Merge branch 'akpm' (Andrew's patch-bomb)

Merge Andrew's second set of patches:
 - MM
 - a few random fixes
 - a couple of RTC leftovers

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (120 commits)
  rtc/rtc-88pm80x: remove unneed devm_kfree
  rtc/rtc-88pm80x: assign ret only when rtc_register_driver fails
  mm: hugetlbfs: close race during teardown of hugetlbfs shared page tables
  tmpfs: distribute interleave better across nodes
  mm: remove redundant initialization
  mm: warn if pg_data_t isn't initialized with zero
  mips: zero out pg_data_t when it's allocated
  memcg: gix memory accounting scalability in shrink_page_list
  mm/sparse: remove index_init_lock
  mm/sparse: more checks on mem_section number
  mm/sparse: optimize sparse_index_alloc
  memcg: add mem_cgroup_from_css() helper
  memcg: further prevent OOM with too many dirty pages
  memcg: prevent OOM with too many dirty pages
  mm: mmu_notifier: fix freed page still mapped in secondary MMU
  mm: memcg: only check anon swapin page charges for swap cache
  mm: memcg: only check swap cache pages for repeated charging
  mm: memcg: split swapin charge function into private and public part
  mm: memcg: remove needless !mm fixup to init_mm when charging
  mm: memcg: remove unneeded shmem charge type
  ...

Documentation/ABI/obsolete/proc-sys-vm-nr_pdflush_threads

@@ -0,0 +1,5 @@
+What:		/proc/sys/vm/nr_pdflush_threads
+Date:		June 2012
+Contact:	Wanpeng Li <liwp@linux.vnet.ibm.com>
+Description: Since pdflush is replaced by per-BDI flusher, the interface of old pdflush
+             exported in /proc/sys/vm/ should be removed.

Documentation/cgroups/hugetlb.txt

@@ -0,0 +1,45 @@
+HugeTLB Controller
+-------------------
+
+The HugeTLB controller allows to limit the HugeTLB usage per control group and
+enforces the controller limit during page fault. Since HugeTLB doesn't
+support page reclaim, enforcing the limit at page fault time implies that,
+the application will get SIGBUS signal if it tries to access HugeTLB pages
+beyond its limit. This requires the application to know beforehand how much
+HugeTLB pages it would require for its use.
+
+HugeTLB controller can be created by first mounting the cgroup filesystem.
+
+# mount -t cgroup -o hugetlb none /sys/fs/cgroup
+
+With the above step, the initial or the parent HugeTLB group becomes
+visible at /sys/fs/cgroup. At bootup, this group includes all the tasks in
+the system. /sys/fs/cgroup/tasks lists the tasks in this cgroup.
+
+New groups can be created under the parent group /sys/fs/cgroup.
+
+# cd /sys/fs/cgroup
+# mkdir g1
+# echo $$ > g1/tasks
+
+The above steps create a new group g1 and move the current shell
+process (bash) into it.
+
+Brief summary of control files
+
+ hugetlb.<hugepagesize>.limit_in_bytes     # set/show limit of "hugepagesize" hugetlb usage
+ hugetlb.<hugepagesize>.max_usage_in_bytes # show max "hugepagesize" hugetlb  usage recorded
+ hugetlb.<hugepagesize>.usage_in_bytes     # show current res_counter usage for "hugepagesize" hugetlb
+ hugetlb.<hugepagesize>.failcnt		   # show the number of allocation failure due to HugeTLB limit
+
+For a system supporting two hugepage size (16M and 16G) the control
+files include:
+
+hugetlb.16GB.limit_in_bytes
+hugetlb.16GB.max_usage_in_bytes
+hugetlb.16GB.usage_in_bytes
+hugetlb.16GB.failcnt
+hugetlb.16MB.limit_in_bytes
+hugetlb.16MB.max_usage_in_bytes
+hugetlb.16MB.usage_in_bytes
+hugetlb.16MB.failcnt

Documentation/cgroups/memory.txt

@@ -73,6 +73,8 @@ Brief summary of control files.
 
  memory.kmem.tcp.limit_in_bytes  # set/show hard limit for tcp buf memory
  memory.kmem.tcp.usage_in_bytes  # show current tcp buf memory allocation
+ memory.kmem.tcp.failcnt            # show the number of tcp buf memory usage hits limits
+ memory.kmem.tcp.max_usage_in_bytes # show max tcp buf memory usage recorded
 
 1. History
 
@@ -187,12 +189,12 @@ the cgroup that brought it in -- this will happen on memory pressure).
 But see section 8.2: when moving a task to another cgroup, its pages may
 be recharged to the new cgroup, if move_charge_at_immigrate has been chosen.
 
-Exception: If CONFIG_CGROUP_CGROUP_MEM_RES_CTLR_SWAP is not used.
+Exception: If CONFIG_CGROUP_CGROUP_MEMCG_SWAP is not used.
 When you do swapoff and make swapped-out pages of shmem(tmpfs) to
 be backed into memory in force, charges for pages are accounted against the
 caller of swapoff rather than the users of shmem.
 
-2.4 Swap Extension (CONFIG_CGROUP_MEM_RES_CTLR_SWAP)
+2.4 Swap Extension (CONFIG_MEMCG_SWAP)
 
 Swap Extension allows you to record charge for swap. A swapped-in page is
 charged back to original page allocator if possible.
@@ -259,7 +261,7 @@ When oom event notifier is registered, event will be delivered.
   per-zone-per-cgroup LRU (cgroup's private LRU) is just guarded by
   zone->lru_lock, it has no lock of its own.
 
-2.7 Kernel Memory Extension (CONFIG_CGROUP_MEM_RES_CTLR_KMEM)
+2.7 Kernel Memory Extension (CONFIG_MEMCG_KMEM)
 
 With the Kernel memory extension, the Memory Controller is able to limit
 the amount of kernel memory used by the system. Kernel memory is fundamentally
@@ -286,8 +288,8 @@ per cgroup, instead of globally.
 
 a. Enable CONFIG_CGROUPS
 b. Enable CONFIG_RESOURCE_COUNTERS
-c. Enable CONFIG_CGROUP_MEM_RES_CTLR
-d. Enable CONFIG_CGROUP_MEM_RES_CTLR_SWAP (to use swap extension)
+c. Enable CONFIG_MEMCG
+d. Enable CONFIG_MEMCG_SWAP (to use swap extension)
 
 1. Prepare the cgroups (see cgroups.txt, Why are cgroups needed?)
 # mount -t tmpfs none /sys/fs/cgroup

Documentation/feature-removal-schedule.txt

@@ -13,6 +13,14 @@ Who:	Jim Cromie <jim.cromie@gmail.com>, Jason Baron <jbaron@redhat.com>
 
 ---------------------------
 
+What: /proc/sys/vm/nr_pdflush_threads
+When: 2012
+Why: Since pdflush is deprecated, the interface exported in /proc/sys/vm/
+     should be removed.
+Who: Wanpeng Li <liwp@linux.vnet.ibm.com>
+
+---------------------------
+
 What:	CONFIG_APM_CPU_IDLE, and its ability to call APM BIOS in idle
 When:	2012
 Why:	This optional sub-feature of APM is of dubious reliability,

Documentation/filesystems/Locking

@@ -206,6 +206,8 @@ prototypes:
 	int (*launder_page)(struct page *);
 	int (*is_partially_uptodate)(struct page *, read_descriptor_t *, unsigned long);
 	int (*error_remove_page)(struct address_space *, struct page *);
+	int (*swap_activate)(struct file *);
+	int (*swap_deactivate)(struct file *);
 
 locking rules:
 	All except set_page_dirty and freepage may block
@@ -229,6 +231,8 @@ migratepage:		yes (both)
 launder_page:		yes
 is_partially_uptodate:	yes
 error_remove_page:	yes
+swap_activate:		no
+swap_deactivate:	no
 
 	->write_begin(), ->write_end(), ->sync_page() and ->readpage()
 may be called from the request handler (/dev/loop).
@@ -330,6 +334,15 @@ cleaned, or an error value if not. Note that in order to prevent the page
 getting mapped back in and redirtied, it needs to be kept locked
 across the entire operation.
 
+	->swap_activate will be called with a non-zero argument on
+files backing (non block device backed) swapfiles. A return value
+of zero indicates success, in which case this file can be used for
+backing swapspace. The swapspace operations will be proxied to the
+address space operations.
+
+	->swap_deactivate() will be called in the sys_swapoff()
+path after ->swap_activate() returned success.
+
 ----------------------- file_lock_operations ------------------------------
 prototypes:
 	void (*fl_copy_lock)(struct file_lock *, struct file_lock *);

Documentation/filesystems/vfs.txt

@@ -592,6 +592,8 @@ struct address_space_operations {
 	int (*migratepage) (struct page *, struct page *);
 	int (*launder_page) (struct page *);
 	int (*error_remove_page) (struct mapping *mapping, struct page *page);
+	int (*swap_activate)(struct file *);
+	int (*swap_deactivate)(struct file *);
 };
 
   writepage: called by the VM to write a dirty page to backing store.
@@ -760,6 +762,16 @@ struct address_space_operations {
 	Setting this implies you deal with pages going away under you,
 	unless you have them locked or reference counts increased.
 
+  swap_activate: Called when swapon is used on a file to allocate
+	space if necessary and pin the block lookup information in
+	memory. A return value of zero indicates success,
+	in which case this file can be used to back swapspace. The
+	swapspace operations will be proxied to this address space's
+	->swap_{out,in} methods.
+
+  swap_deactivate: Called during swapoff on files where swap_activate
+	was successful.
+
 
 The File Object
 ===============

Documentation/sysctl/vm.txt

@@ -42,7 +42,6 @@ Currently, these files are in /proc/sys/vm:
 - mmap_min_addr
 - nr_hugepages
 - nr_overcommit_hugepages
-- nr_pdflush_threads
 - nr_trim_pages         (only if CONFIG_MMU=n)
 - numa_zonelist_order
 - oom_dump_tasks
@@ -426,16 +425,6 @@ See Documentation/vm/hugetlbpage.txt
 
 ==============================================================
 
-nr_pdflush_threads
-
-The current number of pdflush threads.  This value is read-only.
-The value changes according to the number of dirty pages in the system.
-
-When necessary, additional pdflush threads are created, one per second, up to
-nr_pdflush_threads_max.
-
-==============================================================
-
 nr_trim_pages
 
 This is available only on NOMMU kernels.
@@ -502,9 +491,10 @@ oom_dump_tasks
 
 Enables a system-wide task dump (excluding kernel threads) to be
 produced when the kernel performs an OOM-killing and includes such
-information as pid, uid, tgid, vm size, rss, cpu, oom_adj score, and
-name.  This is helpful to determine why the OOM killer was invoked
-and to identify the rogue task that caused it.
+information as pid, uid, tgid, vm size, rss, nr_ptes, swapents,
+oom_score_adj score, and name.  This is helpful to determine why the
+OOM killer was invoked, to identify the rogue task that caused it,
+and to determine why the OOM killer chose the task it did to kill.
 
 If this is set to zero, this information is suppressed.  On very
 large systems with thousands of tasks it may not be feasible to dump
@@ -574,16 +564,24 @@ of physical RAM.  See above.
 
 page-cluster
 
-page-cluster controls the number of pages which are written to swap in
-a single attempt.  The swap I/O size.
+page-cluster controls the number of pages up to which consecutive pages
+are read in from swap in a single attempt. This is the swap counterpart
+to page cache readahead.
+The mentioned consecutivity is not in terms of virtual/physical addresses,
+but consecutive on swap space - that means they were swapped out together.
 
 It is a logarithmic value - setting it to zero means "1 page", setting
 it to 1 means "2 pages", setting it to 2 means "4 pages", etc.
+Zero disables swap readahead completely.
 
 The default value is three (eight pages at a time).  There may be some
 small benefits in tuning this to a different value if your workload is
 swap-intensive.
 
