FMODE_RANDOM;
+		spin_unlock(&f.file->f_lock);
+		break;
+	case POSIX_FADV_RANDOM:
+		spin_lock(&f.file->f_lock);
+		f.file->f_mode |= FMODE_RANDOM;
+		spin_unlock(&f.file->f_lock);
+		break;
+	case POSIX_FADV_SEQUENTIAL:
+		f.file->f_ra.ra_pages = bdi->ra_pages * 2;
+		spin_lock(&f.file->f_lock);
+		f.file->f_mode &= ~FMODE_RANDOM;
+		spin_unlock(&f.file->f_lock);
+		break;
+	case POSIX_FADV_WILLNEED:
+		/* First and last PARTIAL page! */
+		start_index = offset >> PAGE_CACHE_SHIFT;
+		end_index = endbyte >> PAGE_CACHE_SHIFT;
+
+		/* Careful about overflow on the "+1" */
+		nrpages = end_index - start_index + 1;
+		if (!nrpages)
+			nrpages = ~0UL;
+
+		/*
+		 * Ignore return value because fadvise() shall return
+		 * success even if filesystem can't retrieve a hint,
+		 */
+		force_page_cache_readahead(mapping, f.file, start_index,
+					   nrpages);
+		break;
+	case POSIX_FADV_NOREUSE:
+		break;
+	case POSIX_FADV_DONTNEED:
+		if (!bdi_write_congested(mapping->backing_dev_info))
+			__filemap_fdatawrite_range(mapping, offset, endbyte,
+						   WB_SYNC_NONE);
+
+		/* First and last FULL page! */
+		start_index = (offset+(PAGE_CACHE_SIZE-1)) >> PAGE_CACHE_SHIFT;
+		end_index = (endbyte >> PAGE_CACHE_SHIFT);
+
+		if (end_index >= start_index) {
+			unsigned long count = invalidate_mapping_pages(mapping,
+						start_index, end_index);
+
+			/*
+			 * If fewer pages were invalidated than expected then
+			 * it is possible that some of the pages were on
+			 * a per-cpu pagevec for a remote CPU. Drain all
+			 * pagevecs and try again.
+			 */
+			if (count < (end_index - start_index + 1)) {
+				lru_add_drain_all();
+				invalidate_mapping_pages(mapping, start_index,
+						end_index);
+			}
+		}
+		break;
+	default:
+		ret = -EINVAL;
+	}
+out:
+	fdput(f);
+	return ret;
+}
+
+#ifdef __ARCH_WANT_SYS_FADVISE64
+
+SYSCALL_DEFINE4(fadvise64, int, fd, loff_t, offset, size_t, len, int, advice)
+{
+	return sys_fadvise64_64(fd, offset, len, advice);
+}
+
+#endif

mm/failslab.c

@@ -0,0 +1,60 @@
+#include <linux/fault-inject.h>
+#include <linux/slab.h>
+
+static struct {
+	struct fault_attr attr;
+	u32 ignore_gfp_wait;
+	int cache_filter;
+} failslab = {
+	.attr = FAULT_ATTR_INITIALIZER,
+	.ignore_gfp_wait = 1,
+	.cache_filter = 0,
+};
+
+bool should_failslab(size_t size, gfp_t gfpflags, unsigned long cache_flags)
+{
+	if (gfpflags & __GFP_NOFAIL)
+		return false;
+
+        if (failslab.ignore_gfp_wait && (gfpflags & __GFP_WAIT))
+		return false;
+
+	if (failslab.cache_filter && !(cache_flags & SLAB_FAILSLAB))
+		return false;
+
+	return should_fail(&failslab.attr, size);
+}
+
+static int __init setup_failslab(char *str)
+{
+	return setup_fault_attr(&failslab.attr, str);
+}
+__setup("failslab=", setup_failslab);
+
+#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
+static int __init failslab_debugfs_init(void)
+{
+	struct dentry *dir;
+	umode_t mode = S_IFREG | S_IRUSR | S_IWUSR;
+
+	dir = fault_create_debugfs_attr("failslab", NULL, &failslab.attr);
+	if (IS_ERR(dir))
+		return PTR_ERR(dir);
+
+	if (!debugfs_create_bool("ignore-gfp-wait", mode, dir,
+				&failslab.ignore_gfp_wait))
+		goto fail;
+	if (!debugfs_create_bool("cache-filter", mode, dir,
+				&failslab.cache_filter))
+		goto fail;
+
+	return 0;
+fail:
+	debugfs_remove_recursive(dir);
+
+	return -ENOMEM;
+}
+
+late_initcall(failslab_debugfs_init);
+
+#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */

mm/filemap_xip.c

@@ -0,0 +1,483 @@
+/*
+ *	linux/mm/filemap_xip.c
+ *
+ * Copyright (C) 2005 IBM Corporation
+ * Author: Carsten Otte <cotte@de.ibm.com>
+ *
+ * derived from linux/mm/filemap.c - Copyright (C) Linus Torvalds
+ *
+ */
+
+#include <linux/fs.h>
+#include <linux/pagemap.h>
+#include <linux/export.h>
+#include <linux/uio.h>
+#include <linux/rmap.h>
+#include <linux/mmu_notifier.h>
+#include <linux/sched.h>
+#include <linux/seqlock.h>
+#include <linux/mutex.h>
+#include <linux/gfp.h>
+#include <asm/tlbflush.h>
+#include <asm/io.h>
+
+/*
+ * We do use our own empty page to avoid interference with other users
+ * of ZERO_PAGE(), such as /dev/zero
+ */
+static DEFINE_MUTEX(xip_sparse_mutex);
+static seqcount_t xip_sparse_seq = SEQCNT_ZERO(xip_sparse_seq);
+static struct page *__xip_sparse_page;
+
+/* called under xip_sparse_mutex */
+static struct page *xip_sparse_page(void)
+{
+	if (!__xip_sparse_page) {
+		struct page *page = alloc_page(GFP_HIGHUSER | __GFP_ZERO);
+
+		if (page)
+			__xip_sparse_page = page;
+	}
+	return __xip_sparse_page;
+}
+
+/*
+ * This is a file read routine for execute in place files, and uses
+ * the mapping->a_ops->get_xip_mem() function for the actual low-level
+ * stuff.
+ *
+ * Note the struct file* is not used at all.  It may be NULL.
+ */
+static ssize_t
+do_xip_mapping_read(struct address_space *mapping,
+		    struct file_ra_state *_ra,
+		    struct file *filp,
+		    char __user *buf,
+		    size_t len,
+		    loff_t *ppos)
+{
+	struct inode *inode = mapping->host;
+	pgoff_t index, end_index;
+	unsigned long offset;
+	loff_t isize, pos;
+	size_t copied = 0, error = 0;
+
+	BUG_ON(!mapping->a_ops->get_xip_mem);
+
+	pos = *ppos;
+	index = pos >> PAGE_CACHE_SHIFT;
+	offset = pos & ~PAGE_CACHE_MASK;
+
+	isize = i_size_read(inode);
+	if (!isize)
+		goto out;
+
+	end_index = (isize - 1) >> PAGE_CACHE_SHIFT;
+	do {
+		unsigned long nr, left;
+		void *xip_mem;
+		unsigned long xip_pfn;
+		int zero = 0;
+
+		/* nr is the maximum number of bytes to copy from this page */
+		nr = PAGE_CACHE_SIZE;
+		if (index >= end_index) {
+			if (index > end_index)
+				goto out;
+			nr = ((isize - 1) & ~PAGE_CACHE_MASK) + 1;
+			if (nr <= offset) {
+				goto out;
+			}
+		}
+		nr = nr - offset;
+		if (nr > len - copied)
+			nr = len - copied;
+
+		error = mapping->a_ops->get_xip_mem(mapping, index, 0,
+							&xip_mem, &xip_pfn);
+		if (unlikely(error)) {
+			if (error == -ENODATA) {
+				/* sparse */
+				zero = 1;
+			} else
+				goto out;
+		}
+
+		/* If users can be writing to this page using arbitrary
+		 * virtual addresses, take care about potential aliasing
+		 * before reading the page on the kernel side.
+		 */
+		if (mapping_writably_mapped(mapping))
+			/* address based flush */ ;
+
+		/*
+		 * Ok, we have the mem, so now we can copy it to user space...
+		 *
+		 * The actor routine returns how many bytes were actually used..
+		 * NOTE! This may not be the same as how much of a user buffer
+		 * we filled up (we may be padding etc), so we can only update
+		 * "pos" here (the actor routine has to update the user buffer
+		 * pointers and the remaining count).
+		 */
+		if (!zero)
+			left = __copy_to_user(buf+copied, xip_mem+offset, nr);
+		else
+			left = __clear_user(buf + copied, nr);
+
+		if (left) {
+			error = -EFAULT;
+			goto out;
+		}
+
+		copied += (nr - left);
+		offset += (nr - left);
+		index += offset >> PAGE_CACHE_SHIFT;
+		offset &= ~PAGE_CACHE_MASK;
+	} while (copied < len);
+
+out:
+	*ppos = pos + copied;
+	if (filp)
+		file_accessed(filp);
+
+	return (copied ? copied : error);
+}
+
+ssize_t
+xip_file_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos)
+{
+	if (!access_ok(VERIFY_WRITE, buf, len))
+		return -EFAULT;
+
+	return do_xip_mapping_read(filp->f_mapping, &filp->f_ra, filp,
+			    buf, len, ppos);
+}
+EXPORT_SYMBOL_GPL(xip_file_read);
+
+/*
+ * __xip_unmap is invoked from xip_unmap and
+ * xip_write
+ *
+ * This function walks all vmas of the address_space and unmaps the
+ * __xip_sparse_page when found at pgoff.
+ */
+static void
+__xip_unmap (struct address_space * mapping,
+		     unsigned long pgoff)
+{
+	struct vm_area_struct *vma;
+	struct mm_struct *mm;
+	unsigned long address;
+	pte_t *pte;
+	pte_t pteval;
+	spinlock_t *ptl;
+	struct page *page;
+	unsigned count;
+	int locked = 0;
+
+	count = read_seqcount_begin(&xip_sparse_seq);
+
+	page = __xip_sparse_page;
+	if (!page)
+		return;
+
+retry:
+	mutex_lock(&mapping->i_mmap_mutex);
+	vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) {
+		mm = vma->vm_mm;
+		address = vma->vm_start +
+			((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
+		BUG_ON(address < vma->vm_start || address >= vma->vm_end);
+		pte = page_check_address(page, mm, address, &ptl, 1);
+		if (pte) {
+			/* Nuke the page table entry. */
+			flush_cache_page(vma, address, pte_pfn(*pte));
+			pteval = ptep_clear_flush(vma, address, pte);
+			page_remove_rmap(page);
+			dec_mm_counter(mm, MM_FILEPAGES);
+			BUG_ON(pte_dirty(pteval));
+			pte_unmap_unlock(pte, ptl);
+			/* must invalidate_page _before_ freeing the page */
+			mmu_notifier_invalidate_page(mm, address);
+			page_cache_release(page);
+		}
+	}
+	mutex_unlock(&mapping->i_mmap_mutex);
+
+	if (locked) {
+		mutex_unlock(&xip_sparse_mutex);
+	} else if (read_seqcount_retry(&xip_sparse_seq, count)) {
+		mutex_lock(&xip_sparse_mutex);
+		locked = 1;
+		goto retry;
+	}
+}
+
+/*
+ * xip_fault() is invoked via the vma operations vector for a
+ * mapped memory region to read in file data during a page fault.
+ *
+ * This function is derived from filemap_fault, but used for execute in place
+ */
+static int xip_file_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	struct file *file = vma->vm_file;
+	struct address_space *mapping = file->f_mapping;
+	struct inode *inode = mapping->host;
+	pgoff_t size;
+	void *xip_mem;
+	unsigned long xip_pfn;
+	struct page *page;
+	int error;
+
+	/* XXX: are VM_FAULT_ codes OK? */
+again:
+	size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+	if (vmf->pgoff >= size)
+		return VM_FAULT_SIGBUS;
+
+	error = mapping->a_ops->get_xip_mem(mapping, vmf->pgoff, 0,
+						&xip_mem, &xip_pfn);
+	if (likely(!error))
+		goto found;
+	if (error != -ENODATA)
+		return VM_FAULT_OOM;
+
+	/* sparse block */
+	if ((vma->vm_flags & (VM_WRITE | VM_MAYWRITE)) &&
+	    (vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) &&
+	    (!(mapping->host->i_sb->s_flags & MS_RDONLY))) {
+		int err;
+
+		/* maybe shared writable, allocate new block */
+		mutex_lock(&xip_sparse_mutex);
+		error = mapping->a_ops->get_xip_mem(mapping, vmf->pgoff, 1,
+							&xip_mem, &xip_pfn);
+		mutex_unlock(&xip_sparse_mutex);
+		if (error)
+			return VM_FAULT_SIGBUS;
+		/* unmap sparse mappings at pgoff from all other vmas */
+		__xip_unmap(mapping, vmf->pgoff);
+
+found:
+		err = vm_insert_mixed(vma, (unsigned long)vmf->virtual_address,
+							xip_pfn);
+		if (err == -ENOMEM)
+			return VM_FAULT_OOM;
+		/*
+		 * err == -EBUSY is fine, we've raced against another thread
+		 * that faulted-in the same page
+		 */
+		if (err != -EBUSY)
+			BUG_ON(err);
+		return VM_FAULT_NOPAGE;
+	} else {
+		int err, ret = VM_FAULT_OOM;
+
+		mutex_lock(&xip_sparse_mutex);
+		write_seqcount_begin(&xip_sparse_seq);
+		error = mapping->a_ops->get_xip_mem(mapping, vmf->pgoff, 0,
+							&xip_mem, &xip_pfn);
+		if (unlikely(!error)) {
+			write_seqcount_end(&xip_sparse_seq);
+			mutex_unlock(&xip_sparse_mutex);
+			goto again;
+		}
+		if (error != -ENODATA)
+			goto out;
+		/* not shared and writable, use xip_sparse_page() */
+		page = xip_sparse_page();
+		if (!page)
+			goto out;
+		err = vm_insert_page(vma, (unsigned long)vmf->virtual_address,
+							page);
+		if (err == -ENOMEM)
+			goto out;
+
+		ret = VM_FAULT_NOPAGE;
+out:
+		write_seqcount_end(&xip_sparse_seq);
+		mutex_unlock(&xip_sparse_mutex);
+
+		return ret;
+	}
+}
+
+static const struct vm_operations_struct xip_file_vm_ops = {
+	.fault	= xip_file_fault,
+	.page_mkwrite	= filemap_page_mkwrite,
+	.remap_pages = generic_file_remap_pages,
+};
+
+int xip_file_mmap(struct file * file, struct vm_area_struct * vma)
+{
+	BUG_ON(!file->f_mapping->a_ops->get_xip_mem);
+
+	file_accessed(file);
+	vma->vm_ops = &xip_file_vm_ops;
+	vma->vm_flags |= VM_MIXEDMAP;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xip_file_mmap);
+
+static ssize_t
+__xip_file_write(struct file *filp, const char __user *buf,
+		  size_t count, loff_t pos, loff_t *ppos)
+{
+	struct address_space * mapping = filp->f_mapping;
+	const struct address_space_operations *a_ops = mapping->a_ops;
+	struct inode 	*inode = mapping->host;
+	long		status = 0;
+	size_t		bytes;
+	ssize_t		written = 0;
+
+	BUG_ON(!mapping->a_ops->get_xip_mem);
+
+	do {
+		unsigned long index;
+		unsigned long offset;
+		size_t copied;
+		void *xip_mem;
+		unsigned long xip_pfn;
+
+		offset = (pos & (PAGE_CACHE_SIZE -1)); /* Within page */
+		index = pos >> PAGE_CACHE_SHIFT;
+		bytes = PAGE_CACHE_SIZE - offset;
+		if (bytes > count)
+			bytes = count;
+
+		status = a_ops->get_xip_mem(mapping, index, 0,
+						&xip_mem, &xip_pfn);
+		if (status == -ENODATA) {
+			/* we allocate a new page unmap it */
+			mutex_lock(&xip_sparse_mutex);
+			status = a_ops->get_xip_mem(mapping, index, 1,
+							&xip_mem, &xip_pfn);
+			mutex_unlock(&xip_sparse_mutex);
+			if (!status)
+				/* unmap page at pgoff from all other vmas */
+				__xip_unmap(mapping, index);
+		}
+
+		if (status)
+			break;
+
+		copied = bytes -
+			__copy_from_user_nocache(xip_mem + offset, buf, bytes);
+
+		if (likely(copied > 0)) {
+			status = copied;
+
+			if (status >= 0) {
+				written += status;
+				count -= status;
+				pos += status;
+				buf += status;
+			}
+		}
+		if (unlikely(copied != bytes))
+			if (status >= 0)
+				status = -EFAULT;
+		if (status < 0)
+			break;
+	} while (count);
+	*ppos = pos;
+	/*
+	 * No need to use i_size_read() here, the i_size
+	 * cannot change under us because we hold i_mutex.
+	 */
+	if (pos > inode->i_size) {
+		i_size_write(inode, pos);
+		mark_inode_dirty(inode);
+	}
+
+	return written ? written : status;
+}
+
+ssize_t
+xip_file_write(struct file *filp, const char __user *buf, size_t len,
+	       loff_t *ppos)
+{
+	struct address_space *mapping = filp->f_mapping;
+	struct inode *inode = mapping->host;
+	size_t count;
+	loff_t pos;
+	ssize_t ret;
+
+	mutex_lock(&inode->i_mutex);
+
+	if (!access_ok(VERIFY_READ, buf, len)) {
+		ret=-EFAULT;
+		goto out_up;
+	}
+
+	pos = *ppos;
+	count = len;
+
+	/* We can write back this queue in page reclaim */
+	current->backing_dev_info = mapping->backing_dev_info;
+
+	ret = generic_write_checks(filp, &pos, &count, S_ISBLK(inode->i_mode));
+	if (ret)
+		goto out_backing;
+	if (count == 0)
+		goto out_backing;
+
+	ret = file_remove_suid(filp);
+	if (ret)
+		goto out_backing;
+
+	ret = file_update_time(filp);
+	if (ret)
+		goto out_backing;
+
+	ret = __xip_file_write (filp, buf, count, pos, ppos);
+
+ out_backing:
+	current->backing_dev_info = NULL;
+ out_up:
+	mutex_unlock(&inode->i_mutex);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(xip_file_write);
+
+/*
+ * truncate a page used for execute in place
+ * functionality is analog to block_truncate_page but does use get_xip_mem
+ * to get the page instead of page cache
+ */
+int
+xip_truncate_page(struct address_space *mapping, loff_t from)
+{
+	pgoff_t index = from >> PAGE_CACHE_SHIFT;
+	unsigned offset = from & (PAGE_CACHE_SIZE-1);
+	unsigned blocksize;
+	unsigned length;
+	void *xip_mem;
+	unsigned long xip_pfn;
+	int err;
+
+	BUG_ON(!mapping->a_ops->get_xip_mem);
+
+	blocksize = 1 << mapping->host->i_blkbits;
+	length = offset & (blocksize - 1);
+
+	/* Block boundary? Nothing to do */
+	if (!length)
+		return 0;
+
+	length = blocksize - length;
+
+	err = mapping->a_ops->get_xip_mem(mapping, index, 0,
+						&xip_mem, &xip_pfn);
+	if (unlikely(err)) {
+		if (err == -ENODATA)
+			/* Hole? No need to truncate */
+			return 0;
+		else
+			return err;
+	}
+	memset(xip_mem + offset, 0, length);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xip_truncate_page);

mm/fremap.c

@@ -0,0 +1,283 @@
+/*
+ *   linux/mm/fremap.c
+ * 
+ * Explicit pagetable population and nonlinear (random) mappings support.
+ *
+ * started by Ingo Molnar, Copyright (C) 2002, 2003
+ */
+#include <linux/export.h>
+#include <linux/backing-dev.h>
+#include <linux/mm.h>
+#include <linux/swap.h>
+#include <linux/file.h>
+#include <linux/mman.h>
+#include <linux/pagemap.h>
+#include <linux/swapops.h>
+#include <linux/rmap.h>
+#include <linux/syscalls.h>
+#include <linux/mmu_notifier.h>
+
+#include <asm/mmu_context.h>
+#include <asm/cacheflush.h>
+#include <asm/tlbflush.h>
+
+#include "internal.h"
+
+static int mm_counter(struct page *page)
+{
+	return PageAnon(page) ? MM_ANONPAGES : MM_FILEPAGES;
+}
+
+static void zap_pte(struct mm_struct *mm, struct vm_area_struct *vma,
+			unsigned long addr, pte_t *ptep)
+{
+	pte_t pte = *ptep;
+	struct page *page;
+	swp_entry_t entry;
+
+	if (pte_present(pte)) {
+		flush_cache_page(vma, addr, pte_pfn(pte));
+		pte = ptep_clear_flush(vma, addr, ptep);
+		page = vm_normal_page(vma, addr, pte);
+		if (page) {
+			if (pte_dirty(pte))
+				set_page_dirty(page);
+			update_hiwater_rss(mm);
+			dec_mm_counter(mm, mm_counter(page));
+			page_remove_rmap(page);
+			page_cache_release(page);
+		}
+	} else {	/* zap_pte() is not called when pte_none() */
+		if (!pte_file(pte)) {
+			update_hiwater_rss(mm);
+			entry = pte_to_swp_entry(pte);
+			if (non_swap_entry(entry)) {
+				if (is_migration_entry(entry)) {
+					page = migration_entry_to_page(entry);
+					dec_mm_counter(mm, mm_counter(page));
+				}
+			} else {
+				free_swap_and_cache(entry);
+				dec_mm_counter(mm, MM_SWAPENTS);
+			}
+		}
+		pte_clear_not_present_full(mm, addr, ptep, 0);
+	}
+}
+
+/*
+ * Install a file pte to a given virtual memory address, release any
+ * previously existing mapping.
+ */
+static int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma,
+		unsigned long addr, unsigned long pgoff, pgprot_t prot)
+{
+	int err = -ENOMEM;
+	pte_t *pte, ptfile;
+	spinlock_t *ptl;
+
+	pte = get_locked_pte(mm, addr, &ptl);
+	if (!pte)
+		goto out;
+
+	ptfile = pgoff_to_pte(pgoff);
+
+	if (!pte_none(*pte))
+		zap_pte(mm, vma, addr, pte);
+
+	set_pte_at(mm, addr, pte, pte_file_mksoft_dirty(ptfile));
+	/*
+	 * We don't need to run update_mmu_cache() here because the "file pte"
+	 * being installed by install_file_pte() is not a real pte - it's a
+	 * non-present entry (like a swap entry), noting what file offset should
+	 * be mapped there when there's a fault (in a non-linear vma where
+	 * that's not obvious).
+	 */
+	pte_unmap_unlock(pte, ptl);
+	err = 0;
+out:
+	return err;
+}
+
+int generic_file_remap_pages(struct vm_area_struct *vma, unsigned long addr,
+			     unsigned long size, pgoff_t pgoff)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	int err;
+
+	do {
+		err = install_file_pte(mm, vma, addr, pgoff, vma->vm_page_prot);
+		if (err)
+			return err;
+
+		size -= PAGE_SIZE;
+		addr += PAGE_SIZE;
+		pgoff++;
+	} while (size);
+
+	return 0;
+}
+EXPORT_SYMBOL(generic_file_remap_pages);
+
+/**
+ * sys_remap_file_pages - remap arbitrary pages of an existing VM_SHARED vma
+ * @start: start of the remapped virtual memory range
+ * @size: size of the remapped virtual memory range
+ * @prot: new protection bits of the range (see NOTE)
+ * @pgoff: to-be-mapped page of the backing store file
+ * @flags: 0 or MAP_NONBLOCKED - the later will cause no IO.
+ *
+ * sys_remap_file_pages remaps arbitrary pages of an existing VM_SHARED vma
+ * (shared backing store file).
+ *
+ * This syscall works purely via pagetables, so it's the most efficient
+ * way to map the same (large) file into a given virtual window. Unlike
+ * mmap()/mremap() it does not create any new vmas. The new mappings are
+ * also safe across swapout.
+ *
+ * NOTE: the @prot parameter right now is ignored (but must be zero),
+ * and the vma's default protection is used. Arbitrary protections
+ * might be implemented in the future.
+ */
+SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
+		unsigned long, prot, unsigned long, pgoff, unsigned long, flags)
+{
+	struct mm_struct *mm = current->mm;
+	struct address_space *mapping;
+	struct vm_area_struct *vma;
+	int err = -EINVAL;
+	int has_write_lock = 0;
+	vm_flags_t vm_flags = 0;
+
+	pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. "
+			"See Documentation/vm/remap_file_pages.txt.\n",
+			current->comm, current->pid);
+
+	if (prot)
+		return err;
+	/*
+	 * Sanitize the syscall parameters:
+	 */
+	start = start & PAGE_MASK;
+	size = size & PAGE_MASK;
+
+	/* Does the address range wrap, or is the span zero-sized? */
+	if (start + size <= start)
+		return err;
+
+	/* Does pgoff wrap? */
+	if (pgoff + (size >> PAGE_SHIFT) < pgoff)
+		return err;
+
+	/* Can we represent this offset inside this architecture's pte's? */
+#if PTE_FILE_MAX_BITS < BITS_PER_LONG
+	if (pgoff + (size >> PAGE_SHIFT) >= (1UL << PTE_FILE_MAX_BITS))
+		return err;
+#endif
+
+	/* We need down_write() to change vma->vm_flags. */
+	down_read(&mm->mmap_sem);
+ retry:
+	vma = find_vma(mm, start);
+
+	/*
+	 * Make sure the vma is shared, that it supports prefaulting,
+	 * and that the remapped range is valid and fully within
+	 * the single existing vma.
+	 */
+	if (!vma || !(vma->vm_flags & VM_SHARED))
+		goto out;
+
+	if (!vma->vm_ops || !vma->vm_ops->remap_pages)
+		goto out;
+
+	if (start < vma->vm_start || start + size > vma->vm_end)
+		goto out;
+
+	/* Must set VM_NONLINEAR before any pages are populated. */
+	if (!(vma->vm_flags & VM_NONLINEAR)) {
+		/*
+		 * vm_private_data is used as a swapout cursor
+		 * in a VM_NONLINEAR vma.
+		 */
+		if (vma->vm_private_data)
+			goto out;
+
+		/* Don't need a nonlinear mapping, exit success */
+		if (pgoff == linear_page_index(vma, start)) {
+			err = 0;
+			goto out;
+		}
+
+		if (!has_write_lock) {
+get_write_lock:
+			up_read(&mm->mmap_sem);
+			down_write(&mm->mmap_sem);
+			has_write_lock = 1;
+			goto retry;
+		}
+		mapping = vma->vm_file->f_mapping;
+		/*
+		 * page_mkclean doesn't work on nonlinear vmas, so if
+		 * dirty pages need to be accounted, emulate with linear
+		 * vmas.
+		 */
+		if (mapping_cap_account_dirty(mapping)) {
+			unsigned long addr;
+			struct file *file = get_file(vma->vm_file);
+			/* mmap_region may free vma; grab the info now */
+			vm_flags = vma->vm_flags;
+
+			addr = mmap_region(file, start, size, vm_flags, pgoff);
+			fput(file);
+			if (IS_ERR_VALUE(addr)) {
+				err = addr;
+			} else {
+				BUG_ON(addr != start);
+				err = 0;
+			}
+			goto out_freed;
+		}
+		mutex_lock(&mapping->i_mmap_mutex);
+		flush_dcache_mmap_lock(mapping);
+		vma->vm_flags |= VM_NONLINEAR;
+		vma_interval_tree_remove(vma, &mapping->i_mmap);
+		vma_nonlinear_insert(vma, &mapping->i_mmap_nonlinear);
+		flush_dcache_mmap_unlock(mapping);
+		mutex_unlock(&mapping->i_mmap_mutex);
+	}
+
+	if (vma->vm_flags & VM_LOCKED) {
+		/*
+		 * drop PG_Mlocked flag for over-mapped range
+		 */
+		if (!has_write_lock)
+			goto get_write_lock;
+		vm_flags = vma->vm_flags;
+		munlock_vma_pages_range(vma, start, start + size);
+		vma->vm_flags = vm_flags;
+	}
+
+	mmu_notifier_invalidate_range_start(mm, start, start + size);
+	err = vma->vm_ops->remap_pages(vma, start, size, pgoff);
+	mmu_notifier_invalidate_range_end(mm, start, start + size);
+
+	/*
+	 * We can't clear VM_NONLINEAR because we'd have to do
+	 * it after ->populate completes, and that would prevent
+	 * downgrading the lock.  (Locks can't be upgraded).
+	 */
+
+out:
+	if (vma)
+		vm_flags = vma->vm_flags;
+out_freed:
+	if (likely(!has_write_lock))
+		up_read(&mm->mmap_sem);
+	else
+		up_write(&mm->mmap_sem);
+	if (!err && ((vm_flags & VM_LOCKED) || !(flags & MAP_NONBLOCK)))
+		mm_populate(start, size);
+
+	return err;
+}

mm/frontswap.c

@@ -0,0 +1,457 @@
+/*
+ * Frontswap frontend
+ *
+ * This code provides the generic "frontend" layer to call a matching
+ * "backend" driver implementation of frontswap.  See
+ * Documentation/vm/frontswap.txt for more information.
+ *
+ * Copyright (C) 2009-2012 Oracle Corp.  All rights reserved.
+ * Author: Dan Magenheimer
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ */
+
+#include <linux/mman.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
+#include <linux/security.h>
+#include <linux/module.h>
+#include <linux/debugfs.h>
+#include <linux/frontswap.h>
+#include <linux/swapfile.h>
+
+/*
+ * frontswap_ops is set by frontswap_register_ops to contain the pointers
+ * to the frontswap "backend" implementation functions.
+ */
+static struct frontswap_ops *frontswap_ops __read_mostly;
+
+/*
+ * If enabled, frontswap_store will return failure even on success.  As
+ * a result, the swap subsystem will always write the page to swap, in
+ * effect converting frontswap into a writethrough cache.  In this mode,
+ * there is no direct reduction in swap writes, but a frontswap backend
+ * can unilaterally "reclaim" any pages in use with no data loss, thus
+ * providing increases control over maximum memory usage due to frontswap.
+ */
+static bool frontswap_writethrough_enabled __read_mostly;
+
+/*
+ * If enabled, the underlying tmem implementation is capable of doing
+ * exclusive gets, so frontswap_load, on a successful tmem_get must
+ * mark the page as no longer in frontswap AND mark it dirty.
+ */
+static bool frontswap_tmem_exclusive_gets_enabled __read_mostly;
+
+#ifdef CONFIG_DEBUG_FS
+/*
+ * Counters available via /sys/kernel/debug/frontswap (if debugfs is
+ * properly configured).  These are for information only so are not protected
+ * against increment races.
+ */
+static u64 frontswap_loads;
+static u64 frontswap_succ_stores;
+static u64 frontswap_failed_stores;
+static u64 frontswap_invalidates;
+
+static inline void inc_frontswap_loads(void) {
+	frontswap_loads++;
+}
+static inline void inc_frontswap_succ_stores(void) {
+	frontswap_succ_stores++;
+}
+static inline void inc_frontswap_failed_stores(void) {
+	frontswap_failed_stores++;
+}
+static inline void inc_frontswap_invalidates(void) {
+	frontswap_invalidates++;
+}
+#else
+static inline void inc_frontswap_loads(void) { }
+static inline void inc_frontswap_succ_stores(void) { }
+static inline void inc_frontswap_failed_stores(void) { }
+static inline void inc_frontswap_invalidates(void) { }
+#endif
+
+/*
+ * Due to the asynchronous nature of the backends loading potentially
+ * _after_ the swap system has been activated, we have chokepoints
+ * on all frontswap functions to not call the backend until the backend
+ * has registered.
+ *
+ * Specifically when no backend is registered (nobody called
+ * frontswap_register_ops) all calls to frontswap_init (which is done via
+ * swapon -> enable_swap_info -> frontswap_init) are registered and remembered
+ * (via the setting of need_init bitmap) but fail to create tmem_pools. When a
+ * backend registers with frontswap at some later point the previous
+ * calls to frontswap_init are executed (by iterating over the need_init
+ * bitmap) to create tmem_pools and set the respective poolids. All of that is
+ * guarded by us using atomic bit operations on the 'need_init' bitmap.
+ *
+ * This would not guards us against the user deciding to call swapoff right as
+ * we are calling the backend to initialize (so swapon is in action).
+ * Fortunatly for us, the swapon_mutex has been taked by the callee so we are
+ * OK. The other scenario where calls to frontswap_store (called via
+ * swap_writepage) is racing with frontswap_invalidate_area (called via
+ * swapoff) is again guarded by the swap subsystem.
+ *
+ * While no backend is registered all calls to frontswap_[store|load|
+ * invalidate_area|invalidate_page] are ignored or fail.
+ *
+ * The time between the backend being registered and the swap file system
+ * calling the backend (via the frontswap_* functions) is indeterminate as
+ * frontswap_ops is not atomic_t (or a value guarded by a spinlock).
+ * That is OK as we are comfortable missing some of these calls to the newly
+ * registered backend.
+ *
+ * Obviously the opposite (unloading the backend) must be done after all
+ * the frontswap_[store|load|invalidate_area|invalidate_page] start
+ * ignorning or failing the requests - at which point frontswap_ops
+ * would have to be made in some fashion atomic.
+ */
+static DECLARE_BITMAP(need_init, MAX_SWAPFILES);
+
+/*
+ * Register operations for frontswap, returning previous thus allowing
+ * detection of multiple backends and possible nesting.
+ */
+struct frontswap_ops *frontswap_register_ops(struct frontswap_ops *ops)
+{
+	struct frontswap_ops *old = frontswap_ops;
+	int i;
+
+	for (i = 0; i < MAX_SWAPFILES; i++) {
+		if (test_and_clear_bit(i, need_init)) {
+			struct swap_info_struct *sis = swap_info[i];
+			/* __frontswap_init _should_ have set it! */
+			if (!sis->frontswap_map)
+				return ERR_PTR(-EINVAL);
+			ops->init(i);
+		}
+	}
+	/*
+	 * We MUST have frontswap_ops set _after_ the frontswap_init's
+	 * have been called. Otherwise __frontswap_store might fail. Hence
+	 * the barrier to make sure compiler does not re-order us.
+	 */
+	barrier();
+	frontswap_ops = ops;
+	return old;
+}
+EXPORT_SYMBOL(frontswap_register_ops);
+
+/*
+ * Enable/disable frontswap writethrough (see above).
+ */
+void frontswap_writethrough(bool enable)
+{
+	frontswap_writethrough_enabled = enable;
+}
+EXPORT_SYMBOL(frontswap_writethrough);
+
+/*
+ * Enable/disable frontswap exclusive gets (see above).
+ */
+void frontswap_tmem_exclusive_gets(bool enable)
+{
+	frontswap_tmem_exclusive_gets_enabled = enable;
+}
+EXPORT_SYMBOL(frontswap_tmem_exclusive_gets);
+
+/*
+ * Called when a swap device is swapon'd.
+ */
+void __frontswap_init(unsigned type, unsigned long *map)
+{
+	struct swap_info_struct *sis = swap_info[type];
+
+	BUG_ON(sis == NULL);
+
+	/*
+	 * p->frontswap is a bitmap that we MUST have to figure out which page
+	 * has gone in frontswap. Without it there is no point of continuing.
+	 */
+	if (WARN_ON(!map))
+		return;
+	/*
+	 * Irregardless of whether the frontswap backend has been loaded
+	 * before this function or it will be later, we _MUST_ have the
+	 * p->frontswap set to something valid to work properly.
+	 */
+	frontswap_map_set(sis, map);
+	if (frontswap_ops)
+		frontswap_ops->init(type);
+	else {
+		BUG_ON(type > MAX_SWAPFILES);
+		set_bit(type, need_init);
+	}
+}
+EXPORT_SYMBOL(__frontswap_init);
+
+bool __frontswap_test(struct swap_info_struct *sis,
+				pgoff_t offset)
+{
+	bool ret = false;
+
+	if (frontswap_ops && sis->frontswap_map)
+		ret = test_bit(offset, sis->frontswap_map);
+	return ret;
+}
+EXPORT_SYMBOL(__frontswap_test);
+
+static inline void __frontswap_clear(struct swap_info_struct *sis,
+				pgoff_t offset)
+{
+	clear_bit(offset, sis->frontswap_map);
+	atomic_dec(&sis->frontswap_pages);
+}
+
+/*
+ * "Store" data from a page to frontswap and associate it with the page's
+ * swaptype and offset.  Page must be locked and in the swap cache.
+ * If frontswap already contains a page with matching swaptype and
+ * offset, the frontswap implementation may either overwrite the data and
+ * return success or invalidate the page from frontswap and return failure.
+ */
+int __frontswap_store(struct page *page)
+{
+	int ret = -1, dup = 0;
+	swp_entry_t entry = { .val = page_private(page), };
+	int type = swp_type(entry);
+	struct swap_info_struct *sis = swap_info[type];
+	pgoff_t offset = swp_offset(entry);
+
+	/*
+	 * Return if no backend registed.
+	 * Don't need to inc frontswap_failed_stores here.
+	 */
+	if (!frontswap_ops)
+		return ret;
+
+	BUG_ON(!PageLocked(page));
+	BUG_ON(sis == NULL);
+	if (__frontswap_test(sis, offset))
+		dup = 1;
+	ret = frontswap_ops->store(type, offset, page);
+	if (ret == 0) {
+		set_bit(offset, sis->frontswap_map);
+		inc_frontswap_succ_stores();
+		if (!dup)
+			atomic_inc(&sis->frontswap_pages);
+	} else {
+		/*
+		  failed dup always results in automatic invalidate of
+		  the (older) page from frontswap
+		 */
+		inc_frontswap_failed_stores();
+		if (dup) {
+			__frontswap_clear(sis, offset);
+			frontswap_ops->invalidate_page(type, offset);
+		}
+	}
+	if (frontswap_writethrough_enabled)
+		/* report failure so swap also writes to swap device */
+		ret = -1;
+	return ret;
+}
+EXPORT_SYMBOL(__frontswap_store);
+
+/*
+ * "Get" data from frontswap associated with swaptype and offset that were
+ * specified when the data was put to frontswap and use it to fill the
+ * specified page with data. Page must be locked and in the swap cache.
+ */
+int __frontswap_load(struct page *page)
+{
+	int ret = -1;
+	swp_entry_t entry = { .val = page_private(page), };
+	int type = swp_type(entry);
+	struct swap_info_struct *sis = swap_info[type];
+	pgoff_t offset = swp_offset(entry);
+
+	BUG_ON(!PageLocked(page));
+	BUG_ON(sis == NULL);
+	/*
+	 * __frontswap_test() will check whether there is backend registered
+	 */
+	if (__frontswap_test(sis, offset))
+		ret = frontswap_ops->load(type, offset, page);
+	if (ret == 0) {
+		inc_frontswap_loads();
+		if (frontswap_tmem_exclusive_gets_enabled) {
+			SetPageDirty(page);
+			__frontswap_clear(sis, offset);
+		}
+	}
+	return ret;
+}
+EXPORT_SYMBOL(__frontswap_load);
+
+/*
+ * Invalidate any data from frontswap associated with the specified swaptype
+ * and offset so that a subsequent "get" will fail.
+ */
+void __frontswap_invalidate_page(unsigned type, pgoff_t offset)
+{
+	struct swap_info_struct *sis = swap_info[type];
+
+	BUG_ON(sis == NULL);
+	/*
+	 * __frontswap_test() will check whether there is backend registered
+	 */
+	if (__frontswap_test(sis, offset)) {
+		frontswap_ops->invalidate_page(type, offset);
+		__frontswap_clear(sis, offset);
+		inc_frontswap_invalidates();
+	}
+}
+EXPORT_SYMBOL(__frontswap_invalidate_page);
+
+/*
+ * Invalidate all data from frontswap associated with all offsets for the
+ * specified swaptype.
+ */
+void __frontswap_invalidate_area(unsigned type)
+{
+	struct swap_info_struct *sis = swap_info[type];
+
+	if (frontswap_ops) {
+		BUG_ON(sis == NULL);
+		if (sis->frontswap_map == NULL)
+			return;
+		frontswap_ops->invalidate_area(type);
+		atomic_set(&sis->frontswap_pages, 0);
+		bitmap_zero(sis->frontswap_map, sis->max);
+	}
+	clear_bit(type, need_init);
+}
+EXPORT_SYMBOL(__frontswap_invalidate_area);
+
+static unsigned long __frontswap_curr_pages(void)
+{
+	unsigned long totalpages = 0;
+	struct swap_info_struct *si = NULL;
+
+	assert_spin_locked(&swap_lock);
+	plist_for_each_entry(si, &swap_active_head, list)
+		totalpages += atomic_read(&si->frontswap_pages);
+	return totalpages;
+}
+
+static int __frontswap_unuse_pages(unsigned long total, unsigned long *unused,
+					int *swapid)
+{
+	int ret = -EINVAL;
+	struct swap_info_struct *si = NULL;
+	int si_frontswap_pages;
+	unsigned long total_pages_to_unuse = total;
+	unsigned long pages = 0, pages_to_unuse = 0;
+
+	assert_spin_locked(&swap_lock);
+	plist_for_each_entry(si, &swap_active_head, list) {
+		si_frontswap_pages = atomic_read(&si->frontswap_pages);
+		if (total_pages_to_unuse < si_frontswap_pages) {
+			pages = pages_to_unuse = total_pages_to_unuse;
+		} else {
+			pages = si_frontswap_pages;
+			pages_to_unuse = 0; /* unuse all */
+		}
+		/* ensure there is enough RAM to fetch pages from frontswap */
+		if (security_vm_enough_memory_mm(current->mm, pages)) {
+			ret = -ENOMEM;
+			continue;
+		}
+		vm_unacct_memory(pages);
+		*unused = pages_to_unuse;
+		*swapid = si->type;
+		ret = 0;
+		break;
+	}
+
+	return ret;
+}
+
+/*
+ * Used to check if it's necessory and feasible to unuse pages.
+ * Return 1 when nothing to do, 0 when need to shink pages,
+ * error code when there is an error.
+ */
+static int __frontswap_shrink(unsigned long target_pages,
+				unsigned long *pages_to_unuse,
+				int *type)
+{
+	unsigned long total_pages = 0, total_pages_to_unuse;
+
+	assert_spin_locked(&swap_lock);
+
+	total_pages = __frontswap_curr_pages();
+	if (total_pages <= target_pages) {
+		/* Nothing to do */
+		*pages_to_unuse = 0;
+		return 1;
+	}
+	total_pages_to_unuse = total_pages - target_pages;
+	return __frontswap_unuse_pages(total_pages_to_unuse, pages_to_unuse, type);
+}
+
+/*
+ * Frontswap, like a true swap device, may unnecessarily retain pages
+ * under certain circumstances; "shrink" frontswap is essentially a
+ * "partial swapoff" and works by calling try_to_unuse to attempt to
+ * unuse enough frontswap pages to attempt to -- subject to memory
+ * constraints -- reduce the number of pages in frontswap to the
+ * number given in the parameter target_pages.
+ */
+void frontswap_shrink(unsigned long target_pages)
+{
+	unsigned long pages_to_unuse = 0;
+	int uninitialized_var(type), ret;
+
+	/*
+	 * we don't want to hold swap_lock while doing a very
+	 * lengthy try_to_unuse, but swap_list may change
+	 * so restart scan from swap_active_head each time
+	 */
+	spin_lock(&swap_lock);
+	ret = __frontswap_shrink(target_pages, &pages_to_unuse, &type);
+	spin_unlock(&swap_lock);
+	if (ret == 0)
+		try_to_unuse(type, true, pages_to_unuse);
+	return;
+}
+EXPORT_SYMBOL(frontswap_shrink);
+
+/*
+ * Count and return the number of frontswap pages across all
+ * swap devices.  This is exported so that backend drivers can
+ * determine current usage without reading debugfs.
+ */
+unsigned long frontswap_curr_pages(void)
+{
+	unsigned long totalpages = 0;
+
+	spin_lock(&swap_lock);
+	totalpages = __frontswap_curr_pages();
+	spin_unlock(&swap_lock);
+
+	return totalpages;
+}
+EXPORT_SYMBOL(frontswap_curr_pages);
+
+static int __init init_frontswap(void)
+{
+#ifdef CONFIG_DEBUG_FS
+	struct dentry *root = debugfs_create_dir("frontswap", NULL);
+	if (root == NULL)
+		return -ENXIO;
+	debugfs_create_u64("loads", S_IRUGO, root, &frontswap_loads);
+	debugfs_create_u64("succ_stores", S_IRUGO, root, &frontswap_succ_stores);
+	debugfs_create_u64("failed_stores", S_IRUGO, root,
+				&frontswap_failed_stores);
+	debugfs_create_u64("invalidates", S_IRUGO,
+				root, &frontswap_invalidates);
+#endif
+	return 0;
+}
+
+module_init(init_frontswap);

mm/highmem.c

@@ -0,0 +1,488 @@
+/*
+ * High memory handling common code and variables.
+ *
+ * (C) 1999 Andrea Arcangeli, SuSE GmbH, andrea@suse.de
+ *          Gerhard Wichert, Siemens AG, Gerhard.Wichert@pdb.siemens.de
+ *
+ *
+ * Redesigned the x86 32-bit VM architecture to deal with
+ * 64-bit physical space. With current x86 CPUs this
+ * means up to 64 Gigabytes physical RAM.
+ *
+ * Rewrote high memory support to move the page cache into
+ * high memory. Implemented permanent (schedulable) kmaps
+ * based on Linus' idea.
+ *
+ * Copyright (C) 1999 Ingo Molnar <mingo@redhat.com>
+ */
+
+#include <linux/mm.h>
+#include <linux/export.h>
+#include <linux/swap.h>
+#include <linux/bio.h>
+#include <linux/pagemap.h>
+#include <linux/mempool.h>
+#include <linux/blkdev.h>
+#include <linux/init.h>
+#include <linux/hash.h>
+#include <linux/highmem.h>
+#include <linux/kgdb.h>
+#include <asm/tlbflush.h>
+
+
+#if defined(CONFIG_HIGHMEM) || defined(CONFIG_X86_32)
+DEFINE_PER_CPU(int, __kmap_atomic_idx);
+#endif
+
+/*
+ * Virtual_count is not a pure "count".
+ *  0 means that it is not mapped, and has not been mapped
+ *    since a TLB flush - it is usable.
+ *  1 means that there are no users, but it has been mapped
+ *    since the last TLB flush - so we can't use it.
+ *  n means that there are (n-1) current users of it.
+ */
+#ifdef CONFIG_HIGHMEM
+
+/*
+ * Architecture with aliasing data cache may define the following family of
+ * helper functions in its asm/highmem.h to control cache color of virtual
+ * addresses where physical memory pages are mapped by kmap.
+ */
+#ifndef get_pkmap_color
+
+/*
+ * Determine color of virtual address where the page should be mapped.
+ */
+static inline unsigned int get_pkmap_color(struct page *page)
+{
+	return 0;
+}
+#define get_pkmap_color get_pkmap_color
+
+/*
+ * Get next index for mapping inside PKMAP region for page with given color.
+ */
+static inline unsigned int get_next_pkmap_nr(unsigned int color)
+{
+	static unsigned int last_pkmap_nr;
+
+	last_pkmap_nr = (last_pkmap_nr + 1) & LAST_PKMAP_MASK;
+	return last_pkmap_nr;
+}
+
+/*
+ * Determine if page index inside PKMAP region (pkmap_nr) of given color
+ * has wrapped around PKMAP region end. When this happens an attempt to
+ * flush all unused PKMAP slots is made.
+ */
+static inline int no_more_pkmaps(unsigned int pkmap_nr, unsigned int color)
+{
+	return pkmap_nr == 0;
+}
+
+/*
+ * Get the number of PKMAP entries of the given color. If no free slot is
+ * found after checking that many entries, kmap will sleep waiting for
+ * someone to call kunmap and free PKMAP slot.
+ */
+static inline int get_pkmap_entries_count(unsigned int color)
+{
+	return LAST_PKMAP;
+}
+
+/*
+ * Get head of a wait queue for PKMAP entries of the given color.
+ * Wait queues for different mapping colors should be independent to avoid
+ * unnecessary wakeups caused by freeing of slots of other colors.
+ */
+static inline wait_queue_head_t *get_pkmap_wait_queue_head(unsigned int color)
+{
+	static DECLARE_WAIT_QUEUE_HEAD(pkmap_map_wait);
+
+	return &pkmap_map_wait;
+}
+#endif
+
+unsigned long totalhigh_pages __read_mostly;
+EXPORT_SYMBOL(totalhigh_pages);
+
+
+EXPORT_PER_CPU_SYMBOL(__kmap_atomic_idx);
+
+unsigned int nr_free_highpages (void)
+{
+	pg_data_t *pgdat;
+	unsigned int pages = 0;
+
+	for_each_online_pgdat(pgdat) {
+		pages += zone_page_state(&pgdat->node_zones[ZONE_HIGHMEM],
+			NR_FREE_PAGES);
+		if (zone_movable_is_highmem())
+			pages += zone_page_state(
+					&pgdat->node_zones[ZONE_MOVABLE],
+					NR_FREE_PAGES);
+	}
+
+	return pages;
+}
+
+static int pkmap_count[LAST_PKMAP];
+static  __cacheline_aligned_in_smp DEFINE_SPINLOCK(kmap_lock);
+
+pte_t * pkmap_page_table;
+
+/*
+ * Most architectures have no use for kmap_high_get(), so let's abstract
+ * the disabling of IRQ out of the locking in that case to save on a
+ * potential useless overhead.
+ */
+#ifdef ARCH_NEEDS_KMAP_HIGH_GET
+#define lock_kmap()             spin_lock_irq(&kmap_lock)
+#define unlock_kmap()           spin_unlock_irq(&kmap_lock)
+#define lock_kmap_any(flags)    spin_lock_irqsave(&kmap_lock, flags)
+#define unlock_kmap_any(flags)  spin_unlock_irqrestore(&kmap_lock, flags)
+#else
+#define lock_kmap()             spin_lock(&kmap_lock)
+#define unlock_kmap()           spin_unlock(&kmap_lock)
+#define lock_kmap_any(flags)    \
+		do { spin_lock(&kmap_lock); (void)(flags); } while (0)
+#define unlock_kmap_any(flags)  \
+		do { spin_unlock(&kmap_lock); (void)(flags); } while (0)
+#endif
+
+struct page *kmap_to_page(void *vaddr)
+{
+	unsigned long addr = (unsigned long)vaddr;
+
+	if (addr >= PKMAP_ADDR(0) && addr < PKMAP_ADDR(LAST_PKMAP)) {
+		int i = PKMAP_NR(addr);
+		return pte_page(pkmap_page_table[i]);
+	}
+
+	return virt_to_page(addr);
+}
+EXPORT_SYMBOL(kmap_to_page);
+
+static void flush_all_zero_pkmaps(void)
+{
+	int i;
+	int need_flush = 0;
+
+	flush_cache_kmaps();
+
+	for (i = 0; i < LAST_PKMAP; i++) {
+		struct page *page;
+
+		/*
+		 * zero means we don't have anything to do,
+		 * >1 means that it is still in use. Only
+		 * a count of 1 means that it is free but
+		 * needs to be unmapped
+		 */
+		if (pkmap_count[i] != 1)
+			continue;
+		pkmap_count[i] = 0;
+
+		/* sanity check */
+		BUG_ON(pte_none(pkmap_page_table[i]));
+
+		/*
+		 * Don't need an atomic fetch-and-clear op here;
+		 * no-one has the page mapped, and cannot get at
+		 * its virtual address (and hence PTE) without first
+		 * getting the kmap_lock (which is held here).
+		 * So no dangers, even with speculative execution.
+		 */
+		page = pte_page(pkmap_page_table[i]);
+		pte_clear(&init_mm, PKMAP_ADDR(i), &pkmap_page_table[i]);
+
+		set_page_address(page, NULL);
+		need_flush = 1;
+	}
+	if (need_flush)
+		flush_tlb_kernel_range(PKMAP_ADDR(0), PKMAP_ADDR(LAST_PKMAP));
+}
+
+/**
+ * kmap_flush_unused - flush all unused kmap mappings in order to remove stray mappings
+ */
+void kmap_flush_unused(void)
+{
+	lock_kmap();
+	flush_all_zero_pkmaps();
+	unlock_kmap();
+}
+
+static inline unsigned long map_new_virtual(struct page *page)
+{
+	unsigned long vaddr;
+	int count;
+	unsigned int last_pkmap_nr;
+	unsigned int color = get_pkmap_color(page);
+
+start:
+	count = get_pkmap_entries_count(color);
+	/* Find an empty entry */
+	for (;;) {
+		last_pkmap_nr = get_next_pkmap_nr(color);
+		if (no_more_pkmaps(last_pkmap_nr, color)) {
+			flush_all_zero_pkmaps();
+			count = get_pkmap_entries_count(color);
+		}
+		if (!pkmap_count[last_pkmap_nr])
+			break;	/* Found a usable entry */
+		if (--count)
+			continue;
+
+		/*
+		 * Sleep for somebody else to unmap their entries
+		 */
+		{
+			DECLARE_WAITQUEUE(wait, current);
+			wait_queue_head_t *pkmap_map_wait =
+				get_pkmap_wait_queue_head(color);
+
+			__set_current_state(TASK_UNINTERRUPTIBLE);
+			add_wait_queue(pkmap_map_wait, &wait);
+			unlock_kmap();
+			schedule();
+			remove_wait_queue(pkmap_map_wait, &wait);
+			lock_kmap();
+
+			/* Somebody else might have mapped it while we slept */
+			if (page_address(page))
+				return (unsigned long)page_address(page);
+
+			/* Re-start */
+			goto start;
+		}
+	}
+	vaddr = PKMAP_ADDR(last_pkmap_nr);
+	set_pte_at(&init_mm, vaddr,
+		   &(pkmap_page_table[last_pkmap_nr]), mk_pte(page, kmap_prot));
+
+	pkmap_count[last_pkmap_nr] = 1;
+	set_page_address(page, (void *)vaddr);
+
+	return vaddr;
+}
+
+/**
+ * kmap_high - map a highmem page into memory
+ * @page: &struct page to map
+ *
+ * Returns the page's virtual memory address.
+ *
+ * We cannot call this from interrupts, as it may block.
+ */
+void *kmap_high(struct page *page)
+{
+	unsigned long vaddr;
+
+	/*
+	 * For highmem pages, we can't trust "virtual" until
+	 * after we have the lock.
+	 */
+	lock_kmap();
+	vaddr = (unsigned long)page_address(page);
+	if (!vaddr)
+		vaddr = map_new_virtual(page);
+	pkmap_count[PKMAP_NR(vaddr)]++;
+	BUG_ON(pkmap_count[PKMAP_NR(vaddr)] < 2);
+	unlock_kmap();
+	return (void*) vaddr;
+}
+
+EXPORT_SYMBOL(kmap_high);
+
+#ifdef ARCH_NEEDS_KMAP_HIGH_GET
+/**
+ * kmap_high_get - pin a highmem page into memory
+ * @page: &struct page to pin
+ *
+ * Returns the page's current virtual memory address, or NULL if no mapping
+ * exists.  If and only if a non null address is returned then a
+ * matching call to kunmap_high() is necessary.
+ *
+ * This can be called from any context.
+ */
+void *kmap_high_get(struct page *page)
+{
+	unsigned long vaddr, flags;
+
+	lock_kmap_any(flags);
+	vaddr = (unsigned long)page_address(page);
+	if (vaddr) {
+		BUG_ON(pkmap_count[PKMAP_NR(vaddr)] < 1);
+		pkmap_count[PKMAP_NR(vaddr)]++;
+	}
+	unlock_kmap_any(flags);
+	return (void*) vaddr;
+}
+#endif
+
+/**
+ * kunmap_high - unmap a highmem page into memory
+ * @page: &struct page to unmap
+ *
+ * If ARCH_NEEDS_KMAP_HIGH_GET is not defined then this may be called
+ * only from user context.
+ */
+void kunmap_high(struct page *page)
+{
+	unsigned long vaddr;
+	unsigned long nr;
+	unsigned long flags;
+	int need_wakeup;
+	unsigned int color = get_pkmap_color(page);
+	wait_queue_head_t *pkmap_map_wait;
+
+	lock_kmap_any(flags);
+	vaddr = (unsigned long)page_address(page);
+	BUG_ON(!vaddr);
+	nr = PKMAP_NR(vaddr);
+
+	/*
+	 * A count must never go down to zero
+	 * without a TLB flush!
+	 */
+	need_wakeup = 0;
+	switch (--pkmap_count[nr]) {
+	case 0:
+		BUG();
+	case 1:
+		/*
+		 * Avoid an unnecessary wake_up() function call.
+		 * The common case is pkmap_count[] == 1, but
+		 * no waiters.
+		 * The tasks queued in the wait-queue are guarded
+		 * by both the lock in the wait-queue-head and by
+		 * the kmap_lock.  As the kmap_lock is held here,
+		 * no need for the wait-queue-head's lock.  Simply
+		 * test if the queue is empty.
+		 */
+		pkmap_map_wait = get_pkmap_wait_queue_head(color);
+		need_wakeup = waitqueue_active(pkmap_map_wait);
+	}
+	unlock_kmap_any(flags);
+
+	/* do wake-up, if needed, race-free outside of the spin lock */
+	if (need_wakeup)
+		wake_up(pkmap_map_wait);
+}
+
+EXPORT_SYMBOL(kunmap_high);
+#endif
+
+#if defined(HASHED_PAGE_VIRTUAL)
+
+#define PA_HASH_ORDER	7
+
+/*
+ * Describes one page->virtual association
+ */
+struct page_address_map {
+	struct page *page;
+	void *virtual;
+	struct list_head list;
+};
+
+static struct page_address_map page_address_maps[LAST_PKMAP];
+
+/*
+ * Hash table bucket
+ */
+static struct page_address_slot {
+	struct list_head lh;			/* List of page_address_maps */
+	spinlock_t lock;			/* Protect this bucket's list */
+} ____cacheline_aligned_in_smp page_address_htable[1<<PA_HASH_ORDER];
+
+static struct page_address_slot *page_slot(const struct page *page)
+{
+	return &page_address_htable[hash_ptr(page, PA_HASH_ORDER)];
+}
+
+/**
+ * page_address - get the mapped virtual address of a page
+ * @page: &struct page to get the virtual address of
+ *
+ * Returns the page's virtual address.
+ */
+void *page_address(const struct page *page)
+{
+	unsigned long flags;
+	void *ret;
+	struct page_address_slot *pas;
+
+	if (!PageHighMem(page))
+		return lowmem_page_address(page);
+
+	pas = page_slot(page);
+	ret = NULL;
+	spin_lock_irqsave(&pas->lock, flags);
+	if (!list_empty(&pas->lh)) {
+		struct page_address_map *pam;
+
+		list_for_each_entry(pam, &pas->lh, list) {
+			if (pam->page == page) {
+				ret = pam->virtual;
+				goto done;
+			}
+		}
+	}
+done:
+	spin_unlock_irqrestore(&pas->lock, flags);
+	return ret;
+}
+
+EXPORT_SYMBOL(page_address);
+
+/**
+ * set_page_address - set a page's virtual address
+ * @page: &struct page to set
+ * @virtual: virtual address to use
+ */
+void set_page_address(struct page *page, void *virtual)
+{
+	unsigned long flags;
+	struct page_address_slot *pas;
+	struct page_address_map *pam;
+
+	BUG_ON(!PageHighMem(page));
+
+	pas = page_slot(page);
+	if (virtual) {		/* Add */
+		pam = &page_address_maps[PKMAP_NR((unsigned long)virtual)];
+		pam->page = page;
+		pam->virtual = virtual;
+
+		spin_lock_irqsave(&pas->lock, flags);
+		list_add_tail(&pam->list, &pas->lh);
+		spin_unlock_irqrestore(&pas->lock, flags);
+	} else {		/* Remove */
+		spin_lock_irqsave(&pas->lock, flags);
+		list_for_each_entry(pam, &pas->lh, list) {
+			if (pam->page == page) {
+				list_del(&pam->list);
+				spin_unlock_irqrestore(&pas->lock, flags);
+				goto done;
+			}
+		}
+		spin_unlock_irqrestore(&pas->lock, flags);
+	}
+done:
+	return;
+}
+
+void __init page_address_init(void)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(page_address_htable); i++) {
+		INIT_LIST_HEAD(&page_address_htable[i].lh);
+		spin_lock_init(&page_address_htable[i].lock);
+	}
+}
+
+#endif	/* defined(CONFIG_HIGHMEM) && !defined(WANT_PAGE_VIRTUAL) */

mm/hugetlb_cgroup.c

@@ -0,0 +1,409 @@
+/*
+ *
+ * Copyright IBM Corporation, 2012
+ * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2.1 of the GNU Lesser General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ *
+ */
+
+#include <linux/cgroup.h>
+#include <linux/slab.h>
+#include <linux/hugetlb.h>
+#include <linux/hugetlb_cgroup.h>
+
+struct hugetlb_cgroup {
+	struct cgroup_subsys_state css;
+	/*
+	 * the counter to account for hugepages from hugetlb.
+	 */
+	struct res_counter hugepage[HUGE_MAX_HSTATE];
+};
+
+#define MEMFILE_PRIVATE(x, val)	(((x) << 16) | (val))
+#define MEMFILE_IDX(val)	(((val) >> 16) & 0xffff)
+#define MEMFILE_ATTR(val)	((val) & 0xffff)
+
+static struct hugetlb_cgroup *root_h_cgroup __read_mostly;
+
+static inline
+struct hugetlb_cgroup *hugetlb_cgroup_from_css(struct cgroup_subsys_state *s)
+{
+	return s ? container_of(s, struct hugetlb_cgroup, css) : NULL;
+}
+
+static inline
+struct hugetlb_cgroup *hugetlb_cgroup_from_task(struct task_struct *task)
+{
+	return hugetlb_cgroup_from_css(task_css(task, hugetlb_cgrp_id));
+}
+
+static inline bool hugetlb_cgroup_is_root(struct hugetlb_cgroup *h_cg)
+{
+	return (h_cg == root_h_cgroup);
+}
+
+static inline struct hugetlb_cgroup *
+parent_hugetlb_cgroup(struct hugetlb_cgroup *h_cg)
+{
+	return hugetlb_cgroup_from_css(h_cg->css.parent);
+}
+
+static inline bool hugetlb_cgroup_have_usage(struct hugetlb_cgroup *h_cg)
+{
+	int idx;
+
+	for (idx = 0; idx < hugetlb_max_hstate; idx++) {
+		if ((res_counter_read_u64(&h_cg->hugepage[idx], RES_USAGE)) > 0)
+			return true;
+	}
+	return false;
+}
+
+static struct cgroup_subsys_state *
+hugetlb_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
+{
+	struct hugetlb_cgroup *parent_h_cgroup = hugetlb_cgroup_from_css(parent_css);
+	struct hugetlb_cgroup *h_cgroup;
+	int idx;
+
+	h_cgroup = kzalloc(sizeof(*h_cgroup), GFP_KERNEL);
+	if (!h_cgroup)
+		return ERR_PTR(-ENOMEM);
+
+	if (parent_h_cgroup) {
+		for (idx = 0; idx < HUGE_MAX_HSTATE; idx++)
+			res_counter_init(&h_cgroup->hugepage[idx],
+					 &parent_h_cgroup->hugepage[idx]);
+	} else {
+		root_h_cgroup = h_cgroup;
+		for (idx = 0; idx < HUGE_MAX_HSTATE; idx++)
+			res_counter_init(&h_cgroup->hugepage[idx], NULL);
+	}
+	return &h_cgroup->css;
+}
+
+static void hugetlb_cgroup_css_free(struct cgroup_subsys_state *css)
+{
+	struct hugetlb_cgroup *h_cgroup;
+
+	h_cgroup = hugetlb_cgroup_from_css(css);
+	kfree(h_cgroup);
+}
+
+
+/*
+ * Should be called with hugetlb_lock held.
+ * Since we are holding hugetlb_lock, pages cannot get moved from
+ * active list or uncharged from the cgroup, So no need to get
+ * page reference and test for page active here. This function
+ * cannot fail.
+ */
+static void hugetlb_cgroup_move_parent(int idx, struct hugetlb_cgroup *h_cg,
+				       struct page *page)
+{
+	int csize;
+	struct res_counter *counter;
+	struct res_counter *fail_res;
+	struct hugetlb_cgroup *page_hcg;
+	struct hugetlb_cgroup *parent = parent_hugetlb_cgroup(h_cg);
+
+	page_hcg = hugetlb_cgroup_from_page(page);
+	/*
+	 * We can have pages in active list without any cgroup
+	 * ie, hugepage with less than 3 pages. We can safely
+	 * ignore those pages.
+	 */
+	if (!page_hcg || page_hcg != h_cg)
+		goto out;
+
+	csize = PAGE_SIZE << compound_order(page);
+	if (!parent) {
+		parent = root_h_cgroup;
+		/* root has no limit */
+		res_counter_charge_nofail(&parent->hugepage[idx],
+					  csize, &fail_res);
+	}
+	counter = &h_cg->hugepage[idx];
+	res_counter_uncharge_until(counter, counter->parent, csize);
+
+	set_hugetlb_cgroup(page, parent);
+out:
+	return;
+}
+
+/*
+ * Force the hugetlb cgroup to empty the hugetlb resources by moving them to
+ * the parent cgroup.
+ */
+static void hugetlb_cgroup_css_offline(struct cgroup_subsys_state *css)
+{
+	struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css);
+	struct hstate *h;
+	struct page *page;
+	int idx = 0;
+
+	do {
+		for_each_hstate(h) {
+			spin_lock(&hugetlb_lock);
+			list_for_each_entry(page, &h->hugepage_activelist, lru)
+				hugetlb_cgroup_move_parent(idx, h_cg, page);
+
+			spin_unlock(&hugetlb_lock);
+			idx++;
+		}
+		cond_resched();
+	} while (hugetlb_cgroup_have_usage(h_cg));
+}
+
+int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages,
+				 struct hugetlb_cgroup **ptr)
+{
+	int ret = 0;
+	struct res_counter *fail_res;
+	struct hugetlb_cgroup *h_cg = NULL;
+	unsigned long csize = nr_pages * PAGE_SIZE;
+
+	if (hugetlb_cgroup_disabled())
+		goto done;
+	/*
+	 * We don't charge any cgroup if the compound page have less
+	 * than 3 pages.
+	 */
+	if (huge_page_order(&hstates[idx]) < HUGETLB_CGROUP_MIN_ORDER)
+		goto done;
+again:
+	rcu_read_lock();
+	h_cg = hugetlb_cgroup_from_task(current);
+	if (!css_tryget_online(&h_cg->css)) {
+		rcu_read_unlock();
+		goto again;
+	}
+	rcu_read_unlock();
+
+	ret = res_counter_charge(&h_cg->hugepage[idx], csize, &fail_res);
+	css_put(&h_cg->css);
+done:
+	*ptr = h_cg;
+	return ret;
+}
+
+/* Should be called with hugetlb_lock held */
+void hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages,
+				  struct hugetlb_cgroup *h_cg,
+				  struct page *page)
+{
+	if (hugetlb_cgroup_disabled() || !h_cg)
+		return;
+
+	set_hugetlb_cgroup(page, h_cg);
+	return;
+}
+
+/*
+ * Should be called with hugetlb_lock held
+ */
+void hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages,
+				  struct page *page)
+{
+	struct hugetlb_cgroup *h_cg;
+	unsigned long csize = nr_pages * PAGE_SIZE;
+
+	if (hugetlb_cgroup_disabled())
+		return;
+	lockdep_assert_held(&hugetlb_lock);
+	h_cg = hugetlb_cgroup_from_page(page);
+	if (unlikely(!h_cg))
+		return;
+	set_hugetlb_cgroup(page, NULL);
+	res_counter_uncharge(&h_cg->hugepage[idx], csize);
+	return;
+}
+
+void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages,
+				    struct hugetlb_cgroup *h_cg)
+{
+	unsigned long csize = nr_pages * PAGE_SIZE;
+
+	if (hugetlb_cgroup_disabled() || !h_cg)
+		return;
+
+	if (huge_page_order(&hstates[idx]) < HUGETLB_CGROUP_MIN_ORDER)
+		return;
+
+	res_counter_uncharge(&h_cg->hugepage[idx], csize);
+	return;
+}
+
+static u64 hugetlb_cgroup_read_u64(struct cgroup_subsys_state *css,
+				   struct cftype *cft)
+{
+	int idx, name;
+	struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css);
+
+	idx = MEMFILE_IDX(cft->private);
+	name = MEMFILE_ATTR(cft->private);
+
+	return res_counter_read_u64(&h_cg->hugepage[idx], name);
+}
+
+static ssize_t hugetlb_cgroup_write(struct kernfs_open_file *of,
+				    char *buf, size_t nbytes, loff_t off)
+{
+	int idx, name, ret;
+	unsigned long long val;
+	struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(of_css(of));
+
+	buf = strstrip(buf);
+	idx = MEMFILE_IDX(of_cft(of)->private);
+	name = MEMFILE_ATTR(of_cft(of)->private);
+
+	switch (name) {
+	case RES_LIMIT:
+		if (hugetlb_cgroup_is_root(h_cg)) {
+			/* Can't set limit on root */
+			ret = -EINVAL;
+			break;
+		}
+		/* This function does all necessary parse...reuse it */
+		ret = res_counter_memparse_write_strategy(buf, &val);
+		if (ret)
+			break;
+		val = ALIGN(val, 1ULL << huge_page_shift(&hstates[idx]));
+		ret = res_counter_set_limit(&h_cg->hugepage[idx], val);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+	return ret ?: nbytes;
+}
+
+static ssize_t hugetlb_cgroup_reset(struct kernfs_open_file *of,
+				    char *buf, size_t nbytes, loff_t off)
+{
+	int idx, name, ret = 0;
+	struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(of_css(of));
+
+	idx = MEMFILE_IDX(of_cft(of)->private);
+	name = MEMFILE_ATTR(of_cft(of)->private);
+
+	switch (name) {
+	case RES_MAX_USAGE:
+		res_counter_reset_max(&h_cg->hugepage[idx]);
+		break;
+	case RES_FAILCNT:
+		res_counter_reset_failcnt(&h_cg->hugepage[idx]);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+	return ret ?: nbytes;
+}
+
+static char *mem_fmt(char *buf, int size, unsigned long hsize)
+{
+	if (hsize >= (1UL << 30))
+		snprintf(buf, size, "%luGB", hsize >> 30);
+	else if (hsize >= (1UL << 20))
+		snprintf(buf, size, "%luMB", hsize >> 20);
+	else
+		snprintf(buf, size, "%luKB", hsize >> 10);
+	return buf;
+}
+
+static void __init __hugetlb_cgroup_file_init(int idx)
+{
+	char buf[32];
+	struct cftype *cft;
+	struct hstate *h = &hstates[idx];
+
+	/* format the size */
+	mem_fmt(buf, 32, huge_page_size(h));
+
+	/* Add the limit file */
+	cft = &h->cgroup_files[0];
+	snprintf(cft->name, MAX_CFTYPE_NAME, "%s.limit_in_bytes", buf);
+	cft->private = MEMFILE_PRIVATE(idx, RES_LIMIT);
+	cft->read_u64 = hugetlb_cgroup_read_u64;
+	cft->write = hugetlb_cgroup_write;
+
+	/* Add the usage file */
+	cft = &h->cgroup_files[1];
+	snprintf(cft->name, MAX_CFTYPE_NAME, "%s.usage_in_bytes", buf);
+	cft->private = MEMFILE_PRIVATE(idx, RES_USAGE);
+	cft->read_u64 = hugetlb_cgroup_read_u64;
+
+	/* Add the MAX usage file */
+	cft = &h->cgroup_files[2];
+	snprintf(cft->name, MAX_CFTYPE_NAME, "%s.max_usage_in_bytes", buf);
+	cft->private = MEMFILE_PRIVATE(idx, RES_MAX_USAGE);
+	cft->write = hugetlb_cgroup_reset;
+	cft->read_u64 = hugetlb_cgroup_read_u64;
+
+	/* Add the failcntfile */
+	cft = &h->cgroup_files[3];
+	snprintf(cft->name, MAX_CFTYPE_NAME, "%s.failcnt", buf);
+	cft->private  = MEMFILE_PRIVATE(idx, RES_FAILCNT);
+	cft->write = hugetlb_cgroup_reset;
+	cft->read_u64 = hugetlb_cgroup_read_u64;
+
+	/* NULL terminate the last cft */
+	cft = &h->cgroup_files[4];
+	memset(cft, 0, sizeof(*cft));
+
+	WARN_ON(cgroup_add_legacy_cftypes(&hugetlb_cgrp_subsys,
+					  h->cgroup_files));
+}
+
+void __init hugetlb_cgroup_file_init(void)
+{
+	struct hstate *h;
+
+	for_each_hstate(h) {
+		/*
+		 * Add cgroup control files only if the huge page consists
+		 * of more than two normal pages. This is because we use
+		 * page[2].lru.next for storing cgroup details.
+		 */
+		if (huge_page_order(h) >= HUGETLB_CGROUP_MIN_ORDER)
+			__hugetlb_cgroup_file_init(hstate_index(h));
+	}
+}
+
+/*
+ * hugetlb_lock will make sure a parallel cgroup rmdir won't happen
+ * when we migrate hugepages
+ */
+void hugetlb_cgroup_migrate(struct page *oldhpage, struct page *newhpage)
+{
+	struct hugetlb_cgroup *h_cg;
+	struct hstate *h = page_hstate(oldhpage);
+
+	if (hugetlb_cgroup_disabled())
+		return;
+
+	VM_BUG_ON_PAGE(!PageHuge(oldhpage), oldhpage);
+	spin_lock(&hugetlb_lock);
+	h_cg = hugetlb_cgroup_from_page(oldhpage);
+	set_hugetlb_cgroup(oldhpage, NULL);
+
+	/* move the h_cg details to new cgroup */
+	set_hugetlb_cgroup(newhpage, h_cg);
+	list_move(&newhpage->lru, &h->hugepage_activelist);
+	spin_unlock(&hugetlb_lock);
+	return;
+}
+
+struct cgroup_subsys hugetlb_cgrp_subsys = {
+	.css_alloc	= hugetlb_cgroup_css_alloc,
+	.css_offline	= hugetlb_cgroup_css_offline,
+	.css_free	= hugetlb_cgroup_css_free,
+};

mm/hwpoison-inject.c

@@ -0,0 +1,141 @@
+/* Inject a hwpoison memory failure on a arbitrary pfn */
+#include <linux/module.h>
+#include <linux/debugfs.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/swap.h>
+#include <linux/pagemap.h>
+#include <linux/hugetlb.h>
+#include "internal.h"
+
+static struct dentry *hwpoison_dir;
+
+static int hwpoison_inject(void *data, u64 val)
+{
+	unsigned long pfn = val;
+	struct page *p;
+	struct page *hpage;
+	int err;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (!pfn_valid(pfn))
+		return -ENXIO;
+
+	p = pfn_to_page(pfn);
+	hpage = compound_head(p);
+	/*
+	 * This implies unable to support free buddy pages.
+	 */
+	if (!get_page_unless_zero(hpage))
+		return 0;
+
+	if (!hwpoison_filter_enable)
+		goto inject;
+
+	if (!PageLRU(p) && !PageHuge(p))
+		shake_page(p, 0);
+	/*
+	 * This implies unable to support non-LRU pages.
+	 */
+	if (!PageLRU(p) && !PageHuge(p))
+		return 0;
+
+	/*
+	 * do a racy check with elevated page count, to make sure PG_hwpoison
+	 * will only be set for the targeted owner (or on a free page).
+	 * We temporarily take page lock for try_get_mem_cgroup_from_page().
+	 * memory_failure() will redo the check reliably inside page lock.
+	 */
+	lock_page(hpage);
+	err = hwpoison_filter(hpage);
+	unlock_page(hpage);
+	if (err)
+		return 0;
+
+inject:
+	pr_info("Injecting memory failure at pfn %#lx\n", pfn);
+	return memory_failure(pfn, 18, MF_COUNT_INCREASED);
+}
+
+static int hwpoison_unpoison(void *data, u64 val)
+{
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	return unpoison_memory(val);
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(hwpoison_fops, NULL, hwpoison_inject, "%lli\n");
+DEFINE_SIMPLE_ATTRIBUTE(unpoison_fops, NULL, hwpoison_unpoison, "%lli\n");
+
+static void pfn_inject_exit(void)
+{
+	debugfs_remove_recursive(hwpoison_dir);
+}
+
+static int pfn_inject_init(void)
+{
+	struct dentry *dentry;
+
+	hwpoison_dir = debugfs_create_dir("hwpoison", NULL);
+	if (hwpoison_dir == NULL)
+		return -ENOMEM;
+
+	/*
+	 * Note that the below poison/unpoison interfaces do not involve
+	 * hardware status change, hence do not require hardware support.
+	 * They are mainly for testing hwpoison in software level.
+	 */
+	dentry = debugfs_create_file("corrupt-pfn", 0200, hwpoison_dir,
+					  NULL, &hwpoison_fops);
+	if (!dentry)
+		goto fail;
+
+	dentry = debugfs_create_file("unpoison-pfn", 0200, hwpoison_dir,
+				     NULL, &unpoison_fops);
+	if (!dentry)
+		goto fail;
+
+	dentry = debugfs_create_u32("corrupt-filter-enable", 0600,
+				    hwpoison_dir, &hwpoison_filter_enable);
+	if (!dentry)
+		goto fail;
+
+	dentry = debugfs_create_u32("corrupt-filter-dev-major", 0600,
+				    hwpoison_dir, &hwpoison_filter_dev_major);
+	if (!dentry)
+		goto fail;
+
+	dentry = debugfs_create_u32("corrupt-filter-dev-minor", 0600,
+				    hwpoison_dir, &hwpoison_filter_dev_minor);
+	if (!dentry)
+		goto fail;
+
+	dentry = debugfs_create_u64("corrupt-filter-flags-mask", 0600,
+				    hwpoison_dir, &hwpoison_filter_flags_mask);
+	if (!dentry)
+		goto fail;
+
+	dentry = debugfs_create_u64("corrupt-filter-flags-value", 0600,
+				    hwpoison_dir, &hwpoison_filter_flags_value);
+	if (!dentry)
+		goto fail;
+
+#ifdef CONFIG_MEMCG_SWAP
+	dentry = debugfs_create_u64("corrupt-filter-memcg", 0600,
+				    hwpoison_dir, &hwpoison_filter_memcg);
+	if (!dentry)
+		goto fail;
+#endif
+
+	return 0;
+fail:
+	pfn_inject_exit();
+	return -ENOMEM;
+}
+
+module_init(pfn_inject_init);
+module_exit(pfn_inject_exit);
+MODULE_LICENSE("GPL");

mm/init-mm.c

@@ -0,0 +1,25 @@
+#include <linux/mm_types.h>
+#include <linux/rbtree.h>
+#include <linux/rwsem.h>
+#include <linux/spinlock.h>
+#include <linux/list.h>
+#include <linux/cpumask.h>
+
+#include <linux/atomic.h>
+#include <asm/pgtable.h>
+#include <asm/mmu.h>
+
+#ifndef INIT_MM_CONTEXT
+#define INIT_MM_CONTEXT(name)
+#endif
+
+struct mm_struct init_mm = {
+	.mm_rb		= RB_ROOT,
+	.pgd		= swapper_pg_dir,
+	.mm_users	= ATOMIC_INIT(2),
+	.mm_count	= ATOMIC_INIT(1),
+	.mmap_sem	= __RWSEM_INITIALIZER(init_mm.mmap_sem),
+	.page_table_lock =  __SPIN_LOCK_UNLOCKED(init_mm.page_table_lock),
+	.mmlist		= LIST_HEAD_INIT(init_mm.mmlist),
+	INIT_MM_CONTEXT(init_mm)
+};

mm/internal.h

@@ -0,0 +1,413 @@
+/* internal.h: mm/ internal definitions
+ *
+ * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#ifndef __MM_INTERNAL_H
+#define __MM_INTERNAL_H
+
+#include <linux/fs.h>
+#include <linux/mm.h>
+
+void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
+		unsigned long floor, unsigned long ceiling);
+
+static inline void set_page_count(struct page *page, int v)
+{
+	atomic_set(&page->_count, v);
+}
+
+extern int __do_page_cache_readahead(struct address_space *mapping,
+		struct file *filp, pgoff_t offset, unsigned long nr_to_read,
+		unsigned long lookahead_size);
+
+/*
+ * Submit IO for the read-ahead request in file_ra_state.
+ */
+static inline unsigned long ra_submit(struct file_ra_state *ra,
+		struct address_space *mapping, struct file *filp)
+{
+	return __do_page_cache_readahead(mapping, filp,
+					ra->start, ra->size, ra->async_size);
+}
+
+/*
+ * Turn a non-refcounted page (->_count == 0) into refcounted with
+ * a count of one.
+ */
+static inline void set_page_refcounted(struct page *page)
+{
+	VM_BUG_ON_PAGE(PageTail(page), page);
+	VM_BUG_ON_PAGE(atomic_read(&page->_count), page);
+	set_page_count(page, 1);
+}
+
+static inline void __get_page_tail_foll(struct page *page,
+					bool get_page_head)
+{
+	/*
+	 * If we're getting a tail page, the elevated page->_count is
+	 * required only in the head page and we will elevate the head
+	 * page->_count and tail page->_mapcount.
+	 *
+	 * We elevate page_tail->_mapcount for tail pages to force
+	 * page_tail->_count to be zero at all times to avoid getting
+	 * false positives from get_page_unless_zero() with
+	 * speculative page access (like in
+	 * page_cache_get_speculative()) on tail pages.
+	 */
+	VM_BUG_ON_PAGE(atomic_read(&page->first_page->_count) <= 0, page);
+	if (get_page_head)
+		atomic_inc(&page->first_page->_count);
+	get_huge_page_tail(page);
+}
+
+/*
+ * This is meant to be called as the FOLL_GET operation of
+ * follow_page() and it must be called while holding the proper PT
+ * lock while the pte (or pmd_trans_huge) is still mapping the page.
+ */
+static inline void get_page_foll(struct page *page)
+{
+	if (unlikely(PageTail(page)))
+		/*
+		 * This is safe only because
+		 * __split_huge_page_refcount() can't run under
+		 * get_page_foll() because we hold the proper PT lock.
+		 */
+		__get_page_tail_foll(page, true);
+	else {
+		/*
+		 * Getting a normal page or the head of a compound page
+		 * requires to already have an elevated page->_count.
+		 */
+		VM_BUG_ON_PAGE(atomic_read(&page->_count) <= 0, page);
+		atomic_inc(&page->_count);
+	}
+}
+
+extern unsigned long highest_memmap_pfn;
+
+/*
+ * in mm/vmscan.c:
+ */
+extern int isolate_lru_page(struct page *page);
+extern void putback_lru_page(struct page *page);
+extern bool zone_reclaimable(struct zone *zone);
+
+/*
+ * in mm/rmap.c:
+ */
+extern pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address);
+
+/*
+ * in mm/page_alloc.c
+ */
+
+/*
+ * Locate the struct page for both the matching buddy in our
+ * pair (buddy1) and the combined O(n+1) page they form (page).
+ *
+ * 1) Any buddy B1 will have an order O twin B2 which satisfies
+ * the following equation:
+ *     B2 = B1 ^ (1 << O)
+ * For example, if the starting buddy (buddy2) is #8 its order
+ * 1 buddy is #10:
+ *     B2 = 8 ^ (1 << 1) = 8 ^ 2 = 10
+ *
+ * 2) Any buddy B will have an order O+1 parent P which
+ * satisfies the following equation:
+ *     P = B & ~(1 << O)
+ *
+ * Assumption: *_mem_map is contiguous at least up to MAX_ORDER
+ */
+static inline unsigned long
+__find_buddy_index(unsigned long page_idx, unsigned int order)
+{
+	return page_idx ^ (1 << order);
+}
+
+extern int __isolate_free_page(struct page *page, unsigned int order);
+extern void __free_pages_bootmem(struct page *page, unsigned int order);
+extern void prep_compound_page(struct page *page, unsigned long order);
+#ifdef CONFIG_MEMORY_FAILURE
+extern bool is_free_buddy_page(struct page *page);
+#endif
+extern int user_min_free_kbytes;
+
+#if defined CONFIG_COMPACTION || defined CONFIG_CMA
+
+/*
+ * in mm/compaction.c
+ */
+/*
+ * compact_control is used to track pages being migrated and the free pages
+ * they are being migrated to during memory compaction. The free_pfn starts
+ * at the end of a zone and migrate_pfn begins at the start. Movable pages
+ * are moved to the end of a zone during a compaction run and the run
+ * completes when free_pfn <= migrate_pfn
+ */
+struct compact_control {
+	struct list_head freepages;	/* List of free pages to migrate to */
+	struct list_head migratepages;	/* List of pages being migrated */
+	unsigned long nr_freepages;	/* Number of isolated free pages */
+	unsigned long nr_migratepages;	/* Number of pages to migrate */
+	unsigned long free_pfn;		/* isolate_freepages search base */
+	unsigned long migrate_pfn;	/* isolate_migratepages search base */
+	enum migrate_mode mode;		/* Async or sync migration mode */
+	bool ignore_skip_hint;		/* Scan blocks even if marked skip */
+	bool finished_update_free;	/* True when the zone cached pfns are
+					 * no longer being updated
+					 */
+	bool finished_update_migrate;
+
+	int order;			/* order a direct compactor needs */
+	const gfp_t gfp_mask;		/* gfp mask of a direct compactor */
+	struct zone *zone;
+	int contended;			/* Signal need_sched() or lock
+					 * contention detected during
+					 * compaction
+					 */
+};
+
+unsigned long
+isolate_freepages_range(struct compact_control *cc,
+			unsigned long start_pfn, unsigned long end_pfn);
+unsigned long
+isolate_migratepages_range(struct compact_control *cc,
+			   unsigned long low_pfn, unsigned long end_pfn);
+
+#endif
+
+/*
+ * This function returns the order of a free page in the buddy system. In
+ * general, page_zone(page)->lock must be held by the caller to prevent the
+ * page from being allocated in parallel and returning garbage as the order.
+ * If a caller does not hold page_zone(page)->lock, it must guarantee that the
+ * page cannot be allocated or merged in parallel. Alternatively, it must
+ * handle invalid values gracefully, and use page_order_unsafe() below.
+ */
+static inline unsigned long page_order(struct page *page)
+{
+	/* PageBuddy() must be checked by the caller */
+	return page_private(page);
+}
+
+/*
+ * Like page_order(), but for callers who cannot afford to hold the zone lock.
+ * PageBuddy() should be checked first by the caller to minimize race window,
+ * and invalid values must be handled gracefully.
+ *
+ * ACCESS_ONCE is used so that if the caller assigns the result into a local
+ * variable and e.g. tests it for valid range before using, the compiler cannot
+ * decide to remove the variable and inline the page_private(page) multiple
+ * times, potentially observing different values in the tests and the actual
+ * use of the result.
+ */
+#define page_order_unsafe(page)		ACCESS_ONCE(page_private(page))
+
+static inline bool is_cow_mapping(vm_flags_t flags)
+{
+	return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
+}
+
+/* mm/util.c */
+void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
+		struct vm_area_struct *prev, struct rb_node *rb_parent);
+
+#ifdef CONFIG_MMU
+extern long __mlock_vma_pages_range(struct vm_area_struct *vma,
+		unsigned long start, unsigned long end, int *nonblocking);
+extern void munlock_vma_pages_range(struct vm_area_struct *vma,
+			unsigned long start, unsigned long end);
+static inline void munlock_vma_pages_all(struct vm_area_struct *vma)
+{
+	munlock_vma_pages_range(vma, vma->vm_start, vma->vm_end);
+}
+
+/*
+ * must be called with vma's mmap_sem held for read or write, and page locked.
+ */
+extern void mlock_vma_page(struct page *page);
+extern unsigned int munlock_vma_page(struct page *page);
+
+/*
+ * Clear the page's PageMlocked().  This can be useful in a situation where
+ * we want to unconditionally remove a page from the pagecache -- e.g.,
+ * on truncation or freeing.
+ *
+ * It is legal to call this function for any page, mlocked or not.
+ * If called for a page that is still mapped by mlocked vmas, all we do
+ * is revert to lazy LRU behaviour -- semantics are not broken.
+ */
+extern void clear_page_mlock(struct page *page);
+
+/*
+ * mlock_migrate_page - called only from migrate_page_copy() to
+ * migrate the Mlocked page flag; update statistics.
+ */
+static inline void mlock_migrate_page(struct page *newpage, struct page *page)
+{
+	if (TestClearPageMlocked(page)) {
+		unsigned long flags;
+		int nr_pages = hpage_nr_pages(page);
+
+		local_irq_save(flags);
+		__mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages);
+		SetPageMlocked(newpage);
+		__mod_zone_page_state(page_zone(newpage), NR_MLOCK, nr_pages);
+		local_irq_restore(flags);
+	}
+}
+
+extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma);
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+extern unsigned long vma_address(struct page *page,
+				 struct vm_area_struct *vma);
+#endif
+#else /* !CONFIG_MMU */
+static inline void clear_page_mlock(struct page *page) { }
+static inline void mlock_vma_page(struct page *page) { }
+static inline void mlock_migrate_page(struct page *new, struct page *old) { }
+
+#endif /* !CONFIG_MMU */
+
+/*
+ * Return the mem_map entry representing the 'offset' subpage within
+ * the maximally aligned gigantic page 'base'.  Handle any discontiguity
+ * in the mem_map at MAX_ORDER_NR_PAGES boundaries.
+ */
+static inline struct page *mem_map_offset(struct page *base, int offset)
+{
+	if (unlikely(offset >= MAX_ORDER_NR_PAGES))
+		return nth_page(base, offset);
+	return base + offset;
+}
+
+/*
+ * Iterator over all subpages within the maximally aligned gigantic
+ * page 'base'.  Handle any discontiguity in the mem_map.
+ */
+static inline struct page *mem_map_next(struct page *iter,
+						struct page *base, int offset)
+{
+	if (unlikely((offset & (MAX_ORDER_NR_PAGES - 1)) == 0)) {
+		unsigned long pfn = page_to_pfn(base) + offset;
+		if (!pfn_valid(pfn))
+			return NULL;
+		return pfn_to_page(pfn);
+	}
+	return iter + 1;
+}
+
+/*
+ * FLATMEM and DISCONTIGMEM configurations use alloc_bootmem_node,
+ * so all functions starting at paging_init should be marked __init
+ * in those cases. SPARSEMEM, however, allows for memory hotplug,
+ * and alloc_bootmem_node is not used.
+ */
+#ifdef CONFIG_SPARSEMEM
+#define __paginginit __meminit
+#else
+#define __paginginit __init
+#endif
+
+/* Memory initialisation debug and verification */
+enum mminit_level {
+	MMINIT_WARNING,
+	MMINIT_VERIFY,
+	MMINIT_TRACE
+};
+
+#ifdef CONFIG_DEBUG_MEMORY_INIT
+
+extern int mminit_loglevel;
+
+#define mminit_dprintk(level, prefix, fmt, arg...) \
+do { \
+	if (level < mminit_loglevel) { \
+		printk(level <= MMINIT_WARNING ? KERN_WARNING : KERN_DEBUG); \
+		printk(KERN_CONT "mminit::" prefix " " fmt, ##arg); \
+	} \
+} while (0)
+
+extern void mminit_verify_pageflags_layout(void);
+extern void mminit_verify_page_links(struct page *page,
+		enum zone_type zone, unsigned long nid, unsigned long pfn);
+extern void mminit_verify_zonelist(void);
+
+#else
+
+static inline void mminit_dprintk(enum mminit_level level,
+				const char *prefix, const char *fmt, ...)
+{
+}
+
+static inline void mminit_verify_pageflags_layout(void)
+{
+}
+
+static inline void mminit_verify_page_links(struct page *page,
+		enum zone_type zone, unsigned long nid, unsigned long pfn)
+{
+}
+
+static inline void mminit_verify_zonelist(void)
+{
+}
+#endif /* CONFIG_DEBUG_MEMORY_INIT */
+
+/* mminit_validate_memmodel_limits is independent of CONFIG_DEBUG_MEMORY_INIT */
+#if defined(CONFIG_SPARSEMEM)
+extern void mminit_validate_memmodel_limits(unsigned long *start_pfn,
+				unsigned long *end_pfn);
+#else
+static inline void mminit_validate_memmodel_limits(unsigned long *start_pfn,
+				unsigned long *end_pfn)
+{
+}
+#endif /* CONFIG_SPARSEMEM */
+
+#define ZONE_RECLAIM_NOSCAN	-2
+#define ZONE_RECLAIM_FULL	-1
+#define ZONE_RECLAIM_SOME	0
+#define ZONE_RECLAIM_SUCCESS	1
+
+extern int hwpoison_filter(struct page *p);
+
+extern u32 hwpoison_filter_dev_major;
+extern u32 hwpoison_filter_dev_minor;
+extern u64 hwpoison_filter_flags_mask;
+extern u64 hwpoison_filter_flags_value;
+extern u64 hwpoison_filter_memcg;
+extern u32 hwpoison_filter_enable;
+
+extern unsigned long vm_mmap_pgoff(struct file *, unsigned long,
+        unsigned long, unsigned long,
+        unsigned long, unsigned long);
+
+extern void set_pageblock_order(void);
+unsigned long reclaim_clean_pages_from_list(struct zone *zone,
+					    struct list_head *page_list);
+/* The ALLOC_WMARK bits are used as an index to zone->watermark */
+#define ALLOC_WMARK_MIN		WMARK_MIN
+#define ALLOC_WMARK_LOW		WMARK_LOW
+#define ALLOC_WMARK_HIGH	WMARK_HIGH
+#define ALLOC_NO_WATERMARKS	0x04 /* don't check watermarks at all */
+
+/* Mask to get the watermark bits */
+#define ALLOC_WMARK_MASK	(ALLOC_NO_WATERMARKS-1)
+
+#define ALLOC_HARDER		0x10 /* try to alloc harder */
+#define ALLOC_HIGH		0x20 /* __GFP_HIGH set */
+#define ALLOC_CPUSET		0x40 /* check for correct cpuset */
+#define ALLOC_CMA		0x80 /* allow allocations from CMA areas */
+#define ALLOC_FAIR		0x100 /* fair zone allocation */
+
+#endif	/* __MM_INTERNAL_H */

mm/interval_tree.c

@@ -0,0 +1,112 @@
+/*
+ * mm/interval_tree.c - interval tree for mapping->i_mmap
+ *
+ * Copyright (C) 2012, Michel Lespinasse <walken@google.com>
+ *
+ * This file is released under the GPL v2.
+ */
+
+#include <linux/mm.h>
+#include <linux/fs.h>
+#include <linux/rmap.h>
+#include <linux/interval_tree_generic.h>
+
+static inline unsigned long vma_start_pgoff(struct vm_area_struct *v)
+{
+	return v->vm_pgoff;
+}
+
+static inline unsigned long vma_last_pgoff(struct vm_area_struct *v)
+{
+	return v->vm_pgoff + ((v->vm_end - v->vm_start) >> PAGE_SHIFT) - 1;
+}
+
+INTERVAL_TREE_DEFINE(struct vm_area_struct, shared.linear.rb,
+		     unsigned long, shared.linear.rb_subtree_last,
+		     vma_start_pgoff, vma_last_pgoff,, vma_interval_tree)
+
+/* Insert node immediately after prev in the interval tree */
+void vma_interval_tree_insert_after(struct vm_area_struct *node,
+				    struct vm_area_struct *prev,
+				    struct rb_root *root)
+{
+	struct rb_node **link;
+	struct vm_area_struct *parent;
+	unsigned long last = vma_last_pgoff(node);
+
+	VM_BUG_ON_VMA(vma_start_pgoff(node) != vma_start_pgoff(prev), node);
+
+	if (!prev->shared.linear.rb.rb_right) {
+		parent = prev;
+		link = &prev->shared.linear.rb.rb_right;
+	} else {
+		parent = rb_entry(prev->shared.linear.rb.rb_right,
+				  struct vm_area_struct, shared.linear.rb);
+		if (parent->shared.linear.rb_subtree_last < last)
+			parent->shared.linear.rb_subtree_last = last;
+		while (parent->shared.linear.rb.rb_left) {
+			parent = rb_entry(parent->shared.linear.rb.rb_left,
+				struct vm_area_struct, shared.linear.rb);
+			if (parent->shared.linear.rb_subtree_last < last)
+				parent->shared.linear.rb_subtree_last = last;
+		}
+		link = &parent->shared.linear.rb.rb_left;
+	}
+
+	node->shared.linear.rb_subtree_last = last;
+	rb_link_node(&node->shared.linear.rb, &parent->shared.linear.rb, link);
+	rb_insert_augmented(&node->shared.linear.rb, root,
+			    &vma_interval_tree_augment);
+}
+
+static inline unsigned long avc_start_pgoff(struct anon_vma_chain *avc)
+{
+	return vma_start_pgoff(avc->vma);
+}
+
+static inline unsigned long avc_last_pgoff(struct anon_vma_chain *avc)
+{
+	return vma_last_pgoff(avc->vma);
+}
+
+INTERVAL_TREE_DEFINE(struct anon_vma_chain, rb, unsigned long, rb_subtree_last,
+		     avc_start_pgoff, avc_last_pgoff,
+		     static inline, __anon_vma_interval_tree)
+
+void anon_vma_interval_tree_insert(struct anon_vma_chain *node,
+				   struct rb_root *root)
+{
+#ifdef CONFIG_DEBUG_VM_RB
+	node->cached_vma_start = avc_start_pgoff(node);
+	node->cached_vma_last = avc_last_pgoff(node);
+#endif
+	__anon_vma_interval_tree_insert(node, root);
+}
+
+void anon_vma_interval_tree_remove(struct anon_vma_chain *node,
+				   struct rb_root *root)
+{
+	__anon_vma_interval_tree_remove(node, root);
+}
+
+struct anon_vma_chain *
+anon_vma_interval_tree_iter_first(struct rb_root *root,
+				  unsigned long first, unsigned long last)
+{
+	return __anon_vma_interval_tree_iter_first(root, first, last);
+}
+
+struct anon_vma_chain *
+anon_vma_interval_tree_iter_next(struct anon_vma_chain *node,
+				 unsigned long first, unsigned long last)
+{
+	return __anon_vma_interval_tree_iter_next(node, first, last);
+}
+
+#ifdef CONFIG_DEBUG_VM_RB
+void anon_vma_interval_tree_verify(struct anon_vma_chain *node)
+{
+	WARN_ON_ONCE(node->cached_vma_start != avc_start_pgoff(node));
+	WARN_ON_ONCE(node->cached_vma_last != avc_last_pgoff(node));
+}
+#endif

mm/iov_iter.c

@@ -0,0 +1,958 @@
+#include <linux/export.h>
+#include <linux/uio.h>
+#include <linux/pagemap.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+
+static size_t copy_to_iter_iovec(void *from, size_t bytes, struct iov_iter *i)
+{
+	size_t skip, copy, left, wanted;
+	const struct iovec *iov;
+	char __user *buf;
+
+	if (unlikely(bytes > i->count))
+		bytes = i->count;
+
+	if (unlikely(!bytes))
+		return 0;
+
+	wanted = bytes;
+	iov = i->iov;
+	skip = i->iov_offset;
+	buf = iov->iov_base + skip;
+	copy = min(bytes, iov->iov_len - skip);
+
+	left = __copy_to_user(buf, from, copy);
+	copy -= left;
+	skip += copy;
+	from += copy;
+	bytes -= copy;
+	while (unlikely(!left && bytes)) {
+		iov++;
+		buf = iov->iov_base;
+		copy = min(bytes, iov->iov_len);
+		left = __copy_to_user(buf, from, copy);
+		copy -= left;
+		skip = copy;
+		from += copy;
+		bytes -= copy;
+	}
+
+	if (skip == iov->iov_len) {
+		iov++;
+		skip = 0;
+	}
+	i->count -= wanted - bytes;
+	i->nr_segs -= iov - i->iov;
+	i->iov = iov;
+	i->iov_offset = skip;
+	return wanted - bytes;
+}
+
+static size_t copy_from_iter_iovec(void *to, size_t bytes, struct iov_iter *i)
+{
+	size_t skip, copy, left, wanted;
+	const struct iovec *iov;
+	char __user *buf;
+
+	if (unlikely(bytes > i->count))
+		bytes = i->count;
+
+	if (unlikely(!bytes))
+		return 0;
+
+	wanted = bytes;
+	iov = i->iov;
+	skip = i->iov_offset;
+	buf = iov->iov_base + skip;
+	copy = min(bytes, iov->iov_len - skip);
+
+	left = __copy_from_user(to, buf, copy);
+	copy -= left;
+	skip += copy;
+	to += copy;
+	bytes -= copy;
+	while (unlikely(!left && bytes)) {
+		iov++;
+		buf = iov->iov_base;
+		copy = min(bytes, iov->iov_len);
+		left = __copy_from_user(to, buf, copy);
+		copy -= left;
+		skip = copy;
+		to += copy;
+		bytes -= copy;
+	}
+
+	if (skip == iov->iov_len) {
+		iov++;
+		skip = 0;
+	}
+	i->count -= wanted - bytes;
+	i->nr_segs -= iov - i->iov;
+	i->iov = iov;
+	i->iov_offset = skip;
+	return wanted - bytes;
+}
+
+static size_t copy_page_to_iter_iovec(struct page *page, size_t offset, size_t bytes,
+			 struct iov_iter *i)
+{
+	size_t skip, copy, left, wanted;
+	const struct iovec *iov;
+	char __user *buf;
+	void *kaddr, *from;
+
+	if (unlikely(bytes > i->count))
+		bytes = i->count;
+
+	if (unlikely(!bytes))
+		return 0;
+
+	wanted = bytes;
+	iov = i->iov;
+	skip = i->iov_offset;
+	buf = iov->iov_base + skip;
+	copy = min(bytes, iov->iov_len - skip);
+
+	if (!fault_in_pages_writeable(buf, copy)) {
+		kaddr = kmap_atomic(page);
+		from = kaddr + offset;
+
+		/* first chunk, usually the only one */
+		left = __copy_to_user_inatomic(buf, from, copy);
+		copy -= left;
+		skip += copy;
+		from += copy;
+		bytes -= copy;
+
+		while (unlikely(!left && bytes)) {
+			iov++;
+			buf = iov->iov_base;
+			copy = min(bytes, iov->iov_len);
+			left = __copy_to_user_inatomic(buf, from, copy);
+			copy -= left;
+			skip = copy;
+			from += copy;
+			bytes -= copy;
+		}
+		if (likely(!bytes)) {
+			kunmap_atomic(kaddr);
+			goto done;
+		}
+		offset = from - kaddr;
+		buf += copy;
+		kunmap_atomic(kaddr);
+		copy = min(bytes, iov->iov_len - skip);
+	}
+	/* Too bad - revert to non-atomic kmap */
+	kaddr = kmap(page);
+	from = kaddr + offset;
+	left = __copy_to_user(buf, from, copy);
+	copy -= left;
+	skip += copy;
+	from += copy;
+	bytes -= copy;
+	while (unlikely(!left && bytes)) {
+		iov++;
+		buf = iov->iov_base;
+		copy = min(bytes, iov->iov_len);
+		left = __copy_to_user(buf, from, copy);
+		copy -= left;
+		skip = copy;
+		from += copy;
+		bytes -= copy;
+	}
+	kunmap(page);
+done:
+	if (skip == iov->iov_len) {
+		iov++;
+		skip = 0;
+	}
+	i->count -= wanted - bytes;
+	i->nr_segs -= iov - i->iov;
+	i->iov = iov;
+	i->iov_offset = skip;
+	return wanted - bytes;
+}
+
+static size_t copy_page_from_iter_iovec(struct page *page, size_t offset, size_t bytes,
+			 struct iov_iter *i)
+{
+	size_t skip, copy, left, wanted;
+	const struct iovec *iov;
+	char __user *buf;
+	void *kaddr, *to;
+
+	if (unlikely(bytes > i->count))
+		bytes = i->count;
+
+	if (unlikely(!bytes))
+		return 0;
+
+	wanted = bytes;
+	iov = i->iov;
+	skip = i->iov_offset;
+	buf = iov->iov_base + skip;
+	copy = min(bytes, iov->iov_len - skip);
+
+	if (!fault_in_pages_readable(buf, copy)) {
+		kaddr = kmap_atomic(page);
+		to = kaddr + offset;
+
+		/* first chunk, usually the only one */
+		left = __copy_from_user_inatomic(to, buf, copy);
+		copy -= left;
+		skip += copy;
+		to += copy;
+		bytes -= copy;
+
+		while (unlikely(!left && bytes)) {
+			iov++;
+			buf = iov->iov_base;
+			copy = min(bytes, iov->iov_len);
+			left = __copy_from_user_inatomic(to, buf, copy);
+			copy -= left;
+			skip = copy;
+			to += copy;
+			bytes -= copy;
+		}
+		if (likely(!bytes)) {
+			kunmap_atomic(kaddr);
+			goto done;
+		}
+		offset = to - kaddr;
+		buf += copy;
+		kunmap_atomic(kaddr);
+		copy = min(bytes, iov->iov_len - skip);
+	}
+	/* Too bad - revert to non-atomic kmap */
+	kaddr = kmap(page);
+	to = kaddr + offset;
+	left = __copy_from_user(to, buf, copy);
+	copy -= left;
+	skip += copy;
+	to += copy;
+	bytes -= copy;
+	while (unlikely(!left && bytes)) {
+		iov++;
+		buf = iov->iov_base;
+		copy = min(bytes, iov->iov_len);
+		left = __copy_from_user(to, buf, copy);
+		copy -= left;
+		skip = copy;
+		to += copy;
+		bytes -= copy;
+	}
+	kunmap(page);
+done:
+	if (skip == iov->iov_len) {
+		iov++;
+		skip = 0;
+	}
+	i->count -= wanted - bytes;
+	i->nr_segs -= iov - i->iov;
+	i->iov = iov;
+	i->iov_offset = skip;
+	return wanted - bytes;
+}
+
+static size_t zero_iovec(size_t bytes, struct iov_iter *i)
+{
+	size_t skip, copy, left, wanted;
+	const struct iovec *iov;
+	char __user *buf;
+
+	if (unlikely(bytes > i->count))
+		bytes = i->count;
+
+	if (unlikely(!bytes))
+		return 0;
+
+	wanted = bytes;
+	iov = i->iov;
+	skip = i->iov_offset;
+	buf = iov->iov_base + skip;
+	copy = min(bytes, iov->iov_len - skip);
+
+	left = __clear_user(buf, copy);
+	copy -= left;
+	skip += copy;
+	bytes -= copy;
+
+	while (unlikely(!left && bytes)) {
+		iov++;
+		buf = iov->iov_base;
+		copy = min(bytes, iov->iov_len);
+		left = __clear_user(buf, copy);
+		copy -= left;
+		skip = copy;
+		bytes -= copy;
+	}
+
+	if (skip == iov->iov_len) {
+		iov++;
+		skip = 0;
+	}
+	i->count -= wanted - bytes;
+	i->nr_segs -= iov - i->iov;
+	i->iov = iov;
+	i->iov_offset = skip;
+	return wanted - bytes;
+}
+
+static size_t __iovec_copy_from_user_inatomic(char *vaddr,
+			const struct iovec *iov, size_t base, size_t bytes)
+{
+	size_t copied = 0, left = 0;
+
+	while (bytes) {
+		char __user *buf = iov->iov_base + base;
+		int copy = min(bytes, iov->iov_len - base);
+
+		base = 0;
+		left = __copy_from_user_inatomic(vaddr, buf, copy);
+		copied += copy;
+		bytes -= copy;
+		vaddr += copy;
+		iov++;
+
+		if (unlikely(left))
+			break;
+	}
+	return copied - left;
+}
+
+/*
+ * Copy as much as we can into the page and return the number of bytes which
+ * were successfully copied.  If a fault is encountered then return the number of
+ * bytes which were copied.
+ */
+static size_t copy_from_user_atomic_iovec(struct page *page,
+		struct iov_iter *i, unsigned long offset, size_t bytes)
+{
+	char *kaddr;
+	size_t copied;
+
+	kaddr = kmap_atomic(page);
+	if (likely(i->nr_segs == 1)) {
+		int left;
+		char __user *buf = i->iov->iov_base + i->iov_offset;
+		left = __copy_from_user_inatomic(kaddr + offset, buf, bytes);
+		copied = bytes - left;
+	} else {
+		copied = __iovec_copy_from_user_inatomic(kaddr + offset,
+						i->iov, i->iov_offset, bytes);
+	}
+	kunmap_atomic(kaddr);
+
+	return copied;
+}
+
+static void advance_iovec(struct iov_iter *i, size_t bytes)
+{
+	BUG_ON(i->count < bytes);
+
+	if (likely(i->nr_segs == 1)) {
+		i->iov_offset += bytes;
+		i->count -= bytes;
+	} else {
+		const struct iovec *iov = i->iov;
+		size_t base = i->iov_offset;
+		unsigned long nr_segs = i->nr_segs;
+
+		/*
+		 * The !iov->iov_len check ensures we skip over unlikely
+		 * zero-length segments (without overruning the iovec).
+		 */
+		while (bytes || unlikely(i->count && !iov->iov_len)) {
+			int copy;
+
+			copy = min(bytes, iov->iov_len - base);
+			BUG_ON(!i->count || i->count < copy);
+			i->count -= copy;
+			bytes -= copy;
+			base += copy;
+			if (iov->iov_len == base) {
+				iov++;
+				nr_segs--;
+				base = 0;
+			}
+		}
+		i->iov = iov;
+		i->iov_offset = base;
+		i->nr_segs = nr_segs;
+	}
+}
+
+/*
+ * Fault in the first iovec of the given iov_iter, to a maximum length
+ * of bytes. Returns 0 on success, or non-zero if the memory could not be
+ * accessed (ie. because it is an invalid address).
+ *
+ * writev-intensive code may want this to prefault several iovecs -- that
+ * would be possible (callers must not rely on the fact that _only_ the
+ * first iovec will be faulted with the current implementation).
+ */
+int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes)
+{
+	if (!(i->type & ITER_BVEC)) {
+		char __user *buf = i->iov->iov_base + i->iov_offset;
+		bytes = min(bytes, i->iov->iov_len - i->iov_offset);
+		return fault_in_pages_readable(buf, bytes);
+	}
+	return 0;
+}
+EXPORT_SYMBOL(iov_iter_fault_in_readable);
+
+static unsigned long alignment_iovec(const struct iov_iter *i)
+{
+	const struct iovec *iov = i->iov;
+	unsigned long res;
+	size_t size = i->count;
+	size_t n;
+
+	if (!size)
+		return 0;
+
+	res = (unsigned long)iov->iov_base + i->iov_offset;
+	n = iov->iov_len - i->iov_offset;
+	if (n >= size)
+		return res | size;
+	size -= n;
+	res |= n;
+	while (size > (++iov)->iov_len) {
+		res |= (unsigned long)iov->iov_base | iov->iov_len;
+		size -= iov->iov_len;
+	}
+	res |= (unsigned long)iov->iov_base | size;
+	return res;
+}
+
+void iov_iter_init(struct iov_iter *i, int direction,
+			const struct iovec *iov, unsigned long nr_segs,
+			size_t count)
+{
+	/* It will get better.  Eventually... */
+	if (segment_eq(get_fs(), KERNEL_DS))
+		direction |= ITER_KVEC;
+	i->type = direction;
+	i->iov = iov;
+	i->nr_segs = nr_segs;
+	i->iov_offset = 0;
+	i->count = count;
+}
+EXPORT_SYMBOL(iov_iter_init);
+
+static ssize_t get_pages_iovec(struct iov_iter *i,
+		   struct page **pages, size_t maxsize, unsigned maxpages,
+		   size_t *start)
+{
+	size_t offset = i->iov_offset;
+	const struct iovec *iov = i->iov;
+	size_t len;
+	unsigned long addr;
+	int n;
+	int res;
+
+	len = iov->iov_len - offset;
+	if (len > i->count)
+		len = i->count;
+	if (len > maxsize)
+		len = maxsize;
+	addr = (unsigned long)iov->iov_base + offset;
+	len += *start = addr & (PAGE_SIZE - 1);
+	if (len > maxpages * PAGE_SIZE)
+		len = maxpages * PAGE_SIZE;
+	addr &= ~(PAGE_SIZE - 1);
+	n = (len + PAGE_SIZE - 1) / PAGE_SIZE;
+	res = get_user_pages_fast(addr, n, (i->type & WRITE) != WRITE, pages);
+	if (unlikely(res < 0))
+		return res;
+	return (res == n ? len : res * PAGE_SIZE) - *start;
+}
+
+static ssize_t get_pages_alloc_iovec(struct iov_iter *i,
+		   struct page ***pages, size_t maxsize,
+		   size_t *start)
+{
+	size_t offset = i->iov_offset;
+	const struct iovec *iov = i->iov;
+	size_t len;
+	unsigned long addr;
+	void *p;
+	int n;
+	int res;
+
+	len = iov->iov_len - offset;
+	if (len > i->count)
+		len = i->count;
+	if (len > maxsize)
+		len = maxsize;
+	addr = (unsigned long)iov->iov_base + offset;
+	len += *start = addr & (PAGE_SIZE - 1);
+	addr &= ~(PAGE_SIZE - 1);
+	n = (len + PAGE_SIZE - 1) / PAGE_SIZE;
+	
+	p = kmalloc(n * sizeof(struct page *), GFP_KERNEL);
+	if (!p)
+		p = vmalloc(n * sizeof(struct page *));
+	if (!p)
+		return -ENOMEM;
+
+	res = get_user_pages_fast(addr, n, (i->type & WRITE) != WRITE, p);
+	if (unlikely(res < 0)) {
+		kvfree(p);
+		return res;
+	}
+	*pages = p;
+	return (res == n ? len : res * PAGE_SIZE) - *start;
+}
+
+static int iov_iter_npages_iovec(const struct iov_iter *i, int maxpages)
+{
+	size_t offset = i->iov_offset;
+	size_t size = i->count;
+	const struct iovec *iov = i->iov;
+	int npages = 0;
+	int n;
+
+	for (n = 0; size && n < i->nr_segs; n++, iov++) {
+		unsigned long addr = (unsigned long)iov->iov_base + offset;
+		size_t len = iov->iov_len - offset;
+		offset = 0;
+		if (unlikely(!len))	/* empty segment */
+			continue;
+		if (len > size)
+			len = size;
+		npages += (addr + len + PAGE_SIZE - 1) / PAGE_SIZE
+			  - addr / PAGE_SIZE;
+		if (npages >= maxpages)	/* don't bother going further */
+			return maxpages;
+		size -= len;
+		offset = 0;
+	}
+	return min(npages, maxpages);
+}
+
+static void memcpy_from_page(char *to, struct page *page, size_t offset, size_t len)
+{
+	char *from = kmap_atomic(page);
+	memcpy(to, from + offset, len);
+	kunmap_atomic(from);
+}
+
+static void memcpy_to_page(struct page *page, size_t offset, char *from, size_t len)
+{
+	char *to = kmap_atomic(page);
+	memcpy(to + offset, from, len);
+	kunmap_atomic(to);
+}
+
+static void memzero_page(struct page *page, size_t offset, size_t len)
+{
+	char *addr = kmap_atomic(page);
+	memset(addr + offset, 0, len);
+	kunmap_atomic(addr);
+}
+
+static size_t copy_to_iter_bvec(void *from, size_t bytes, struct iov_iter *i)
+{
+	size_t skip, copy, wanted;
+	const struct bio_vec *bvec;
+
+	if (unlikely(bytes > i->count))
+		bytes = i->count;
+
+	if (unlikely(!bytes))
+		return 0;
+
+	wanted = bytes;
+	bvec = i->bvec;
+	skip = i->iov_offset;
+	copy = min_t(size_t, bytes, bvec->bv_len - skip);
+
+	memcpy_to_page(bvec->bv_page, skip + bvec->bv_offset, from, copy);
+	skip += copy;
+	from += copy;
+	bytes -= copy;
+	while (bytes) {
+		bvec++;
+		copy = min(bytes, (size_t)bvec->bv_len);
+		memcpy_to_page(bvec->bv_page, bvec->bv_offset, from, copy);
+		skip = copy;
+		from += copy;
+		bytes -= copy;
+	}
+	if (skip == bvec->bv_len) {
+		bvec++;
+		skip = 0;
+	}
+	i->count -= wanted - bytes;
+	i->nr_segs -= bvec - i->bvec;
+	i->bvec = bvec;
+	i->iov_offset = skip;
+	return wanted - bytes;
+}
+
+static size_t copy_from_iter_bvec(void *to, size_t bytes, struct iov_iter *i)
+{
+	size_t skip, copy, wanted;
+	const struct bio_vec *bvec;
+
+	if (unlikely(bytes > i->count))
+		bytes = i->count;
+
+	if (unlikely(!bytes))
+		return 0;
+
+	wanted = bytes;
+	bvec = i->bvec;
+	skip = i->iov_offset;
+
+	copy = min(bytes, bvec->bv_len - skip);
+
+	memcpy_from_page(to, bvec->bv_page, bvec->bv_offset + skip, copy);
+
+	to += copy;
+	skip += copy;
+	bytes -= copy;
+
+	while (bytes) {
+		bvec++;
+		copy = min(bytes, (size_t)bvec->bv_len);
+		memcpy_from_page(to, bvec->bv_page, bvec->bv_offset, copy);
+		skip = copy;
+		to += copy;
+		bytes -= copy;
+	}
+	if (skip == bvec->bv_len) {
+		bvec++;
+		skip = 0;
+	}
+	i->count -= wanted;
+	i->nr_segs -= bvec - i->bvec;
+	i->bvec = bvec;
+	i->iov_offset = skip;
+	return wanted;
+}
+
+static size_t copy_page_to_iter_bvec(struct page *page, size_t offset,
+					size_t bytes, struct iov_iter *i)
+{
+	void *kaddr = kmap_atomic(page);
+	size_t wanted = copy_to_iter_bvec(kaddr + offset, bytes, i);
+	kunmap_atomic(kaddr);
+	return wanted;
+}
+
+static size_t copy_page_from_iter_bvec(struct page *page, size_t offset,
+					size_t bytes, struct iov_iter *i)
+{
+	void *kaddr = kmap_atomic(page);
+	size_t wanted = copy_from_iter_bvec(kaddr + offset, bytes, i);
+	kunmap_atomic(kaddr);
+	return wanted;
+}
+
+static size_t zero_bvec(size_t bytes, struct iov_iter *i)
+{
+	size_t skip, copy, wanted;
+	const struct bio_vec *bvec;
+
+	if (unlikely(bytes > i->count))
+		bytes = i->count;
+
+	if (unlikely(!bytes))
+		return 0;
+
+	wanted = bytes;
+	bvec = i->bvec;
+	skip = i->iov_offset;
+	copy = min_t(size_t, bytes, bvec->bv_len - skip);
+
+	memzero_page(bvec->bv_page, skip + bvec->bv_offset, copy);
+	skip += copy;
+	bytes -= copy;
+	while (bytes) {
+		bvec++;
+		copy = min(bytes, (size_t)bvec->bv_len);
+		memzero_page(bvec->bv_page, bvec->bv_offset, copy);
+		skip = copy;
+		bytes -= copy;
+	}
+	if (skip == bvec->bv_len) {
+		bvec++;
+		skip = 0;
+	}
+	i->count -= wanted - bytes;
+	i->nr_segs -= bvec - i->bvec;
+	i->bvec = bvec;
+	i->iov_offset = skip;
+	return wanted - bytes;
+}
+
+static size_t copy_from_user_bvec(struct page *page,
+		struct iov_iter *i, unsigned long offset, size_t bytes)
+{
+	char *kaddr;
+	size_t left;
+	const struct bio_vec *bvec;
+	size_t base = i->iov_offset;
+
+	kaddr = kmap_atomic(page);
+	for (left = bytes, bvec = i->bvec; left; bvec++, base = 0) {
+		size_t copy = min(left, bvec->bv_len - base);
+		if (!bvec->bv_len)
+			continue;
+		memcpy_from_page(kaddr + offset, bvec->bv_page,
+				 bvec->bv_offset + base, copy);
+		offset += copy;
+		left -= copy;
+	}
+	kunmap_atomic(kaddr);
+	return bytes;
+}
+
+static void advance_bvec(struct iov_iter *i, size_t bytes)
+{
+	BUG_ON(i->count < bytes);
+
+	if (likely(i->nr_segs == 1)) {
+		i->iov_offset += bytes;
+		i->count -= bytes;
+	} else {
+		const struct bio_vec *bvec = i->bvec;
+		size_t base = i->iov_offset;
+		unsigned long nr_segs = i->nr_segs;
+
+		/*
+		 * The !iov->iov_len check ensures we skip over unlikely
+		 * zero-length segments (without overruning the iovec).
+		 */
+		while (bytes || unlikely(i->count && !bvec->bv_len)) {
+			int copy;
+
+			copy = min(bytes, bvec->bv_len - base);
+			BUG_ON(!i->count || i->count < copy);
+			i->count -= copy;
+			bytes -= copy;
+			base += copy;
+			if (bvec->bv_len == base) {
+				bvec++;
+				nr_segs--;
+				base = 0;
+			}
+		}
+		i->bvec = bvec;
+		i->iov_offset = base;
+		i->nr_segs = nr_segs;
+	}
+}
+
+static unsigned long alignment_bvec(const struct iov_iter *i)
+{
+	const struct bio_vec *bvec = i->bvec;
+	unsigned long res;
+	size_t size = i->count;
+	size_t n;
+
+	if (!size)
+		return 0;
+
+	res = bvec->bv_offset + i->iov_offset;
+	n = bvec->bv_len - i->iov_offset;
+	if (n >= size)
+		return res | size;
+	size -= n;
+	res |= n;
+	while (size > (++bvec)->bv_len) {
+		res |= bvec->bv_offset | bvec->bv_len;
+		size -= bvec->bv_len;
+	}
+	res |= bvec->bv_offset | size;
+	return res;
+}
+
+static ssize_t get_pages_bvec(struct iov_iter *i,
+		   struct page **pages, size_t maxsize, unsigned maxpages,
+		   size_t *start)
+{
+	const struct bio_vec *bvec = i->bvec;
+	size_t len = bvec->bv_len - i->iov_offset;
+	if (len > i->count)
+		len = i->count;
+	if (len > maxsize)
+		len = maxsize;
+	/* can't be more than PAGE_SIZE */
+	*start = bvec->bv_offset + i->iov_offset;
+
+	get_page(*pages = bvec->bv_page);
+
+	return len;
+}
+
+static ssize_t get_pages_alloc_bvec(struct iov_iter *i,
+		   struct page ***pages, size_t maxsize,
+		   size_t *start)
+{
+	const struct bio_vec *bvec = i->bvec;
+	size_t len = bvec->bv_len - i->iov_offset;
+	if (len > i->count)
+		len = i->count;
+	if (len > maxsize)
+		len = maxsize;
+	*start = bvec->bv_offset + i->iov_offset;
+
+	*pages = kmalloc(sizeof(struct page *), GFP_KERNEL);
+	if (!*pages)
+		return -ENOMEM;
+
+	get_page(**pages = bvec->bv_page);
+
+	return len;
+}
+
+static int iov_iter_npages_bvec(const struct iov_iter *i, int maxpages)
+{
+	size_t offset = i->iov_offset;
+	size_t size = i->count;
+	const struct bio_vec *bvec = i->bvec;
+	int npages = 0;
+	int n;
+
+	for (n = 0; size && n < i->nr_segs; n++, bvec++) {
+		size_t len = bvec->bv_len - offset;
+		offset = 0;
+		if (unlikely(!len))	/* empty segment */
+			continue;
+		if (len > size)
+			len = size;
+		npages++;
+		if (npages >= maxpages)	/* don't bother going further */
+			return maxpages;
+		size -= len;
+		offset = 0;
+	}
+	return min(npages, maxpages);
+}
+
+size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes,
+			 struct iov_iter *i)
+{
+	if (i->type & ITER_BVEC)
+		return copy_page_to_iter_bvec(page, offset, bytes, i);
+	else
+		return copy_page_to_iter_iovec(page, offset, bytes, i);
+}
+EXPORT_SYMBOL(copy_page_to_iter);
+
+size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes,
+			 struct iov_iter *i)
+{
+	if (i->type & ITER_BVEC)
+		return copy_page_from_iter_bvec(page, offset, bytes, i);
+	else
+		return copy_page_from_iter_iovec(page, offset, bytes, i);
+}
+EXPORT_SYMBOL(copy_page_from_iter);
+
+size_t copy_to_iter(void *addr, size_t bytes, struct iov_iter *i)
+{
+	if (i->type & ITER_BVEC)
+		return copy_to_iter_bvec(addr, bytes, i);
+	else
+		return copy_to_iter_iovec(addr, bytes, i);
+}
+EXPORT_SYMBOL(copy_to_iter);
+
+size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i)
+{
+	if (i->type & ITER_BVEC)
+		return copy_from_iter_bvec(addr, bytes, i);
+	else
+		return copy_from_iter_iovec(addr, bytes, i);
+}
+EXPORT_SYMBOL(copy_from_iter);
+
+size_t iov_iter_zero(size_t bytes, struct iov_iter *i)
+{
+	if (i->type & ITER_BVEC) {
+		return zero_bvec(bytes, i);
+	} else {
+		return zero_iovec(bytes, i);
+	}
+}
+EXPORT_SYMBOL(iov_iter_zero);
+
+size_t iov_iter_copy_from_user_atomic(struct page *page,
+		struct iov_iter *i, unsigned long offset, size_t bytes)
+{
+	if (i->type & ITER_BVEC)
+		return copy_from_user_bvec(page, i, offset, bytes);
+	else
+		return copy_from_user_atomic_iovec(page, i, offset, bytes);
+}
+EXPORT_SYMBOL(iov_iter_copy_from_user_atomic);
+
+void iov_iter_advance(struct iov_iter *i, size_t size)
+{
+	if (i->type & ITER_BVEC)
+		advance_bvec(i, size);
+	else
+		advance_iovec(i, size);
+}
+EXPORT_SYMBOL(iov_iter_advance);
+
+/*
+ * Return the count of just the current iov_iter segment.
+ */
+size_t iov_iter_single_seg_count(const struct iov_iter *i)
+{
+	if (i->nr_segs == 1)
+		return i->count;
+	else if (i->type & ITER_BVEC)
+		return min(i->count, i->bvec->bv_len - i->iov_offset);
+	else
+		return min(i->count, i->iov->iov_len - i->iov_offset);
+}
+EXPORT_SYMBOL(iov_iter_single_seg_count);
+
+unsigned long iov_iter_alignment(const struct iov_iter *i)
+{
+	if (i->type & ITER_BVEC)
+		return alignment_bvec(i);
+	else
+		return alignment_iovec(i);
+}
+EXPORT_SYMBOL(iov_iter_alignment);
+
+ssize_t iov_iter_get_pages(struct iov_iter *i,
+		   struct page **pages, size_t maxsize, unsigned maxpages,
+		   size_t *start)
+{
+	if (i->type & ITER_BVEC)
+		return get_pages_bvec(i, pages, maxsize, maxpages, start);
+	else
+		return get_pages_iovec(i, pages, maxsize, maxpages, start);
+}
+EXPORT_SYMBOL(iov_iter_get_pages);
+
+ssize_t iov_iter_get_pages_alloc(struct iov_iter *i,
+		   struct page ***pages, size_t maxsize,
+		   size_t *start)
+{
+	if (i->type & ITER_BVEC)
+		return get_pages_alloc_bvec(i, pages, maxsize, start);
+	else
+		return get_pages_alloc_iovec(i, pages, maxsize, start);
+}
+EXPORT_SYMBOL(iov_iter_get_pages_alloc);
+
+int iov_iter_npages(const struct iov_iter *i, int maxpages)
+{
+	if (i->type & ITER_BVEC)
+		return iov_iter_npages_bvec(i, maxpages);
+	else
+		return iov_iter_npages_iovec(i, maxpages);
+}
+EXPORT_SYMBOL(iov_iter_npages);

mm/kmemcheck.c

@@ -0,0 +1,123 @@
+#include <linux/gfp.h>
+#include <linux/mm_types.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include "slab.h"
+#include <linux/kmemcheck.h>
+
+void kmemcheck_alloc_shadow(struct page *page, int order, gfp_t flags, int node)
+{
+	struct page *shadow;
+	int pages;
+	int i;
+
+	pages = 1 << order;
+
+	/*
+	 * With kmemcheck enabled, we need to allocate a memory area for the
+	 * shadow bits as well.
+	 */
+	shadow = alloc_pages_node(node, flags | __GFP_NOTRACK, order);
+	if (!shadow) {
+		if (printk_ratelimit())
+			printk(KERN_ERR "kmemcheck: failed to allocate "
+				"shadow bitmap\n");
+		return;
+	}
+
+	for(i = 0; i < pages; ++i)
+		page[i].shadow = page_address(&shadow[i]);
+
+	/*
+	 * Mark it as non-present for the MMU so that our accesses to
+	 * this memory will trigger a page fault and let us analyze
+	 * the memory accesses.
+	 */
+	kmemcheck_hide_pages(page, pages);
+}
+
+void kmemcheck_free_shadow(struct page *page, int order)
+{
+	struct page *shadow;
+	int pages;
+	int i;
+
+	if (!kmemcheck_page_is_tracked(page))
+		return;
+
+	pages = 1 << order;
+
+	kmemcheck_show_pages(page, pages);
+
+	shadow = virt_to_page(page[0].shadow);
+
+	for(i = 0; i < pages; ++i)
+		page[i].shadow = NULL;
+
+	__free_pages(shadow, order);
+}
+
+void kmemcheck_slab_alloc(struct kmem_cache *s, gfp_t gfpflags, void *object,
+			  size_t size)
+{
+	/*
+	 * Has already been memset(), which initializes the shadow for us
+	 * as well.
+	 */
+	if (gfpflags & __GFP_ZERO)
+		return;
+
+	/* No need to initialize the shadow of a non-tracked slab. */
+	if (s->flags & SLAB_NOTRACK)
+		return;
+
+	if (!kmemcheck_enabled || gfpflags & __GFP_NOTRACK) {
+		/*
+		 * Allow notracked objects to be allocated from
+		 * tracked caches. Note however that these objects
+		 * will still get page faults on access, they just
+		 * won't ever be flagged as uninitialized. If page
+		 * faults are not acceptable, the slab cache itself
+		 * should be marked NOTRACK.
+		 */
+		kmemcheck_mark_initialized(object, size);
+	} else if (!s->ctor) {
+		/*
+		 * New objects should be marked uninitialized before
+		 * they're returned to the called.
+		 */
+		kmemcheck_mark_uninitialized(object, size);
+	}
+}
+
+void kmemcheck_slab_free(struct kmem_cache *s, void *object, size_t size)
+{
+	/* TODO: RCU freeing is unsupported for now; hide false positives. */
+	if (!s->ctor && !(s->flags & SLAB_DESTROY_BY_RCU))
+		kmemcheck_mark_freed(object, size);
+}
+
+void kmemcheck_pagealloc_alloc(struct page *page, unsigned int order,
+			       gfp_t gfpflags)
+{
+	int pages;
+
+	if (gfpflags & (__GFP_HIGHMEM | __GFP_NOTRACK))
+		return;
+
+	pages = 1 << order;
+
+	/*
+	 * NOTE: We choose to track GFP_ZERO pages too; in fact, they
+	 * can become uninitialized by copying uninitialized memory
+	 * into them.
+	 */
+
+	/* XXX: Can use zone->node for node? */
+	kmemcheck_alloc_shadow(page, order, gfpflags, -1);
+
+	if (gfpflags & __GFP_ZERO)
+		kmemcheck_mark_initialized_pages(page, pages);
+	else
+		kmemcheck_mark_uninitialized_pages(page, pages);
+}

mm/kmemleak-test.c

@@ -0,0 +1,111 @@
+/*
+ * mm/kmemleak-test.c
+ *
+ * Copyright (C) 2008 ARM Limited
+ * Written by Catalin Marinas <catalin.marinas@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#define pr_fmt(fmt) "kmemleak: " fmt
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/list.h>
+#include <linux/percpu.h>
+#include <linux/fdtable.h>
+
+#include <linux/kmemleak.h>
+
+struct test_node {
+	long header[25];
+	struct list_head list;
+	long footer[25];
+};
+
+static LIST_HEAD(test_list);
+static DEFINE_PER_CPU(void *, kmemleak_test_pointer);
+
+/*
+ * Some very simple testing. This function needs to be extended for
+ * proper testing.
+ */
+static int __init kmemleak_test_init(void)
+{
+	struct test_node *elem;
+	int i;
+
+	printk(KERN_INFO "Kmemleak testing\n");
+
+	/* make some orphan objects */
+	pr_info("kmalloc(32) = %p\n", kmalloc(32, GFP_KERNEL));
+	pr_info("kmalloc(32) = %p\n", kmalloc(32, GFP_KERNEL));
+	pr_info("kmalloc(1024) = %p\n", kmalloc(1024, GFP_KERNEL));
+	pr_info("kmalloc(1024) = %p\n", kmalloc(1024, GFP_KERNEL));
+	pr_info("kmalloc(2048) = %p\n", kmalloc(2048, GFP_KERNEL));
+	pr_info("kmalloc(2048) = %p\n", kmalloc(2048, GFP_KERNEL));
+	pr_info("kmalloc(4096) = %p\n", kmalloc(4096, GFP_KERNEL));
+	pr_info("kmalloc(4096) = %p\n", kmalloc(4096, GFP_KERNEL));
+#ifndef CONFIG_MODULES
+	pr_info("kmem_cache_alloc(files_cachep) = %p\n",
+		kmem_cache_alloc(files_cachep, GFP_KERNEL));
+	pr_info("kmem_cache_alloc(files_cachep) = %p\n",
+		kmem_cache_alloc(files_cachep, GFP_KERNEL));
+#endif
+	pr_info("vmalloc(64) = %p\n", vmalloc(64));
+	pr_info("vmalloc(64) = %p\n", vmalloc(64));
+	pr_info("vmalloc(64) = %p\n", vmalloc(64));
+	pr_info("vmalloc(64) = %p\n", vmalloc(64));
+	pr_info("vmalloc(64) = %p\n", vmalloc(64));
+
+	/*
+	 * Add elements to a list. They should only appear as orphan
+	 * after the module is removed.
+	 */
+	for (i = 0; i < 10; i++) {
+		elem = kzalloc(sizeof(*elem), GFP_KERNEL);
+		pr_info("kzalloc(sizeof(*elem)) = %p\n", elem);
+		if (!elem)
+			return -ENOMEM;
+		INIT_LIST_HEAD(&elem->list);
+		list_add_tail(&elem->list, &test_list);
+	}
+
+	for_each_possible_cpu(i) {
+		per_cpu(kmemleak_test_pointer, i) = kmalloc(129, GFP_KERNEL);
+		pr_info("kmalloc(129) = %p\n",
+			per_cpu(kmemleak_test_pointer, i));
+	}
+
+	return 0;
+}
+module_init(kmemleak_test_init);
+
+static void __exit kmemleak_test_exit(void)
+{
+	struct test_node *elem, *tmp;
+
+	/*
+	 * Remove the list elements without actually freeing the
+	 * memory.
+	 */
+	list_for_each_entry_safe(elem, tmp, &test_list, list)
+		list_del(&elem->list);
+}
+module_exit(kmemleak_test_exit);
+
+MODULE_LICENSE("GPL");

mm/list_lru.c

@@ -0,0 +1,152 @@
+/*
+ * Copyright (c) 2013 Red Hat, Inc. and Parallels Inc. All rights reserved.
+ * Authors: David Chinner and Glauber Costa
+ *
+ * Generic LRU infrastructure
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mm.h>
+#include <linux/list_lru.h>
+#include <linux/slab.h>
+
+bool list_lru_add(struct list_lru *lru, struct list_head *item)
+{
+	int nid = page_to_nid(virt_to_page(item));
+	struct list_lru_node *nlru = &lru->node[nid];
+
+	spin_lock(&nlru->lock);
+	WARN_ON_ONCE(nlru->nr_items < 0);
+	if (list_empty(item)) {
+		list_add_tail(item, &nlru->list);
+		if (nlru->nr_items++ == 0)
+			node_set(nid, lru->active_nodes);
+		spin_unlock(&nlru->lock);
+		return true;
+	}
+	spin_unlock(&nlru->lock);
+	return false;
+}
+EXPORT_SYMBOL_GPL(list_lru_add);
+
+bool list_lru_del(struct list_lru *lru, struct list_head *item)
+{
+	int nid = page_to_nid(virt_to_page(item));
+	struct list_lru_node *nlru = &lru->node[nid];
+
+	spin_lock(&nlru->lock);
+	if (!list_empty(item)) {
+		list_del_init(item);
+		if (--nlru->nr_items == 0)
+			node_clear(nid, lru->active_nodes);
+		WARN_ON_ONCE(nlru->nr_items < 0);
+		spin_unlock(&nlru->lock);
+		return true;
+	}
+	spin_unlock(&nlru->lock);
+	return false;
+}
+EXPORT_SYMBOL_GPL(list_lru_del);
+
+unsigned long
+list_lru_count_node(struct list_lru *lru, int nid)
+{
+	unsigned long count = 0;
+	struct list_lru_node *nlru = &lru->node[nid];
+
+	spin_lock(&nlru->lock);
+	WARN_ON_ONCE(nlru->nr_items < 0);
+	count += nlru->nr_items;
+	spin_unlock(&nlru->lock);
+
+	return count;
+}
+EXPORT_SYMBOL_GPL(list_lru_count_node);
+
+unsigned long
+list_lru_walk_node(struct list_lru *lru, int nid, list_lru_walk_cb isolate,
+		   void *cb_arg, unsigned long *nr_to_walk)
+{
+
+	struct list_lru_node	*nlru = &lru->node[nid];
+	struct list_head *item, *n;
+	unsigned long isolated = 0;
+
+	spin_lock(&nlru->lock);
+restart:
+	list_for_each_safe(item, n, &nlru->list) {
+		enum lru_status ret;
+
+		/*
+		 * decrement nr_to_walk first so that we don't livelock if we
+		 * get stuck on large numbesr of LRU_RETRY items
+		 */
+		if (!*nr_to_walk)
+			break;
+		--*nr_to_walk;
+
+		ret = isolate(item, &nlru->lock, cb_arg);
+		switch (ret) {
+		case LRU_REMOVED_RETRY:
+			assert_spin_locked(&nlru->lock);
+		case LRU_REMOVED:
+			if (--nlru->nr_items == 0)
+				node_clear(nid, lru->active_nodes);
+			WARN_ON_ONCE(nlru->nr_items < 0);
+			isolated++;
+			/*
+			 * If the lru lock has been dropped, our list
+			 * traversal is now invalid and so we have to
+			 * restart from scratch.
+			 */
+			if (ret == LRU_REMOVED_RETRY)
+				goto restart;
+			break;
+		case LRU_ROTATE:
+			list_move_tail(item, &nlru->list);
+			break;
+		case LRU_SKIP:
+			break;
+		case LRU_RETRY:
+			/*
+			 * The lru lock has been dropped, our list traversal is
+			 * now invalid and so we have to restart from scratch.
+			 */
+			assert_spin_locked(&nlru->lock);
+			goto restart;
+		default:
+			BUG();
+		}
+	}
+
+	spin_unlock(&nlru->lock);
+	return isolated;
+}
+EXPORT_SYMBOL_GPL(list_lru_walk_node);
+
+int list_lru_init_key(struct list_lru *lru, struct lock_class_key *key)
+{
+	int i;
+	size_t size = sizeof(*lru->node) * nr_node_ids;
+
+	lru->node = kzalloc(size, GFP_KERNEL);
+	if (!lru->node)
+		return -ENOMEM;
+
+	nodes_clear(lru->active_nodes);
+	for (i = 0; i < nr_node_ids; i++) {
+		spin_lock_init(&lru->node[i].lock);
+		if (key)
+			lockdep_set_class(&lru->node[i].lock, key);
+		INIT_LIST_HEAD(&lru->node[i].list);
+		lru->node[i].nr_items = 0;
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(list_lru_init_key);
+
+void list_lru_destroy(struct list_lru *lru)
+{
+	kfree(lru->node);
+}
+EXPORT_SYMBOL_GPL(list_lru_destroy);

mm/maccess.c

@@ -0,0 +1,62 @@
+/*
+ * Access kernel memory without faulting.
+ */
+#include <linux/export.h>
+#include <linux/mm.h>
+#include <linux/uaccess.h>
+
+/**
+ * probe_kernel_read(): safely attempt to read from a location
+ * @dst: pointer to the buffer that shall take the data
+ * @src: address to read from
+ * @size: size of the data chunk
+ *
+ * Safely read from address @src to the buffer at @dst.  If a kernel fault
+ * happens, handle that and return -EFAULT.
+ */
+
+long __weak probe_kernel_read(void *dst, const void *src, size_t size)
+    __attribute__((alias("__probe_kernel_read")));
+
+long __probe_kernel_read(void *dst, const void *src, size_t size)
+{
+	long ret;
+	mm_segment_t old_fs = get_fs();
+
+	set_fs(KERNEL_DS);
+	pagefault_disable();
+	ret = __copy_from_user_inatomic(dst,
+			(__force const void __user *)src, size);
+	pagefault_enable();
+	set_fs(old_fs);
+
+	return ret ? -EFAULT : 0;
+}
+EXPORT_SYMBOL_GPL(probe_kernel_read);
+
+/**
+ * probe_kernel_write(): safely attempt to write to a location
+ * @dst: address to write to
+ * @src: pointer to the data that shall be written
+ * @size: size of the data chunk
+ *
+ * Safely write to address @dst from the buffer at @src.  If a kernel fault
+ * happens, handle that and return -EFAULT.
+ */
+long __weak probe_kernel_write(void *dst, const void *src, size_t size)
+    __attribute__((alias("__probe_kernel_write")));
+
+long __probe_kernel_write(void *dst, const void *src, size_t size)
+{
+	long ret;
+	mm_segment_t old_fs = get_fs();
+
+	set_fs(KERNEL_DS);
+	pagefault_disable();
+	ret = __copy_to_user_inatomic((__force void __user *)dst, src, size);
+	pagefault_enable();
+	set_fs(old_fs);
+
+	return ret ? -EFAULT : 0;
+}
+EXPORT_SYMBOL_GPL(probe_kernel_write);

mm/madvise.c

@@ -0,0 +1,554 @@
+/*
+ *	linux/mm/madvise.c
+ *
+ * Copyright (C) 1999  Linus Torvalds
+ * Copyright (C) 2002  Christoph Hellwig
+ */
+
+#include <linux/mman.h>
+#include <linux/pagemap.h>
+#include <linux/syscalls.h>
+#include <linux/mempolicy.h>
+#include <linux/page-isolation.h>
+#include <linux/hugetlb.h>
+#include <linux/falloc.h>
+#include <linux/sched.h>
+#include <linux/ksm.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/blkdev.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
+
+/*
+ * Any behaviour which results in changes to the vma->vm_flags needs to
+ * take mmap_sem for writing. Others, which simply traverse vmas, need
+ * to only take it for reading.
+ */
+static int madvise_need_mmap_write(int behavior)
+{
+	switch (behavior) {
+	case MADV_REMOVE:
+	case MADV_WILLNEED:
+	case MADV_DONTNEED:
+		return 0;
+	default:
+		/* be safe, default to 1. list exceptions explicitly */
+		return 1;
+	}
+}
+
+/*
+ * We can potentially split a vm area into separate
+ * areas, each area with its own behavior.
+ */
+static long madvise_behavior(struct vm_area_struct *vma,
+		     struct vm_area_struct **prev,
+		     unsigned long start, unsigned long end, int behavior)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	int error = 0;
+	pgoff_t pgoff;
+	unsigned long new_flags = vma->vm_flags;
+
+	switch (behavior) {
+	case MADV_NORMAL:
+		new_flags = new_flags & ~VM_RAND_READ & ~VM_SEQ_READ;
+		break;
+	case MADV_SEQUENTIAL:
+		new_flags = (new_flags & ~VM_RAND_READ) | VM_SEQ_READ;
+		break;
+	case MADV_RANDOM:
+		new_flags = (new_flags & ~VM_SEQ_READ) | VM_RAND_READ;
+		break;
+	case MADV_DONTFORK:
+		new_flags |= VM_DONTCOPY;
+		break;
+	case MADV_DOFORK:
+		if (vma->vm_flags & VM_IO) {
+			error = -EINVAL;
+			goto out;
+		}
+		new_flags &= ~VM_DONTCOPY;
+		break;
+	case MADV_DONTDUMP:
+		new_flags |= VM_DONTDUMP;
+		break;
+	case MADV_DODUMP:
+		if (new_flags & VM_SPECIAL) {
+			error = -EINVAL;
+			goto out;
+		}
+		new_flags &= ~VM_DONTDUMP;
+		break;
+	case MADV_MERGEABLE:
+	case MADV_UNMERGEABLE:
+		error = ksm_madvise(vma, start, end, behavior, &new_flags);
+		if (error)
+			goto out;
+		break;
+	case MADV_HUGEPAGE:
+	case MADV_NOHUGEPAGE:
+		error = hugepage_madvise(vma, &new_flags, behavior);
+		if (error)
+			goto out;
+		break;
+	}
+
+	if (new_flags == vma->vm_flags) {
+		*prev = vma;
+		goto out;
+	}
+
+	pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
+	*prev = vma_merge(mm, *prev, start, end, new_flags, vma->anon_vma,
+				vma->vm_file, pgoff, vma_policy(vma),
+				vma_get_anon_name(vma));
+	if (*prev) {
+		vma = *prev;
+		goto success;
+	}
+
+	*prev = vma;
+
+	if (start != vma->vm_start) {
+		error = split_vma(mm, vma, start, 1);
+		if (error)
+			goto out;
+	}
+
+	if (end != vma->vm_end) {
+		error = split_vma(mm, vma, end, 0);
+		if (error)
+			goto out;
+	}
+
+success:
+	/*
+	 * vm_flags is protected by the mmap_sem held in write mode.
+	 */
+	vma->vm_flags = new_flags;
+
+out:
+	if (error == -ENOMEM)
+		error = -EAGAIN;
+	return error;
+}
+
+#ifdef CONFIG_SWAP
+static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start,
+	unsigned long end, struct mm_walk *walk)
+{
+	pte_t *orig_pte;
+	struct vm_area_struct *vma = walk->private;
+	unsigned long index;
+
+	if (pmd_none_or_trans_huge_or_clear_bad(pmd))
+		return 0;
+
+	for (index = start; index != end; index += PAGE_SIZE) {
+		pte_t pte;
+		swp_entry_t entry;
+		struct page *page;
+		spinlock_t *ptl;
+
+		orig_pte = pte_offset_map_lock(vma->vm_mm, pmd, start, &ptl);
+		pte = *(orig_pte + ((index - start) / PAGE_SIZE));
+		pte_unmap_unlock(orig_pte, ptl);
+
+		if (pte_present(pte) || pte_none(pte) || pte_file(pte))
+			continue;
+		entry = pte_to_swp_entry(pte);
+		if (unlikely(non_swap_entry(entry)))
+			continue;
+
+		page = read_swap_cache_async(entry, GFP_HIGHUSER_MOVABLE,
+								vma, index);
+		if (page)
+			page_cache_release(page);
+	}
+
+	return 0;
+}
+
+static void force_swapin_readahead(struct vm_area_struct *vma,
+		unsigned long start, unsigned long end)
+{
+	struct mm_walk walk = {
+		.mm = vma->vm_mm,
+		.pmd_entry = swapin_walk_pmd_entry,
+		.private = vma,
+	};
+
+	walk_page_range(start, end, &walk);
+
+	lru_add_drain();	/* Push any new pages onto the LRU now */
+}
+
+static void force_shm_swapin_readahead(struct vm_area_struct *vma,
+		unsigned long start, unsigned long end,
+		struct address_space *mapping)
+{
+	pgoff_t index;
+	struct page *page;
+	swp_entry_t swap;
+
+	for (; start < end; start += PAGE_SIZE) {
+		index = ((start - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
+
+		page = find_get_entry(mapping, index);
+		if (!radix_tree_exceptional_entry(page)) {
+			if (page)
+				page_cache_release(page);
+			continue;
+		}
+		swap = radix_to_swp_entry(page);
+		page = read_swap_cache_async(swap, GFP_HIGHUSER_MOVABLE,
+								NULL, 0);
+		if (page)
+			page_cache_release(page);
+	}
+
+	lru_add_drain();	/* Push any new pages onto the LRU now */
+}
+#endif		/* CONFIG_SWAP */
+
+/*
+ * Schedule all required I/O operations.  Do not wait for completion.
+ */
+static long madvise_willneed(struct vm_area_struct *vma,
+			     struct vm_area_struct **prev,
+			     unsigned long start, unsigned long end)
+{
+	struct file *file = vma->vm_file;
+
+#ifdef CONFIG_SWAP
+	if (!file || mapping_cap_swap_backed(file->f_mapping)) {
+		*prev = vma;
+		if (!file)
+			force_swapin_readahead(vma, start, end);
+		else
+			force_shm_swapin_readahead(vma, start, end,
+						file->f_mapping);
+		return 0;
+	}
+#endif
+
+	if (!file)
+		return -EBADF;
+
+	if (file->f_mapping->a_ops->get_xip_mem) {
+		/* no bad return value, but ignore advice */
+		return 0;
+	}
+
+	*prev = vma;
+	start = ((start - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
+	if (end > vma->vm_end)
+		end = vma->vm_end;
+	end = ((end - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
+
+	force_page_cache_readahead(file->f_mapping, file, start, end - start);
+	return 0;
+}
+
+/*
+ * Application no longer needs these pages.  If the pages are dirty,
+ * it's OK to just throw them away.  The app will be more careful about
+ * data it wants to keep.  Be sure to free swap resources too.  The
+ * zap_page_range call sets things up for shrink_active_list to actually free
+ * these pages later if no one else has touched them in the meantime,
+ * although we could add these pages to a global reuse list for
+ * shrink_active_list to pick up before reclaiming other pages.
+ *
+ * NB: This interface discards data rather than pushes it out to swap,
+ * as some implementations do.  This has performance implications for
+ * applications like large transactional databases which want to discard
+ * pages in anonymous maps after committing to backing store the data
+ * that was kept in them.  There is no reason to write this data out to
+ * the swap area if the application is discarding it.
+ *
+ * An interface that causes the system to free clean pages and flush
+ * dirty pages is already available as msync(MS_INVALIDATE).
+ */
+static long madvise_dontneed(struct vm_area_struct *vma,
+			     struct vm_area_struct **prev,
+			     unsigned long start, unsigned long end)
+{
+	*prev = vma;
+	if (vma->vm_flags & (VM_LOCKED|VM_HUGETLB|VM_PFNMAP))
+		return -EINVAL;
+
+	if (unlikely(vma->vm_flags & VM_NONLINEAR)) {
+		struct zap_details details = {
+			.nonlinear_vma = vma,
+			.last_index = ULONG_MAX,
+		};
+		zap_page_range(vma, start, end - start, &details);
+	} else
+		zap_page_range(vma, start, end - start, NULL);
+	return 0;
+}
+
+/*
+ * Application wants to free up the pages and associated backing store.
+ * This is effectively punching a hole into the middle of a file.
+ */
+static long madvise_remove(struct vm_area_struct *vma,
+				struct vm_area_struct **prev,
+				unsigned long start, unsigned long end)
+{
+	loff_t offset;
+	int error;
+	struct file *f;
+
+	*prev = NULL;	/* tell sys_madvise we drop mmap_sem */
+
+	if (vma->vm_flags & (VM_LOCKED|VM_NONLINEAR|VM_HUGETLB))
+		return -EINVAL;
+
+	f = vma->vm_file;
+
+	if (!f || !f->f_mapping || !f->f_mapping->host) {
+			return -EINVAL;
+	}
+
+	if ((vma->vm_flags & (VM_SHARED|VM_WRITE)) != (VM_SHARED|VM_WRITE))
+		return -EACCES;
+
+	offset = (loff_t)(start - vma->vm_start)
+			+ ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
+
+	/*
+	 * Filesystem's fallocate may need to take i_mutex.  We need to
+	 * explicitly grab a reference because the vma (and hence the
+	 * vma's reference to the file) can go away as soon as we drop
+	 * mmap_sem.
+	 */
+	get_file(f);
+	up_read(&current->mm->mmap_sem);
+	error = do_fallocate(f,
+				FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
+				offset, end - start);
+	fput(f);
+	down_read(&current->mm->mmap_sem);
+	return error;
+}
+
+#ifdef CONFIG_MEMORY_FAILURE
+/*
+ * Error injection support for memory error handling.
+ */
+static int madvise_hwpoison(int bhv, unsigned long start, unsigned long end)
+{
+	struct page *p;
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+	for (; start < end; start += PAGE_SIZE <<
+				compound_order(compound_head(p))) {
+		int ret;
+
+		ret = get_user_pages_fast(start, 1, 0, &p);
+		if (ret != 1)
+			return ret;
+
+		if (PageHWPoison(p)) {
+			put_page(p);
+			continue;
+		}
+		if (bhv == MADV_SOFT_OFFLINE) {
+			pr_info("Soft offlining page %#lx at %#lx\n",
+				page_to_pfn(p), start);
+			ret = soft_offline_page(p, MF_COUNT_INCREASED);
+			if (ret)
+				return ret;
+			continue;
+		}
+		pr_info("Injecting memory failure for page %#lx at %#lx\n",
+		       page_to_pfn(p), start);
+		/* Ignore return value for now */
+		memory_failure(page_to_pfn(p), 0, MF_COUNT_INCREASED);
+	}
+	return 0;
+}
+#endif
+
+static long
+madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev,
+		unsigned long start, unsigned long end, int behavior)
+{
+	switch (behavior) {
+	case MADV_REMOVE:
+		return madvise_remove(vma, prev, start, end);
+	case MADV_WILLNEED:
+		return madvise_willneed(vma, prev, start, end);
+	case MADV_DONTNEED:
+		return madvise_dontneed(vma, prev, start, end);
+	default:
+		return madvise_behavior(vma, prev, start, end, behavior);
+	}
+}
+
+static int
+madvise_behavior_valid(int behavior)
+{
+	switch (behavior) {
+	case MADV_DOFORK:
+	case MADV_DONTFORK:
+	case MADV_NORMAL:
+	case MADV_SEQUENTIAL:
+	case MADV_RANDOM:
+	case MADV_REMOVE:
+	case MADV_WILLNEED:
+	case MADV_DONTNEED:
+#ifdef CONFIG_KSM
+	case MADV_MERGEABLE:
+	case MADV_UNMERGEABLE:
+#endif
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	case MADV_HUGEPAGE:
+	case MADV_NOHUGEPAGE:
+#endif
+	case MADV_DONTDUMP:
+	case MADV_DODUMP:
+		return 1;
+
+	default:
+		return 0;
+	}
+}
+
+/*
+ * The madvise(2) system call.
+ *
+ * Applications can use madvise() to advise the kernel how it should
+ * handle paging I/O in this VM area.  The idea is to help the kernel
+ * use appropriate read-ahead and caching techniques.  The information
+ * provided is advisory only, and can be safely disregarded by the
+ * kernel without affecting the correct operation of the application.
+ *
+ * behavior values:
+ *  MADV_NORMAL - the default behavior is to read clusters.  This
+ *		results in some read-ahead and read-behind.
+ *  MADV_RANDOM - the system should read the minimum amount of data
+ *		on any access, since it is unlikely that the appli-
+ *		cation will need more than what it asks for.
+ *  MADV_SEQUENTIAL - pages in the given range will probably be accessed
+ *		once, so they can be aggressively read ahead, and
+ *		can be freed soon after they are accessed.
+ *  MADV_WILLNEED - the application is notifying the system to read
+ *		some pages ahead.
+ *  MADV_DONTNEED - the application is finished with the given range,
+ *		so the kernel can free resources associated with it.
+ *  MADV_REMOVE - the application wants to free up the given range of
+ *		pages and associated backing store.
+ *  MADV_DONTFORK - omit this area from child's address space when forking:
+ *		typically, to avoid COWing pages pinned by get_user_pages().
+ *  MADV_DOFORK - cancel MADV_DONTFORK: no longer omit this area when forking.
+ *  MADV_MERGEABLE - the application recommends that KSM try to merge pages in
+ *		this area with pages of identical content from other such areas.
+ *  MADV_UNMERGEABLE- cancel MADV_MERGEABLE: no longer merge pages with others.
+ *
+ * return values:
+ *  zero    - success
+ *  -EINVAL - start + len < 0, start is not page-aligned,
+ *		"behavior" is not a valid value, or application
+ *		is attempting to release locked or shared pages.
+ *  -ENOMEM - addresses in the specified range are not currently
+ *		mapped, or are outside the AS of the process.
+ *  -EIO    - an I/O error occurred while paging in data.
+ *  -EBADF  - map exists, but area maps something that isn't a file.
+ *  -EAGAIN - a kernel resource was temporarily unavailable.
+ */
+SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
+{
+	unsigned long end, tmp;
+	struct vm_area_struct *vma, *prev;
+	int unmapped_error = 0;
+	int error = -EINVAL;
+	int write;
+	size_t len;
+	struct blk_plug plug;
+
+#ifdef CONFIG_MEMORY_FAILURE
+	if (behavior == MADV_HWPOISON || behavior == MADV_SOFT_OFFLINE)
+		return madvise_hwpoison(behavior, start, start+len_in);
+#endif
+	if (!madvise_behavior_valid(behavior))
+		return error;
+
+	if (start & ~PAGE_MASK)
+		return error;
+	len = (len_in + ~PAGE_MASK) & PAGE_MASK;
+
+	/* Check to see whether len was rounded up from small -ve to zero */
+	if (len_in && !len)
+		return error;
+
+	end = start + len;
+	if (end < start)
+		return error;
+
+	error = 0;
+	if (end == start)
+		return error;
+
+	write = madvise_need_mmap_write(behavior);
+	if (write)
+		down_write(&current->mm->mmap_sem);
+	else
+		down_read(&current->mm->mmap_sem);
+
+	/*
+	 * If the interval [start,end) covers some unmapped address
+	 * ranges, just ignore them, but return -ENOMEM at the end.
+	 * - different from the way of handling in mlock etc.
+	 */
+	vma = find_vma_prev(current->mm, start, &prev);
+	if (vma && start > vma->vm_start)
+		prev = vma;
+
+	blk_start_plug(&plug);
+	for (;;) {
+		/* Still start < end. */
+		error = -ENOMEM;
+		if (!vma)
+			goto out;
+
+		/* Here start < (end|vma->vm_end). */
+		if (start < vma->vm_start) {
+			unmapped_error = -ENOMEM;
+			start = vma->vm_start;
+			if (start >= end)
+				goto out;
+		}
+
+		/* Here vma->vm_start <= start < (end|vma->vm_end) */
+		tmp = vma->vm_end;
+		if (end < tmp)
+			tmp = end;
+
+		/* Here vma->vm_start <= start < tmp <= (end|vma->vm_end). */
+		error = madvise_vma(vma, &prev, start, tmp, behavior);
+		if (error)
+			goto out;
+		start = tmp;
+		if (prev && start < prev->vm_end)
+			start = prev->vm_end;
+		error = unmapped_error;
+		if (start >= end)
+			goto out;
+		if (prev)
+			vma = prev->vm_next;
+		else	/* madvise_remove dropped mmap_sem */
+			vma = find_vma(current->mm, start);
+	}
+out:
+	blk_finish_plug(&plug);
+	if (write)
+		up_write(&current->mm->mmap_sem);
+	else
+		up_read(&current->mm->mmap_sem);
+
+	return error;
+}