+Lower values mean lower latencies for initial faults, but at the same time
+extra faults and I/O delays for following faults if they would have been part of
+that consecutive pages readahead would have brought in.
+
 =============================================================
 
 panic_on_oom

arch/ia64/kernel/perfmon.c

@@ -2353,7 +2353,6 @@ pfm_smpl_buffer_alloc(struct task_struct *task, struct file *filp, pfm_context_t
 	 */
 	insert_vm_struct(mm, vma);
 
-	mm->total_vm  += size >> PAGE_SHIFT;
 	vm_stat_account(vma->vm_mm, vma->vm_flags, vma->vm_file,
 							vma_pages(vma));
 	up_write(&task->mm->mmap_sem);

arch/mips/sgi-ip27/ip27-memory.c

@@ -401,6 +401,7 @@ static void __init node_mem_init(cnodeid_t node)
 	 * Allocate the node data structures on the node first.
 	 */
 	__node_data[node] = __va(slot_freepfn << PAGE_SHIFT);
+	memset(__node_data[node], 0, PAGE_SIZE);
 
 	NODE_DATA(node)->bdata = &bootmem_node_data[node];
 	NODE_DATA(node)->node_start_pfn = start_pfn;

arch/powerpc/configs/chroma_defconfig

@@ -21,8 +21,8 @@ CONFIG_CGROUP_DEVICE=y
 CONFIG_CPUSETS=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_RESOURCE_COUNTERS=y
-CONFIG_CGROUP_MEM_RES_CTLR=y
-CONFIG_CGROUP_MEM_RES_CTLR_SWAP=y
+CONFIG_CGROUP_MEMCG=y
+CONFIG_CGROUP_MEMCG_SWAP=y
 CONFIG_NAMESPACES=y
 CONFIG_RELAY=y
 CONFIG_BLK_DEV_INITRD=y

arch/s390/defconfig

@@ -16,7 +16,7 @@ CONFIG_CGROUPS=y
 CONFIG_CPUSETS=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_RESOURCE_COUNTERS=y
-CONFIG_CGROUP_MEM_RES_CTLR=y
+CONFIG_CGROUP_MEMCG=y
 CONFIG_CGROUP_MEM_RES_CTLR_SWAP=y
 CONFIG_CGROUP_SCHED=y
 CONFIG_RT_GROUP_SCHED=y

arch/sh/configs/apsh4ad0a_defconfig

@@ -11,7 +11,7 @@ CONFIG_CGROUP_FREEZER=y
 CONFIG_CGROUP_DEVICE=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_RESOURCE_COUNTERS=y
-CONFIG_CGROUP_MEM_RES_CTLR=y
+CONFIG_CGROUP_MEMCG=y
 CONFIG_BLK_CGROUP=y
 CONFIG_NAMESPACES=y
 CONFIG_BLK_DEV_INITRD=y

arch/sh/configs/sdk7786_defconfig

@@ -18,8 +18,8 @@ CONFIG_CPUSETS=y
 # CONFIG_PROC_PID_CPUSET is not set
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_RESOURCE_COUNTERS=y
-CONFIG_CGROUP_MEM_RES_CTLR=y
-CONFIG_CGROUP_MEM_RES_CTLR_SWAP=y
+CONFIG_CGROUP_MEMCG=y
+CONFIG_CGROUP_MEMCG_SWAP=y
 CONFIG_CGROUP_SCHED=y
 CONFIG_RT_GROUP_SCHED=y
 CONFIG_BLK_CGROUP=y

arch/sh/configs/se7206_defconfig

@@ -11,7 +11,7 @@ CONFIG_CGROUP_DEBUG=y
 CONFIG_CGROUP_DEVICE=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_RESOURCE_COUNTERS=y
-CONFIG_CGROUP_MEM_RES_CTLR=y
+CONFIG_CGROUP_MEMCG=y
 CONFIG_RELAY=y
 CONFIG_NAMESPACES=y
 CONFIG_UTS_NS=y

arch/sh/configs/shx3_defconfig

@@ -13,7 +13,7 @@ CONFIG_CGROUP_FREEZER=y
 CONFIG_CGROUP_DEVICE=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_RESOURCE_COUNTERS=y
-CONFIG_CGROUP_MEM_RES_CTLR=y
+CONFIG_CGROUP_MEMCG=y
 CONFIG_RELAY=y
 CONFIG_NAMESPACES=y
 CONFIG_UTS_NS=y

arch/sh/configs/urquell_defconfig

@@ -15,8 +15,8 @@ CONFIG_CPUSETS=y
 # CONFIG_PROC_PID_CPUSET is not set
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_RESOURCE_COUNTERS=y
-CONFIG_CGROUP_MEM_RES_CTLR=y
-CONFIG_CGROUP_MEM_RES_CTLR_SWAP=y
+CONFIG_CGROUP_MEMCG=y
+CONFIG_CGROUP_MEMCG_SWAP=y
 CONFIG_CGROUP_SCHED=y
 CONFIG_RT_GROUP_SCHED=y
 CONFIG_BLK_DEV_INITRD=y

arch/tile/configs/tilegx_defconfig

@@ -18,8 +18,8 @@ CONFIG_CGROUP_DEVICE=y
 CONFIG_CPUSETS=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_RESOURCE_COUNTERS=y
-CONFIG_CGROUP_MEM_RES_CTLR=y
-CONFIG_CGROUP_MEM_RES_CTLR_SWAP=y
+CONFIG_CGROUP_MEMCG=y
+CONFIG_CGROUP_MEMCG_SWAP=y
 CONFIG_CGROUP_SCHED=y
 CONFIG_RT_GROUP_SCHED=y
 CONFIG_BLK_CGROUP=y

arch/tile/configs/tilepro_defconfig

@@ -17,8 +17,8 @@ CONFIG_CGROUP_DEVICE=y
 CONFIG_CPUSETS=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_RESOURCE_COUNTERS=y
-CONFIG_CGROUP_MEM_RES_CTLR=y
-CONFIG_CGROUP_MEM_RES_CTLR_SWAP=y
+CONFIG_CGROUP_MEMCG=y
+CONFIG_CGROUP_MEMCG_SWAP=y
 CONFIG_CGROUP_SCHED=y
 CONFIG_RT_GROUP_SCHED=y
 CONFIG_BLK_CGROUP=y

arch/um/defconfig

@@ -155,10 +155,10 @@ CONFIG_CPUSETS=y
 CONFIG_PROC_PID_CPUSET=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_RESOURCE_COUNTERS=y
-CONFIG_CGROUP_MEM_RES_CTLR=y
-CONFIG_CGROUP_MEM_RES_CTLR_SWAP=y
-# CONFIG_CGROUP_MEM_RES_CTLR_SWAP_ENABLED is not set
-# CONFIG_CGROUP_MEM_RES_CTLR_KMEM is not set
+CONFIG_CGROUP_MEMCG=y
+CONFIG_CGROUP_MEMCG_SWAP=y
+# CONFIG_CGROUP_MEMCG_SWAP_ENABLED is not set
+# CONFIG_CGROUP_MEMCG_KMEM is not set
 CONFIG_CGROUP_SCHED=y
 CONFIG_FAIR_GROUP_SCHED=y
 # CONFIG_CFS_BANDWIDTH is not set

arch/xtensa/Kconfig

@@ -7,6 +7,7 @@ config ZONE_DMA
 config XTENSA
 	def_bool y
 	select HAVE_IDE
+	select GENERIC_ATOMIC64
 	select HAVE_GENERIC_HARDIRQS
 	select GENERIC_IRQ_SHOW
 	select GENERIC_CPU_DEVICES

drivers/base/Kconfig

@@ -196,6 +196,7 @@ config CMA
 	bool "Contiguous Memory Allocator (EXPERIMENTAL)"
 	depends on HAVE_DMA_CONTIGUOUS && HAVE_MEMBLOCK && EXPERIMENTAL
 	select MIGRATION
+	select MEMORY_ISOLATION
 	help
 	  This enables the Contiguous Memory Allocator which allows drivers
 	  to allocate big physically-contiguous blocks of memory for use with

drivers/block/nbd.c

@@ -154,6 +154,7 @@ static int sock_xmit(struct nbd_device *nbd, int send, void *buf, int size,
 	struct msghdr msg;
 	struct kvec iov;
 	sigset_t blocked, oldset;
+	unsigned long pflags = current->flags;
 
 	if (unlikely(!sock)) {
 		dev_err(disk_to_dev(nbd->disk),
@@ -167,8 +168,9 @@ static int sock_xmit(struct nbd_device *nbd, int send, void *buf, int size,
 	siginitsetinv(&blocked, sigmask(SIGKILL));
 	sigprocmask(SIG_SETMASK, &blocked, &oldset);
 
+	current->flags |= PF_MEMALLOC;
 	do {
-		sock->sk->sk_allocation = GFP_NOIO;
+		sock->sk->sk_allocation = GFP_NOIO | __GFP_MEMALLOC;
 		iov.iov_base = buf;
 		iov.iov_len = size;
 		msg.msg_name = NULL;
@@ -214,6 +216,7 @@ static int sock_xmit(struct nbd_device *nbd, int send, void *buf, int size,
 	} while (size > 0);
 
 	sigprocmask(SIG_SETMASK, &oldset, NULL);
+	tsk_restore_flags(current, pflags, PF_MEMALLOC);
 
 	return result;
 }
@@ -405,6 +408,7 @@ static int nbd_do_it(struct nbd_device *nbd)
 
 	BUG_ON(nbd->magic != NBD_MAGIC);
 
+	sk_set_memalloc(nbd->sock->sk);
 	nbd->pid = task_pid_nr(current);
 	ret = device_create_file(disk_to_dev(nbd->disk), &pid_attr);
 	if (ret) {

drivers/net/ethernet/chelsio/cxgb4/sge.c

@@ -528,7 +528,7 @@ static unsigned int refill_fl(struct adapter *adap, struct sge_fl *q, int n,
 #endif
 
 	while (n--) {
-		pg = alloc_page(gfp);
+		pg = __skb_alloc_page(gfp, NULL);
 		if (unlikely(!pg)) {
 			q->alloc_failed++;
 			break;

drivers/net/ethernet/chelsio/cxgb4vf/sge.c

@@ -653,7 +653,7 @@ static unsigned int refill_fl(struct adapter *adapter, struct sge_fl *fl,
 
 alloc_small_pages:
 	while (n--) {
-		page = alloc_page(gfp | __GFP_NOWARN | __GFP_COLD);
+		page = __skb_alloc_page(gfp | __GFP_NOWARN, NULL);
 		if (unlikely(!page)) {
 			fl->alloc_failed++;
 			break;

drivers/net/ethernet/intel/igb/igb_main.c

@@ -6235,7 +6235,7 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring,
 		return true;
 
 	if (!page) {
-		page = alloc_page(GFP_ATOMIC | __GFP_COLD);
+		page = __skb_alloc_page(GFP_ATOMIC, bi->skb);
 		bi->page = page;
 		if (unlikely(!page)) {
 			rx_ring->rx_stats.alloc_failed++;

drivers/net/ethernet/intel/ixgbe/ixgbe_main.c

@@ -1141,8 +1141,8 @@ static bool ixgbe_alloc_mapped_page(struct ixgbe_ring *rx_ring,
 
 	/* alloc new page for storage */
 	if (likely(!page)) {
-		page = alloc_pages(GFP_ATOMIC | __GFP_COLD | __GFP_COMP,
-				   ixgbe_rx_pg_order(rx_ring));
+		page = __skb_alloc_pages(GFP_ATOMIC | __GFP_COLD | __GFP_COMP,
+					 bi->skb, ixgbe_rx_pg_order(rx_ring));
 		if (unlikely(!page)) {
 			rx_ring->rx_stats.alloc_rx_page_failed++;
 			return false;

drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c

@@ -352,7 +352,6 @@ static void ixgbevf_alloc_rx_buffers(struct ixgbevf_adapter *adapter,
 				adapter->alloc_rx_buff_failed++;
 				goto no_buffers;
 			}
-
 			bi->skb = skb;
 		}
 		if (!bi->dma) {

drivers/net/usb/cdc-phonet.c

@@ -130,7 +130,7 @@ static int rx_submit(struct usbpn_dev *pnd, struct urb *req, gfp_t gfp_flags)
 	struct page *page;
 	int err;
 
-	page = alloc_page(gfp_flags);
+	page = __skb_alloc_page(gfp_flags | __GFP_NOMEMALLOC, NULL);
 	if (!page)
 		return -ENOMEM;
 

drivers/rtc/rtc-88pm80x.c

@@ -314,8 +314,8 @@ static int __devinit pm80x_rtc_probe(struct platform_device *pdev)
 
 	info->rtc_dev = rtc_device_register("88pm80x-rtc", &pdev->dev,
 					    &pm80x_rtc_ops, THIS_MODULE);
-	ret = PTR_ERR(info->rtc_dev);
 	if (IS_ERR(info->rtc_dev)) {
+		ret = PTR_ERR(info->rtc_dev);
 		dev_err(&pdev->dev, "Failed to register RTC device: %d\n", ret);
 		goto out_rtc;
 	}
@@ -339,7 +339,6 @@ static int __devinit pm80x_rtc_probe(struct platform_device *pdev)
 out_rtc:
 	pm80x_free_irq(chip, info->irq, info);
 out:
-	devm_kfree(&pdev->dev, info);
 	return ret;
 }
 
@@ -349,7 +348,6 @@ static int __devexit pm80x_rtc_remove(struct platform_device *pdev)
 	platform_set_drvdata(pdev, NULL);
 	rtc_device_unregister(info->rtc_dev);
 	pm80x_free_irq(info->chip, info->irq, info);
-	devm_kfree(&pdev->dev, info);
 	return 0;
 }
 

drivers/usb/gadget/f_phonet.c

@@ -301,7 +301,7 @@ pn_rx_submit(struct f_phonet *fp, struct usb_request *req, gfp_t gfp_flags)
 	struct page *page;
 	int err;
 
-	page = alloc_page(gfp_flags);
+	page = __skb_alloc_page(gfp_flags | __GFP_NOMEMALLOC, NULL);
 	if (!page)
 		return -ENOMEM;
 

fs/fs-writeback.c

@@ -52,11 +52,6 @@ struct wb_writeback_work {
 	struct completion *done;	/* set if the caller waits */
 };
 
-/*
- * We don't actually have pdflush, but this one is exported though /proc...
- */
-int nr_pdflush_threads;
-
 /**
  * writeback_in_progress - determine whether there is writeback in progress
  * @bdi: the device's backing_dev_info structure.

fs/hugetlbfs/inode.c

@@ -416,8 +416,8 @@ hugetlb_vmtruncate_list(struct prio_tree_root *root, pgoff_t pgoff)
 		else
 			v_offset = 0;
 
-		__unmap_hugepage_range(vma,
-				vma->vm_start + v_offset, vma->vm_end, NULL);
+		unmap_hugepage_range(vma, vma->vm_start + v_offset,
+				     vma->vm_end, NULL);
 	}
 }
 

fs/nfs/Kconfig

@@ -86,6 +86,14 @@ config NFS_V4
 
 	  If unsure, say Y.
 