mm/mempool.c

@@ -0,0 +1,379 @@
+/*
+ *  linux/mm/mempool.c
+ *
+ *  memory buffer pool support. Such pools are mostly used
+ *  for guaranteed, deadlock-free memory allocations during
+ *  extreme VM load.
+ *
+ *  started by Ingo Molnar, Copyright (C) 2001
+ */
+
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/kmemleak.h>
+#include <linux/export.h>
+#include <linux/mempool.h>
+#include <linux/blkdev.h>
+#include <linux/writeback.h>
+
+static void add_element(mempool_t *pool, void *element)
+{
+	BUG_ON(pool->curr_nr >= pool->min_nr);
+	pool->elements[pool->curr_nr++] = element;
+}
+
+static void *remove_element(mempool_t *pool)
+{
+	BUG_ON(pool->curr_nr <= 0);
+	return pool->elements[--pool->curr_nr];
+}
+
+/**
+ * mempool_destroy - deallocate a memory pool
+ * @pool:      pointer to the memory pool which was allocated via
+ *             mempool_create().
+ *
+ * Free all reserved elements in @pool and @pool itself.  This function
+ * only sleeps if the free_fn() function sleeps.
+ */
+void mempool_destroy(mempool_t *pool)
+{
+	while (pool->curr_nr) {
+		void *element = remove_element(pool);
+		pool->free(element, pool->pool_data);
+	}
+	kfree(pool->elements);
+	kfree(pool);
+}
+EXPORT_SYMBOL(mempool_destroy);
+
+/**
+ * mempool_create - create a memory pool
+ * @min_nr:    the minimum number of elements guaranteed to be
+ *             allocated for this pool.
+ * @alloc_fn:  user-defined element-allocation function.
+ * @free_fn:   user-defined element-freeing function.
+ * @pool_data: optional private data available to the user-defined functions.
+ *
+ * this function creates and allocates a guaranteed size, preallocated
+ * memory pool. The pool can be used from the mempool_alloc() and mempool_free()
+ * functions. This function might sleep. Both the alloc_fn() and the free_fn()
+ * functions might sleep - as long as the mempool_alloc() function is not called
+ * from IRQ contexts.
+ */
+mempool_t *mempool_create(int min_nr, mempool_alloc_t *alloc_fn,
+				mempool_free_t *free_fn, void *pool_data)
+{
+	return mempool_create_node(min_nr,alloc_fn,free_fn, pool_data,
+				   GFP_KERNEL, NUMA_NO_NODE);
+}
+EXPORT_SYMBOL(mempool_create);
+
+mempool_t *mempool_create_node(int min_nr, mempool_alloc_t *alloc_fn,
+			       mempool_free_t *free_fn, void *pool_data,
+			       gfp_t gfp_mask, int node_id)
+{
+	mempool_t *pool;
+	pool = kzalloc_node(sizeof(*pool), gfp_mask, node_id);
+	if (!pool)
+		return NULL;
+	pool->elements = kmalloc_node(min_nr * sizeof(void *),
+				      gfp_mask, node_id);
+	if (!pool->elements) {
+		kfree(pool);
+		return NULL;
+	}
+	spin_lock_init(&pool->lock);
+	pool->min_nr = min_nr;
+	pool->pool_data = pool_data;
+	init_waitqueue_head(&pool->wait);
+	pool->alloc = alloc_fn;
+	pool->free = free_fn;
+
+	/*
+	 * First pre-allocate the guaranteed number of buffers.
+	 */
+	while (pool->curr_nr < pool->min_nr) {
+		void *element;
+
+		element = pool->alloc(gfp_mask, pool->pool_data);
+		if (unlikely(!element)) {
+			mempool_destroy(pool);
+			return NULL;
+		}
+		add_element(pool, element);
+	}
+	return pool;
+}
+EXPORT_SYMBOL(mempool_create_node);
+
+/**
+ * mempool_resize - resize an existing memory pool
+ * @pool:       pointer to the memory pool which was allocated via
+ *              mempool_create().
+ * @new_min_nr: the new minimum number of elements guaranteed to be
+ *              allocated for this pool.
+ * @gfp_mask:   the usual allocation bitmask.
+ *
+ * This function shrinks/grows the pool. In the case of growing,
+ * it cannot be guaranteed that the pool will be grown to the new
+ * size immediately, but new mempool_free() calls will refill it.
+ *
+ * Note, the caller must guarantee that no mempool_destroy is called
+ * while this function is running. mempool_alloc() & mempool_free()
+ * might be called (eg. from IRQ contexts) while this function executes.
+ */
+int mempool_resize(mempool_t *pool, int new_min_nr, gfp_t gfp_mask)
+{
+	void *element;
+	void **new_elements;
+	unsigned long flags;
+
+	BUG_ON(new_min_nr <= 0);
+
+	spin_lock_irqsave(&pool->lock, flags);
+	if (new_min_nr <= pool->min_nr) {
+		while (new_min_nr < pool->curr_nr) {
+			element = remove_element(pool);
+			spin_unlock_irqrestore(&pool->lock, flags);
+			pool->free(element, pool->pool_data);
+			spin_lock_irqsave(&pool->lock, flags);
+		}
+		pool->min_nr = new_min_nr;
+		goto out_unlock;
+	}
+	spin_unlock_irqrestore(&pool->lock, flags);
+
+	/* Grow the pool */
+	new_elements = kmalloc(new_min_nr * sizeof(*new_elements), gfp_mask);
+	if (!new_elements)
+		return -ENOMEM;
+
+	spin_lock_irqsave(&pool->lock, flags);
+	if (unlikely(new_min_nr <= pool->min_nr)) {
+		/* Raced, other resize will do our work */
+		spin_unlock_irqrestore(&pool->lock, flags);
+		kfree(new_elements);
+		goto out;
+	}
+	memcpy(new_elements, pool->elements,
+			pool->curr_nr * sizeof(*new_elements));
+	kfree(pool->elements);
+	pool->elements = new_elements;
+	pool->min_nr = new_min_nr;
+
+	while (pool->curr_nr < pool->min_nr) {
+		spin_unlock_irqrestore(&pool->lock, flags);
+		element = pool->alloc(gfp_mask, pool->pool_data);
+		if (!element)
+			goto out;
+		spin_lock_irqsave(&pool->lock, flags);
+		if (pool->curr_nr < pool->min_nr) {
+			add_element(pool, element);
+		} else {
+			spin_unlock_irqrestore(&pool->lock, flags);
+			pool->free(element, pool->pool_data);	/* Raced */
+			goto out;
+		}
+	}
+out_unlock:
+	spin_unlock_irqrestore(&pool->lock, flags);
+out:
+	return 0;
+}
+EXPORT_SYMBOL(mempool_resize);
+
+/**
+ * mempool_alloc - allocate an element from a specific memory pool
+ * @pool:      pointer to the memory pool which was allocated via
+ *             mempool_create().
+ * @gfp_mask:  the usual allocation bitmask.
+ *
+ * this function only sleeps if the alloc_fn() function sleeps or
+ * returns NULL. Note that due to preallocation, this function
+ * *never* fails when called from process contexts. (it might
+ * fail if called from an IRQ context.)
+ * Note: using __GFP_ZERO is not supported.
+ */
+void * mempool_alloc(mempool_t *pool, gfp_t gfp_mask)
+{
+	void *element;
+	unsigned long flags;
+	wait_queue_t wait;
+	gfp_t gfp_temp;
+
+	VM_WARN_ON_ONCE(gfp_mask & __GFP_ZERO);
+	might_sleep_if(gfp_mask & __GFP_WAIT);
+
+	gfp_mask |= __GFP_NOMEMALLOC;	/* don't allocate emergency reserves */
+	gfp_mask |= __GFP_NORETRY;	/* don't loop in __alloc_pages */
+	gfp_mask |= __GFP_NOWARN;	/* failures are OK */
+
+	gfp_temp = gfp_mask & ~(__GFP_WAIT|__GFP_IO);
+
+repeat_alloc:
+
+	element = pool->alloc(gfp_temp, pool->pool_data);
+	if (likely(element != NULL))
+		return element;
+
+	spin_lock_irqsave(&pool->lock, flags);
+	if (likely(pool->curr_nr)) {
+		element = remove_element(pool);
+		spin_unlock_irqrestore(&pool->lock, flags);
+		/* paired with rmb in mempool_free(), read comment there */
+		smp_wmb();
+		/*
+		 * Update the allocation stack trace as this is more useful
+		 * for debugging.
+		 */
+		kmemleak_update_trace(element);
+		return element;
+	}
+
+	/*
+	 * We use gfp mask w/o __GFP_WAIT or IO for the first round.  If
+	 * alloc failed with that and @pool was empty, retry immediately.
+	 */
+	if (gfp_temp != gfp_mask) {
+		spin_unlock_irqrestore(&pool->lock, flags);
+		gfp_temp = gfp_mask;
+		goto repeat_alloc;
+	}
+
+	/* We must not sleep if !__GFP_WAIT */
+	if (!(gfp_mask & __GFP_WAIT)) {
+		spin_unlock_irqrestore(&pool->lock, flags);
+		return NULL;
+	}
+
+	/* Let's wait for someone else to return an element to @pool */
+	init_wait(&wait);
+	prepare_to_wait(&pool->wait, &wait, TASK_UNINTERRUPTIBLE);
+
+	spin_unlock_irqrestore(&pool->lock, flags);
+
+	/*
+	 * FIXME: this should be io_schedule().  The timeout is there as a
+	 * workaround for some DM problems in 2.6.18.
+	 */
+	io_schedule_timeout(5*HZ);
+
+	finish_wait(&pool->wait, &wait);
+	goto repeat_alloc;
+}
+EXPORT_SYMBOL(mempool_alloc);
+
+/**
+ * mempool_free - return an element to the pool.
+ * @element:   pool element pointer.
+ * @pool:      pointer to the memory pool which was allocated via
+ *             mempool_create().
+ *
+ * this function only sleeps if the free_fn() function sleeps.
+ */
+void mempool_free(void *element, mempool_t *pool)
+{
+	unsigned long flags;
+
+	if (unlikely(element == NULL))
+		return;
+
+	/*
+	 * Paired with the wmb in mempool_alloc().  The preceding read is
+	 * for @element and the following @pool->curr_nr.  This ensures
+	 * that the visible value of @pool->curr_nr is from after the
+	 * allocation of @element.  This is necessary for fringe cases
+	 * where @element was passed to this task without going through
+	 * barriers.
+	 *
+	 * For example, assume @p is %NULL at the beginning and one task
+	 * performs "p = mempool_alloc(...);" while another task is doing
+	 * "while (!p) cpu_relax(); mempool_free(p, ...);".  This function
+	 * may end up using curr_nr value which is from before allocation
+	 * of @p without the following rmb.
+	 */
+	smp_rmb();
+
+	/*
+	 * For correctness, we need a test which is guaranteed to trigger
+	 * if curr_nr + #allocated == min_nr.  Testing curr_nr < min_nr
+	 * without locking achieves that and refilling as soon as possible
+	 * is desirable.
+	 *
+	 * Because curr_nr visible here is always a value after the
+	 * allocation of @element, any task which decremented curr_nr below
+	 * min_nr is guaranteed to see curr_nr < min_nr unless curr_nr gets
+	 * incremented to min_nr afterwards.  If curr_nr gets incremented
+	 * to min_nr after the allocation of @element, the elements
+	 * allocated after that are subject to the same guarantee.
+	 *
+	 * Waiters happen iff curr_nr is 0 and the above guarantee also
+	 * ensures that there will be frees which return elements to the
+	 * pool waking up the waiters.
+	 */
+	if (unlikely(pool->curr_nr < pool->min_nr)) {
+		spin_lock_irqsave(&pool->lock, flags);
+		if (likely(pool->curr_nr < pool->min_nr)) {
+			add_element(pool, element);
+			spin_unlock_irqrestore(&pool->lock, flags);
+			wake_up(&pool->wait);
+			return;
+		}
+		spin_unlock_irqrestore(&pool->lock, flags);
+	}
+	pool->free(element, pool->pool_data);
+}
+EXPORT_SYMBOL(mempool_free);
+
+/*
+ * A commonly used alloc and free fn.
+ */
+void *mempool_alloc_slab(gfp_t gfp_mask, void *pool_data)
+{
+	struct kmem_cache *mem = pool_data;
+	return kmem_cache_alloc(mem, gfp_mask);
+}
+EXPORT_SYMBOL(mempool_alloc_slab);
+
+void mempool_free_slab(void *element, void *pool_data)
+{
+	struct kmem_cache *mem = pool_data;
+	kmem_cache_free(mem, element);
+}
+EXPORT_SYMBOL(mempool_free_slab);
+
+/*
+ * A commonly used alloc and free fn that kmalloc/kfrees the amount of memory
+ * specified by pool_data
+ */
+void *mempool_kmalloc(gfp_t gfp_mask, void *pool_data)
+{
+	size_t size = (size_t)pool_data;
+	return kmalloc(size, gfp_mask);
+}
+EXPORT_SYMBOL(mempool_kmalloc);
+
+void mempool_kfree(void *element, void *pool_data)
+{
+	kfree(element);
+}
+EXPORT_SYMBOL(mempool_kfree);
+
+/*
+ * A simple mempool-backed page allocator that allocates pages
+ * of the order specified by pool_data.
+ */
+void *mempool_alloc_pages(gfp_t gfp_mask, void *pool_data)
+{
+	int order = (int)(long)pool_data;
+	return alloc_pages(gfp_mask, order);
+}
+EXPORT_SYMBOL(mempool_alloc_pages);
+
+void mempool_free_pages(void *element, void *pool_data)
+{
+	int order = (int)(long)pool_data;
+	__free_pages(element, order);
+}
+EXPORT_SYMBOL(mempool_free_pages);

mm/mincore.c

@@ -0,0 +1,317 @@
+/*
+ *	linux/mm/mincore.c
+ *
+ * Copyright (C) 1994-2006  Linus Torvalds
+ */
+
+/*
+ * The mincore() system call.
+ */
+#include <linux/pagemap.h>
+#include <linux/gfp.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/syscalls.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
+#include <linux/hugetlb.h>
+
+#include <asm/uaccess.h>
+#include <asm/pgtable.h>
+
+static void mincore_hugetlb_page_range(struct vm_area_struct *vma,
+				unsigned long addr, unsigned long end,
+				unsigned char *vec)
+{
+#ifdef CONFIG_HUGETLB_PAGE
+	struct hstate *h;
+
+	h = hstate_vma(vma);
+	while (1) {
+		unsigned char present;
+		pte_t *ptep;
+		/*
+		 * Huge pages are always in RAM for now, but
+		 * theoretically it needs to be checked.
+		 */
+		ptep = huge_pte_offset(current->mm,
+				       addr & huge_page_mask(h));
+		present = ptep && !huge_pte_none(huge_ptep_get(ptep));
+		while (1) {
+			*vec = present;
+			vec++;
+			addr += PAGE_SIZE;
+			if (addr == end)
+				return;
+			/* check hugepage border */
+			if (!(addr & ~huge_page_mask(h)))
+				break;
+		}
+	}
+#else
+	BUG();
+#endif
+}
+
+/*
+ * Later we can get more picky about what "in core" means precisely.
+ * For now, simply check to see if the page is in the page cache,
+ * and is up to date; i.e. that no page-in operation would be required
+ * at this time if an application were to map and access this page.
+ */
+static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff)
+{
+	unsigned char present = 0;
+	struct page *page;
+
+	/*
+	 * When tmpfs swaps out a page from a file, any process mapping that
+	 * file will not get a swp_entry_t in its pte, but rather it is like
+	 * any other file mapping (ie. marked !present and faulted in with
+	 * tmpfs's .fault). So swapped out tmpfs mappings are tested here.
+	 */
+#ifdef CONFIG_SWAP
+	if (shmem_mapping(mapping)) {
+		page = find_get_entry(mapping, pgoff);
+		/*
+		 * shmem/tmpfs may return swap: account for swapcache
+		 * page too.
+		 */
+		if (radix_tree_exceptional_entry(page)) {
+			swp_entry_t swp = radix_to_swp_entry(page);
+			page = find_get_page(swap_address_space(swp), swp.val);
+		}
+	} else
+		page = find_get_page(mapping, pgoff);
+#else
+	page = find_get_page(mapping, pgoff);
+#endif
+	if (page) {
+		present = PageUptodate(page);
+		page_cache_release(page);
+	}
+
+	return present;
+}
+
+static void mincore_unmapped_range(struct vm_area_struct *vma,
+				unsigned long addr, unsigned long end,
+				unsigned char *vec)
+{
+	unsigned long nr = (end - addr) >> PAGE_SHIFT;
+	int i;
+
+	if (vma->vm_file) {
+		pgoff_t pgoff;
+
+		pgoff = linear_page_index(vma, addr);
+		for (i = 0; i < nr; i++, pgoff++)
+			vec[i] = mincore_page(vma->vm_file->f_mapping, pgoff);
+	} else {
+		for (i = 0; i < nr; i++)
+			vec[i] = 0;
+	}
+}
+
+static void mincore_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
+			unsigned long addr, unsigned long end,
+			unsigned char *vec)
+{
+	unsigned long next;
+	spinlock_t *ptl;
+	pte_t *ptep;
+
+	ptep = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+	do {
+		pte_t pte = *ptep;
+		pgoff_t pgoff;
+
+		next = addr + PAGE_SIZE;
+		if (pte_none(pte))
+			mincore_unmapped_range(vma, addr, next, vec);
+		else if (pte_present(pte))
+			*vec = 1;
+		else if (pte_file(pte)) {
+			pgoff = pte_to_pgoff(pte);
+			*vec = mincore_page(vma->vm_file->f_mapping, pgoff);
+		} else { /* pte is a swap entry */
+			swp_entry_t entry = pte_to_swp_entry(pte);
+
+			if (is_migration_entry(entry)) {
+				/* migration entries are always uptodate */
+				*vec = 1;
+			} else {
+#ifdef CONFIG_SWAP
+				pgoff = entry.val;
+				*vec = mincore_page(swap_address_space(entry),
+					pgoff);
+#else
+				WARN_ON(1);
+				*vec = 1;
+#endif
+			}
+		}
+		vec++;
+	} while (ptep++, addr = next, addr != end);
+	pte_unmap_unlock(ptep - 1, ptl);
+}
+
+static void mincore_pmd_range(struct vm_area_struct *vma, pud_t *pud,
+			unsigned long addr, unsigned long end,
+			unsigned char *vec)
+{
+	unsigned long next;
+	pmd_t *pmd;
+
+	pmd = pmd_offset(pud, addr);
+	do {
+		next = pmd_addr_end(addr, end);
+		if (pmd_trans_huge(*pmd)) {
+			if (mincore_huge_pmd(vma, pmd, addr, next, vec)) {
+				vec += (next - addr) >> PAGE_SHIFT;
+				continue;
+			}
+			/* fall through */
+		}
+		if (pmd_none_or_trans_huge_or_clear_bad(pmd))
+			mincore_unmapped_range(vma, addr, next, vec);
+		else
+			mincore_pte_range(vma, pmd, addr, next, vec);
+		vec += (next - addr) >> PAGE_SHIFT;
+	} while (pmd++, addr = next, addr != end);
+}
+
+static void mincore_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
+			unsigned long addr, unsigned long end,
+			unsigned char *vec)
+{
+	unsigned long next;
+	pud_t *pud;
+
+	pud = pud_offset(pgd, addr);
+	do {
+		next = pud_addr_end(addr, end);
+		if (pud_none_or_clear_bad(pud))
+			mincore_unmapped_range(vma, addr, next, vec);
+		else
+			mincore_pmd_range(vma, pud, addr, next, vec);
+		vec += (next - addr) >> PAGE_SHIFT;
+	} while (pud++, addr = next, addr != end);
+}
+
+static void mincore_page_range(struct vm_area_struct *vma,
+			unsigned long addr, unsigned long end,
+			unsigned char *vec)
+{
+	unsigned long next;
+	pgd_t *pgd;
+
+	pgd = pgd_offset(vma->vm_mm, addr);
+	do {
+		next = pgd_addr_end(addr, end);
+		if (pgd_none_or_clear_bad(pgd))
+			mincore_unmapped_range(vma, addr, next, vec);
+		else
+			mincore_pud_range(vma, pgd, addr, next, vec);
+		vec += (next - addr) >> PAGE_SHIFT;
+	} while (pgd++, addr = next, addr != end);
+}
+
+/*
+ * Do a chunk of "sys_mincore()". We've already checked
+ * all the arguments, we hold the mmap semaphore: we should
+ * just return the amount of info we're asked for.
+ */
+static long do_mincore(unsigned long addr, unsigned long pages, unsigned char *vec)
+{
+	struct vm_area_struct *vma;
+	unsigned long end;
+
+	vma = find_vma(current->mm, addr);
+	if (!vma || addr < vma->vm_start)
+		return -ENOMEM;
+
+	end = min(vma->vm_end, addr + (pages << PAGE_SHIFT));
+
+	if (is_vm_hugetlb_page(vma))
+		mincore_hugetlb_page_range(vma, addr, end, vec);
+	else
+		mincore_page_range(vma, addr, end, vec);
+
+	return (end - addr) >> PAGE_SHIFT;
+}
+
+/*
+ * The mincore(2) system call.
+ *
+ * mincore() returns the memory residency status of the pages in the
+ * current process's address space specified by [addr, addr + len).
+ * The status is returned in a vector of bytes.  The least significant
+ * bit of each byte is 1 if the referenced page is in memory, otherwise
+ * it is zero.
+ *
+ * Because the status of a page can change after mincore() checks it
+ * but before it returns to the application, the returned vector may
+ * contain stale information.  Only locked pages are guaranteed to
+ * remain in memory.
+ *
+ * return values:
+ *  zero    - success
+ *  -EFAULT - vec points to an illegal address
+ *  -EINVAL - addr is not a multiple of PAGE_CACHE_SIZE
+ *  -ENOMEM - Addresses in the range [addr, addr + len] are
+ *		invalid for the address space of this process, or
+ *		specify one or more pages which are not currently
+ *		mapped
+ *  -EAGAIN - A kernel resource was temporarily unavailable.
+ */
+SYSCALL_DEFINE3(mincore, unsigned long, start, size_t, len,
+		unsigned char __user *, vec)
+{
+	long retval;
+	unsigned long pages;
+	unsigned char *tmp;
+
+	/* Check the start address: needs to be page-aligned.. */
+ 	if (start & ~PAGE_CACHE_MASK)
+		return -EINVAL;
+
+	/* ..and we need to be passed a valid user-space range */
+	if (!access_ok(VERIFY_READ, (void __user *) start, len))
+		return -ENOMEM;
+
+	/* This also avoids any overflows on PAGE_CACHE_ALIGN */
+	pages = len >> PAGE_SHIFT;
+	pages += (len & ~PAGE_MASK) != 0;
+
+	if (!access_ok(VERIFY_WRITE, vec, pages))
+		return -EFAULT;
+
+	tmp = (void *) __get_free_page(GFP_USER);
+	if (!tmp)
+		return -EAGAIN;
+
+	retval = 0;
+	while (pages) {
+		/*
+		 * Do at most PAGE_SIZE entries per iteration, due to
+		 * the temporary buffer size.
+		 */
+		down_read(&current->mm->mmap_sem);
+		retval = do_mincore(start, min(pages, PAGE_SIZE), tmp);
+		up_read(&current->mm->mmap_sem);
+
+		if (retval <= 0)
+			break;
+		if (copy_to_user(vec, tmp, retval)) {
+			retval = -EFAULT;
+			break;
+		}
+		pages -= retval;
+		vec += retval;
+		start += retval << PAGE_SHIFT;
+		retval = 0;
+	}
+	free_page((unsigned long) tmp);
+	return retval;
+}

mm/mlock.c

@@ -0,0 +1,874 @@
+/*
+ *	linux/mm/mlock.c
+ *
+ *  (C) Copyright 1995 Linus Torvalds
+ *  (C) Copyright 2002 Christoph Hellwig
+ */
+
+#include <linux/capability.h>
+#include <linux/mman.h>
+#include <linux/mm.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
+#include <linux/pagemap.h>
+#include <linux/pagevec.h>
+#include <linux/mempolicy.h>
+#include <linux/syscalls.h>
+#include <linux/sched.h>
+#include <linux/export.h>
+#include <linux/rmap.h>
+#include <linux/mmzone.h>
+#include <linux/hugetlb.h>
+#include <linux/memcontrol.h>
+#include <linux/mm_inline.h>
+
+#include "internal.h"
+
+int can_do_mlock(void)
+{
+	if (capable(CAP_IPC_LOCK))
+		return 1;
+	if (rlimit(RLIMIT_MEMLOCK) != 0)
+		return 1;
+	return 0;
+}
+EXPORT_SYMBOL(can_do_mlock);
+
+/*
+ * Mlocked pages are marked with PageMlocked() flag for efficient testing
+ * in vmscan and, possibly, the fault path; and to support semi-accurate
+ * statistics.
+ *
+ * An mlocked page [PageMlocked(page)] is unevictable.  As such, it will
+ * be placed on the LRU "unevictable" list, rather than the [in]active lists.
+ * The unevictable list is an LRU sibling list to the [in]active lists.
+ * PageUnevictable is set to indicate the unevictable state.
+ *
+ * When lazy mlocking via vmscan, it is important to ensure that the
+ * vma's VM_LOCKED status is not concurrently being modified, otherwise we
+ * may have mlocked a page that is being munlocked. So lazy mlock must take
+ * the mmap_sem for read, and verify that the vma really is locked
+ * (see mm/rmap.c).
+ */
+
+/*
+ *  LRU accounting for clear_page_mlock()
+ */
+void clear_page_mlock(struct page *page)
+{
+	if (!TestClearPageMlocked(page))
+		return;
+
+	mod_zone_page_state(page_zone(page), NR_MLOCK,
+			    -hpage_nr_pages(page));
+	count_vm_event(UNEVICTABLE_PGCLEARED);
+	if (!isolate_lru_page(page)) {
+		putback_lru_page(page);
+	} else {
+		/*
+		 * We lost the race. the page already moved to evictable list.
+		 */
+		if (PageUnevictable(page))
+			count_vm_event(UNEVICTABLE_PGSTRANDED);
+	}
+}
+
+/*
+ * Mark page as mlocked if not already.
+ * If page on LRU, isolate and putback to move to unevictable list.
+ */
+void mlock_vma_page(struct page *page)
+{
+	/* Serialize with page migration */
+	BUG_ON(!PageLocked(page));
+
+	if (!TestSetPageMlocked(page)) {
+		mod_zone_page_state(page_zone(page), NR_MLOCK,
+				    hpage_nr_pages(page));
+		count_vm_event(UNEVICTABLE_PGMLOCKED);
+		if (!isolate_lru_page(page))
+			putback_lru_page(page);
+	}
+}
+
+/*
+ * Isolate a page from LRU with optional get_page() pin.
+ * Assumes lru_lock already held and page already pinned.
+ */
+static bool __munlock_isolate_lru_page(struct page *page, bool getpage)
+{
+	if (PageLRU(page)) {
+		struct lruvec *lruvec;
+
+		lruvec = mem_cgroup_page_lruvec(page, page_zone(page));
+		if (getpage)
+			get_page(page);
+		ClearPageLRU(page);
+		del_page_from_lru_list(page, lruvec, page_lru(page));
+		return true;
+	}
+
+	return false;
+}
+
+/*
+ * Finish munlock after successful page isolation
+ *
+ * Page must be locked. This is a wrapper for try_to_munlock()
+ * and putback_lru_page() with munlock accounting.
+ */
+static void __munlock_isolated_page(struct page *page)
+{
+	int ret = SWAP_AGAIN;
+
+	/*
+	 * Optimization: if the page was mapped just once, that's our mapping
+	 * and we don't need to check all the other vmas.
+	 */
+	if (page_mapcount(page) > 1)
+		ret = try_to_munlock(page);
+
+	/* Did try_to_unlock() succeed or punt? */
+	if (ret != SWAP_MLOCK)
+		count_vm_event(UNEVICTABLE_PGMUNLOCKED);
+
+	putback_lru_page(page);
+}
+
+/*
+ * Accounting for page isolation fail during munlock
+ *
+ * Performs accounting when page isolation fails in munlock. There is nothing
+ * else to do because it means some other task has already removed the page
+ * from the LRU. putback_lru_page() will take care of removing the page from
+ * the unevictable list, if necessary. vmscan [page_referenced()] will move
+ * the page back to the unevictable list if some other vma has it mlocked.
+ */
+static void __munlock_isolation_failed(struct page *page)
+{
+	if (PageUnevictable(page))
+		__count_vm_event(UNEVICTABLE_PGSTRANDED);
+	else
+		__count_vm_event(UNEVICTABLE_PGMUNLOCKED);
+}
+
+/**
+ * munlock_vma_page - munlock a vma page
+ * @page - page to be unlocked, either a normal page or THP page head
+ *
+ * returns the size of the page as a page mask (0 for normal page,
+ *         HPAGE_PMD_NR - 1 for THP head page)
+ *
+ * called from munlock()/munmap() path with page supposedly on the LRU.
+ * When we munlock a page, because the vma where we found the page is being
+ * munlock()ed or munmap()ed, we want to check whether other vmas hold the
+ * page locked so that we can leave it on the unevictable lru list and not
+ * bother vmscan with it.  However, to walk the page's rmap list in
+ * try_to_munlock() we must isolate the page from the LRU.  If some other
+ * task has removed the page from the LRU, we won't be able to do that.
+ * So we clear the PageMlocked as we might not get another chance.  If we
+ * can't isolate the page, we leave it for putback_lru_page() and vmscan
+ * [page_referenced()/try_to_unmap()] to deal with.
+ */
+unsigned int munlock_vma_page(struct page *page)
+{
+	unsigned int nr_pages;
+	struct zone *zone = page_zone(page);
+
+	/* For try_to_munlock() and to serialize with page migration */
+	BUG_ON(!PageLocked(page));
+
+	/*
+	 * Serialize with any parallel __split_huge_page_refcount() which
+	 * might otherwise copy PageMlocked to part of the tail pages before
+	 * we clear it in the head page. It also stabilizes hpage_nr_pages().
+	 */
+	spin_lock_irq(&zone->lru_lock);
+
+	nr_pages = hpage_nr_pages(page);
+	if (!TestClearPageMlocked(page))
+		goto unlock_out;
+
+	__mod_zone_page_state(zone, NR_MLOCK, -nr_pages);
+
+	if (__munlock_isolate_lru_page(page, true)) {
+		spin_unlock_irq(&zone->lru_lock);
+		__munlock_isolated_page(page);
+		goto out;
+	}
+	__munlock_isolation_failed(page);
+
+unlock_out:
+	spin_unlock_irq(&zone->lru_lock);
+
+out:
+	return nr_pages - 1;
+}
+
+/**
+ * __mlock_vma_pages_range() -  mlock a range of pages in the vma.
+ * @vma:   target vma
+ * @start: start address
+ * @end:   end address
+ * @nonblocking:
+ *
+ * This takes care of making the pages present too.
+ *
+ * return 0 on success, negative error code on error.
+ *
+ * vma->vm_mm->mmap_sem must be held.
+ *
+ * If @nonblocking is NULL, it may be held for read or write and will
+ * be unperturbed.
+ *
+ * If @nonblocking is non-NULL, it must held for read only and may be
+ * released.  If it's released, *@nonblocking will be set to 0.
+ */
+long __mlock_vma_pages_range(struct vm_area_struct *vma,
+		unsigned long start, unsigned long end, int *nonblocking)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	unsigned long nr_pages = (end - start) / PAGE_SIZE;
+	int gup_flags;
+
+	VM_BUG_ON(start & ~PAGE_MASK);
+	VM_BUG_ON(end   & ~PAGE_MASK);
+	VM_BUG_ON_VMA(start < vma->vm_start, vma);
+	VM_BUG_ON_VMA(end   > vma->vm_end, vma);
+	VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_sem), mm);
+
+	gup_flags = FOLL_TOUCH | FOLL_MLOCK;
+	/*
+	 * We want to touch writable mappings with a write fault in order
+	 * to break COW, except for shared mappings because these don't COW
+	 * and we would not want to dirty them for nothing.
+	 */
+	if ((vma->vm_flags & (VM_WRITE | VM_SHARED)) == VM_WRITE)
+		gup_flags |= FOLL_WRITE;
+
+	/*
+	 * We want mlock to succeed for regions that have any permissions
+	 * other than PROT_NONE.
+	 */
+	if (vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC))
+		gup_flags |= FOLL_FORCE;
+
+	/*
+	 * We made sure addr is within a VMA, so the following will
+	 * not result in a stack expansion that recurses back here.
+	 */
+	return __get_user_pages(current, mm, start, nr_pages, gup_flags,
+				NULL, NULL, nonblocking);
+}
+
+/*
+ * convert get_user_pages() return value to posix mlock() error
+ */
+static int __mlock_posix_error_return(long retval)
+{
+	if (retval == -EFAULT)
+		retval = -ENOMEM;
+	else if (retval == -ENOMEM)
+		retval = -EAGAIN;
+	return retval;
+}
+
+/*
+ * Prepare page for fast batched LRU putback via putback_lru_evictable_pagevec()
+ *
+ * The fast path is available only for evictable pages with single mapping.
+ * Then we can bypass the per-cpu pvec and get better performance.
+ * when mapcount > 1 we need try_to_munlock() which can fail.
+ * when !page_evictable(), we need the full redo logic of putback_lru_page to
+ * avoid leaving evictable page in unevictable list.
+ *
+ * In case of success, @page is added to @pvec and @pgrescued is incremented
+ * in case that the page was previously unevictable. @page is also unlocked.
+ */
+static bool __putback_lru_fast_prepare(struct page *page, struct pagevec *pvec,
+		int *pgrescued)
+{
+	VM_BUG_ON_PAGE(PageLRU(page), page);
+	VM_BUG_ON_PAGE(!PageLocked(page), page);
+
+	if (page_mapcount(page) <= 1 && page_evictable(page)) {
+		pagevec_add(pvec, page);
+		if (TestClearPageUnevictable(page))
+			(*pgrescued)++;
+		unlock_page(page);
+		return true;
+	}
+
+	return false;
+}
+
+/*
+ * Putback multiple evictable pages to the LRU
+ *
+ * Batched putback of evictable pages that bypasses the per-cpu pvec. Some of
+ * the pages might have meanwhile become unevictable but that is OK.
+ */
+static void __putback_lru_fast(struct pagevec *pvec, int pgrescued)
+{
+	count_vm_events(UNEVICTABLE_PGMUNLOCKED, pagevec_count(pvec));
+	/*
+	 *__pagevec_lru_add() calls release_pages() so we don't call
+	 * put_page() explicitly
+	 */
+	__pagevec_lru_add(pvec);
+	count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued);
+}
+
+/*
+ * Munlock a batch of pages from the same zone
+ *
+ * The work is split to two main phases. First phase clears the Mlocked flag
+ * and attempts to isolate the pages, all under a single zone lru lock.
+ * The second phase finishes the munlock only for pages where isolation
+ * succeeded.
+ *
+ * Note that the pagevec may be modified during the process.
+ */
+static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
+{
+	int i;
+	int nr = pagevec_count(pvec);
+	int delta_munlocked;
+	struct pagevec pvec_putback;
+	int pgrescued = 0;
+
+	pagevec_init(&pvec_putback, 0);
+
+	/* Phase 1: page isolation */
+	spin_lock_irq(&zone->lru_lock);
+	for (i = 0; i < nr; i++) {
+		struct page *page = pvec->pages[i];
+
+		if (TestClearPageMlocked(page)) {
+			/*
+			 * We already have pin from follow_page_mask()
+			 * so we can spare the get_page() here.
+			 */
+			if (__munlock_isolate_lru_page(page, false))
+				continue;
+			else
+				__munlock_isolation_failed(page);
+		}
+
+		/*
+		 * We won't be munlocking this page in the next phase
+		 * but we still need to release the follow_page_mask()
+		 * pin. We cannot do it under lru_lock however. If it's
+		 * the last pin, __page_cache_release() would deadlock.
+		 */
+		pagevec_add(&pvec_putback, pvec->pages[i]);
+		pvec->pages[i] = NULL;
+	}
+	delta_munlocked = -nr + pagevec_count(&pvec_putback);
+	__mod_zone_page_state(zone, NR_MLOCK, delta_munlocked);
+	spin_unlock_irq(&zone->lru_lock);
+
+	/* Now we can release pins of pages that we are not munlocking */
+	pagevec_release(&pvec_putback);
+
+	/* Phase 2: page munlock */
+	for (i = 0; i < nr; i++) {
+		struct page *page = pvec->pages[i];
+
+		if (page) {
+			lock_page(page);
+			if (!__putback_lru_fast_prepare(page, &pvec_putback,
+					&pgrescued)) {
+				/*
+				 * Slow path. We don't want to lose the last
+				 * pin before unlock_page()
+				 */
+				get_page(page); /* for putback_lru_page() */
+				__munlock_isolated_page(page);
+				unlock_page(page);
+				put_page(page); /* from follow_page_mask() */
+			}
+		}
+	}
+
+	/*
+	 * Phase 3: page putback for pages that qualified for the fast path
+	 * This will also call put_page() to return pin from follow_page_mask()
+	 */
+	if (pagevec_count(&pvec_putback))
+		__putback_lru_fast(&pvec_putback, pgrescued);
+}
+
+/*
+ * Fill up pagevec for __munlock_pagevec using pte walk
+ *
+ * The function expects that the struct page corresponding to @start address is
+ * a non-TPH page already pinned and in the @pvec, and that it belongs to @zone.
+ *
+ * The rest of @pvec is filled by subsequent pages within the same pmd and same
+ * zone, as long as the pte's are present and vm_normal_page() succeeds. These
+ * pages also get pinned.
+ *
+ * Returns the address of the next page that should be scanned. This equals
+ * @start + PAGE_SIZE when no page could be added by the pte walk.
+ */
+static unsigned long __munlock_pagevec_fill(struct pagevec *pvec,
+		struct vm_area_struct *vma, int zoneid,	unsigned long start,
+		unsigned long end)
+{
+	pte_t *pte;
+	spinlock_t *ptl;
+
+	/*
+	 * Initialize pte walk starting at the already pinned page where we
+	 * are sure that there is a pte, as it was pinned under the same
+	 * mmap_sem write op.
+	 */
+	pte = get_locked_pte(vma->vm_mm, start,	&ptl);
+	/* Make sure we do not cross the page table boundary */
+	end = pgd_addr_end(start, end);
+	end = pud_addr_end(start, end);
+	end = pmd_addr_end(start, end);
+
+	/* The page next to the pinned page is the first we will try to get */
+	start += PAGE_SIZE;
+	while (start < end) {
+		struct page *page = NULL;
+		pte++;
+		if (pte_present(*pte))
+			page = vm_normal_page(vma, start, *pte);
+		/*
+		 * Break if page could not be obtained or the page's node+zone does not
+		 * match
+		 */
+		if (!page || page_zone_id(page) != zoneid)
+			break;
+
+		get_page(page);
+		/*
+		 * Increase the address that will be returned *before* the
+		 * eventual break due to pvec becoming full by adding the page
+		 */
+		start += PAGE_SIZE;
+		if (pagevec_add(pvec, page) == 0)
+			break;
+	}
+	pte_unmap_unlock(pte, ptl);
+	return start;
+}
+
+/*
+ * munlock_vma_pages_range() - munlock all pages in the vma range.'
+ * @vma - vma containing range to be munlock()ed.
+ * @start - start address in @vma of the range
+ * @end - end of range in @vma.
+ *
+ *  For mremap(), munmap() and exit().
+ *
+ * Called with @vma VM_LOCKED.
+ *
+ * Returns with VM_LOCKED cleared.  Callers must be prepared to
+ * deal with this.
+ *
+ * We don't save and restore VM_LOCKED here because pages are
+ * still on lru.  In unmap path, pages might be scanned by reclaim
+ * and re-mlocked by try_to_{munlock|unmap} before we unmap and
+ * free them.  This will result in freeing mlocked pages.
+ */
+void munlock_vma_pages_range(struct vm_area_struct *vma,
+			     unsigned long start, unsigned long end)
+{
+	vma->vm_flags &= ~VM_LOCKED;
+
+	while (start < end) {
+		struct page *page = NULL;
+		unsigned int page_mask;
+		unsigned long page_increm;
+		struct pagevec pvec;
+		struct zone *zone;
+		int zoneid;
+
+		pagevec_init(&pvec, 0);
+		/*
+		 * Although FOLL_DUMP is intended for get_dump_page(),
+		 * it just so happens that its special treatment of the
+		 * ZERO_PAGE (returning an error instead of doing get_page)
+		 * suits munlock very well (and if somehow an abnormal page
+		 * has sneaked into the range, we won't oops here: great).
+		 */
+		page = follow_page_mask(vma, start, FOLL_GET | FOLL_DUMP,
+				&page_mask);
+
+		if (page && !IS_ERR(page)) {
+			if (PageTransHuge(page)) {
+				lock_page(page);
+				/*
+				 * Any THP page found by follow_page_mask() may
+				 * have gotten split before reaching
+				 * munlock_vma_page(), so we need to recompute
+				 * the page_mask here.
+				 */
+				page_mask = munlock_vma_page(page);
+				unlock_page(page);
+				put_page(page); /* follow_page_mask() */
+			} else {
+				/*
+				 * Non-huge pages are handled in batches via
+				 * pagevec. The pin from follow_page_mask()
+				 * prevents them from collapsing by THP.
+				 */
+				pagevec_add(&pvec, page);
+				zone = page_zone(page);
+				zoneid = page_zone_id(page);
+
+				/*
+				 * Try to fill the rest of pagevec using fast
+				 * pte walk. This will also update start to
+				 * the next page to process. Then munlock the
+				 * pagevec.
+				 */
+				start = __munlock_pagevec_fill(&pvec, vma,
+						zoneid, start, end);
+				__munlock_pagevec(&pvec, zone);
+				goto next;
+			}
+		}
+		/* It's a bug to munlock in the middle of a THP page */
+		VM_BUG_ON((start >> PAGE_SHIFT) & page_mask);
+		page_increm = 1 + page_mask;
+		start += page_increm * PAGE_SIZE;
+next:
+		cond_resched();
+	}
+}
+
+/*
+ * mlock_fixup  - handle mlock[all]/munlock[all] requests.
+ *
+ * Filters out "special" vmas -- VM_LOCKED never gets set for these, and
+ * munlock is a no-op.  However, for some special vmas, we go ahead and
+ * populate the ptes.
+ *
+ * For vmas that pass the filters, merge/split as appropriate.
+ */
+static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev,
+	unsigned long start, unsigned long end, vm_flags_t newflags)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	pgoff_t pgoff;
+	int nr_pages;
+	int ret = 0;
+	int lock = !!(newflags & VM_LOCKED);
+
+	if (newflags == vma->vm_flags || (vma->vm_flags & VM_SPECIAL) ||
+	    is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm))
+		goto out;	/* don't set VM_LOCKED,  don't count */
+
+	pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
+	*prev = vma_merge(mm, *prev, start, end, newflags, vma->anon_vma,
+			  vma->vm_file, pgoff, vma_policy(vma),
+			  vma_get_anon_name(vma));
+	if (*prev) {
+		vma = *prev;
+		goto success;
+	}
+
+	if (start != vma->vm_start) {
+		ret = split_vma(mm, vma, start, 1);
+		if (ret)
+			goto out;
+	}
+
+	if (end != vma->vm_end) {
+		ret = split_vma(mm, vma, end, 0);
+		if (ret)
+			goto out;
+	}
+
+success:
+	/*
+	 * Keep track of amount of locked VM.
+	 */
+	nr_pages = (end - start) >> PAGE_SHIFT;
+	if (!lock)
+		nr_pages = -nr_pages;
+	mm->locked_vm += nr_pages;
+
+	/*
+	 * vm_flags is protected by the mmap_sem held in write mode.
+	 * It's okay if try_to_unmap_one unmaps a page just after we
+	 * set VM_LOCKED, __mlock_vma_pages_range will bring it back.
+	 */
+
+	if (lock)
+		vma->vm_flags = newflags;
+	else
+		munlock_vma_pages_range(vma, start, end);
+
+out:
+	*prev = vma;
+	return ret;
+}
+
+static int do_mlock(unsigned long start, size_t len, int on)
+{
+	unsigned long nstart, end, tmp;
+	struct vm_area_struct * vma, * prev;
+	int error;
+
+	VM_BUG_ON(start & ~PAGE_MASK);
+	VM_BUG_ON(len != PAGE_ALIGN(len));
+	end = start + len;
+	if (end < start)
+		return -EINVAL;
+	if (end == start)
+		return 0;
+	vma = find_vma(current->mm, start);
+	if (!vma || vma->vm_start > start)
+		return -ENOMEM;
+
+	prev = vma->vm_prev;
+	if (start > vma->vm_start)
+		prev = vma;
+
+	for (nstart = start ; ; ) {
+		vm_flags_t newflags;
+
+		/* Here we know that  vma->vm_start <= nstart < vma->vm_end. */
+
+		newflags = vma->vm_flags & ~VM_LOCKED;
+		if (on)
+			newflags |= VM_LOCKED;
+
+		tmp = vma->vm_end;
+		if (tmp > end)
+			tmp = end;
+		error = mlock_fixup(vma, &prev, nstart, tmp, newflags);
+		if (error)
+			break;
+		nstart = tmp;
+		if (nstart < prev->vm_end)
+			nstart = prev->vm_end;
+		if (nstart >= end)
+			break;
+
+		vma = prev->vm_next;
+		if (!vma || vma->vm_start != nstart) {
+			error = -ENOMEM;
+			break;
+		}
+	}
+	return error;
+}
+
+/*
+ * __mm_populate - populate and/or mlock pages within a range of address space.
+ *
+ * This is used to implement mlock() and the MAP_POPULATE / MAP_LOCKED mmap
+ * flags. VMAs must be already marked with the desired vm_flags, and
+ * mmap_sem must not be held.
+ */
+int __mm_populate(unsigned long start, unsigned long len, int ignore_errors)
+{
+	struct mm_struct *mm = current->mm;
+	unsigned long end, nstart, nend;
+	struct vm_area_struct *vma = NULL;
+	int locked = 0;
+	long ret = 0;
+
+	VM_BUG_ON(start & ~PAGE_MASK);
+	VM_BUG_ON(len != PAGE_ALIGN(len));
+	end = start + len;
+
+	for (nstart = start; nstart < end; nstart = nend) {
+		/*
+		 * We want to fault in pages for [nstart; end) address range.
+		 * Find first corresponding VMA.
+		 */
+		if (!locked) {
+			locked = 1;
+			down_read(&mm->mmap_sem);
+			vma = find_vma(mm, nstart);
+		} else if (nstart >= vma->vm_end)
+			vma = vma->vm_next;
+		if (!vma || vma->vm_start >= end)
+			break;
+		/*
+		 * Set [nstart; nend) to intersection of desired address
+		 * range with the first VMA. Also, skip undesirable VMA types.
+		 */
+		nend = min(end, vma->vm_end);
+		if (vma->vm_flags & (VM_IO | VM_PFNMAP))
+			continue;
+		if (nstart < vma->vm_start)
+			nstart = vma->vm_start;
+		/*
+		 * Now fault in a range of pages. __mlock_vma_pages_range()
+		 * double checks the vma flags, so that it won't mlock pages
+		 * if the vma was already munlocked.
+		 */
+		ret = __mlock_vma_pages_range(vma, nstart, nend, &locked);
+		if (ret < 0) {
+			if (ignore_errors) {
+				ret = 0;
+				continue;	/* continue at next VMA */
+			}
+			ret = __mlock_posix_error_return(ret);
+			break;
+		}
+		nend = nstart + ret * PAGE_SIZE;
+		ret = 0;
+	}
+	if (locked)
+		up_read(&mm->mmap_sem);
+	return ret;	/* 0 or negative error code */
+}
+
+SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len)
+{
+	unsigned long locked;
+	unsigned long lock_limit;
+	int error = -ENOMEM;
+
+	if (!can_do_mlock())
+		return -EPERM;
+
+	lru_add_drain_all();	/* flush pagevec */
+
+	len = PAGE_ALIGN(len + (start & ~PAGE_MASK));
+	start &= PAGE_MASK;
+
+	lock_limit = rlimit(RLIMIT_MEMLOCK);
+	lock_limit >>= PAGE_SHIFT;
+	locked = len >> PAGE_SHIFT;
+
+	down_write(&current->mm->mmap_sem);
+
+	locked += current->mm->locked_vm;
+
+	/* check against resource limits */
+	if ((locked <= lock_limit) || capable(CAP_IPC_LOCK))
+		error = do_mlock(start, len, 1);
+
+	up_write(&current->mm->mmap_sem);
+	if (!error)
+		error = __mm_populate(start, len, 0);
+	return error;
+}
+
+SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len)
+{
+	int ret;
+
+	len = PAGE_ALIGN(len + (start & ~PAGE_MASK));
+	start &= PAGE_MASK;
+
+	down_write(&current->mm->mmap_sem);
+	ret = do_mlock(start, len, 0);
+	up_write(&current->mm->mmap_sem);
+
+	return ret;
+}
+
+static int do_mlockall(int flags)
+{
+	struct vm_area_struct * vma, * prev = NULL;
+
+	if (flags & MCL_FUTURE)
+		current->mm->def_flags |= VM_LOCKED;
+	else
+		current->mm->def_flags &= ~VM_LOCKED;
+	if (flags == MCL_FUTURE)
+		goto out;
+
+	for (vma = current->mm->mmap; vma ; vma = prev->vm_next) {
+		vm_flags_t newflags;
+
+		newflags = vma->vm_flags & ~VM_LOCKED;
+		if (flags & MCL_CURRENT)
+			newflags |= VM_LOCKED;
+
+		/* Ignore errors */
+		mlock_fixup(vma, &prev, vma->vm_start, vma->vm_end, newflags);
+		cond_resched_rcu_qs();
+	}
+out:
+	return 0;
+}
+
+SYSCALL_DEFINE1(mlockall, int, flags)
+{
+	unsigned long lock_limit;
+	int ret = -EINVAL;
+
+	if (!flags || (flags & ~(MCL_CURRENT | MCL_FUTURE)))
+		goto out;
+
+	ret = -EPERM;
+	if (!can_do_mlock())
+		goto out;
+
+	if (flags & MCL_CURRENT)
+		lru_add_drain_all();	/* flush pagevec */
+
+	lock_limit = rlimit(RLIMIT_MEMLOCK);
+	lock_limit >>= PAGE_SHIFT;
+
+	ret = -ENOMEM;
+	down_write(&current->mm->mmap_sem);
+
+	if (!(flags & MCL_CURRENT) || (current->mm->total_vm <= lock_limit) ||
+	    capable(CAP_IPC_LOCK))
+		ret = do_mlockall(flags);
+	up_write(&current->mm->mmap_sem);
+	if (!ret && (flags & MCL_CURRENT))
+		mm_populate(0, TASK_SIZE);
+out:
+	return ret;
+}
+
+SYSCALL_DEFINE0(munlockall)
+{
+	int ret;
+
+	down_write(&current->mm->mmap_sem);
+	ret = do_mlockall(0);
+	up_write(&current->mm->mmap_sem);
+	return ret;
+}
+
+/*
+ * Objects with different lifetime than processes (SHM_LOCK and SHM_HUGETLB
+ * shm segments) get accounted against the user_struct instead.
+ */
+static DEFINE_SPINLOCK(shmlock_user_lock);
+
+int user_shm_lock(size_t size, struct user_struct *user)
+{
+	unsigned long lock_limit, locked;
+	int allowed = 0;
+
+	locked = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	lock_limit = rlimit(RLIMIT_MEMLOCK);
+	if (lock_limit == RLIM_INFINITY)
+		allowed = 1;
+	lock_limit >>= PAGE_SHIFT;
+	spin_lock(&shmlock_user_lock);
+	if (!allowed &&
+	    locked + user->locked_shm > lock_limit && !capable(CAP_IPC_LOCK))
+		goto out;
+	get_uid(user);
+	user->locked_shm += locked;
+	allowed = 1;
+out:
+	spin_unlock(&shmlock_user_lock);
+	return allowed;
+}
+
+void user_shm_unlock(size_t size, struct user_struct *user)
+{
+	spin_lock(&shmlock_user_lock);
+	user->locked_shm -= (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	spin_unlock(&shmlock_user_lock);
+	free_uid(user);
+}

mm/mm_init.c

@@ -0,0 +1,205 @@
+/*
+ * mm_init.c - Memory initialisation verification and debugging
+ *
+ * Copyright 2008 IBM Corporation, 2008
+ * Author Mel Gorman <mel@csn.ul.ie>
+ *
+ */
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/kobject.h>
+#include <linux/export.h>
+#include <linux/memory.h>
+#include <linux/notifier.h>
+#include "internal.h"
+
+#ifdef CONFIG_DEBUG_MEMORY_INIT
+int mminit_loglevel;
+
+#ifndef SECTIONS_SHIFT
+#define SECTIONS_SHIFT	0
+#endif
+
+/* The zonelists are simply reported, validation is manual. */
+void mminit_verify_zonelist(void)
+{
+	int nid;
+
+	if (mminit_loglevel < MMINIT_VERIFY)
+		return;
+
+	for_each_online_node(nid) {
+		pg_data_t *pgdat = NODE_DATA(nid);
+		struct zone *zone;
+		struct zoneref *z;
+		struct zonelist *zonelist;
+		int i, listid, zoneid;
+
+		BUG_ON(MAX_ZONELISTS > 2);
+		for (i = 0; i < MAX_ZONELISTS * MAX_NR_ZONES; i++) {
+
+			/* Identify the zone and nodelist */
+			zoneid = i % MAX_NR_ZONES;
+			listid = i / MAX_NR_ZONES;
+			zonelist = &pgdat->node_zonelists[listid];
+			zone = &pgdat->node_zones[zoneid];
+			if (!populated_zone(zone))
+				continue;
+
+			/* Print information about the zonelist */
+			printk(KERN_DEBUG "mminit::zonelist %s %d:%s = ",
+				listid > 0 ? "thisnode" : "general", nid,
+				zone->name);
+
+			/* Iterate the zonelist */
+			for_each_zone_zonelist(zone, z, zonelist, zoneid) {
+#ifdef CONFIG_NUMA
+				printk(KERN_CONT "%d:%s ",
+					zone->node, zone->name);
+#else
+				printk(KERN_CONT "0:%s ", zone->name);
+#endif /* CONFIG_NUMA */
+			}
+			printk(KERN_CONT "\n");
+		}
+	}
+}
+
+void __init mminit_verify_pageflags_layout(void)
+{
+	int shift, width;
+	unsigned long or_mask, add_mask;
+
+	shift = 8 * sizeof(unsigned long);
+	width = shift - SECTIONS_WIDTH - NODES_WIDTH - ZONES_WIDTH - LAST_CPUPID_SHIFT;
+	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_widths",
+		"Section %d Node %d Zone %d Lastcpupid %d Flags %d\n",
+		SECTIONS_WIDTH,
+		NODES_WIDTH,
+		ZONES_WIDTH,
+		LAST_CPUPID_WIDTH,
+		NR_PAGEFLAGS);
+	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_shifts",
+		"Section %d Node %d Zone %d Lastcpupid %d\n",
+		SECTIONS_SHIFT,
+		NODES_SHIFT,
+		ZONES_SHIFT,
+		LAST_CPUPID_SHIFT);
+	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_pgshifts",
+		"Section %lu Node %lu Zone %lu Lastcpupid %lu\n",
+		(unsigned long)SECTIONS_PGSHIFT,
+		(unsigned long)NODES_PGSHIFT,
+		(unsigned long)ZONES_PGSHIFT,
+		(unsigned long)LAST_CPUPID_PGSHIFT);
+	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodezoneid",
+		"Node/Zone ID: %lu -> %lu\n",
+		(unsigned long)(ZONEID_PGOFF + ZONEID_SHIFT),
+		(unsigned long)ZONEID_PGOFF);
+	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_usage",
+		"location: %d -> %d layout %d -> %d unused %d -> %d page-flags\n",
+		shift, width, width, NR_PAGEFLAGS, NR_PAGEFLAGS, 0);
+#ifdef NODE_NOT_IN_PAGE_FLAGS
+	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodeflags",
+		"Node not in page flags");
+#endif
+#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
+	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodeflags",
+		"Last cpupid not in page flags");
+#endif
+
+	if (SECTIONS_WIDTH) {
+		shift -= SECTIONS_WIDTH;
+		BUG_ON(shift != SECTIONS_PGSHIFT);
+	}
+	if (NODES_WIDTH) {
+		shift -= NODES_WIDTH;
+		BUG_ON(shift != NODES_PGSHIFT);
+	}
+	if (ZONES_WIDTH) {
+		shift -= ZONES_WIDTH;
+		BUG_ON(shift != ZONES_PGSHIFT);
+	}
+
+	/* Check for bitmask overlaps */
+	or_mask = (ZONES_MASK << ZONES_PGSHIFT) |
+			(NODES_MASK << NODES_PGSHIFT) |
+			(SECTIONS_MASK << SECTIONS_PGSHIFT);
+	add_mask = (ZONES_MASK << ZONES_PGSHIFT) +
+			(NODES_MASK << NODES_PGSHIFT) +
+			(SECTIONS_MASK << SECTIONS_PGSHIFT);
+	BUG_ON(or_mask != add_mask);
+}
+
+void __meminit mminit_verify_page_links(struct page *page, enum zone_type zone,
+			unsigned long nid, unsigned long pfn)
+{
+	BUG_ON(page_to_nid(page) != nid);
+	BUG_ON(page_zonenum(page) != zone);
+	BUG_ON(page_to_pfn(page) != pfn);
+}
+
+static __init int set_mminit_loglevel(char *str)
+{
+	get_option(&str, &mminit_loglevel);
+	return 0;
+}
+early_param("mminit_loglevel", set_mminit_loglevel);
+#endif /* CONFIG_DEBUG_MEMORY_INIT */
+
+struct kobject *mm_kobj;
+EXPORT_SYMBOL_GPL(mm_kobj);
+
+#ifdef CONFIG_SMP
+s32 vm_committed_as_batch = 32;
+
+static void __meminit mm_compute_batch(void)
+{
+	u64 memsized_batch;
+	s32 nr = num_present_cpus();
+	s32 batch = max_t(s32, nr*2, 32);
+
+	/* batch size set to 0.4% of (total memory/#cpus), or max int32 */
+	memsized_batch = min_t(u64, (totalram_pages/nr)/256, 0x7fffffff);
+
+	vm_committed_as_batch = max_t(s32, memsized_batch, batch);
+}
+
+static int __meminit mm_compute_batch_notifier(struct notifier_block *self,
+					unsigned long action, void *arg)
+{
+	switch (action) {
+	case MEM_ONLINE:
+	case MEM_OFFLINE:
+		mm_compute_batch();
+	default:
+		break;
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block compute_batch_nb __meminitdata = {
+	.notifier_call = mm_compute_batch_notifier,
+	.priority = IPC_CALLBACK_PRI, /* use lowest priority */
+};
+
+static int __init mm_compute_batch_init(void)
+{
+	mm_compute_batch();
+	register_hotmemory_notifier(&compute_batch_nb);
+
+	return 0;
+}
+
+__initcall(mm_compute_batch_init);
+
+#endif
+
+static int __init mm_sysfs_init(void)
+{
+	mm_kobj = kobject_create_and_add("mm", kernel_kobj);
+	if (!mm_kobj)
+		return -ENOMEM;
+
+	return 0;
+}
+postcore_initcall(mm_sysfs_init);

mm/mmu_context.c

@@ -0,0 +1,62 @@
+/* Copyright (C) 2009 Red Hat, Inc.
+ *
+ * See ../COPYING for licensing terms.
+ */
+
+#include <linux/mm.h>
+#include <linux/mmu_context.h>
+#include <linux/export.h>
+#include <linux/sched.h>
+
+#include <asm/mmu_context.h>
+
+/*
+ * use_mm
+ *	Makes the calling kernel thread take on the specified
+ *	mm context.
+ *	(Note: this routine is intended to be called only
+ *	from a kernel thread context)
+ */
+void use_mm(struct mm_struct *mm)
+{
+	struct mm_struct *active_mm;
+	struct task_struct *tsk = current;
+
+	task_lock(tsk);
+	active_mm = tsk->active_mm;
+	if (active_mm != mm) {
+		atomic_inc(&mm->mm_count);
+		tsk->active_mm = mm;
+	}
+	tsk->mm = mm;
+	switch_mm(active_mm, mm, tsk);
+	task_unlock(tsk);
+#ifdef finish_arch_post_lock_switch
+	finish_arch_post_lock_switch();
+#endif
+
+	if (active_mm != mm)
+		mmdrop(active_mm);
+}
+EXPORT_SYMBOL_GPL(use_mm);
+
+/*
+ * unuse_mm
+ *	Reverses the effect of use_mm, i.e. releases the
+ *	specified mm context which was earlier taken on
+ *	by the calling kernel thread
+ *	(Note: this routine is intended to be called only
+ *	from a kernel thread context)
+ */
+void unuse_mm(struct mm_struct *mm)
+{
+	struct task_struct *tsk = current;
+
+	task_lock(tsk);
+	sync_mm_rss(mm);
+	tsk->mm = NULL;
+	/* active_mm is still 'mm' */
+	enter_lazy_tlb(mm, tsk);
+	task_unlock(tsk);
+}
+EXPORT_SYMBOL_GPL(unuse_mm);

mm/mmu_notifier.c

@@ -0,0 +1,371 @@
+/*
+ *  linux/mm/mmu_notifier.c
+ *
+ *  Copyright (C) 2008  Qumranet, Inc.
+ *  Copyright (C) 2008  SGI
+ *             Christoph Lameter <clameter@sgi.com>
+ *
+ *  This work is licensed under the terms of the GNU GPL, version 2. See
+ *  the COPYING file in the top-level directory.
+ */
+
+#include <linux/rculist.h>
+#include <linux/mmu_notifier.h>
+#include <linux/export.h>
+#include <linux/mm.h>
+#include <linux/err.h>
+#include <linux/srcu.h>
+#include <linux/rcupdate.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+
+/* global SRCU for all MMs */
+static struct srcu_struct srcu;
+
+/*
+ * This function allows mmu_notifier::release callback to delay a call to
+ * a function that will free appropriate resources. The function must be
+ * quick and must not block.
+ */
+void mmu_notifier_call_srcu(struct rcu_head *rcu,
+			    void (*func)(struct rcu_head *rcu))
+{
+	call_srcu(&srcu, rcu, func);
+}
+EXPORT_SYMBOL_GPL(mmu_notifier_call_srcu);
+
+void mmu_notifier_synchronize(void)
+{
+	/* Wait for any running method to finish. */
+	srcu_barrier(&srcu);
+}
+EXPORT_SYMBOL_GPL(mmu_notifier_synchronize);
+
+/*
+ * This function can't run concurrently against mmu_notifier_register
+ * because mm->mm_users > 0 during mmu_notifier_register and exit_mmap
+ * runs with mm_users == 0. Other tasks may still invoke mmu notifiers
+ * in parallel despite there being no task using this mm any more,
+ * through the vmas outside of the exit_mmap context, such as with
+ * vmtruncate. This serializes against mmu_notifier_unregister with
+ * the mmu_notifier_mm->lock in addition to SRCU and it serializes
+ * against the other mmu notifiers with SRCU. struct mmu_notifier_mm
+ * can't go away from under us as exit_mmap holds an mm_count pin
+ * itself.
+ */
+void __mmu_notifier_release(struct mm_struct *mm)
+{
+	struct mmu_notifier *mn;
+	int id;
+
+	/*
+	 * SRCU here will block mmu_notifier_unregister until
+	 * ->release returns.
+	 */
+	id = srcu_read_lock(&srcu);
+	hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist)
+		/*
+		 * If ->release runs before mmu_notifier_unregister it must be
+		 * handled, as it's the only way for the driver to flush all
+		 * existing sptes and stop the driver from establishing any more
+		 * sptes before all the pages in the mm are freed.
+		 */
+		if (mn->ops->release)
+			mn->ops->release(mn, mm);
+
+	spin_lock(&mm->mmu_notifier_mm->lock);
+	while (unlikely(!hlist_empty(&mm->mmu_notifier_mm->list))) {
+		mn = hlist_entry(mm->mmu_notifier_mm->list.first,
+				 struct mmu_notifier,
+				 hlist);
+		/*
+		 * We arrived before mmu_notifier_unregister so
+		 * mmu_notifier_unregister will do nothing other than to wait
+		 * for ->release to finish and for mmu_notifier_unregister to
+		 * return.
+		 */
+		hlist_del_init_rcu(&mn->hlist);
+	}
+	spin_unlock(&mm->mmu_notifier_mm->lock);
+	srcu_read_unlock(&srcu, id);
+
+	/*
+	 * synchronize_srcu here prevents mmu_notifier_release from returning to
+	 * exit_mmap (which would proceed with freeing all pages in the mm)
+	 * until the ->release method returns, if it was invoked by
+	 * mmu_notifier_unregister.
+	 *
+	 * The mmu_notifier_mm can't go away from under us because one mm_count
+	 * is held by exit_mmap.
+	 */
+	synchronize_srcu(&srcu);
+}
+
+/*
+ * If no young bitflag is supported by the hardware, ->clear_flush_young can
+ * unmap the address and return 1 or 0 depending if the mapping previously
+ * existed or not.
+ */
+int __mmu_notifier_clear_flush_young(struct mm_struct *mm,
+					unsigned long start,
+					unsigned long end)
+{
+	struct mmu_notifier *mn;
+	int young = 0, id;
+
+	id = srcu_read_lock(&srcu);
+	hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
+		if (mn->ops->clear_flush_young)
+			young |= mn->ops->clear_flush_young(mn, mm, start, end);
+	}
+	srcu_read_unlock(&srcu, id);
+
+	return young;
+}
+
+int __mmu_notifier_test_young(struct mm_struct *mm,
+			      unsigned long address)
+{
+	struct mmu_notifier *mn;
+	int young = 0, id;
+
+	id = srcu_read_lock(&srcu);
+	hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
+		if (mn->ops->test_young) {
+			young = mn->ops->test_young(mn, mm, address);
+			if (young)
+				break;
+		}
+	}
+	srcu_read_unlock(&srcu, id);
+
+	return young;
+}
+
+void __mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address,
+			       pte_t pte)
+{
+	struct mmu_notifier *mn;
+	int id;
+
+	id = srcu_read_lock(&srcu);
+	hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
+		if (mn->ops->change_pte)
+			mn->ops->change_pte(mn, mm, address, pte);
+	}
+	srcu_read_unlock(&srcu, id);
+}
+
+void __mmu_notifier_invalidate_page(struct mm_struct *mm,
+					  unsigned long address)
+{
+	struct mmu_notifier *mn;
+	int id;
+
+	id = srcu_read_lock(&srcu);
+	hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
+		if (mn->ops->invalidate_page)
+			mn->ops->invalidate_page(mn, mm, address);
+	}
+	srcu_read_unlock(&srcu, id);
+}
+
+void __mmu_notifier_invalidate_range_start(struct mm_struct *mm,
+				  unsigned long start, unsigned long end)
+{
+	struct mmu_notifier *mn;
+	int id;
+
+	id = srcu_read_lock(&srcu);
+	hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
+		if (mn->ops->invalidate_range_start)
+			mn->ops->invalidate_range_start(mn, mm, start, end);
+	}
+	srcu_read_unlock(&srcu, id);
+}
+EXPORT_SYMBOL_GPL(__mmu_notifier_invalidate_range_start);
+
+void __mmu_notifier_invalidate_range_end(struct mm_struct *mm,
+				  unsigned long start, unsigned long end)
+{
+	struct mmu_notifier *mn;
+	int id;
+
+	id = srcu_read_lock(&srcu);
+	hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
+		if (mn->ops->invalidate_range_end)
+			mn->ops->invalidate_range_end(mn, mm, start, end);
+	}
+	srcu_read_unlock(&srcu, id);
+}
+EXPORT_SYMBOL_GPL(__mmu_notifier_invalidate_range_end);
+
+static int do_mmu_notifier_register(struct mmu_notifier *mn,
+				    struct mm_struct *mm,
+				    int take_mmap_sem)
+{
+	struct mmu_notifier_mm *mmu_notifier_mm;
+	int ret;
+
+	BUG_ON(atomic_read(&mm->mm_users) <= 0);
+
+	/*
+	 * Verify that mmu_notifier_init() already run and the global srcu is
+	 * initialized.
+	 */
+	BUG_ON(!srcu.per_cpu_ref);
+
+	ret = -ENOMEM;
+	mmu_notifier_mm = kmalloc(sizeof(struct mmu_notifier_mm), GFP_KERNEL);
+	if (unlikely(!mmu_notifier_mm))
+		goto out;
+
+	if (take_mmap_sem)
+		down_write(&mm->mmap_sem);
+	ret = mm_take_all_locks(mm);
+	if (unlikely(ret))
+		goto out_clean;
+
+	if (!mm_has_notifiers(mm)) {
+		INIT_HLIST_HEAD(&mmu_notifier_mm->list);
+		spin_lock_init(&mmu_notifier_mm->lock);
+
+		mm->mmu_notifier_mm = mmu_notifier_mm;
+		mmu_notifier_mm = NULL;
+	}
+	atomic_inc(&mm->mm_count);
+
+	/*
+	 * Serialize the update against mmu_notifier_unregister. A
+	 * side note: mmu_notifier_release can't run concurrently with
+	 * us because we hold the mm_users pin (either implicitly as
+	 * current->mm or explicitly with get_task_mm() or similar).
+	 * We can't race against any other mmu notifier method either
+	 * thanks to mm_take_all_locks().
+	 */
+	spin_lock(&mm->mmu_notifier_mm->lock);
+	hlist_add_head(&mn->hlist, &mm->mmu_notifier_mm->list);
+	spin_unlock(&mm->mmu_notifier_mm->lock);
+
+	mm_drop_all_locks(mm);
+out_clean:
+	if (take_mmap_sem)
+		up_write(&mm->mmap_sem);
+	kfree(mmu_notifier_mm);
+out:
+	BUG_ON(atomic_read(&mm->mm_users) <= 0);
+	return ret;
+}
+
+/*
+ * Must not hold mmap_sem nor any other VM related lock when calling
+ * this registration function. Must also ensure mm_users can't go down
+ * to zero while this runs to avoid races with mmu_notifier_release,
+ * so mm has to be current->mm or the mm should be pinned safely such
+ * as with get_task_mm(). If the mm is not current->mm, the mm_users
+ * pin should be released by calling mmput after mmu_notifier_register
+ * returns. mmu_notifier_unregister must be always called to
+ * unregister the notifier. mm_count is automatically pinned to allow
+ * mmu_notifier_unregister to safely run at any time later, before or
+ * after exit_mmap. ->release will always be called before exit_mmap
+ * frees the pages.
+ */
+int mmu_notifier_register(struct mmu_notifier *mn, struct mm_struct *mm)
+{
+	return do_mmu_notifier_register(mn, mm, 1);
+}
+EXPORT_SYMBOL_GPL(mmu_notifier_register);
+
+/*
+ * Same as mmu_notifier_register but here the caller must hold the
+ * mmap_sem in write mode.
+ */
+int __mmu_notifier_register(struct mmu_notifier *mn, struct mm_struct *mm)
+{
+	return do_mmu_notifier_register(mn, mm, 0);
+}
+EXPORT_SYMBOL_GPL(__mmu_notifier_register);
+
+/* this is called after the last mmu_notifier_unregister() returned */
+void __mmu_notifier_mm_destroy(struct mm_struct *mm)
+{
+	BUG_ON(!hlist_empty(&mm->mmu_notifier_mm->list));
+	kfree(mm->mmu_notifier_mm);
+	mm->mmu_notifier_mm = LIST_POISON1; /* debug */
+}
+
+/*
+ * This releases the mm_count pin automatically and frees the mm
+ * structure if it was the last user of it. It serializes against
+ * running mmu notifiers with SRCU and against mmu_notifier_unregister
+ * with the unregister lock + SRCU. All sptes must be dropped before
+ * calling mmu_notifier_unregister. ->release or any other notifier
+ * method may be invoked concurrently with mmu_notifier_unregister,
+ * and only after mmu_notifier_unregister returned we're guaranteed
+ * that ->release or any other method can't run anymore.
+ */
+void mmu_notifier_unregister(struct mmu_notifier *mn, struct mm_struct *mm)
+{
+	BUG_ON(atomic_read(&mm->mm_count) <= 0);
+
+	if (!hlist_unhashed(&mn->hlist)) {
+		/*
+		 * SRCU here will force exit_mmap to wait for ->release to
+		 * finish before freeing the pages.
+		 */
+		int id;
+
+		id = srcu_read_lock(&srcu);
+		/*
+		 * exit_mmap will block in mmu_notifier_release to guarantee
+		 * that ->release is called before freeing the pages.
+		 */
+		if (mn->ops->release)
+			mn->ops->release(mn, mm);
+		srcu_read_unlock(&srcu, id);
+
+		spin_lock(&mm->mmu_notifier_mm->lock);
+		/*
+		 * Can not use list_del_rcu() since __mmu_notifier_release
+		 * can delete it before we hold the lock.
+		 */
+		hlist_del_init_rcu(&mn->hlist);
+		spin_unlock(&mm->mmu_notifier_mm->lock);
+	}
+
+	/*
+	 * Wait for any running method to finish, of course including
+	 * ->release if it was run by mmu_notifier_release instead of us.
+	 */
+	synchronize_srcu(&srcu);
+
+	BUG_ON(atomic_read(&mm->mm_count) <= 0);
+
+	mmdrop(mm);
+}
+EXPORT_SYMBOL_GPL(mmu_notifier_unregister);
+
+/*
+ * Same as mmu_notifier_unregister but no callback and no srcu synchronization.
+ */
+void mmu_notifier_unregister_no_release(struct mmu_notifier *mn,
+					struct mm_struct *mm)
+{
+	spin_lock(&mm->mmu_notifier_mm->lock);
+	/*
+	 * Can not use list_del_rcu() since __mmu_notifier_release
+	 * can delete it before we hold the lock.
+	 */
+	hlist_del_init_rcu(&mn->hlist);
+	spin_unlock(&mm->mmu_notifier_mm->lock);
+
+	BUG_ON(atomic_read(&mm->mm_count) <= 0);
+	mmdrop(mm);
+}
+EXPORT_SYMBOL_GPL(mmu_notifier_unregister_no_release);
+
+static int __init mmu_notifier_init(void)
+{
+	return init_srcu_struct(&srcu);
+}
+subsys_initcall(mmu_notifier_init);

mm/mmzone.c

@@ -0,0 +1,116 @@
+/*
+ * linux/mm/mmzone.c
+ *
+ * management codes for pgdats, zones and page flags
+ */
+
+
+#include <linux/stddef.h>
+#include <linux/mm.h>
+#include <linux/mmzone.h>
+
+struct pglist_data *first_online_pgdat(void)
+{
+	return NODE_DATA(first_online_node);
+}
+
+struct pglist_data *next_online_pgdat(struct pglist_data *pgdat)
+{
+	int nid = next_online_node(pgdat->node_id);
+
+	if (nid == MAX_NUMNODES)
+		return NULL;
+	return NODE_DATA(nid);
+}
+
+/*
+ * next_zone - helper magic for for_each_zone()
+ */
+struct zone *next_zone(struct zone *zone)
+{
+	pg_data_t *pgdat = zone->zone_pgdat;
+
+	if (zone < pgdat->node_zones + MAX_NR_ZONES - 1)
+		zone++;
+	else {
+		pgdat = next_online_pgdat(pgdat);
+		if (pgdat)
+			zone = pgdat->node_zones;
+		else
+			zone = NULL;
+	}
+	return zone;
+}
+
+static inline int zref_in_nodemask(struct zoneref *zref, nodemask_t *nodes)
+{
+#ifdef CONFIG_NUMA
+	return node_isset(zonelist_node_idx(zref), *nodes);
+#else
+	return 1;
+#endif /* CONFIG_NUMA */
+}
+
+/* Returns the next zone at or below highest_zoneidx in a zonelist */
+struct zoneref *next_zones_zonelist(struct zoneref *z,
+					enum zone_type highest_zoneidx,
+					nodemask_t *nodes,
+					struct zone **zone)
+{
+	/*
+	 * Find the next suitable zone to use for the allocation.
+	 * Only filter based on nodemask if it's set
+	 */
+	if (likely(nodes == NULL))
+		while (zonelist_zone_idx(z) > highest_zoneidx)
+			z++;
+	else
+		while (zonelist_zone_idx(z) > highest_zoneidx ||
+				(z->zone && !zref_in_nodemask(z, nodes)))
+			z++;
+
+	*zone = zonelist_zone(z);
+	return z;
+}
+
+#ifdef CONFIG_ARCH_HAS_HOLES_MEMORYMODEL
+int memmap_valid_within(unsigned long pfn,
+					struct page *page, struct zone *zone)
+{
+	if (page_to_pfn(page) != pfn)
+		return 0;
+
+	if (page_zone(page) != zone)
+		return 0;
+
+	return 1;
+}
+#endif /* CONFIG_ARCH_HAS_HOLES_MEMORYMODEL */
+
+void lruvec_init(struct lruvec *lruvec)
+{
+	enum lru_list lru;
+
+	memset(lruvec, 0, sizeof(struct lruvec));
+
+	for_each_lru(lru)
+		INIT_LIST_HEAD(&lruvec->lists[lru]);
+}
+
+#if defined(CONFIG_NUMA_BALANCING) && !defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS)
+int page_cpupid_xchg_last(struct page *page, int cpupid)
+{
+	unsigned long old_flags, flags;
+	int last_cpupid;
+
+	do {
+		old_flags = flags = page->flags;
+		last_cpupid = page_cpupid_last(page);
+
+		flags &= ~(LAST_CPUPID_MASK << LAST_CPUPID_PGSHIFT);
+		flags |= (cpupid & LAST_CPUPID_MASK) << LAST_CPUPID_PGSHIFT;
+	} while (unlikely(cmpxchg(&page->flags, old_flags, flags) != old_flags));
+
+	return last_cpupid;
+}
+#endif

mm/mprotect.c

@@ -0,0 +1,433 @@
+/*
+ *  mm/mprotect.c
+ *
+ *  (C) Copyright 1994 Linus Torvalds
+ *  (C) Copyright 2002 Christoph Hellwig
+ *
+ *  Address space accounting code	<alan@lxorguk.ukuu.org.uk>
+ *  (C) Copyright 2002 Red Hat Inc, All Rights Reserved
+ */
+
+#include <linux/mm.h>
+#include <linux/hugetlb.h>
+#include <linux/shm.h>
+#include <linux/mman.h>
+#include <linux/fs.h>
+#include <linux/highmem.h>
+#include <linux/security.h>
+#include <linux/mempolicy.h>
+#include <linux/personality.h>
+#include <linux/syscalls.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
+#include <linux/mmu_notifier.h>
+#include <linux/migrate.h>
+#include <linux/perf_event.h>
+#include <linux/ksm.h>
+#include <asm/uaccess.h>
+#include <asm/pgtable.h>
+#include <asm/cacheflush.h>
+#include <asm/tlbflush.h>
+
+/*
+ * For a prot_numa update we only hold mmap_sem for read so there is a
+ * potential race with faulting where a pmd was temporarily none. This
+ * function checks for a transhuge pmd under the appropriate lock. It
+ * returns a pte if it was successfully locked or NULL if it raced with
+ * a transhuge insertion.
+ */
+static pte_t *lock_pte_protection(struct vm_area_struct *vma, pmd_t *pmd,
+			unsigned long addr, int prot_numa, spinlock_t **ptl)
+{
+	pte_t *pte;
+	spinlock_t *pmdl;
+
+	/* !prot_numa is protected by mmap_sem held for write */
+	if (!prot_numa)
+		return pte_offset_map_lock(vma->vm_mm, pmd, addr, ptl);
+
+	pmdl = pmd_lock(vma->vm_mm, pmd);
+	if (unlikely(pmd_trans_huge(*pmd) || pmd_none(*pmd))) {
+		spin_unlock(pmdl);
+		return NULL;
+	}
+
+	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, ptl);
+	spin_unlock(pmdl);
+	return pte;
+}
+
+static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
+		unsigned long addr, unsigned long end, pgprot_t newprot,
+		int dirty_accountable, int prot_numa)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	pte_t *pte, oldpte;
+	spinlock_t *ptl;
+	unsigned long pages = 0;
+
+	pte = lock_pte_protection(vma, pmd, addr, prot_numa, &ptl);
+	if (!pte)
+		return 0;
+
+	arch_enter_lazy_mmu_mode();
+	do {
+		oldpte = *pte;
+		if (pte_present(oldpte)) {
+			pte_t ptent;
+			bool updated = false;
+
+			if (!prot_numa) {
+				ptent = ptep_modify_prot_start(mm, addr, pte);
+				if (pte_numa(ptent))
+					ptent = pte_mknonnuma(ptent);
+				ptent = pte_modify(ptent, newprot);
+				/*
+				 * Avoid taking write faults for pages we
+				 * know to be dirty.
+				 */
+				if (dirty_accountable && pte_dirty(ptent) &&
+				    (pte_soft_dirty(ptent) ||
+				     !(vma->vm_flags & VM_SOFTDIRTY)))
+					ptent = pte_mkwrite(ptent);
+				ptep_modify_prot_commit(mm, addr, pte, ptent);
+				updated = true;
+			} else {
+				struct page *page;
+
+				page = vm_normal_page(vma, addr, oldpte);
+				if (page && !PageKsm(page)) {
+					if (!pte_numa(oldpte)) {
+						ptep_set_numa(mm, addr, pte);
+						updated = true;
+					}
+				}
+			}
+			if (updated)
+				pages++;
+		} else if (IS_ENABLED(CONFIG_MIGRATION) && !pte_file(oldpte)) {
+			swp_entry_t entry = pte_to_swp_entry(oldpte);
+
+			if (is_write_migration_entry(entry)) {
+				pte_t newpte;
+				/*
+				 * A protection check is difficult so
+				 * just be safe and disable write
+				 */
+				make_migration_entry_read(&entry);
+				newpte = swp_entry_to_pte(entry);
+				if (pte_swp_soft_dirty(oldpte))
+					newpte = pte_swp_mksoft_dirty(newpte);
+				set_pte_at(mm, addr, pte, newpte);
+
+				pages++;
+			}
+		}
+	} while (pte++, addr += PAGE_SIZE, addr != end);
+	arch_leave_lazy_mmu_mode();
+	pte_unmap_unlock(pte - 1, ptl);
+
+	return pages;
+}
+
+static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
+		pud_t *pud, unsigned long addr, unsigned long end,
+		pgprot_t newprot, int dirty_accountable, int prot_numa)
+{
+	pmd_t *pmd;
+	struct mm_struct *mm = vma->vm_mm;
+	unsigned long next;
+	unsigned long pages = 0;
+	unsigned long nr_huge_updates = 0;
+	unsigned long mni_start = 0;
+
+	pmd = pmd_offset(pud, addr);
+	do {
+		unsigned long this_pages;
+
+		next = pmd_addr_end(addr, end);
+		if (!pmd_trans_huge(*pmd) && pmd_none_or_clear_bad(pmd))
+			continue;
+
+		/* invoke the mmu notifier if the pmd is populated */
+		if (!mni_start) {
+			mni_start = addr;
+			mmu_notifier_invalidate_range_start(mm, mni_start, end);
+		}
+
+		if (pmd_trans_huge(*pmd)) {
+			if (next - addr != HPAGE_PMD_SIZE)
+				split_huge_page_pmd(vma, addr, pmd);
+			else {
+				int nr_ptes = change_huge_pmd(vma, pmd, addr,
+						newprot, prot_numa);
+
+				if (nr_ptes) {
+					if (nr_ptes == HPAGE_PMD_NR) {
+						pages += HPAGE_PMD_NR;
+						nr_huge_updates++;
+					}
+
+					/* huge pmd was handled */
+					continue;
+				}
+			}
+			/* fall through, the trans huge pmd just split */
+		}
+		this_pages = change_pte_range(vma, pmd, addr, next, newprot,
+				 dirty_accountable, prot_numa);
+		pages += this_pages;
+	} while (pmd++, addr = next, addr != end);
+
+	if (mni_start)
+		mmu_notifier_invalidate_range_end(mm, mni_start, end);
+
+	if (nr_huge_updates)
+		count_vm_numa_events(NUMA_HUGE_PTE_UPDATES, nr_huge_updates);
+	return pages;
+}
+
+static inline unsigned long change_pud_range(struct vm_area_struct *vma,
+		pgd_t *pgd, unsigned long addr, unsigned long end,
+		pgprot_t newprot, int dirty_accountable, int prot_numa)
+{
+	pud_t *pud;
+	unsigned long next;
+	unsigned long pages = 0;
+
+	pud = pud_offset(pgd, addr);
+	do {
+		next = pud_addr_end(addr, end);
+		if (pud_none_or_clear_bad(pud))
+			continue;
+		pages += change_pmd_range(vma, pud, addr, next, newprot,
+				 dirty_accountable, prot_numa);
+	} while (pud++, addr = next, addr != end);
+
+	return pages;
+}
+
+static unsigned long change_protection_range(struct vm_area_struct *vma,
+		unsigned long addr, unsigned long end, pgprot_t newprot,
+		int dirty_accountable, int prot_numa)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	pgd_t *pgd;
+	unsigned long next;
+	unsigned long start = addr;
+	unsigned long pages = 0;
+
+	BUG_ON(addr >= end);
+	pgd = pgd_offset(mm, addr);
+	flush_cache_range(vma, addr, end);
+	set_tlb_flush_pending(mm);
+	do {
+		next = pgd_addr_end(addr, end);
+		if (pgd_none_or_clear_bad(pgd))
+			continue;
+		pages += change_pud_range(vma, pgd, addr, next, newprot,
+				 dirty_accountable, prot_numa);
+	} while (pgd++, addr = next, addr != end);
+
+	/* Only flush the TLB if we actually modified any entries: */
+	if (pages)
+		flush_tlb_range(vma, start, end);
+	clear_tlb_flush_pending(mm);
+
+	return pages;
+}
+
+unsigned long change_protection(struct vm_area_struct *vma, unsigned long start,
+		       unsigned long end, pgprot_t newprot,
+		       int dirty_accountable, int prot_numa)
+{
+	unsigned long pages;
+
+	if (is_vm_hugetlb_page(vma))
+		pages = hugetlb_change_protection(vma, start, end, newprot);
+	else
+		pages = change_protection_range(vma, start, end, newprot, dirty_accountable, prot_numa);
+
+	return pages;
+}
+
+int
+mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
+	unsigned long start, unsigned long end, unsigned long newflags)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	unsigned long oldflags = vma->vm_flags;
+	long nrpages = (end - start) >> PAGE_SHIFT;
+	unsigned long charged = 0;
+	pgoff_t pgoff;
+	int error;
+	int dirty_accountable = 0;
+
+	if (newflags == oldflags) {
+		*pprev = vma;
+		return 0;
+	}
+
+	/*
+	 * If we make a private mapping writable we increase our commit;
+	 * but (without finer accounting) cannot reduce our commit if we
+	 * make it unwritable again. hugetlb mapping were accounted for
+	 * even if read-only so there is no need to account for them here
+	 */
+	if (newflags & VM_WRITE) {
+		if (!(oldflags & (VM_ACCOUNT|VM_WRITE|VM_HUGETLB|
+						VM_SHARED|VM_NORESERVE))) {
+			charged = nrpages;
+			if (security_vm_enough_memory_mm(mm, charged))
+				return -ENOMEM;
+			newflags |= VM_ACCOUNT;
+		}
+	}
+
+	/*
+	 * First try to merge with previous and/or next vma.
+	 */
+	pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
+	*pprev = vma_merge(mm, *pprev, start, end, newflags,
+			vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma),
+			vma_get_anon_name(vma));
+	if (*pprev) {
+		vma = *pprev;
+		goto success;
+	}
+
+	*pprev = vma;
+
+	if (start != vma->vm_start) {
+		error = split_vma(mm, vma, start, 1);
+		if (error)
+			goto fail;
+	}
+
+	if (end != vma->vm_end) {
+		error = split_vma(mm, vma, end, 0);
+		if (error)
+			goto fail;
+	}
+
+success:
+	/*
+	 * vm_flags and vm_page_prot are protected by the mmap_sem
+	 * held in write mode.
+	 */
+	vma->vm_flags = newflags;
+	dirty_accountable = vma_wants_writenotify(vma);
+	vma_set_page_prot(vma);
+
+	change_protection(vma, start, end, vma->vm_page_prot,
+			  dirty_accountable, 0);
+
+	vm_stat_account(mm, oldflags, vma->vm_file, -nrpages);
+	vm_stat_account(mm, newflags, vma->vm_file, nrpages);
+	perf_event_mmap(vma);
+	return 0;
+
+fail:
+	vm_unacct_memory(charged);
+	return error;
+}
+
+SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len,
+		unsigned long, prot)
+{
+	unsigned long vm_flags, nstart, end, tmp, reqprot;
+	struct vm_area_struct *vma, *prev;
+	int error = -EINVAL;
+	const int grows = prot & (PROT_GROWSDOWN|PROT_GROWSUP);
+	prot &= ~(PROT_GROWSDOWN|PROT_GROWSUP);
+	if (grows == (PROT_GROWSDOWN|PROT_GROWSUP)) /* can't be both */
+		return -EINVAL;
+
+	if (start & ~PAGE_MASK)
+		return -EINVAL;
+	if (!len)
+		return 0;
+	len = PAGE_ALIGN(len);
+	end = start + len;
+	if (end <= start)
+		return -ENOMEM;
+	if (!arch_validate_prot(prot))
+		return -EINVAL;
+
+	reqprot = prot;
+	/*
+	 * Does the application expect PROT_READ to imply PROT_EXEC:
+	 */
+	if ((prot & PROT_READ) && (current->personality & READ_IMPLIES_EXEC))
+		prot |= PROT_EXEC;
+
+	vm_flags = calc_vm_prot_bits(prot);
+
+	down_write(&current->mm->mmap_sem);
+
+	vma = find_vma(current->mm, start);
+	error = -ENOMEM;
+	if (!vma)
+		goto out;
+	prev = vma->vm_prev;
+	if (unlikely(grows & PROT_GROWSDOWN)) {
+		if (vma->vm_start >= end)
+			goto out;
+		start = vma->vm_start;
+		error = -EINVAL;
+		if (!(vma->vm_flags & VM_GROWSDOWN))
+			goto out;
+	} else {
+		if (vma->vm_start > start)
+			goto out;
+		if (unlikely(grows & PROT_GROWSUP)) {
+			end = vma->vm_end;
+			error = -EINVAL;
+			if (!(vma->vm_flags & VM_GROWSUP))
+				goto out;
+		}
+	}
+	if (start > vma->vm_start)
+		prev = vma;
+
+	for (nstart = start ; ; ) {
+		unsigned long newflags;
+
+		/* Here we know that vma->vm_start <= nstart < vma->vm_end. */
+
+		newflags = vm_flags;
+		newflags |= (vma->vm_flags & ~(VM_READ | VM_WRITE | VM_EXEC));
+
+		/* newflags >> 4 shift VM_MAY% in place of VM_% */
+		if ((newflags & ~(newflags >> 4)) & (VM_READ | VM_WRITE | VM_EXEC)) {
+			error = -EACCES;
+			goto out;
+		}
+
+		error = security_file_mprotect(vma, reqprot, prot);
+		if (error)
+			goto out;
+
+		tmp = vma->vm_end;
+		if (tmp > end)
+			tmp = end;
+		error = mprotect_fixup(vma, &prev, nstart, tmp, newflags);
+		if (error)
+			goto out;
+		nstart = tmp;
+
+		if (nstart < prev->vm_end)
+			nstart = prev->vm_end;
+		if (nstart >= end)
+			goto out;
+
+		vma = prev->vm_next;
+		if (!vma || vma->vm_start != nstart) {
+			error = -ENOMEM;
+			goto out;
+		}
+	}
+out:
+	up_write(&current->mm->mmap_sem);
+	return error;
+}

mm/mremap.c

@@ -0,0 +1,588 @@
+/*
+ *	mm/mremap.c
+ *
+ *	(C) Copyright 1996 Linus Torvalds
+ *
+ *	Address space accounting code	<alan@lxorguk.ukuu.org.uk>
+ *	(C) Copyright 2002 Red Hat Inc, All Rights Reserved
+ */
+
+#include <linux/mm.h>
+#include <linux/hugetlb.h>
+#include <linux/shm.h>
+#include <linux/ksm.h>
+#include <linux/mman.h>
+#include <linux/swap.h>
+#include <linux/capability.h>
+#include <linux/fs.h>
+#include <linux/swapops.h>
+#include <linux/highmem.h>
+#include <linux/security.h>
+#include <linux/syscalls.h>
+#include <linux/mmu_notifier.h>
+#include <linux/sched/sysctl.h>
+#include <linux/uaccess.h>
+
+#include <asm/cacheflush.h>
+#include <asm/tlbflush.h>
+
+#include "internal.h"
+
+static pmd_t *get_old_pmd(struct mm_struct *mm, unsigned long addr)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
+
+	pgd = pgd_offset(mm, addr);
+	if (pgd_none_or_clear_bad(pgd))
+		return NULL;
+
+	pud = pud_offset(pgd, addr);
+	if (pud_none_or_clear_bad(pud))
+		return NULL;
+
+	pmd = pmd_offset(pud, addr);
+	if (pmd_none(*pmd))
+		return NULL;
+
+	return pmd;
+}
+
+static pmd_t *alloc_new_pmd(struct mm_struct *mm, struct vm_area_struct *vma,
+			    unsigned long addr)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
+
+	pgd = pgd_offset(mm, addr);
+	pud = pud_alloc(mm, pgd, addr);
+	if (!pud)
+		return NULL;
+
+	pmd = pmd_alloc(mm, pud, addr);
+	if (!pmd)
+		return NULL;
+
+	VM_BUG_ON(pmd_trans_huge(*pmd));
+
+	return pmd;
+}
+
+static pte_t move_soft_dirty_pte(pte_t pte)
+{
+	/*
+	 * Set soft dirty bit so we can notice
+	 * in userspace the ptes were moved.
+	 */
+#ifdef CONFIG_MEM_SOFT_DIRTY
+	if (pte_present(pte))
+		pte = pte_mksoft_dirty(pte);
+	else if (is_swap_pte(pte))
+		pte = pte_swp_mksoft_dirty(pte);
+	else if (pte_file(pte))
+		pte = pte_file_mksoft_dirty(pte);
+#endif
+	return pte;
+}
+
+static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
+		unsigned long old_addr, unsigned long old_end,
+		struct vm_area_struct *new_vma, pmd_t *new_pmd,
+		unsigned long new_addr, bool need_rmap_locks)
+{
+	struct address_space *mapping = NULL;
+	struct anon_vma *anon_vma = NULL;
+	struct mm_struct *mm = vma->vm_mm;
+	pte_t *old_pte, *new_pte, pte;
+	spinlock_t *old_ptl, *new_ptl;
+
+	/*
+	 * When need_rmap_locks is true, we take the i_mmap_mutex and anon_vma
+	 * locks to ensure that rmap will always observe either the old or the
+	 * new ptes. This is the easiest way to avoid races with
+	 * truncate_pagecache(), page migration, etc...
+	 *
+	 * When need_rmap_locks is false, we use other ways to avoid
+	 * such races:
+	 *
+	 * - During exec() shift_arg_pages(), we use a specially tagged vma
+	 *   which rmap call sites look for using is_vma_temporary_stack().
+	 *
+	 * - During mremap(), new_vma is often known to be placed after vma
+	 *   in rmap traversal order. This ensures rmap will always observe
+	 *   either the old pte, or the new pte, or both (the page table locks
+	 *   serialize access to individual ptes, but only rmap traversal
+	 *   order guarantees that we won't miss both the old and new ptes).
+	 */
+	if (need_rmap_locks) {
+		if (vma->vm_file) {
+			mapping = vma->vm_file->f_mapping;
+			mutex_lock(&mapping->i_mmap_mutex);
+		}
+		if (vma->anon_vma) {
+			anon_vma = vma->anon_vma;
+			anon_vma_lock_write(anon_vma);
+		}
+	}
+
+	/*
+	 * We don't have to worry about the ordering of src and dst
+	 * pte locks because exclusive mmap_sem prevents deadlock.
+	 */
+	old_pte = pte_offset_map_lock(mm, old_pmd, old_addr, &old_ptl);
+	new_pte = pte_offset_map(new_pmd, new_addr);
+	new_ptl = pte_lockptr(mm, new_pmd);
+	if (new_ptl != old_ptl)
+		spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
+	arch_enter_lazy_mmu_mode();
+
+	for (; old_addr < old_end; old_pte++, old_addr += PAGE_SIZE,
+				   new_pte++, new_addr += PAGE_SIZE) {
+		if (pte_none(*old_pte))
+			continue;
+		pte = ptep_get_and_clear(mm, old_addr, old_pte);
+		pte = move_pte(pte, new_vma->vm_page_prot, old_addr, new_addr);
+		pte = move_soft_dirty_pte(pte);
+		set_pte_at(mm, new_addr, new_pte, pte);
+	}
+
+	arch_leave_lazy_mmu_mode();
+	if (new_ptl != old_ptl)
+		spin_unlock(new_ptl);
+	pte_unmap(new_pte - 1);
+	pte_unmap_unlock(old_pte - 1, old_ptl);
+	if (anon_vma)
+		anon_vma_unlock_write(anon_vma);
+	if (mapping)
+		mutex_unlock(&mapping->i_mmap_mutex);
+}
+
+#define LATENCY_LIMIT	(64 * PAGE_SIZE)
+
+unsigned long move_page_tables(struct vm_area_struct *vma,
+		unsigned long old_addr, struct vm_area_struct *new_vma,
+		unsigned long new_addr, unsigned long len,
+		bool need_rmap_locks)
+{
+	unsigned long extent, next, old_end;
+	pmd_t *old_pmd, *new_pmd;
+	bool need_flush = false;
+	unsigned long mmun_start;	/* For mmu_notifiers */
+	unsigned long mmun_end;		/* For mmu_notifiers */
+
+	old_end = old_addr + len;
+	flush_cache_range(vma, old_addr, old_end);
+
+	mmun_start = old_addr;
+	mmun_end   = old_end;
+	mmu_notifier_invalidate_range_start(vma->vm_mm, mmun_start, mmun_end);
+
+	for (; old_addr < old_end; old_addr += extent, new_addr += extent) {
+		cond_resched();
+		next = (old_addr + PMD_SIZE) & PMD_MASK;
+		/* even if next overflowed, extent below will be ok */
+		extent = next - old_addr;
+		if (extent > old_end - old_addr)
+			extent = old_end - old_addr;
+		old_pmd = get_old_pmd(vma->vm_mm, old_addr);
+		if (!old_pmd)
+			continue;
+		new_pmd = alloc_new_pmd(vma->vm_mm, vma, new_addr);
+		if (!new_pmd)
+			break;
+		if (pmd_trans_huge(*old_pmd)) {
+			int err = 0;
+			if (extent == HPAGE_PMD_SIZE) {
+				VM_BUG_ON_VMA(vma->vm_file || !vma->anon_vma,
+					      vma);
+				/* See comment in move_ptes() */
+				if (need_rmap_locks)
+					anon_vma_lock_write(vma->anon_vma);
+				err = move_huge_pmd(vma, new_vma, old_addr,
+						    new_addr, old_end,
+						    old_pmd, new_pmd);
+				if (need_rmap_locks)
+					anon_vma_unlock_write(vma->anon_vma);
+			}
+			if (err > 0) {
+				need_flush = true;
+				continue;
+			} else if (!err) {
+				split_huge_page_pmd(vma, old_addr, old_pmd);
+			}
+			VM_BUG_ON(pmd_trans_huge(*old_pmd));
+		}
+		if (pmd_none(*new_pmd) && __pte_alloc(new_vma->vm_mm, new_vma,
+						      new_pmd, new_addr))
+			break;
+		next = (new_addr + PMD_SIZE) & PMD_MASK;
+		if (extent > next - new_addr)
+			extent = next - new_addr;
+		if (extent > LATENCY_LIMIT)
+			extent = LATENCY_LIMIT;
+		move_ptes(vma, old_pmd, old_addr, old_addr + extent,
+			  new_vma, new_pmd, new_addr, need_rmap_locks);
+		need_flush = true;
+	}
+	if (likely(need_flush))
+		flush_tlb_range(vma, old_end-len, old_addr);
+
+	mmu_notifier_invalidate_range_end(vma->vm_mm, mmun_start, mmun_end);
+
+	return len + old_addr - old_end;	/* how much done */
+}
+
+static unsigned long move_vma(struct vm_area_struct *vma,
+		unsigned long old_addr, unsigned long old_len,
+		unsigned long new_len, unsigned long new_addr, bool *locked)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	struct vm_area_struct *new_vma;
+	unsigned long vm_flags = vma->vm_flags;
+	unsigned long new_pgoff;
+	unsigned long moved_len;
+	unsigned long excess = 0;
+	unsigned long hiwater_vm;
+	int split = 0;
+	int err;
+	bool need_rmap_locks;
+
+	/*
+	 * We'd prefer to avoid failure later on in do_munmap:
+	 * which may split one vma into three before unmapping.
+	 */
+	if (mm->map_count >= sysctl_max_map_count - 3)
+		return -ENOMEM;
+
+	/*
+	 * Advise KSM to break any KSM pages in the area to be moved:
+	 * it would be confusing if they were to turn up at the new
+	 * location, where they happen to coincide with different KSM
+	 * pages recently unmapped.  But leave vma->vm_flags as it was,
+	 * so KSM can come around to merge on vma and new_vma afterwards.
+	 */
+	err = ksm_madvise(vma, old_addr, old_addr + old_len,
+						MADV_UNMERGEABLE, &vm_flags);
+	if (err)
+		return err;
+
+	new_pgoff = vma->vm_pgoff + ((old_addr - vma->vm_start) >> PAGE_SHIFT);
+	new_vma = copy_vma(&vma, new_addr, new_len, new_pgoff,
+			   &need_rmap_locks);
+	if (!new_vma)
+		return -ENOMEM;
+
+	moved_len = move_page_tables(vma, old_addr, new_vma, new_addr, old_len,
+				     need_rmap_locks);
+	if (moved_len < old_len) {
+		/*
+		 * On error, move entries back from new area to old,
+		 * which will succeed since page tables still there,
+		 * and then proceed to unmap new area instead of old.
+		 */
+		move_page_tables(new_vma, new_addr, vma, old_addr, moved_len,
+				 true);
+		vma = new_vma;
+		old_len = new_len;
+		old_addr = new_addr;
+		new_addr = -ENOMEM;
+	}
+
+	/* Conceal VM_ACCOUNT so old reservation is not undone */
+	if (vm_flags & VM_ACCOUNT) {
+		vma->vm_flags &= ~VM_ACCOUNT;
+		excess = vma->vm_end - vma->vm_start - old_len;
+		if (old_addr > vma->vm_start &&
+		    old_addr + old_len < vma->vm_end)
+			split = 1;
+	}
+
+	/*
+	 * If we failed to move page tables we still do total_vm increment
+	 * since do_munmap() will decrement it by old_len == new_len.
+	 *
+	 * Since total_vm is about to be raised artificially high for a
+	 * moment, we need to restore high watermark afterwards: if stats
+	 * are taken meanwhile, total_vm and hiwater_vm appear too high.
+	 * If this were a serious issue, we'd add a flag to do_munmap().
+	 */
+	hiwater_vm = mm->hiwater_vm;
+	vm_stat_account(mm, vma->vm_flags, vma->vm_file, new_len>>PAGE_SHIFT);
+
+	if (do_munmap(mm, old_addr, old_len) < 0) {
+		/* OOM: unable to split vma, just get accounts right */
+		vm_unacct_memory(excess >> PAGE_SHIFT);
+		excess = 0;
+	}
+	mm->hiwater_vm = hiwater_vm;
+
+	/* Restore VM_ACCOUNT if one or two pieces of vma left */
+	if (excess) {
+		vma->vm_flags |= VM_ACCOUNT;
+		if (split)
+			vma->vm_next->vm_flags |= VM_ACCOUNT;
+	}
+
+	if (vm_flags & VM_LOCKED) {
+		mm->locked_vm += new_len >> PAGE_SHIFT;
+		*locked = true;
+	}
+
+	return new_addr;
+}
+
+static struct vm_area_struct *vma_to_resize(unsigned long addr,
+	unsigned long old_len, unsigned long new_len, unsigned long *p)
+{
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma = find_vma(mm, addr);
+
+	if (!vma || vma->vm_start > addr)
+		goto Efault;
+
+	if (is_vm_hugetlb_page(vma))
+		goto Einval;
+
+	/* We can't remap across vm area boundaries */
+	if (old_len > vma->vm_end - addr)
+		goto Efault;
+
+	/* Need to be careful about a growing mapping */
+	if (new_len > old_len) {
+		unsigned long pgoff;
+
+		if (vma->vm_flags & (VM_DONTEXPAND | VM_PFNMAP))
+			goto Efault;
+		pgoff = (addr - vma->vm_start) >> PAGE_SHIFT;
+		pgoff += vma->vm_pgoff;
+		if (pgoff + (new_len >> PAGE_SHIFT) < pgoff)
+			goto Einval;
+	}
+
+	if (vma->vm_flags & VM_LOCKED) {
+		unsigned long locked, lock_limit;
+		locked = mm->locked_vm << PAGE_SHIFT;
+		lock_limit = rlimit(RLIMIT_MEMLOCK);
+		locked += new_len - old_len;
+		if (locked > lock_limit && !capable(CAP_IPC_LOCK))
+			goto Eagain;
+	}
+
+	if (!may_expand_vm(mm, (new_len - old_len) >> PAGE_SHIFT))
+		goto Enomem;
+
+	if (vma->vm_flags & VM_ACCOUNT) {
+		unsigned long charged = (new_len - old_len) >> PAGE_SHIFT;
+		if (security_vm_enough_memory_mm(mm, charged))
+			goto Efault;
+		*p = charged;
+	}
+
+	return vma;
+
+Efault:	/* very odd choice for most of the cases, but... */
+	return ERR_PTR(-EFAULT);
+Einval:
+	return ERR_PTR(-EINVAL);
+Enomem:
+	return ERR_PTR(-ENOMEM);
+Eagain:
+	return ERR_PTR(-EAGAIN);
+}
+
+static unsigned long mremap_to(unsigned long addr, unsigned long old_len,
+		unsigned long new_addr, unsigned long new_len, bool *locked)
+{
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	unsigned long ret = -EINVAL;
+	unsigned long charged = 0;
+	unsigned long map_flags;
+
+	if (new_addr & ~PAGE_MASK)
+		goto out;
+
+	if (new_len > TASK_SIZE || new_addr > TASK_SIZE - new_len)
+		goto out;
+
+	/* Check if the location we're moving into overlaps the
+	 * old location at all, and fail if it does.
+	 */
+	if ((new_addr <= addr) && (new_addr+new_len) > addr)
+		goto out;
+
+	if ((addr <= new_addr) && (addr+old_len) > new_addr)
+		goto out;
+
+	ret = do_munmap(mm, new_addr, new_len);
+	if (ret)
+		goto out;
+
+	if (old_len >= new_len) {
+		ret = do_munmap(mm, addr+new_len, old_len - new_len);
+		if (ret && old_len != new_len)
+			goto out;
+		old_len = new_len;
+	}
+
+	vma = vma_to_resize(addr, old_len, new_len, &charged);
+	if (IS_ERR(vma)) {
+		ret = PTR_ERR(vma);
+		goto out;
+	}
+
+	map_flags = MAP_FIXED;
+	if (vma->vm_flags & VM_MAYSHARE)
+		map_flags |= MAP_SHARED;
+
+	ret = get_unmapped_area(vma->vm_file, new_addr, new_len, vma->vm_pgoff +
+				((addr - vma->vm_start) >> PAGE_SHIFT),
+				map_flags);
+	if (ret & ~PAGE_MASK)
+		goto out1;
+
+	ret = move_vma(vma, addr, old_len, new_len, new_addr, locked);
+	if (!(ret & ~PAGE_MASK))
+		goto out;
+out1:
+	vm_unacct_memory(charged);
+
+out:
+	return ret;
+}
+
+static int vma_expandable(struct vm_area_struct *vma, unsigned long delta)
+{
+	unsigned long end = vma->vm_end + delta;
+	if (end < vma->vm_end) /* overflow */
+		return 0;
+	if (vma->vm_next && vma->vm_next->vm_start < end) /* intersection */
+		return 0;
+	if (get_unmapped_area(NULL, vma->vm_start, end - vma->vm_start,
+			      0, MAP_FIXED) & ~PAGE_MASK)
+		return 0;
+	return 1;
+}
+
+/*
+ * Expand (or shrink) an existing mapping, potentially moving it at the
+ * same time (controlled by the MREMAP_MAYMOVE flag and available VM space)
+ *
+ * MREMAP_FIXED option added 5-Dec-1999 by Benjamin LaHaise
+ * This option implies MREMAP_MAYMOVE.
+ */
+SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
+		unsigned long, new_len, unsigned long, flags,
+		unsigned long, new_addr)
+{
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	unsigned long ret = -EINVAL;
+	unsigned long charged = 0;
+	bool locked = false;
+
+	if (flags & ~(MREMAP_FIXED | MREMAP_MAYMOVE))
+		return ret;
+
+	if (flags & MREMAP_FIXED && !(flags & MREMAP_MAYMOVE))
+		return ret;
+
+	if (addr & ~PAGE_MASK)
+		return ret;
+
+	old_len = PAGE_ALIGN(old_len);
+	new_len = PAGE_ALIGN(new_len);
+
+	/*
+	 * We allow a zero old-len as a special case
+	 * for DOS-emu "duplicate shm area" thing. But
+	 * a zero new-len is nonsensical.
+	 */
+	if (!new_len)
+		return ret;
+
+	down_write(&current->mm->mmap_sem);
+
+	if (flags & MREMAP_FIXED) {
+		ret = mremap_to(addr, old_len, new_addr, new_len,
+				&locked);
+		goto out;
+	}
+
+	/*
+	 * Always allow a shrinking remap: that just unmaps
+	 * the unnecessary pages..
+	 * do_munmap does all the needed commit accounting
+	 */
+	if (old_len >= new_len) {
+		ret = do_munmap(mm, addr+new_len, old_len - new_len);
+		if (ret && old_len != new_len)
+			goto out;
+		ret = addr;
+		goto out;
+	}
+
+	/*
+	 * Ok, we need to grow..
+	 */
+	vma = vma_to_resize(addr, old_len, new_len, &charged);
+	if (IS_ERR(vma)) {
+		ret = PTR_ERR(vma);
+		goto out;
+	}
+
+	/* old_len exactly to the end of the area..
+	 */
+	if (old_len == vma->vm_end - addr) {
+		/* can we just expand the current mapping? */
+		if (vma_expandable(vma, new_len - old_len)) {
+			int pages = (new_len - old_len) >> PAGE_SHIFT;
+
+			if (vma_adjust(vma, vma->vm_start, addr + new_len,
+				       vma->vm_pgoff, NULL)) {
+				ret = -ENOMEM;
+				goto out;
+			}
+
+			vm_stat_account(mm, vma->vm_flags, vma->vm_file, pages);
+			if (vma->vm_flags & VM_LOCKED) {
+				mm->locked_vm += pages;
+				locked = true;
+				new_addr = addr;
+			}
+			ret = addr;
+			goto out;
+		}
+	}
+
+	/*
+	 * We weren't able to just expand or shrink the area,
+	 * we need to create a new one and move it..
+	 */
+	ret = -ENOMEM;
+	if (flags & MREMAP_MAYMOVE) {
+		unsigned long map_flags = 0;
+		if (vma->vm_flags & VM_MAYSHARE)
+			map_flags |= MAP_SHARED;
+
+		new_addr = get_unmapped_area(vma->vm_file, 0, new_len,
+					vma->vm_pgoff +
+					((addr - vma->vm_start) >> PAGE_SHIFT),
+					map_flags);
+		if (new_addr & ~PAGE_MASK) {
+			ret = new_addr;
+			goto out;
+		}
+
+		ret = move_vma(vma, addr, old_len, new_len, new_addr, &locked);
+	}
+out:
+	if (ret & ~PAGE_MASK)
+		vm_unacct_memory(charged);
+	up_write(&current->mm->mmap_sem);
+	if (locked && new_len > old_len)
+		mm_populate(new_addr + old_len, new_len - old_len);
+	return ret;
+}

mm/msync.c

@@ -0,0 +1,110 @@
+/*
+ *	linux/mm/msync.c
+ *
+ * Copyright (C) 1994-1999  Linus Torvalds
+ */
+
+/*
+ * The msync() system call.
+ */
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/file.h>
+#include <linux/syscalls.h>
+#include <linux/sched.h>
+
+/*
+ * MS_SYNC syncs the entire file - including mappings.
+ *
+ * MS_ASYNC does not start I/O (it used to, up to 2.5.67).
+ * Nor does it marks the relevant pages dirty (it used to up to 2.6.17).
+ * Now it doesn't do anything, since dirty pages are properly tracked.
+ *
+ * The application may now run fsync() to
+ * write out the dirty pages and wait on the writeout and check the result.
+ * Or the application may run fadvise(FADV_DONTNEED) against the fd to start
+ * async writeout immediately.
+ * So by _not_ starting I/O in MS_ASYNC we provide complete flexibility to
+ * applications.
+ */
+SYSCALL_DEFINE3(msync, unsigned long, start, size_t, len, int, flags)
+{
+	unsigned long end;
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	int unmapped_error = 0;
+	int error = -EINVAL;
+
+	if (flags & ~(MS_ASYNC | MS_INVALIDATE | MS_SYNC))
+		goto out;
+	if (start & ~PAGE_MASK)
+		goto out;
+	if ((flags & MS_ASYNC) && (flags & MS_SYNC))
+		goto out;
+	error = -ENOMEM;
+	len = (len + ~PAGE_MASK) & PAGE_MASK;
+	end = start + len;
+	if (end < start)
+		goto out;
+	error = 0;
+	if (end == start)
+		goto out;
+	/*
+	 * If the interval [start,end) covers some unmapped address ranges,
+	 * just ignore them, but return -ENOMEM at the end.
+	 */
+	down_read(&mm->mmap_sem);
+	vma = find_vma(mm, start);
+	for (;;) {
+		struct file *file;
+		loff_t fstart, fend;
+
+		/* Still start < end. */
+		error = -ENOMEM;
+		if (!vma)
+			goto out_unlock;
+		/* Here start < vma->vm_end. */
+		if (start < vma->vm_start) {
+			start = vma->vm_start;
+			if (start >= end)
+				goto out_unlock;
+			unmapped_error = -ENOMEM;
+		}
+		/* Here vma->vm_start <= start < vma->vm_end. */
+		if ((flags & MS_INVALIDATE) &&
+				(vma->vm_flags & VM_LOCKED)) {
+			error = -EBUSY;
+			goto out_unlock;
+		}
+		file = vma->vm_file;
+		fstart = (start - vma->vm_start) +
+			 ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
+		fend = fstart + (min(end, vma->vm_end) - start) - 1;
+		start = vma->vm_end;
+		if ((flags & MS_SYNC) && file &&
+				(vma->vm_flags & VM_SHARED)) {
+			get_file(file);
+			up_read(&mm->mmap_sem);
+			if (vma->vm_flags & VM_NONLINEAR)
+				error = vfs_fsync(file, 1);
+			else
+				error = vfs_fsync_range(file, fstart, fend, 1);
+			fput(file);
+			if (error || start >= end)
+				goto out;
+			down_read(&mm->mmap_sem);
+			vma = find_vma(mm, start);
+		} else {
+			if (start >= end) {
+				error = 0;
+				goto out_unlock;
+			}
+			vma = vma->vm_next;
+		}
+	}
+out_unlock:
+	up_read(&mm->mmap_sem);
+out:
+	return error ? : unmapped_error;
+}

mm/nobootmem.c

@@ -0,0 +1,438 @@
+/*
+ *  bootmem - A boot-time physical memory allocator and configurator
+ *
+ *  Copyright (C) 1999 Ingo Molnar
+ *                1999 Kanoj Sarcar, SGI
+ *                2008 Johannes Weiner
+ *
+ * Access to this subsystem has to be serialized externally (which is true
+ * for the boot process anyway).
+ */
+#include <linux/init.h>
+#include <linux/pfn.h>
+#include <linux/slab.h>
+#include <linux/bootmem.h>
+#include <linux/export.h>
+#include <linux/kmemleak.h>
+#include <linux/range.h>
+#include <linux/memblock.h>
+
+#include <asm/bug.h>
+#include <asm/io.h>
+#include <asm/processor.h>
+
+#include "internal.h"
+
+#ifndef CONFIG_NEED_MULTIPLE_NODES
+struct pglist_data __refdata contig_page_data;
+EXPORT_SYMBOL(contig_page_data);
+#endif
+
+unsigned long max_low_pfn;
+unsigned long min_low_pfn;
+unsigned long max_pfn;
+
+static void * __init __alloc_memory_core_early(int nid, u64 size, u64 align,
+					u64 goal, u64 limit)
+{
+	void *ptr;
+	u64 addr;
+
+	if (limit > memblock.current_limit)
+		limit = memblock.current_limit;
+
+	addr = memblock_find_in_range_node(size, align, goal, limit, nid);
+	if (!addr)
+		return NULL;
+
+	if (memblock_reserve(addr, size))
+		return NULL;
+
+	ptr = phys_to_virt(addr);
+	memset(ptr, 0, size);
+	/*
+	 * The min_count is set to 0 so that bootmem allocated blocks
+	 * are never reported as leaks.
+	 */
+	kmemleak_alloc(ptr, size, 0, 0);
+	return ptr;
+}
+
+/*
+ * free_bootmem_late - free bootmem pages directly to page allocator
+ * @addr: starting address of the range
+ * @size: size of the range in bytes
+ *
+ * This is only useful when the bootmem allocator has already been torn
+ * down, but we are still initializing the system.  Pages are given directly
+ * to the page allocator, no bootmem metadata is updated because it is gone.
+ */
+void __init free_bootmem_late(unsigned long addr, unsigned long size)
+{
+	unsigned long cursor, end;
+
+	kmemleak_free_part(__va(addr), size);
+
+	cursor = PFN_UP(addr);
+	end = PFN_DOWN(addr + size);
+
+	for (; cursor < end; cursor++) {
+		__free_pages_bootmem(pfn_to_page(cursor), 0);
+		totalram_pages++;
+	}
+}
+
+static void __init __free_pages_memory(unsigned long start, unsigned long end)
+{
+	int order;
+
+	while (start < end) {
+		order = min(MAX_ORDER - 1UL, __ffs(start));
+
+		while (start + (1UL << order) > end)
+			order--;
+
+		__free_pages_bootmem(pfn_to_page(start), order);
+
+		start += (1UL << order);
+	}
+}
+
+static unsigned long __init __free_memory_core(phys_addr_t start,
+				 phys_addr_t end)
+{
+	unsigned long start_pfn = PFN_UP(start);
+	unsigned long end_pfn = min_t(unsigned long,
+				      PFN_DOWN(end), max_low_pfn);
+
+	if (start_pfn > end_pfn)
+		return 0;
+
+	__free_pages_memory(start_pfn, end_pfn);
+
+	return end_pfn - start_pfn;
+}
+
+static unsigned long __init free_low_memory_core_early(void)
+{
+	unsigned long count = 0;
+	phys_addr_t start, end;
+	u64 i;
+
+	memblock_clear_hotplug(0, -1);
+
+	for_each_free_mem_range(i, NUMA_NO_NODE, &start, &end, NULL)
+		count += __free_memory_core(start, end);
+
+#ifdef CONFIG_ARCH_DISCARD_MEMBLOCK
+	{
+		phys_addr_t size;
+
+		/* Free memblock.reserved array if it was allocated */
+		size = get_allocated_memblock_reserved_regions_info(&start);
+		if (size)
+			count += __free_memory_core(start, start + size);
+
+		/* Free memblock.memory array if it was allocated */
+		size = get_allocated_memblock_memory_regions_info(&start);
+		if (size)
+			count += __free_memory_core(start, start + size);
+	}
+#endif
+
+	return count;
+}
+
+static int reset_managed_pages_done __initdata;
+
+void reset_node_managed_pages(pg_data_t *pgdat)
+{
+	struct zone *z;
+
+	for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++)
+		z->managed_pages = 0;
+}
+
+void __init reset_all_zones_managed_pages(void)
+{
+	struct pglist_data *pgdat;
+
+	if (reset_managed_pages_done)
+		return;
+
+	for_each_online_pgdat(pgdat)
+		reset_node_managed_pages(pgdat);
+
+	reset_managed_pages_done = 1;
+}
+
+/**
+ * free_all_bootmem - release free pages to the buddy allocator
+ *
+ * Returns the number of pages actually released.
+ */
+unsigned long __init free_all_bootmem(void)
+{
+	unsigned long pages;
+
+	reset_all_zones_managed_pages();
+
+	/*
+	 * We need to use NUMA_NO_NODE instead of NODE_DATA(0)->node_id
+	 *  because in some case like Node0 doesn't have RAM installed
+	 *  low ram will be on Node1
+	 */
+	pages = free_low_memory_core_early();
+	totalram_pages += pages;
+
+	return pages;
+}
+
+/**
+ * free_bootmem_node - mark a page range as usable
+ * @pgdat: node the range resides on
+ * @physaddr: starting address of the range
+ * @size: size of the range in bytes
+ *
+ * Partial pages will be considered reserved and left as they are.
+ *
+ * The range must reside completely on the specified node.
+ */
+void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
+			      unsigned long size)
+{
+	memblock_free(physaddr, size);
+}
+
+/**
+ * free_bootmem - mark a page range as usable
+ * @addr: starting address of the range
+ * @size: size of the range in bytes
+ *
+ * Partial pages will be considered reserved and left as they are.
+ *
+ * The range must be contiguous but may span node boundaries.
+ */
+void __init free_bootmem(unsigned long addr, unsigned long size)
+{
+	memblock_free(addr, size);
+}
+
+static void * __init ___alloc_bootmem_nopanic(unsigned long size,
+					unsigned long align,
+					unsigned long goal,
+					unsigned long limit)
+{
+	void *ptr;
+
+	if (WARN_ON_ONCE(slab_is_available()))
+		return kzalloc(size, GFP_NOWAIT);
+
+restart:
+
+	ptr = __alloc_memory_core_early(NUMA_NO_NODE, size, align, goal, limit);
+
+	if (ptr)
+		return ptr;
+
+	if (goal != 0) {
+		goal = 0;
+		goto restart;
+	}
+
+	return NULL;
+}
+
+/**
+ * __alloc_bootmem_nopanic - allocate boot memory without panicking
+ * @size: size of the request in bytes
+ * @align: alignment of the region
+ * @goal: preferred starting address of the region
+ *
+ * The goal is dropped if it can not be satisfied and the allocation will
+ * fall back to memory below @goal.
+ *
+ * Allocation may happen on any node in the system.
+ *
+ * Returns NULL on failure.
+ */
+void * __init __alloc_bootmem_nopanic(unsigned long size, unsigned long align,
+					unsigned long goal)
+{
+	unsigned long limit = -1UL;
+
+	return ___alloc_bootmem_nopanic(size, align, goal, limit);
+}
+
+static void * __init ___alloc_bootmem(unsigned long size, unsigned long align,
+					unsigned long goal, unsigned long limit)
+{
+	void *mem = ___alloc_bootmem_nopanic(size, align, goal, limit);
+
+	if (mem)
+		return mem;
+	/*
+	 * Whoops, we cannot satisfy the allocation request.
+	 */
+	printk(KERN_ALERT "bootmem alloc of %lu bytes failed!\n", size);
+	panic("Out of memory");
+	return NULL;
+}
+
+/**
+ * __alloc_bootmem - allocate boot memory
+ * @size: size of the request in bytes
+ * @align: alignment of the region
+ * @goal: preferred starting address of the region
+ *
+ * The goal is dropped if it can not be satisfied and the allocation will
+ * fall back to memory below @goal.
+ *
+ * Allocation may happen on any node in the system.
+ *
+ * The function panics if the request can not be satisfied.
+ */
+void * __init __alloc_bootmem(unsigned long size, unsigned long align,
+			      unsigned long goal)
+{
+	unsigned long limit = -1UL;
+
+	return ___alloc_bootmem(size, align, goal, limit);
+}
+
+void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat,
+						   unsigned long size,
+						   unsigned long align,
+						   unsigned long goal,
+						   unsigned long limit)
+{
+	void *ptr;
+
+again:
+	ptr = __alloc_memory_core_early(pgdat->node_id, size, align,
+					goal, limit);
+	if (ptr)
+		return ptr;
+
+	ptr = __alloc_memory_core_early(NUMA_NO_NODE, size, align,
+					goal, limit);
+	if (ptr)
+		return ptr;
+
+	if (goal) {
+		goal = 0;
+		goto again;
+	}
+
+	return NULL;
+}
+
+void * __init __alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size,
+				   unsigned long align, unsigned long goal)
+{
+	if (WARN_ON_ONCE(slab_is_available()))
+		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
+
+	return ___alloc_bootmem_node_nopanic(pgdat, size, align, goal, 0);
+}
+
+static void * __init ___alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
+				    unsigned long align, unsigned long goal,
+				    unsigned long limit)
+{
+	void *ptr;
+
+	ptr = ___alloc_bootmem_node_nopanic(pgdat, size, align, goal, limit);
+	if (ptr)
+		return ptr;
+
+	printk(KERN_ALERT "bootmem alloc of %lu bytes failed!\n", size);
+	panic("Out of memory");
+	return NULL;
+}
+
+/**
+ * __alloc_bootmem_node - allocate boot memory from a specific node
+ * @pgdat: node to allocate from
+ * @size: size of the request in bytes
+ * @align: alignment of the region
+ * @goal: preferred starting address of the region
+ *
+ * The goal is dropped if it can not be satisfied and the allocation will
+ * fall back to memory below @goal.
+ *
+ * Allocation may fall back to any node in the system if the specified node
+ * can not hold the requested memory.
+ *
+ * The function panics if the request can not be satisfied.
+ */
+void * __init __alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
+				   unsigned long align, unsigned long goal)
+{
+	if (WARN_ON_ONCE(slab_is_available()))
+		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
+
+	return ___alloc_bootmem_node(pgdat, size, align, goal, 0);
+}
+
+void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size,
+				   unsigned long align, unsigned long goal)
+{
+	return __alloc_bootmem_node(pgdat, size, align, goal);
+}
+
+#ifndef ARCH_LOW_ADDRESS_LIMIT
+#define ARCH_LOW_ADDRESS_LIMIT	0xffffffffUL
+#endif
+
+/**
+ * __alloc_bootmem_low - allocate low boot memory
+ * @size: size of the request in bytes
+ * @align: alignment of the region
+ * @goal: preferred starting address of the region
+ *
+ * The goal is dropped if it can not be satisfied and the allocation will
+ * fall back to memory below @goal.
+ *
+ * Allocation may happen on any node in the system.
+ *
+ * The function panics if the request can not be satisfied.
+ */
+void * __init __alloc_bootmem_low(unsigned long size, unsigned long align,
+				  unsigned long goal)
+{
+	return ___alloc_bootmem(size, align, goal, ARCH_LOW_ADDRESS_LIMIT);
+}
+
+void * __init __alloc_bootmem_low_nopanic(unsigned long size,
+					  unsigned long align,
+					  unsigned long goal)
+{
+	return ___alloc_bootmem_nopanic(size, align, goal,
+					ARCH_LOW_ADDRESS_LIMIT);
+}
+
+/**
+ * __alloc_bootmem_low_node - allocate low boot memory from a specific node
+ * @pgdat: node to allocate from
+ * @size: size of the request in bytes
+ * @align: alignment of the region
+ * @goal: preferred starting address of the region
+ *
+ * The goal is dropped if it can not be satisfied and the allocation will
+ * fall back to memory below @goal.
+ *
+ * Allocation may fall back to any node in the system if the specified node
+ * can not hold the requested memory.
+ *
+ * The function panics if the request can not be satisfied.
+ */
+void * __init __alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long size,
+				       unsigned long align, unsigned long goal)
+{
+	if (WARN_ON_ONCE(slab_is_available()))
+		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
+
+	return ___alloc_bootmem_node(pgdat, size, align, goal,
+				     ARCH_LOW_ADDRESS_LIMIT);
+}

mm/oom_kill.c

@@ -0,0 +1,754 @@
+/*
+ *  linux/mm/oom_kill.c
+ * 
+ *  Copyright (C)  1998,2000  Rik van Riel
+ *	Thanks go out to Claus Fischer for some serious inspiration and
+ *	for goading me into coding this file...
+ *  Copyright (C)  2010  Google, Inc.
+ *	Rewritten by David Rientjes
+ *
+ *  The routines in this file are used to kill a process when
+ *  we're seriously out of memory. This gets called from __alloc_pages()
+ *  in mm/page_alloc.c when we really run out of memory.
+ *
+ *  Since we won't call these routines often (on a well-configured
+ *  machine) this file will double as a 'coding guide' and a signpost
+ *  for newbie kernel hackers. It features several pointers to major
+ *  kernel subsystems and hints as to where to find out what things do.
+ */
+
+#include <linux/oom.h>
+#include <linux/mm.h>
+#include <linux/err.h>
+#include <linux/gfp.h>
+#include <linux/sched.h>
+#include <linux/swap.h>
+#include <linux/timex.h>
+#include <linux/jiffies.h>
+#include <linux/cpuset.h>
+#include <linux/export.h>
+#include <linux/notifier.h>
+#include <linux/memcontrol.h>
+#include <linux/mempolicy.h>
+#include <linux/security.h>
+#include <linux/ptrace.h>
+#include <linux/freezer.h>
+#include <linux/ftrace.h>
+#include <linux/ratelimit.h>
+#include <linux/compaction.h>
+#include "internal.h"
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/oom.h>
+
+int sysctl_panic_on_oom;
+int sysctl_oom_kill_allocating_task;
+int sysctl_oom_dump_tasks = 1;
+static DEFINE_SPINLOCK(zone_scan_lock);
+
+#ifdef CONFIG_NUMA
+/**
+ * has_intersects_mems_allowed() - check task eligiblity for kill
+ * @start: task struct of which task to consider
+ * @mask: nodemask passed to page allocator for mempolicy ooms
+ *
+ * Task eligibility is determined by whether or not a candidate task, @tsk,
+ * shares the same mempolicy nodes as current if it is bound by such a policy
+ * and whether or not it has the same set of allowed cpuset nodes.
+ */
+static bool has_intersects_mems_allowed(struct task_struct *start,
+					const nodemask_t *mask)
+{
+	struct task_struct *tsk;
+	bool ret = false;
+
+	rcu_read_lock();
+	for_each_thread(start, tsk) {
+		if (mask) {
+			/*
+			 * If this is a mempolicy constrained oom, tsk's
+			 * cpuset is irrelevant.  Only return true if its
+			 * mempolicy intersects current, otherwise it may be
+			 * needlessly killed.
+			 */
+			ret = mempolicy_nodemask_intersects(tsk, mask);
+		} else {
+			/*
+			 * This is not a mempolicy constrained oom, so only
+			 * check the mems of tsk's cpuset.
+			 */
+			ret = cpuset_mems_allowed_intersects(current, tsk);
+		}
+		if (ret)
+			break;
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
+#else
+static bool has_intersects_mems_allowed(struct task_struct *tsk,
+					const nodemask_t *mask)
+{
+	return true;
+}
+#endif /* CONFIG_NUMA */
+
+/*
+ * The process p may have detached its own ->mm while exiting or through
+ * use_mm(), but one or more of its subthreads may still have a valid
+ * pointer.  Return p, or any of its subthreads with a valid ->mm, with
+ * task_lock() held.
+ */
+struct task_struct *find_lock_task_mm(struct task_struct *p)
+{
+	struct task_struct *t;
+
+	rcu_read_lock();
+
+	for_each_thread(p, t) {
+		task_lock(t);
+		if (likely(t->mm))
+			goto found;
+		task_unlock(t);
+	}
+	t = NULL;
+found:
+	rcu_read_unlock();
+
+	return t;
+}
+
+/* return true if the task is not adequate as candidate victim task. */
+static bool oom_unkillable_task(struct task_struct *p,
+		const struct mem_cgroup *memcg, const nodemask_t *nodemask)
+{
+	if (is_global_init(p))
+		return true;
+	if (p->flags & PF_KTHREAD)
+		return true;
+
+	/* When mem_cgroup_out_of_memory() and p is not member of the group */
+	if (memcg && !task_in_mem_cgroup(p, memcg))
+		return true;
+
+	/* p may not have freeable memory in nodemask */
+	if (!has_intersects_mems_allowed(p, nodemask))
+		return true;
+
+	return false;
+}
+
+/**
+ * oom_badness - heuristic function to determine which candidate task to kill
+ * @p: task struct of which task we should calculate
+ * @totalpages: total present RAM allowed for page allocation
+ *
+ * The heuristic for determining which task to kill is made to be as simple and
+ * predictable as possible.  The goal is to return the highest value for the
+ * task consuming the most memory to avoid subsequent oom failures.
+ */
+unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
+			  const nodemask_t *nodemask, unsigned long totalpages)
+{
+	long points;
+	long adj;
+
+	if (oom_unkillable_task(p, memcg, nodemask))
+		return 0;
+
+	p = find_lock_task_mm(p);
+	if (!p)
+		return 0;
+
+	adj = (long)p->signal->oom_score_adj;
+	if (adj == OOM_SCORE_ADJ_MIN) {
+		task_unlock(p);
+		return 0;
+	}
+
+	/*
+	 * The baseline for the badness score is the proportion of RAM that each
+	 * task's rss, pagetable and swap space use.
+	 */
+	points = get_mm_rss(p->mm) + atomic_long_read(&p->mm->nr_ptes) +
+		 get_mm_counter(p->mm, MM_SWAPENTS);
+	task_unlock(p);
+
+	/*
+	 * Root processes get 3% bonus, just like the __vm_enough_memory()
+	 * implementation used by LSMs.
+	 */
+	if (has_capability_noaudit(p, CAP_SYS_ADMIN))
+		points -= (points * 3) / 100;
+
+	/* Normalize to oom_score_adj units */
+	adj *= totalpages / 1000;
+	points += adj;
+
+	/*
+	 * Never return 0 for an eligible task regardless of the root bonus and
+	 * oom_score_adj (oom_score_adj can't be OOM_SCORE_ADJ_MIN here).
+	 */
+	return points > 0 ? points : 1;
+}
+
+/*
+ * Determine the type of allocation constraint.
+ */
+#ifdef CONFIG_NUMA
+static enum oom_constraint constrained_alloc(struct zonelist *zonelist,
+				gfp_t gfp_mask, nodemask_t *nodemask,
+				unsigned long *totalpages)
+{
+	struct zone *zone;
+	struct zoneref *z;
+	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
+	bool cpuset_limited = false;
+	int nid;
+
+	/* Default to all available memory */
+	*totalpages = totalram_pages + total_swap_pages;
+
+	if (!zonelist)
+		return CONSTRAINT_NONE;
+	/*
+	 * Reach here only when __GFP_NOFAIL is used. So, we should avoid
+	 * to kill current.We have to random task kill in this case.
+	 * Hopefully, CONSTRAINT_THISNODE...but no way to handle it, now.
+	 */
+	if (gfp_mask & __GFP_THISNODE)
+		return CONSTRAINT_NONE;
+
+	/*
+	 * This is not a __GFP_THISNODE allocation, so a truncated nodemask in
+	 * the page allocator means a mempolicy is in effect.  Cpuset policy
+	 * is enforced in get_page_from_freelist().
+	 */
+	if (nodemask && !nodes_subset(node_states[N_MEMORY], *nodemask)) {
+		*totalpages = total_swap_pages;
+		for_each_node_mask(nid, *nodemask)
+			*totalpages += node_spanned_pages(nid);
+		return CONSTRAINT_MEMORY_POLICY;
+	}
+
+	/* Check this allocation failure is caused by cpuset's wall function */
+	for_each_zone_zonelist_nodemask(zone, z, zonelist,
+			high_zoneidx, nodemask)
+		if (!cpuset_zone_allowed_softwall(zone, gfp_mask))
+			cpuset_limited = true;
+
+	if (cpuset_limited) {
+		*totalpages = total_swap_pages;
+		for_each_node_mask(nid, cpuset_current_mems_allowed)
+			*totalpages += node_spanned_pages(nid);
+		return CONSTRAINT_CPUSET;
+	}
+	return CONSTRAINT_NONE;
+}
+#else
+static enum oom_constraint constrained_alloc(struct zonelist *zonelist,
+				gfp_t gfp_mask, nodemask_t *nodemask,
+				unsigned long *totalpages)
+{
+	*totalpages = totalram_pages + total_swap_pages;
+	return CONSTRAINT_NONE;
+}
+#endif
+
+enum oom_scan_t oom_scan_process_thread(struct task_struct *task,
+		unsigned long totalpages, const nodemask_t *nodemask,
+		bool force_kill)
+{
+	if (oom_unkillable_task(task, NULL, nodemask))
+		return OOM_SCAN_CONTINUE;
+
+	/*
+	 * This task already has access to memory reserves and is being killed.
+	 * Don't allow any other task to have access to the reserves.
+	 */
+	if (test_tsk_thread_flag(task, TIF_MEMDIE)) {
+		if (unlikely(frozen(task)))
+			__thaw_task(task);
+		if (!force_kill)
+			return OOM_SCAN_ABORT;
+	}
+	if (!task->mm)
+		return OOM_SCAN_CONTINUE;
+
+	/*
+	 * If task is allocating a lot of memory and has been marked to be
+	 * killed first if it triggers an oom, then select it.
+	 */
+	if (oom_task_origin(task))
+		return OOM_SCAN_SELECT;
+
+	if (task->flags & PF_EXITING && !force_kill) {
+		/*
+		 * If this task is not being ptraced on exit, then wait for it
+		 * to finish before killing some other task unnecessarily.
+		 */
+		if (!(task->group_leader->ptrace & PT_TRACE_EXIT))
+			return OOM_SCAN_ABORT;
+	}
+	return OOM_SCAN_OK;
+}
+
+/*
+ * Simple selection loop. We chose the process with the highest
+ * number of 'points'.  Returns -1 on scan abort.
+ *
+ * (not docbooked, we don't want this one cluttering up the manual)
+ */
+static struct task_struct *select_bad_process(unsigned int *ppoints,
+		unsigned long totalpages, const nodemask_t *nodemask,
+		bool force_kill)
+{
+	struct task_struct *g, *p;
+	struct task_struct *chosen = NULL;
+	unsigned long chosen_points = 0;
+
+	rcu_read_lock();
+	for_each_process_thread(g, p) {
+		unsigned int points;
+
+		switch (oom_scan_process_thread(p, totalpages, nodemask,
+						force_kill)) {
+		case OOM_SCAN_SELECT:
+			chosen = p;
+			chosen_points = ULONG_MAX;
+			/* fall through */
+		case OOM_SCAN_CONTINUE:
+			continue;
+		case OOM_SCAN_ABORT:
+			rcu_read_unlock();
+			return (struct task_struct *)(-1UL);
+		case OOM_SCAN_OK:
+			break;
+		};
+		points = oom_badness(p, NULL, nodemask, totalpages);
+		if (!points || points < chosen_points)
+			continue;
+		/* Prefer thread group leaders for display purposes */
+		if (points == chosen_points && thread_group_leader(chosen))
+			continue;
+
+		chosen = p;
+		chosen_points = points;
+	}
+	if (chosen)
+		get_task_struct(chosen);
+	rcu_read_unlock();
+
+	*ppoints = chosen_points * 1000 / totalpages;
+	return chosen;
+}
+
+/**
+ * dump_tasks - dump current memory state of all system tasks
+ * @memcg: current's memory controller, if constrained
+ * @nodemask: nodemask passed to page allocator for mempolicy ooms
+ *
+ * Dumps the current memory state of all eligible tasks.  Tasks not in the same
+ * memcg, not in the same cpuset, or bound to a disjoint set of mempolicy nodes
+ * are not shown.
+ * State information includes task's pid, uid, tgid, vm size, rss, nr_ptes,
+ * swapents, oom_score_adj value, and name.
+ */
+static void dump_tasks(const struct mem_cgroup *memcg, const nodemask_t *nodemask)
+{
+	struct task_struct *p;
+	struct task_struct *task;
+
+	pr_info("[ pid ]   uid  tgid total_vm      rss nr_ptes swapents oom_score_adj name\n");
+	rcu_read_lock();
+	for_each_process(p) {
+		if (oom_unkillable_task(p, memcg, nodemask))
+			continue;
+
+		task = find_lock_task_mm(p);
+		if (!task) {
+			/*
+			 * This is a kthread or all of p's threads have already
+			 * detached their mm's.  There's no need to report
+			 * them; they can't be oom killed anyway.
+			 */
+			continue;
+		}
+
+		pr_info("[%5d] %5d %5d %8lu %8lu %7ld %8lu         %5hd %s\n",
+			task->pid, from_kuid(&init_user_ns, task_uid(task)),
+			task->tgid, task->mm->total_vm, get_mm_rss(task->mm),
+			atomic_long_read(&task->mm->nr_ptes),
+			get_mm_counter(task->mm, MM_SWAPENTS),
+			task->signal->oom_score_adj, task->comm);
+		task_unlock(task);
+	}
+	rcu_read_unlock();
+}
+
+static BLOCKING_NOTIFIER_HEAD(oomdebug_notify_list);
+
+int register_oomdebug_notifier(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_register(&oomdebug_notify_list, nb);
+}
+EXPORT_SYMBOL_GPL(register_oomdebug_notifier);
+
+int unregister_oomdebug_notifier(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_unregister(&oomdebug_notify_list, nb);
+}
+EXPORT_SYMBOL_GPL(unregister_oomdebug_notifier);
+
+static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order,
+			struct mem_cgroup *memcg, const nodemask_t *nodemask)
+{
+	struct zone *zone;
+	struct zoneref *z;
+	int alloc_flags = 0;
+	int ret = 0;
+
+	task_lock(current);
+	pr_warning("%s invoked oom-killer: gfp_mask=0x%x, order=%d, "
+		"oom_score_adj=%hd\n",
+		current->comm, gfp_mask, order,
+		current->signal->oom_score_adj);
+	cpuset_print_task_mems_allowed(current);
+	task_unlock(current);
+	dump_stack();
+	if (memcg)
+		mem_cgroup_print_oom_info(memcg, p);
+	else {
+		show_mem(SHOW_MEM_FILTER_NODES);
+#ifdef CONFIG_CMA
+		if (gfpflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)
+			alloc_flags |= ALLOC_CMA;
+#endif
+		for_each_zone_zonelist_nodemask(zone, z, node_zonelist(0,
+					gfp_mask), gfp_zone(gfp_mask), NULL) {
+			pr_info("%s: HIGH wmark ok? (%s)"
+				" LOW wmark ok? %s)"
+				" MIN wmark ok? (%s)"
+				" compaction_suitable %lu\n", zone->name,
+			(zone_watermark_ok(zone, order,
+			high_wmark_pages(zone), 0, alloc_flags) ? "yes" : "no"),
+			(zone_watermark_ok(zone, order,
+			low_wmark_pages(zone), 0, alloc_flags) ? "yes" : "no"),
+			(zone_watermark_ok(zone, order,
+			min_wmark_pages(zone), 0, alloc_flags) ? "yes" : "no"),
+			compaction_suitable(zone, order));
+		}
+	}
+	if (sysctl_oom_dump_tasks)
+		dump_tasks(memcg, nodemask);
+	blocking_notifier_call_chain(&oomdebug_notify_list, 0, &ret);
+}
+
+/*
+ * Number of OOM killer invocations (including memcg OOM killer).
+ * Primarily used by PM freezer to check for potential races with
+ * OOM killed frozen task.
+ */
+static atomic_t oom_kills = ATOMIC_INIT(0);
+
+int oom_kills_count(void)
+{
+	return atomic_read(&oom_kills);
+}
+
+void note_oom_kill(void)
+{
+	atomic_inc(&oom_kills);
+}
+
+#define K(x) ((x) << (PAGE_SHIFT-10))
+/*
+ * Must be called while holding a reference to p, which will be released upon
+ * returning.
+ */
+void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
+		      unsigned int points, unsigned long totalpages,
+		      struct mem_cgroup *memcg, nodemask_t *nodemask,
+		      const char *message)
+{
+	struct task_struct *victim = p;
+	struct task_struct *child;
+	struct task_struct *t;
+	struct mm_struct *mm;
+	unsigned int victim_points = 0;
+	static DEFINE_RATELIMIT_STATE(oom_rs, DEFAULT_RATELIMIT_INTERVAL,
+					      DEFAULT_RATELIMIT_BURST);
+
+	/*
+	 * If the task is already exiting, don't alarm the sysadmin or kill
+	 * its children or threads, just set TIF_MEMDIE so it can die quickly
+	 */
+	if (p->flags & PF_EXITING) {
+		set_tsk_thread_flag(p, TIF_MEMDIE);
+		put_task_struct(p);
+		return;
+	}
+
+	if (__ratelimit(&oom_rs))
+		dump_header(p, gfp_mask, order, memcg, nodemask);
+
+	task_lock(p);
+	pr_err("%s: Kill process %d (%s) score %d or sacrifice child\n",
+		message, task_pid_nr(p), p->comm, points);
+	task_unlock(p);
+
+	/*
+	 * If any of p's children has a different mm and is eligible for kill,
+	 * the one with the highest oom_badness() score is sacrificed for its
+	 * parent.  This attempts to lose the minimal amount of work done while
+	 * still freeing memory.
+	 */
+	read_lock(&tasklist_lock);
+	for_each_thread(p, t) {
+		list_for_each_entry(child, &t->children, sibling) {
+			unsigned int child_points;
+
+			if (child->mm == p->mm)
+				continue;
+			/*
+			 * oom_badness() returns 0 if the thread is unkillable
+			 */
+			child_points = oom_badness(child, memcg, nodemask,
+								totalpages);
+			if (child_points > victim_points) {
+				put_task_struct(victim);
+				victim = child;
+				victim_points = child_points;
+				get_task_struct(victim);
+			}
+		}
+	}
+	read_unlock(&tasklist_lock);
+
+	p = find_lock_task_mm(victim);
+	if (!p) {
+		put_task_struct(victim);
+		return;
+	} else if (victim != p) {
+		get_task_struct(p);
+		put_task_struct(victim);
+		victim = p;
+	}
+
+	/* mm cannot safely be dereferenced after task_unlock(victim) */
+	mm = victim->mm;
+	pr_err("Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB, file-rss:%lukB\n",
+		task_pid_nr(victim), victim->comm, K(victim->mm->total_vm),
+		K(get_mm_counter(victim->mm, MM_ANONPAGES)),
+		K(get_mm_counter(victim->mm, MM_FILEPAGES)));
+	task_unlock(victim);
+
+	/*
+	 * Kill all user processes sharing victim->mm in other thread groups, if
+	 * any.  They don't get access to memory reserves, though, to avoid
+	 * depletion of all memory.  This prevents mm->mmap_sem livelock when an
+	 * oom killed thread cannot exit because it requires the semaphore and
+	 * its contended by another thread trying to allocate memory itself.
+	 * That thread will now get access to memory reserves since it has a
+	 * pending fatal signal.
+	 */
+	rcu_read_lock();
+	for_each_process(p)
+		if (p->mm == mm && !same_thread_group(p, victim) &&
+		    !(p->flags & PF_KTHREAD)) {
+			if (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN)
+				continue;
+
+			task_lock(p);	/* Protect ->comm from prctl() */
+			pr_err("Kill process %d (%s) sharing same memory\n",
+				task_pid_nr(p), p->comm);
+			task_unlock(p);
+			do_send_sig_info(SIGKILL, SEND_SIG_FORCED, p, true);
+		}
+	rcu_read_unlock();
+
+	set_tsk_thread_flag(victim, TIF_MEMDIE);
+	do_send_sig_info(SIGKILL, SEND_SIG_FORCED, victim, true);
+	put_task_struct(victim);
+}
+#undef K
+
+/*
+ * Determines whether the kernel must panic because of the panic_on_oom sysctl.
+ */
+void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask,
+			int order, const nodemask_t *nodemask)
+{
+	if (likely(!sysctl_panic_on_oom))
+		return;
+	if (sysctl_panic_on_oom != 2) {
+		/*
+		 * panic_on_oom == 1 only affects CONSTRAINT_NONE, the kernel
+		 * does not panic for cpuset, mempolicy, or memcg allocation
+		 * failures.
+		 */
+		if (constraint != CONSTRAINT_NONE)
+			return;
+	}
+	dump_header(NULL, gfp_mask, order, NULL, nodemask);
+	panic("Out of memory: %s panic_on_oom is enabled\n",
+		sysctl_panic_on_oom == 2 ? "compulsory" : "system-wide");
+}
+
+static BLOCKING_NOTIFIER_HEAD(oom_notify_list);
+
+int register_oom_notifier(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_register(&oom_notify_list, nb);
+}
+EXPORT_SYMBOL_GPL(register_oom_notifier);
+
+int unregister_oom_notifier(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_unregister(&oom_notify_list, nb);
+}
+EXPORT_SYMBOL_GPL(unregister_oom_notifier);
+
+/*
+ * Try to acquire the OOM killer lock for the zones in zonelist.  Returns zero
+ * if a parallel OOM killing is already taking place that includes a zone in
+ * the zonelist.  Otherwise, locks all zones in the zonelist and returns 1.
+ */
+bool oom_zonelist_trylock(struct zonelist *zonelist, gfp_t gfp_mask)
+{
+	struct zoneref *z;
+	struct zone *zone;
+	bool ret = true;
+
+	spin_lock(&zone_scan_lock);
+	for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask))
+		if (test_bit(ZONE_OOM_LOCKED, &zone->flags)) {
+			ret = false;
+			goto out;
+		}
+
+	/*
+	 * Lock each zone in the zonelist under zone_scan_lock so a parallel
+	 * call to oom_zonelist_trylock() doesn't succeed when it shouldn't.
+	 */
+	for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask))
+		set_bit(ZONE_OOM_LOCKED, &zone->flags);
+
+out:
+	spin_unlock(&zone_scan_lock);
+	return ret;
+}
+
+/*
+ * Clears the ZONE_OOM_LOCKED flag for all zones in the zonelist so that failed
+ * allocation attempts with zonelists containing them may now recall the OOM
+ * killer, if necessary.
+ */
+void oom_zonelist_unlock(struct zonelist *zonelist, gfp_t gfp_mask)
+{
+	struct zoneref *z;
+	struct zone *zone;
+
+	spin_lock(&zone_scan_lock);
+	for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask))
+		clear_bit(ZONE_OOM_LOCKED, &zone->flags);
+	spin_unlock(&zone_scan_lock);
+}
+
+/**
+ * out_of_memory - kill the "best" process when we run out of memory
+ * @zonelist: zonelist pointer
+ * @gfp_mask: memory allocation flags
+ * @order: amount of memory being requested as a power of 2
+ * @nodemask: nodemask passed to page allocator
+ * @force_kill: true if a task must be killed, even if others are exiting
+ *
+ * If we run out of memory, we have the choice between either
+ * killing a random task (bad), letting the system crash (worse)
+ * OR try to be smart about which process to kill. Note that we
+ * don't have to be perfect here, we just have to be good.
+ */
+void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
+		int order, nodemask_t *nodemask, bool force_kill)
+{
+	const nodemask_t *mpol_mask;
+	struct task_struct *p;
+	unsigned long totalpages;
+	unsigned long freed = 0;
+	unsigned int uninitialized_var(points);
+	enum oom_constraint constraint = CONSTRAINT_NONE;
+	int killed = 0;
+
+	blocking_notifier_call_chain(&oom_notify_list, 0, &freed);
+	if (freed > 0)
+		/* Got some memory back in the last second. */
+		return;
+
+	/*
+	 * If current has a pending SIGKILL or is exiting, then automatically
+	 * select it.  The goal is to allow it to allocate so that it may
+	 * quickly exit and free its memory.
+	 */
+	if (fatal_signal_pending(current) || current->flags & PF_EXITING) {
+		set_thread_flag(TIF_MEMDIE);
+		return;
+	}
+
+	/*
+	 * Check if there were limitations on the allocation (only relevant for
+	 * NUMA) that may require different handling.
+	 */
+	constraint = constrained_alloc(zonelist, gfp_mask, nodemask,
+						&totalpages);
+	mpol_mask = (constraint == CONSTRAINT_MEMORY_POLICY) ? nodemask : NULL;
+	check_panic_on_oom(constraint, gfp_mask, order, mpol_mask);
+
+	if (sysctl_oom_kill_allocating_task && current->mm &&
+	    !oom_unkillable_task(current, NULL, nodemask) &&
+	    current->signal->oom_score_adj != OOM_SCORE_ADJ_MIN) {
+		get_task_struct(current);
+		oom_kill_process(current, gfp_mask, order, 0, totalpages, NULL,
+				 nodemask,
+				 "Out of memory (oom_kill_allocating_task)");
+		goto out;
+	}
+
+	p = select_bad_process(&points, totalpages, mpol_mask, force_kill);
+	/* Found nothing?!?! Either we hang forever, or we panic. */
+	if (!p) {
+		dump_header(NULL, gfp_mask, order, NULL, mpol_mask);
+		panic("Out of memory and no killable processes...\n");
+	}
+	if (p != (void *)-1UL) {
+		oom_kill_process(p, gfp_mask, order, points, totalpages, NULL,
+				 nodemask, "Out of memory");
+		killed = 1;
+	}
+out:
+	/*
+	 * Give the killed threads a good chance of exiting before trying to
+	 * allocate memory again.
+	 */
+	if (killed)
+		schedule_timeout_killable(1);
+}
+
+/*
+ * The pagefault handler calls here because it is out of memory, so kill a
+ * memory-hogging task.  If any populated zone has ZONE_OOM_LOCKED set, a
+ * parallel oom killing is already in progress so do nothing.
+ */
+void pagefault_out_of_memory(void)
+{
+	struct zonelist *zonelist;
+
+	if (mem_cgroup_oom_synchronize(true))
+		return;
+
+	zonelist = node_zonelist(first_memory_node, GFP_KERNEL);
+	if (oom_zonelist_trylock(zonelist, GFP_KERNEL)) {
+		out_of_memory(NULL, 0, 0, NULL, false);
+		oom_zonelist_unlock(zonelist, GFP_KERNEL);
+	}
+}