+config NFS_SWAP
+	bool "Provide swap over NFS support"
+	default n
+	depends on NFS_FS
+	select SUNRPC_SWAP
+	help
+	  This option enables swapon to work on files located on NFS mounts.
+
 config NFS_V4_1
 	bool "NFS client support for NFSv4.1 (EXPERIMENTAL)"
 	depends on NFS_V4 && EXPERIMENTAL

fs/nfs/direct.c

@@ -115,17 +115,28 @@ static inline int put_dreq(struct nfs_direct_req *dreq)
  * @nr_segs: size of iovec array
  *
  * The presence of this routine in the address space ops vector means
- * the NFS client supports direct I/O.  However, we shunt off direct
- * read and write requests before the VFS gets them, so this method
- * should never be called.
+ * the NFS client supports direct I/O. However, for most direct IO, we
+ * shunt off direct read and write requests before the VFS gets them,
+ * so this method is only ever called for swap.
  */
 ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, loff_t pos, unsigned long nr_segs)
 {
+#ifndef CONFIG_NFS_SWAP
 	dprintk("NFS: nfs_direct_IO (%s) off/no(%Ld/%lu) EINVAL\n",
 			iocb->ki_filp->f_path.dentry->d_name.name,
 			(long long) pos, nr_segs);
 
 	return -EINVAL;
+#else
+	VM_BUG_ON(iocb->ki_left != PAGE_SIZE);
+	VM_BUG_ON(iocb->ki_nbytes != PAGE_SIZE);
+
+	if (rw == READ || rw == KERNEL_READ)
+		return nfs_file_direct_read(iocb, iov, nr_segs, pos,
+				rw == READ ? true : false);
+	return nfs_file_direct_write(iocb, iov, nr_segs, pos,
+				rw == WRITE ? true : false);
+#endif /* CONFIG_NFS_SWAP */
 }
 
 static void nfs_direct_release_pages(struct page **pages, unsigned int npages)
@@ -303,7 +314,7 @@ static const struct nfs_pgio_completion_ops nfs_direct_read_completion_ops = {
  */
 static ssize_t nfs_direct_read_schedule_segment(struct nfs_pageio_descriptor *desc,
 						const struct iovec *iov,
-						loff_t pos)
+						loff_t pos, bool uio)
 {
 	struct nfs_direct_req *dreq = desc->pg_dreq;
 	struct nfs_open_context *ctx = dreq->ctx;
@@ -331,12 +342,20 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_pageio_descriptor *de
 					  GFP_KERNEL);
 		if (!pagevec)
 			break;
-		down_read(&current->mm->mmap_sem);
-		result = get_user_pages(current, current->mm, user_addr,
+		if (uio) {
+			down_read(&current->mm->mmap_sem);
+			result = get_user_pages(current, current->mm, user_addr,
 					npages, 1, 0, pagevec, NULL);
-		up_read(&current->mm->mmap_sem);
-		if (result < 0)
-			break;
+			up_read(&current->mm->mmap_sem);
+			if (result < 0)
+				break;
+		} else {
+			WARN_ON(npages != 1);
+			result = get_kernel_page(user_addr, 1, pagevec);
+			if (WARN_ON(result != 1))
+				break;
+		}
+
 		if ((unsigned)result < npages) {
 			bytes = result * PAGE_SIZE;
 			if (bytes <= pgbase) {
@@ -386,7 +405,7 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_pageio_descriptor *de
 static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
 					      const struct iovec *iov,
 					      unsigned long nr_segs,
-					      loff_t pos)
+					      loff_t pos, bool uio)
 {
 	struct nfs_pageio_descriptor desc;
 	ssize_t result = -EINVAL;
@@ -400,7 +419,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
 
 	for (seg = 0; seg < nr_segs; seg++) {
 		const struct iovec *vec = &iov[seg];
-		result = nfs_direct_read_schedule_segment(&desc, vec, pos);
+		result = nfs_direct_read_schedule_segment(&desc, vec, pos, uio);
 		if (result < 0)
 			break;
 		requested_bytes += result;
@@ -426,7 +445,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
 }
 
 static ssize_t nfs_direct_read(struct kiocb *iocb, const struct iovec *iov,
-			       unsigned long nr_segs, loff_t pos)
+			       unsigned long nr_segs, loff_t pos, bool uio)
 {
 	ssize_t result = -ENOMEM;
 	struct inode *inode = iocb->ki_filp->f_mapping->host;
@@ -444,7 +463,7 @@ static ssize_t nfs_direct_read(struct kiocb *iocb, const struct iovec *iov,
 	if (!is_sync_kiocb(iocb))
 		dreq->iocb = iocb;
 
-	result = nfs_direct_read_schedule_iovec(dreq, iov, nr_segs, pos);
+	result = nfs_direct_read_schedule_iovec(dreq, iov, nr_segs, pos, uio);
 	if (!result)
 		result = nfs_direct_wait(dreq);
 	NFS_I(inode)->read_io += result;
@@ -610,7 +629,7 @@ static void nfs_direct_write_complete(struct nfs_direct_req *dreq, struct inode
  */
 static ssize_t nfs_direct_write_schedule_segment(struct nfs_pageio_descriptor *desc,
 						 const struct iovec *iov,
-						 loff_t pos)
+						 loff_t pos, bool uio)
 {
 	struct nfs_direct_req *dreq = desc->pg_dreq;
 	struct nfs_open_context *ctx = dreq->ctx;
@@ -638,12 +657,19 @@ static ssize_t nfs_direct_write_schedule_segment(struct nfs_pageio_descriptor *d
 		if (!pagevec)
 			break;
 
-		down_read(&current->mm->mmap_sem);
-		result = get_user_pages(current, current->mm, user_addr,
-					npages, 0, 0, pagevec, NULL);
-		up_read(&current->mm->mmap_sem);
-		if (result < 0)
-			break;
+		if (uio) {
+			down_read(&current->mm->mmap_sem);
+			result = get_user_pages(current, current->mm, user_addr,
+						npages, 0, 0, pagevec, NULL);
+			up_read(&current->mm->mmap_sem);
+			if (result < 0)
+				break;
+		} else {
+			WARN_ON(npages != 1);
+			result = get_kernel_page(user_addr, 0, pagevec);
+			if (WARN_ON(result != 1))
+				break;
+		}
 
 		if ((unsigned)result < npages) {
 			bytes = result * PAGE_SIZE;
@@ -774,7 +800,7 @@ static const struct nfs_pgio_completion_ops nfs_direct_write_completion_ops = {
 static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
 					       const struct iovec *iov,
 					       unsigned long nr_segs,
-					       loff_t pos)
+					       loff_t pos, bool uio)
 {
 	struct nfs_pageio_descriptor desc;
 	struct inode *inode = dreq->inode;
@@ -790,7 +816,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
 
 	for (seg = 0; seg < nr_segs; seg++) {
 		const struct iovec *vec = &iov[seg];
-		result = nfs_direct_write_schedule_segment(&desc, vec, pos);
+		result = nfs_direct_write_schedule_segment(&desc, vec, pos, uio);
 		if (result < 0)
 			break;
 		requested_bytes += result;
@@ -818,7 +844,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
 
 static ssize_t nfs_direct_write(struct kiocb *iocb, const struct iovec *iov,
 				unsigned long nr_segs, loff_t pos,
-				size_t count)
+				size_t count, bool uio)
 {
 	ssize_t result = -ENOMEM;
 	struct inode *inode = iocb->ki_filp->f_mapping->host;
@@ -836,7 +862,7 @@ static ssize_t nfs_direct_write(struct kiocb *iocb, const struct iovec *iov,
 	if (!is_sync_kiocb(iocb))
 		dreq->iocb = iocb;
 
-	result = nfs_direct_write_schedule_iovec(dreq, iov, nr_segs, pos);
+	result = nfs_direct_write_schedule_iovec(dreq, iov, nr_segs, pos, uio);
 	if (!result)
 		result = nfs_direct_wait(dreq);
 out_release:
@@ -867,7 +893,7 @@ out:
  * cache.
  */
 ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov,
-				unsigned long nr_segs, loff_t pos)
+				unsigned long nr_segs, loff_t pos, bool uio)
 {
 	ssize_t retval = -EINVAL;
 	struct file *file = iocb->ki_filp;
@@ -892,7 +918,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov,
 
 	task_io_account_read(count);
 
-	retval = nfs_direct_read(iocb, iov, nr_segs, pos);
+	retval = nfs_direct_read(iocb, iov, nr_segs, pos, uio);
 	if (retval > 0)
 		iocb->ki_pos = pos + retval;
 
@@ -923,7 +949,7 @@ out:
  * is no atomic O_APPEND write facility in the NFS protocol.
  */
 ssize_t nfs_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
-				unsigned long nr_segs, loff_t pos)
+				unsigned long nr_segs, loff_t pos, bool uio)
 {
 	ssize_t retval = -EINVAL;
 	struct file *file = iocb->ki_filp;
@@ -955,7 +981,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
 
 	task_io_account_write(count);
 
-	retval = nfs_direct_write(iocb, iov, nr_segs, pos, count);
+	retval = nfs_direct_write(iocb, iov, nr_segs, pos, count, uio);
 	if (retval > 0) {
 		struct inode *inode = mapping->host;
 

fs/nfs/file.c

@@ -180,7 +180,7 @@ nfs_file_read(struct kiocb *iocb, const struct iovec *iov,
 	ssize_t result;
 
 	if (iocb->ki_filp->f_flags & O_DIRECT)
-		return nfs_file_direct_read(iocb, iov, nr_segs, pos);
+		return nfs_file_direct_read(iocb, iov, nr_segs, pos, true);
 
 	dprintk("NFS: read(%s/%s, %lu@%lu)\n",
 		dentry->d_parent->d_name.name, dentry->d_name.name,
@@ -439,7 +439,7 @@ static void nfs_invalidate_page(struct page *page, unsigned long offset)
 	if (offset != 0)
 		return;
 	/* Cancel any unstarted writes on this page */
-	nfs_wb_page_cancel(page->mapping->host, page);
+	nfs_wb_page_cancel(page_file_mapping(page)->host, page);
 
 	nfs_fscache_invalidate_page(page, page->mapping->host);
 }
@@ -484,7 +484,7 @@ static int nfs_release_page(struct page *page, gfp_t gfp)
  */
 static int nfs_launder_page(struct page *page)
 {
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = page_file_mapping(page)->host;
 	struct nfs_inode *nfsi = NFS_I(inode);
 
 	dfprintk(PAGECACHE, "NFS: launder_page(%ld, %llu)\n",
@@ -494,6 +494,20 @@ static int nfs_launder_page(struct page *page)
 	return nfs_wb_page(inode, page);
 }
 
+#ifdef CONFIG_NFS_SWAP
+static int nfs_swap_activate(struct swap_info_struct *sis, struct file *file,
+						sector_t *span)
+{
+	*span = sis->pages;
+	return xs_swapper(NFS_CLIENT(file->f_mapping->host)->cl_xprt, 1);
+}
+
+static void nfs_swap_deactivate(struct file *file)
+{
+	xs_swapper(NFS_CLIENT(file->f_mapping->host)->cl_xprt, 0);
+}
+#endif
+
 const struct address_space_operations nfs_file_aops = {
 	.readpage = nfs_readpage,
 	.readpages = nfs_readpages,
@@ -508,6 +522,10 @@ const struct address_space_operations nfs_file_aops = {
 	.migratepage = nfs_migrate_page,
 	.launder_page = nfs_launder_page,
 	.error_remove_page = generic_error_remove_page,
+#ifdef CONFIG_NFS_SWAP
+	.swap_activate = nfs_swap_activate,
+	.swap_deactivate = nfs_swap_deactivate,
+#endif
 };
 
 /*
@@ -533,7 +551,7 @@ static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	nfs_fscache_wait_on_page_write(NFS_I(dentry->d_inode), page);
 
 	lock_page(page);
-	mapping = page->mapping;
+	mapping = page_file_mapping(page);
 	if (mapping != dentry->d_inode->i_mapping)
 		goto out_unlock;
 
@@ -582,7 +600,7 @@ ssize_t nfs_file_write(struct kiocb *iocb, const struct iovec *iov,
 	size_t count = iov_length(iov, nr_segs);
 
 	if (iocb->ki_filp->f_flags & O_DIRECT)
-		return nfs_file_direct_write(iocb, iov, nr_segs, pos);
+		return nfs_file_direct_write(iocb, iov, nr_segs, pos, true);
 
 	dprintk("NFS: write(%s/%s, %lu@%Ld)\n",
 		dentry->d_parent->d_name.name, dentry->d_name.name,

fs/nfs/inode.c

@@ -897,6 +897,10 @@ int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
 	struct nfs_inode *nfsi = NFS_I(inode);
 	int ret = 0;
 