mm/page_cgroup.c

@@ -0,0 +1,530 @@
+#include <linux/mm.h>
+#include <linux/mmzone.h>
+#include <linux/bootmem.h>
+#include <linux/bit_spinlock.h>
+#include <linux/page_cgroup.h>
+#include <linux/hash.h>
+#include <linux/slab.h>
+#include <linux/memory.h>
+#include <linux/vmalloc.h>
+#include <linux/cgroup.h>
+#include <linux/swapops.h>
+#include <linux/kmemleak.h>
+
+static unsigned long total_usage;
+
+#if !defined(CONFIG_SPARSEMEM)
+
+
+void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat)
+{
+	pgdat->node_page_cgroup = NULL;
+}
+
+struct page_cgroup *lookup_page_cgroup(struct page *page)
+{
+	unsigned long pfn = page_to_pfn(page);
+	unsigned long offset;
+	struct page_cgroup *base;
+
+	base = NODE_DATA(page_to_nid(page))->node_page_cgroup;
+#ifdef CONFIG_DEBUG_VM
+	/*
+	 * The sanity checks the page allocator does upon freeing a
+	 * page can reach here before the page_cgroup arrays are
+	 * allocated when feeding a range of pages to the allocator
+	 * for the first time during bootup or memory hotplug.
+	 */
+	if (unlikely(!base))
+		return NULL;
+#endif
+	offset = pfn - NODE_DATA(page_to_nid(page))->node_start_pfn;
+	return base + offset;
+}
+
+static int __init alloc_node_page_cgroup(int nid)
+{
+	struct page_cgroup *base;
+	unsigned long table_size;
+	unsigned long nr_pages;
+
+	nr_pages = NODE_DATA(nid)->node_spanned_pages;
+	if (!nr_pages)
+		return 0;
+
+	table_size = sizeof(struct page_cgroup) * nr_pages;
+
+	base = memblock_virt_alloc_try_nid_nopanic(
+			table_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS),
+			BOOTMEM_ALLOC_ACCESSIBLE, nid);
+	if (!base)
+		return -ENOMEM;
+	NODE_DATA(nid)->node_page_cgroup = base;
+	total_usage += table_size;
+	return 0;
+}
+
+void __init page_cgroup_init_flatmem(void)
+{
+
+	int nid, fail;
+
+	if (mem_cgroup_disabled())
+		return;
+
+	for_each_online_node(nid)  {
+		fail = alloc_node_page_cgroup(nid);
+		if (fail)
+			goto fail;
+	}
+	printk(KERN_INFO "allocated %ld bytes of page_cgroup\n", total_usage);
+	printk(KERN_INFO "please try 'cgroup_disable=memory' option if you"
+	" don't want memory cgroups\n");
+	return;
+fail:
+	printk(KERN_CRIT "allocation of page_cgroup failed.\n");
+	printk(KERN_CRIT "please try 'cgroup_disable=memory' boot option\n");
+	panic("Out of memory");
+}
+
+#else /* CONFIG_FLAT_NODE_MEM_MAP */
+
+struct page_cgroup *lookup_page_cgroup(struct page *page)
+{
+	unsigned long pfn = page_to_pfn(page);
+	struct mem_section *section = __pfn_to_section(pfn);
+#ifdef CONFIG_DEBUG_VM
+	/*
+	 * The sanity checks the page allocator does upon freeing a
+	 * page can reach here before the page_cgroup arrays are
+	 * allocated when feeding a range of pages to the allocator
+	 * for the first time during bootup or memory hotplug.
+	 */
+	if (!section->page_cgroup)
+		return NULL;
+#endif
+	return section->page_cgroup + pfn;
+}
+
+static void *__meminit alloc_page_cgroup(size_t size, int nid)
+{
+	gfp_t flags = GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN;
+	void *addr = NULL;
+
+	addr = alloc_pages_exact_nid(nid, size, flags);
+	if (addr) {
+		kmemleak_alloc(addr, size, 1, flags);
+		return addr;
+	}
+
+	if (node_state(nid, N_HIGH_MEMORY))
+		addr = vzalloc_node(size, nid);
+	else
+		addr = vzalloc(size);
+
+	return addr;
+}
+
+static int __meminit init_section_page_cgroup(unsigned long pfn, int nid)
+{
+	struct mem_section *section;
+	struct page_cgroup *base;
+	unsigned long table_size;
+
+	section = __pfn_to_section(pfn);
+
+	if (section->page_cgroup)
+		return 0;
+
+	table_size = sizeof(struct page_cgroup) * PAGES_PER_SECTION;
+	base = alloc_page_cgroup(table_size, nid);
+
+	/*
+	 * The value stored in section->page_cgroup is (base - pfn)
+	 * and it does not point to the memory block allocated above,
+	 * causing kmemleak false positives.
+	 */
+	kmemleak_not_leak(base);
+
+	if (!base) {
+		printk(KERN_ERR "page cgroup allocation failure\n");
+		return -ENOMEM;
+	}
+
+	/*
+	 * The passed "pfn" may not be aligned to SECTION.  For the calculation
+	 * we need to apply a mask.
+	 */
+	pfn &= PAGE_SECTION_MASK;
+	section->page_cgroup = base - pfn;
+	total_usage += table_size;
+	return 0;
+}
+#ifdef CONFIG_MEMORY_HOTPLUG
+static void free_page_cgroup(void *addr)
+{
+	if (is_vmalloc_addr(addr)) {
+		vfree(addr);
+	} else {
+		struct page *page = virt_to_page(addr);
+		size_t table_size =
+			sizeof(struct page_cgroup) * PAGES_PER_SECTION;
+
+		BUG_ON(PageReserved(page));
+		kmemleak_free(addr);
+		free_pages_exact(addr, table_size);
+	}
+}
+
+static void __free_page_cgroup(unsigned long pfn)
+{
+	struct mem_section *ms;
+	struct page_cgroup *base;
+
+	ms = __pfn_to_section(pfn);
+	if (!ms || !ms->page_cgroup)
+		return;
+	base = ms->page_cgroup + pfn;
+	free_page_cgroup(base);
+	ms->page_cgroup = NULL;
+}
+
+static int __meminit online_page_cgroup(unsigned long start_pfn,
+				unsigned long nr_pages,
+				int nid)
+{
+	unsigned long start, end, pfn;
+	int fail = 0;
+
+	start = SECTION_ALIGN_DOWN(start_pfn);
+	end = SECTION_ALIGN_UP(start_pfn + nr_pages);
+
+	if (nid == -1) {
+		/*
+		 * In this case, "nid" already exists and contains valid memory.
+		 * "start_pfn" passed to us is a pfn which is an arg for
+		 * online__pages(), and start_pfn should exist.
+		 */
+		nid = pfn_to_nid(start_pfn);
+		VM_BUG_ON(!node_state(nid, N_ONLINE));
+	}
+
+	for (pfn = start; !fail && pfn < end; pfn += PAGES_PER_SECTION) {
+		if (!pfn_present(pfn))
+			continue;
+		fail = init_section_page_cgroup(pfn, nid);
+	}
+	if (!fail)
+		return 0;
+
+	/* rollback */
+	for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION)
+		__free_page_cgroup(pfn);
+
+	return -ENOMEM;
+}
+
+static int __meminit offline_page_cgroup(unsigned long start_pfn,
+				unsigned long nr_pages, int nid)
+{
+	unsigned long start, end, pfn;
+
+	start = SECTION_ALIGN_DOWN(start_pfn);
+	end = SECTION_ALIGN_UP(start_pfn + nr_pages);
+
+	for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION)
+		__free_page_cgroup(pfn);
+	return 0;
+
+}
+
+static int __meminit page_cgroup_callback(struct notifier_block *self,
+			       unsigned long action, void *arg)
+{
+	struct memory_notify *mn = arg;
+	int ret = 0;
+	switch (action) {
+	case MEM_GOING_ONLINE:
+		ret = online_page_cgroup(mn->start_pfn,
+				   mn->nr_pages, mn->status_change_nid);
+		break;
+	case MEM_OFFLINE:
+		offline_page_cgroup(mn->start_pfn,
+				mn->nr_pages, mn->status_change_nid);
+		break;
+	case MEM_CANCEL_ONLINE:
+		offline_page_cgroup(mn->start_pfn,
+				mn->nr_pages, mn->status_change_nid);
+		break;
+	case MEM_GOING_OFFLINE:
+		break;
+	case MEM_ONLINE:
+	case MEM_CANCEL_OFFLINE:
+		break;
+	}
+
+	return notifier_from_errno(ret);
+}
+
+#endif
+
+void __init page_cgroup_init(void)
+{
+	unsigned long pfn;
+	int nid;
+
+	if (mem_cgroup_disabled())
+		return;
+
+	for_each_node_state(nid, N_MEMORY) {
+		unsigned long start_pfn, end_pfn;
+
+		start_pfn = node_start_pfn(nid);
+		end_pfn = node_end_pfn(nid);
+		/*
+		 * start_pfn and end_pfn may not be aligned to SECTION and the
+		 * page->flags of out of node pages are not initialized.  So we
+		 * scan [start_pfn, the biggest section's pfn < end_pfn) here.
+		 */
+		for (pfn = start_pfn;
+		     pfn < end_pfn;
+                     pfn = ALIGN(pfn + 1, PAGES_PER_SECTION)) {
+
+			if (!pfn_valid(pfn))
+				continue;
+			/*
+			 * Nodes's pfns can be overlapping.
+			 * We know some arch can have a nodes layout such as
+			 * -------------pfn-------------->
+			 * N0 | N1 | N2 | N0 | N1 | N2|....
+			 */
+			if (pfn_to_nid(pfn) != nid)
+				continue;
+			if (init_section_page_cgroup(pfn, nid))
+				goto oom;
+		}
+	}
+	hotplug_memory_notifier(page_cgroup_callback, 0);
+	printk(KERN_INFO "allocated %ld bytes of page_cgroup\n", total_usage);
+	printk(KERN_INFO "please try 'cgroup_disable=memory' option if you "
+			 "don't want memory cgroups\n");
+	return;
+oom:
+	printk(KERN_CRIT "try 'cgroup_disable=memory' boot option\n");
+	panic("Out of memory");
+}
+
+void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat)
+{
+	return;
+}
+
+#endif
+
+
+#ifdef CONFIG_MEMCG_SWAP
+
+static DEFINE_MUTEX(swap_cgroup_mutex);
+struct swap_cgroup_ctrl {
+	struct page **map;
+	unsigned long length;
+	spinlock_t	lock;
+};
+
+static struct swap_cgroup_ctrl swap_cgroup_ctrl[MAX_SWAPFILES];
+
+struct swap_cgroup {
+	unsigned short		id;
+};
+#define SC_PER_PAGE	(PAGE_SIZE/sizeof(struct swap_cgroup))
+
+/*
+ * SwapCgroup implements "lookup" and "exchange" operations.
+ * In typical usage, this swap_cgroup is accessed via memcg's charge/uncharge
+ * against SwapCache. At swap_free(), this is accessed directly from swap.
+ *
+ * This means,
+ *  - we have no race in "exchange" when we're accessed via SwapCache because
+ *    SwapCache(and its swp_entry) is under lock.
+ *  - When called via swap_free(), there is no user of this entry and no race.
+ * Then, we don't need lock around "exchange".
+ *
+ * TODO: we can push these buffers out to HIGHMEM.
+ */
+
+/*
+ * allocate buffer for swap_cgroup.
+ */
+static int swap_cgroup_prepare(int type)
+{
+	struct page *page;
+	struct swap_cgroup_ctrl *ctrl;
+	unsigned long idx, max;
+
+	ctrl = &swap_cgroup_ctrl[type];
+
+	for (idx = 0; idx < ctrl->length; idx++) {
+		page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+		if (!page)
+			goto not_enough_page;
+		ctrl->map[idx] = page;
+	}
+	return 0;
+not_enough_page:
+	max = idx;
+	for (idx = 0; idx < max; idx++)
+		__free_page(ctrl->map[idx]);
+
+	return -ENOMEM;
+}
+
+static struct swap_cgroup *lookup_swap_cgroup(swp_entry_t ent,
+					struct swap_cgroup_ctrl **ctrlp)
+{
+	pgoff_t offset = swp_offset(ent);
+	struct swap_cgroup_ctrl *ctrl;
+	struct page *mappage;
+	struct swap_cgroup *sc;
+
+	ctrl = &swap_cgroup_ctrl[swp_type(ent)];
+	if (ctrlp)
+		*ctrlp = ctrl;
+
+	mappage = ctrl->map[offset / SC_PER_PAGE];
+	sc = page_address(mappage);
+	return sc + offset % SC_PER_PAGE;
+}
+
+/**
+ * swap_cgroup_cmpxchg - cmpxchg mem_cgroup's id for this swp_entry.
+ * @ent: swap entry to be cmpxchged
+ * @old: old id
+ * @new: new id
+ *
+ * Returns old id at success, 0 at failure.
+ * (There is no mem_cgroup using 0 as its id)
+ */
+unsigned short swap_cgroup_cmpxchg(swp_entry_t ent,
+					unsigned short old, unsigned short new)
+{
+	struct swap_cgroup_ctrl *ctrl;
+	struct swap_cgroup *sc;
+	unsigned long flags;
+	unsigned short retval;
+
+	sc = lookup_swap_cgroup(ent, &ctrl);
+
+	spin_lock_irqsave(&ctrl->lock, flags);
+	retval = sc->id;
+	if (retval == old)
+		sc->id = new;
+	else
+		retval = 0;
+	spin_unlock_irqrestore(&ctrl->lock, flags);
+	return retval;
+}
+
+/**
+ * swap_cgroup_record - record mem_cgroup for this swp_entry.
+ * @ent: swap entry to be recorded into
+ * @id: mem_cgroup to be recorded
+ *
+ * Returns old value at success, 0 at failure.
+ * (Of course, old value can be 0.)
+ */
+unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id)
+{
+	struct swap_cgroup_ctrl *ctrl;
+	struct swap_cgroup *sc;
+	unsigned short old;
+	unsigned long flags;
+
+	sc = lookup_swap_cgroup(ent, &ctrl);
+
+	spin_lock_irqsave(&ctrl->lock, flags);
+	old = sc->id;
+	sc->id = id;
+	spin_unlock_irqrestore(&ctrl->lock, flags);
+
+	return old;
+}
+
+/**
+ * lookup_swap_cgroup_id - lookup mem_cgroup id tied to swap entry
+ * @ent: swap entry to be looked up.
+ *
+ * Returns ID of mem_cgroup at success. 0 at failure. (0 is invalid ID)
+ */
+unsigned short lookup_swap_cgroup_id(swp_entry_t ent)
+{
+	return lookup_swap_cgroup(ent, NULL)->id;
+}
+
+int swap_cgroup_swapon(int type, unsigned long max_pages)
+{
+	void *array;
+	unsigned long array_size;
+	unsigned long length;
+	struct swap_cgroup_ctrl *ctrl;
+
+	if (!do_swap_account)
+		return 0;
+
+	length = DIV_ROUND_UP(max_pages, SC_PER_PAGE);
+	array_size = length * sizeof(void *);
+
+	array = vzalloc(array_size);
+	if (!array)
+		goto nomem;
+
+	ctrl = &swap_cgroup_ctrl[type];
+	mutex_lock(&swap_cgroup_mutex);
+	ctrl->length = length;
+	ctrl->map = array;
+	spin_lock_init(&ctrl->lock);
+	if (swap_cgroup_prepare(type)) {
+		/* memory shortage */
+		ctrl->map = NULL;
+		ctrl->length = 0;
+		mutex_unlock(&swap_cgroup_mutex);
+		vfree(array);
+		goto nomem;
+	}
+	mutex_unlock(&swap_cgroup_mutex);
+
+	return 0;
+nomem:
+	printk(KERN_INFO "couldn't allocate enough memory for swap_cgroup.\n");
+	printk(KERN_INFO
+		"swap_cgroup can be disabled by swapaccount=0 boot option\n");
+	return -ENOMEM;
+}
+
+void swap_cgroup_swapoff(int type)
+{
+	struct page **map;
+	unsigned long i, length;
+	struct swap_cgroup_ctrl *ctrl;
+
+	if (!do_swap_account)
+		return;
+
+	mutex_lock(&swap_cgroup_mutex);
+	ctrl = &swap_cgroup_ctrl[type];
+	map = ctrl->map;
+	length = ctrl->length;
+	ctrl->map = NULL;
+	ctrl->length = 0;
+	mutex_unlock(&swap_cgroup_mutex);
+
+	if (map) {
+		for (i = 0; i < length; i++) {
+			struct page *page = map[i];
+			if (page)
+				__free_page(page);
+		}
+		vfree(map);
+	}
+}
+
+#endif

mm/page_io.c

@@ -0,0 +1,397 @@
+/*
+ *  linux/mm/page_io.c
+ *
+ *  Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
+ *
+ *  Swap reorganised 29.12.95, 
+ *  Asynchronous swapping added 30.12.95. Stephen Tweedie
+ *  Removed race in async swapping. 14.4.1996. Bruno Haible
+ *  Add swap of shared pages through the page cache. 20.2.1998. Stephen Tweedie
+ *  Always use brw_page, life becomes simpler. 12 May 1998 Eric Biederman
+ */
+
+#include <linux/mm.h>
+#include <linux/kernel_stat.h>
+#include <linux/gfp.h>
+#include <linux/pagemap.h>
+#include <linux/swap.h>
+#include <linux/bio.h>
+#include <linux/swapops.h>
+#include <linux/buffer_head.h>
+#include <linux/writeback.h>
+#include <linux/frontswap.h>
+#include <linux/aio.h>
+#include <linux/blkdev.h>
+#include <asm/pgtable.h>
+
+static struct bio *get_swap_bio(gfp_t gfp_flags,
+				struct page *page, bio_end_io_t end_io)
+{
+	struct bio *bio;
+
+	bio = bio_alloc(gfp_flags, 1);
+	if (bio) {
+		bio->bi_iter.bi_sector = map_swap_page(page, &bio->bi_bdev);
+		bio->bi_iter.bi_sector <<= PAGE_SHIFT - 9;
+		bio->bi_io_vec[0].bv_page = page;
+		bio->bi_io_vec[0].bv_len = PAGE_SIZE;
+		bio->bi_io_vec[0].bv_offset = 0;
+		bio->bi_vcnt = 1;
+		bio->bi_iter.bi_size = PAGE_SIZE;
+		bio->bi_end_io = end_io;
+	}
+	return bio;
+}
+
+void end_swap_bio_write(struct bio *bio, int err)
+{
+	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
+	struct page *page = bio->bi_io_vec[0].bv_page;
+
+	if (!uptodate) {
+		SetPageError(page);
+		/*
+		 * We failed to write the page out to swap-space.
+		 * Re-dirty the page in order to avoid it being reclaimed.
+		 * Also print a dire warning that things will go BAD (tm)
+		 * very quickly.
+		 *
+		 * Also clear PG_reclaim to avoid rotate_reclaimable_page()
+		 */
+		set_page_dirty(page);
+#ifndef CONFIG_VNSWAP
+		printk(KERN_ALERT "Write-error on swap-device (%u:%u:%Lu)\n",
+				imajor(bio->bi_bdev->bd_inode),
+				iminor(bio->bi_bdev->bd_inode),
+				(unsigned long long)bio->bi_iter.bi_sector);
+#endif
+		ClearPageReclaim(page);
+	}
+	end_page_writeback(page);
+	bio_put(bio);
+}
+
+void end_swap_bio_read(struct bio *bio, int err)
+{
+	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
+	struct page *page = bio->bi_io_vec[0].bv_page;
+
+	if (!uptodate) {
+		SetPageError(page);
+		ClearPageUptodate(page);
+		printk(KERN_ALERT "Read-error on swap-device (%u:%u:%Lu)\n",
+				imajor(bio->bi_bdev->bd_inode),
+				iminor(bio->bi_bdev->bd_inode),
+				(unsigned long long)bio->bi_iter.bi_sector);
+		goto out;
+	}
+
+	SetPageUptodate(page);
+
+	/*
+	 * There is no guarantee that the page is in swap cache - the software
+	 * suspend code (at least) uses end_swap_bio_read() against a non-
+	 * swapcache page.  So we must check PG_swapcache before proceeding with
+	 * this optimization.
+	 */
+	if (likely(PageSwapCache(page))) {
+		struct swap_info_struct *sis;
+
+		sis = page_swap_info(page);
+		if (sis->flags & SWP_BLKDEV) {
+			/*
+			 * The swap subsystem performs lazy swap slot freeing,
+			 * expecting that the page will be swapped out again.
+			 * So we can avoid an unnecessary write if the page
+			 * isn't redirtied.
+			 * This is good for real swap storage because we can
+			 * reduce unnecessary I/O and enhance wear-leveling
+			 * if an SSD is used as the as swap device.
+			 * But if in-memory swap device (eg zram) is used,
+			 * this causes a duplicated copy between uncompressed
+			 * data in VM-owned memory and compressed data in
+			 * zram-owned memory.  So let's free zram-owned memory
+			 * and make the VM-owned decompressed page *dirty*,
+			 * so the page should be swapped out somewhere again if
+			 * we again wish to reclaim it.
+			 */
+			struct gendisk *disk = sis->bdev->bd_disk;
+			if (disk->fops->swap_slot_free_notify) {
+				swp_entry_t entry;
+				unsigned long offset;
+
+				entry.val = page_private(page);
+				offset = swp_offset(entry);
+
+				SetPageDirty(page);
+				disk->fops->swap_slot_free_notify(sis->bdev,
+						offset);
+			}
+		}
+	}
+
+out:
+	unlock_page(page);
+	bio_put(bio);
+}
+
+int generic_swapfile_activate(struct swap_info_struct *sis,
+				struct file *swap_file,
+				sector_t *span)
+{
+	struct address_space *mapping = swap_file->f_mapping;
+	struct inode *inode = mapping->host;
+	unsigned blocks_per_page;
+	unsigned long page_no;
+	unsigned blkbits;
+	sector_t probe_block;
+	sector_t last_block;
+	sector_t lowest_block = -1;
+	sector_t highest_block = 0;
+	int nr_extents = 0;
+	int ret;
+
+	blkbits = inode->i_blkbits;
+	blocks_per_page = PAGE_SIZE >> blkbits;
+
+	/*
+	 * Map all the blocks into the extent list.  This code doesn't try
+	 * to be very smart.
+	 */
+	probe_block = 0;
+	page_no = 0;
+	last_block = i_size_read(inode) >> blkbits;
+	while ((probe_block + blocks_per_page) <= last_block &&
+			page_no < sis->max) {
+		unsigned block_in_page;
+		sector_t first_block;
+
+		first_block = bmap(inode, probe_block);
+		if (first_block == 0)
+			goto bad_bmap;
+
+		/*
+		 * It must be PAGE_SIZE aligned on-disk
+		 */
+		if (first_block & (blocks_per_page - 1)) {
+			probe_block++;
+			goto reprobe;
+		}
+
+		for (block_in_page = 1; block_in_page < blocks_per_page;
+					block_in_page++) {
+			sector_t block;
+
+			block = bmap(inode, probe_block + block_in_page);
+			if (block == 0)
+				goto bad_bmap;
+			if (block != first_block + block_in_page) {
+				/* Discontiguity */
+				probe_block++;
+				goto reprobe;
+			}
+		}
+
+		first_block >>= (PAGE_SHIFT - blkbits);
+		if (page_no) {	/* exclude the header page */
+			if (first_block < lowest_block)
+				lowest_block = first_block;
+			if (first_block > highest_block)
+				highest_block = first_block;
+		}
+
+		/*
+		 * We found a PAGE_SIZE-length, PAGE_SIZE-aligned run of blocks
+		 */
+		ret = add_swap_extent(sis, page_no, 1, first_block);
+		if (ret < 0)
+			goto out;
+		nr_extents += ret;
+		page_no++;
+		probe_block += blocks_per_page;
+reprobe:
+		continue;
+	}
+	ret = nr_extents;
+	*span = 1 + highest_block - lowest_block;
+	if (page_no == 0)
+		page_no = 1;	/* force Empty message */
+	sis->max = page_no;
+	sis->pages = page_no - 1;
+	sis->highest_bit = page_no - 1;
+out:
+	return ret;
+bad_bmap:
+	printk(KERN_ERR "swapon: swapfile has holes\n");
+	ret = -EINVAL;
+	goto out;
+}
+
+/*
+ * We may have stale swap cache pages in memory: notice
+ * them here and get rid of the unnecessary final write.
+ */
+int swap_writepage(struct page *page, struct writeback_control *wbc)
+{
+	int ret = 0;
+
+	if (try_to_free_swap(page)) {
+		unlock_page(page);
+		goto out;
+	}
+	if (frontswap_store(page) == 0) {
+		set_page_writeback(page);
+		unlock_page(page);
+		end_page_writeback(page);
+		goto out;
+	}
+#ifdef CONFIG_VNSWAP
+	set_page_dirty(page);
+	ClearPageReclaim(page);
+	unlock_page(page);
+#else
+	ret = __swap_writepage(page, wbc, end_swap_bio_write);
+#endif
+out:
+	return ret;
+}
+
+static sector_t swap_page_sector(struct page *page)
+{
+	return (sector_t)__page_file_index(page) << (PAGE_CACHE_SHIFT - 9);
+}
+
+int __swap_writepage(struct page *page, struct writeback_control *wbc,
+	void (*end_write_func)(struct bio *, int))
+{
+	struct bio *bio;
+	int ret, rw = WRITE;
+	struct swap_info_struct *sis = page_swap_info(page);
+
+	if (sis->flags & SWP_FILE) {
+		struct kiocb kiocb;
+		struct file *swap_file = sis->swap_file;
+		struct address_space *mapping = swap_file->f_mapping;
+		struct bio_vec bv = {
+			.bv_page = page,
+			.bv_len  = PAGE_SIZE,
+			.bv_offset = 0
+		};
+		struct iov_iter from = {
+			.type = ITER_BVEC | WRITE,
+			.count = PAGE_SIZE,
+			.iov_offset = 0,
+			.nr_segs = 1,
+		};
+		from.bvec = &bv;	/* older gcc versions are broken */
+
+		init_sync_kiocb(&kiocb, swap_file);
+		kiocb.ki_pos = page_file_offset(page);
+		kiocb.ki_nbytes = PAGE_SIZE;
+
+		set_page_writeback(page);
+		unlock_page(page);
+		ret = mapping->a_ops->direct_IO(ITER_BVEC | WRITE,
+						&kiocb, &from,
+						kiocb.ki_pos);
+		if (ret == PAGE_SIZE) {
+			count_vm_event(PSWPOUT);
+			ret = 0;
+		} else {
+			/*
+			 * In the case of swap-over-nfs, this can be a
+			 * temporary failure if the system has limited
+			 * memory for allocating transmit buffers.
+			 * Mark the page dirty and avoid
+			 * rotate_reclaimable_page but rate-limit the
+			 * messages but do not flag PageError like
+			 * the normal direct-to-bio case as it could
+			 * be temporary.
+			 */
+			set_page_dirty(page);
+			ClearPageReclaim(page);
+			pr_err_ratelimited("Write error on dio swapfile (%Lu)\n",
+				page_file_offset(page));
+		}
+		end_page_writeback(page);
+		return ret;
+	}
+
+	ret = bdev_write_page(sis->bdev, swap_page_sector(page), page, wbc);
+	if (!ret) {
+		count_vm_event(PSWPOUT);
+		return 0;
+	}
+
+	ret = 0;
+	bio = get_swap_bio(GFP_NOIO, page, end_write_func);
+	if (bio == NULL) {
+		set_page_dirty(page);
+		unlock_page(page);
+		ret = -ENOMEM;
+		goto out;
+	}
+	if (wbc->sync_mode == WB_SYNC_ALL)
+		rw |= REQ_SYNC;
+	count_vm_event(PSWPOUT);
+	set_page_writeback(page);
+	unlock_page(page);
+	submit_bio(rw, bio);
+out:
+	return ret;
+}
+
+int swap_readpage(struct page *page)
+{
+	struct bio *bio;
+	int ret = 0;
+	struct swap_info_struct *sis = page_swap_info(page);
+
+	VM_BUG_ON_PAGE(!PageLocked(page), page);
+	VM_BUG_ON_PAGE(PageUptodate(page), page);
+	if (frontswap_load(page) == 0) {
+		SetPageUptodate(page);
+		unlock_page(page);
+		goto out;
+	}
+
+	if (sis->flags & SWP_FILE) {
+		struct file *swap_file = sis->swap_file;
+		struct address_space *mapping = swap_file->f_mapping;
+
+		ret = mapping->a_ops->readpage(swap_file, page);
+		if (!ret)
+			count_vm_event(PSWPIN);
+		return ret;
+	}
+
+	ret = bdev_read_page(sis->bdev, swap_page_sector(page), page);
+	if (!ret) {
+		count_vm_event(PSWPIN);
+		return 0;
+	}
+
+	ret = 0;
+	bio = get_swap_bio(GFP_KERNEL, page, end_swap_bio_read);
+	if (bio == NULL) {
+		unlock_page(page);
+		ret = -ENOMEM;
+		goto out;
+	}
+	count_vm_event(PSWPIN);
+	submit_bio(READ, bio);
+out:
+	return ret;
+}
+
+int swap_set_page_dirty(struct page *page)
+{
+	struct swap_info_struct *sis = page_swap_info(page);
+
+	if (sis->flags & SWP_FILE) {
+		struct address_space *mapping = sis->swap_file->f_mapping;
+		return mapping->a_ops->set_page_dirty(page);
+	} else {
+		return __set_page_dirty_no_writeback(page);
+	}
+}

mm/page_isolation.c

@@ -0,0 +1,313 @@
+/*
+ * linux/mm/page_isolation.c
+ */
+
+#include <linux/mm.h>
+#include <linux/page-isolation.h>
+#include <linux/pageblock-flags.h>
+#include <linux/memory.h>
+#include <linux/hugetlb.h>
+#include "internal.h"
+
+int set_migratetype_isolate(struct page *page, bool skip_hwpoisoned_pages)
+{
+	struct zone *zone;
+	unsigned long flags, pfn;
+	struct memory_isolate_notify arg;
+	int notifier_ret;
+	int ret = -EBUSY;
+
+	zone = page_zone(page);
+
+	spin_lock_irqsave(&zone->lock, flags);
+
+	pfn = page_to_pfn(page);
+	arg.start_pfn = pfn;
+	arg.nr_pages = pageblock_nr_pages;
+	arg.pages_found = 0;
+
+	/*
+	 * It may be possible to isolate a pageblock even if the
+	 * migratetype is not MIGRATE_MOVABLE. The memory isolation
+	 * notifier chain is used by balloon drivers to return the
+	 * number of pages in a range that are held by the balloon
+	 * driver to shrink memory. If all the pages are accounted for
+	 * by balloons, are free, or on the LRU, isolation can continue.
+	 * Later, for example, when memory hotplug notifier runs, these
+	 * pages reported as "can be isolated" should be isolated(freed)
+	 * by the balloon driver through the memory notifier chain.
+	 */
+	notifier_ret = memory_isolate_notify(MEM_ISOLATE_COUNT, &arg);
+	notifier_ret = notifier_to_errno(notifier_ret);
+	if (notifier_ret)
+		goto out;
+	/*
+	 * FIXME: Now, memory hotplug doesn't call shrink_slab() by itself.
+	 * We just check MOVABLE pages.
+	 */
+	if (!has_unmovable_pages(zone, page, arg.pages_found,
+				 skip_hwpoisoned_pages))
+		ret = 0;
+
+	/*
+	 * immobile means "not-on-lru" paes. If immobile is larger than
+	 * removable-by-driver pages reported by notifier, we'll fail.
+	 */
+
+out:
+	if (!ret) {
+		unsigned long nr_pages;
+		int migratetype = get_pageblock_migratetype(page);
+
+		set_pageblock_migratetype(page, MIGRATE_ISOLATE);
+		zone->nr_isolate_pageblock++;
+		nr_pages = move_freepages_block(zone, page, MIGRATE_ISOLATE);
+
+		__mod_zone_freepage_state(zone, -nr_pages, migratetype);
+	}
+
+	spin_unlock_irqrestore(&zone->lock, flags);
+	if (!ret)
+		drain_all_pages();
+	return ret;
+}
+
+void unset_migratetype_isolate(struct page *page, unsigned migratetype)
+{
+	struct zone *zone;
+	unsigned long flags, nr_pages;
+	struct page *isolated_page = NULL;
+	unsigned int order;
+	unsigned long page_idx, buddy_idx;
+	struct page *buddy;
+
+	zone = page_zone(page);
+	spin_lock_irqsave(&zone->lock, flags);
+	if (get_pageblock_migratetype(page) != MIGRATE_ISOLATE)
+		goto out;
+
+	/*
+	 * Because freepage with more than pageblock_order on isolated
+	 * pageblock is restricted to merge due to freepage counting problem,
+	 * it is possible that there is free buddy page.
+	 * move_freepages_block() doesn't care of merge so we need other
+	 * approach in order to merge them. Isolation and free will make
+	 * these pages to be merged.
+	 */
+	if (PageBuddy(page)) {
+		order = page_order(page);
+		if (order >= pageblock_order) {
+			page_idx = page_to_pfn(page) & ((1 << MAX_ORDER) - 1);
+			buddy_idx = __find_buddy_index(page_idx, order);
+			buddy = page + (buddy_idx - page_idx);
+
+			if (!is_migrate_isolate_page(buddy)) {
+				__isolate_free_page(page, order);
+				kernel_map_pages(page, (1 << order), 1);
+				set_page_refcounted(page);
+				isolated_page = page;
+			}
+		}
+	}
+
+	/*
+	 * If we isolate freepage with more than pageblock_order, there
+	 * should be no freepage in the range, so we could avoid costly
+	 * pageblock scanning for freepage moving.
+	 */
+	if (!isolated_page) {
+		nr_pages = move_freepages_block(zone, page, migratetype);
+		__mod_zone_freepage_state(zone, nr_pages, migratetype);
+	}
+	set_pageblock_migratetype(page, migratetype);
+	zone->nr_isolate_pageblock--;
+out:
+	spin_unlock_irqrestore(&zone->lock, flags);
+	if (isolated_page)
+		__free_pages(isolated_page, order);
+}
+
+static inline struct page *
+__first_valid_page(unsigned long pfn, unsigned long nr_pages)
+{
+	int i;
+	for (i = 0; i < nr_pages; i++)
+		if (pfn_valid_within(pfn + i))
+			break;
+	if (unlikely(i == nr_pages))
+		return NULL;
+	return pfn_to_page(pfn + i);
+}
+
+/*
+ * start_isolate_page_range() -- make page-allocation-type of range of pages
+ * to be MIGRATE_ISOLATE.
+ * @start_pfn: The lower PFN of the range to be isolated.
+ * @end_pfn: The upper PFN of the range to be isolated.
+ * @migratetype: migrate type to set in error recovery.
+ *
+ * Making page-allocation-type to be MIGRATE_ISOLATE means free pages in
+ * the range will never be allocated. Any free pages and pages freed in the
+ * future will not be allocated again.
+ *
+ * start_pfn/end_pfn must be aligned to pageblock_order.
+ * Returns 0 on success and -EBUSY if any part of range cannot be isolated.
+ */
+int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
+			     unsigned migratetype, bool skip_hwpoisoned_pages)
+{
+	unsigned long pfn;
+	unsigned long undo_pfn;
+	struct page *page;
+
+	BUG_ON((start_pfn) & (pageblock_nr_pages - 1));
+	BUG_ON((end_pfn) & (pageblock_nr_pages - 1));
+
+	for (pfn = start_pfn;
+	     pfn < end_pfn;
+	     pfn += pageblock_nr_pages) {
+		page = __first_valid_page(pfn, pageblock_nr_pages);
+		if (page &&
+		    set_migratetype_isolate(page, skip_hwpoisoned_pages)) {
+			undo_pfn = pfn;
+			goto undo;
+		}
+	}
+	return 0;
+undo:
+	for (pfn = start_pfn;
+	     pfn < undo_pfn;
+	     pfn += pageblock_nr_pages)
+		unset_migratetype_isolate(pfn_to_page(pfn), migratetype);
+
+	return -EBUSY;
+}
+
+/*
+ * Make isolated pages available again.
+ */
+int undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
+			    unsigned migratetype)
+{
+	unsigned long pfn;
+	struct page *page;
+	BUG_ON((start_pfn) & (pageblock_nr_pages - 1));
+	BUG_ON((end_pfn) & (pageblock_nr_pages - 1));
+	for (pfn = start_pfn;
+	     pfn < end_pfn;
+	     pfn += pageblock_nr_pages) {
+		page = __first_valid_page(pfn, pageblock_nr_pages);
+		if (!page || get_pageblock_migratetype(page) != MIGRATE_ISOLATE)
+			continue;
+		unset_migratetype_isolate(page, migratetype);
+	}
+	return 0;
+}
+/*
+ * Test all pages in the range is free(means isolated) or not.
+ * all pages in [start_pfn...end_pfn) must be in the same zone.
+ * zone->lock must be held before call this.
+ *
+ * Returns 1 if all pages in the range are isolated.
+ */
+static int
+__test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn,
+				  bool skip_hwpoisoned_pages)
+{
+	struct page *page;
+
+	while (pfn < end_pfn) {
+		if (!pfn_valid_within(pfn)) {
+			pfn++;
+			continue;
+		}
+		page = pfn_to_page(pfn);
+		if (PageBuddy(page)) {
+			/*
+			 * If race between isolatation and allocation happens,
+			 * some free pages could be in MIGRATE_MOVABLE list
+			 * although pageblock's migratation type of the page
+			 * is MIGRATE_ISOLATE. Catch it and move the page into
+			 * MIGRATE_ISOLATE list.
+			 */
+			if (get_freepage_migratetype(page) != MIGRATE_ISOLATE) {
+				struct page *end_page;
+
+				end_page = page + (1 << page_order(page)) - 1;
+				move_freepages(page_zone(page), page, end_page,
+						MIGRATE_ISOLATE);
+			}
+			pfn += 1 << page_order(page);
+		}
+		else if (page_count(page) == 0 &&
+			get_freepage_migratetype(page) == MIGRATE_ISOLATE)
+			pfn += 1;
+		else if (skip_hwpoisoned_pages && PageHWPoison(page)) {
+			/*
+			 * The HWPoisoned page may be not in buddy
+			 * system, and page_count() is not 0.
+			 */
+			pfn++;
+			continue;
+		}
+		else
+			break;
+	}
+	if (pfn < end_pfn)
+		return 0;
+	return 1;
+}
+
+int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn,
+			bool skip_hwpoisoned_pages)
+{
+	unsigned long pfn, flags;
+	struct page *page;
+	struct zone *zone;
+	int ret;
+
+	/*
+	 * Note: pageblock_nr_pages != MAX_ORDER. Then, chunks of free pages
+	 * are not aligned to pageblock_nr_pages.
+	 * Then we just check migratetype first.
+	 */
+	for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) {
+		page = __first_valid_page(pfn, pageblock_nr_pages);
+		if (page && get_pageblock_migratetype(page) != MIGRATE_ISOLATE)
+			break;
+	}
+	page = __first_valid_page(start_pfn, end_pfn - start_pfn);
+	if ((pfn < end_pfn) || !page)
+		return -EBUSY;
+	/* Check all pages are free or marked as ISOLATED */
+	zone = page_zone(page);
+	spin_lock_irqsave(&zone->lock, flags);
+	ret = __test_page_isolated_in_pageblock(start_pfn, end_pfn,
+						skip_hwpoisoned_pages);
+	spin_unlock_irqrestore(&zone->lock, flags);
+	return ret ? 0 : -EBUSY;
+}
+
+struct page *alloc_migrate_target(struct page *page, unsigned long private,
+				  int **resultp)
+{
+	gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE;
+
+	/*
+	 * TODO: allocate a destination hugepage from a nearest neighbor node,
+	 * accordance with memory policy of the user process if possible. For
+	 * now as a simple work-around, we use the next node for destination.
+	 */
+	if (PageHuge(page)) {
+		nodemask_t src = nodemask_of_node(page_to_nid(page));
+		nodemask_t dst;
+		nodes_complement(dst, src);
+		return alloc_huge_page_node(page_hstate(compound_head(page)),
+					    next_node(page_to_nid(page), dst));
+	}
+
+	if (PageHighMem(page))
+		gfp_mask |= __GFP_HIGHMEM;
+
+	return alloc_page(gfp_mask);
+}

mm/pagewalk.c

@@ -0,0 +1,251 @@
+#include <linux/mm.h>
+#include <linux/highmem.h>
+#include <linux/sched.h>
+#include <linux/hugetlb.h>
+
+static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
+			  struct mm_walk *walk)
+{
+	pte_t *pte;
+	int err = 0;
+
+	pte = pte_offset_map(pmd, addr);
+	for (;;) {
+		err = walk->pte_entry(pte, addr, addr + PAGE_SIZE, walk);
+		if (err)
+		       break;
+		addr += PAGE_SIZE;
+		if (addr == end)
+			break;
+		pte++;
+	}
+
+	pte_unmap(pte);
+	return err;
+}
+
+static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
+			  struct mm_walk *walk)
+{
+	pmd_t *pmd;
+	unsigned long next;
+	int err = 0;
+
+	pmd = pmd_offset(pud, addr);
+	do {
+again:
+		next = pmd_addr_end(addr, end);
+		if (pmd_none(*pmd)) {
+			if (walk->pte_hole)
+				err = walk->pte_hole(addr, next, walk);
+			if (err)
+				break;
+			continue;
+		}
+		/*
+		 * This implies that each ->pmd_entry() handler
+		 * needs to know about pmd_trans_huge() pmds
+		 */
+		if (walk->pmd_entry)
+			err = walk->pmd_entry(pmd, addr, next, walk);
+		if (err)
+			break;
+
+		/*
+		 * Check this here so we only break down trans_huge
+		 * pages when we _need_ to
+		 */
+		if (!walk->pte_entry)
+			continue;
+
+		split_huge_page_pmd_mm(walk->mm, addr, pmd);
+		if (pmd_none_or_trans_huge_or_clear_bad(pmd))
+			goto again;
+		err = walk_pte_range(pmd, addr, next, walk);
+		if (err)
+			break;
+	} while (pmd++, addr = next, addr != end);
+
+	return err;
+}
+
+static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end,
+			  struct mm_walk *walk)
+{
+	pud_t *pud;
+	unsigned long next;
+	int err = 0;
+
+	pud = pud_offset(pgd, addr);
+	do {
+		next = pud_addr_end(addr, end);
+		if (pud_none_or_clear_bad(pud)) {
+			if (walk->pte_hole)
+				err = walk->pte_hole(addr, next, walk);
+			if (err)
+				break;
+			continue;
+		}
+		if (walk->pud_entry)
+			err = walk->pud_entry(pud, addr, next, walk);
+		if (!err && (walk->pmd_entry || walk->pte_entry))
+			err = walk_pmd_range(pud, addr, next, walk);
+		if (err)
+			break;
+	} while (pud++, addr = next, addr != end);
+
+	return err;
+}
+
+#ifdef CONFIG_HUGETLB_PAGE
+static unsigned long hugetlb_entry_end(struct hstate *h, unsigned long addr,
+				       unsigned long end)
+{
+	unsigned long boundary = (addr & huge_page_mask(h)) + huge_page_size(h);
+	return boundary < end ? boundary : end;
+}
+
+static int walk_hugetlb_range(struct vm_area_struct *vma,
+			      unsigned long addr, unsigned long end,
+			      struct mm_walk *walk)
+{
+	struct hstate *h = hstate_vma(vma);
+	unsigned long next;
+	unsigned long hmask = huge_page_mask(h);
+	pte_t *pte;
+	int err = 0;
+
+	do {
+		next = hugetlb_entry_end(h, addr, end);
+		pte = huge_pte_offset(walk->mm, addr & hmask);
+		if (pte && walk->hugetlb_entry)
+			err = walk->hugetlb_entry(pte, hmask, addr, next, walk);
+		if (err)
+			return err;
+	} while (addr = next, addr != end);
+
+	return 0;
+}
+
+#else /* CONFIG_HUGETLB_PAGE */
+static int walk_hugetlb_range(struct vm_area_struct *vma,
+			      unsigned long addr, unsigned long end,
+			      struct mm_walk *walk)
+{
+	return 0;
+}
+
+#endif /* CONFIG_HUGETLB_PAGE */
+
+
+
+/**
+ * walk_page_range - walk a memory map's page tables with a callback
+ * @addr: starting address
+ * @end: ending address
+ * @walk: set of callbacks to invoke for each level of the tree
+ *
+ * Recursively walk the page table for the memory area in a VMA,
+ * calling supplied callbacks. Callbacks are called in-order (first
+ * PGD, first PUD, first PMD, first PTE, second PTE... second PMD,
+ * etc.). If lower-level callbacks are omitted, walking depth is reduced.
+ *
+ * Each callback receives an entry pointer and the start and end of the
+ * associated range, and a copy of the original mm_walk for access to
+ * the ->private or ->mm fields.
+ *
+ * Usually no locks are taken, but splitting transparent huge page may
+ * take page table lock. And the bottom level iterator will map PTE
+ * directories from highmem if necessary.
+ *
+ * If any callback returns a non-zero value, the walk is aborted and
+ * the return value is propagated back to the caller. Otherwise 0 is returned.
+ *
+ * walk->mm->mmap_sem must be held for at least read if walk->hugetlb_entry
+ * is !NULL.
+ */
+int walk_page_range(unsigned long addr, unsigned long end,
+		    struct mm_walk *walk)
+{
+	pgd_t *pgd;
+	unsigned long next;
+	int err = 0;
+
+	if (addr >= end)
+		return err;
+
+	if (!walk->mm)
+		return -EINVAL;
+
+	VM_BUG_ON_MM(!rwsem_is_locked(&walk->mm->mmap_sem), walk->mm);
+
+	pgd = pgd_offset(walk->mm, addr);
+	do {
+		struct vm_area_struct *vma = NULL;
+
+		next = pgd_addr_end(addr, end);
+
+		/*
+		 * This function was not intended to be vma based.
+		 * But there are vma special cases to be handled:
+		 * - hugetlb vma's
+		 * - VM_PFNMAP vma's
+		 */
+		vma = find_vma(walk->mm, addr);
+		if (vma) {
+			/*
+			 * There are no page structures backing a VM_PFNMAP
+			 * range, so do not allow split_huge_page_pmd().
+			 */
+			if ((vma->vm_start <= addr) &&
+			    (vma->vm_flags & VM_PFNMAP)) {
+				if (walk->pte_hole)
+					err = walk->pte_hole(addr, next, walk);
+				if (err)
+					break;
+				pgd = pgd_offset(walk->mm, next);
+				continue;
+			}
+			/*
+			 * Handle hugetlb vma individually because pagetable
+			 * walk for the hugetlb page is dependent on the
+			 * architecture and we can't handled it in the same
+			 * manner as non-huge pages.
+			 */
+			if (walk->hugetlb_entry && (vma->vm_start <= addr) &&
+			    is_vm_hugetlb_page(vma)) {
+				if (vma->vm_end < next)
+					next = vma->vm_end;
+				/*
+				 * Hugepage is very tightly coupled with vma,
+				 * so walk through hugetlb entries within a
+				 * given vma.
+				 */
+				err = walk_hugetlb_range(vma, addr, next, walk);
+				if (err)
+					break;
+				pgd = pgd_offset(walk->mm, next);
+				continue;
+			}
+		}
+
+		if (pgd_none_or_clear_bad(pgd)) {
+			if (walk->pte_hole)
+				err = walk->pte_hole(addr, next, walk);
+			if (err)
+				break;
+			pgd++;
+			continue;
+		}
+		if (walk->pgd_entry)
+			err = walk->pgd_entry(pgd, addr, next, walk);
+		if (!err &&
+		    (walk->pud_entry || walk->pmd_entry || walk->pte_entry))
+			err = walk_pud_range(pgd, addr, next, walk);
+		if (err)
+			break;
+		pgd++;
+	} while (addr = next, addr < end);
+
+	return err;
+}

mm/percpu-km.c

@@ -0,0 +1,110 @@
+/*
+ * mm/percpu-km.c - kernel memory based chunk allocation
+ *
+ * Copyright (C) 2010		SUSE Linux Products GmbH
+ * Copyright (C) 2010		Tejun Heo <tj@kernel.org>
+ *
+ * This file is released under the GPLv2.
+ *
+ * Chunks are allocated as a contiguous kernel memory using gfp
+ * allocation.  This is to be used on nommu architectures.
+ *
+ * To use percpu-km,
+ *
+ * - define CONFIG_NEED_PER_CPU_KM from the arch Kconfig.
+ *
+ * - CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK must not be defined.  It's
+ *   not compatible with PER_CPU_KM.  EMBED_FIRST_CHUNK should work
+ *   fine.
+ *
+ * - NUMA is not supported.  When setting up the first chunk,
+ *   @cpu_distance_fn should be NULL or report all CPUs to be nearer
+ *   than or at LOCAL_DISTANCE.
+ *
+ * - It's best if the chunk size is power of two multiple of
+ *   PAGE_SIZE.  Because each chunk is allocated as a contiguous
+ *   kernel memory block using alloc_pages(), memory will be wasted if
+ *   chunk size is not aligned.  percpu-km code will whine about it.
+ */
+
+#if defined(CONFIG_SMP) && defined(CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK)
+#error "contiguous percpu allocation is incompatible with paged first chunk"
+#endif
+
+#include <linux/log2.h>
+
+static int pcpu_populate_chunk(struct pcpu_chunk *chunk,
+			       int page_start, int page_end)
+{
+	return 0;
+}
+
+static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk,
+				  int page_start, int page_end)
+{
+	/* nada */
+}
+
+static struct pcpu_chunk *pcpu_create_chunk(void)
+{
+	const int nr_pages = pcpu_group_sizes[0] >> PAGE_SHIFT;
+	struct pcpu_chunk *chunk;
+	struct page *pages;
+	int i;
+
+	chunk = pcpu_alloc_chunk();
+	if (!chunk)
+		return NULL;
+
+	pages = alloc_pages(GFP_KERNEL, order_base_2(nr_pages));
+	if (!pages) {
+		pcpu_free_chunk(chunk);
+		return NULL;
+	}
+
+	for (i = 0; i < nr_pages; i++)
+		pcpu_set_page_chunk(nth_page(pages, i), chunk);
+
+	chunk->data = pages;
+	chunk->base_addr = page_address(pages) - pcpu_group_offsets[0];
+
+	spin_lock_irq(&pcpu_lock);
+	pcpu_chunk_populated(chunk, 0, nr_pages);
+	spin_unlock_irq(&pcpu_lock);
+
+	return chunk;
+}
+
+static void pcpu_destroy_chunk(struct pcpu_chunk *chunk)
+{
+	const int nr_pages = pcpu_group_sizes[0] >> PAGE_SHIFT;
+
+	if (chunk && chunk->data)
+		__free_pages(chunk->data, order_base_2(nr_pages));
+	pcpu_free_chunk(chunk);
+}
+
+static struct page *pcpu_addr_to_page(void *addr)
+{
+	return virt_to_page(addr);
+}
+
+static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai)
+{
+	size_t nr_pages, alloc_pages;
+
+	/* all units must be in a single group */
+	if (ai->nr_groups != 1) {
+		printk(KERN_CRIT "percpu: can't handle more than one groups\n");
+		return -EINVAL;
+	}
+
+	nr_pages = (ai->groups[0].nr_units * ai->unit_size) >> PAGE_SHIFT;
+	alloc_pages = roundup_pow_of_two(nr_pages);
+
+	if (alloc_pages > nr_pages)
+		printk(KERN_WARNING "percpu: wasting %zu pages per chunk\n",
+		       alloc_pages - nr_pages);
+
+	return 0;
+}

mm/percpu-vm.c

@@ -0,0 +1,366 @@
+/*
+ * mm/percpu-vm.c - vmalloc area based chunk allocation
+ *
+ * Copyright (C) 2010		SUSE Linux Products GmbH
+ * Copyright (C) 2010		Tejun Heo <tj@kernel.org>
+ *
+ * This file is released under the GPLv2.
+ *
+ * Chunks are mapped into vmalloc areas and populated page by page.
+ * This is the default chunk allocator.
+ */
+
+static struct page *pcpu_chunk_page(struct pcpu_chunk *chunk,
+				    unsigned int cpu, int page_idx)
+{
+	/* must not be used on pre-mapped chunk */
+	WARN_ON(chunk->immutable);
+
+	return vmalloc_to_page((void *)pcpu_chunk_addr(chunk, cpu, page_idx));
+}
+
+/**
+ * pcpu_get_pages - get temp pages array
+ * @chunk: chunk of interest
+ *
+ * Returns pointer to array of pointers to struct page which can be indexed
+ * with pcpu_page_idx().  Note that there is only one array and accesses
+ * should be serialized by pcpu_alloc_mutex.
+ *
+ * RETURNS:
+ * Pointer to temp pages array on success.
+ */
+static struct page **pcpu_get_pages(struct pcpu_chunk *chunk_alloc)
+{
+	static struct page **pages;
+	size_t pages_size = pcpu_nr_units * pcpu_unit_pages * sizeof(pages[0]);
+
+	lockdep_assert_held(&pcpu_alloc_mutex);
+
+	if (!pages)
+		pages = pcpu_mem_zalloc(pages_size);
+	return pages;
+}
+
+/**
+ * pcpu_free_pages - free pages which were allocated for @chunk
+ * @chunk: chunk pages were allocated for
+ * @pages: array of pages to be freed, indexed by pcpu_page_idx()
+ * @page_start: page index of the first page to be freed
+ * @page_end: page index of the last page to be freed + 1
+ *
+ * Free pages [@page_start and @page_end) in @pages for all units.
+ * The pages were allocated for @chunk.
+ */
+static void pcpu_free_pages(struct pcpu_chunk *chunk,
+			    struct page **pages, int page_start, int page_end)
+{
+	unsigned int cpu;
+	int i;
+
+	for_each_possible_cpu(cpu) {
+		for (i = page_start; i < page_end; i++) {
+			struct page *page = pages[pcpu_page_idx(cpu, i)];
+
+			if (page)
+				__free_page(page);
+		}
+	}
+}
+
+/**
+ * pcpu_alloc_pages - allocates pages for @chunk
+ * @chunk: target chunk
+ * @pages: array to put the allocated pages into, indexed by pcpu_page_idx()
+ * @page_start: page index of the first page to be allocated
+ * @page_end: page index of the last page to be allocated + 1
+ *
+ * Allocate pages [@page_start,@page_end) into @pages for all units.
+ * The allocation is for @chunk.  Percpu core doesn't care about the
+ * content of @pages and will pass it verbatim to pcpu_map_pages().
+ */
+static int pcpu_alloc_pages(struct pcpu_chunk *chunk,
+			    struct page **pages, int page_start, int page_end)
+{
+	const gfp_t gfp = GFP_KERNEL | __GFP_HIGHMEM | __GFP_COLD;
+	unsigned int cpu, tcpu;
+	int i;
+
+	for_each_possible_cpu(cpu) {
+		for (i = page_start; i < page_end; i++) {
+			struct page **pagep = &pages[pcpu_page_idx(cpu, i)];
+
+			*pagep = alloc_pages_node(cpu_to_node(cpu), gfp, 0);
+			if (!*pagep)
+				goto err;
+		}
+	}
+	return 0;
+
+err:
+	while (--i >= page_start)
+		__free_page(pages[pcpu_page_idx(cpu, i)]);
+
+	for_each_possible_cpu(tcpu) {
+		if (tcpu == cpu)
+			break;
+		for (i = page_start; i < page_end; i++)
+			__free_page(pages[pcpu_page_idx(tcpu, i)]);
+	}
+	return -ENOMEM;
+}
+
+/**
+ * pcpu_pre_unmap_flush - flush cache prior to unmapping
+ * @chunk: chunk the regions to be flushed belongs to
+ * @page_start: page index of the first page to be flushed
+ * @page_end: page index of the last page to be flushed + 1
+ *
+ * Pages in [@page_start,@page_end) of @chunk are about to be
+ * unmapped.  Flush cache.  As each flushing trial can be very
+ * expensive, issue flush on the whole region at once rather than
+ * doing it for each cpu.  This could be an overkill but is more
+ * scalable.
+ */
+static void pcpu_pre_unmap_flush(struct pcpu_chunk *chunk,
+				 int page_start, int page_end)
+{
+	flush_cache_vunmap(
+		pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start),
+		pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end));
+}
+
+static void __pcpu_unmap_pages(unsigned long addr, int nr_pages)
+{
+	unmap_kernel_range_noflush(addr, nr_pages << PAGE_SHIFT);
+}
+
+/**
+ * pcpu_unmap_pages - unmap pages out of a pcpu_chunk
+ * @chunk: chunk of interest
+ * @pages: pages array which can be used to pass information to free
+ * @page_start: page index of the first page to unmap
+ * @page_end: page index of the last page to unmap + 1
+ *
+ * For each cpu, unmap pages [@page_start,@page_end) out of @chunk.
+ * Corresponding elements in @pages were cleared by the caller and can
+ * be used to carry information to pcpu_free_pages() which will be
+ * called after all unmaps are finished.  The caller should call
+ * proper pre/post flush functions.
+ */
+static void pcpu_unmap_pages(struct pcpu_chunk *chunk,
+			     struct page **pages, int page_start, int page_end)
+{
+	unsigned int cpu;
+	int i;
+
+	for_each_possible_cpu(cpu) {
+		for (i = page_start; i < page_end; i++) {
+			struct page *page;
+
+			page = pcpu_chunk_page(chunk, cpu, i);
+			WARN_ON(!page);
+			pages[pcpu_page_idx(cpu, i)] = page;
+		}
+		__pcpu_unmap_pages(pcpu_chunk_addr(chunk, cpu, page_start),
+				   page_end - page_start);
+	}
+}
+
+/**
+ * pcpu_post_unmap_tlb_flush - flush TLB after unmapping
+ * @chunk: pcpu_chunk the regions to be flushed belong to
+ * @page_start: page index of the first page to be flushed
+ * @page_end: page index of the last page to be flushed + 1
+ *
+ * Pages [@page_start,@page_end) of @chunk have been unmapped.  Flush
+ * TLB for the regions.  This can be skipped if the area is to be
+ * returned to vmalloc as vmalloc will handle TLB flushing lazily.
+ *
+ * As with pcpu_pre_unmap_flush(), TLB flushing also is done at once
+ * for the whole region.
+ */
+static void pcpu_post_unmap_tlb_flush(struct pcpu_chunk *chunk,
+				      int page_start, int page_end)
+{
+	flush_tlb_kernel_range(
+		pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start),
+		pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end));
+}
+
+static int __pcpu_map_pages(unsigned long addr, struct page **pages,
+			    int nr_pages)
+{
+	return map_kernel_range_noflush(addr, nr_pages << PAGE_SHIFT,
+					PAGE_KERNEL, pages);
+}
+
+/**
+ * pcpu_map_pages - map pages into a pcpu_chunk
+ * @chunk: chunk of interest
+ * @pages: pages array containing pages to be mapped
+ * @page_start: page index of the first page to map
+ * @page_end: page index of the last page to map + 1
+ *
+ * For each cpu, map pages [@page_start,@page_end) into @chunk.  The
+ * caller is responsible for calling pcpu_post_map_flush() after all
+ * mappings are complete.
+ *
+ * This function is responsible for setting up whatever is necessary for
+ * reverse lookup (addr -> chunk).
+ */
+static int pcpu_map_pages(struct pcpu_chunk *chunk,
+			  struct page **pages, int page_start, int page_end)
+{
+	unsigned int cpu, tcpu;
+	int i, err;
+
+	for_each_possible_cpu(cpu) {
+		err = __pcpu_map_pages(pcpu_chunk_addr(chunk, cpu, page_start),
+				       &pages[pcpu_page_idx(cpu, page_start)],
+				       page_end - page_start);
+		if (err < 0)
+			goto err;
+
+		for (i = page_start; i < page_end; i++)
+			pcpu_set_page_chunk(pages[pcpu_page_idx(cpu, i)],
+					    chunk);
+	}
+	return 0;
+err:
+	for_each_possible_cpu(tcpu) {
+		if (tcpu == cpu)
+			break;
+		__pcpu_unmap_pages(pcpu_chunk_addr(chunk, tcpu, page_start),
+				   page_end - page_start);
+	}
+	pcpu_post_unmap_tlb_flush(chunk, page_start, page_end);
+	return err;
+}
+
+/**
+ * pcpu_post_map_flush - flush cache after mapping
+ * @chunk: pcpu_chunk the regions to be flushed belong to
+ * @page_start: page index of the first page to be flushed
+ * @page_end: page index of the last page to be flushed + 1
+ *
+ * Pages [@page_start,@page_end) of @chunk have been mapped.  Flush
+ * cache.
+ *
+ * As with pcpu_pre_unmap_flush(), TLB flushing also is done at once
+ * for the whole region.
+ */
+static void pcpu_post_map_flush(struct pcpu_chunk *chunk,
+				int page_start, int page_end)
+{
+	flush_cache_vmap(
+		pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start),
+		pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end));
+}
+
+/**
+ * pcpu_populate_chunk - populate and map an area of a pcpu_chunk
+ * @chunk: chunk of interest
+ * @page_start: the start page
+ * @page_end: the end page
+ *
+ * For each cpu, populate and map pages [@page_start,@page_end) into
+ * @chunk.
+ *
+ * CONTEXT:
+ * pcpu_alloc_mutex, does GFP_KERNEL allocation.
+ */
+static int pcpu_populate_chunk(struct pcpu_chunk *chunk,
+			       int page_start, int page_end)
+{
+	struct page **pages;
+
+	pages = pcpu_get_pages(chunk);
+	if (!pages)
+		return -ENOMEM;
+
+	if (pcpu_alloc_pages(chunk, pages, page_start, page_end))
+		return -ENOMEM;
+
+	if (pcpu_map_pages(chunk, pages, page_start, page_end)) {
+		pcpu_free_pages(chunk, pages, page_start, page_end);
+		return -ENOMEM;
+	}
+	pcpu_post_map_flush(chunk, page_start, page_end);
+
+	return 0;
+}
+
+/**
+ * pcpu_depopulate_chunk - depopulate and unmap an area of a pcpu_chunk
+ * @chunk: chunk to depopulate
+ * @page_start: the start page
+ * @page_end: the end page
+ *
+ * For each cpu, depopulate and unmap pages [@page_start,@page_end)
+ * from @chunk.
+ *
+ * CONTEXT:
+ * pcpu_alloc_mutex.
+ */
+static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk,
+				  int page_start, int page_end)
+{
+	struct page **pages;
+
+	/*
+	 * If control reaches here, there must have been at least one
+	 * successful population attempt so the temp pages array must
+	 * be available now.
+	 */
+	pages = pcpu_get_pages(chunk);
+	BUG_ON(!pages);
+
+	/* unmap and free */
+	pcpu_pre_unmap_flush(chunk, page_start, page_end);
+
+	pcpu_unmap_pages(chunk, pages, page_start, page_end);
+
+	/* no need to flush tlb, vmalloc will handle it lazily */
+
+	pcpu_free_pages(chunk, pages, page_start, page_end);
+}
+
+static struct pcpu_chunk *pcpu_create_chunk(void)
+{
+	struct pcpu_chunk *chunk;
+	struct vm_struct **vms;
+
+	chunk = pcpu_alloc_chunk();
+	if (!chunk)
+		return NULL;
+
+	vms = pcpu_get_vm_areas(pcpu_group_offsets, pcpu_group_sizes,
+				pcpu_nr_groups, pcpu_atom_size);
+	if (!vms) {
+		pcpu_free_chunk(chunk);
+		return NULL;
+	}
+
+	chunk->data = vms;
+	chunk->base_addr = vms[0]->addr - pcpu_group_offsets[0];
+	return chunk;
+}
+
+static void pcpu_destroy_chunk(struct pcpu_chunk *chunk)
+{
+	if (chunk && chunk->data)
+		pcpu_free_vm_areas(chunk->data, pcpu_nr_groups);
+	pcpu_free_chunk(chunk);
+}
+
+static struct page *pcpu_addr_to_page(void *addr)
+{
+	return vmalloc_to_page(addr);
+}
+
+static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai)
+{
+	/* no extra restriction */
+	return 0;
+}

mm/pgtable-generic.c

@@ -0,0 +1,202 @@
+/*
+ *  mm/pgtable-generic.c
+ *
+ *  Generic pgtable methods declared in asm-generic/pgtable.h
+ *
+ *  Copyright (C) 2010  Linus Torvalds
+ */
+
+#include <linux/pagemap.h>
+#include <asm/tlb.h>
+#include <asm-generic/pgtable.h>
+
+/*
+ * If a p?d_bad entry is found while walking page tables, report
+ * the error, before resetting entry to p?d_none.  Usually (but
+ * very seldom) called out from the p?d_none_or_clear_bad macros.
+ */
+
+void pgd_clear_bad(pgd_t *pgd)
+{
+	pgd_ERROR(*pgd);
+	pgd_clear(pgd);
+}
+
+void pud_clear_bad(pud_t *pud)
+{
+	pud_ERROR(*pud);
+	pud_clear(pud);
+}
+
+void pmd_clear_bad(pmd_t *pmd)
+{
+	pmd_ERROR(*pmd);
+	pmd_clear(pmd);
+}
+
+#ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
+/*
+ * Only sets the access flags (dirty, accessed), as well as write 
+ * permission. Furthermore, we know it always gets set to a "more
+ * permissive" setting, which allows most architectures to optimize
+ * this. We return whether the PTE actually changed, which in turn
+ * instructs the caller to do things like update__mmu_cache.  This
+ * used to be done in the caller, but sparc needs minor faults to
+ * force that call on sun4c so we changed this macro slightly
+ */
+int ptep_set_access_flags(struct vm_area_struct *vma,
+			  unsigned long address, pte_t *ptep,
+			  pte_t entry, int dirty)
+{
+	int changed = !pte_same(*ptep, entry);
+	if (changed) {
+		set_pte_at(vma->vm_mm, address, ptep, entry);
+		flush_tlb_fix_spurious_fault(vma, address);
+	}
+	return changed;
+}
+#endif
+
+#ifndef __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
+int pmdp_set_access_flags(struct vm_area_struct *vma,
+			  unsigned long address, pmd_t *pmdp,
+			  pmd_t entry, int dirty)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	int changed = !pmd_same(*pmdp, entry);
+	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
+	if (changed) {
+		set_pmd_at(vma->vm_mm, address, pmdp, entry);
+		flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
+	}
+	return changed;
+#else /* CONFIG_TRANSPARENT_HUGEPAGE */
+	BUG();
+	return 0;
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+}
+#endif
+
+#ifndef __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
+int ptep_clear_flush_young(struct vm_area_struct *vma,
+			   unsigned long address, pte_t *ptep)
+{
+	int young;
+	young = ptep_test_and_clear_young(vma, address, ptep);
+	if (young)
+		flush_tlb_page(vma, address);
+	return young;
+}
+#endif
+
+#ifndef __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH
+int pmdp_clear_flush_young(struct vm_area_struct *vma,
+			   unsigned long address, pmd_t *pmdp)
+{
+	int young;
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
+#else
+	BUG();
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+	young = pmdp_test_and_clear_young(vma, address, pmdp);
+	if (young)
+		flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
+	return young;
+}
+#endif
+
+#ifndef __HAVE_ARCH_PTEP_CLEAR_FLUSH
+pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long address,
+		       pte_t *ptep)
+{
+	struct mm_struct *mm = (vma)->vm_mm;
+	pte_t pte;
+	pte = ptep_get_and_clear(mm, address, ptep);
+	if (pte_accessible(mm, pte))
+		flush_tlb_page(vma, address);
+	return pte;
+}
+#endif
+
+#ifndef __HAVE_ARCH_PMDP_CLEAR_FLUSH
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+pmd_t pmdp_clear_flush(struct vm_area_struct *vma, unsigned long address,
+		       pmd_t *pmdp)
+{
+	pmd_t pmd;
+	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
+	pmd = pmdp_get_and_clear(vma->vm_mm, address, pmdp);
+	flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
+	return pmd;
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#endif
+
+#ifndef __HAVE_ARCH_PMDP_SPLITTING_FLUSH
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
+			  pmd_t *pmdp)
+{
+	pmd_t pmd = pmd_mksplitting(*pmdp);
+	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
+	set_pmd_at(vma->vm_mm, address, pmdp, pmd);
+	/* tlb flush only to serialize against gup-fast */
+	flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#endif
+
+#ifndef __HAVE_ARCH_PGTABLE_DEPOSIT
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
+				pgtable_t pgtable)
+{
+	assert_spin_locked(pmd_lockptr(mm, pmdp));
+
+	/* FIFO */
+	if (!pmd_huge_pte(mm, pmdp))
+		INIT_LIST_HEAD(&pgtable->lru);
+	else
+		list_add(&pgtable->lru, &pmd_huge_pte(mm, pmdp)->lru);
+	pmd_huge_pte(mm, pmdp) = pgtable;
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#endif
+
+#ifndef __HAVE_ARCH_PGTABLE_WITHDRAW
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+/* no "address" argument so destroys page coloring of some arch */
+pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
+{
+	pgtable_t pgtable;
+
+	assert_spin_locked(pmd_lockptr(mm, pmdp));
+
+	/* FIFO */
+	pgtable = pmd_huge_pte(mm, pmdp);
+	if (list_empty(&pgtable->lru))
+		pmd_huge_pte(mm, pmdp) = NULL;
+	else {
+		pmd_huge_pte(mm, pmdp) = list_entry(pgtable->lru.next,
+					      struct page, lru);
+		list_del(&pgtable->lru);
+	}
+	return pgtable;
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#endif
+
+#ifndef __HAVE_ARCH_PMDP_INVALIDATE
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
+		     pmd_t *pmdp)
+{
+	pmd_t entry = *pmdp;
+	if (pmd_numa(entry))
+		entry = pmd_mknonnuma(entry);
+	set_pmd_at(vma->vm_mm, address, pmdp, pmd_mknotpresent(entry));
+	flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#endif

mm/process_vm_access.c

@@ -0,0 +1,379 @@
+/*
+ * linux/mm/process_vm_access.c
+ *
+ * Copyright (C) 2010-2011 Christopher Yeoh <cyeoh@au1.ibm.com>, IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/mm.h>
+#include <linux/uio.h>
+#include <linux/sched.h>
+#include <linux/highmem.h>
+#include <linux/ptrace.h>
+#include <linux/slab.h>
+#include <linux/syscalls.h>
+
+#ifdef CONFIG_COMPAT
+#include <linux/compat.h>
+#endif
+
+/**
+ * process_vm_rw_pages - read/write pages from task specified
+ * @pages: array of pointers to pages we want to copy
+ * @start_offset: offset in page to start copying from/to
+ * @len: number of bytes to copy
+ * @iter: where to copy to/from locally
+ * @vm_write: 0 means copy from, 1 means copy to
+ * Returns 0 on success, error code otherwise
+ */
+static int process_vm_rw_pages(struct page **pages,
+			       unsigned offset,
+			       size_t len,
+			       struct iov_iter *iter,
+			       int vm_write)
+{
+	/* Do the copy for each page */
+	while (len && iov_iter_count(iter)) {
+		struct page *page = *pages++;
+		size_t copy = PAGE_SIZE - offset;
+		size_t copied;
+
+		if (copy > len)
+			copy = len;
+
+		if (vm_write) {
+			copied = copy_page_from_iter(page, offset, copy, iter);
+			set_page_dirty_lock(page);
+		} else {
+			copied = copy_page_to_iter(page, offset, copy, iter);
+		}
+		len -= copied;
+		if (copied < copy && iov_iter_count(iter))
+			return -EFAULT;
+		offset = 0;
+	}
+	return 0;
+}
+
+/* Maximum number of pages kmalloc'd to hold struct page's during copy */
+#define PVM_MAX_KMALLOC_PAGES (PAGE_SIZE * 2)
+
+/**
+ * process_vm_rw_single_vec - read/write pages from task specified
+ * @addr: start memory address of target process
+ * @len: size of area to copy to/from
+ * @iter: where to copy to/from locally
+ * @process_pages: struct pages area that can store at least
+ *  nr_pages_to_copy struct page pointers
+ * @mm: mm for task
+ * @task: task to read/write from
+ * @vm_write: 0 means copy from, 1 means copy to
+ * Returns 0 on success or on failure error code
+ */
+static int process_vm_rw_single_vec(unsigned long addr,
+				    unsigned long len,
+				    struct iov_iter *iter,
+				    struct page **process_pages,
+				    struct mm_struct *mm,
+				    struct task_struct *task,
+				    int vm_write)
+{
+	unsigned long pa = addr & PAGE_MASK;
+	unsigned long start_offset = addr - pa;
+	unsigned long nr_pages;
+	ssize_t rc = 0;
+	unsigned long max_pages_per_loop = PVM_MAX_KMALLOC_PAGES
+		/ sizeof(struct pages *);
+
+	/* Work out address and page range required */
+	if (len == 0)
+		return 0;
+	nr_pages = (addr + len - 1) / PAGE_SIZE - addr / PAGE_SIZE + 1;
+
+	while (!rc && nr_pages && iov_iter_count(iter)) {
+		int pages = min(nr_pages, max_pages_per_loop);
+		size_t bytes;
+
+		/* Get the pages we're interested in */
+		down_read(&mm->mmap_sem);
+		pages = get_user_pages(task, mm, pa, pages,
+				      vm_write, 0, process_pages, NULL);
+		up_read(&mm->mmap_sem);
+
+		if (pages <= 0)
+			return -EFAULT;
+
+		bytes = pages * PAGE_SIZE - start_offset;
+		if (bytes > len)
+			bytes = len;
+
+		rc = process_vm_rw_pages(process_pages,
+					 start_offset, bytes, iter,
+					 vm_write);
+		len -= bytes;
+		start_offset = 0;
+		nr_pages -= pages;
+		pa += pages * PAGE_SIZE;
+		while (pages)
+			put_page(process_pages[--pages]);
+	}
+
+	return rc;
+}
+
+/* Maximum number of entries for process pages array
+   which lives on stack */
+#define PVM_MAX_PP_ARRAY_COUNT 16
+
+/**
+ * process_vm_rw_core - core of reading/writing pages from task specified
+ * @pid: PID of process to read/write from/to
+ * @iter: where to copy to/from locally
+ * @rvec: iovec array specifying where to copy to/from in the other process
+ * @riovcnt: size of rvec array
+ * @flags: currently unused
+ * @vm_write: 0 if reading from other process, 1 if writing to other process
+ * Returns the number of bytes read/written or error code. May
+ *  return less bytes than expected if an error occurs during the copying
+ *  process.
+ */
+static ssize_t process_vm_rw_core(pid_t pid, struct iov_iter *iter,
+				  const struct iovec *rvec,
+				  unsigned long riovcnt,
+				  unsigned long flags, int vm_write)
+{
+	struct task_struct *task;
+	struct page *pp_stack[PVM_MAX_PP_ARRAY_COUNT];
+	struct page **process_pages = pp_stack;
+	struct mm_struct *mm;
+	unsigned long i;
+	ssize_t rc = 0;
+	unsigned long nr_pages = 0;
+	unsigned long nr_pages_iov;
+	ssize_t iov_len;
+	size_t total_len = iov_iter_count(iter);
+
+	/*
+	 * Work out how many pages of struct pages we're going to need
+	 * when eventually calling get_user_pages
+	 */
+	for (i = 0; i < riovcnt; i++) {
+		iov_len = rvec[i].iov_len;
+		if (iov_len > 0) {
+			nr_pages_iov = ((unsigned long)rvec[i].iov_base
+					+ iov_len)
+				/ PAGE_SIZE - (unsigned long)rvec[i].iov_base
+				/ PAGE_SIZE + 1;
+			nr_pages = max(nr_pages, nr_pages_iov);
+		}
+	}
+
+	if (nr_pages == 0)
+		return 0;
+
+	if (nr_pages > PVM_MAX_PP_ARRAY_COUNT) {
+		/* For reliability don't try to kmalloc more than
+		   2 pages worth */
+		process_pages = kmalloc(min_t(size_t, PVM_MAX_KMALLOC_PAGES,
+					      sizeof(struct pages *)*nr_pages),
+					GFP_KERNEL);
+
+		if (!process_pages)
+			return -ENOMEM;
+	}
+
+	/* Get process information */
+	rcu_read_lock();
+	task = find_task_by_vpid(pid);
+	if (task)
+		get_task_struct(task);
+	rcu_read_unlock();
+	if (!task) {
+		rc = -ESRCH;
+		goto free_proc_pages;
+	}
+
+	mm = mm_access(task, PTRACE_MODE_ATTACH);
+	if (!mm || IS_ERR(mm)) {
+		rc = IS_ERR(mm) ? PTR_ERR(mm) : -ESRCH;
+		/*
+		 * Explicitly map EACCES to EPERM as EPERM is a more a
+		 * appropriate error code for process_vw_readv/writev
+		 */
+		if (rc == -EACCES)
+			rc = -EPERM;
+		goto put_task_struct;
+	}
+
+	for (i = 0; i < riovcnt && iov_iter_count(iter) && !rc; i++)
+		rc = process_vm_rw_single_vec(
+			(unsigned long)rvec[i].iov_base, rvec[i].iov_len,
+			iter, process_pages, mm, task, vm_write);
+
+	/* copied = space before - space after */
+	total_len -= iov_iter_count(iter);
+
+	/* If we have managed to copy any data at all then
+	   we return the number of bytes copied. Otherwise
+	   we return the error code */
+	if (total_len)
+		rc = total_len;
+
+	mmput(mm);
+
+put_task_struct:
+	put_task_struct(task);
+
+free_proc_pages:
+	if (process_pages != pp_stack)
+		kfree(process_pages);
+	return rc;
+}
+
+/**
+ * process_vm_rw - check iovecs before calling core routine
+ * @pid: PID of process to read/write from/to
+ * @lvec: iovec array specifying where to copy to/from locally
+ * @liovcnt: size of lvec array
+ * @rvec: iovec array specifying where to copy to/from in the other process
+ * @riovcnt: size of rvec array
+ * @flags: currently unused
+ * @vm_write: 0 if reading from other process, 1 if writing to other process
+ * Returns the number of bytes read/written or error code. May
+ *  return less bytes than expected if an error occurs during the copying
+ *  process.
+ */
+static ssize_t process_vm_rw(pid_t pid,
+			     const struct iovec __user *lvec,
+			     unsigned long liovcnt,
+			     const struct iovec __user *rvec,
+			     unsigned long riovcnt,
+			     unsigned long flags, int vm_write)
+{
+	struct iovec iovstack_l[UIO_FASTIOV];
+	struct iovec iovstack_r[UIO_FASTIOV];
+	struct iovec *iov_l = iovstack_l;
+	struct iovec *iov_r = iovstack_r;
+	struct iov_iter iter;
+	ssize_t rc;
+
+	if (flags != 0)
+		return -EINVAL;
+
+	/* Check iovecs */
+	if (vm_write)
+		rc = rw_copy_check_uvector(WRITE, lvec, liovcnt, UIO_FASTIOV,
+					   iovstack_l, &iov_l);
+	else
+		rc = rw_copy_check_uvector(READ, lvec, liovcnt, UIO_FASTIOV,
+					   iovstack_l, &iov_l);
+	if (rc <= 0)
+		goto free_iovecs;
+
+	iov_iter_init(&iter, vm_write ? WRITE : READ, iov_l, liovcnt, rc);
+
+	rc = rw_copy_check_uvector(CHECK_IOVEC_ONLY, rvec, riovcnt, UIO_FASTIOV,
+				   iovstack_r, &iov_r);
+	if (rc <= 0)
+		goto free_iovecs;
+
+	rc = process_vm_rw_core(pid, &iter, iov_r, riovcnt, flags, vm_write);
+
+free_iovecs:
+	if (iov_r != iovstack_r)
+		kfree(iov_r);
+	if (iov_l != iovstack_l)
+		kfree(iov_l);
+
+	return rc;
+}
+
+SYSCALL_DEFINE6(process_vm_readv, pid_t, pid, const struct iovec __user *, lvec,
+		unsigned long, liovcnt, const struct iovec __user *, rvec,
+		unsigned long, riovcnt,	unsigned long, flags)
+{
+	return process_vm_rw(pid, lvec, liovcnt, rvec, riovcnt, flags, 0);
+}
+
+SYSCALL_DEFINE6(process_vm_writev, pid_t, pid,
+		const struct iovec __user *, lvec,
+		unsigned long, liovcnt, const struct iovec __user *, rvec,
+		unsigned long, riovcnt,	unsigned long, flags)
+{
+	return process_vm_rw(pid, lvec, liovcnt, rvec, riovcnt, flags, 1);
+}
+
+#ifdef CONFIG_COMPAT
+
+static ssize_t
+compat_process_vm_rw(compat_pid_t pid,
+		     const struct compat_iovec __user *lvec,
+		     unsigned long liovcnt,
+		     const struct compat_iovec __user *rvec,
+		     unsigned long riovcnt,
+		     unsigned long flags, int vm_write)
+{
+	struct iovec iovstack_l[UIO_FASTIOV];
+	struct iovec iovstack_r[UIO_FASTIOV];
+	struct iovec *iov_l = iovstack_l;
+	struct iovec *iov_r = iovstack_r;
+	struct iov_iter iter;
+	ssize_t rc = -EFAULT;
+
+	if (flags != 0)
+		return -EINVAL;
+
+	if (vm_write)
+		rc = compat_rw_copy_check_uvector(WRITE, lvec, liovcnt,
+						  UIO_FASTIOV, iovstack_l,
+						  &iov_l);
+	else
+		rc = compat_rw_copy_check_uvector(READ, lvec, liovcnt,
+						  UIO_FASTIOV, iovstack_l,
+						  &iov_l);
+	if (rc <= 0)
+		goto free_iovecs;
+	iov_iter_init(&iter, vm_write ? WRITE : READ, iov_l, liovcnt, rc);
+	rc = compat_rw_copy_check_uvector(CHECK_IOVEC_ONLY, rvec, riovcnt,
+					  UIO_FASTIOV, iovstack_r,
+					  &iov_r);
+	if (rc <= 0)
+		goto free_iovecs;
+
+	rc = process_vm_rw_core(pid, &iter, iov_r, riovcnt, flags, vm_write);
+
+free_iovecs:
+	if (iov_r != iovstack_r)
+		kfree(iov_r);
+	if (iov_l != iovstack_l)
+		kfree(iov_l);
+	return rc;
+}
+
+COMPAT_SYSCALL_DEFINE6(process_vm_readv, compat_pid_t, pid,
+		       const struct compat_iovec __user *, lvec,
+		       compat_ulong_t, liovcnt,
+		       const struct compat_iovec __user *, rvec,
+		       compat_ulong_t, riovcnt,
+		       compat_ulong_t, flags)
+{
+	return compat_process_vm_rw(pid, lvec, liovcnt, rvec,
+				    riovcnt, flags, 0);
+}
+
+COMPAT_SYSCALL_DEFINE6(process_vm_writev, compat_pid_t, pid,
+		       const struct compat_iovec __user *, lvec,
+		       compat_ulong_t, liovcnt,
+		       const struct compat_iovec __user *, rvec,
+		       compat_ulong_t, riovcnt,
+		       compat_ulong_t, flags)
+{
+	return compat_process_vm_rw(pid, lvec, liovcnt, rvec,
+				    riovcnt, flags, 1);
+}
+
+#endif

mm/quicklist.c

@@ -0,0 +1,102 @@
+/*
+ * Quicklist support.
+ *
+ * Quicklists are light weight lists of pages that have a defined state
+ * on alloc and free. Pages must be in the quicklist specific defined state
+ * (zero by default) when the page is freed. It seems that the initial idea
+ * for such lists first came from Dave Miller and then various other people
+ * improved on it.
+ *
+ * Copyright (C) 2007 SGI,
+ * 	Christoph Lameter <clameter@sgi.com>
+ * 		Generalized, added support for multiple lists and
+ * 		constructors / destructors.
+ */
+#include <linux/kernel.h>
+
+#include <linux/gfp.h>
+#include <linux/mm.h>
+#include <linux/mmzone.h>
+#include <linux/quicklist.h>
+
+DEFINE_PER_CPU(struct quicklist [CONFIG_NR_QUICK], quicklist);
+
+#define FRACTION_OF_NODE_MEM	16
+
+static unsigned long max_pages(unsigned long min_pages)
+{
+	unsigned long node_free_pages, max;
+	int node = numa_node_id();
+	struct zone *zones = NODE_DATA(node)->node_zones;
+	int num_cpus_on_node;
+
+	node_free_pages =
+#ifdef CONFIG_ZONE_DMA
+		zone_page_state(&zones[ZONE_DMA], NR_FREE_PAGES) +
+#endif
+#ifdef CONFIG_ZONE_DMA32
+		zone_page_state(&zones[ZONE_DMA32], NR_FREE_PAGES) +
+#endif
+		zone_page_state(&zones[ZONE_NORMAL], NR_FREE_PAGES);
+
+	max = node_free_pages / FRACTION_OF_NODE_MEM;
+
+	num_cpus_on_node = cpumask_weight(cpumask_of_node(node));
+	max /= num_cpus_on_node;
+
+	return max(max, min_pages);
+}
+
+static long min_pages_to_free(struct quicklist *q,
+	unsigned long min_pages, long max_free)
+{
+	long pages_to_free;
+
+	pages_to_free = q->nr_pages - max_pages(min_pages);
+
+	return min(pages_to_free, max_free);
+}
+
+/*
+ * Trim down the number of pages in the quicklist
+ */
+void quicklist_trim(int nr, void (*dtor)(void *),
+	unsigned long min_pages, unsigned long max_free)
+{
+	long pages_to_free;
+	struct quicklist *q;
+
+	q = &get_cpu_var(quicklist)[nr];
+	if (q->nr_pages > min_pages) {
+		pages_to_free = min_pages_to_free(q, min_pages, max_free);
+
+		while (pages_to_free > 0) {
+			/*
+			 * We pass a gfp_t of 0 to quicklist_alloc here
+			 * because we will never call into the page allocator.
+			 */
+			void *p = quicklist_alloc(nr, 0, NULL);
+
+			if (dtor)
+				dtor(p);
+			free_page((unsigned long)p);
+			pages_to_free--;
+		}
+	}
+	put_cpu_var(quicklist);
+}
+
+unsigned long quicklist_total_size(void)
+{
+	unsigned long count = 0;
+	int cpu;
+	struct quicklist *ql, *q;
+
+	for_each_online_cpu(cpu) {
+		ql = per_cpu(quicklist, cpu);
+		for (q = ql; q < ql + CONFIG_NR_QUICK; q++)
+			count += q->nr_pages;
+	}
+	return count;
+}
+

mm/readahead.c

@@ -0,0 +1,580 @@
+/*
+ * mm/readahead.c - address_space-level file readahead.
+ *
+ * Copyright (C) 2002, Linus Torvalds
+ *
+ * 09Apr2002	Andrew Morton
+ *		Initial version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/gfp.h>
+#include <linux/export.h>
+#include <linux/blkdev.h>
+#include <linux/backing-dev.h>
+#include <linux/task_io_accounting_ops.h>
+#include <linux/pagevec.h>
+#include <linux/pagemap.h>
+#include <linux/syscalls.h>
+#include <linux/file.h>
+
+#include "internal.h"
+
+/*
+ * Initialise a struct file's readahead state.  Assumes that the caller has
+ * memset *ra to zero.
+ */
+void
+file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping)
+{
+	ra->ra_pages = mapping->backing_dev_info->ra_pages;
+	ra->prev_pos = -1;
+}
+EXPORT_SYMBOL_GPL(file_ra_state_init);
+
+#define list_to_page(head) (list_entry((head)->prev, struct page, lru))
+
+/*
+ * see if a page needs releasing upon read_cache_pages() failure
+ * - the caller of read_cache_pages() may have set PG_private or PG_fscache
+ *   before calling, such as the NFS fs marking pages that are cached locally
+ *   on disk, thus we need to give the fs a chance to clean up in the event of
+ *   an error
+ */
+static void read_cache_pages_invalidate_page(struct address_space *mapping,
+					     struct page *page)
+{
+	if (page_has_private(page)) {
+		if (!trylock_page(page))
+			BUG();
+		page->mapping = mapping;
+		do_invalidatepage(page, 0, PAGE_CACHE_SIZE);
+		page->mapping = NULL;
+		unlock_page(page);
+	}
+	page_cache_release(page);
+}
+
+/*
+ * release a list of pages, invalidating them first if need be
+ */
+static void read_cache_pages_invalidate_pages(struct address_space *mapping,
+					      struct list_head *pages)
+{
+	struct page *victim;
+
+	while (!list_empty(pages)) {
+		victim = list_to_page(pages);
+		list_del(&victim->lru);
+		read_cache_pages_invalidate_page(mapping, victim);
+	}
+}
+
+/**
+ * read_cache_pages - populate an address space with some pages & start reads against them
+ * @mapping: the address_space
+ * @pages: The address of a list_head which contains the target pages.  These
+ *   pages have their ->index populated and are otherwise uninitialised.
+ * @filler: callback routine for filling a single page.
+ * @data: private data for the callback routine.
+ *
+ * Hides the details of the LRU cache etc from the filesystems.
+ */
+int read_cache_pages(struct address_space *mapping, struct list_head *pages,
+			int (*filler)(void *, struct page *), void *data)
+{
+	struct page *page;
+	int ret = 0;
+
+	while (!list_empty(pages)) {
+		page = list_to_page(pages);
+		list_del(&page->lru);
+		if (add_to_page_cache_lru(page, mapping,
+					page->index, GFP_KERNEL)) {
+			read_cache_pages_invalidate_page(mapping, page);
+			continue;
+		}
+		page_cache_release(page);
+
+		ret = filler(data, page);
+		if (unlikely(ret)) {
+			read_cache_pages_invalidate_pages(mapping, pages);
+			break;
+		}
+		task_io_account_read(PAGE_CACHE_SIZE);
+	}
+	return ret;
+}
+
+EXPORT_SYMBOL(read_cache_pages);
+
+static int read_pages(struct address_space *mapping, struct file *filp,
+		struct list_head *pages, unsigned nr_pages)
+{
+	struct blk_plug plug;
+	unsigned page_idx;
+	int ret;
+
+	blk_start_plug(&plug);
+
+	if (mapping->a_ops->readpages) {
+		ret = mapping->a_ops->readpages(filp, mapping, pages, nr_pages);
+		/* Clean up the remaining pages */
+		put_pages_list(pages);
+		goto out;
+	}
+
+	for (page_idx = 0; page_idx < nr_pages; page_idx++) {
+		struct page *page = list_to_page(pages);
+		list_del(&page->lru);
+		if (!add_to_page_cache_lru(page, mapping,
+					page->index, GFP_KERNEL)) {
+			mapping->a_ops->readpage(filp, page);
+		}
+		page_cache_release(page);
+	}
+	ret = 0;
+
+out:
+	blk_finish_plug(&plug);
+
+	return ret;
+}
+
+/*
+ * __do_page_cache_readahead() actually reads a chunk of disk.  It allocates all
+ * the pages first, then submits them all for I/O. This avoids the very bad
+ * behaviour which would occur if page allocations are causing VM writeback.
+ * We really don't want to intermingle reads and writes like that.
+ *
+ * Returns the number of pages requested, or the maximum amount of I/O allowed.
+ */
+int __do_page_cache_readahead(struct address_space *mapping, struct file *filp,
+			pgoff_t offset, unsigned long nr_to_read,
+			unsigned long lookahead_size)
+{
+	struct inode *inode = mapping->host;
+	struct page *page;
+	unsigned long end_index;	/* The last page we want to read */
+	LIST_HEAD(page_pool);
+	int page_idx;
+	int ret = 0;
+	loff_t isize = i_size_read(inode);
+
+	if (isize == 0)
+		goto out;
+
+	end_index = ((isize - 1) >> PAGE_CACHE_SHIFT);
+
+	/*
+	 * Preallocate as many pages as we will need.
+	 */
+	for (page_idx = 0; page_idx < nr_to_read; page_idx++) {
+		pgoff_t page_offset = offset + page_idx;
+
+		if (page_offset > end_index)
+			break;
+
+		rcu_read_lock();
+		page = radix_tree_lookup(&mapping->page_tree, page_offset);
+		rcu_read_unlock();
+		if (page && !radix_tree_exceptional_entry(page))
+			continue;
+
+		page = page_cache_alloc_readahead(mapping);
+		if (!page)
+			break;
+		page->index = page_offset;
+		list_add(&page->lru, &page_pool);
+		if (page_idx == nr_to_read - lookahead_size)
+			SetPageReadahead(page);
+		ret++;
+	}
+
+	/*
+	 * Now start the IO.  We ignore I/O errors - if the page is not
+	 * uptodate then the caller will launch readpage again, and
+	 * will then handle the error.
+	 */
+	if (ret)
+		read_pages(mapping, filp, &page_pool, ret);
+	BUG_ON(!list_empty(&page_pool));
+out:
+	return ret;
+}
+
+/*
+ * Chunk the readahead into 2 megabyte units, so that we don't pin too much
+ * memory at once.
+ */
+int force_page_cache_readahead(struct address_space *mapping, struct file *filp,
+		pgoff_t offset, unsigned long nr_to_read)
+{
+	if (unlikely(!mapping->a_ops->readpage && !mapping->a_ops->readpages))
+		return -EINVAL;
+
+	nr_to_read = max_sane_readahead(nr_to_read);
+	while (nr_to_read) {
+		int err;
+
+		unsigned long this_chunk = (2 * 1024 * 1024) / PAGE_CACHE_SIZE;
+
+		if (this_chunk > nr_to_read)
+			this_chunk = nr_to_read;
+		err = __do_page_cache_readahead(mapping, filp,
+						offset, this_chunk, 0);
+		if (err < 0)
+			return err;
+
+		offset += this_chunk;
+		nr_to_read -= this_chunk;
+	}
+	return 0;
+}
+
+#define MAX_READAHEAD   ((512*4096)/PAGE_CACHE_SIZE)
+/*
+ * Given a desired number of PAGE_CACHE_SIZE readahead pages, return a
+ * sensible upper limit.
+ */
+unsigned long max_sane_readahead(unsigned long nr)
+{
+	return min(nr, MAX_READAHEAD);
+}
+
+/*
+ * Set the initial window size, round to next power of 2 and square
+ * for small size, x 4 for medium, and x 2 for large
+ * for 128k (32 page) max ra
+ * 1-8 page = 32k initial, > 8 page = 128k initial
+ */
+static unsigned long get_init_ra_size(unsigned long size, unsigned long max)
+{
+	unsigned long newsize = roundup_pow_of_two(size);
+
+	if (newsize <= max / 32)
+		newsize = newsize * 4;
+	else if (newsize <= max / 4)
+		newsize = newsize * 2;
+	else
+		newsize = max;
+
+	return newsize;
+}
+
+/*
+ *  Get the previous window size, ramp it up, and
+ *  return it as the new window size.
+ */
+static unsigned long get_next_ra_size(struct file_ra_state *ra,
+						unsigned long max)
+{
+	unsigned long cur = ra->size;
+	unsigned long newsize;
+
+	if (cur < max / 16)
+		newsize = 4 * cur;
+	else
+		newsize = 2 * cur;
+
+	return min(newsize, max);
+}
+
+/*
+ * On-demand readahead design.
+ *
+ * The fields in struct file_ra_state represent the most-recently-executed
+ * readahead attempt:
+ *
+ *                        |<----- async_size ---------|
+ *     |------------------- size -------------------->|
+ *     |==================#===========================|
+ *     ^start             ^page marked with PG_readahead
+ *
+ * To overlap application thinking time and disk I/O time, we do
+ * `readahead pipelining': Do not wait until the application consumed all
+ * readahead pages and stalled on the missing page at readahead_index;
+ * Instead, submit an asynchronous readahead I/O as soon as there are
+ * only async_size pages left in the readahead window. Normally async_size
+ * will be equal to size, for maximum pipelining.
+ *
+ * In interleaved sequential reads, concurrent streams on the same fd can
+ * be invalidating each other's readahead state. So we flag the new readahead
+ * page at (start+size-async_size) with PG_readahead, and use it as readahead
+ * indicator. The flag won't be set on already cached pages, to avoid the
+ * readahead-for-nothing fuss, saving pointless page cache lookups.
+ *
+ * prev_pos tracks the last visited byte in the _previous_ read request.
+ * It should be maintained by the caller, and will be used for detecting
+ * small random reads. Note that the readahead algorithm checks loosely
+ * for sequential patterns. Hence interleaved reads might be served as
+ * sequential ones.
+ *
+ * There is a special-case: if the first page which the application tries to
+ * read happens to be the first page of the file, it is assumed that a linear
+ * read is about to happen and the window is immediately set to the initial size
+ * based on I/O request size and the max_readahead.
+ *
+ * The code ramps up the readahead size aggressively at first, but slow down as
+ * it approaches max_readhead.
+ */
+
+/*
+ * Count contiguously cached pages from @offset-1 to @offset-@max,
+ * this count is a conservative estimation of
+ * 	- length of the sequential read sequence, or
+ * 	- thrashing threshold in memory tight systems
+ */
+static pgoff_t count_history_pages(struct address_space *mapping,
+				   pgoff_t offset, unsigned long max)
+{
+	pgoff_t head;
+
+	rcu_read_lock();
+	head = page_cache_prev_hole(mapping, offset - 1, max);
+	rcu_read_unlock();
+
+	return offset - 1 - head;
+}
+
+/*
+ * page cache context based read-ahead
+ */
+static int try_context_readahead(struct address_space *mapping,
+				 struct file_ra_state *ra,
+				 pgoff_t offset,
+				 unsigned long req_size,
+				 unsigned long max)
+{
+	pgoff_t size;
+
+	size = count_history_pages(mapping, offset, max);
+
+	/*
+	 * not enough history pages:
+	 * it could be a random read
+	 */
+	if (size <= req_size)
+		return 0;
+
+	/*
+	 * starts from beginning of file:
+	 * it is a strong indication of long-run stream (or whole-file-read)
+	 */
+	if (size >= offset)
+		size *= 2;
+
+	ra->start = offset;
+	ra->size = min(size + req_size, max);
+	ra->async_size = 1;
+
+	return 1;
+}
+
+/*
+ * A minimal readahead algorithm for trivial sequential/random reads.
+ */
+static unsigned long
+ondemand_readahead(struct address_space *mapping,
+		   struct file_ra_state *ra, struct file *filp,
+		   bool hit_readahead_marker, pgoff_t offset,
+		   unsigned long req_size)
+{
+	unsigned long max = max_sane_readahead(ra->ra_pages);
+	pgoff_t prev_offset;
+
+	/*
+	 * start of file
+	 */
+	if (!offset)
+		goto initial_readahead;
+
+	/*
+	 * It's the expected callback offset, assume sequential access.
+	 * Ramp up sizes, and push forward the readahead window.
+	 */
+	if ((offset == (ra->start + ra->size - ra->async_size) ||
+	     offset == (ra->start + ra->size))) {
+		ra->start += ra->size;
+		ra->size = get_next_ra_size(ra, max);
+		ra->async_size = ra->size;
+		goto readit;
+	}
+
+	/*
+	 * Hit a marked page without valid readahead state.
+	 * E.g. interleaved reads.
+	 * Query the pagecache for async_size, which normally equals to
+	 * readahead size. Ramp it up and use it as the new readahead size.
+	 */
+	if (hit_readahead_marker) {
+		pgoff_t start;
+
+		rcu_read_lock();
+		start = page_cache_next_hole(mapping, offset + 1, max);
+		rcu_read_unlock();
+
+		if (!start || start - offset > max)
+			return 0;
+
+		ra->start = start;
+		ra->size = start - offset;	/* old async_size */
+		ra->size += req_size;
+		ra->size = get_next_ra_size(ra, max);
+		ra->async_size = ra->size;
+		goto readit;
+	}
+
+	/*
+	 * oversize read
+	 */
+	if (req_size > max)
+		goto initial_readahead;
+
+	/*
+	 * sequential cache miss
+	 * trivial case: (offset - prev_offset) == 1
+	 * unaligned reads: (offset - prev_offset) == 0
+	 */
+	prev_offset = (unsigned long long)ra->prev_pos >> PAGE_CACHE_SHIFT;
+	if (offset - prev_offset <= 1UL)
+		goto initial_readahead;
+
+	/*
+	 * Query the page cache and look for the traces(cached history pages)
+	 * that a sequential stream would leave behind.
+	 */
+	if (try_context_readahead(mapping, ra, offset, req_size, max))
+		goto readit;
+
+	/*
+	 * standalone, small random read
+	 * Read as is, and do not pollute the readahead state.
+	 */
+	return __do_page_cache_readahead(mapping, filp, offset, req_size, 0);
+
+initial_readahead:
+	ra->start = offset;
+	ra->size = get_init_ra_size(req_size, max);
+	ra->async_size = ra->size > req_size ? ra->size - req_size : ra->size;
+
+readit:
+	/*
+	 * Will this read hit the readahead marker made by itself?
+	 * If so, trigger the readahead marker hit now, and merge
+	 * the resulted next readahead window into the current one.
+	 */
+	if (offset == ra->start && ra->size == ra->async_size) {
+		ra->async_size = get_next_ra_size(ra, max);
+		ra->size += ra->async_size;
+	}
+
+	return ra_submit(ra, mapping, filp);
+}
+
+/**
+ * page_cache_sync_readahead - generic file readahead
+ * @mapping: address_space which holds the pagecache and I/O vectors
+ * @ra: file_ra_state which holds the readahead state
+ * @filp: passed on to ->readpage() and ->readpages()
+ * @offset: start offset into @mapping, in pagecache page-sized units
+ * @req_size: hint: total size of the read which the caller is performing in
+ *            pagecache pages
+ *
+ * page_cache_sync_readahead() should be called when a cache miss happened:
+ * it will submit the read.  The readahead logic may decide to piggyback more
+ * pages onto the read request if access patterns suggest it will improve
+ * performance.
+ */
+void page_cache_sync_readahead(struct address_space *mapping,
+			       struct file_ra_state *ra, struct file *filp,
+			       pgoff_t offset, unsigned long req_size)
+{
+	/* no read-ahead */
+	if (!ra->ra_pages)
+		return;
+
+	/* be dumb */
+	if (filp && (filp->f_mode & FMODE_RANDOM)) {
+		force_page_cache_readahead(mapping, filp, offset, req_size);
+		return;
+	}
+
+	/* do read-ahead */
+	ondemand_readahead(mapping, ra, filp, false, offset, req_size);
+}
+EXPORT_SYMBOL_GPL(page_cache_sync_readahead);
+
+/**
+ * page_cache_async_readahead - file readahead for marked pages
+ * @mapping: address_space which holds the pagecache and I/O vectors
+ * @ra: file_ra_state which holds the readahead state
+ * @filp: passed on to ->readpage() and ->readpages()
+ * @page: the page at @offset which has the PG_readahead flag set
+ * @offset: start offset into @mapping, in pagecache page-sized units
+ * @req_size: hint: total size of the read which the caller is performing in
+ *            pagecache pages
+ *
+ * page_cache_async_readahead() should be called when a page is used which
+ * has the PG_readahead flag; this is a marker to suggest that the application
+ * has used up enough of the readahead window that we should start pulling in
+ * more pages.
+ */
+void
+page_cache_async_readahead(struct address_space *mapping,
+			   struct file_ra_state *ra, struct file *filp,
+			   struct page *page, pgoff_t offset,
+			   unsigned long req_size)
+{
+	/* no read-ahead */
+	if (!ra->ra_pages)
+		return;
+
+	/*
+	 * Same bit is used for PG_readahead and PG_reclaim.
+	 */
+	if (PageWriteback(page))
+		return;
+
+	ClearPageReadahead(page);
+
+	/*
+	 * Defer asynchronous read-ahead on IO congestion.
+	 */
+	if (bdi_read_congested(mapping->backing_dev_info))
+		return;
+
+	/* do read-ahead */
+	ondemand_readahead(mapping, ra, filp, true, offset, req_size);
+}
+EXPORT_SYMBOL_GPL(page_cache_async_readahead);
+
+static ssize_t
+do_readahead(struct address_space *mapping, struct file *filp,
+	     pgoff_t index, unsigned long nr)
+{
+	if (!mapping || !mapping->a_ops)
+		return -EINVAL;
+
+	return force_page_cache_readahead(mapping, filp, index, nr);
+}
+
+SYSCALL_DEFINE3(readahead, int, fd, loff_t, offset, size_t, count)
+{
+	ssize_t ret;
+	struct fd f;
+
+	ret = -EBADF;
+	f = fdget(fd);
+	if (f.file) {
+		if (f.file->f_mode & FMODE_READ) {
+			struct address_space *mapping = f.file->f_mapping;
+			pgoff_t start = offset >> PAGE_CACHE_SHIFT;
+			pgoff_t end = (offset + count - 1) >> PAGE_CACHE_SHIFT;
+			unsigned long len = end - start + 1;
+			ret = do_readahead(mapping, f.file, start, len);
+		}
+		fdput(f);
+	}
+	return ret;
+}

mm/slab.h

@@ -0,0 +1,363 @@
+#ifndef MM_SLAB_H
+#define MM_SLAB_H
+/*
+ * Internal slab definitions
+ */
+
+#ifdef CONFIG_SLOB
+/*
+ * Common fields provided in kmem_cache by all slab allocators
+ * This struct is either used directly by the allocator (SLOB)
+ * or the allocator must include definitions for all fields
+ * provided in kmem_cache_common in their definition of kmem_cache.
+ *
+ * Once we can do anonymous structs (C11 standard) we could put a
+ * anonymous struct definition in these allocators so that the
+ * separate allocations in the kmem_cache structure of SLAB and
+ * SLUB is no longer needed.
+ */
+struct kmem_cache {
+	unsigned int object_size;/* The original size of the object */
+	unsigned int size;	/* The aligned/padded/added on size  */
+	unsigned int align;	/* Alignment as calculated */
+	unsigned long flags;	/* Active flags on the slab */
+	const char *name;	/* Slab name for sysfs */
+	int refcount;		/* Use counter */
+	void (*ctor)(void *);	/* Called on object slot creation */
+	struct list_head list;	/* List of all slab caches on the system */
+};
+
+#endif /* CONFIG_SLOB */
+
+#ifdef CONFIG_SLAB
+#include <linux/slab_def.h>
+#endif
+
+#ifdef CONFIG_SLUB
+#include <linux/slub_def.h>
+#endif
+
+#include <linux/memcontrol.h>
+
+/*
+ * State of the slab allocator.
+ *
+ * This is used to describe the states of the allocator during bootup.
+ * Allocators use this to gradually bootstrap themselves. Most allocators
+ * have the problem that the structures used for managing slab caches are
+ * allocated from slab caches themselves.
+ */
+enum slab_state {
+	DOWN,			/* No slab functionality yet */
+	PARTIAL,		/* SLUB: kmem_cache_node available */
+	PARTIAL_NODE,		/* SLAB: kmalloc size for node struct available */
+	UP,			/* Slab caches usable but not all extras yet */
+	FULL			/* Everything is working */
+};
+
+extern enum slab_state slab_state;
+
+/* The slab cache mutex protects the management structures during changes */
+extern struct mutex slab_mutex;
+
+/* The list of all slab caches on the system */
+extern struct list_head slab_caches;
+
+/* The slab cache that manages slab cache information */
+extern struct kmem_cache *kmem_cache;
+
+unsigned long calculate_alignment(unsigned long flags,
+		unsigned long align, unsigned long size);
+
+#ifndef CONFIG_SLOB
+/* Kmalloc array related functions */
+void create_kmalloc_caches(unsigned long);
+
+/* Find the kmalloc slab corresponding for a certain size */
+struct kmem_cache *kmalloc_slab(size_t, gfp_t);
+#endif
+
+
+/* Functions provided by the slab allocators */
+extern int __kmem_cache_create(struct kmem_cache *, unsigned long flags);
+
+extern struct kmem_cache *create_kmalloc_cache(const char *name, size_t size,
+			unsigned long flags);
+extern void create_boot_cache(struct kmem_cache *, const char *name,
+			size_t size, unsigned long flags);
+
+struct mem_cgroup;
+
+int slab_unmergeable(struct kmem_cache *s);
+struct kmem_cache *find_mergeable(size_t size, size_t align,
+		unsigned long flags, const char *name, void (*ctor)(void *));
+#ifndef CONFIG_SLOB
+struct kmem_cache *
+__kmem_cache_alias(const char *name, size_t size, size_t align,
+		   unsigned long flags, void (*ctor)(void *));
+
+unsigned long kmem_cache_flags(unsigned long object_size,
+	unsigned long flags, const char *name,
+	void (*ctor)(void *));
+#else
+static inline struct kmem_cache *
+__kmem_cache_alias(const char *name, size_t size, size_t align,
+		   unsigned long flags, void (*ctor)(void *))
+{ return NULL; }
+
+static inline unsigned long kmem_cache_flags(unsigned long object_size,
+	unsigned long flags, const char *name,
+	void (*ctor)(void *))
+{
+	return flags;
+}
+#endif
+
+
+/* Legal flag mask for kmem_cache_create(), for various configurations */
+#define SLAB_CORE_FLAGS (SLAB_HWCACHE_ALIGN | SLAB_CACHE_DMA | SLAB_PANIC | \
+			 SLAB_DESTROY_BY_RCU | SLAB_DEBUG_OBJECTS )
+
+#if defined(CONFIG_DEBUG_SLAB)
+#define SLAB_DEBUG_FLAGS (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER)
+#elif defined(CONFIG_SLUB_DEBUG)
+#define SLAB_DEBUG_FLAGS (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER | \
+			  SLAB_TRACE | SLAB_DEBUG_FREE)
+#else
+#define SLAB_DEBUG_FLAGS (0)
+#endif
+
+#if defined(CONFIG_SLAB)
+#define SLAB_CACHE_FLAGS (SLAB_MEM_SPREAD | SLAB_NOLEAKTRACE | \
+			  SLAB_RECLAIM_ACCOUNT | SLAB_TEMPORARY | SLAB_NOTRACK)
+#elif defined(CONFIG_SLUB)
+#define SLAB_CACHE_FLAGS (SLAB_NOLEAKTRACE | SLAB_RECLAIM_ACCOUNT | \
+			  SLAB_TEMPORARY | SLAB_NOTRACK)
+#else
+#define SLAB_CACHE_FLAGS (0)
+#endif
+
+#define CACHE_CREATE_MASK (SLAB_CORE_FLAGS | SLAB_DEBUG_FLAGS | SLAB_CACHE_FLAGS)
+
+int __kmem_cache_shutdown(struct kmem_cache *);
+int __kmem_cache_shrink(struct kmem_cache *);
+void slab_kmem_cache_release(struct kmem_cache *);
+
+struct seq_file;
+struct file;
+
+struct slabinfo {
+	unsigned long active_objs;
+	unsigned long num_objs;
+	unsigned long active_slabs;
+	unsigned long num_slabs;
+	unsigned long shared_avail;
+	unsigned int limit;
+	unsigned int batchcount;
+	unsigned int shared;
+	unsigned int objects_per_slab;
+	unsigned int cache_order;
+};
+
+void get_slabinfo(struct kmem_cache *s, struct slabinfo *sinfo);
+void slabinfo_show_stats(struct seq_file *m, struct kmem_cache *s);
+ssize_t slabinfo_write(struct file *file, const char __user *buffer,
+		       size_t count, loff_t *ppos);
+
+#ifdef CONFIG_MEMCG_KMEM
+static inline bool is_root_cache(struct kmem_cache *s)
+{
+	return !s->memcg_params || s->memcg_params->is_root_cache;
+}
+
+static inline bool slab_equal_or_root(struct kmem_cache *s,
+					struct kmem_cache *p)
+{
+	return (p == s) ||
+		(s->memcg_params && (p == s->memcg_params->root_cache));
+}
+
+/*
+ * We use suffixes to the name in memcg because we can't have caches
+ * created in the system with the same name. But when we print them
+ * locally, better refer to them with the base name
+ */
+static inline const char *cache_name(struct kmem_cache *s)
+{
+	if (!is_root_cache(s))
+		return s->memcg_params->root_cache->name;
+	return s->name;
+}
+
+/*
+ * Note, we protect with RCU only the memcg_caches array, not per-memcg caches.
+ * That said the caller must assure the memcg's cache won't go away. Since once
+ * created a memcg's cache is destroyed only along with the root cache, it is
+ * true if we are going to allocate from the cache or hold a reference to the
+ * root cache by other means. Otherwise, we should hold either the slab_mutex
+ * or the memcg's slab_caches_mutex while calling this function and accessing
+ * the returned value.
+ */
+static inline struct kmem_cache *
+cache_from_memcg_idx(struct kmem_cache *s, int idx)
+{
+	struct kmem_cache *cachep;
+	struct memcg_cache_params *params;
+
+	if (!s->memcg_params)
+		return NULL;
+
+	rcu_read_lock();
+	params = rcu_dereference(s->memcg_params);
+	cachep = params->memcg_caches[idx];
+	rcu_read_unlock();
+
+	/*
+	 * Make sure we will access the up-to-date value. The code updating
+	 * memcg_caches issues a write barrier to match this (see
+	 * memcg_register_cache()).
+	 */
+	smp_read_barrier_depends();
+	return cachep;
+}
+
+static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s)
+{
+	if (is_root_cache(s))
+		return s;
+	return s->memcg_params->root_cache;
+}
+
+static __always_inline int memcg_charge_slab(struct kmem_cache *s,
+					     gfp_t gfp, int order)
+{
+	if (!memcg_kmem_enabled())
+		return 0;
+	if (is_root_cache(s))
+		return 0;
+	return __memcg_charge_slab(s, gfp, order);
+}
+
+static __always_inline void memcg_uncharge_slab(struct kmem_cache *s, int order)
+{
+	if (!memcg_kmem_enabled())
+		return;
+	if (is_root_cache(s))
+		return;
+	__memcg_uncharge_slab(s, order);
+}
+#else
+static inline bool is_root_cache(struct kmem_cache *s)
+{
+	return true;
+}
+
+static inline bool slab_equal_or_root(struct kmem_cache *s,
+				      struct kmem_cache *p)
+{
+	return true;
+}
+
+static inline const char *cache_name(struct kmem_cache *s)
+{
+	return s->name;
+}
+
+static inline struct kmem_cache *
+cache_from_memcg_idx(struct kmem_cache *s, int idx)
+{
+	return NULL;
+}
+
+static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s)
+{
+	return s;
+}
+
+static inline int memcg_charge_slab(struct kmem_cache *s, gfp_t gfp, int order)
+{
+	return 0;
+}
+
+static inline void memcg_uncharge_slab(struct kmem_cache *s, int order)
+{
+}
+#endif
+
+static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x)
+{
+	struct kmem_cache *cachep;
+	struct page *page;
+
+	/*
+	 * When kmemcg is not being used, both assignments should return the
+	 * same value. but we don't want to pay the assignment price in that
+	 * case. If it is not compiled in, the compiler should be smart enough
+	 * to not do even the assignment. In that case, slab_equal_or_root
+	 * will also be a constant.
+	 */
+	if (!memcg_kmem_enabled() && !unlikely(s->flags & SLAB_DEBUG_FREE))
+		return s;
+
+	page = virt_to_head_page(x);
+	cachep = page->slab_cache;
+	if (slab_equal_or_root(cachep, s))
+		return cachep;
+
+	pr_err("%s: Wrong slab cache. %s but object is from %s\n",
+	       __func__, cachep->name, s->name);
+	WARN_ON_ONCE(1);
+	return s;
+}
+
+#ifndef CONFIG_SLOB
+/*
+ * The slab lists for all objects.
+ */
+struct kmem_cache_node {
+	spinlock_t list_lock;
+
+#ifdef CONFIG_SLAB
+	struct list_head slabs_partial;	/* partial list first, better asm code */
+	struct list_head slabs_full;
+	struct list_head slabs_free;
+	unsigned long free_objects;
+	unsigned int free_limit;
+	unsigned int colour_next;	/* Per-node cache coloring */
+	struct array_cache *shared;	/* shared per node */
+	struct alien_cache **alien;	/* on other nodes */
+	unsigned long next_reap;	/* updated without locking */
+	int free_touched;		/* updated without locking */
+#endif
+
+#ifdef CONFIG_SLUB
+	unsigned long nr_partial;
+	struct list_head partial;
+#ifdef CONFIG_SLUB_DEBUG
+	atomic_long_t nr_slabs;
+	atomic_long_t total_objects;
+	struct list_head full;
+#endif
+#endif
+
+};
+
+static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
+{
+	return s->node[node];
+}
+
+/*
+ * Iterator over all nodes. The body will be executed for each node that has
+ * a kmem_cache_node structure allocated (which is true for all online nodes)
+ */
+#define for_each_kmem_cache_node(__s, __node, __n) \
+	for (__node = 0; __node < nr_node_ids; __node++) \
+		 if ((__n = get_node(__s, __node)))
+
+#endif
+
+void *slab_next(struct seq_file *m, void *p, loff_t *pos);
+void slab_stop(struct seq_file *m, void *p);
+
+#endif /* MM_SLAB_H */

mm/slob.c

@@ -0,0 +1,642 @@
+/*
+ * SLOB Allocator: Simple List Of Blocks
+ *
+ * Matt Mackall <mpm@selenic.com> 12/30/03
+ *
+ * NUMA support by Paul Mundt, 2007.
+ *
+ * How SLOB works:
+ *
+ * The core of SLOB is a traditional K&R style heap allocator, with
+ * support for returning aligned objects. The granularity of this
+ * allocator is as little as 2 bytes, however typically most architectures
+ * will require 4 bytes on 32-bit and 8 bytes on 64-bit.
+ *
+ * The slob heap is a set of linked list of pages from alloc_pages(),
+ * and within each page, there is a singly-linked list of free blocks
+ * (slob_t). The heap is grown on demand. To reduce fragmentation,
+ * heap pages are segregated into three lists, with objects less than
+ * 256 bytes, objects less than 1024 bytes, and all other objects.
+ *
+ * Allocation from heap involves first searching for a page with
+ * sufficient free blocks (using a next-fit-like approach) followed by
+ * a first-fit scan of the page. Deallocation inserts objects back
+ * into the free list in address order, so this is effectively an
+ * address-ordered first fit.
+ *
+ * Above this is an implementation of kmalloc/kfree. Blocks returned
+ * from kmalloc are prepended with a 4-byte header with the kmalloc size.
+ * If kmalloc is asked for objects of PAGE_SIZE or larger, it calls
+ * alloc_pages() directly, allocating compound pages so the page order
+ * does not have to be separately tracked.
+ * These objects are detected in kfree() because PageSlab()
+ * is false for them.
+ *
+ * SLAB is emulated on top of SLOB by simply calling constructors and
+ * destructors for every SLAB allocation. Objects are returned with the
+ * 4-byte alignment unless the SLAB_HWCACHE_ALIGN flag is set, in which
+ * case the low-level allocator will fragment blocks to create the proper
+ * alignment. Again, objects of page-size or greater are allocated by
+ * calling alloc_pages(). As SLAB objects know their size, no separate
+ * size bookkeeping is necessary and there is essentially no allocation
+ * space overhead, and compound pages aren't needed for multi-page
+ * allocations.
+ *
+ * NUMA support in SLOB is fairly simplistic, pushing most of the real
+ * logic down to the page allocator, and simply doing the node accounting
+ * on the upper levels. In the event that a node id is explicitly
+ * provided, alloc_pages_exact_node() with the specified node id is used
+ * instead. The common case (or when the node id isn't explicitly provided)
+ * will default to the current node, as per numa_node_id().
+ *
+ * Node aware pages are still inserted in to the global freelist, and
+ * these are scanned for by matching against the node id encoded in the
+ * page flags. As a result, block allocations that can be satisfied from
+ * the freelist will only be done so on pages residing on the same node,
+ * in order to prevent random node placement.
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+
+#include <linux/mm.h>
+#include <linux/swap.h> /* struct reclaim_state */
+#include <linux/cache.h>
+#include <linux/init.h>
+#include <linux/export.h>
+#include <linux/rcupdate.h>
+#include <linux/list.h>
+#include <linux/kmemleak.h>
+
+#include <trace/events/kmem.h>
+
+#include <linux/atomic.h>
+
+#include "slab.h"
+/*
+ * slob_block has a field 'units', which indicates size of block if +ve,
+ * or offset of next block if -ve (in SLOB_UNITs).
+ *
+ * Free blocks of size 1 unit simply contain the offset of the next block.
+ * Those with larger size contain their size in the first SLOB_UNIT of
+ * memory, and the offset of the next free block in the second SLOB_UNIT.
+ */
+#if PAGE_SIZE <= (32767 * 2)
+typedef s16 slobidx_t;
+#else
+typedef s32 slobidx_t;
+#endif
+
+struct slob_block {
+	slobidx_t units;
+};
+typedef struct slob_block slob_t;
+
+/*
+ * All partially free slob pages go on these lists.
+ */
+#define SLOB_BREAK1 256
+#define SLOB_BREAK2 1024
+static LIST_HEAD(free_slob_small);
+static LIST_HEAD(free_slob_medium);
+static LIST_HEAD(free_slob_large);
+
+/*
+ * slob_page_free: true for pages on free_slob_pages list.
+ */
+static inline int slob_page_free(struct page *sp)
+{
+	return PageSlobFree(sp);
+}
+
+static void set_slob_page_free(struct page *sp, struct list_head *list)
+{
+	list_add(&sp->lru, list);
+	__SetPageSlobFree(sp);
+}
+
+static inline void clear_slob_page_free(struct page *sp)
+{
+	list_del(&sp->lru);
+	__ClearPageSlobFree(sp);
+}
+
+#define SLOB_UNIT sizeof(slob_t)
+#define SLOB_UNITS(size) DIV_ROUND_UP(size, SLOB_UNIT)
+
+/*
+ * struct slob_rcu is inserted at the tail of allocated slob blocks, which
+ * were created with a SLAB_DESTROY_BY_RCU slab. slob_rcu is used to free
+ * the block using call_rcu.
+ */
+struct slob_rcu {
+	struct rcu_head head;
+	int size;
+};
+
+/*
+ * slob_lock protects all slob allocator structures.
+ */
+static DEFINE_SPINLOCK(slob_lock);
+
+/*
+ * Encode the given size and next info into a free slob block s.
+ */
+static void set_slob(slob_t *s, slobidx_t size, slob_t *next)
+{
+	slob_t *base = (slob_t *)((unsigned long)s & PAGE_MASK);
+	slobidx_t offset = next - base;
+
+	if (size > 1) {
+		s[0].units = size;
+		s[1].units = offset;
+	} else
+		s[0].units = -offset;
+}
+
+/*
+ * Return the size of a slob block.
+ */
+static slobidx_t slob_units(slob_t *s)
+{
+	if (s->units > 0)
+		return s->units;
+	return 1;
+}
+
+/*
+ * Return the next free slob block pointer after this one.
+ */
+static slob_t *slob_next(slob_t *s)
+{
+	slob_t *base = (slob_t *)((unsigned long)s & PAGE_MASK);
+	slobidx_t next;
+
+	if (s[0].units < 0)
+		next = -s[0].units;
+	else
+		next = s[1].units;
+	return base+next;
+}
+
+/*
+ * Returns true if s is the last free block in its page.
+ */
+static int slob_last(slob_t *s)
+{
+	return !((unsigned long)slob_next(s) & ~PAGE_MASK);
+}
+
+static void *slob_new_pages(gfp_t gfp, int order, int node)
+{
+	void *page;
+
+#ifdef CONFIG_NUMA
+	if (node != NUMA_NO_NODE)
+		page = alloc_pages_exact_node(node, gfp, order);
+	else
+#endif
+		page = alloc_pages(gfp, order);
+
+	if (!page)
+		return NULL;
+
+	return page_address(page);
+}
+
+static void slob_free_pages(void *b, int order)
+{
+	if (current->reclaim_state)
+		current->reclaim_state->reclaimed_slab += 1 << order;
+	free_pages((unsigned long)b, order);
+}
+
+/*
+ * Allocate a slob block within a given slob_page sp.
+ */
+static void *slob_page_alloc(struct page *sp, size_t size, int align)
+{
+	slob_t *prev, *cur, *aligned = NULL;
+	int delta = 0, units = SLOB_UNITS(size);
+
+	for (prev = NULL, cur = sp->freelist; ; prev = cur, cur = slob_next(cur)) {
+		slobidx_t avail = slob_units(cur);
+
+		if (align) {
+			aligned = (slob_t *)ALIGN((unsigned long)cur, align);
+			delta = aligned - cur;
+		}
+		if (avail >= units + delta) { /* room enough? */
+			slob_t *next;
+
+			if (delta) { /* need to fragment head to align? */
+				next = slob_next(cur);
+				set_slob(aligned, avail - delta, next);
+				set_slob(cur, delta, aligned);
+				prev = cur;
+				cur = aligned;
+				avail = slob_units(cur);
+			}
+
+			next = slob_next(cur);
+			if (avail == units) { /* exact fit? unlink. */
+				if (prev)
+					set_slob(prev, slob_units(prev), next);
+				else
+					sp->freelist = next;
+			} else { /* fragment */
+				if (prev)
+					set_slob(prev, slob_units(prev), cur + units);
+				else
+					sp->freelist = cur + units;
+				set_slob(cur + units, avail - units, next);
+			}
+
+			sp->units -= units;
+			if (!sp->units)
+				clear_slob_page_free(sp);
+			return cur;
+		}
+		if (slob_last(cur))
+			return NULL;
+	}
+}
+
+/*
+ * slob_alloc: entry point into the slob allocator.
+ */
+static void *slob_alloc(size_t size, gfp_t gfp, int align, int node)
+{
+	struct page *sp;
+	struct list_head *prev;
+	struct list_head *slob_list;
+	slob_t *b = NULL;
+	unsigned long flags;
+
+	if (size < SLOB_BREAK1)
+		slob_list = &free_slob_small;
+	else if (size < SLOB_BREAK2)
+		slob_list = &free_slob_medium;
+	else
+		slob_list = &free_slob_large;
+
+	spin_lock_irqsave(&slob_lock, flags);
+	/* Iterate through each partially free page, try to find room */
+	list_for_each_entry(sp, slob_list, lru) {
+#ifdef CONFIG_NUMA
+		/*
+		 * If there's a node specification, search for a partial
+		 * page with a matching node id in the freelist.
+		 */
+		if (node != NUMA_NO_NODE && page_to_nid(sp) != node)
+			continue;
+#endif
+		/* Enough room on this page? */
+		if (sp->units < SLOB_UNITS(size))
+			continue;
+
+		/* Attempt to alloc */
+		prev = sp->lru.prev;
+		b = slob_page_alloc(sp, size, align);
+		if (!b)
+			continue;
+
+		/* Improve fragment distribution and reduce our average
+		 * search time by starting our next search here. (see
+		 * Knuth vol 1, sec 2.5, pg 449) */
+		if (prev != slob_list->prev &&
+				slob_list->next != prev->next)
+			list_move_tail(slob_list, prev->next);
+		break;
+	}
+	spin_unlock_irqrestore(&slob_lock, flags);
+
+	/* Not enough space: must allocate a new page */
+	if (!b) {
+		b = slob_new_pages(gfp & ~__GFP_ZERO, 0, node);
+		if (!b)
+			return NULL;
+		sp = virt_to_page(b);
+		__SetPageSlab(sp);
+
+		spin_lock_irqsave(&slob_lock, flags);
+		sp->units = SLOB_UNITS(PAGE_SIZE);
+		sp->freelist = b;
+		INIT_LIST_HEAD(&sp->lru);
+		set_slob(b, SLOB_UNITS(PAGE_SIZE), b + SLOB_UNITS(PAGE_SIZE));
+		set_slob_page_free(sp, slob_list);
+		b = slob_page_alloc(sp, size, align);
+		BUG_ON(!b);
+		spin_unlock_irqrestore(&slob_lock, flags);
+	}
+	if (unlikely((gfp & __GFP_ZERO) && b))
+		memset(b, 0, size);
+	return b;
+}
+
+/*
+ * slob_free: entry point into the slob allocator.
+ */
+static void slob_free(void *block, int size)
+{
+	struct page *sp;
+	slob_t *prev, *next, *b = (slob_t *)block;
+	slobidx_t units;
+	unsigned long flags;
+	struct list_head *slob_list;
+
+	if (unlikely(ZERO_OR_NULL_PTR(block)))
+		return;
+	BUG_ON(!size);
+
+	sp = virt_to_page(block);
+	units = SLOB_UNITS(size);
+
+	spin_lock_irqsave(&slob_lock, flags);
+
+	if (sp->units + units == SLOB_UNITS(PAGE_SIZE)) {
+		/* Go directly to page allocator. Do not pass slob allocator */
+		if (slob_page_free(sp))
+			clear_slob_page_free(sp);
+		spin_unlock_irqrestore(&slob_lock, flags);
+		__ClearPageSlab(sp);
+		page_mapcount_reset(sp);
+		slob_free_pages(b, 0);
+		return;
+	}
+
+	if (!slob_page_free(sp)) {
+		/* This slob page is about to become partially free. Easy! */
+		sp->units = units;
+		sp->freelist = b;
+		set_slob(b, units,
+			(void *)((unsigned long)(b +
+					SLOB_UNITS(PAGE_SIZE)) & PAGE_MASK));
+		if (size < SLOB_BREAK1)
+			slob_list = &free_slob_small;
+		else if (size < SLOB_BREAK2)
+			slob_list = &free_slob_medium;
+		else
+			slob_list = &free_slob_large;
+		set_slob_page_free(sp, slob_list);
+		goto out;
+	}
+
+	/*
+	 * Otherwise the page is already partially free, so find reinsertion
+	 * point.
+	 */
+	sp->units += units;
+
+	if (b < (slob_t *)sp->freelist) {
+		if (b + units == sp->freelist) {
+			units += slob_units(sp->freelist);
+			sp->freelist = slob_next(sp->freelist);
+		}
+		set_slob(b, units, sp->freelist);
+		sp->freelist = b;
+	} else {
+		prev = sp->freelist;
+		next = slob_next(prev);
+		while (b > next) {
+			prev = next;
+			next = slob_next(prev);
+		}
+
+		if (!slob_last(prev) && b + units == next) {
+			units += slob_units(next);
+			set_slob(b, units, slob_next(next));
+		} else
+			set_slob(b, units, next);
+
+		if (prev + slob_units(prev) == b) {
+			units = slob_units(b) + slob_units(prev);
+			set_slob(prev, units, slob_next(b));
+		} else
+			set_slob(prev, slob_units(prev), b);
+	}
+out:
+	spin_unlock_irqrestore(&slob_lock, flags);
+}
+
+/*
+ * End of slob allocator proper. Begin kmem_cache_alloc and kmalloc frontend.
+ */
+
+static __always_inline void *
+__do_kmalloc_node(size_t size, gfp_t gfp, int node, unsigned long caller)
+{
+	unsigned int *m;
+	int align = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
+	void *ret;
+
+	gfp &= gfp_allowed_mask;
+
+	lockdep_trace_alloc(gfp);
+
+	if (size < PAGE_SIZE - align) {
+		if (!size)
+			return ZERO_SIZE_PTR;
+
+		m = slob_alloc(size + align, gfp, align, node);
+
+		if (!m)
+			return NULL;
+		*m = size;
+		ret = (void *)m + align;
+
+		trace_kmalloc_node(caller, ret,
+				   size, size + align, gfp, node);
+	} else {
+		unsigned int order = get_order(size);
+
+		if (likely(order))
+			gfp |= __GFP_COMP;
+		ret = slob_new_pages(gfp, order, node);
+
+		trace_kmalloc_node(caller, ret,
+				   size, PAGE_SIZE << order, gfp, node);
+	}
+
+	kmemleak_alloc(ret, size, 1, gfp);
+	return ret;
+}
+
+void *__kmalloc(size_t size, gfp_t gfp)
+{
+	return __do_kmalloc_node(size, gfp, NUMA_NO_NODE, _RET_IP_);
+}
+EXPORT_SYMBOL(__kmalloc);
+
+void *__kmalloc_track_caller(size_t size, gfp_t gfp, unsigned long caller)
+{
+	return __do_kmalloc_node(size, gfp, NUMA_NO_NODE, caller);
+}
+
+#ifdef CONFIG_NUMA
+void *__kmalloc_node_track_caller(size_t size, gfp_t gfp,
+					int node, unsigned long caller)
+{
+	return __do_kmalloc_node(size, gfp, node, caller);
+}
+#endif
+
+void kfree(const void *block)
+{
+	struct page *sp;
+
+	trace_kfree(_RET_IP_, block);
+
+	if (unlikely(ZERO_OR_NULL_PTR(block)))
+		return;
+	kmemleak_free(block);
+
+	sp = virt_to_page(block);
+	if (PageSlab(sp)) {
+		int align = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
+		unsigned int *m = (unsigned int *)(block - align);
+		slob_free(m, *m + align);
+	} else
+		__free_pages(sp, compound_order(sp));
+}
+EXPORT_SYMBOL(kfree);
+
+/* can't use ksize for kmem_cache_alloc memory, only kmalloc */
+size_t ksize(const void *block)
+{
+	struct page *sp;
+	int align;
+	unsigned int *m;
+
+	BUG_ON(!block);
+	if (unlikely(block == ZERO_SIZE_PTR))
+		return 0;
+
+	sp = virt_to_page(block);
+	if (unlikely(!PageSlab(sp)))
+		return PAGE_SIZE << compound_order(sp);
+
+	align = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
+	m = (unsigned int *)(block - align);
+	return SLOB_UNITS(*m) * SLOB_UNIT;
+}
+EXPORT_SYMBOL(ksize);
+
+int __kmem_cache_create(struct kmem_cache *c, unsigned long flags)
+{
+	if (flags & SLAB_DESTROY_BY_RCU) {
+		/* leave room for rcu footer at the end of object */
+		c->size += sizeof(struct slob_rcu);
+	}
+	c->flags = flags;
+	return 0;
+}
+
+void *slob_alloc_node(struct kmem_cache *c, gfp_t flags, int node)
+{
+	void *b;
+
+	flags &= gfp_allowed_mask;
+
+	lockdep_trace_alloc(flags);
+
+	if (c->size < PAGE_SIZE) {
+		b = slob_alloc(c->size, flags, c->align, node);
+		trace_kmem_cache_alloc_node(_RET_IP_, b, c->object_size,
+					    SLOB_UNITS(c->size) * SLOB_UNIT,
+					    flags, node);
+	} else {
+		b = slob_new_pages(flags, get_order(c->size), node);
+		trace_kmem_cache_alloc_node(_RET_IP_, b, c->object_size,
+					    PAGE_SIZE << get_order(c->size),
+					    flags, node);
+	}
+
+	if (b && c->ctor)
+		c->ctor(b);
+
+	kmemleak_alloc_recursive(b, c->size, 1, c->flags, flags);
+	return b;
+}
+EXPORT_SYMBOL(slob_alloc_node);
+
+void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags)
+{
+	return slob_alloc_node(cachep, flags, NUMA_NO_NODE);
+}
+EXPORT_SYMBOL(kmem_cache_alloc);
+
+#ifdef CONFIG_NUMA
+void *__kmalloc_node(size_t size, gfp_t gfp, int node)
+{
+	return __do_kmalloc_node(size, gfp, node, _RET_IP_);
+}
+EXPORT_SYMBOL(__kmalloc_node);
+
+void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t gfp, int node)
+{
+	return slob_alloc_node(cachep, gfp, node);
+}
+EXPORT_SYMBOL(kmem_cache_alloc_node);
+#endif
+
+static void __kmem_cache_free(void *b, int size)
+{
+	if (size < PAGE_SIZE)
+		slob_free(b, size);
+	else
+		slob_free_pages(b, get_order(size));
+}
+
+static void kmem_rcu_free(struct rcu_head *head)
+{
+	struct slob_rcu *slob_rcu = (struct slob_rcu *)head;
+	void *b = (void *)slob_rcu - (slob_rcu->size - sizeof(struct slob_rcu));
+
+	__kmem_cache_free(b, slob_rcu->size);
+}
+
+void kmem_cache_free(struct kmem_cache *c, void *b)
+{
+	kmemleak_free_recursive(b, c->flags);
+	if (unlikely(c->flags & SLAB_DESTROY_BY_RCU)) {
+		struct slob_rcu *slob_rcu;
+		slob_rcu = b + (c->size - sizeof(struct slob_rcu));
+		slob_rcu->size = c->size;
+		call_rcu(&slob_rcu->head, kmem_rcu_free);
+	} else {
+		__kmem_cache_free(b, c->size);
+	}
+
+	trace_kmem_cache_free(_RET_IP_, b);
+}
+EXPORT_SYMBOL(kmem_cache_free);
+
+int __kmem_cache_shutdown(struct kmem_cache *c)
+{
+	/* No way to check for remaining objects */
+	return 0;
+}
+
+int __kmem_cache_shrink(struct kmem_cache *d)
+{
+	return 0;
+}
+
+struct kmem_cache kmem_cache_boot = {
+	.name = "kmem_cache",
+	.size = sizeof(struct kmem_cache),
+	.flags = SLAB_PANIC,
+	.align = ARCH_KMALLOC_MINALIGN,
+};
+
+void __init kmem_cache_init(void)
+{
+	kmem_cache = &kmem_cache_boot;
+	slab_state = UP;
+}
+
+void __init kmem_cache_init_late(void)
+{
+	slab_state = FULL;
+}

mm/sparse-vmemmap.c

@@ -0,0 +1,253 @@
+/*
+ * Virtual Memory Map support
+ *
+ * (C) 2007 sgi. Christoph Lameter.
+ *
+ * Virtual memory maps allow VM primitives pfn_to_page, page_to_pfn,
+ * virt_to_page, page_address() to be implemented as a base offset
+ * calculation without memory access.
+ *
+ * However, virtual mappings need a page table and TLBs. Many Linux
+ * architectures already map their physical space using 1-1 mappings
+ * via TLBs. For those arches the virtual memory map is essentially
+ * for free if we use the same page size as the 1-1 mappings. In that
+ * case the overhead consists of a few additional pages that are
+ * allocated to create a view of memory for vmemmap.
+ *
+ * The architecture is expected to provide a vmemmap_populate() function
+ * to instantiate the mapping.
+ */
+#include <linux/mm.h>
+#include <linux/mmzone.h>
+#include <linux/bootmem.h>
+#include <linux/highmem.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/vmalloc.h>
+#include <linux/sched.h>
+#include <asm/dma.h>
+#include <asm/pgalloc.h>
+#include <asm/pgtable.h>
+
+/*
+ * Allocate a block of memory to be used to back the virtual memory map
+ * or to back the page tables that are used to create the mapping.
+ * Uses the main allocators if they are available, else bootmem.
+ */
+
+static void * __init_refok __earlyonly_bootmem_alloc(int node,
+				unsigned long size,
+				unsigned long align,
+				unsigned long goal)
+{
+	return memblock_virt_alloc_try_nid(size, align, goal,
+					    BOOTMEM_ALLOC_ACCESSIBLE, node);
+}
+
+static void *vmemmap_buf;
+static void *vmemmap_buf_end;
+
+void * __meminit vmemmap_alloc_block(unsigned long size, int node)
+{
+	/* If the main allocator is up use that, fallback to bootmem. */
+	if (slab_is_available()) {
+		struct page *page;
+
+		if (node_state(node, N_HIGH_MEMORY))
+			page = alloc_pages_node(
+				node, GFP_KERNEL | __GFP_ZERO | __GFP_REPEAT,
+				get_order(size));
+		else
+			page = alloc_pages(
+				GFP_KERNEL | __GFP_ZERO | __GFP_REPEAT,
+				get_order(size));
+		if (page)
+			return page_address(page);
+		return NULL;
+	} else
+		return __earlyonly_bootmem_alloc(node, size, size,
+				__pa(MAX_DMA_ADDRESS));
+}
+
+/* need to make sure size is all the same during early stage */
+void * __meminit vmemmap_alloc_block_buf(unsigned long size, int node)
+{
+	void *ptr;
+
+	if (!vmemmap_buf)
+		return vmemmap_alloc_block(size, node);
+
+	/* take the from buf */
+	ptr = (void *)ALIGN((unsigned long)vmemmap_buf, size);
+	if (ptr + size > vmemmap_buf_end)
+		return vmemmap_alloc_block(size, node);
+
+	vmemmap_buf = ptr + size;
+
+	return ptr;
+}
+
+void __meminit vmemmap_verify(pte_t *pte, int node,
+				unsigned long start, unsigned long end)
+{
+	unsigned long pfn = pte_pfn(*pte);
+	int actual_node = early_pfn_to_nid(pfn);
+
+	if (node_distance(actual_node, node) > LOCAL_DISTANCE)
+		printk(KERN_WARNING "[%lx-%lx] potential offnode "
+			"page_structs\n", start, end - 1);
+}
+
+pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node)
+{
+	pte_t *pte = pte_offset_kernel(pmd, addr);
+	if (pte_none(*pte)) {
+		pte_t entry;
+		void *p = vmemmap_alloc_block_buf(PAGE_SIZE, node);
+		if (!p)
+			return NULL;
+		entry = pfn_pte(__pa(p) >> PAGE_SHIFT, PAGE_KERNEL);
+		set_pte_at(&init_mm, addr, pte, entry);
+	}
+	return pte;
+}
+
+pmd_t * __meminit vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node)
+{
+	pmd_t *pmd = pmd_offset(pud, addr);
+	if (pmd_none(*pmd)) {
+		void *p = vmemmap_alloc_block(PAGE_SIZE, node);
+		if (!p)
+			return NULL;
+		pmd_populate_kernel(&init_mm, pmd, p);
+	}
+	return pmd;
+}
+
+pud_t * __meminit vmemmap_pud_populate(pgd_t *pgd, unsigned long addr, int node)
+{
+#ifdef CONFIG_TIMA_RKP
+	int rkp_do = 0; 
+#endif 	
+	void *p = NULL ;
+	pud_t *pud = pud_offset(pgd, addr);
+	if (pud_none(*pud)) {
+#ifdef CONFIG_TIMA_RKP
+#ifdef CONFIG_KNOX_KAP
+		if (boot_mode_security)
+#endif
+			rkp_do = 1;
+		if( rkp_do ){
+			p =  rkp_ro_alloc();
+			if (!p)
+				p = vmemmap_alloc_block(PAGE_SIZE, node);
+		}else{
+			p = vmemmap_alloc_block(PAGE_SIZE, node);
+		}
+#else /* !CONFIG_TIMA_RKP */
+		p = vmemmap_alloc_block(PAGE_SIZE, node);
+#endif
+		if (!p)
+			return NULL;
+		pud_populate(&init_mm, pud, p);
+	}
+	return pud;
+}
+
+pgd_t * __meminit vmemmap_pgd_populate(unsigned long addr, int node)
+{
+	pgd_t *pgd = pgd_offset_k(addr);
+	if (pgd_none(*pgd)) {
+		void *p = vmemmap_alloc_block(PAGE_SIZE, node);
+		if (!p)
+			return NULL;
+		pgd_populate(&init_mm, pgd, p);
+	}
+	return pgd;
+}
+
+int __meminit vmemmap_populate_basepages(unsigned long start,
+					 unsigned long end, int node)
+{
+	unsigned long addr = start;
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+
+	for (; addr < end; addr += PAGE_SIZE) {
+		pgd = vmemmap_pgd_populate(addr, node);
+		if (!pgd)
+			return -ENOMEM;
+		pud = vmemmap_pud_populate(pgd, addr, node);
+		if (!pud)
+			return -ENOMEM;
+		pmd = vmemmap_pmd_populate(pud, addr, node);
+		if (!pmd)
+			return -ENOMEM;
+		pte = vmemmap_pte_populate(pmd, addr, node);
+		if (!pte)
+			return -ENOMEM;
+		vmemmap_verify(pte, node, addr, addr + PAGE_SIZE);
+	}
+
+	return 0;
+}
+
+struct page * __meminit sparse_mem_map_populate(unsigned long pnum, int nid)
+{
+	unsigned long start;
+	unsigned long end;
+	struct page *map;
+
+	map = pfn_to_page(pnum * PAGES_PER_SECTION);
+	start = (unsigned long)map;
+	end = (unsigned long)(map + PAGES_PER_SECTION);
+
+	if (vmemmap_populate(start, end, nid))
+		return NULL;
+
+	return map;
+}
+
+void __init sparse_mem_maps_populate_node(struct page **map_map,
+					  unsigned long pnum_begin,
+					  unsigned long pnum_end,
+					  unsigned long map_count, int nodeid)
+{
+	unsigned long pnum;
+	unsigned long size = sizeof(struct page) * PAGES_PER_SECTION;
+	void *vmemmap_buf_start;
+
+	size = ALIGN(size, PMD_SIZE);
+	vmemmap_buf_start = __earlyonly_bootmem_alloc(nodeid, size * map_count,
+			 PMD_SIZE, __pa(MAX_DMA_ADDRESS));
+
+	if (vmemmap_buf_start) {
+		vmemmap_buf = vmemmap_buf_start;
+		vmemmap_buf_end = vmemmap_buf_start + size * map_count;
+	}
+
+	for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
+		struct mem_section *ms;
+
+		if (!present_section_nr(pnum))
+			continue;
+
+		map_map[pnum] = sparse_mem_map_populate(pnum, nodeid);
+		if (map_map[pnum])
+			continue;
+		ms = __nr_to_section(pnum);
+		printk(KERN_ERR "%s: sparsemem memory map backing failed "
+			"some memory will not be available.\n", __func__);
+		ms->section_mem_map = 0;
+	}
+
+	if (vmemmap_buf_start) {
+		/* need to free left buf */
+		memblock_free_early(__pa(vmemmap_buf),
+				    vmemmap_buf_end - vmemmap_buf);
+		vmemmap_buf = NULL;
+		vmemmap_buf_end = NULL;
+	}
+}