+	/* swapfiles are not supposed to be shared. */
+	if (IS_SWAPFILE(inode))
+		goto out;
+
 	if (nfs_mapping_need_revalidate_inode(inode)) {
 		ret = __nfs_revalidate_inode(NFS_SERVER(inode), inode);
 		if (ret < 0)

fs/nfs/internal.h

@@ -554,13 +554,14 @@ void nfs_super_set_maxbytes(struct super_block *sb, __u64 maxfilesize)
 static inline
 unsigned int nfs_page_length(struct page *page)
 {
-	loff_t i_size = i_size_read(page->mapping->host);
+	loff_t i_size = i_size_read(page_file_mapping(page)->host);
 
 	if (i_size > 0) {
+		pgoff_t page_index = page_file_index(page);
 		pgoff_t end_index = (i_size - 1) >> PAGE_CACHE_SHIFT;
-		if (page->index < end_index)
+		if (page_index < end_index)
 			return PAGE_CACHE_SIZE;
-		if (page->index == end_index)
+		if (page_index == end_index)
 			return ((i_size - 1) & ~PAGE_CACHE_MASK) + 1;
 	}
 	return 0;

fs/nfs/pagelist.c

@@ -71,7 +71,7 @@ void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos)
 static inline struct nfs_page *
 nfs_page_alloc(void)
 {
-	struct nfs_page	*p = kmem_cache_zalloc(nfs_page_cachep, GFP_KERNEL);
+	struct nfs_page	*p = kmem_cache_zalloc(nfs_page_cachep, GFP_NOIO);
 	if (p)
 		INIT_LIST_HEAD(&p->wb_list);
 	return p;
@@ -118,7 +118,7 @@ nfs_create_request(struct nfs_open_context *ctx, struct inode *inode,
 	 * long write-back delay. This will be adjusted in
 	 * update_nfs_request below if the region is not locked. */
 	req->wb_page    = page;
-	req->wb_index	= page->index;
+	req->wb_index	= page_file_index(page);
 	page_cache_get(page);
 	req->wb_offset  = offset;
 	req->wb_pgbase	= offset;

fs/nfs/read.c

@@ -527,11 +527,11 @@ static const struct rpc_call_ops nfs_read_common_ops = {
 int nfs_readpage(struct file *file, struct page *page)
 {
 	struct nfs_open_context *ctx;
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = page_file_mapping(page)->host;
 	int		error;
 
 	dprintk("NFS: nfs_readpage (%p %ld@%lu)\n",
-		page, PAGE_CACHE_SIZE, page->index);
+		page, PAGE_CACHE_SIZE, page_file_index(page));
 	nfs_inc_stats(inode, NFSIOS_VFSREADPAGE);
 	nfs_add_stats(inode, NFSIOS_READPAGES, 1);
 
@@ -585,7 +585,7 @@ static int
 readpage_async_filler(void *data, struct page *page)
 {
 	struct nfs_readdesc *desc = (struct nfs_readdesc *)data;
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = page_file_mapping(page)->host;
 	struct nfs_page *new;
 	unsigned int len;
 	int error;

fs/nfs/write.c

@@ -52,7 +52,7 @@ static mempool_t *nfs_commit_mempool;
 
 struct nfs_commit_data *nfs_commitdata_alloc(void)
 {
-	struct nfs_commit_data *p = mempool_alloc(nfs_commit_mempool, GFP_NOFS);
+	struct nfs_commit_data *p = mempool_alloc(nfs_commit_mempool, GFP_NOIO);
 
 	if (p) {
 		memset(p, 0, sizeof(*p));
@@ -70,7 +70,7 @@ EXPORT_SYMBOL_GPL(nfs_commit_free);
 
 struct nfs_write_header *nfs_writehdr_alloc(void)
 {
-	struct nfs_write_header *p = mempool_alloc(nfs_wdata_mempool, GFP_NOFS);
+	struct nfs_write_header *p = mempool_alloc(nfs_wdata_mempool, GFP_NOIO);
 
 	if (p) {
 		struct nfs_pgio_header *hdr = &p->header;
@@ -142,25 +142,38 @@ static void nfs_context_set_write_error(struct nfs_open_context *ctx, int error)
 	set_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags);
 }
 
-static struct nfs_page *nfs_page_find_request_locked(struct page *page)
+static struct nfs_page *
+nfs_page_find_request_locked(struct nfs_inode *nfsi, struct page *page)
 {
 	struct nfs_page *req = NULL;
 
-	if (PagePrivate(page)) {
+	if (PagePrivate(page))
 		req = (struct nfs_page *)page_private(page);
-		if (req != NULL)
-			kref_get(&req->wb_kref);
+	else if (unlikely(PageSwapCache(page))) {
+		struct nfs_page *freq, *t;
+
+		/* Linearly search the commit list for the correct req */
+		list_for_each_entry_safe(freq, t, &nfsi->commit_info.list, wb_list) {
+			if (freq->wb_page == page) {
+				req = freq;
+				break;
+			}
+		}
 	}
+
+	if (req)
+		kref_get(&req->wb_kref);
+
 	return req;
 }
 
 static struct nfs_page *nfs_page_find_request(struct page *page)
 {
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = page_file_mapping(page)->host;
 	struct nfs_page *req = NULL;
 
 	spin_lock(&inode->i_lock);
-	req = nfs_page_find_request_locked(page);
+	req = nfs_page_find_request_locked(NFS_I(inode), page);
 	spin_unlock(&inode->i_lock);
 	return req;
 }
@@ -168,16 +181,16 @@ static struct nfs_page *nfs_page_find_request(struct page *page)
 /* Adjust the file length if we're writing beyond the end */
 static void nfs_grow_file(struct page *page, unsigned int offset, unsigned int count)
 {
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = page_file_mapping(page)->host;
 	loff_t end, i_size;
 	pgoff_t end_index;
 
 	spin_lock(&inode->i_lock);
 	i_size = i_size_read(inode);
 	end_index = (i_size - 1) >> PAGE_CACHE_SHIFT;
-	if (i_size > 0 && page->index < end_index)
+	if (i_size > 0 && page_file_index(page) < end_index)
 		goto out;
-	end = ((loff_t)page->index << PAGE_CACHE_SHIFT) + ((loff_t)offset+count);
+	end = page_file_offset(page) + ((loff_t)offset+count);
 	if (i_size >= end)
 		goto out;
 	i_size_write(inode, end);
@@ -190,7 +203,7 @@ out:
 static void nfs_set_pageerror(struct page *page)
 {
 	SetPageError(page);
-	nfs_zap_mapping(page->mapping->host, page->mapping);
+	nfs_zap_mapping(page_file_mapping(page)->host, page_file_mapping(page));
 }
 
 /* We can set the PG_uptodate flag if we see that a write request
@@ -231,7 +244,7 @@ static int nfs_set_page_writeback(struct page *page)
 	int ret = test_set_page_writeback(page);
 
 	if (!ret) {
-		struct inode *inode = page->mapping->host;
+		struct inode *inode = page_file_mapping(page)->host;
 		struct nfs_server *nfss = NFS_SERVER(inode);
 
 		if (atomic_long_inc_return(&nfss->writeback) >
@@ -245,7 +258,7 @@ static int nfs_set_page_writeback(struct page *page)
 
 static void nfs_end_page_writeback(struct page *page)
 {
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = page_file_mapping(page)->host;
 	struct nfs_server *nfss = NFS_SERVER(inode);
 
 	end_page_writeback(page);
@@ -255,13 +268,13 @@ static void nfs_end_page_writeback(struct page *page)
 
 static struct nfs_page *nfs_find_and_lock_request(struct page *page, bool nonblock)
 {
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = page_file_mapping(page)->host;
 	struct nfs_page *req;
 	int ret;
 
 	spin_lock(&inode->i_lock);
 	for (;;) {
-		req = nfs_page_find_request_locked(page);
+		req = nfs_page_find_request_locked(NFS_I(inode), page);
 		if (req == NULL)
 			break;
 		if (nfs_lock_request(req))
@@ -316,13 +329,13 @@ out:
 
 static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, struct nfs_pageio_descriptor *pgio)
 {
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = page_file_mapping(page)->host;
 	int ret;
 
 	nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE);
 	nfs_add_stats(inode, NFSIOS_WRITEPAGES, 1);
 
-	nfs_pageio_cond_complete(pgio, page->index);
+	nfs_pageio_cond_complete(pgio, page_file_index(page));
 	ret = nfs_page_async_flush(pgio, page, wbc->sync_mode == WB_SYNC_NONE);
 	if (ret == -EAGAIN) {
 		redirty_page_for_writepage(wbc, page);
@@ -339,7 +352,7 @@ static int nfs_writepage_locked(struct page *page, struct writeback_control *wbc
 	struct nfs_pageio_descriptor pgio;
 	int err;
 
-	NFS_PROTO(page->mapping->host)->write_pageio_init(&pgio,
+	NFS_PROTO(page_file_mapping(page)->host)->write_pageio_init(&pgio,
 							  page->mapping->host,
 							  wb_priority(wbc),
 							  &nfs_async_write_completion_ops);
@@ -416,9 +429,15 @@ static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req)
 	spin_lock(&inode->i_lock);
 	if (!nfsi->npages && NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE))
 		inode->i_version++;
-	set_bit(PG_MAPPED, &req->wb_flags);
-	SetPagePrivate(req->wb_page);
-	set_page_private(req->wb_page, (unsigned long)req);
+	/*
+	 * Swap-space should not get truncated. Hence no need to plug the race
+	 * with invalidate/truncate.
+	 */
+	if (likely(!PageSwapCache(req->wb_page))) {
+		set_bit(PG_MAPPED, &req->wb_flags);
+		SetPagePrivate(req->wb_page);
+		set_page_private(req->wb_page, (unsigned long)req);
+	}
 	nfsi->npages++;
 	kref_get(&req->wb_kref);
 	spin_unlock(&inode->i_lock);
@@ -435,9 +454,11 @@ static void nfs_inode_remove_request(struct nfs_page *req)
 	BUG_ON (!NFS_WBACK_BUSY(req));
 
 	spin_lock(&inode->i_lock);
-	set_page_private(req->wb_page, 0);
-	ClearPagePrivate(req->wb_page);
-	clear_bit(PG_MAPPED, &req->wb_flags);
+	if (likely(!PageSwapCache(req->wb_page))) {
+		set_page_private(req->wb_page, 0);
+		ClearPagePrivate(req->wb_page);
+		clear_bit(PG_MAPPED, &req->wb_flags);
+	}
 	nfsi->npages--;
 	spin_unlock(&inode->i_lock);
 	nfs_release_request(req);
@@ -474,7 +495,7 @@ nfs_request_add_commit_list(struct nfs_page *req, struct list_head *dst,
 	spin_unlock(cinfo->lock);
 	if (!cinfo->dreq) {
 		inc_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
-		inc_bdi_stat(req->wb_page->mapping->backing_dev_info,
+		inc_bdi_stat(page_file_mapping(req->wb_page)->backing_dev_info,
 			     BDI_RECLAIMABLE);
 		__mark_inode_dirty(req->wb_context->dentry->d_inode,
 				   I_DIRTY_DATASYNC);
@@ -541,7 +562,7 @@ static void
 nfs_clear_page_commit(struct page *page)
 {
 	dec_zone_page_state(page, NR_UNSTABLE_NFS);
-	dec_bdi_stat(page->mapping->backing_dev_info, BDI_RECLAIMABLE);
+	dec_bdi_stat(page_file_mapping(page)->backing_dev_info, BDI_RECLAIMABLE);
 }
 
 static void
@@ -733,7 +754,7 @@ static struct nfs_page *nfs_try_to_update_request(struct inode *inode,
 	spin_lock(&inode->i_lock);
 
 	for (;;) {
-		req = nfs_page_find_request_locked(page);
+		req = nfs_page_find_request_locked(NFS_I(inode), page);
 		if (req == NULL)
 			goto out_unlock;
 
@@ -792,7 +813,7 @@ out_err:
 static struct nfs_page * nfs_setup_write_request(struct nfs_open_context* ctx,
 		struct page *page, unsigned int offset, unsigned int bytes)
 {
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = page_file_mapping(page)->host;
 	struct nfs_page	*req;
 
 	req = nfs_try_to_update_request(inode, page, offset, bytes);
@@ -845,7 +866,7 @@ int nfs_flush_incompatible(struct file *file, struct page *page)
 		nfs_release_request(req);
 		if (!do_flush)
 			return 0;
-		status = nfs_wb_page(page->mapping->host, page);
+		status = nfs_wb_page(page_file_mapping(page)->host, page);
 	} while (status == 0);
 	return status;
 }
@@ -875,7 +896,7 @@ int nfs_updatepage(struct file *file, struct page *page,
 		unsigned int offset, unsigned int count)
 {
 	struct nfs_open_context *ctx = nfs_file_open_context(file);
-	struct inode	*inode = page->mapping->host;
+	struct inode	*inode = page_file_mapping(page)->host;
 	int		status = 0;
 
 	nfs_inc_stats(inode, NFSIOS_VFSUPDATEPAGE);
@@ -883,7 +904,7 @@ int nfs_updatepage(struct file *file, struct page *page,
 	dprintk("NFS:       nfs_updatepage(%s/%s %d@%lld)\n",
 		file->f_path.dentry->d_parent->d_name.name,
 		file->f_path.dentry->d_name.name, count,
-		(long long)(page_offset(page) + offset));
+		(long long)(page_file_offset(page) + offset));
 