mm/sparse.c

@@ -0,0 +1,811 @@
+/*
+ * sparse memory mappings.
+ */
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/mmzone.h>
+#include <linux/bootmem.h>
+#include <linux/compiler.h>
+#include <linux/highmem.h>
+#include <linux/export.h>
+#include <linux/spinlock.h>
+#include <linux/vmalloc.h>
+
+#include "internal.h"
+#include <asm/dma.h>
+#include <asm/pgalloc.h>
+#include <asm/pgtable.h>
+
+/*
+ * Permanent SPARSEMEM data:
+ *
+ * 1) mem_section	- memory sections, mem_map's for valid memory
+ */
+#ifdef CONFIG_SPARSEMEM_EXTREME
+struct mem_section *mem_section[NR_SECTION_ROOTS]
+	____cacheline_internodealigned_in_smp;
+#else
+struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT]
+	____cacheline_internodealigned_in_smp;
+#endif
+EXPORT_SYMBOL(mem_section);
+
+#ifdef NODE_NOT_IN_PAGE_FLAGS
+/*
+ * If we did not store the node number in the page then we have to
+ * do a lookup in the section_to_node_table in order to find which
+ * node the page belongs to.
+ */
+#if MAX_NUMNODES <= 256
+static u8 section_to_node_table[NR_MEM_SECTIONS] __cacheline_aligned;
+#else
+static u16 section_to_node_table[NR_MEM_SECTIONS] __cacheline_aligned;
+#endif
+
+int page_to_nid(const struct page *page)
+{
+	return section_to_node_table[page_to_section(page)];
+}
+EXPORT_SYMBOL(page_to_nid);
+
+static void set_section_nid(unsigned long section_nr, int nid)
+{
+	section_to_node_table[section_nr] = nid;
+}
+#else /* !NODE_NOT_IN_PAGE_FLAGS */
+static inline void set_section_nid(unsigned long section_nr, int nid)
+{
+}
+#endif
+
+#ifdef CONFIG_SPARSEMEM_EXTREME
+static struct mem_section noinline __init_refok *sparse_index_alloc(int nid)
+{
+	struct mem_section *section = NULL;
+	unsigned long array_size = SECTIONS_PER_ROOT *
+				   sizeof(struct mem_section);
+
+	if (slab_is_available()) {
+		if (node_state(nid, N_HIGH_MEMORY))
+			section = kzalloc_node(array_size, GFP_KERNEL, nid);
+		else
+			section = kzalloc(array_size, GFP_KERNEL);
+	} else {
+		section = memblock_virt_alloc_node(array_size, nid);
+	}
+
+	return section;
+}
+
+static int __meminit sparse_index_init(unsigned long section_nr, int nid)
+{
+	unsigned long root = SECTION_NR_TO_ROOT(section_nr);
+	struct mem_section *section;
+
+	if (mem_section[root])
+		return -EEXIST;
+
+	section = sparse_index_alloc(nid);
+	if (!section)
+		return -ENOMEM;
+
+	mem_section[root] = section;
+
+	return 0;
+}
+#else /* !SPARSEMEM_EXTREME */
+static inline int sparse_index_init(unsigned long section_nr, int nid)
+{
+	return 0;
+}
+#endif
+
+/*
+ * Although written for the SPARSEMEM_EXTREME case, this happens
+ * to also work for the flat array case because
+ * NR_SECTION_ROOTS==NR_MEM_SECTIONS.
+ */
+int __section_nr(struct mem_section* ms)
+{
+	unsigned long root_nr;
+	struct mem_section* root;
+
+	for (root_nr = 0; root_nr < NR_SECTION_ROOTS; root_nr++) {
+		root = __nr_to_section(root_nr * SECTIONS_PER_ROOT);
+		if (!root)
+			continue;
+
+		if ((ms >= root) && (ms < (root + SECTIONS_PER_ROOT)))
+		     break;
+	}
+
+	VM_BUG_ON(root_nr == NR_SECTION_ROOTS);
+
+	return (root_nr * SECTIONS_PER_ROOT) + (ms - root);
+}
+
+/*
+ * During early boot, before section_mem_map is used for an actual
+ * mem_map, we use section_mem_map to store the section's NUMA
+ * node.  This keeps us from having to use another data structure.  The
+ * node information is cleared just before we store the real mem_map.
+ */
+static inline unsigned long sparse_encode_early_nid(int nid)
+{
+	return (nid << SECTION_NID_SHIFT);
+}
+
+static inline int sparse_early_nid(struct mem_section *section)
+{
+	return (section->section_mem_map >> SECTION_NID_SHIFT);
+}
+
+/* Validate the physical addressing limitations of the model */
+void __meminit mminit_validate_memmodel_limits(unsigned long *start_pfn,
+						unsigned long *end_pfn)
+{
+	unsigned long max_sparsemem_pfn = 1UL << (MAX_PHYSMEM_BITS-PAGE_SHIFT);
+
+	/*
+	 * Sanity checks - do not allow an architecture to pass
+	 * in larger pfns than the maximum scope of sparsemem:
+	 */
+	if (*start_pfn > max_sparsemem_pfn) {
+		mminit_dprintk(MMINIT_WARNING, "pfnvalidation",
+			"Start of range %lu -> %lu exceeds SPARSEMEM max %lu\n",
+			*start_pfn, *end_pfn, max_sparsemem_pfn);
+		WARN_ON_ONCE(1);
+		*start_pfn = max_sparsemem_pfn;
+		*end_pfn = max_sparsemem_pfn;
+	} else if (*end_pfn > max_sparsemem_pfn) {
+		mminit_dprintk(MMINIT_WARNING, "pfnvalidation",
+			"End of range %lu -> %lu exceeds SPARSEMEM max %lu\n",
+			*start_pfn, *end_pfn, max_sparsemem_pfn);
+		WARN_ON_ONCE(1);
+		*end_pfn = max_sparsemem_pfn;
+	}
+}
+
+/* Record a memory area against a node. */
+void __init memory_present(int nid, unsigned long start, unsigned long end)
+{
+	unsigned long pfn;
+
+	start &= PAGE_SECTION_MASK;
+	mminit_validate_memmodel_limits(&start, &end);
+	for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) {
+		unsigned long section = pfn_to_section_nr(pfn);
+		struct mem_section *ms;
+
+		sparse_index_init(section, nid);
+		set_section_nid(section, nid);
+
+		ms = __nr_to_section(section);
+		if (!ms->section_mem_map)
+			ms->section_mem_map = sparse_encode_early_nid(nid) |
+							SECTION_MARKED_PRESENT;
+	}
+}
+
+/*
+ * Only used by the i386 NUMA architecures, but relatively
+ * generic code.
+ */
+unsigned long __init node_memmap_size_bytes(int nid, unsigned long start_pfn,
+						     unsigned long end_pfn)
+{
+	unsigned long pfn;
+	unsigned long nr_pages = 0;
+
+	mminit_validate_memmodel_limits(&start_pfn, &end_pfn);
+	for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
+		if (nid != early_pfn_to_nid(pfn))
+			continue;
+
+		if (pfn_present(pfn))
+			nr_pages += PAGES_PER_SECTION;
+	}
+
+	return nr_pages * sizeof(struct page);
+}
+
+/*
+ * Subtle, we encode the real pfn into the mem_map such that
+ * the identity pfn - section_mem_map will return the actual
+ * physical page frame number.
+ */
+static unsigned long sparse_encode_mem_map(struct page *mem_map, unsigned long pnum)
+{
+	return (unsigned long)(mem_map - (section_nr_to_pfn(pnum)));
+}
+
+/*
+ * Decode mem_map from the coded memmap
+ */
+struct page *sparse_decode_mem_map(unsigned long coded_mem_map, unsigned long pnum)
+{
+	/* mask off the extra low bits of information */
+	coded_mem_map &= SECTION_MAP_MASK;
+	return ((struct page *)coded_mem_map) + section_nr_to_pfn(pnum);
+}
+
+static int __meminit sparse_init_one_section(struct mem_section *ms,
+		unsigned long pnum, struct page *mem_map,
+		unsigned long *pageblock_bitmap)
+{
+	if (!present_section(ms))
+		return -EINVAL;
+
+	ms->section_mem_map &= ~SECTION_MAP_MASK;
+	ms->section_mem_map |= sparse_encode_mem_map(mem_map, pnum) |
+							SECTION_HAS_MEM_MAP;
+ 	ms->pageblock_flags = pageblock_bitmap;
+
+	return 1;
+}
+
+unsigned long usemap_size(void)
+{
+	unsigned long size_bytes;
+	size_bytes = roundup(SECTION_BLOCKFLAGS_BITS, 8) / 8;
+	size_bytes = roundup(size_bytes, sizeof(unsigned long));
+	return size_bytes;
+}
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+static unsigned long *__kmalloc_section_usemap(void)
+{
+	return kmalloc(usemap_size(), GFP_KERNEL);
+}
+#endif /* CONFIG_MEMORY_HOTPLUG */
+
+#ifdef CONFIG_MEMORY_HOTREMOVE
+static unsigned long * __init
+sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat,
+					 unsigned long size)
+{
+	unsigned long goal, limit;
+	unsigned long *p;
+	int nid;
+	/*
+	 * A page may contain usemaps for other sections preventing the
+	 * page being freed and making a section unremovable while
+	 * other sections referencing the usemap remain active. Similarly,
+	 * a pgdat can prevent a section being removed. If section A
+	 * contains a pgdat and section B contains the usemap, both
+	 * sections become inter-dependent. This allocates usemaps
+	 * from the same section as the pgdat where possible to avoid
+	 * this problem.
+	 */
+	goal = __pa(pgdat) & (PAGE_SECTION_MASK << PAGE_SHIFT);
+	limit = goal + (1UL << PA_SECTION_SHIFT);
+	nid = early_pfn_to_nid(goal >> PAGE_SHIFT);
+again:
+	p = memblock_virt_alloc_try_nid_nopanic(size,
+						SMP_CACHE_BYTES, goal, limit,
+						nid);
+	if (!p && limit) {
+		limit = 0;
+		goto again;
+	}
+	return p;
+}
+
+static void __init check_usemap_section_nr(int nid, unsigned long *usemap)
+{
+	unsigned long usemap_snr, pgdat_snr;
+	static unsigned long old_usemap_snr = NR_MEM_SECTIONS;
+	static unsigned long old_pgdat_snr = NR_MEM_SECTIONS;
+	struct pglist_data *pgdat = NODE_DATA(nid);
+	int usemap_nid;
+
+	usemap_snr = pfn_to_section_nr(__pa(usemap) >> PAGE_SHIFT);
+	pgdat_snr = pfn_to_section_nr(__pa(pgdat) >> PAGE_SHIFT);
+	if (usemap_snr == pgdat_snr)
+		return;
+
+	if (old_usemap_snr == usemap_snr && old_pgdat_snr == pgdat_snr)
+		/* skip redundant message */
+		return;
+
+	old_usemap_snr = usemap_snr;
+	old_pgdat_snr = pgdat_snr;
+
+	usemap_nid = sparse_early_nid(__nr_to_section(usemap_snr));
+	if (usemap_nid != nid) {
+		printk(KERN_INFO
+		       "node %d must be removed before remove section %ld\n",
+		       nid, usemap_snr);
+		return;
+	}
+	/*
+	 * There is a circular dependency.
+	 * Some platforms allow un-removable section because they will just
+	 * gather other removable sections for dynamic partitioning.
+	 * Just notify un-removable section's number here.
+	 */
+	printk(KERN_INFO "Section %ld and %ld (node %d)", usemap_snr,
+	       pgdat_snr, nid);
+	printk(KERN_CONT
+	       " have a circular dependency on usemap and pgdat allocations\n");
+}
+#else
+static unsigned long * __init
+sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat,
+					 unsigned long size)
+{
+	return memblock_virt_alloc_node_nopanic(size, pgdat->node_id);
+}
+
+static void __init check_usemap_section_nr(int nid, unsigned long *usemap)
+{
+}
+#endif /* CONFIG_MEMORY_HOTREMOVE */
+
+static void __init sparse_early_usemaps_alloc_node(void *data,
+				 unsigned long pnum_begin,
+				 unsigned long pnum_end,
+				 unsigned long usemap_count, int nodeid)
+{
+	void *usemap;
+	unsigned long pnum;
+	unsigned long **usemap_map = (unsigned long **)data;
+	int size = usemap_size();
+
+	usemap = sparse_early_usemaps_alloc_pgdat_section(NODE_DATA(nodeid),
+							  size * usemap_count);
+	if (!usemap) {
+		printk(KERN_WARNING "%s: allocation failed\n", __func__);
+		return;
+	}
+
+	for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
+		if (!present_section_nr(pnum))
+			continue;
+		usemap_map[pnum] = usemap;
+		usemap += size;
+		check_usemap_section_nr(nodeid, usemap_map[pnum]);
+	}
+}
+
+#ifndef CONFIG_SPARSEMEM_VMEMMAP
+struct page __init *sparse_mem_map_populate(unsigned long pnum, int nid)
+{
+	struct page *map;
+	unsigned long size;
+
+	map = alloc_remap(nid, sizeof(struct page) * PAGES_PER_SECTION);
+	if (map)
+		return map;
+
+	size = PAGE_ALIGN(sizeof(struct page) * PAGES_PER_SECTION);
+	map = memblock_virt_alloc_try_nid(size,
+					  PAGE_SIZE, __pa(MAX_DMA_ADDRESS),
+					  BOOTMEM_ALLOC_ACCESSIBLE, nid);
+	return map;
+}
+void __init sparse_mem_maps_populate_node(struct page **map_map,
+					  unsigned long pnum_begin,
+					  unsigned long pnum_end,
+					  unsigned long map_count, int nodeid)
+{
+	void *map;
+	unsigned long pnum;
+	unsigned long size = sizeof(struct page) * PAGES_PER_SECTION;
+
+	map = alloc_remap(nodeid, size * map_count);
+	if (map) {
+		for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
+			if (!present_section_nr(pnum))
+				continue;
+			map_map[pnum] = map;
+			map += size;
+		}
+		return;
+	}
+
+	size = PAGE_ALIGN(size);
+	map = memblock_virt_alloc_try_nid(size * map_count,
+					  PAGE_SIZE, __pa(MAX_DMA_ADDRESS),
+					  BOOTMEM_ALLOC_ACCESSIBLE, nodeid);
+	if (map) {
+		for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
+			if (!present_section_nr(pnum))
+				continue;
+			map_map[pnum] = map;
+			map += size;
+		}
+		return;
+	}
+
+	/* fallback */
+	for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
+		struct mem_section *ms;
+
+		if (!present_section_nr(pnum))
+			continue;
+		map_map[pnum] = sparse_mem_map_populate(pnum, nodeid);
+		if (map_map[pnum])
+			continue;
+		ms = __nr_to_section(pnum);
+		printk(KERN_ERR "%s: sparsemem memory map backing failed "
+			"some memory will not be available.\n", __func__);
+		ms->section_mem_map = 0;
+	}
+}
+#endif /* !CONFIG_SPARSEMEM_VMEMMAP */
+
+#ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
+static void __init sparse_early_mem_maps_alloc_node(void *data,
+				 unsigned long pnum_begin,
+				 unsigned long pnum_end,
+				 unsigned long map_count, int nodeid)
+{
+	struct page **map_map = (struct page **)data;
+	sparse_mem_maps_populate_node(map_map, pnum_begin, pnum_end,
+					 map_count, nodeid);
+}
+#else
+static struct page __init *sparse_early_mem_map_alloc(unsigned long pnum)
+{
+	struct page *map;
+	struct mem_section *ms = __nr_to_section(pnum);
+	int nid = sparse_early_nid(ms);
+
+	map = sparse_mem_map_populate(pnum, nid);
+	if (map)
+		return map;
+
+	printk(KERN_ERR "%s: sparsemem memory map backing failed "
+			"some memory will not be available.\n", __func__);
+	ms->section_mem_map = 0;
+	return NULL;
+}
+#endif
+
+void __weak __meminit vmemmap_populate_print_last(void)
+{
+}
+
+/**
+ *  alloc_usemap_and_memmap - memory alloction for pageblock flags and vmemmap
+ *  @map: usemap_map for pageblock flags or mmap_map for vmemmap
+ */
+static void __init alloc_usemap_and_memmap(void (*alloc_func)
+					(void *, unsigned long, unsigned long,
+					unsigned long, int), void *data)
+{
+	unsigned long pnum;
+	unsigned long map_count;
+	int nodeid_begin = 0;
+	unsigned long pnum_begin = 0;
+
+	for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) {
+		struct mem_section *ms;
+
+		if (!present_section_nr(pnum))
+			continue;
+		ms = __nr_to_section(pnum);
+		nodeid_begin = sparse_early_nid(ms);
+		pnum_begin = pnum;
+		break;
+	}
+	map_count = 1;
+	for (pnum = pnum_begin + 1; pnum < NR_MEM_SECTIONS; pnum++) {
+		struct mem_section *ms;
+		int nodeid;
+
+		if (!present_section_nr(pnum))
+			continue;
+		ms = __nr_to_section(pnum);
+		nodeid = sparse_early_nid(ms);
+		if (nodeid == nodeid_begin) {
+			map_count++;
+			continue;
+		}
+		/* ok, we need to take cake of from pnum_begin to pnum - 1*/
+		alloc_func(data, pnum_begin, pnum,
+						map_count, nodeid_begin);
+		/* new start, update count etc*/
+		nodeid_begin = nodeid;
+		pnum_begin = pnum;
+		map_count = 1;
+	}
+	/* ok, last chunk */
+	alloc_func(data, pnum_begin, NR_MEM_SECTIONS,
+						map_count, nodeid_begin);
+}
+
+/*
+ * Allocate the accumulated non-linear sections, allocate a mem_map
+ * for each and record the physical to section mapping.
+ */
+void __init sparse_init(void)
+{
+	unsigned long pnum;
+	struct page *map;
+	unsigned long *usemap;
+	unsigned long **usemap_map;
+	int size;
+#ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
+	int size2;
+	struct page **map_map;
+#endif
+
+	/* see include/linux/mmzone.h 'struct mem_section' definition */
+	BUILD_BUG_ON(!is_power_of_2(sizeof(struct mem_section)));
+
+	/* Setup pageblock_order for HUGETLB_PAGE_SIZE_VARIABLE */
+	set_pageblock_order();
+
+	/*
+	 * map is using big page (aka 2M in x86 64 bit)
+	 * usemap is less one page (aka 24 bytes)
+	 * so alloc 2M (with 2M align) and 24 bytes in turn will
+	 * make next 2M slip to one more 2M later.
+	 * then in big system, the memory will have a lot of holes...
+	 * here try to allocate 2M pages continuously.
+	 *
+	 * powerpc need to call sparse_init_one_section right after each
+	 * sparse_early_mem_map_alloc, so allocate usemap_map at first.
+	 */
+	size = sizeof(unsigned long *) * NR_MEM_SECTIONS;
+	usemap_map = memblock_virt_alloc(size, 0);
+	if (!usemap_map)
+		panic("can not allocate usemap_map\n");
+	alloc_usemap_and_memmap(sparse_early_usemaps_alloc_node,
+							(void *)usemap_map);
+
+#ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
+	size2 = sizeof(struct page *) * NR_MEM_SECTIONS;
+	map_map = memblock_virt_alloc(size2, 0);
+	if (!map_map)
+		panic("can not allocate map_map\n");
+	alloc_usemap_and_memmap(sparse_early_mem_maps_alloc_node,
+							(void *)map_map);
+#endif
+
+	for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) {
+		if (!present_section_nr(pnum))
+			continue;
+
+		usemap = usemap_map[pnum];
+		if (!usemap)
+			continue;
+
+#ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
+		map = map_map[pnum];
+#else
+		map = sparse_early_mem_map_alloc(pnum);
+#endif
+		if (!map)
+			continue;
+
+		sparse_init_one_section(__nr_to_section(pnum), pnum, map,
+								usemap);
+	}
+
+	vmemmap_populate_print_last();
+
+#ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
+	memblock_free_early(__pa(map_map), size2);
+#endif
+	memblock_free_early(__pa(usemap_map), size);
+}
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid)
+{
+	/* This will make the necessary allocations eventually. */
+	return sparse_mem_map_populate(pnum, nid);
+}
+static void __kfree_section_memmap(struct page *memmap)
+{
+	unsigned long start = (unsigned long)memmap;
+	unsigned long end = (unsigned long)(memmap + PAGES_PER_SECTION);
+
+	vmemmap_free(start, end);
+}
+#ifdef CONFIG_MEMORY_HOTREMOVE
+static void free_map_bootmem(struct page *memmap)
+{
+	unsigned long start = (unsigned long)memmap;
+	unsigned long end = (unsigned long)(memmap + PAGES_PER_SECTION);
+
+	vmemmap_free(start, end);
+}
+#endif /* CONFIG_MEMORY_HOTREMOVE */
+#else
+static struct page *__kmalloc_section_memmap(void)
+{
+	struct page *page, *ret;
+	unsigned long memmap_size = sizeof(struct page) * PAGES_PER_SECTION;
+
+	page = alloc_pages(GFP_KERNEL|__GFP_NOWARN, get_order(memmap_size));
+	if (page)
+		goto got_map_page;
+
+	ret = vmalloc(memmap_size);
+	if (ret)
+		goto got_map_ptr;
+
+	return NULL;
+got_map_page:
+	ret = (struct page *)pfn_to_kaddr(page_to_pfn(page));
+got_map_ptr:
+
+	return ret;
+}
+
+static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid)
+{
+	return __kmalloc_section_memmap();
+}
+
+static void __kfree_section_memmap(struct page *memmap)
+{
+	if (is_vmalloc_addr(memmap))
+		vfree(memmap);
+	else
+		free_pages((unsigned long)memmap,
+			   get_order(sizeof(struct page) * PAGES_PER_SECTION));
+}
+
+#ifdef CONFIG_MEMORY_HOTREMOVE
+static void free_map_bootmem(struct page *memmap)
+{
+	unsigned long maps_section_nr, removing_section_nr, i;
+	unsigned long magic, nr_pages;
+	struct page *page = virt_to_page(memmap);
+
+	nr_pages = PAGE_ALIGN(PAGES_PER_SECTION * sizeof(struct page))
+		>> PAGE_SHIFT;
+
+	for (i = 0; i < nr_pages; i++, page++) {
+		magic = (unsigned long) page->lru.next;
+
+		BUG_ON(magic == NODE_INFO);
+
+		maps_section_nr = pfn_to_section_nr(page_to_pfn(page));
+		removing_section_nr = page->private;
+
+		/*
+		 * When this function is called, the removing section is
+		 * logical offlined state. This means all pages are isolated
+		 * from page allocator. If removing section's memmap is placed
+		 * on the same section, it must not be freed.
+		 * If it is freed, page allocator may allocate it which will
+		 * be removed physically soon.
+		 */
+		if (maps_section_nr != removing_section_nr)
+			put_page_bootmem(page);
+	}
+}
+#endif /* CONFIG_MEMORY_HOTREMOVE */
+#endif /* CONFIG_SPARSEMEM_VMEMMAP */
+
+/*
+ * returns the number of sections whose mem_maps were properly
+ * set.  If this is <=0, then that means that the passed-in
+ * map was not consumed and must be freed.
+ */
+int __meminit sparse_add_one_section(struct zone *zone, unsigned long start_pfn)
+{
+	unsigned long section_nr = pfn_to_section_nr(start_pfn);
+	struct pglist_data *pgdat = zone->zone_pgdat;
+	struct mem_section *ms;
+	struct page *memmap;
+	unsigned long *usemap;
+	unsigned long flags;
+	int ret;
+
+	/*
+	 * no locking for this, because it does its own
+	 * plus, it does a kmalloc
+	 */
+	ret = sparse_index_init(section_nr, pgdat->node_id);
+	if (ret < 0 && ret != -EEXIST)
+		return ret;
+	memmap = kmalloc_section_memmap(section_nr, pgdat->node_id);
+	if (!memmap)
+		return -ENOMEM;
+	usemap = __kmalloc_section_usemap();
+	if (!usemap) {
+		__kfree_section_memmap(memmap);
+		return -ENOMEM;
+	}
+
+	pgdat_resize_lock(pgdat, &flags);
+
+	ms = __pfn_to_section(start_pfn);
+	if (ms->section_mem_map & SECTION_MARKED_PRESENT) {
+		ret = -EEXIST;
+		goto out;
+	}
+
+	memset(memmap, 0, sizeof(struct page) * PAGES_PER_SECTION);
+
+	ms->section_mem_map |= SECTION_MARKED_PRESENT;
+
+	ret = sparse_init_one_section(ms, section_nr, memmap, usemap);
+
+out:
+	pgdat_resize_unlock(pgdat, &flags);
+	if (ret <= 0) {
+		kfree(usemap);
+		__kfree_section_memmap(memmap);
+	}
+	return ret;
+}
+
+#ifdef CONFIG_MEMORY_HOTREMOVE
+#ifdef CONFIG_MEMORY_FAILURE
+static void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
+{
+	int i;
+
+	if (!memmap)
+		return;
+
+	for (i = 0; i < PAGES_PER_SECTION; i++) {
+		if (PageHWPoison(&memmap[i])) {
+			atomic_long_sub(1, &num_poisoned_pages);
+			ClearPageHWPoison(&memmap[i]);
+		}
+	}
+}
+#else
+static inline void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
+{
+}
+#endif
+
+static void free_section_usemap(struct page *memmap, unsigned long *usemap)
+{
+	struct page *usemap_page;
+
+	if (!usemap)
+		return;
+
+	usemap_page = virt_to_page(usemap);
+	/*
+	 * Check to see if allocation came from hot-plug-add
+	 */
+	if (PageSlab(usemap_page) || PageCompound(usemap_page)) {
+		kfree(usemap);
+		if (memmap)
+			__kfree_section_memmap(memmap);
+		return;
+	}
+
+	/*
+	 * The usemap came from bootmem. This is packed with other usemaps
+	 * on the section which has pgdat at boot time. Just keep it as is now.
+	 */
+
+	if (memmap)
+		free_map_bootmem(memmap);
+}
+
+void sparse_remove_one_section(struct zone *zone, struct mem_section *ms)
+{
+	struct page *memmap = NULL;
+	unsigned long *usemap = NULL, flags;
+	struct pglist_data *pgdat = zone->zone_pgdat;
+
+	pgdat_resize_lock(pgdat, &flags);
+	if (ms->section_mem_map) {
+		usemap = ms->pageblock_flags;
+		memmap = sparse_decode_mem_map(ms->section_mem_map,
+						__section_nr(ms));
+		ms->section_mem_map = 0;
+		ms->pageblock_flags = NULL;
+	}
+	pgdat_resize_unlock(pgdat, &flags);
+
+	clear_hwpoisoned_pages(memmap, PAGES_PER_SECTION);
+	free_section_usemap(memmap, usemap);
+}
+#endif /* CONFIG_MEMORY_HOTREMOVE */
+#endif /* CONFIG_MEMORY_HOTPLUG */

mm/swap_state.c

@@ -0,0 +1,497 @@
+/*
+ *  linux/mm/swap_state.c
+ *
+ *  Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
+ *  Swap reorganised 29.12.95, Stephen Tweedie
+ *
+ *  Rewritten to use page cache, (C) 1998 Stephen Tweedie
+ */
+#include <linux/mm.h>
+#include <linux/gfp.h>
+#include <linux/kernel_stat.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
+#include <linux/init.h>
+#include <linux/pagemap.h>
+#include <linux/backing-dev.h>
+#include <linux/blkdev.h>
+#include <linux/pagevec.h>
+#include <linux/migrate.h>
+#include <linux/page_cgroup.h>
+
+#include <asm/pgtable.h>
+
+/*
+ * swapper_space is a fiction, retained to simplify the path through
+ * vmscan's shrink_page_list.
+ */
+static const struct address_space_operations swap_aops = {
+	.writepage	= swap_writepage,
+	.set_page_dirty	= swap_set_page_dirty,
+#ifdef CONFIG_MIGRATION
+	.migratepage	= migrate_page,
+#endif
+};
+
+static struct backing_dev_info swap_backing_dev_info = {
+	.name		= "swap",
+	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED,
+};
+
+struct address_space swapper_spaces[MAX_SWAPFILES] = {
+	[0 ... MAX_SWAPFILES - 1] = {
+		.page_tree	= RADIX_TREE_INIT(GFP_ATOMIC|__GFP_NOWARN),
+		.i_mmap_writable = ATOMIC_INIT(0),
+		.a_ops		= &swap_aops,
+		.backing_dev_info = &swap_backing_dev_info,
+	}
+};
+
+#define INC_CACHE_INFO(x)	do { swap_cache_info.x++; } while (0)
+
+static struct {
+	unsigned long add_total;
+	unsigned long del_total;
+	unsigned long find_success;
+	unsigned long find_total;
+} swap_cache_info;
+
+unsigned long total_swapcache_pages(void)
+{
+	int i;
+	unsigned long ret = 0;
+
+	for (i = 0; i < MAX_SWAPFILES; i++)
+		ret += swapper_spaces[i].nrpages;
+	return ret;
+}
+
+static atomic_t swapin_readahead_hits = ATOMIC_INIT(4);
+
+void show_swap_cache_info(void)
+{
+	printk("%lu pages in swap cache\n", total_swapcache_pages());
+	printk("Swap cache stats: add %lu, delete %lu, find %lu/%lu\n",
+		swap_cache_info.add_total, swap_cache_info.del_total,
+		swap_cache_info.find_success, swap_cache_info.find_total);
+	printk("Free swap  = %ldkB\n",
+		get_nr_swap_pages() << (PAGE_SHIFT - 10));
+	printk("Total swap = %lukB\n", total_swap_pages << (PAGE_SHIFT - 10));
+}
+
+/*
+ * __add_to_swap_cache resembles add_to_page_cache_locked on swapper_space,
+ * but sets SwapCache flag and private instead of mapping and index.
+ */
+int __add_to_swap_cache(struct page *page, swp_entry_t entry)
+{
+	int error;
+	struct address_space *address_space;
+
+	VM_BUG_ON_PAGE(!PageLocked(page), page);
+	VM_BUG_ON_PAGE(PageSwapCache(page), page);
+	VM_BUG_ON_PAGE(!PageSwapBacked(page), page);
+
+	page_cache_get(page);
+	SetPageSwapCache(page);
+	set_page_private(page, entry.val);
+
+	address_space = swap_address_space(entry);
+	spin_lock_irq(&address_space->tree_lock);
+	error = radix_tree_insert(&address_space->page_tree,
+					entry.val, page);
+	if (likely(!error)) {
+		address_space->nrpages++;
+		__inc_zone_page_state(page, NR_FILE_PAGES);
+		INC_CACHE_INFO(add_total);
+	}
+	spin_unlock_irq(&address_space->tree_lock);
+
+	if (unlikely(error)) {
+		/*
+		 * Only the context which have set SWAP_HAS_CACHE flag
+		 * would call add_to_swap_cache().
+		 * So add_to_swap_cache() doesn't returns -EEXIST.
+		 */
+		VM_BUG_ON(error == -EEXIST);
+		set_page_private(page, 0UL);
+		ClearPageSwapCache(page);
+		page_cache_release(page);
+	}
+
+	return error;
+}
+
+
+int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp_mask)
+{
+	int error;
+
+	error = radix_tree_maybe_preload(gfp_mask);
+	if (!error) {
+		error = __add_to_swap_cache(page, entry);
+		radix_tree_preload_end();
+	}
+	return error;
+}
+
+/*
+ * This must be called only on pages that have
+ * been verified to be in the swap cache.
+ */
+void __delete_from_swap_cache(struct page *page)
+{
+	swp_entry_t entry;
+	struct address_space *address_space;
+
+	VM_BUG_ON_PAGE(!PageLocked(page), page);
+	VM_BUG_ON_PAGE(!PageSwapCache(page), page);
+	VM_BUG_ON_PAGE(PageWriteback(page), page);
+
+	entry.val = page_private(page);
+	address_space = swap_address_space(entry);
+	radix_tree_delete(&address_space->page_tree, page_private(page));
+	set_page_private(page, 0);
+	ClearPageSwapCache(page);
+	address_space->nrpages--;
+	__dec_zone_page_state(page, NR_FILE_PAGES);
+	INC_CACHE_INFO(del_total);
+}
+
+/**
+ * add_to_swap - allocate swap space for a page
+ * @page: page we want to move to swap
+ *
+ * Allocate swap space for the page and add the page to the
+ * swap cache.  Caller needs to hold the page lock. 
+ */
+int add_to_swap(struct page *page, struct list_head *list)
+{
+	swp_entry_t entry;
+	int err;
+
+	VM_BUG_ON_PAGE(!PageLocked(page), page);
+	VM_BUG_ON_PAGE(!PageUptodate(page), page);
+
+	entry = get_swap_page();
+	if (!entry.val)
+		return 0;
+
+	if (unlikely(PageTransHuge(page)))
+		if (unlikely(split_huge_page_to_list(page, list))) {
+			swapcache_free(entry);
+			return 0;
+		}
+
+	/*
+	 * Radix-tree node allocations from PF_MEMALLOC contexts could
+	 * completely exhaust the page allocator. __GFP_NOMEMALLOC
+	 * stops emergency reserves from being allocated.
+	 *
+	 * TODO: this could cause a theoretical memory reclaim
+	 * deadlock in the swap out path.
+	 */
+	/*
+	 * Add it to the swap cache and mark it dirty
+	 */
+	err = add_to_swap_cache(page, entry,
+			__GFP_HIGH|__GFP_NOMEMALLOC|__GFP_NOWARN);
+
+	if (!err) {	/* Success */
+		SetPageDirty(page);
+		return 1;
+	} else {	/* -ENOMEM radix-tree allocation failure */
+		/*
+		 * add_to_swap_cache() doesn't return -EEXIST, so we can safely
+		 * clear SWAP_HAS_CACHE flag.
+		 */
+		swapcache_free(entry);
+		return 0;
+	}
+}
+
+/*
+ * This must be called only on pages that have
+ * been verified to be in the swap cache and locked.
+ * It will never put the page into the free list,
+ * the caller has a reference on the page.
+ */
+void delete_from_swap_cache(struct page *page)
+{
+	swp_entry_t entry;
+	struct address_space *address_space;
+
+	entry.val = page_private(page);
+
+	address_space = swap_address_space(entry);
+	spin_lock_irq(&address_space->tree_lock);
+	__delete_from_swap_cache(page);
+	spin_unlock_irq(&address_space->tree_lock);
+
+	swapcache_free(entry);
+	page_cache_release(page);
+}
+
+/* 
+ * If we are the only user, then try to free up the swap cache. 
+ * 
+ * Its ok to check for PageSwapCache without the page lock
+ * here because we are going to recheck again inside
+ * try_to_free_swap() _with_ the lock.
+ * 					- Marcelo
+ */
+static inline void free_swap_cache(struct page *page)
+{
+	if (PageSwapCache(page) && !page_mapped(page) && trylock_page(page)) {
+		try_to_free_swap(page);
+		unlock_page(page);
+	}
+}
+
+/* 
+ * Perform a free_page(), also freeing any swap cache associated with
+ * this page if it is the last user of the page.
+ */
+void free_page_and_swap_cache(struct page *page)
+{
+	free_swap_cache(page);
+	page_cache_release(page);
+}
+
+/*
+ * Passed an array of pages, drop them all from swapcache and then release
+ * them.  They are removed from the LRU and freed if this is their last use.
+ */
+void free_pages_and_swap_cache(struct page **pages, int nr)
+{
+	struct page **pagep = pages;
+	int i;
+
+	lru_add_drain();
+	for (i = 0; i < nr; i++)
+		free_swap_cache(pagep[i]);
+	release_pages(pagep, nr, false);
+}
+
+/*
+ * Lookup a swap entry in the swap cache. A found page will be returned
+ * unlocked and with its refcount incremented - we rely on the kernel
+ * lock getting page table operations atomic even if we drop the page
+ * lock before returning.
+ */
+struct page * lookup_swap_cache(swp_entry_t entry)
+{
+	struct page *page;
+
+	page = find_get_page(swap_address_space(entry), entry.val);
+
+	if (page) {
+		INC_CACHE_INFO(find_success);
+		if (TestClearPageReadahead(page))
+			atomic_inc(&swapin_readahead_hits);
+	}
+
+	INC_CACHE_INFO(find_total);
+	return page;
+}
+
+/* 
+ * Locate a page of swap in physical memory, reserving swap cache space
+ * and reading the disk if it is not already cached.
+ * A failure return means that either the page allocation failed or that
+ * the swap entry is no longer in use.
+ */
+struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
+			struct vm_area_struct *vma, unsigned long addr)
+{
+	struct page *found_page, *new_page = NULL;
+	int err;
+
+	do {
+		/*
+		 * First check the swap cache.  Since this is normally
+		 * called after lookup_swap_cache() failed, re-calling
+		 * that would confuse statistics.
+		 */
+		found_page = find_get_page(swap_address_space(entry),
+					entry.val);
+		if (found_page)
+			break;
+
+		/*
+		 * Get a new page to read into from swap.
+		 */
+		if (!new_page) {
+			new_page = alloc_page_vma(gfp_mask, vma, addr);
+			if (!new_page)
+				break;		/* Out of memory */
+		}
+
+		/*
+		 * call radix_tree_preload() while we can wait.
+		 */
+		err = radix_tree_maybe_preload(gfp_mask & GFP_KERNEL);
+		if (err)
+			break;
+
+		/*
+		 * Swap entry may have been freed since our caller observed it.
+		 */
+		err = swapcache_prepare(entry);
+		if (err == -EEXIST) {
+			radix_tree_preload_end();
+			/*
+			 * We might race against get_swap_page() and stumble
+			 * across a SWAP_HAS_CACHE swap_map entry whose page
+			 * has not been brought into the swapcache yet, while
+			 * the other end is scheduled away waiting on discard
+			 * I/O completion at scan_swap_map().
+			 *
+			 * In order to avoid turning this transitory state
+			 * into a permanent loop around this -EEXIST case
+			 * if !CONFIG_PREEMPT and the I/O completion happens
+			 * to be waiting on the CPU waitqueue where we are now
+			 * busy looping, we just conditionally invoke the
+			 * scheduler here, if there are some more important
+			 * tasks to run.
+			 */
+			cond_resched();
+			continue;
+		}
+		if (err) {		/* swp entry is obsolete ? */
+			radix_tree_preload_end();
+			break;
+		}
+
+		/* May fail (-ENOMEM) if radix-tree node allocation failed. */
+		__set_page_locked(new_page);
+		SetPageSwapBacked(new_page);
+		err = __add_to_swap_cache(new_page, entry);
+		if (likely(!err)) {
+			radix_tree_preload_end();
+			/*
+			 * Initiate read into locked page and return.
+			 */
+			lru_cache_add_anon(new_page);
+			swap_readpage(new_page);
+			return new_page;
+		}
+		radix_tree_preload_end();
+		ClearPageSwapBacked(new_page);
+		__clear_page_locked(new_page);
+		/*
+		 * add_to_swap_cache() doesn't return -EEXIST, so we can safely
+		 * clear SWAP_HAS_CACHE flag.
+		 */
+		swapcache_free(entry);
+	} while (err != -ENOMEM);
+
+	if (new_page)
+		page_cache_release(new_page);
+	return found_page;
+}
+
+#ifdef CONFIG_SWAP_ENABLE_READAHEAD
+static unsigned long swapin_nr_pages(unsigned long offset)
+{
+	static unsigned long prev_offset;
+	unsigned int pages, max_pages, last_ra;
+	static atomic_t last_readahead_pages;
+
+	max_pages = 1 << ACCESS_ONCE(page_cluster);
+	if (max_pages <= 1)
+		return 1;
+
+	/*
+	 * This heuristic has been found to work well on both sequential and
+	 * random loads, swapping to hard disk or to SSD: please don't ask
+	 * what the "+ 2" means, it just happens to work well, that's all.
+	 */
+	pages = atomic_xchg(&swapin_readahead_hits, 0) + 2;
+	if (pages == 2) {
+		/*
+		 * We can have no readahead hits to judge by: but must not get
+		 * stuck here forever, so check for an adjacent offset instead
+		 * (and don't even bother to check whether swap type is same).
+		 */
+		if (offset != prev_offset + 1 && offset != prev_offset - 1)
+			pages = 1;
+		prev_offset = offset;
+	} else {
+		unsigned int roundup = 4;
+		while (roundup < pages)
+			roundup <<= 1;
+		pages = roundup;
+	}
+
+	if (pages > max_pages)
+		pages = max_pages;
+
+	/* Don't shrink readahead too fast */
+	last_ra = atomic_read(&last_readahead_pages) / 2;
+	if (pages < last_ra)
+		pages = last_ra;
+	atomic_set(&last_readahead_pages, pages);
+
+	return pages;
+}
+#endif
+
+/**
+ * swapin_readahead - swap in pages in hope we need them soon
+ * @entry: swap entry of this memory
+ * @gfp_mask: memory allocation flags
+ * @vma: user vma this address belongs to
+ * @addr: target address for mempolicy
+ *
+ * Returns the struct page for entry and addr, after queueing swapin.
+ *
+ * Primitive swap readahead code. We simply read an aligned block of
+ * (1 << page_cluster) entries in the swap area. This method is chosen
+ * because it doesn't cost us any seek time.  We also make sure to queue
+ * the 'original' request together with the readahead ones...
+ *
+ * This has been extended to use the NUMA policies from the mm triggering
+ * the readahead.
+ *
+ * Caller must hold down_read on the vma->vm_mm if vma is not NULL.
+ */
+struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask,
+			struct vm_area_struct *vma, unsigned long addr)
+{
+#ifdef CONFIG_SWAP_ENABLE_READAHEAD
+	struct page *page;
+	unsigned long entry_offset = swp_offset(entry);
+	unsigned long offset = entry_offset;
+	unsigned long start_offset, end_offset;
+	unsigned long mask;
+	struct blk_plug plug;
+
+	mask = swapin_nr_pages(offset) - 1;
+	if (!mask)
+		goto skip;
+
+	/* Read a page_cluster sized and aligned cluster around offset. */
+	start_offset = offset & ~mask;
+	end_offset = offset | mask;
+	if (!start_offset)	/* First page is swap header. */
+		start_offset++;
+
+	blk_start_plug(&plug);
+	for (offset = start_offset; offset <= end_offset ; offset++) {
+		/* Ok, do the async read-ahead now */
+		page = read_swap_cache_async(swp_entry(swp_type(entry), offset),
+						gfp_mask, vma, addr);
+		if (!page)
+			continue;
+		if (offset != entry_offset)
+			SetPageReadahead(page);
+		page_cache_release(page);
+	}
+	blk_finish_plug(&plug);
+
+	lru_add_drain();	/* Push any new pages onto the LRU now */
+skip:
+#endif
+	return read_swap_cache_async(entry, gfp_mask, vma, addr);
+}

mm/truncate.c

@@ -0,0 +1,820 @@
+/*
+ * mm/truncate.c - code for taking down pages from address_spaces
+ *
+ * Copyright (C) 2002, Linus Torvalds
+ *
+ * 10Sep2002	Andrew Morton
+ *		Initial version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/backing-dev.h>
+#include <linux/gfp.h>
+#include <linux/mm.h>
+#include <linux/swap.h>
+#include <linux/export.h>
+#include <linux/pagemap.h>
+#include <linux/highmem.h>
+#include <linux/pagevec.h>
+#include <linux/task_io_accounting_ops.h>
+#include <linux/buffer_head.h>	/* grr. try_to_release_page,
+				   do_invalidatepage */
+#include <linux/cleancache.h>
+#include <linux/rmap.h>
+#include "internal.h"
+
+static void clear_exceptional_entry(struct address_space *mapping,
+				    pgoff_t index, void *entry)
+{
+	struct radix_tree_node *node;
+	void **slot;
+
+	/* Handled by shmem itself */
+	if (shmem_mapping(mapping))
+		return;
+
+	spin_lock_irq(&mapping->tree_lock);
+	/*
+	 * Regular page slots are stabilized by the page lock even
+	 * without the tree itself locked.  These unlocked entries
+	 * need verification under the tree lock.
+	 */
+	if (!__radix_tree_lookup(&mapping->page_tree, index, &node, &slot))
+		goto unlock;
+	if (*slot != entry)
+		goto unlock;
+	radix_tree_replace_slot(slot, NULL);
+	mapping->nrshadows--;
+	if (!node)
+		goto unlock;
+	workingset_node_shadows_dec(node);
+	/*
+	 * Don't track node without shadow entries.
+	 *
+	 * Avoid acquiring the list_lru lock if already untracked.
+	 * The list_empty() test is safe as node->private_list is
+	 * protected by mapping->tree_lock.
+	 */
+	if (!workingset_node_shadows(node) &&
+	    !list_empty(&node->private_list))
+		list_lru_del(&workingset_shadow_nodes, &node->private_list);
+	__radix_tree_delete_node(&mapping->page_tree, node);
+unlock:
+	spin_unlock_irq(&mapping->tree_lock);
+}
+
+/**
+ * do_invalidatepage - invalidate part or all of a page
+ * @page: the page which is affected
+ * @offset: start of the range to invalidate
+ * @length: length of the range to invalidate
+ *
+ * do_invalidatepage() is called when all or part of the page has become
+ * invalidated by a truncate operation.
+ *
+ * do_invalidatepage() does not have to release all buffers, but it must
+ * ensure that no dirty buffer is left outside @offset and that no I/O
+ * is underway against any of the blocks which are outside the truncation
+ * point.  Because the caller is about to free (and possibly reuse) those
+ * blocks on-disk.
+ */
+void do_invalidatepage(struct page *page, unsigned int offset,
+		       unsigned int length)
+{
+	void (*invalidatepage)(struct page *, unsigned int, unsigned int);
+
+	invalidatepage = page->mapping->a_ops->invalidatepage;
+#ifdef CONFIG_BLOCK
+	if (!invalidatepage)
+		invalidatepage = block_invalidatepage;
+#endif
+	if (invalidatepage)
+		(*invalidatepage)(page, offset, length);
+}
+
+/*
+ * This cancels just the dirty bit on the kernel page itself, it
+ * does NOT actually remove dirty bits on any mmap's that may be
+ * around. It also leaves the page tagged dirty, so any sync
+ * activity will still find it on the dirty lists, and in particular,
+ * clear_page_dirty_for_io() will still look at the dirty bits in
+ * the VM.
+ *
+ * Doing this should *normally* only ever be done when a page
+ * is truncated, and is not actually mapped anywhere at all. However,
+ * fs/buffer.c does this when it notices that somebody has cleaned
+ * out all the buffers on a page without actually doing it through
+ * the VM. Can you say "ext3 is horribly ugly"? Tought you could.
+ */
+void cancel_dirty_page(struct page *page, unsigned int account_size)
+{
+	if (TestClearPageDirty(page)) {
+		struct address_space *mapping = page->mapping;
+		if (mapping && mapping_cap_account_dirty(mapping)) {
+			dec_zone_page_state(page, NR_FILE_DIRTY);
+			dec_bdi_stat(mapping->backing_dev_info,
+					BDI_RECLAIMABLE);
+			if (account_size)
+				task_io_account_cancelled_write(account_size);
+		}
+	}
+}
+EXPORT_SYMBOL(cancel_dirty_page);
+
+/*
+ * If truncate cannot remove the fs-private metadata from the page, the page
+ * becomes orphaned.  It will be left on the LRU and may even be mapped into
+ * user pagetables if we're racing with filemap_fault().
+ *
+ * We need to bale out if page->mapping is no longer equal to the original
+ * mapping.  This happens a) when the VM reclaimed the page while we waited on
+ * its lock, b) when a concurrent invalidate_mapping_pages got there first and
+ * c) when tmpfs swizzles a page between a tmpfs inode and swapper_space.
+ */
+static int
+truncate_complete_page(struct address_space *mapping, struct page *page)
+{
+	if (page->mapping != mapping)
+		return -EIO;
+
+	if (page_has_private(page))
+		do_invalidatepage(page, 0, PAGE_CACHE_SIZE);
+
+	cancel_dirty_page(page, PAGE_CACHE_SIZE);
+
+	ClearPageMappedToDisk(page);
+	delete_from_page_cache(page);
+	return 0;
+}
+
+/*
+ * This is for invalidate_mapping_pages().  That function can be called at
+ * any time, and is not supposed to throw away dirty pages.  But pages can
+ * be marked dirty at any time too, so use remove_mapping which safely
+ * discards clean, unused pages.
+ *
+ * Returns non-zero if the page was successfully invalidated.
+ */
+static int
+invalidate_complete_page(struct address_space *mapping, struct page *page)
+{
+	int ret;
+
+	if (page->mapping != mapping)
+		return 0;
+
+	if (page_has_private(page) && !try_to_release_page(page, 0))
+		return 0;
+
+	ret = remove_mapping(mapping, page);
+
+	return ret;
+}
+
+int truncate_inode_page(struct address_space *mapping, struct page *page)
+{
+	if (page_mapped(page)) {
+		unmap_mapping_range(mapping,
+				   (loff_t)page->index << PAGE_CACHE_SHIFT,
+				   PAGE_CACHE_SIZE, 0);
+	}
+	return truncate_complete_page(mapping, page);
+}
+
+/*
+ * Used to get rid of pages on hardware memory corruption.
+ */
+int generic_error_remove_page(struct address_space *mapping, struct page *page)
+{
+	if (!mapping)
+		return -EINVAL;
+	/*
+	 * Only punch for normal data pages for now.
+	 * Handling other types like directories would need more auditing.
+	 */
+	if (!S_ISREG(mapping->host->i_mode))
+		return -EIO;
+	return truncate_inode_page(mapping, page);
+}
+EXPORT_SYMBOL(generic_error_remove_page);
+
+/*
+ * Safely invalidate one page from its pagecache mapping.
+ * It only drops clean, unused pages. The page must be locked.
+ *
+ * Returns 1 if the page is successfully invalidated, otherwise 0.
+ */
+int invalidate_inode_page(struct page *page)
+{
+	struct address_space *mapping = page_mapping(page);
+	if (!mapping)
+		return 0;
+	if (PageDirty(page) || PageWriteback(page))
+		return 0;
+	if (page_mapped(page))
+		return 0;
+	return invalidate_complete_page(mapping, page);
+}
+
+/**
+ * truncate_inode_pages_range - truncate range of pages specified by start & end byte offsets
+ * @mapping: mapping to truncate
+ * @lstart: offset from which to truncate
+ * @lend: offset to which to truncate (inclusive)
+ *
+ * Truncate the page cache, removing the pages that are between
+ * specified offsets (and zeroing out partial pages
+ * if lstart or lend + 1 is not page aligned).
+ *
+ * Truncate takes two passes - the first pass is nonblocking.  It will not
+ * block on page locks and it will not block on writeback.  The second pass
+ * will wait.  This is to prevent as much IO as possible in the affected region.
+ * The first pass will remove most pages, so the search cost of the second pass
+ * is low.
+ *
+ * We pass down the cache-hot hint to the page freeing code.  Even if the
+ * mapping is large, it is probably the case that the final pages are the most
+ * recently touched, and freeing happens in ascending file offset order.
+ *
+ * Note that since ->invalidatepage() accepts range to invalidate
+ * truncate_inode_pages_range is able to handle cases where lend + 1 is not
+ * page aligned properly.
+ */
+void truncate_inode_pages_range(struct address_space *mapping,
+				loff_t lstart, loff_t lend)
+{
+	pgoff_t		start;		/* inclusive */
+	pgoff_t		end;		/* exclusive */
+	unsigned int	partial_start;	/* inclusive */
+	unsigned int	partial_end;	/* exclusive */
+	struct pagevec	pvec;
+	pgoff_t		indices[PAGEVEC_SIZE];
+	pgoff_t		index;
+	int		i;
+
+	cleancache_invalidate_inode(mapping);
+	if (mapping->nrpages == 0 && mapping->nrshadows == 0)
+		return;
+
+	/* Offsets within partial pages */
+	partial_start = lstart & (PAGE_CACHE_SIZE - 1);
+	partial_end = (lend + 1) & (PAGE_CACHE_SIZE - 1);
+
+	/*
+	 * 'start' and 'end' always covers the range of pages to be fully
+	 * truncated. Partial pages are covered with 'partial_start' at the
+	 * start of the range and 'partial_end' at the end of the range.
+	 * Note that 'end' is exclusive while 'lend' is inclusive.
+	 */
+	start = (lstart + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+	if (lend == -1)
+		/*
+		 * lend == -1 indicates end-of-file so we have to set 'end'
+		 * to the highest possible pgoff_t and since the type is
+		 * unsigned we're using -1.
+		 */
+		end = -1;
+	else
+		end = (lend + 1) >> PAGE_CACHE_SHIFT;
+
+	pagevec_init(&pvec, 0);
+	index = start;
+	while (index < end && pagevec_lookup_entries(&pvec, mapping, index,
+			min(end - index, (pgoff_t)PAGEVEC_SIZE),
+			indices)) {
+		for (i = 0; i < pagevec_count(&pvec); i++) {
+			struct page *page = pvec.pages[i];
+
+			/* We rely upon deletion not changing page->index */
+			index = indices[i];
+			if (index >= end)
+				break;
+
+			if (radix_tree_exceptional_entry(page)) {
+				clear_exceptional_entry(mapping, index, page);
+				continue;
+			}
+
+			if (!trylock_page(page))
+				continue;
+			WARN_ON(page->index != index);
+			if (PageWriteback(page)) {
+				unlock_page(page);
+				continue;
+			}
+			truncate_inode_page(mapping, page);
+			unlock_page(page);
+		}
+		pagevec_remove_exceptionals(&pvec);
+		pagevec_release(&pvec);
+		cond_resched();
+		index++;
+	}
+
+	if (partial_start) {
+		struct page *page = find_lock_page(mapping, start - 1);
+		if (page) {
+			unsigned int top = PAGE_CACHE_SIZE;
+			if (start > end) {
+				/* Truncation within a single page */
+				top = partial_end;
+				partial_end = 0;
+			}
+			wait_on_page_writeback(page);
+			zero_user_segment(page, partial_start, top);
+			cleancache_invalidate_page(mapping, page);
+			if (page_has_private(page))
+				do_invalidatepage(page, partial_start,
+						  top - partial_start);
+			unlock_page(page);
+			page_cache_release(page);
+		}
+	}
+	if (partial_end) {
+		struct page *page = find_lock_page(mapping, end);
+		if (page) {
+			wait_on_page_writeback(page);
+			zero_user_segment(page, 0, partial_end);
+			cleancache_invalidate_page(mapping, page);
+			if (page_has_private(page))
+				do_invalidatepage(page, 0,
+						  partial_end);
+			unlock_page(page);
+			page_cache_release(page);
+		}
+	}
+	/*
+	 * If the truncation happened within a single page no pages
+	 * will be released, just zeroed, so we can bail out now.
+	 */
+	if (start >= end)
+		return;
+
+	index = start;
+	for ( ; ; ) {
+		cond_resched();
+		if (!pagevec_lookup_entries(&pvec, mapping, index,
+			min(end - index, (pgoff_t)PAGEVEC_SIZE), indices)) {
+			/* If all gone from start onwards, we're done */
+			if (index == start)
+				break;
+			/* Otherwise restart to make sure all gone */
+			index = start;
+			continue;
+		}
+		if (index == start && indices[0] >= end) {
+			/* All gone out of hole to be punched, we're done */
+			pagevec_remove_exceptionals(&pvec);
+			pagevec_release(&pvec);
+			break;
+		}
+		for (i = 0; i < pagevec_count(&pvec); i++) {
+			struct page *page = pvec.pages[i];
+
+			/* We rely upon deletion not changing page->index */
+			index = indices[i];
+			if (index >= end) {
+				/* Restart punch to make sure all gone */
+				index = start - 1;
+				break;
+			}
+
+			if (radix_tree_exceptional_entry(page)) {
+				clear_exceptional_entry(mapping, index, page);
+				continue;
+			}
+
+			lock_page(page);
+			WARN_ON(page->index != index);
+			wait_on_page_writeback(page);
+			truncate_inode_page(mapping, page);
+			unlock_page(page);
+		}
+		pagevec_remove_exceptionals(&pvec);
+		pagevec_release(&pvec);
+		index++;
+	}
+	cleancache_invalidate_inode(mapping);
+}
+EXPORT_SYMBOL(truncate_inode_pages_range);
+
+/**
+ * truncate_inode_pages - truncate *all* the pages from an offset
+ * @mapping: mapping to truncate
+ * @lstart: offset from which to truncate
+ *
+ * Called under (and serialised by) inode->i_mutex.
+ *
+ * Note: When this function returns, there can be a page in the process of
+ * deletion (inside __delete_from_page_cache()) in the specified range.  Thus
+ * mapping->nrpages can be non-zero when this function returns even after
+ * truncation of the whole mapping.
+ */
+void truncate_inode_pages(struct address_space *mapping, loff_t lstart)
+{
+	truncate_inode_pages_range(mapping, lstart, (loff_t)-1);
+}
+EXPORT_SYMBOL(truncate_inode_pages);
+
+/**
+ * truncate_inode_pages_final - truncate *all* pages before inode dies
+ * @mapping: mapping to truncate
+ *
+ * Called under (and serialized by) inode->i_mutex.
+ *
+ * Filesystems have to use this in the .evict_inode path to inform the
+ * VM that this is the final truncate and the inode is going away.
+ */
+void truncate_inode_pages_final(struct address_space *mapping)
+{
+	unsigned long nrshadows;
+	unsigned long nrpages;
+
+	/*
+	 * Page reclaim can not participate in regular inode lifetime
+	 * management (can't call iput()) and thus can race with the
+	 * inode teardown.  Tell it when the address space is exiting,
+	 * so that it does not install eviction information after the
+	 * final truncate has begun.
+	 */
+	mapping_set_exiting(mapping);
+
+	/*
+	 * When reclaim installs eviction entries, it increases
+	 * nrshadows first, then decreases nrpages.  Make sure we see
+	 * this in the right order or we might miss an entry.
+	 */
+	nrpages = mapping->nrpages;
+	smp_rmb();
+	nrshadows = mapping->nrshadows;
+
+	if (nrpages || nrshadows) {
+		/*
+		 * As truncation uses a lockless tree lookup, cycle
+		 * the tree lock to make sure any ongoing tree
+		 * modification that does not see AS_EXITING is
+		 * completed before starting the final truncate.
+		 */
+		spin_lock_irq(&mapping->tree_lock);
+		spin_unlock_irq(&mapping->tree_lock);
+
+		truncate_inode_pages(mapping, 0);
+	}
+}
+EXPORT_SYMBOL(truncate_inode_pages_final);
+
+/**
+ * invalidate_mapping_pages - Invalidate all the unlocked pages of one inode
+ * @mapping: the address_space which holds the pages to invalidate
+ * @start: the offset 'from' which to invalidate
+ * @end: the offset 'to' which to invalidate (inclusive)
+ *
+ * This function only removes the unlocked pages, if you want to
+ * remove all the pages of one inode, you must call truncate_inode_pages.
+ *
+ * invalidate_mapping_pages() will not block on IO activity. It will not
+ * invalidate pages which are dirty, locked, under writeback or mapped into
+ * pagetables.
+ */
+unsigned long invalidate_mapping_pages(struct address_space *mapping,
+		pgoff_t start, pgoff_t end)
+{
+	pgoff_t indices[PAGEVEC_SIZE];
+	struct pagevec pvec;
+	pgoff_t index = start;
+	unsigned long ret;
+	unsigned long count = 0;
+	int i;
+
+	pagevec_init(&pvec, 0);
+	while (index <= end && pagevec_lookup_entries(&pvec, mapping, index,
+			min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1,
+			indices)) {
+		for (i = 0; i < pagevec_count(&pvec); i++) {
+			struct page *page = pvec.pages[i];
+
+			/* We rely upon deletion not changing page->index */
+			index = indices[i];
+			if (index > end)
+				break;
+
+			if (radix_tree_exceptional_entry(page)) {
+				clear_exceptional_entry(mapping, index, page);
+				continue;
+			}
+
+			if (!trylock_page(page))
+				continue;
+			WARN_ON(page->index != index);
+			ret = invalidate_inode_page(page);
+			unlock_page(page);
+			/*
+			 * Invalidation is a hint that the page is no longer
+			 * of interest and try to speed up its reclaim.
+			 */
+			if (!ret)
+				deactivate_page(page);
+			count += ret;
+		}
+		pagevec_remove_exceptionals(&pvec);
+		pagevec_release(&pvec);
+		cond_resched();
+		index++;
+	}
+	return count;
+}
+EXPORT_SYMBOL(invalidate_mapping_pages);
+
+/*
+ * This is like invalidate_complete_page(), except it ignores the page's
+ * refcount.  We do this because invalidate_inode_pages2() needs stronger
+ * invalidation guarantees, and cannot afford to leave pages behind because
+ * shrink_page_list() has a temp ref on them, or because they're transiently
+ * sitting in the lru_cache_add() pagevecs.
+ */
+static int
+invalidate_complete_page2(struct address_space *mapping, struct page *page)
+{
+	if (page->mapping != mapping)
+		return 0;
+
+	if (page_has_private(page) && !try_to_release_page(page, GFP_KERNEL))
+		return 0;
+
+	spin_lock_irq(&mapping->tree_lock);
+	if (PageDirty(page))
+		goto failed;
+
+	BUG_ON(page_has_private(page));
+	__delete_from_page_cache(page, NULL);
+	spin_unlock_irq(&mapping->tree_lock);
+
+	if (mapping->a_ops->freepage)
+		mapping->a_ops->freepage(page);
+
+	page_cache_release(page);	/* pagecache ref */
+	return 1;
+failed:
+	spin_unlock_irq(&mapping->tree_lock);
+	return 0;
+}
+
+static int do_launder_page(struct address_space *mapping, struct page *page)
+{
+	if (!PageDirty(page))
+		return 0;
+	if (page->mapping != mapping || mapping->a_ops->launder_page == NULL)
+		return 0;
+	return mapping->a_ops->launder_page(page);
+}
+
+/**
+ * invalidate_inode_pages2_range - remove range of pages from an address_space
+ * @mapping: the address_space
+ * @start: the page offset 'from' which to invalidate
+ * @end: the page offset 'to' which to invalidate (inclusive)
+ *
+ * Any pages which are found to be mapped into pagetables are unmapped prior to
+ * invalidation.
+ *
+ * Returns -EBUSY if any pages could not be invalidated.
+ */
+int invalidate_inode_pages2_range(struct address_space *mapping,
+				  pgoff_t start, pgoff_t end)
+{
+	pgoff_t indices[PAGEVEC_SIZE];
+	struct pagevec pvec;
+	pgoff_t index;
+	int i;
+	int ret = 0;
+	int ret2 = 0;
+	int did_range_unmap = 0;
+
+	cleancache_invalidate_inode(mapping);
+	pagevec_init(&pvec, 0);
+	index = start;
+	while (index <= end && pagevec_lookup_entries(&pvec, mapping, index,
+			min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1,
+			indices)) {
+		for (i = 0; i < pagevec_count(&pvec); i++) {
+			struct page *page = pvec.pages[i];
+
+			/* We rely upon deletion not changing page->index */
+			index = indices[i];
+			if (index > end)
+				break;
+
+			if (radix_tree_exceptional_entry(page)) {
+				clear_exceptional_entry(mapping, index, page);
+				continue;
+			}
+
+			lock_page(page);
+			WARN_ON(page->index != index);
+			if (page->mapping != mapping) {
+				unlock_page(page);
+				continue;
+			}
+			wait_on_page_writeback(page);
+			if (page_mapped(page)) {
+				if (!did_range_unmap) {
+					/*
+					 * Zap the rest of the file in one hit.
+					 */
+					unmap_mapping_range(mapping,
+					   (loff_t)index << PAGE_CACHE_SHIFT,
+					   (loff_t)(1 + end - index)
+							 << PAGE_CACHE_SHIFT,
+					    0);
+					did_range_unmap = 1;
+				} else {
+					/*
+					 * Just zap this page
+					 */
+					unmap_mapping_range(mapping,
+					   (loff_t)index << PAGE_CACHE_SHIFT,
+					   PAGE_CACHE_SIZE, 0);
+				}
+			}
+			BUG_ON(page_mapped(page));
+			ret2 = do_launder_page(mapping, page);
+			if (ret2 == 0) {
+				if (!invalidate_complete_page2(mapping, page))
+					ret2 = -EBUSY;
+			}
+			if (ret2 < 0)
+				ret = ret2;
+			unlock_page(page);
+		}
+		pagevec_remove_exceptionals(&pvec);
+		pagevec_release(&pvec);
+		cond_resched();
+		index++;
+	}
+	cleancache_invalidate_inode(mapping);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(invalidate_inode_pages2_range);
+
+/**
+ * invalidate_inode_pages2 - remove all pages from an address_space
+ * @mapping: the address_space
+ *
+ * Any pages which are found to be mapped into pagetables are unmapped prior to
+ * invalidation.
+ *
+ * Returns -EBUSY if any pages could not be invalidated.
+ */
+int invalidate_inode_pages2(struct address_space *mapping)
+{
+	return invalidate_inode_pages2_range(mapping, 0, -1);
+}
+EXPORT_SYMBOL_GPL(invalidate_inode_pages2);
+
+/**
+ * truncate_pagecache - unmap and remove pagecache that has been truncated
+ * @inode: inode
+ * @newsize: new file size
+ *
+ * inode's new i_size must already be written before truncate_pagecache
+ * is called.
+ *
+ * This function should typically be called before the filesystem
+ * releases resources associated with the freed range (eg. deallocates
+ * blocks). This way, pagecache will always stay logically coherent
+ * with on-disk format, and the filesystem would not have to deal with
+ * situations such as writepage being called for a page that has already
+ * had its underlying blocks deallocated.
+ */
+void truncate_pagecache(struct inode *inode, loff_t newsize)
+{
+	struct address_space *mapping = inode->i_mapping;
+	loff_t holebegin = round_up(newsize, PAGE_SIZE);
+
+	/*
+	 * unmap_mapping_range is called twice, first simply for
+	 * efficiency so that truncate_inode_pages does fewer
+	 * single-page unmaps.  However after this first call, and
+	 * before truncate_inode_pages finishes, it is possible for
+	 * private pages to be COWed, which remain after
+	 * truncate_inode_pages finishes, hence the second
+	 * unmap_mapping_range call must be made for correctness.
+	 */
+	unmap_mapping_range(mapping, holebegin, 0, 1);
+	truncate_inode_pages(mapping, newsize);
+	unmap_mapping_range(mapping, holebegin, 0, 1);
+}
+EXPORT_SYMBOL(truncate_pagecache);
+
+/**
+ * truncate_setsize - update inode and pagecache for a new file size
+ * @inode: inode
+ * @newsize: new file size
+ *
+ * truncate_setsize updates i_size and performs pagecache truncation (if
+ * necessary) to @newsize. It will be typically be called from the filesystem's
+ * setattr function when ATTR_SIZE is passed in.
+ *
+ * Must be called with a lock serializing truncates and writes (generally
+ * i_mutex but e.g. xfs uses a different lock) and before all filesystem
+ * specific block truncation has been performed.
+ */
+void truncate_setsize(struct inode *inode, loff_t newsize)
+{
+	loff_t oldsize = inode->i_size;
+
+	i_size_write(inode, newsize);
+	if (newsize > oldsize)
+		pagecache_isize_extended(inode, oldsize, newsize);
+	truncate_pagecache(inode, newsize);
+}
+EXPORT_SYMBOL(truncate_setsize);
+
+/**
+ * pagecache_isize_extended - update pagecache after extension of i_size
+ * @inode:	inode for which i_size was extended
+ * @from:	original inode size
+ * @to:		new inode size
+ *
+ * Handle extension of inode size either caused by extending truncate or by
+ * write starting after current i_size. We mark the page straddling current
+ * i_size RO so that page_mkwrite() is called on the nearest write access to
+ * the page.  This way filesystem can be sure that page_mkwrite() is called on
+ * the page before user writes to the page via mmap after the i_size has been
+ * changed.
+ *
+ * The function must be called after i_size is updated so that page fault
+ * coming after we unlock the page will already see the new i_size.
+ * The function must be called while we still hold i_mutex - this not only
+ * makes sure i_size is stable but also that userspace cannot observe new
+ * i_size value before we are prepared to store mmap writes at new inode size.
+ */
+void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to)
+{
+	int bsize = 1 << inode->i_blkbits;
+	loff_t rounded_from;
+	struct page *page;
+	pgoff_t index;
+
+	WARN_ON(to > inode->i_size);
+
+	if (from >= to || bsize == PAGE_CACHE_SIZE)
+		return;
+	/* Page straddling @from will not have any hole block created? */
+	rounded_from = round_up(from, bsize);
+	if (to <= rounded_from || !(rounded_from & (PAGE_CACHE_SIZE - 1)))
+		return;
+
+	index = from >> PAGE_CACHE_SHIFT;
+	page = find_lock_page(inode->i_mapping, index);
+	/* Page not cached? Nothing to do */
+	if (!page)
+		return;
+	/*
+	 * See clear_page_dirty_for_io() for details why set_page_dirty()
+	 * is needed.
+	 */
+	if (page_mkclean(page))
+		set_page_dirty(page);
+	unlock_page(page);
+	page_cache_release(page);
+}
+EXPORT_SYMBOL(pagecache_isize_extended);
+
+/**
+ * truncate_pagecache_range - unmap and remove pagecache that is hole-punched
+ * @inode: inode
+ * @lstart: offset of beginning of hole
+ * @lend: offset of last byte of hole
+ *
+ * This function should typically be called before the filesystem
+ * releases resources associated with the freed range (eg. deallocates
+ * blocks). This way, pagecache will always stay logically coherent
+ * with on-disk format, and the filesystem would not have to deal with
+ * situations such as writepage being called for a page that has already
+ * had its underlying blocks deallocated.
+ */
+void truncate_pagecache_range(struct inode *inode, loff_t lstart, loff_t lend)
+{
+	struct address_space *mapping = inode->i_mapping;
+	loff_t unmap_start = round_up(lstart, PAGE_SIZE);
+	loff_t unmap_end = round_down(1 + lend, PAGE_SIZE) - 1;
+	/*
+	 * This rounding is currently just for example: unmap_mapping_range
+	 * expands its hole outwards, whereas we want it to contract the hole
+	 * inwards.  However, existing callers of truncate_pagecache_range are
+	 * doing their own page rounding first.  Note that unmap_mapping_range
+	 * allows holelen 0 for all, and we allow lend -1 for end of file.
+	 */
+
+	/*
+	 * Unlike in truncate_pagecache, unmap_mapping_range is called only
+	 * once (before truncating pagecache), and without "even_cows" flag:
+	 * hole-punching should not remove private COWed pages from the hole.
+	 */
+	if ((u64)unmap_end > (u64)unmap_start)
+		unmap_mapping_range(mapping, unmap_start,
+				    1 + unmap_end - unmap_start, 0);
+	truncate_inode_pages_range(mapping, lstart, lend);
+}
+EXPORT_SYMBOL(truncate_pagecache_range);