 	/* If we're not using byte range locks, and we know the page
 	 * is up to date, it may be more efficient to extend the write
@@ -1474,7 +1495,7 @@ void nfs_retry_commit(struct list_head *page_list,
 		nfs_mark_request_commit(req, lseg, cinfo);
 		if (!cinfo->dreq) {
 			dec_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
-			dec_bdi_stat(req->wb_page->mapping->backing_dev_info,
+			dec_bdi_stat(page_file_mapping(req->wb_page)->backing_dev_info,
 				     BDI_RECLAIMABLE);
 		}
 		nfs_unlock_and_release_request(req);
@@ -1731,7 +1752,7 @@ int nfs_wb_page_cancel(struct inode *inode, struct page *page)
  */
 int nfs_wb_page(struct inode *inode, struct page *page)
 {
-	loff_t range_start = page_offset(page);
+	loff_t range_start = page_file_offset(page);
 	loff_t range_end = range_start + (loff_t)(PAGE_CACHE_SIZE - 1);
 	struct writeback_control wbc = {
 		.sync_mode = WB_SYNC_ALL,

fs/super.c

@@ -62,7 +62,7 @@ static int prune_super(struct shrinker *shrink, struct shrink_control *sc)
 		return -1;
 
 	if (!grab_super_passive(sb))
-		return !sc->nr_to_scan ? 0 : -1;
+		return -1;
 
 	if (sb->s_op && sb->s_op->nr_cached_objects)
 		fs_objects = sb->s_op->nr_cached_objects(sb);

include/linux/backing-dev.h

@@ -17,6 +17,7 @@
 #include <linux/timer.h>
 #include <linux/writeback.h>
 #include <linux/atomic.h>
+#include <linux/sysctl.h>
 
 struct page;
 struct device;
@@ -304,6 +305,8 @@ void clear_bdi_congested(struct backing_dev_info *bdi, int sync);
 void set_bdi_congested(struct backing_dev_info *bdi, int sync);
 long congestion_wait(int sync, long timeout);
 long wait_iff_congested(struct zone *zone, int sync, long timeout);
+int pdflush_proc_obsolete(struct ctl_table *table, int write,
+		void __user *buffer, size_t *lenp, loff_t *ppos);
 
 static inline bool bdi_cap_writeback_dirty(struct backing_dev_info *bdi)
 {

include/linux/blk_types.h

@@ -160,6 +160,7 @@ enum rq_flag_bits {
 	__REQ_FLUSH_SEQ,	/* request for flush sequence */
 	__REQ_IO_STAT,		/* account I/O stat */
 	__REQ_MIXED_MERGE,	/* merge of different types, fail separately */
+	__REQ_KERNEL, 		/* direct IO to kernel pages */
 	__REQ_NR_BITS,		/* stops here */
 };
 
@@ -201,5 +202,6 @@ enum rq_flag_bits {
 #define REQ_IO_STAT		(1 << __REQ_IO_STAT)
 #define REQ_MIXED_MERGE		(1 << __REQ_MIXED_MERGE)
 #define REQ_SECURE		(1 << __REQ_SECURE)
+#define REQ_KERNEL		(1 << __REQ_KERNEL)
 
 #endif /* __LINUX_BLK_TYPES_H */

include/linux/cgroup_subsys.h

@@ -31,7 +31,7 @@ SUBSYS(cpuacct)
 
 /* */
 
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+#ifdef CONFIG_MEMCG
 SUBSYS(mem_cgroup)
 #endif
 
@@ -72,3 +72,9 @@ SUBSYS(net_prio)
 #endif
 
 /* */
+
+#ifdef CONFIG_CGROUP_HUGETLB
+SUBSYS(hugetlb)
+#endif
+
+/* */

include/linux/compaction.h

@@ -58,7 +58,7 @@ static inline bool compaction_deferred(struct zone *zone, int order)
 	if (++zone->compact_considered > defer_limit)
 		zone->compact_considered = defer_limit;
 
-	return zone->compact_considered < (1UL << zone->compact_defer_shift);
+	return zone->compact_considered < defer_limit;
 }
 
 #else
@@ -85,7 +85,7 @@ static inline void defer_compaction(struct zone *zone, int order)
 
 static inline bool compaction_deferred(struct zone *zone, int order)
 {
-	return 1;
+	return true;
 }
 
 #endif /* CONFIG_COMPACTION */

include/linux/fs.h

@@ -165,6 +165,8 @@ struct inodes_stat_t {
 #define READ			0
 #define WRITE			RW_MASK
 #define READA			RWA_MASK
+#define KERNEL_READ		(READ|REQ_KERNEL)
+#define KERNEL_WRITE		(WRITE|REQ_KERNEL)
 
 #define READ_SYNC		(READ | REQ_SYNC)
 #define WRITE_SYNC		(WRITE | REQ_SYNC | REQ_NOIDLE)
@@ -427,6 +429,7 @@ struct kstatfs;
 struct vm_area_struct;
 struct vfsmount;
 struct cred;
+struct swap_info_struct;
 
 extern void __init inode_init(void);
 extern void __init inode_init_early(void);
@@ -636,6 +639,11 @@ struct address_space_operations {
 	int (*is_partially_uptodate) (struct page *, read_descriptor_t *,
 					unsigned long);
 	int (*error_remove_page)(struct address_space *, struct page *);
+
+	/* swapfile support */
+	int (*swap_activate)(struct swap_info_struct *sis, struct file *file,
+				sector_t *span);
+	void (*swap_deactivate)(struct file *file);
 };
 
 extern const struct address_space_operations empty_aops;

include/linux/gfp.h

@@ -23,6 +23,7 @@ struct vm_area_struct;
 #define ___GFP_REPEAT		0x400u
 #define ___GFP_NOFAIL		0x800u
 #define ___GFP_NORETRY		0x1000u
+#define ___GFP_MEMALLOC		0x2000u
 #define ___GFP_COMP		0x4000u
 #define ___GFP_ZERO		0x8000u
 #define ___GFP_NOMEMALLOC	0x10000u
@@ -76,9 +77,14 @@ struct vm_area_struct;
 #define __GFP_REPEAT	((__force gfp_t)___GFP_REPEAT)	/* See above */
 #define __GFP_NOFAIL	((__force gfp_t)___GFP_NOFAIL)	/* See above */
 #define __GFP_NORETRY	((__force gfp_t)___GFP_NORETRY) /* See above */
+#define __GFP_MEMALLOC	((__force gfp_t)___GFP_MEMALLOC)/* Allow access to emergency reserves */
 #define __GFP_COMP	((__force gfp_t)___GFP_COMP)	/* Add compound page metadata */
 #define __GFP_ZERO	((__force gfp_t)___GFP_ZERO)	/* Return zeroed page on success */
-#define __GFP_NOMEMALLOC ((__force gfp_t)___GFP_NOMEMALLOC) /* Don't use emergency reserves */
+#define __GFP_NOMEMALLOC ((__force gfp_t)___GFP_NOMEMALLOC) /* Don't use emergency reserves.
+							 * This takes precedence over the
+							 * __GFP_MEMALLOC flag if both are
+							 * set
+							 */
 #define __GFP_HARDWALL   ((__force gfp_t)___GFP_HARDWALL) /* Enforce hardwall cpuset memory allocs */
 #define __GFP_THISNODE	((__force gfp_t)___GFP_THISNODE)/* No fallback, no policies */
 #define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE) /* Page is reclaimable */
@@ -129,7 +135,7 @@ struct vm_area_struct;
 /* Control page allocator reclaim behavior */
 #define GFP_RECLAIM_MASK (__GFP_WAIT|__GFP_HIGH|__GFP_IO|__GFP_FS|\
 			__GFP_NOWARN|__GFP_REPEAT|__GFP_NOFAIL|\
-			__GFP_NORETRY|__GFP_NOMEMALLOC)
+			__GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC)
 
 /* Control slab gfp mask during early boot */
 #define GFP_BOOT_MASK (__GFP_BITS_MASK & ~(__GFP_WAIT|__GFP_IO|__GFP_FS))
@@ -379,6 +385,9 @@ void drain_local_pages(void *dummy);
  */
 extern gfp_t gfp_allowed_mask;
 
+/* Returns true if the gfp_mask allows use of ALLOC_NO_WATERMARK */
+bool gfp_pfmemalloc_allowed(gfp_t gfp_mask);
+
 extern void pm_restrict_gfp_mask(void);
 extern void pm_restore_gfp_mask(void);
 

include/linux/highmem.h

@@ -39,10 +39,17 @@ extern unsigned long totalhigh_pages;
 
 void kmap_flush_unused(void);
 
+struct page *kmap_to_page(void *addr);
+
 #else /* CONFIG_HIGHMEM */
 
 static inline unsigned int nr_free_highpages(void) { return 0; }
 
+static inline struct page *kmap_to_page(void *addr)
+{
+	return virt_to_page(addr);
+}
+
 #define totalhigh_pages 0UL
 
 #ifndef ARCH_HAS_KMAP

include/linux/hugetlb.h

@@ -4,9 +4,11 @@
 #include <linux/mm_types.h>
 #include <linux/fs.h>
 #include <linux/hugetlb_inline.h>
+#include <linux/cgroup.h>
 
 struct ctl_table;
 struct user_struct;
+struct mmu_gather;
 
 #ifdef CONFIG_HUGETLB_PAGE
 
@@ -20,6 +22,11 @@ struct hugepage_subpool {
 	long max_hpages, used_hpages;
 };
 
+extern spinlock_t hugetlb_lock;
+extern int hugetlb_max_hstate __read_mostly;
+#define for_each_hstate(h) \
+	for ((h) = hstates; (h) < &hstates[hugetlb_max_hstate]; (h)++)
+
 struct hugepage_subpool *hugepage_new_subpool(long nr_blocks);
 void hugepage_put_subpool(struct hugepage_subpool *spool);
 
@@ -40,9 +47,14 @@ int follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *,
 			struct page **, struct vm_area_struct **,
 			unsigned long *, int *, int, unsigned int flags);
 void unmap_hugepage_range(struct vm_area_struct *,
-			unsigned long, unsigned long, struct page *);
-void __unmap_hugepage_range(struct vm_area_struct *,
-			unsigned long, unsigned long, struct page *);
+			  unsigned long, unsigned long, struct page *);
+void __unmap_hugepage_range_final(struct mmu_gather *tlb,
+			  struct vm_area_struct *vma,
+			  unsigned long start, unsigned long end,
+			  struct page *ref_page);
+void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
+				unsigned long start, unsigned long end,
+				struct page *ref_page);
 int hugetlb_prefault(struct address_space *, struct vm_area_struct *);
 void hugetlb_report_meminfo(struct seq_file *);
 int hugetlb_report_node_meminfo(int, char *);
@@ -98,7 +110,6 @@ static inline unsigned long hugetlb_total_pages(void)
 #define follow_huge_addr(mm, addr, write)	ERR_PTR(-EINVAL)
 #define copy_hugetlb_page_range(src, dst, vma)	({ BUG(); 0; })
 #define hugetlb_prefault(mapping, vma)		({ BUG(); 0; })
-#define unmap_hugepage_range(vma, start, end, page)	BUG()
 static inline void hugetlb_report_meminfo(struct seq_file *m)
 {
 }
@@ -112,13 +123,31 @@ static inline void hugetlb_report_meminfo(struct seq_file *m)
 #define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) ({BUG(); 0; })
 #define hugetlb_fault(mm, vma, addr, flags)	({ BUG(); 0; })
 #define huge_pte_offset(mm, address)	0
-#define dequeue_hwpoisoned_huge_page(page)	0
+static inline int dequeue_hwpoisoned_huge_page(struct page *page)
+{
+	return 0;
+}
+
 static inline void copy_huge_page(struct page *dst, struct page *src)
 {
 }
 
 #define hugetlb_change_protection(vma, address, end, newprot)
 
+static inline void __unmap_hugepage_range_final(struct mmu_gather *tlb,
+			struct vm_area_struct *vma, unsigned long start,
+			unsigned long end, struct page *ref_page)
+{
+	BUG();
+}
+
+static inline void __unmap_hugepage_range(struct mmu_gather *tlb,
+			struct vm_area_struct *vma, unsigned long start,
+			unsigned long end, struct page *ref_page)
+{
+	BUG();
+}
+
 #endif /* !CONFIG_HUGETLB_PAGE */
 
 #define HUGETLB_ANON_FILE "anon_hugepage"
@@ -199,10 +228,15 @@ struct hstate {
 	unsigned long resv_huge_pages;
 	unsigned long surplus_huge_pages;
 	unsigned long nr_overcommit_huge_pages;
+	struct list_head hugepage_activelist;
 	struct list_head hugepage_freelists[MAX_NUMNODES];
 	unsigned int nr_huge_pages_node[MAX_NUMNODES];
 	unsigned int free_huge_pages_node[MAX_NUMNODES];
 	unsigned int surplus_huge_pages_node[MAX_NUMNODES];
+#ifdef CONFIG_CGROUP_HUGETLB
+	/* cgroup control files */
+	struct cftype cgroup_files[5];
+#endif
 	char name[HSTATE_NAME_LEN];
 };
 
@@ -302,6 +336,11 @@ static inline unsigned hstate_index_to_shift(unsigned index)
 	return hstates[index].order + PAGE_SHIFT;
 }
 
+static inline int hstate_index(struct hstate *h)
+{
+	return h - hstates;
+}
+
 #else
 struct hstate {};
 #define alloc_huge_page_node(h, nid) NULL
@@ -320,6 +359,7 @@ static inline unsigned int pages_per_huge_page(struct hstate *h)
 	return 1;
 }
 #define hstate_index_to_shift(index) 0
+#define hstate_index(h) 0
 #endif
 
 #endif /* _LINUX_HUGETLB_H */

include/linux/hugetlb_cgroup.h

@@ -0,0 +1,126 @@
+/*
+ * 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.
+ *
+ */
+
+#ifndef _LINUX_HUGETLB_CGROUP_H
+#define _LINUX_HUGETLB_CGROUP_H
+
+#include <linux/res_counter.h>
+
+struct hugetlb_cgroup;
+/*
+ * Minimum page order trackable by hugetlb cgroup.
+ * At least 3 pages are necessary for all the tracking information.
+ */
+#define HUGETLB_CGROUP_MIN_ORDER	2
+
+#ifdef CONFIG_CGROUP_HUGETLB
+
+static inline struct hugetlb_cgroup *hugetlb_cgroup_from_page(struct page *page)
+{
+	VM_BUG_ON(!PageHuge(page));
+
+	if (compound_order(page) < HUGETLB_CGROUP_MIN_ORDER)
+		return NULL;
+	return (struct hugetlb_cgroup *)page[2].lru.next;
+}
+
+static inline
+int set_hugetlb_cgroup(struct page *page, struct hugetlb_cgroup *h_cg)
+{
+	VM_BUG_ON(!PageHuge(page));
+
+	if (compound_order(page) < HUGETLB_CGROUP_MIN_ORDER)
+		return -1;
+	page[2].lru.next = (void *)h_cg;
+	return 0;
+}
+
+static inline bool hugetlb_cgroup_disabled(void)
+{
+	if (hugetlb_subsys.disabled)
+		return true;
+	return false;
+}
+
+extern int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages,
+					struct hugetlb_cgroup **ptr);
+extern void hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages,
+					 struct hugetlb_cgroup *h_cg,
+					 struct page *page);
+extern void hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages,
+					 struct page *page);
+extern void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages,
+					   struct hugetlb_cgroup *h_cg);
+extern int hugetlb_cgroup_file_init(int idx) __init;
+extern void hugetlb_cgroup_migrate(struct page *oldhpage,
+				   struct page *newhpage);
+
+#else
+static inline struct hugetlb_cgroup *hugetlb_cgroup_from_page(struct page *page)
+{
+	return NULL;
+}
+
+static inline
+int set_hugetlb_cgroup(struct page *page, struct hugetlb_cgroup *h_cg)
+{
+	return 0;
+}
+
+static inline bool hugetlb_cgroup_disabled(void)
+{
+	return true;
+}
+
+static inline int
+hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages,
+			     struct hugetlb_cgroup **ptr)
+{
+	return 0;
+}
+
+static inline void
+hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages,
+			     struct hugetlb_cgroup *h_cg,
+			     struct page *page)
+{
+	return;
+}
+
+static inline void
+hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages, struct page *page)
+{
+	return;
+}
+
+static inline void
+hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages,
+			       struct hugetlb_cgroup *h_cg)
+{
+	return;
+}
+
+static inline int __init hugetlb_cgroup_file_init(int idx)
+{
+	return 0;
+}
+
+static inline void hugetlb_cgroup_migrate(struct page *oldhpage,
+					  struct page *newhpage)
+{
+	return;
+}
+
+#endif  /* CONFIG_MEM_RES_CTLR_HUGETLB */
+#endif

include/linux/memcontrol.h

@@ -38,7 +38,7 @@ struct mem_cgroup_reclaim_cookie {
 	unsigned int generation;
 };
 
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+#ifdef CONFIG_MEMCG
 /*
  * All "charge" functions with gfp_mask should use GFP_KERNEL or
  * (gfp_mask & GFP_RECLAIM_MASK). In current implementatin, memcg doesn't
@@ -72,8 +72,6 @@ extern void mem_cgroup_uncharge_end(void);
 extern void mem_cgroup_uncharge_page(struct page *page);
 extern void mem_cgroup_uncharge_cache_page(struct page *page);
 
-extern void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
-				     int order);
 bool __mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg,
 				  struct mem_cgroup *memcg);
 int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *memcg);
@@ -100,9 +98,9 @@ int mm_match_cgroup(const struct mm_struct *mm, const struct mem_cgroup *cgroup)
 
 extern struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg);
 
-extern int
-mem_cgroup_prepare_migration(struct page *page,
-	struct page *newpage, struct mem_cgroup **memcgp, gfp_t gfp_mask);
+extern void
+mem_cgroup_prepare_migration(struct page *page, struct page *newpage,
+			     struct mem_cgroup **memcgp);
 extern void mem_cgroup_end_migration(struct mem_cgroup *memcg,
 	struct page *oldpage, struct page *newpage, bool migration_ok);
 
@@ -124,7 +122,7 @@ extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg,
 extern void mem_cgroup_replace_page_cache(struct page *oldpage,
 					struct page *newpage);
 
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+#ifdef CONFIG_MEMCG_SWAP
 extern int do_swap_account;
 #endif
 
@@ -182,7 +180,6 @@ static inline void mem_cgroup_dec_page_stat(struct page *page,
 unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
 						gfp_t gfp_mask,
 						unsigned long *total_scanned);
-u64 mem_cgroup_get_limit(struct mem_cgroup *memcg);
 
 void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx);
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -193,7 +190,7 @@ void mem_cgroup_split_huge_fixup(struct page *head);
 bool mem_cgroup_bad_page_check(struct page *page);
 void mem_cgroup_print_bad_page(struct page *page);
 #endif
-#else /* CONFIG_CGROUP_MEM_RES_CTLR */
+#else /* CONFIG_MEMCG */
 struct mem_cgroup;
 
 static inline int mem_cgroup_newpage_charge(struct page *page,
@@ -279,11 +276,10 @@ static inline struct cgroup_subsys_state
 	return NULL;
 }
 
-static inline int
+static inline void
 mem_cgroup_prepare_migration(struct page *page, struct page *newpage,
-	struct mem_cgroup **memcgp, gfp_t gfp_mask)
+			     struct mem_cgroup **memcgp)
 {
-	return 0;
 }
 
 static inline void mem_cgroup_end_migration(struct mem_cgroup *memcg,
@@ -366,12 +362,6 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
 	return 0;
 }
 
-static inline
-u64 mem_cgroup_get_limit(struct mem_cgroup *memcg)
-{
-	return 0;
-}
-
 static inline void mem_cgroup_split_huge_fixup(struct page *head)
 {
 }
@@ -384,9 +374,9 @@ static inline void mem_cgroup_replace_page_cache(struct page *oldpage,
 				struct page *newpage)
 {
 }
-#endif /* CONFIG_CGROUP_MEM_RES_CTLR */
+#endif /* CONFIG_MEMCG */
 
-#if !defined(CONFIG_CGROUP_MEM_RES_CTLR) || !defined(CONFIG_DEBUG_VM)
+#if !defined(CONFIG_MEMCG) || !defined(CONFIG_DEBUG_VM)
 static inline bool
 mem_cgroup_bad_page_check(struct page *page)
 {
@@ -406,7 +396,7 @@ enum {
 };
 
 struct sock;
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+#ifdef CONFIG_MEMCG_KMEM
 void sock_update_memcg(struct sock *sk);
 void sock_release_memcg(struct sock *sk);
 #else
@@ -416,6 +406,6 @@ static inline void sock_update_memcg(struct sock *sk)
 static inline void sock_release_memcg(struct sock *sk)
 {
 }
-#endif /* CONFIG_CGROUP_MEM_RES_CTLR_KMEM */
+#endif /* CONFIG_MEMCG_KMEM */
 #endif /* _LINUX_MEMCONTROL_H */
 

include/linux/migrate.h

@@ -15,7 +15,7 @@ extern int migrate_page(struct address_space *,
 extern int migrate_pages(struct list_head *l, new_page_t x,
 			unsigned long private, bool offlining,
 			enum migrate_mode mode);
-extern int migrate_huge_pages(struct list_head *l, new_page_t x,
+extern int migrate_huge_page(struct page *, new_page_t x,
 			unsigned long private, bool offlining,
 			enum migrate_mode mode);
 
@@ -36,7 +36,7 @@ static inline void putback_lru_pages(struct list_head *l) {}
 static inline int migrate_pages(struct list_head *l, new_page_t x,
 		unsigned long private, bool offlining,
 		enum migrate_mode mode) { return -ENOSYS; }
-static inline int migrate_huge_pages(struct list_head *l, new_page_t x,
+static inline int migrate_huge_page(struct page *page, new_page_t x,
 		unsigned long private, bool offlining,
 		enum migrate_mode mode) { return -ENOSYS; }
 

include/linux/mm.h

@@ -805,6 +805,17 @@ static inline void *page_rmapping(struct page *page)
 	return (void *)((unsigned long)page->mapping & ~PAGE_MAPPING_FLAGS);
 }
 
+extern struct address_space *__page_file_mapping(struct page *);
+
+static inline
+struct address_space *page_file_mapping(struct page *page)
+{
+	if (unlikely(PageSwapCache(page)))
+		return __page_file_mapping(page);
+
+	return page->mapping;
+}
+
 static inline int PageAnon(struct page *page)
 {
 	return ((unsigned long)page->mapping & PAGE_MAPPING_ANON) != 0;
@@ -821,6 +832,20 @@ static inline pgoff_t page_index(struct page *page)
 	return page->index;
 }
 
+extern pgoff_t __page_file_index(struct page *page);
+
+/*
+ * Return the file index of the page. Regular pagecache pages use ->index
+ * whereas swapcache pages use swp_offset(->private)
+ */
+static inline pgoff_t page_file_index(struct page *page)
+{
+	if (unlikely(PageSwapCache(page)))
+		return __page_file_index(page);
+
+	return page->index;
+}
+
 /*
  * Return true if this page is mapped into pagetables.
  */
@@ -994,6 +1019,10 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 			struct page **pages, struct vm_area_struct **vmas);
 int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 			struct page **pages);
+struct kvec;
+int get_kernel_pages(const struct kvec *iov, int nr_pages, int write,
+			struct page **pages);
+int get_kernel_page(unsigned long start, int write, struct page **pages);
 struct page *get_dump_page(unsigned long addr);
 
 extern int try_to_release_page(struct page * page, gfp_t gfp_mask);
@@ -1331,6 +1360,7 @@ void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...);
 extern void setup_per_cpu_pageset(void);
 
 extern void zone_pcp_update(struct zone *zone);
+extern void zone_pcp_reset(struct zone *zone);
 
 /* nommu.c */
 extern atomic_long_t mmap_pages_allocated;
@@ -1528,6 +1558,7 @@ void vm_stat_account(struct mm_struct *, unsigned long, struct file *, long);
 static inline void vm_stat_account(struct mm_struct *mm,
 			unsigned long flags, struct file *file, long pages)
 {
+	mm->total_vm += pages;
 }
 #endif /* CONFIG_PROC_FS */
 

include/linux/mm_types.h

@@ -54,6 +54,15 @@ struct page {
 		union {
 			pgoff_t index;		/* Our offset within mapping. */
 			void *freelist;		/* slub/slob first free object */
+			bool pfmemalloc;	/* If set by the page allocator,
+						 * ALLOC_NO_WATERMARKS was set
+						 * and the low watermark was not
+						 * met implying that the system
+						 * is under some pressure. The
+						 * caller should try ensure
+						 * this page is only used to
+						 * free other pages.
+						 */
 		};
 
 		union {

include/linux/mmzone.h

@@ -201,7 +201,7 @@ struct zone_reclaim_stat {
 struct lruvec {
 	struct list_head lists[NR_LRU_LISTS];
 	struct zone_reclaim_stat reclaim_stat;
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+#ifdef CONFIG_MEMCG
 	struct zone *zone;
 #endif
 };
@@ -209,7 +209,6 @@ struct lruvec {
 /* Mask used at gathering information at once (see memcontrol.c) */
 #define LRU_ALL_FILE (BIT(LRU_INACTIVE_FILE) | BIT(LRU_ACTIVE_FILE))
 #define LRU_ALL_ANON (BIT(LRU_INACTIVE_ANON) | BIT(LRU_ACTIVE_ANON))
-#define LRU_ALL_EVICTABLE (LRU_ALL_FILE | LRU_ALL_ANON)
 #define LRU_ALL	     ((1 << NR_LRU_LISTS) - 1)
 
 /* Isolate clean file */
@@ -369,6 +368,10 @@ struct zone {
 	 */
 	spinlock_t		lock;
 	int                     all_unreclaimable; /* All pages pinned */
+#if defined CONFIG_COMPACTION || defined CONFIG_CMA
+	/* pfn where the last incremental compaction isolated free pages */
+	unsigned long		compact_cached_free_pfn;
+#endif
 #ifdef CONFIG_MEMORY_HOTPLUG
 	/* see spanned/present_pages for more description */
 	seqlock_t		span_seqlock;
@@ -475,6 +478,14 @@ struct zone {
 	 * rarely used fields:
 	 */
 	const char		*name;
+#ifdef CONFIG_MEMORY_ISOLATION
+	/*
+	 * the number of MIGRATE_ISOLATE *pageblock*.
+	 * We need this for free page counting. Look at zone_watermark_ok_safe.
+	 * It's protected by zone->lock
+	 */
+	int		nr_pageblock_isolate;
+#endif
 } ____cacheline_internodealigned_in_smp;
 
 typedef enum {
@@ -671,7 +682,7 @@ typedef struct pglist_data {
 	int nr_zones;
 #ifdef CONFIG_FLAT_NODE_MEM_MAP	/* means !SPARSEMEM */
 	struct page *node_mem_map;
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+#ifdef CONFIG_MEMCG
 	struct page_cgroup *node_page_cgroup;
 #endif
 #endif
@@ -694,6 +705,7 @@ typedef struct pglist_data {
 					     range, including holes */
 	int node_id;
 	wait_queue_head_t kswapd_wait;
+	wait_queue_head_t pfmemalloc_wait;
 	struct task_struct *kswapd;	/* Protected by lock_memory_hotplug() */
 	int kswapd_max_order;
 	enum zone_type classzone_idx;
@@ -718,7 +730,7 @@ typedef struct pglist_data {
 #include <linux/memory_hotplug.h>
 
 extern struct mutex zonelists_mutex;
-void build_all_zonelists(void *data);
+void build_all_zonelists(pg_data_t *pgdat, struct zone *zone);
 void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx);
 bool zone_watermark_ok(struct zone *z, int order, unsigned long mark,
 		int classzone_idx, int alloc_flags);
@@ -736,7 +748,7 @@ extern void lruvec_init(struct lruvec *lruvec, struct zone *zone);
 
 static inline struct zone *lruvec_zone(struct lruvec *lruvec)
 {
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+#ifdef CONFIG_MEMCG
 	return lruvec->zone;
 #else
 	return container_of(lruvec, struct zone, lruvec);
@@ -773,7 +785,7 @@ extern int movable_zone;
 
 static inline int zone_movable_is_highmem(void)
 {
-#if defined(CONFIG_HIGHMEM) && defined(CONFIG_HAVE_MEMBLOCK_NODE)
+#if defined(CONFIG_HIGHMEM) && defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP)
 	return movable_zone == ZONE_HIGHMEM;
 #else
 	return 0;
@@ -1052,7 +1064,7 @@ struct mem_section {
 