mm/util.c

@@ -0,0 +1,402 @@
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/compiler.h>
+#include <linux/export.h>
+#include <linux/err.h>
+#include <linux/sched.h>
+#include <linux/security.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
+#include <linux/mman.h>
+#include <linux/hugetlb.h>
+#include <linux/vmalloc.h>
+
+#include <asm/uaccess.h>
+
+#include "internal.h"
+
+/**
+ * kstrdup - allocate space for and copy an existing string
+ * @s: the string to duplicate
+ * @gfp: the GFP mask used in the kmalloc() call when allocating memory
+ */
+char *kstrdup(const char *s, gfp_t gfp)
+{
+	size_t len;
+	char *buf;
+
+	if (!s)
+		return NULL;
+
+	len = strlen(s) + 1;
+	buf = kmalloc_track_caller(len, gfp);
+	if (buf)
+		memcpy(buf, s, len);
+	return buf;
+}
+EXPORT_SYMBOL(kstrdup);
+
+/**
+ * kstrndup - allocate space for and copy an existing string
+ * @s: the string to duplicate
+ * @max: read at most @max chars from @s
+ * @gfp: the GFP mask used in the kmalloc() call when allocating memory
+ */
+char *kstrndup(const char *s, size_t max, gfp_t gfp)
+{
+	size_t len;
+	char *buf;
+
+	if (!s)
+		return NULL;
+
+	len = strnlen(s, max);
+	buf = kmalloc_track_caller(len+1, gfp);
+	if (buf) {
+		memcpy(buf, s, len);
+		buf[len] = '\0';
+	}
+	return buf;
+}
+EXPORT_SYMBOL(kstrndup);
+
+/**
+ * kmemdup - duplicate region of memory
+ *
+ * @src: memory region to duplicate
+ * @len: memory region length
+ * @gfp: GFP mask to use
+ */
+void *kmemdup(const void *src, size_t len, gfp_t gfp)
+{
+	void *p;
+
+	p = kmalloc_track_caller(len, gfp);
+	if (p)
+		memcpy(p, src, len);
+	return p;
+}
+EXPORT_SYMBOL(kmemdup);
+
+/**
+ * memdup_user - duplicate memory region from user space
+ *
+ * @src: source address in user space
+ * @len: number of bytes to copy
+ *
+ * Returns an ERR_PTR() on failure.
+ */
+void *memdup_user(const void __user *src, size_t len)
+{
+	void *p;
+
+	/*
+	 * Always use GFP_KERNEL, since copy_from_user() can sleep and
+	 * cause pagefault, which makes it pointless to use GFP_NOFS
+	 * or GFP_ATOMIC.
+	 */
+	p = kmalloc_track_caller(len, GFP_KERNEL);
+	if (!p)
+		return ERR_PTR(-ENOMEM);
+
+	if (copy_from_user(p, src, len)) {
+		kfree(p);
+		return ERR_PTR(-EFAULT);
+	}
+
+	return p;
+}
+EXPORT_SYMBOL(memdup_user);
+
+/*
+ * strndup_user - duplicate an existing string from user space
+ * @s: The string to duplicate
+ * @n: Maximum number of bytes to copy, including the trailing NUL.
+ */
+char *strndup_user(const char __user *s, long n)
+{
+	char *p;
+	long length;
+
+	length = strnlen_user(s, n);
+
+	if (!length)
+		return ERR_PTR(-EFAULT);
+
+	if (length > n)
+		return ERR_PTR(-EINVAL);
+
+	p = memdup_user(s, length);
+
+	if (IS_ERR(p))
+		return p;
+
+	p[length - 1] = '\0';
+
+	return p;
+}
+EXPORT_SYMBOL(strndup_user);
+
+void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
+		struct vm_area_struct *prev, struct rb_node *rb_parent)
+{
+	struct vm_area_struct *next;
+
+	vma->vm_prev = prev;
+	if (prev) {
+		next = prev->vm_next;
+		prev->vm_next = vma;
+	} else {
+		mm->mmap = vma;
+		if (rb_parent)
+			next = rb_entry(rb_parent,
+					struct vm_area_struct, vm_rb);
+		else
+			next = NULL;
+	}
+	vma->vm_next = next;
+	if (next)
+		next->vm_prev = vma;
+}
+
+/* Check if the vma is being used as a stack by this task */
+static int vm_is_stack_for_task(struct task_struct *t,
+				struct vm_area_struct *vma)
+{
+	return (vma->vm_start <= KSTK_ESP(t) && vma->vm_end >= KSTK_ESP(t));
+}
+
+/*
+ * Check if the vma is being used as a stack.
+ * If is_group is non-zero, check in the entire thread group or else
+ * just check in the current task. Returns the task_struct of the task
+ * that the vma is stack for. Must be called under rcu_read_lock().
+ */
+struct task_struct *task_of_stack(struct task_struct *task,
+				struct vm_area_struct *vma, bool in_group)
+{
+	if (vm_is_stack_for_task(task, vma))
+		return task;
+
+	if (in_group) {
+		struct task_struct *t;
+
+		for_each_thread(task, t) {
+			if (vm_is_stack_for_task(t, vma))
+				return t;
+		}
+	}
+
+	return NULL;
+}
+
+#if defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT)
+void arch_pick_mmap_layout(struct mm_struct *mm)
+{
+	mm->mmap_base = TASK_UNMAPPED_BASE;
+	mm->get_unmapped_area = arch_get_unmapped_area;
+}
+#endif
+
+/*
+ * Like get_user_pages_fast() except its IRQ-safe in that it won't fall
+ * back to the regular GUP.
+ * If the architecture not support this function, simply return with no
+ * page pinned
+ */
+int __weak __get_user_pages_fast(unsigned long start,
+				 int nr_pages, int write, struct page **pages)
+{
+	return 0;
+}
+EXPORT_SYMBOL_GPL(__get_user_pages_fast);
+
+/**
+ * get_user_pages_fast() - pin user pages in memory
+ * @start:	starting user address
+ * @nr_pages:	number of pages from start to pin
+ * @write:	whether pages will be written to
+ * @pages:	array that receives pointers to the pages pinned.
+ *		Should be at least nr_pages long.
+ *
+ * Returns number of pages pinned. This may be fewer than the number
+ * requested. If nr_pages is 0 or negative, returns 0. If no pages
+ * were pinned, returns -errno.
+ *
+ * get_user_pages_fast provides equivalent functionality to get_user_pages,
+ * operating on current and current->mm, with force=0 and vma=NULL. However
+ * unlike get_user_pages, it must be called without mmap_sem held.
+ *
+ * get_user_pages_fast may take mmap_sem and page table locks, so no
+ * assumptions can be made about lack of locking. get_user_pages_fast is to be
+ * implemented in a way that is advantageous (vs get_user_pages()) when the
+ * user memory area is already faulted in and present in ptes. However if the
+ * pages have to be faulted in, it may turn out to be slightly slower so
+ * callers need to carefully consider what to use. On many architectures,
+ * get_user_pages_fast simply falls back to get_user_pages.
+ */
+int __weak get_user_pages_fast(unsigned long start,
+				int nr_pages, int write, struct page **pages)
+{
+	struct mm_struct *mm = current->mm;
+	int ret;
+
+	down_read(&mm->mmap_sem);
+	ret = get_user_pages(current, mm, start, nr_pages,
+					write, 0, pages, NULL);
+	up_read(&mm->mmap_sem);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(get_user_pages_fast);
+
+unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr,
+	unsigned long len, unsigned long prot,
+	unsigned long flag, unsigned long pgoff)
+{
+	unsigned long ret;
+	struct mm_struct *mm = current->mm;
+	unsigned long populate;
+
+	ret = security_mmap_file(file, prot, flag);
+	if (!ret) {
+		down_write(&mm->mmap_sem);
+		ret = do_mmap_pgoff(file, addr, len, prot, flag, pgoff,
+				    &populate);
+		up_write(&mm->mmap_sem);
+		if (populate)
+			mm_populate(ret, populate);
+	}
+	return ret;
+}
+
+unsigned long vm_mmap(struct file *file, unsigned long addr,
+	unsigned long len, unsigned long prot,
+	unsigned long flag, unsigned long offset)
+{
+	if (unlikely(offset + PAGE_ALIGN(len) < offset))
+		return -EINVAL;
+	if (unlikely(offset & ~PAGE_MASK))
+		return -EINVAL;
+
+	return vm_mmap_pgoff(file, addr, len, prot, flag, offset >> PAGE_SHIFT);
+}
+EXPORT_SYMBOL(vm_mmap);
+
+void kvfree(const void *addr)
+{
+	if (is_vmalloc_addr(addr))
+		vfree(addr);
+	else
+		kfree(addr);
+}
+EXPORT_SYMBOL(kvfree);
+
+struct address_space *page_mapping(struct page *page)
+{
+	struct address_space *mapping = page->mapping;
+
+	/* This happens if someone calls flush_dcache_page on slab page */
+	if (unlikely(PageSlab(page)))
+		return NULL;
+
+	if (unlikely(PageSwapCache(page))) {
+		swp_entry_t entry;
+
+		entry.val = page_private(page);
+		mapping = swap_address_space(entry);
+	} else if ((unsigned long)mapping & PAGE_MAPPING_ANON)
+		mapping = NULL;
+	return mapping;
+}
+
+int overcommit_ratio_handler(struct ctl_table *table, int write,
+			     void __user *buffer, size_t *lenp,
+			     loff_t *ppos)
+{
+	int ret;
+
+	ret = proc_dointvec(table, write, buffer, lenp, ppos);
+	if (ret == 0 && write)
+		sysctl_overcommit_kbytes = 0;
+	return ret;
+}
+
+int overcommit_kbytes_handler(struct ctl_table *table, int write,
+			     void __user *buffer, size_t *lenp,
+			     loff_t *ppos)
+{
+	int ret;
+
+	ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
+	if (ret == 0 && write)
+		sysctl_overcommit_ratio = 0;
+	return ret;
+}
+
+/*
+ * Committed memory limit enforced when OVERCOMMIT_NEVER policy is used
+ */
+unsigned long vm_commit_limit(void)
+{
+	unsigned long allowed;
+
+	if (sysctl_overcommit_kbytes)
+		allowed = sysctl_overcommit_kbytes >> (PAGE_SHIFT - 10);
+	else
+		allowed = ((totalram_pages - hugetlb_total_pages())
+			   * sysctl_overcommit_ratio / 100);
+	allowed += total_swap_pages;
+
+	return allowed;
+}
+
+/**
+ * get_cmdline() - copy the cmdline value to a buffer.
+ * @task:     the task whose cmdline value to copy.
+ * @buffer:   the buffer to copy to.
+ * @buflen:   the length of the buffer. Larger cmdline values are truncated
+ *            to this length.
+ * Returns the size of the cmdline field copied. Note that the copy does
+ * not guarantee an ending NULL byte.
+ */
+int get_cmdline(struct task_struct *task, char *buffer, int buflen)
+{
+	int res = 0;
+	unsigned int len;
+	struct mm_struct *mm = get_task_mm(task);
+	if (!mm)
+		goto out;
+	if (!mm->arg_end)
+		goto out_mm;	/* Shh! No looking before we're done */
+
+	len = mm->arg_end - mm->arg_start;
+
+	if (len > buflen)
+		len = buflen;
+
+	res = access_process_vm(task, mm->arg_start, buffer, len, 0);
+
+	/*
+	 * If the nul at the end of args has been overwritten, then
+	 * assume application is using setproctitle(3).
+	 */
+	if (res > 0 && buffer[res-1] != '\0' && len < buflen) {
+		len = strnlen(buffer, res);
+		if (len < res) {
+			res = len;
+		} else {
+			len = mm->env_end - mm->env_start;
+			if (len > buflen - res)
+				len = buflen - res;
+			res += access_process_vm(task, mm->env_start,
+						 buffer+res, len, 0);
+			res = strnlen(buffer, res);
+		}
+	}
+out_mm:
+	mmput(mm);
+out:
+	return res;
+}

mm/vmacache.c

@@ -0,0 +1,132 @@
+/*
+ * Copyright (C) 2014 Davidlohr Bueso.
+ */
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/vmacache.h>
+
+/*
+ * Flush vma caches for threads that share a given mm.
+ *
+ * The operation is safe because the caller holds the mmap_sem
+ * exclusively and other threads accessing the vma cache will
+ * have mmap_sem held at least for read, so no extra locking
+ * is required to maintain the vma cache.
+ */
+void vmacache_flush_all(struct mm_struct *mm)
+{
+	struct task_struct *g, *p;
+
+	/*
+	 * Single threaded tasks need not iterate the entire
+	 * list of process. We can avoid the flushing as well
+	 * since the mm's seqnum was increased and don't have
+	 * to worry about other threads' seqnum. Current's
+	 * flush will occur upon the next lookup.
+	 */
+	if (atomic_read(&mm->mm_users) == 1)
+		return;
+
+	rcu_read_lock();
+	for_each_process_thread(g, p) {
+		/*
+		 * Only flush the vmacache pointers as the
+		 * mm seqnum is already set and curr's will
+		 * be set upon invalidation when the next
+		 * lookup is done.
+		 */
+		if (mm == p->mm)
+			vmacache_flush(p);
+	}
+	rcu_read_unlock();
+}
+
+/*
+ * This task may be accessing a foreign mm via (for example)
+ * get_user_pages()->find_vma().  The vmacache is task-local and this
+ * task's vmacache pertains to a different mm (ie, its own).  There is
+ * nothing we can do here.
+ *
+ * Also handle the case where a kernel thread has adopted this mm via use_mm().
+ * That kernel thread's vmacache is not applicable to this mm.
+ */
+static bool vmacache_valid_mm(struct mm_struct *mm)
+{
+	return current->mm == mm && !(current->flags & PF_KTHREAD);
+}
+
+void vmacache_update(unsigned long addr, struct vm_area_struct *newvma)
+{
+	if (vmacache_valid_mm(newvma->vm_mm))
+		current->vmacache[VMACACHE_HASH(addr)] = newvma;
+}
+
+static bool vmacache_valid(struct mm_struct *mm)
+{
+	struct task_struct *curr;
+
+	if (!vmacache_valid_mm(mm))
+		return false;
+
+	curr = current;
+	if (mm->vmacache_seqnum != curr->vmacache_seqnum) {
+		/*
+		 * First attempt will always be invalid, initialize
+		 * the new cache for this task here.
+		 */
+		curr->vmacache_seqnum = mm->vmacache_seqnum;
+		vmacache_flush(curr);
+		return false;
+	}
+	return true;
+}
+
+struct vm_area_struct *vmacache_find(struct mm_struct *mm, unsigned long addr)
+{
+	int i;
+
+	if (!vmacache_valid(mm))
+		return NULL;
+
+	count_vm_vmacache_event(VMACACHE_FIND_CALLS);
+
+	for (i = 0; i < VMACACHE_SIZE; i++) {
+		struct vm_area_struct *vma = current->vmacache[i];
+
+		if (!vma)
+			continue;
+		if (WARN_ON_ONCE(vma->vm_mm != mm))
+			break;
+		if (vma->vm_start <= addr && vma->vm_end > addr) {
+			count_vm_vmacache_event(VMACACHE_FIND_HITS);
+			return vma;
+		}
+	}
+
+	return NULL;
+}
+
+#ifndef CONFIG_MMU
+struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm,
+					   unsigned long start,
+					   unsigned long end)
+{
+	int i;
+
+	if (!vmacache_valid(mm))
+		return NULL;
+
+	count_vm_vmacache_event(VMACACHE_FIND_CALLS);
+
+	for (i = 0; i < VMACACHE_SIZE; i++) {
+		struct vm_area_struct *vma = current->vmacache[i];
+
+		if (vma && vma->vm_start == start && vma->vm_end == end) {
+			count_vm_vmacache_event(VMACACHE_FIND_HITS);
+			return vma;
+		}
+	}
+
+	return NULL;
+}
+#endif

mm/vmpressure.c

@@ -0,0 +1,382 @@
+/*
+ * Linux VM pressure
+ *
+ * Copyright 2012 Linaro Ltd.
+ *		  Anton Vorontsov <anton.vorontsov@linaro.org>
+ *
+ * Based on ideas from Andrew Morton, David Rientjes, KOSAKI Motohiro,
+ * Leonid Moiseichuk, Mel Gorman, Minchan Kim and Pekka Enberg.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include <linux/cgroup.h>
+#include <linux/fs.h>
+#include <linux/log2.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/vmstat.h>
+#include <linux/eventfd.h>
+#include <linux/slab.h>
+#include <linux/swap.h>
+#include <linux/printk.h>
+#include <linux/vmpressure.h>
+
+/*
+ * The window size (vmpressure_win) is the number of scanned pages before
+ * we try to analyze scanned/reclaimed ratio. So the window is used as a
+ * rate-limit tunable for the "low" level notification, and also for
+ * averaging the ratio for medium/critical levels. Using small window
+ * sizes can cause lot of false positives, but too big window size will
+ * delay the notifications.
+ *
+ * As the vmscan reclaimer logic works with chunks which are multiple of
+ * SWAP_CLUSTER_MAX, it makes sense to use it for the window size as well.
+ *
+ * TODO: Make the window size depend on machine size, as we do for vmstat
+ * thresholds. Currently we set it to 512 pages (2MB for 4KB pages).
+ */
+static const unsigned long vmpressure_win = SWAP_CLUSTER_MAX * 16;
+
+/*
+ * These thresholds are used when we account memory pressure through
+ * scanned/reclaimed ratio. The current values were chosen empirically. In
+ * essence, they are percents: the higher the value, the more number
+ * unsuccessful reclaims there were.
+ */
+static const unsigned int vmpressure_level_med = 60;
+static const unsigned int vmpressure_level_critical = 95;
+
+/*
+ * When there are too little pages left to scan, vmpressure() may miss the
+ * critical pressure as number of pages will be less than "window size".
+ * However, in that case the vmscan priority will raise fast as the
+ * reclaimer will try to scan LRUs more deeply.
+ *
+ * The vmscan logic considers these special priorities:
+ *
+ * prio == DEF_PRIORITY (12): reclaimer starts with that value
+ * prio <= DEF_PRIORITY - 2 : kswapd becomes somewhat overwhelmed
+ * prio == 0                : close to OOM, kernel scans every page in an lru
+ *
+ * Any value in this range is acceptable for this tunable (i.e. from 12 to
+ * 0). Current value for the vmpressure_level_critical_prio is chosen
+ * empirically, but the number, in essence, means that we consider
+ * critical level when scanning depth is ~10% of the lru size (vmscan
+ * scans 'lru_size >> prio' pages, so it is actually 12.5%, or one
+ * eights).
+ */
+static const unsigned int vmpressure_level_critical_prio = ilog2(100 / 10);
+
+static struct vmpressure *work_to_vmpressure(struct work_struct *work)
+{
+	return container_of(work, struct vmpressure, work);
+}
+
+static struct vmpressure *vmpressure_parent(struct vmpressure *vmpr)
+{
+	struct cgroup_subsys_state *css = vmpressure_to_css(vmpr);
+	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+
+	memcg = parent_mem_cgroup(memcg);
+	if (!memcg)
+		return NULL;
+	return memcg_to_vmpressure(memcg);
+}
+
+enum vmpressure_levels {
+	VMPRESSURE_LOW = 0,
+	VMPRESSURE_MEDIUM,
+	VMPRESSURE_CRITICAL,
+	VMPRESSURE_NUM_LEVELS,
+};
+
+static const char * const vmpressure_str_levels[] = {
+	[VMPRESSURE_LOW] = "low",
+	[VMPRESSURE_MEDIUM] = "medium",
+	[VMPRESSURE_CRITICAL] = "critical",
+};
+
+static enum vmpressure_levels vmpressure_level(unsigned long pressure)
+{
+	if (pressure >= vmpressure_level_critical)
+		return VMPRESSURE_CRITICAL;
+	else if (pressure >= vmpressure_level_med)
+		return VMPRESSURE_MEDIUM;
+	return VMPRESSURE_LOW;
+}
+
+static enum vmpressure_levels vmpressure_calc_level(unsigned long scanned,
+						    unsigned long reclaimed)
+{
+	unsigned long scale = scanned + reclaimed;
+	unsigned long pressure;
+
+	/*
+	 * We calculate the ratio (in percents) of how many pages were
+	 * scanned vs. reclaimed in a given time frame (window). Note that
+	 * time is in VM reclaimer's "ticks", i.e. number of pages
+	 * scanned. This makes it possible to set desired reaction time
+	 * and serves as a ratelimit.
+	 */
+	pressure = scale - (reclaimed * scale / scanned);
+	pressure = pressure * 100 / scale;
+
+	pr_debug("%s: %3lu  (s: %lu  r: %lu)\n", __func__, pressure,
+		 scanned, reclaimed);
+
+	return vmpressure_level(pressure);
+}
+
+struct vmpressure_event {
+	struct eventfd_ctx *efd;
+	enum vmpressure_levels level;
+	struct list_head node;
+};
+
+static bool vmpressure_event(struct vmpressure *vmpr,
+			     unsigned long scanned, unsigned long reclaimed)
+{
+	struct vmpressure_event *ev;
+	enum vmpressure_levels level;
+	bool signalled = false;
+
+	level = vmpressure_calc_level(scanned, reclaimed);
+
+	mutex_lock(&vmpr->events_lock);
+
+	list_for_each_entry(ev, &vmpr->events, node) {
+		if (level >= ev->level) {
+			eventfd_signal(ev->efd, 1);
+			signalled = true;
+		}
+	}
+
+	mutex_unlock(&vmpr->events_lock);
+
+	return signalled;
+}
+
+static void vmpressure_work_fn(struct work_struct *work)
+{
+	struct vmpressure *vmpr = work_to_vmpressure(work);
+	unsigned long scanned;
+	unsigned long reclaimed;
+
+	spin_lock(&vmpr->sr_lock);
+	/*
+	 * Several contexts might be calling vmpressure(), so it is
+	 * possible that the work was rescheduled again before the old
+	 * work context cleared the counters. In that case we will run
+	 * just after the old work returns, but then scanned might be zero
+	 * here. No need for any locks here since we don't care if
+	 * vmpr->reclaimed is in sync.
+	 */
+	scanned = vmpr->scanned;
+	if (!scanned) {
+		spin_unlock(&vmpr->sr_lock);
+		return;
+	}
+
+	reclaimed = vmpr->reclaimed;
+	vmpr->scanned = 0;
+	vmpr->reclaimed = 0;
+	spin_unlock(&vmpr->sr_lock);
+
+	do {
+		if (vmpressure_event(vmpr, scanned, reclaimed))
+			break;
+		/*
+		 * If not handled, propagate the event upward into the
+		 * hierarchy.
+		 */
+	} while ((vmpr = vmpressure_parent(vmpr)));
+}
+
+/**
+ * vmpressure() - Account memory pressure through scanned/reclaimed ratio
+ * @gfp:	reclaimer's gfp mask
+ * @memcg:	cgroup memory controller handle
+ * @scanned:	number of pages scanned
+ * @reclaimed:	number of pages reclaimed
+ *
+ * This function should be called from the vmscan reclaim path to account
+ * "instantaneous" memory pressure (scanned/reclaimed ratio). The raw
+ * pressure index is then further refined and averaged over time.
+ *
+ * This function does not return any value.
+ */
+void vmpressure(gfp_t gfp, struct mem_cgroup *memcg,
+		unsigned long scanned, unsigned long reclaimed)
+{
+	struct vmpressure *vmpr = memcg_to_vmpressure(memcg);
+
+	/*
+	 * Here we only want to account pressure that userland is able to
+	 * help us with. For example, suppose that DMA zone is under
+	 * pressure; if we notify userland about that kind of pressure,
+	 * then it will be mostly a waste as it will trigger unnecessary
+	 * freeing of memory by userland (since userland is more likely to
+	 * have HIGHMEM/MOVABLE pages instead of the DMA fallback). That
+	 * is why we include only movable, highmem and FS/IO pages.
+	 * Indirect reclaim (kswapd) sets sc->gfp_mask to GFP_KERNEL, so
+	 * we account it too.
+	 */
+	if (!(gfp & (__GFP_HIGHMEM | __GFP_MOVABLE | __GFP_IO | __GFP_FS)))
+		return;
+
+	/*
+	 * If we got here with no pages scanned, then that is an indicator
+	 * that reclaimer was unable to find any shrinkable LRUs at the
+	 * current scanning depth. But it does not mean that we should
+	 * report the critical pressure, yet. If the scanning priority
+	 * (scanning depth) goes too high (deep), we will be notified
+	 * through vmpressure_prio(). But so far, keep calm.
+	 */
+	if (!scanned)
+		return;
+
+	spin_lock(&vmpr->sr_lock);
+	vmpr->scanned += scanned;
+	vmpr->reclaimed += reclaimed;
+	scanned = vmpr->scanned;
+	spin_unlock(&vmpr->sr_lock);
+
+	if (scanned < vmpressure_win)
+		return;
+	schedule_work(&vmpr->work);
+}
+
+/**
+ * vmpressure_prio() - Account memory pressure through reclaimer priority level
+ * @gfp:	reclaimer's gfp mask
+ * @memcg:	cgroup memory controller handle
+ * @prio:	reclaimer's priority
+ *
+ * This function should be called from the reclaim path every time when
+ * the vmscan's reclaiming priority (scanning depth) changes.
+ *
+ * This function does not return any value.
+ */
+void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg, int prio)
+{
+	/*
+	 * We only use prio for accounting critical level. For more info
+	 * see comment for vmpressure_level_critical_prio variable above.
+	 */
+	if (prio > vmpressure_level_critical_prio)
+		return;
+
+	/*
+	 * OK, the prio is below the threshold, updating vmpressure
+	 * information before shrinker dives into long shrinking of long
+	 * range vmscan. Passing scanned = vmpressure_win, reclaimed = 0
+	 * to the vmpressure() basically means that we signal 'critical'
+	 * level.
+	 */
+	vmpressure(gfp, memcg, vmpressure_win, 0);
+}
+
+/**
+ * vmpressure_register_event() - Bind vmpressure notifications to an eventfd
+ * @memcg:	memcg that is interested in vmpressure notifications
+ * @eventfd:	eventfd context to link notifications with
+ * @args:	event arguments (used to set up a pressure level threshold)
+ *
+ * This function associates eventfd context with the vmpressure
+ * infrastructure, so that the notifications will be delivered to the
+ * @eventfd. The @args parameter is a string that denotes pressure level
+ * threshold (one of vmpressure_str_levels, i.e. "low", "medium", or
+ * "critical").
+ *
+ * To be used as memcg event method.
+ */
+int vmpressure_register_event(struct mem_cgroup *memcg,
+			      struct eventfd_ctx *eventfd, const char *args)
+{
+	struct vmpressure *vmpr = memcg_to_vmpressure(memcg);
+	struct vmpressure_event *ev;
+	int level;
+
+	for (level = 0; level < VMPRESSURE_NUM_LEVELS; level++) {
+		if (!strcmp(vmpressure_str_levels[level], args))
+			break;
+	}
+
+	if (level >= VMPRESSURE_NUM_LEVELS)
+		return -EINVAL;
+
+	ev = kzalloc(sizeof(*ev), GFP_KERNEL);
+	if (!ev)
+		return -ENOMEM;
+
+	ev->efd = eventfd;
+	ev->level = level;
+
+	mutex_lock(&vmpr->events_lock);
+	list_add(&ev->node, &vmpr->events);
+	mutex_unlock(&vmpr->events_lock);
+
+	return 0;
+}
+
+/**
+ * vmpressure_unregister_event() - Unbind eventfd from vmpressure
+ * @memcg:	memcg handle
+ * @eventfd:	eventfd context that was used to link vmpressure with the @cg
+ *
+ * This function does internal manipulations to detach the @eventfd from
+ * the vmpressure notifications, and then frees internal resources
+ * associated with the @eventfd (but the @eventfd itself is not freed).
+ *
+ * To be used as memcg event method.
+ */
+void vmpressure_unregister_event(struct mem_cgroup *memcg,
+				 struct eventfd_ctx *eventfd)
+{
+	struct vmpressure *vmpr = memcg_to_vmpressure(memcg);
+	struct vmpressure_event *ev;
+
+	mutex_lock(&vmpr->events_lock);
+	list_for_each_entry(ev, &vmpr->events, node) {
+		if (ev->efd != eventfd)
+			continue;
+		list_del(&ev->node);
+		kfree(ev);
+		break;
+	}
+	mutex_unlock(&vmpr->events_lock);
+}
+
+/**
+ * vmpressure_init() - Initialize vmpressure control structure
+ * @vmpr:	Structure to be initialized
+ *
+ * This function should be called on every allocated vmpressure structure
+ * before any usage.
+ */
+void vmpressure_init(struct vmpressure *vmpr)
+{
+	spin_lock_init(&vmpr->sr_lock);
+	mutex_init(&vmpr->events_lock);
+	INIT_LIST_HEAD(&vmpr->events);
+	INIT_WORK(&vmpr->work, vmpressure_work_fn);
+}
+
+/**
+ * vmpressure_cleanup() - shuts down vmpressure control structure
+ * @vmpr:	Structure to be cleaned up
+ *
+ * This function should be called before the structure in which it is
+ * embedded is cleaned up.
+ */
+void vmpressure_cleanup(struct vmpressure *vmpr)
+{
+	/*
+	 * Make sure there is no pending work before eventfd infrastructure
+	 * goes away.
+	 */
+	flush_work(&vmpr->work);
+}

mm/workingset.c

@@ -0,0 +1,414 @@
+/*
+ * Workingset detection
+ *
+ * Copyright (C) 2013 Red Hat, Inc., Johannes Weiner
+ */
+
+#include <linux/memcontrol.h>
+#include <linux/writeback.h>
+#include <linux/pagemap.h>
+#include <linux/atomic.h>
+#include <linux/module.h>
+#include <linux/swap.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+
+/*
+ *		Double CLOCK lists
+ *
+ * Per zone, two clock lists are maintained for file pages: the
+ * inactive and the active list.  Freshly faulted pages start out at
+ * the head of the inactive list and page reclaim scans pages from the
+ * tail.  Pages that are accessed multiple times on the inactive list
+ * are promoted to the active list, to protect them from reclaim,
+ * whereas active pages are demoted to the inactive list when the
+ * active list grows too big.
+ *
+ *   fault ------------------------+
+ *                                 |
+ *              +--------------+   |            +-------------+
+ *   reclaim <- |   inactive   | <-+-- demotion |    active   | <--+
+ *              +--------------+                +-------------+    |
+ *                     |                                           |
+ *                     +-------------- promotion ------------------+
+ *
+ *
+ *		Access frequency and refault distance
+ *
+ * A workload is thrashing when its pages are frequently used but they
+ * are evicted from the inactive list every time before another access
+ * would have promoted them to the active list.
+ *
+ * In cases where the average access distance between thrashing pages
+ * is bigger than the size of memory there is nothing that can be
+ * done - the thrashing set could never fit into memory under any
+ * circumstance.
+ *
+ * However, the average access distance could be bigger than the
+ * inactive list, yet smaller than the size of memory.  In this case,
+ * the set could fit into memory if it weren't for the currently
+ * active pages - which may be used more, hopefully less frequently:
+ *
+ *      +-memory available to cache-+
+ *      |                           |
+ *      +-inactive------+-active----+
+ *  a b | c d e f g h i | J K L M N |
+ *      +---------------+-----------+
+ *
+ * It is prohibitively expensive to accurately track access frequency
+ * of pages.  But a reasonable approximation can be made to measure
+ * thrashing on the inactive list, after which refaulting pages can be
+ * activated optimistically to compete with the existing active pages.
+ *
+ * Approximating inactive page access frequency - Observations:
+ *
+ * 1. When a page is accessed for the first time, it is added to the
+ *    head of the inactive list, slides every existing inactive page
+ *    towards the tail by one slot, and pushes the current tail page
+ *    out of memory.
+ *
+ * 2. When a page is accessed for the second time, it is promoted to
+ *    the active list, shrinking the inactive list by one slot.  This
+ *    also slides all inactive pages that were faulted into the cache
+ *    more recently than the activated page towards the tail of the
+ *    inactive list.
+ *
+ * Thus:
+ *
+ * 1. The sum of evictions and activations between any two points in
+ *    time indicate the minimum number of inactive pages accessed in
+ *    between.
+ *
+ * 2. Moving one inactive page N page slots towards the tail of the
+ *    list requires at least N inactive page accesses.
+ *
+ * Combining these:
+ *
+ * 1. When a page is finally evicted from memory, the number of
+ *    inactive pages accessed while the page was in cache is at least
+ *    the number of page slots on the inactive list.
+ *
+ * 2. In addition, measuring the sum of evictions and activations (E)
+ *    at the time of a page's eviction, and comparing it to another
+ *    reading (R) at the time the page faults back into memory tells
+ *    the minimum number of accesses while the page was not cached.
+ *    This is called the refault distance.
+ *
+ * Because the first access of the page was the fault and the second
+ * access the refault, we combine the in-cache distance with the
+ * out-of-cache distance to get the complete minimum access distance
+ * of this page:
+ *
+ *      NR_inactive + (R - E)
+ *
+ * And knowing the minimum access distance of a page, we can easily
+ * tell if the page would be able to stay in cache assuming all page
+ * slots in the cache were available:
+ *
+ *   NR_inactive + (R - E) <= NR_inactive + NR_active
+ *
+ * which can be further simplified to
+ *
+ *   (R - E) <= NR_active
+ *
+ * Put into words, the refault distance (out-of-cache) can be seen as
+ * a deficit in inactive list space (in-cache).  If the inactive list
+ * had (R - E) more page slots, the page would not have been evicted
+ * in between accesses, but activated instead.  And on a full system,
+ * the only thing eating into inactive list space is active pages.
+ *
+ *
+ *		Activating refaulting pages
+ *
+ * All that is known about the active list is that the pages have been
+ * accessed more than once in the past.  This means that at any given
+ * time there is actually a good chance that pages on the active list
+ * are no longer in active use.
+ *
+ * So when a refault distance of (R - E) is observed and there are at
+ * least (R - E) active pages, the refaulting page is activated
+ * optimistically in the hope that (R - E) active pages are actually
+ * used less frequently than the refaulting page - or even not used at
+ * all anymore.
+ *
+ * If this is wrong and demotion kicks in, the pages which are truly
+ * used more frequently will be reactivated while the less frequently
+ * used once will be evicted from memory.
+ *
+ * But if this is right, the stale pages will be pushed out of memory
+ * and the used pages get to stay in cache.
+ *
+ *
+ *		Implementation
+ *
+ * For each zone's file LRU lists, a counter for inactive evictions
+ * and activations is maintained (zone->inactive_age).
+ *
+ * On eviction, a snapshot of this counter (along with some bits to
+ * identify the zone) is stored in the now empty page cache radix tree
+ * slot of the evicted page.  This is called a shadow entry.
+ *
+ * On cache misses for which there are shadow entries, an eligible
+ * refault distance will immediately activate the refaulting page.
+ */
+
+static void *pack_shadow(unsigned long eviction, struct zone *zone)
+{
+	eviction = (eviction << NODES_SHIFT) | zone_to_nid(zone);
+	eviction = (eviction << ZONES_SHIFT) | zone_idx(zone);
+	eviction = (eviction << RADIX_TREE_EXCEPTIONAL_SHIFT);
+
+	return (void *)(eviction | RADIX_TREE_EXCEPTIONAL_ENTRY);
+}
+
+static void unpack_shadow(void *shadow,
+			  struct zone **zone,
+			  unsigned long *distance)
+{
+	unsigned long entry = (unsigned long)shadow;
+	unsigned long eviction;
+	unsigned long refault;
+	unsigned long mask;
+	int zid, nid;
+
+	entry >>= RADIX_TREE_EXCEPTIONAL_SHIFT;
+	zid = entry & ((1UL << ZONES_SHIFT) - 1);
+	entry >>= ZONES_SHIFT;
+	nid = entry & ((1UL << NODES_SHIFT) - 1);
+	entry >>= NODES_SHIFT;
+	eviction = entry;
+
+	*zone = NODE_DATA(nid)->node_zones + zid;
+
+	refault = atomic_long_read(&(*zone)->inactive_age);
+	mask = ~0UL >> (NODES_SHIFT + ZONES_SHIFT +
+			RADIX_TREE_EXCEPTIONAL_SHIFT);
+	/*
+	 * The unsigned subtraction here gives an accurate distance
+	 * across inactive_age overflows in most cases.
+	 *
+	 * There is a special case: usually, shadow entries have a
+	 * short lifetime and are either refaulted or reclaimed along
+	 * with the inode before they get too old.  But it is not
+	 * impossible for the inactive_age to lap a shadow entry in
+	 * the field, which can then can result in a false small
+	 * refault distance, leading to a false activation should this
+	 * old entry actually refault again.  However, earlier kernels
+	 * used to deactivate unconditionally with *every* reclaim
+	 * invocation for the longest time, so the occasional
+	 * inappropriate activation leading to pressure on the active
+	 * list is not a problem.
+	 */
+	*distance = (refault - eviction) & mask;
+}
+
+/**
+ * workingset_eviction - note the eviction of a page from memory
+ * @mapping: address space the page was backing
+ * @page: the page being evicted
+ *
+ * Returns a shadow entry to be stored in @mapping->page_tree in place
+ * of the evicted @page so that a later refault can be detected.
+ */
+void *workingset_eviction(struct address_space *mapping, struct page *page)
+{
+	struct zone *zone = page_zone(page);
+	unsigned long eviction;
+
+	eviction = atomic_long_inc_return(&zone->inactive_age);
+	return pack_shadow(eviction, zone);
+}
+
+/**
+ * workingset_refault - evaluate the refault of a previously evicted page
+ * @shadow: shadow entry of the evicted page
+ *
+ * Calculates and evaluates the refault distance of the previously
+ * evicted page in the context of the zone it was allocated in.
+ *
+ * Returns %true if the page should be activated, %false otherwise.
+ */
+bool workingset_refault(void *shadow)
+{
+	unsigned long refault_distance;
+	struct zone *zone;
+
+	unpack_shadow(shadow, &zone, &refault_distance);
+	inc_zone_state(zone, WORKINGSET_REFAULT);
+
+	if (refault_distance <= zone_page_state(zone, NR_ACTIVE_FILE)) {
+		inc_zone_state(zone, WORKINGSET_ACTIVATE);
+		return true;
+	}
+	return false;
+}
+
+/**
+ * workingset_activation - note a page activation
+ * @page: page that is being activated
+ */
+void workingset_activation(struct page *page)
+{
+	atomic_long_inc(&page_zone(page)->inactive_age);
+}
+
+/*
+ * Shadow entries reflect the share of the working set that does not
+ * fit into memory, so their number depends on the access pattern of
+ * the workload.  In most cases, they will refault or get reclaimed
+ * along with the inode, but a (malicious) workload that streams
+ * through files with a total size several times that of available
+ * memory, while preventing the inodes from being reclaimed, can
+ * create excessive amounts of shadow nodes.  To keep a lid on this,
+ * track shadow nodes and reclaim them when they grow way past the
+ * point where they would still be useful.
+ */
+
+struct list_lru workingset_shadow_nodes;
+
+static unsigned long count_shadow_nodes(struct shrinker *shrinker,
+					struct shrink_control *sc)
+{
+	unsigned long shadow_nodes;
+	unsigned long max_nodes;
+	unsigned long pages;
+
+	/* list_lru lock nests inside IRQ-safe mapping->tree_lock */
+	local_irq_disable();
+	shadow_nodes = list_lru_count_node(&workingset_shadow_nodes, sc->nid);
+	local_irq_enable();
+
+	pages = node_present_pages(sc->nid);
+	/*
+	 * Active cache pages are limited to 50% of memory, and shadow
+	 * entries that represent a refault distance bigger than that
+	 * do not have any effect.  Limit the number of shadow nodes
+	 * such that shadow entries do not exceed the number of active
+	 * cache pages, assuming a worst-case node population density
+	 * of 1/8th on average.
+	 *
+	 * On 64-bit with 7 radix_tree_nodes per page and 64 slots
+	 * each, this will reclaim shadow entries when they consume
+	 * ~2% of available memory:
+	 *
+	 * PAGE_SIZE / radix_tree_nodes / node_entries / PAGE_SIZE
+	 */
+	max_nodes = pages >> (1 + RADIX_TREE_MAP_SHIFT - 3);
+
+	if (shadow_nodes <= max_nodes)
+		return 0;
+
+	return shadow_nodes - max_nodes;
+}
+
+static enum lru_status shadow_lru_isolate(struct list_head *item,
+					  spinlock_t *lru_lock,
+					  void *arg)
+{
+	struct address_space *mapping;
+	struct radix_tree_node *node;
+	unsigned int i;
+	int ret;
+
+	/*
+	 * Page cache insertions and deletions synchroneously maintain
+	 * the shadow node LRU under the mapping->tree_lock and the
+	 * lru_lock.  Because the page cache tree is emptied before
+	 * the inode can be destroyed, holding the lru_lock pins any
+	 * address_space that has radix tree nodes on the LRU.
+	 *
+	 * We can then safely transition to the mapping->tree_lock to
+	 * pin only the address_space of the particular node we want
+	 * to reclaim, take the node off-LRU, and drop the lru_lock.
+	 */
+
+	node = container_of(item, struct radix_tree_node, private_list);
+	mapping = node->private_data;
+
+	/* Coming from the list, invert the lock order */
+	if (!spin_trylock(&mapping->tree_lock)) {
+		spin_unlock(lru_lock);
+		ret = LRU_RETRY;
+		goto out;
+	}
+
+	list_del_init(item);
+	spin_unlock(lru_lock);
+
+	/*
+	 * The nodes should only contain one or more shadow entries,
+	 * no pages, so we expect to be able to remove them all and
+	 * delete and free the empty node afterwards.
+	 */
+
+	BUG_ON(!node->count);
+	BUG_ON(node->count & RADIX_TREE_COUNT_MASK);
+
+	for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) {
+		if (node->slots[i]) {
+			BUG_ON(!radix_tree_exceptional_entry(node->slots[i]));
+			node->slots[i] = NULL;
+			BUG_ON(node->count < (1U << RADIX_TREE_COUNT_SHIFT));
+			node->count -= 1U << RADIX_TREE_COUNT_SHIFT;
+			BUG_ON(!mapping->nrshadows);
+			mapping->nrshadows--;
+		}
+	}
+	BUG_ON(node->count);
+	inc_zone_state(page_zone(virt_to_page(node)), WORKINGSET_NODERECLAIM);
+	if (!__radix_tree_delete_node(&mapping->page_tree, node))
+		BUG();
+
+	spin_unlock(&mapping->tree_lock);
+	ret = LRU_REMOVED_RETRY;
+out:
+	local_irq_enable();
+	cond_resched();
+	local_irq_disable();
+	spin_lock(lru_lock);
+	return ret;
+}
+
+static unsigned long scan_shadow_nodes(struct shrinker *shrinker,
+				       struct shrink_control *sc)
+{
+	unsigned long ret;
+
+	/* list_lru lock nests inside IRQ-safe mapping->tree_lock */
+	local_irq_disable();
+	ret =  list_lru_walk_node(&workingset_shadow_nodes, sc->nid,
+				  shadow_lru_isolate, NULL, &sc->nr_to_scan);
+	local_irq_enable();
+	return ret;
+}
+
+static struct shrinker workingset_shadow_shrinker = {
+	.count_objects = count_shadow_nodes,
+	.scan_objects = scan_shadow_nodes,
+	.seeks = DEFAULT_SEEKS,
+	.flags = SHRINKER_NUMA_AWARE,
+};
+
+/*
+ * Our list_lru->lock is IRQ-safe as it nests inside the IRQ-safe
+ * mapping->tree_lock.
+ */
+static struct lock_class_key shadow_nodes_key;
+
+static int __init workingset_init(void)
+{
+	int ret;
+
+	ret = list_lru_init_key(&workingset_shadow_nodes, &shadow_nodes_key);
+	if (ret)
+		goto err;
+	ret = register_shrinker(&workingset_shadow_shrinker);
+	if (ret)
+		goto err_list_lru;
+	return 0;
+err_list_lru:
+	list_lru_destroy(&workingset_shadow_nodes);
+err:
+	return ret;
+}
+module_init(workingset_init);

mm/zbud.c

@@ -0,0 +1,636 @@
+/*
+ * zbud.c
+ *
+ * Copyright (C) 2013, Seth Jennings, IBM
+ *
+ * Concepts based on zcache internal zbud allocator by Dan Magenheimer.
+ *
+ * zbud is an special purpose allocator for storing compressed pages.  Contrary
+ * to what its name may suggest, zbud is not a buddy allocator, but rather an
+ * allocator that "buddies" two compressed pages together in a single memory
+ * page.
+ *
+ * While this design limits storage density, it has simple and deterministic
+ * reclaim properties that make it preferable to a higher density approach when
+ * reclaim will be used.
+ *
+ * zbud works by storing compressed pages, or "zpages", together in pairs in a
+ * single memory page called a "zbud page".  The first buddy is "left
+ * justified" at the beginning of the zbud page, and the last buddy is "right
+ * justified" at the end of the zbud page.  The benefit is that if either
+ * buddy is freed, the freed buddy space, coalesced with whatever slack space
+ * that existed between the buddies, results in the largest possible free region
+ * within the zbud page.
+ *
+ * zbud also provides an attractive lower bound on density. The ratio of zpages
+ * to zbud pages can not be less than 1.  This ensures that zbud can never "do
+ * harm" by using more pages to store zpages than the uncompressed zpages would
+ * have used on their own.
+ *
+ * zbud pages are divided into "chunks".  The size of the chunks is fixed at
+ * compile time and determined by NCHUNKS_ORDER below.  Dividing zbud pages
+ * into chunks allows organizing unbuddied zbud pages into a manageable number
+ * of unbuddied lists according to the number of free chunks available in the
+ * zbud page.
+ *
+ * The zbud API differs from that of conventional allocators in that the
+ * allocation function, zbud_alloc(), returns an opaque handle to the user,
+ * not a dereferenceable pointer.  The user must map the handle using
+ * zbud_map() in order to get a usable pointer by which to access the
+ * allocation data and unmap the handle with zbud_unmap() when operations
+ * on the allocation data are complete.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/atomic.h>
+#include <linux/list.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/preempt.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/zbud.h>
+#include <linux/zpool.h>
+
+/*****************
+ * Structures
+*****************/
+/*
+ * NCHUNKS_ORDER determines the internal allocation granularity, effectively
+ * adjusting internal fragmentation.  It also determines the number of
+ * freelists maintained in each pool. NCHUNKS_ORDER of 6 means that the
+ * allocation granularity will be in chunks of size PAGE_SIZE/64. As one chunk
+ * in allocated page is occupied by zbud header, NCHUNKS will be calculated to
+ * 63 which shows the max number of free chunks in zbud page, also there will be
+ * 63 freelists per pool.
+ */
+#define NCHUNKS_ORDER	6
+
+#define CHUNK_SHIFT	(PAGE_SHIFT - NCHUNKS_ORDER)
+#define CHUNK_SIZE	(1 << CHUNK_SHIFT)
+#define ZHDR_SIZE_ALIGNED CHUNK_SIZE
+#define NCHUNKS		((PAGE_SIZE - ZHDR_SIZE_ALIGNED) >> CHUNK_SHIFT)
+
+/**
+ * struct zbud_pool - stores metadata for each zbud pool
+ * @lock:	protects all pool fields and first|last_chunk fields of any
+ *		zbud page in the pool
+ * @unbuddied:	array of lists tracking zbud pages that only contain one buddy;
+ *		the lists each zbud page is added to depends on the size of
+ *		its free region.
+ * @buddied:	list tracking the zbud pages that contain two buddies;
+ *		these zbud pages are full
+ * @lru:	list tracking the zbud pages in LRU order by most recently
+ *		added buddy.
+ * @pages_nr:	number of zbud pages in the pool.
+ * @ops:	pointer to a structure of user defined operations specified at
+ *		pool creation time.
+ *
+ * This structure is allocated at pool creation time and maintains metadata
+ * pertaining to a particular zbud pool.
+ */
+struct zbud_pool {
+	spinlock_t lock;
+	struct list_head unbuddied[NCHUNKS];
+	struct list_head buddied;
+	struct list_head lru;
+	u64 pages_nr;
+	struct zbud_ops *ops;
+};
+
+/*
+ * struct zbud_header - zbud page metadata occupying the first chunk of each
+ *			zbud page.
+ * @buddy:	links the zbud page into the unbuddied/buddied lists in the pool
+ * @lru:	links the zbud page into the lru list in the pool
+ * @first_chunks:	the size of the first buddy in chunks, 0 if free
+ * @last_chunks:	the size of the last buddy in chunks, 0 if free
+ */
+struct zbud_header {
+	struct list_head buddy;
+	struct list_head lru;
+	unsigned int first_chunks;
+	unsigned int last_chunks;
+	bool under_reclaim;
+};
+
+/*****************
+ * zpool
+ ****************/
+
+#ifdef CONFIG_ZPOOL
+
+static int zbud_zpool_evict(struct zbud_pool *pool, unsigned long handle)
+{
+	return zpool_evict(pool, handle);
+}
+
+static struct zbud_ops zbud_zpool_ops = {
+	.evict =	zbud_zpool_evict
+};
+
+static void *zbud_zpool_create(char *name, gfp_t gfp,
+			struct zpool_ops *zpool_ops)
+{
+	return zbud_create_pool(gfp, zpool_ops ? &zbud_zpool_ops : NULL);
+}
+
+static void zbud_zpool_destroy(void *pool)
+{
+	zbud_destroy_pool(pool);
+}
+
+static int zbud_zpool_malloc(void *pool, size_t size, gfp_t gfp,
+			unsigned long *handle)
+{
+	return zbud_alloc(pool, size, gfp, handle);
+}
+static void zbud_zpool_free(void *pool, unsigned long handle)
+{
+	zbud_free(pool, handle);
+}
+
+static int zbud_zpool_shrink(void *pool, unsigned int pages,
+			unsigned int *reclaimed)
+{
+	unsigned int total = 0;
+	int ret = -EINVAL;
+
+	while (total < pages) {
+		ret = zbud_reclaim_page(pool, 8);
+		if (ret < 0)
+			break;
+		total++;
+	}
+
+	if (reclaimed)
+		*reclaimed = total;
+
+	return ret;
+}
+
+static void *zbud_zpool_map(void *pool, unsigned long handle,
+			enum zpool_mapmode mm)
+{
+	return zbud_map(pool, handle);
+}
+static void zbud_zpool_unmap(void *pool, unsigned long handle)
+{
+	zbud_unmap(pool, handle);
+}
+
+static u64 zbud_zpool_total_size(void *pool)
+{
+	return zbud_get_pool_size(pool) * PAGE_SIZE;
+}
+
+static unsigned long zbud_zpool_compact(void *pool)
+{
+	return 0;
+}
+
+static bool zbud_zpool_compactable(void *pool, unsigned int pages)
+{
+	return false;
+}
+
+static struct zpool_driver zbud_zpool_driver = {
+	.type =		"zbud",
+	.owner =	THIS_MODULE,
+	.create =	zbud_zpool_create,
+	.destroy =	zbud_zpool_destroy,
+	.malloc =	zbud_zpool_malloc,
+	.free =		zbud_zpool_free,
+	.shrink =	zbud_zpool_shrink,
+	.map =		zbud_zpool_map,
+	.unmap =	zbud_zpool_unmap,
+	.total_size =	zbud_zpool_total_size,
+	.compact =	zbud_zpool_compact,
+	.compactable =	zbud_zpool_compactable,
+};
+
+MODULE_ALIAS("zpool-zbud");
+#endif /* CONFIG_ZPOOL */
+
+/*****************
+ * Helpers
+*****************/
+/* Just to make the code easier to read */
+enum buddy {
+	FIRST,
+	LAST
+};
+
+/* Converts an allocation size in bytes to size in zbud chunks */
+static int size_to_chunks(size_t size)
+{
+	return (size + CHUNK_SIZE - 1) >> CHUNK_SHIFT;
+}
+
+#define for_each_unbuddied_list(_iter, _begin) \
+	for ((_iter) = (_begin); (_iter) < NCHUNKS; (_iter)++)
+
+/* Initializes the zbud header of a newly allocated zbud page */
+static struct zbud_header *init_zbud_page(struct page *page)
+{
+	struct zbud_header *zhdr = page_address(page);
+	zhdr->first_chunks = 0;
+	zhdr->last_chunks = 0;
+	INIT_LIST_HEAD(&zhdr->buddy);
+	INIT_LIST_HEAD(&zhdr->lru);
+	zhdr->under_reclaim = 0;
+	return zhdr;
+}
+
+/* Resets the struct page fields and frees the page */
+static void free_zbud_page(struct zbud_header *zhdr)
+{
+	__free_page(virt_to_page(zhdr));
+}
+
+/*
+ * Encodes the handle of a particular buddy within a zbud page
+ * Pool lock should be held as this function accesses first|last_chunks
+ */
+static unsigned long encode_handle(struct zbud_header *zhdr, enum buddy bud)
+{
+	unsigned long handle;
+
+	/*
+	 * For now, the encoded handle is actually just the pointer to the data
+	 * but this might not always be the case.  A little information hiding.
+	 * Add CHUNK_SIZE to the handle if it is the first allocation to jump
+	 * over the zbud header in the first chunk.
+	 */
+	handle = (unsigned long)zhdr;
+	if (bud == FIRST)
+		/* skip over zbud header */
+		handle += ZHDR_SIZE_ALIGNED;
+	else /* bud == LAST */
+		handle += PAGE_SIZE - (zhdr->last_chunks  << CHUNK_SHIFT);
+	return handle;
+}
+
+/* Returns the zbud page where a given handle is stored */
+static struct zbud_header *handle_to_zbud_header(unsigned long handle)
+{
+	return (struct zbud_header *)(handle & PAGE_MASK);
+}
+
+/* Returns the number of free chunks in a zbud page */
+static int num_free_chunks(struct zbud_header *zhdr)
+{
+	/*
+	 * Rather than branch for different situations, just use the fact that
+	 * free buddies have a length of zero to simplify everything.
+	 */
+	return NCHUNKS - zhdr->first_chunks - zhdr->last_chunks;
+}
+
+/*****************
+ * API Functions
+*****************/
+/**
+ * zbud_create_pool() - create a new zbud pool
+ * @gfp:	gfp flags when allocating the zbud pool structure
+ * @ops:	user-defined operations for the zbud pool
+ *
+ * Return: pointer to the new zbud pool or NULL if the metadata allocation
+ * failed.
+ */
+struct zbud_pool *zbud_create_pool(gfp_t gfp, struct zbud_ops *ops)
+{
+	struct zbud_pool *pool;
+	int i;
+
+	pool = kmalloc(sizeof(struct zbud_pool), gfp);
+	if (!pool)
+		return NULL;
+	spin_lock_init(&pool->lock);
+	for_each_unbuddied_list(i, 0)
+		INIT_LIST_HEAD(&pool->unbuddied[i]);
+	INIT_LIST_HEAD(&pool->buddied);
+	INIT_LIST_HEAD(&pool->lru);
+	pool->pages_nr = 0;
+	pool->ops = ops;
+	return pool;
+}
+
+/**
+ * zbud_destroy_pool() - destroys an existing zbud pool
+ * @pool:	the zbud pool to be destroyed
+ *
+ * The pool should be emptied before this function is called.
+ */
+void zbud_destroy_pool(struct zbud_pool *pool)
+{
+	kfree(pool);
+}
+
+/**
+ * zbud_alloc() - allocates a region of a given size
+ * @pool:	zbud pool from which to allocate
+ * @size:	size in bytes of the desired allocation
+ * @gfp:	gfp flags used if the pool needs to grow
+ * @handle:	handle of the new allocation
+ *
+ * This function will attempt to find a free region in the pool large enough to
+ * satisfy the allocation request.  A search of the unbuddied lists is
+ * performed first. If no suitable free region is found, then a new page is
+ * allocated and added to the pool to satisfy the request.
+ *
+ * gfp should not set __GFP_HIGHMEM as highmem pages cannot be used
+ * as zbud pool pages.
+ *
+ * Return: 0 if success and handle is set, otherwise -EINVAL if the size or
+ * gfp arguments are invalid or -ENOMEM if the pool was unable to allocate
+ * a new page.
+ */
+int zbud_alloc(struct zbud_pool *pool, size_t size, gfp_t gfp,
+			unsigned long *handle)
+{
+	int chunks, i, freechunks;
+	struct zbud_header *zhdr = NULL;
+	enum buddy bud;
+	struct page *page;
+
+	if (!size || (gfp & __GFP_HIGHMEM))
+		return -EINVAL;
+	if (size > PAGE_SIZE - ZHDR_SIZE_ALIGNED - CHUNK_SIZE)
+		return -ENOSPC;
+	chunks = size_to_chunks(size);
+	spin_lock(&pool->lock);
+
+	/* First, try to find an unbuddied zbud page. */
+	zhdr = NULL;
+	for_each_unbuddied_list(i, chunks) {
+		if (!list_empty(&pool->unbuddied[i])) {
+			zhdr = list_first_entry(&pool->unbuddied[i],
+					struct zbud_header, buddy);
+			list_del(&zhdr->buddy);
+			if (zhdr->first_chunks == 0)
+				bud = FIRST;
+			else
+				bud = LAST;
+			goto found;
+		}
+	}
+
+	/* Couldn't find unbuddied zbud page, create new one */
+	spin_unlock(&pool->lock);
+	page = alloc_page(gfp);
+	if (!page)
+		return -ENOMEM;
+	spin_lock(&pool->lock);
+	pool->pages_nr++;
+	zhdr = init_zbud_page(page);
+	bud = FIRST;
+
+found:
+	if (bud == FIRST)
+		zhdr->first_chunks = chunks;
+	else
+		zhdr->last_chunks = chunks;
+
+	if (zhdr->first_chunks == 0 || zhdr->last_chunks == 0) {
+		/* Add to unbuddied list */
+		freechunks = num_free_chunks(zhdr);
+		list_add(&zhdr->buddy, &pool->unbuddied[freechunks]);
+	} else {
+		/* Add to buddied list */
+		list_add(&zhdr->buddy, &pool->buddied);
+	}
+
+	/* Add/move zbud page to beginning of LRU */
+	if (!list_empty(&zhdr->lru))
+		list_del(&zhdr->lru);
+	list_add(&zhdr->lru, &pool->lru);
+
+	*handle = encode_handle(zhdr, bud);
+	spin_unlock(&pool->lock);
+
+	return 0;
+}
+
+/**
+ * zbud_free() - frees the allocation associated with the given handle
+ * @pool:	pool in which the allocation resided
+ * @handle:	handle associated with the allocation returned by zbud_alloc()
+ *
+ * In the case that the zbud page in which the allocation resides is under
+ * reclaim, as indicated by the PG_reclaim flag being set, this function
+ * only sets the first|last_chunks to 0.  The page is actually freed
+ * once both buddies are evicted (see zbud_reclaim_page() below).
+ */
+void zbud_free(struct zbud_pool *pool, unsigned long handle)
+{
+	struct zbud_header *zhdr;
+	int freechunks;
+
+	spin_lock(&pool->lock);
+	zhdr = handle_to_zbud_header(handle);
+
+	/* If first buddy, handle will be page aligned */
+	if ((handle - ZHDR_SIZE_ALIGNED) & ~PAGE_MASK)
+		zhdr->last_chunks = 0;
+	else
+		zhdr->first_chunks = 0;
+
+	if (zhdr->under_reclaim) {
+		/* zbud page is under reclaim, reclaim will free */
+		spin_unlock(&pool->lock);
+		return;
+	}
+
+	/* Remove from existing buddy list */
+	list_del(&zhdr->buddy);
+
+	if (zhdr->first_chunks == 0 && zhdr->last_chunks == 0) {
+		/* zbud page is empty, free */
+		list_del(&zhdr->lru);
+		free_zbud_page(zhdr);
+		pool->pages_nr--;
+	} else {
+		/* Add to unbuddied list */
+		freechunks = num_free_chunks(zhdr);
+		list_add(&zhdr->buddy, &pool->unbuddied[freechunks]);
+	}
+
+	spin_unlock(&pool->lock);
+}
+
+#define list_tail_entry(ptr, type, member) \
+	list_entry((ptr)->prev, type, member)
+
+/**
+ * zbud_reclaim_page() - evicts allocations from a pool page and frees it
+ * @pool:	pool from which a page will attempt to be evicted
+ * @retires:	number of pages on the LRU list for which eviction will
+ *		be attempted before failing
+ *
+ * zbud reclaim is different from normal system reclaim in that the reclaim is
+ * done from the bottom, up.  This is because only the bottom layer, zbud, has
+ * information on how the allocations are organized within each zbud page. This
+ * has the potential to create interesting locking situations between zbud and
+ * the user, however.
+ *
+ * To avoid these, this is how zbud_reclaim_page() should be called:
+
+ * The user detects a page should be reclaimed and calls zbud_reclaim_page().
+ * zbud_reclaim_page() will remove a zbud page from the pool LRU list and call
+ * the user-defined eviction handler with the pool and handle as arguments.
+ *
+ * If the handle can not be evicted, the eviction handler should return
+ * non-zero. zbud_reclaim_page() will add the zbud page back to the
+ * appropriate list and try the next zbud page on the LRU up to
+ * a user defined number of retries.
+ *
+ * If the handle is successfully evicted, the eviction handler should
+ * return 0 _and_ should have called zbud_free() on the handle. zbud_free()
+ * contains logic to delay freeing the page if the page is under reclaim,
+ * as indicated by the setting of the PG_reclaim flag on the underlying page.
+ *
+ * If all buddies in the zbud page are successfully evicted, then the
+ * zbud page can be freed.
+ *
+ * Returns: 0 if page is successfully freed, otherwise -EINVAL if there are
+ * no pages to evict or an eviction handler is not registered, -EAGAIN if
+ * the retry limit was hit.
+ */
+int zbud_reclaim_page(struct zbud_pool *pool, unsigned int retries)
+{
+	int i, ret, freechunks;
+	struct zbud_header *zhdr;
+	unsigned long first_handle = 0, last_handle = 0;
+
+	spin_lock(&pool->lock);
+	if (!pool->ops || !pool->ops->evict || list_empty(&pool->lru) ||
+			retries == 0) {
+		spin_unlock(&pool->lock);
+		return -EINVAL;
+	}
+	for (i = 0; i < retries; i++) {
+		zhdr = list_tail_entry(&pool->lru, struct zbud_header, lru);
+		list_del(&zhdr->lru);
+		list_del(&zhdr->buddy);
+		/* Protect zbud page against free */
+		zhdr->under_reclaim = true;
+		/*
+		 * We need encode the handles before unlocking, since we can
+		 * race with free that will set (first|last)_chunks to 0
+		 */
+		first_handle = 0;
+		last_handle = 0;
+		if (zhdr->first_chunks)
+			first_handle = encode_handle(zhdr, FIRST);
+		if (zhdr->last_chunks)
+			last_handle = encode_handle(zhdr, LAST);
+		spin_unlock(&pool->lock);
+
+		/* Issue the eviction callback(s) */
+		if (first_handle) {
+			ret = pool->ops->evict(pool, first_handle);
+			if (ret)
+				goto next;
+		}
+		if (last_handle) {
+			ret = pool->ops->evict(pool, last_handle);
+			if (ret)
+				goto next;
+		}
+next:
+		spin_lock(&pool->lock);
+		zhdr->under_reclaim = false;
+		if (zhdr->first_chunks == 0 && zhdr->last_chunks == 0) {
+			/*
+			 * Both buddies are now free, free the zbud page and
+			 * return success.
+			 */
+			free_zbud_page(zhdr);
+			pool->pages_nr--;
+			spin_unlock(&pool->lock);
+			return 0;
+		} else if (zhdr->first_chunks == 0 ||
+				zhdr->last_chunks == 0) {
+			/* add to unbuddied list */
+			freechunks = num_free_chunks(zhdr);
+			list_add(&zhdr->buddy, &pool->unbuddied[freechunks]);
+		} else {
+			/* add to buddied list */
+			list_add(&zhdr->buddy, &pool->buddied);
+		}
+
+		/* add to beginning of LRU */
+		list_add(&zhdr->lru, &pool->lru);
+	}
+	spin_unlock(&pool->lock);
+	return -EAGAIN;
+}
+
+/**
+ * zbud_map() - maps the allocation associated with the given handle
+ * @pool:	pool in which the allocation resides
+ * @handle:	handle associated with the allocation to be mapped
+ *
+ * While trivial for zbud, the mapping functions for others allocators
+ * implementing this allocation API could have more complex information encoded
+ * in the handle and could create temporary mappings to make the data
+ * accessible to the user.
+ *
+ * Returns: a pointer to the mapped allocation
+ */
+void *zbud_map(struct zbud_pool *pool, unsigned long handle)
+{
+	return (void *)(handle);
+}
+
+/**
+ * zbud_unmap() - maps the allocation associated with the given handle
+ * @pool:	pool in which the allocation resides
+ * @handle:	handle associated with the allocation to be unmapped
+ */
+void zbud_unmap(struct zbud_pool *pool, unsigned long handle)
+{
+}
+
+/**
+ * zbud_get_pool_size() - gets the zbud pool size in pages
+ * @pool:	pool whose size is being queried
+ *
+ * Returns: size in pages of the given pool.  The pool lock need not be
+ * taken to access pages_nr.
+ */
+u64 zbud_get_pool_size(struct zbud_pool *pool)
+{
+	return pool->pages_nr;
+}
+
+static int __init init_zbud(void)
+{
+	/* Make sure the zbud header will fit in one chunk */
+	BUILD_BUG_ON(sizeof(struct zbud_header) > ZHDR_SIZE_ALIGNED);
+	pr_info("loaded\n");
+
+#ifdef CONFIG_ZPOOL
+	zpool_register_driver(&zbud_zpool_driver);
+#endif
+
+	return 0;
+}
+
+static void __exit exit_zbud(void)
+{
+#ifdef CONFIG_ZPOOL
+	zpool_unregister_driver(&zbud_zpool_driver);
+#endif
+
+	pr_info("unloaded\n");
+}
+
+module_init(init_zbud);
+module_exit(exit_zbud);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Seth Jennings <sjenning@linux.vnet.ibm.com>");
+MODULE_DESCRIPTION("Buddy Allocator for Compressed Pages");

mm/zpool.c

@@ -0,0 +1,376 @@
+/*
+ * zpool memory storage api
+ *
+ * Copyright (C) 2014 Dan Streetman
+ *
+ * This is a common frontend for memory storage pool implementations.
+ * Typically, this is used to store compressed memory.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/list.h>
+#include <linux/types.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/module.h>
+#include <linux/zpool.h>
+
+struct zpool {
+	char *type;
+
+	struct zpool_driver *driver;
+	void *pool;
+	struct zpool_ops *ops;
+
+	struct list_head list;
+};
+
+static LIST_HEAD(drivers_head);
+static DEFINE_SPINLOCK(drivers_lock);
+
+static LIST_HEAD(pools_head);
+static DEFINE_SPINLOCK(pools_lock);
+
+/**
+ * zpool_register_driver() - register a zpool implementation.
+ * @driver:	driver to register
+ */
+void zpool_register_driver(struct zpool_driver *driver)
+{
+	spin_lock(&drivers_lock);
+	atomic_set(&driver->refcount, 0);
+	list_add(&driver->list, &drivers_head);
+	spin_unlock(&drivers_lock);
+}
+EXPORT_SYMBOL(zpool_register_driver);
+
+/**
+ * zpool_unregister_driver() - unregister a zpool implementation.
+ * @driver:	driver to unregister.
+ *
+ * Module usage counting is used to prevent using a driver
+ * while/after unloading, so if this is called from module
+ * exit function, this should never fail; if called from
+ * other than the module exit function, and this returns
+ * failure, the driver is in use and must remain available.
+ */
+int zpool_unregister_driver(struct zpool_driver *driver)
+{
+	int ret = 0, refcount;
+
+	spin_lock(&drivers_lock);
+	refcount = atomic_read(&driver->refcount);
+	WARN_ON(refcount < 0);
+	if (refcount > 0)
+		ret = -EBUSY;
+	else
+		list_del(&driver->list);
+	spin_unlock(&drivers_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL(zpool_unregister_driver);
+
+/**
+ * zpool_evict() - evict callback from a zpool implementation.
+ * @pool:	pool to evict from.
+ * @handle:	handle to evict.
+ *
+ * This can be used by zpool implementations to call the
+ * user's evict zpool_ops struct evict callback.
+ */
+int zpool_evict(void *pool, unsigned long handle)
+{
+	struct zpool *zpool;
+
+	spin_lock(&pools_lock);
+	list_for_each_entry(zpool, &pools_head, list) {
+		if (zpool->pool == pool) {
+			spin_unlock(&pools_lock);
+			if (!zpool->ops || !zpool->ops->evict)
+				return -EINVAL;
+			return zpool->ops->evict(zpool, handle);
+		}
+	}
+	spin_unlock(&pools_lock);
+
+	return -ENOENT;
+}
+EXPORT_SYMBOL(zpool_evict);
+
+static struct zpool_driver *zpool_get_driver(char *type)
+{
+	struct zpool_driver *driver;
+
+	spin_lock(&drivers_lock);
+	list_for_each_entry(driver, &drivers_head, list) {
+		if (!strcmp(driver->type, type)) {
+			bool got = try_module_get(driver->owner);
+
+			if (got)
+				atomic_inc(&driver->refcount);
+			spin_unlock(&drivers_lock);
+			return got ? driver : NULL;
+		}
+	}
+
+	spin_unlock(&drivers_lock);
+	return NULL;
+}
+
+static void zpool_put_driver(struct zpool_driver *driver)
+{
+	atomic_dec(&driver->refcount);
+	module_put(driver->owner);
+}
+
+/**
+ * zpool_create_pool() - Create a new zpool
+ * @type	The type of the zpool to create (e.g. zbud, zsmalloc)
+ * @name	The name of the zpool (e.g. zram0, zswap)
+ * @gfp		The GFP flags to use when allocating the pool.
+ * @ops		The optional ops callback.
+ *
+ * This creates a new zpool of the specified type.  The gfp flags will be
+ * used when allocating memory, if the implementation supports it.  If the
+ * ops param is NULL, then the created zpool will not be shrinkable.
+ *
+ * Implementations must guarantee this to be thread-safe.
+ *
+ * Returns: New zpool on success, NULL on failure.
+ */
+struct zpool *zpool_create_pool(char *type, char *name, gfp_t gfp,
+		struct zpool_ops *ops)
+{
+	struct zpool_driver *driver;
+	struct zpool *zpool;
+
+	pr_info("creating pool type %s\n", type);
+
+	driver = zpool_get_driver(type);
+
+	if (!driver) {
+		request_module("zpool-%s", type);
+		driver = zpool_get_driver(type);
+	}
+
+	if (!driver) {
+		pr_err("no driver for type %s\n", type);
+		return NULL;
+	}
+
+	zpool = kmalloc(sizeof(*zpool), GFP_KERNEL);
+	if (!zpool) {
+		pr_err("couldn't create zpool - out of memory\n");
+		zpool_put_driver(driver);
+		return NULL;
+	}
+
+	zpool->type = driver->type;
+	zpool->driver = driver;
+	zpool->pool = driver->create(name, gfp, ops);
+	zpool->ops = ops;
+
+	if (!zpool->pool) {
+		pr_err("couldn't create %s pool\n", type);
+		zpool_put_driver(driver);
+		kfree(zpool);
+		return NULL;
+	}
+
+	pr_info("created %s pool\n", type);
+
+	spin_lock(&pools_lock);
+	list_add(&zpool->list, &pools_head);
+	spin_unlock(&pools_lock);
+
+	return zpool;
+}
+
+/**
+ * zpool_destroy_pool() - Destroy a zpool
+ * @pool	The zpool to destroy.
+ *
+ * Implementations must guarantee this to be thread-safe,
+ * however only when destroying different pools.  The same
+ * pool should only be destroyed once, and should not be used
+ * after it is destroyed.
+ *
+ * This destroys an existing zpool.  The zpool should not be in use.
+ */
+void zpool_destroy_pool(struct zpool *zpool)
+{
+	pr_info("destroying pool type %s\n", zpool->type);
+
+	spin_lock(&pools_lock);
+	list_del(&zpool->list);
+	spin_unlock(&pools_lock);
+	zpool->driver->destroy(zpool->pool);
+	zpool_put_driver(zpool->driver);
+	kfree(zpool);
+}
+
+/**
+ * zpool_get_type() - Get the type of the zpool
+ * @pool	The zpool to check
+ *
+ * This returns the type of the pool.
+ *
+ * Implementations must guarantee this to be thread-safe.
+ *
+ * Returns: The type of zpool.
+ */
+char *zpool_get_type(struct zpool *zpool)
+{
+	return zpool->type;
+}
+
+/**
+ * zpool_malloc() - Allocate memory
+ * @pool	The zpool to allocate from.
+ * @size	The amount of memory to allocate.
+ * @gfp		The GFP flags to use when allocating memory.
+ * @handle	Pointer to the handle to set
+ *
+ * This allocates the requested amount of memory from the pool.
+ * The gfp flags will be used when allocating memory, if the
+ * implementation supports it.  The provided @handle will be
+ * set to the allocated object handle.
+ *
+ * Implementations must guarantee this to be thread-safe.
+ *
+ * Returns: 0 on success, negative value on error.
+ */
+int zpool_malloc(struct zpool *zpool, size_t size, gfp_t gfp,
+			unsigned long *handle)
+{
+	return zpool->driver->malloc(zpool->pool, size, gfp, handle);
+}
+
+/**
+ * zpool_free() - Free previously allocated memory
+ * @pool	The zpool that allocated the memory.
+ * @handle	The handle to the memory to free.
+ *
+ * This frees previously allocated memory.  This does not guarantee
+ * that the pool will actually free memory, only that the memory
+ * in the pool will become available for use by the pool.
+ *
+ * Implementations must guarantee this to be thread-safe,
+ * however only when freeing different handles.  The same
+ * handle should only be freed once, and should not be used
+ * after freeing.
+ */
+void zpool_free(struct zpool *zpool, unsigned long handle)
+{
+	zpool->driver->free(zpool->pool, handle);
+}
+
+/**
+ * zpool_shrink() - Shrink the pool size
+ * @pool	The zpool to shrink.
+ * @pages	The number of pages to shrink the pool.
+ * @reclaimed	The number of pages successfully evicted.
+ *
+ * This attempts to shrink the actual memory size of the pool
+ * by evicting currently used handle(s).  If the pool was
+ * created with no zpool_ops, or the evict call fails for any
+ * of the handles, this will fail.  If non-NULL, the @reclaimed
+ * parameter will be set to the number of pages reclaimed,
+ * which may be more than the number of pages requested.
+ *
+ * Implementations must guarantee this to be thread-safe.
+ *
+ * Returns: 0 on success, negative value on error/failure.
+ */
+int zpool_shrink(struct zpool *zpool, unsigned int pages,
+			unsigned int *reclaimed)
+{
+	return zpool->driver->shrink(zpool->pool, pages, reclaimed);
+}
+
+/**
+ * zpool_map_handle() - Map a previously allocated handle into memory
+ * @pool	The zpool that the handle was allocated from
+ * @handle	The handle to map
+ * @mm		How the memory should be mapped
+ *
+ * This maps a previously allocated handle into memory.  The @mm
+ * param indicates to the implementation how the memory will be
+ * used, i.e. read-only, write-only, read-write.  If the
+ * implementation does not support it, the memory will be treated
+ * as read-write.
+ *
+ * This may hold locks, disable interrupts, and/or preemption,
+ * and the zpool_unmap_handle() must be called to undo those
+ * actions.  The code that uses the mapped handle should complete
+ * its operatons on the mapped handle memory quickly and unmap
+ * as soon as possible.  As the implementation may use per-cpu
+ * data, multiple handles should not be mapped concurrently on
+ * any cpu.
+ *
+ * Returns: A pointer to the handle's mapped memory area.
+ */
+void *zpool_map_handle(struct zpool *zpool, unsigned long handle,
+			enum zpool_mapmode mapmode)
+{
+	return zpool->driver->map(zpool->pool, handle, mapmode);
+}
+
+/**
+ * zpool_unmap_handle() - Unmap a previously mapped handle
+ * @pool	The zpool that the handle was allocated from
+ * @handle	The handle to unmap
+ *
+ * This unmaps a previously mapped handle.  Any locks or other
+ * actions that the implementation took in zpool_map_handle()
+ * will be undone here.  The memory area returned from
+ * zpool_map_handle() should no longer be used after this.
+ */
+void zpool_unmap_handle(struct zpool *zpool, unsigned long handle)
+{
+	zpool->driver->unmap(zpool->pool, handle);
+}
+
+/**
+ * zpool_get_total_size() - The total size of the pool
+ * @pool	The zpool to check
+ *
+ * This returns the total size in bytes of the pool.
+ *
+ * Returns: Total size of the zpool in bytes.
+ */
+u64 zpool_get_total_size(struct zpool *zpool)
+{
+	return zpool->driver->total_size(zpool->pool);
+}
+
+unsigned long zpool_compact(struct zpool *zpool)
+{
+	return zpool->driver->compact(zpool->pool);
+}
+
+bool zpool_compactable(struct zpool *zpool, unsigned int pages)
+{
+	return zpool->driver->compactable(zpool->pool, pages);
+}
+
+static int __init init_zpool(void)
+{
+	pr_info("loaded\n");
+	return 0;
+}
+
+static void __exit exit_zpool(void)
+{
+	pr_info("unloaded\n");
+}
+
+module_init(init_zpool);
+module_exit(exit_zpool);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Dan Streetman <ddstreet@ieee.org>");
+MODULE_DESCRIPTION("Common API for compressed memory storage");