 	/* See declaration of similar field in struct zone */
 	unsigned long *pageblock_flags;
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+#ifdef CONFIG_MEMCG
 	/*
 	 * If !SPARSEMEM, pgdat doesn't have page_cgroup pointer. We use
 	 * section. (see memcontrol.h/page_cgroup.h about this.)

include/linux/nfs_fs.h

@@ -473,10 +473,10 @@ extern ssize_t nfs_direct_IO(int, struct kiocb *, const struct iovec *, loff_t,
 			unsigned long);
 extern ssize_t nfs_file_direct_read(struct kiocb *iocb,
 			const struct iovec *iov, unsigned long nr_segs,
-			loff_t pos);
+			loff_t pos, bool uio);
 extern ssize_t nfs_file_direct_write(struct kiocb *iocb,
 			const struct iovec *iov, unsigned long nr_segs,
-			loff_t pos);
+			loff_t pos, bool uio);
 
 /*
  * linux/fs/nfs/dir.c

include/linux/oom.h

@@ -40,15 +40,36 @@ enum oom_constraint {
 	CONSTRAINT_MEMCG,
 };
 
+enum oom_scan_t {
+	OOM_SCAN_OK,		/* scan thread and find its badness */
+	OOM_SCAN_CONTINUE,	/* do not consider thread for oom kill */
+	OOM_SCAN_ABORT,		/* abort the iteration and return */
+	OOM_SCAN_SELECT,	/* always select this thread first */
+};
+
 extern void compare_swap_oom_score_adj(int old_val, int new_val);
 extern int test_set_oom_score_adj(int new_val);
 
 extern unsigned long oom_badness(struct task_struct *p,
 		struct mem_cgroup *memcg, const nodemask_t *nodemask,
 		unsigned long totalpages);
+extern 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);
+
 extern int try_set_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_flags);
 extern void clear_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_flags);
 
+extern void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask,
+			       int order, const nodemask_t *nodemask);
+
+extern enum oom_scan_t oom_scan_process_thread(struct task_struct *task,
+		unsigned long totalpages, const nodemask_t *nodemask,
+		bool force_kill);
+extern void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
+				     int order);
+
 extern void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
 		int order, nodemask_t *mask, bool force_kill);
 extern int register_oom_notifier(struct notifier_block *nb);

include/linux/page-flags.h

@@ -7,6 +7,7 @@
 
 #include <linux/types.h>
 #include <linux/bug.h>
+#include <linux/mmdebug.h>
 #ifndef __GENERATING_BOUNDS_H
 #include <linux/mm_types.h>
 #include <generated/bounds.h>
@@ -453,6 +454,34 @@ static inline int PageTransTail(struct page *page)
 }
 #endif
 
+/*
+ * If network-based swap is enabled, sl*b must keep track of whether pages
+ * were allocated from pfmemalloc reserves.
+ */
+static inline int PageSlabPfmemalloc(struct page *page)
+{
+	VM_BUG_ON(!PageSlab(page));
+	return PageActive(page);
+}
+
+static inline void SetPageSlabPfmemalloc(struct page *page)
+{
+	VM_BUG_ON(!PageSlab(page));
+	SetPageActive(page);
+}
+
+static inline void __ClearPageSlabPfmemalloc(struct page *page)
+{
+	VM_BUG_ON(!PageSlab(page));
+	__ClearPageActive(page);
+}
+
+static inline void ClearPageSlabPfmemalloc(struct page *page)
+{
+	VM_BUG_ON(!PageSlab(page));
+	ClearPageActive(page);
+}
+
 #ifdef CONFIG_MMU
 #define __PG_MLOCKED		(1 << PG_mlocked)
 #else

include/linux/page-isolation.h

@@ -1,6 +1,11 @@
 #ifndef __LINUX_PAGEISOLATION_H
 #define __LINUX_PAGEISOLATION_H
 
+
+bool has_unmovable_pages(struct zone *zone, struct page *page, int count);
+void set_pageblock_migratetype(struct page *page, int migratetype);
+int move_freepages_block(struct zone *zone, struct page *page,
+				int migratetype);
 /*
  * Changes migrate type in [start_pfn, end_pfn) to be MIGRATE_ISOLATE.
  * If specified range includes migrate types other than MOVABLE or CMA,
@@ -10,7 +15,7 @@
  * free all pages in the range. test_page_isolated() can be used for
  * test it.
  */
-extern int
+int
 start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 			 unsigned migratetype);
 
@@ -18,7 +23,7 @@ start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
  * Changes MIGRATE_ISOLATE to MIGRATE_MOVABLE.
  * target range is [start_pfn, end_pfn)
  */
-extern int
+int
 undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 			unsigned migratetype);
 
@@ -30,8 +35,8 @@ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn);
 /*
  * Internal functions. Changes pageblock's migrate type.
  */
-extern int set_migratetype_isolate(struct page *page);
-extern void unset_migratetype_isolate(struct page *page, unsigned migratetype);
+int set_migratetype_isolate(struct page *page);
+void unset_migratetype_isolate(struct page *page, unsigned migratetype);
 
 
 #endif

include/linux/page_cgroup.h

@@ -12,7 +12,7 @@ enum {
 #ifndef __GENERATING_BOUNDS_H
 #include <generated/bounds.h>
 
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+#ifdef CONFIG_MEMCG
 #include <linux/bit_spinlock.h>
 
 /*
@@ -82,7 +82,7 @@ static inline void unlock_page_cgroup(struct page_cgroup *pc)
 	bit_spin_unlock(PCG_LOCK, &pc->flags);
 }
 
-#else /* CONFIG_CGROUP_MEM_RES_CTLR */
+#else /* CONFIG_MEMCG */
 struct page_cgroup;
 
 static inline void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat)
@@ -102,11 +102,11 @@ static inline void __init page_cgroup_init_flatmem(void)
 {
 }
 
-#endif /* CONFIG_CGROUP_MEM_RES_CTLR */
+#endif /* CONFIG_MEMCG */
 
 #include <linux/swap.h>
 
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+#ifdef CONFIG_MEMCG_SWAP
 extern unsigned short swap_cgroup_cmpxchg(swp_entry_t ent,
 					unsigned short old, unsigned short new);
 extern unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id);
@@ -138,7 +138,7 @@ static inline void swap_cgroup_swapoff(int type)
 	return;
 }
 
-#endif /* CONFIG_CGROUP_MEM_RES_CTLR_SWAP */
+#endif /* CONFIG_MEMCG_SWAP */
 
 #endif /* !__GENERATING_BOUNDS_H */
 

include/linux/pagemap.h

@@ -286,6 +286,11 @@ static inline loff_t page_offset(struct page *page)
 	return ((loff_t)page->index) << PAGE_CACHE_SHIFT;
 }
 
+static inline loff_t page_file_offset(struct page *page)
+{
+	return ((loff_t)page_file_index(page)) << PAGE_CACHE_SHIFT;
+}
+
 extern pgoff_t linear_hugepage_index(struct vm_area_struct *vma,
 				     unsigned long address);
 

include/linux/sched.h

@@ -1584,7 +1584,7 @@ struct task_struct {
 	/* bitmask and counter of trace recursion */
 	unsigned long trace_recursion;
 #endif /* CONFIG_TRACING */
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR /* memcg uses this to do batch job */
+#ifdef CONFIG_MEMCG /* memcg uses this to do batch job */
 	struct memcg_batch_info {
 		int do_batch;	/* incremented when batch uncharge started */
 		struct mem_cgroup *memcg; /* target memcg of uncharge */
@@ -1894,6 +1894,13 @@ static inline void rcu_copy_process(struct task_struct *p)
 
 #endif
 
+static inline void tsk_restore_flags(struct task_struct *task,
+				unsigned long orig_flags, unsigned long flags)
+{
+	task->flags &= ~flags;
+	task->flags |= orig_flags & flags;
+}
+
 #ifdef CONFIG_SMP
 extern void do_set_cpus_allowed(struct task_struct *p,
 			       const struct cpumask *new_mask);

include/linux/shrinker.h

@@ -20,7 +20,6 @@ struct shrink_control {
  * 'nr_to_scan' entries and attempt to free them up.  It should return
  * the number of objects which remain in the cache.  If it returns -1, it means
  * it cannot do any scanning at this time (eg. there is a risk of deadlock).
- * The callback must not return -1 if nr_to_scan is zero.
  *
  * The 'gfpmask' refers to the allocation we are currently trying to
  * fulfil.

include/linux/skbuff.h

@@ -462,6 +462,7 @@ struct sk_buff {
 #ifdef CONFIG_IPV6_NDISC_NODETYPE
 	__u8			ndisc_nodetype:2;
 #endif
+	__u8			pfmemalloc:1;
 	__u8			ooo_okay:1;
 	__u8			l4_rxhash:1;
 	__u8			wifi_acked_valid:1;
@@ -502,6 +503,15 @@ struct sk_buff {
 #include <linux/slab.h>
 
 
+#define SKB_ALLOC_FCLONE	0x01
+#define SKB_ALLOC_RX		0x02
+
+/* Returns true if the skb was allocated from PFMEMALLOC reserves */
+static inline bool skb_pfmemalloc(const struct sk_buff *skb)
+{
+	return unlikely(skb->pfmemalloc);
+}
+
 /*
  * skb might have a dst pointer attached, refcounted or not.
  * _skb_refdst low order bit is set if refcount was _not_ taken
@@ -565,7 +575,7 @@ extern bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
 			     bool *fragstolen, int *delta_truesize);
 
 extern struct sk_buff *__alloc_skb(unsigned int size,
-				   gfp_t priority, int fclone, int node);
+				   gfp_t priority, int flags, int node);
 extern struct sk_buff *build_skb(void *data, unsigned int frag_size);
 static inline struct sk_buff *alloc_skb(unsigned int size,
 					gfp_t priority)
@@ -576,7 +586,7 @@ static inline struct sk_buff *alloc_skb(unsigned int size,
 static inline struct sk_buff *alloc_skb_fclone(unsigned int size,
 					       gfp_t priority)
 {
-	return __alloc_skb(size, priority, 1, NUMA_NO_NODE);
+	return __alloc_skb(size, priority, SKB_ALLOC_FCLONE, NUMA_NO_NODE);
 }
 
 extern void skb_recycle(struct sk_buff *skb);
@@ -1237,6 +1247,17 @@ static inline void __skb_fill_page_desc(struct sk_buff *skb, int i,
 {
 	skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
 
+	/*
+	 * Propagate page->pfmemalloc to the skb if we can. The problem is
+	 * that not all callers have unique ownership of the page. If
+	 * pfmemalloc is set, we check the mapping as a mapping implies
+	 * page->index is set (index and pfmemalloc share space).
+	 * If it's a valid mapping, we cannot use page->pfmemalloc but we
+	 * do not lose pfmemalloc information as the pages would not be
+	 * allocated using __GFP_MEMALLOC.
+	 */
+	if (page->pfmemalloc && !page->mapping)
+		skb->pfmemalloc	= true;
 	frag->page.p		  = page;
 	frag->page_offset	  = off;
 	skb_frag_size_set(frag, size);
@@ -1753,6 +1774,61 @@ static inline struct sk_buff *netdev_alloc_skb_ip_align(struct net_device *dev,
 	return __netdev_alloc_skb_ip_align(dev, length, GFP_ATOMIC);
 }
 
+/*
+ *	__skb_alloc_page - allocate pages for ps-rx on a skb and preserve pfmemalloc data
+ *	@gfp_mask: alloc_pages_node mask. Set __GFP_NOMEMALLOC if not for network packet RX
+ *	@skb: skb to set pfmemalloc on if __GFP_MEMALLOC is used
+ *	@order: size of the allocation
+ *
+ * 	Allocate a new page.
+ *
+ * 	%NULL is returned if there is no free memory.
+*/
+static inline struct page *__skb_alloc_pages(gfp_t gfp_mask,
+					      struct sk_buff *skb,
+					      unsigned int order)
+{
+	struct page *page;
+
+	gfp_mask |= __GFP_COLD;
+
+	if (!(gfp_mask & __GFP_NOMEMALLOC))
+		gfp_mask |= __GFP_MEMALLOC;
+
+	page = alloc_pages_node(NUMA_NO_NODE, gfp_mask, order);
+	if (skb && page && page->pfmemalloc)
+		skb->pfmemalloc = true;
+
+	return page;
+}
+
+/**
+ *	__skb_alloc_page - allocate a page for ps-rx for a given skb and preserve pfmemalloc data
+ *	@gfp_mask: alloc_pages_node mask. Set __GFP_NOMEMALLOC if not for network packet RX
+ *	@skb: skb to set pfmemalloc on if __GFP_MEMALLOC is used
+ *
+ * 	Allocate a new page.
+ *
+ * 	%NULL is returned if there is no free memory.
+ */
+static inline struct page *__skb_alloc_page(gfp_t gfp_mask,
+					     struct sk_buff *skb)
+{
+	return __skb_alloc_pages(gfp_mask, skb, 0);
+}
+
+/**
+ *	skb_propagate_pfmemalloc - Propagate pfmemalloc if skb is allocated after RX page
+ *	@page: The page that was allocated from skb_alloc_page
+ *	@skb: The skb that may need pfmemalloc set
+ */
+static inline void skb_propagate_pfmemalloc(struct page *page,
+					     struct sk_buff *skb)
+{
+	if (page && page->pfmemalloc)
+		skb->pfmemalloc = true;
+}
+
 /**
  * skb_frag_page - retrieve the page refered to by a paged fragment
  * @frag: the paged fragment

include/linux/sunrpc/xprt.h

@@ -174,6 +174,8 @@ struct rpc_xprt {
 	unsigned long		state;		/* transport state */
 	unsigned char		shutdown   : 1,	/* being shut down */
 				resvport   : 1; /* use a reserved port */
+	unsigned int		swapper;	/* we're swapping over this
+						   transport */
 	unsigned int		bind_index;	/* bind function index */
 
 	/*
@@ -316,6 +318,7 @@ void			xprt_release_rqst_cong(struct rpc_task *task);
 void			xprt_disconnect_done(struct rpc_xprt *xprt);
 void			xprt_force_disconnect(struct rpc_xprt *xprt);
 void			xprt_conditional_disconnect(struct rpc_xprt *xprt, unsigned int cookie);
+int			xs_swapper(struct rpc_xprt *xprt, int enable);
 
 /*
  * Reserved bit positions in xprt->state

include/linux/swap.h

@@ -151,6 +151,7 @@ enum {
 	SWP_SOLIDSTATE	= (1 << 4),	/* blkdev seeks are cheap */
 	SWP_CONTINUED	= (1 << 5),	/* swap_map has count continuation */
 	SWP_BLKDEV	= (1 << 6),	/* its a block device */
+	SWP_FILE	= (1 << 7),	/* set after swap_activate success */
 					/* add others here before... */
 	SWP_SCANNING	= (1 << 8),	/* refcount in scan_swap_map */
 };
@@ -301,7 +302,7 @@ static inline void scan_unevictable_unregister_node(struct node *node)
 
 extern int kswapd_run(int nid);
 extern void kswapd_stop(int nid);
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+#ifdef CONFIG_MEMCG
 extern int mem_cgroup_swappiness(struct mem_cgroup *mem);
 #else
 static inline int mem_cgroup_swappiness(struct mem_cgroup *mem)
@@ -309,7 +310,7 @@ static inline int mem_cgroup_swappiness(struct mem_cgroup *mem)
 	return vm_swappiness;
 }
 #endif
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+#ifdef CONFIG_MEMCG_SWAP
 extern void mem_cgroup_uncharge_swap(swp_entry_t ent);
 #else
 static inline void mem_cgroup_uncharge_swap(swp_entry_t ent)
@@ -320,8 +321,14 @@ static inline void mem_cgroup_uncharge_swap(swp_entry_t ent)
 /* linux/mm/page_io.c */
 extern int swap_readpage(struct page *);
 extern int swap_writepage(struct page *page, struct writeback_control *wbc);
+extern int swap_set_page_dirty(struct page *page);
 extern void end_swap_bio_read(struct bio *bio, int err);
 
+int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page,
+		unsigned long nr_pages, sector_t start_block);
+int generic_swapfile_activate(struct swap_info_struct *, struct file *,
+		sector_t *);
+
 /* linux/mm/swap_state.c */
 extern struct address_space swapper_space;
 #define total_swapcache_pages  swapper_space.nrpages
@@ -356,11 +363,12 @@ extern unsigned int count_swap_pages(int, int);
 extern sector_t map_swap_page(struct page *, struct block_device **);
 extern sector_t swapdev_block(int, pgoff_t);
 extern int page_swapcount(struct page *);
+extern struct swap_info_struct *page_swap_info(struct page *);
 extern int reuse_swap_page(struct page *);
 extern int try_to_free_swap(struct page *);
 struct backing_dev_info;
 
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+#ifdef CONFIG_MEMCG
 extern void
 mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout);
 #else

include/linux/vm_event_item.h

@@ -30,6 +30,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		FOR_ALL_ZONES(PGSTEAL_DIRECT),
 		FOR_ALL_ZONES(PGSCAN_KSWAPD),
 		FOR_ALL_ZONES(PGSCAN_DIRECT),
+		PGSCAN_DIRECT_THROTTLE,
 #ifdef CONFIG_NUMA
 		PGSCAN_ZONE_RECLAIM_FAILED,
 #endif

include/linux/vmstat.h

@@ -179,11 +179,6 @@ extern void zone_statistics(struct zone *, struct zone *, gfp_t gfp);
 #define add_zone_page_state(__z, __i, __d) mod_zone_page_state(__z, __i, __d)
 #define sub_zone_page_state(__z, __i, __d) mod_zone_page_state(__z, __i, -(__d))
 
-static inline void zap_zone_vm_stats(struct zone *zone)
-{
-	memset(zone->vm_stat, 0, sizeof(zone->vm_stat));
-}
-
 extern void inc_zone_state(struct zone *, enum zone_stat_item);
 
 #ifdef CONFIG_SMP

include/linux/writeback.h

@@ -189,9 +189,4 @@ void tag_pages_for_writeback(struct address_space *mapping,
 
 void account_page_redirty(struct page *page);
 
-/* pdflush.c */
-extern int nr_pdflush_threads;	/* Global so it can be exported to sysctl
-				   read-only. */
-
-
 #endif		/* WRITEBACK_H */

include/net/sock.h

@@ -621,6 +621,7 @@ enum sock_flags {
 	SOCK_RCVTSTAMPNS, /* %SO_TIMESTAMPNS setting */
 	SOCK_LOCALROUTE, /* route locally only, %SO_DONTROUTE setting */
 	SOCK_QUEUE_SHRUNK, /* write queue has been shrunk recently */
+	SOCK_MEMALLOC, /* VM depends on this socket for swapping */
 	SOCK_TIMESTAMPING_TX_HARDWARE,  /* %SOF_TIMESTAMPING_TX_HARDWARE */
 	SOCK_TIMESTAMPING_TX_SOFTWARE,  /* %SOF_TIMESTAMPING_TX_SOFTWARE */
 	SOCK_TIMESTAMPING_RX_HARDWARE,  /* %SOF_TIMESTAMPING_RX_HARDWARE */
@@ -658,6 +659,26 @@ static inline bool sock_flag(const struct sock *sk, enum sock_flags flag)
 	return test_bit(flag, &sk->sk_flags);
 }
 
+#ifdef CONFIG_NET
+extern struct static_key memalloc_socks;
+static inline int sk_memalloc_socks(void)
+{
+	return static_key_false(&memalloc_socks);
+}
+#else
+
+static inline int sk_memalloc_socks(void)
+{
+	return 0;
+}
+
+#endif
+
+static inline gfp_t sk_gfp_atomic(struct sock *sk, gfp_t gfp_mask)
+{
+	return GFP_ATOMIC | (sk->sk_allocation & __GFP_MEMALLOC);
+}
+
 static inline void sk_acceptq_removed(struct sock *sk)
 {
 	sk->sk_ack_backlog--;
@@ -733,8 +754,13 @@ static inline __must_check int sk_add_backlog(struct sock *sk, struct sk_buff *s
 	return 0;
 }
 
+extern int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb);
+
 static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
 {
+	if (sk_memalloc_socks() && skb_pfmemalloc(skb))
+		return __sk_backlog_rcv(sk, skb);
+
 	return sk->sk_backlog_rcv(sk, skb);
 }
 
@@ -798,6 +824,8 @@ extern int sk_stream_wait_memory(struct sock *sk, long *timeo_p);
 extern void sk_stream_wait_close(struct sock *sk, long timeo_p);
 extern int sk_stream_error(struct sock *sk, int flags, int err);
 extern void sk_stream_kill_queues(struct sock *sk);
+extern void sk_set_memalloc(struct sock *sk);
+extern void sk_clear_memalloc(struct sock *sk);
 
 extern int sk_wait_data(struct sock *sk, long *timeo);
 
@@ -913,7 +941,7 @@ struct proto {
 #ifdef SOCK_REFCNT_DEBUG
 	atomic_t		socks;
 #endif
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+#ifdef CONFIG_MEMCG_KMEM
 	/*
 	 * cgroup specific init/deinit functions. Called once for all
 	 * protocols that implement it, from cgroups populate function.
@@ -994,7 +1022,7 @@ inline void sk_refcnt_debug_release(const struct sock *sk)
 #define sk_refcnt_debug_release(sk) do { } while (0)
 #endif /* SOCK_REFCNT_DEBUG */
 
-#if defined(CONFIG_CGROUP_MEM_RES_CTLR_KMEM) && defined(CONFIG_NET)
+#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_NET)
 extern struct static_key memcg_socket_limit_enabled;
 static inline struct cg_proto *parent_cg_proto(struct proto *proto,
 					       struct cg_proto *cg_proto)
@@ -1301,12 +1329,14 @@ static inline bool sk_wmem_schedule(struct sock *sk, int size)
 		__sk_mem_schedule(sk, size, SK_MEM_SEND);
 }
 
-static inline bool sk_rmem_schedule(struct sock *sk, int size)
+static inline bool
+sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, unsigned int size)
 {
 	if (!sk_has_account(sk))
 		return true;
-	return size <= sk->sk_forward_alloc ||
-		__sk_mem_schedule(sk, size, SK_MEM_RECV);
+	return size<= sk->sk_forward_alloc ||
+		__sk_mem_schedule(sk, size, SK_MEM_RECV) ||
+		skb_pfmemalloc(skb);
 }
 
 static inline void sk_mem_reclaim(struct sock *sk)

include/trace/events/gfpflags.h

@@ -30,6 +30,7 @@
 	{(unsigned long)__GFP_COMP,		"GFP_COMP"},		\
 	{(unsigned long)__GFP_ZERO,		"GFP_ZERO"},		\
 	{(unsigned long)__GFP_NOMEMALLOC,	"GFP_NOMEMALLOC"},	\
+	{(unsigned long)__GFP_MEMALLOC,		"GFP_MEMALLOC"},	\
 	{(unsigned long)__GFP_HARDWALL,		"GFP_HARDWALL"},	\
 	{(unsigned long)__GFP_THISNODE,		"GFP_THISNODE"},	\
 	{(unsigned long)__GFP_RECLAIMABLE,	"GFP_RECLAIMABLE"},	\

init/Kconfig

@@ -686,7 +686,7 @@ config RESOURCE_COUNTERS
 	  This option enables controller independent resource accounting
 	  infrastructure that works with cgroups.
 
-config CGROUP_MEM_RES_CTLR
+config MEMCG
 	bool "Memory Resource Controller for Control Groups"
 	depends on RESOURCE_COUNTERS
 	select MM_OWNER
@@ -709,9 +709,9 @@ config CGROUP_MEM_RES_CTLR
 	  This config option also selects MM_OWNER config option, which
 	  could in turn add some fork/exit overhead.
 
-config CGROUP_MEM_RES_CTLR_SWAP
+config MEMCG_SWAP
 	bool "Memory Resource Controller Swap Extension"
-	depends on CGROUP_MEM_RES_CTLR && SWAP
+	depends on MEMCG && SWAP
 	help
 	  Add swap management feature to memory resource controller. When you
 	  enable this, you can limit mem+swap usage per cgroup. In other words,
@@ -726,9 +726,9 @@ config CGROUP_MEM_RES_CTLR_SWAP
 	  if boot option "swapaccount=0" is set, swap will not be accounted.
 	  Now, memory usage of swap_cgroup is 2 bytes per entry. If swap page
 	  size is 4096bytes, 512k per 1Gbytes of swap.
-config CGROUP_MEM_RES_CTLR_SWAP_ENABLED
+config MEMCG_SWAP_ENABLED
 	bool "Memory Resource Controller Swap Extension enabled by default"
-	depends on CGROUP_MEM_RES_CTLR_SWAP
+	depends on MEMCG_SWAP
 	default y
 	help
 	  Memory Resource Controller Swap Extension comes with its price in
@@ -739,9 +739,9 @@ config CGROUP_MEM_RES_CTLR_SWAP_ENABLED
 	  For those who want to have the feature enabled by default should
 	  select this option (if, for some reason, they need to disable it
 	  then swapaccount=0 does the trick).
-config CGROUP_MEM_RES_CTLR_KMEM
+config MEMCG_KMEM
 	bool "Memory Resource Controller Kernel Memory accounting (EXPERIMENTAL)"
-	depends on CGROUP_MEM_RES_CTLR && EXPERIMENTAL
+	depends on MEMCG && EXPERIMENTAL
 	default n
 	help
 	  The Kernel Memory extension for Memory Resource Controller can limit
@@ -751,6 +751,21 @@ config CGROUP_MEM_RES_CTLR_KMEM
 	  the kmem extension can use it to guarantee that no group of processes
 	  will ever exhaust kernel resources alone.
 
+config CGROUP_HUGETLB
+	bool "HugeTLB Resource Controller for Control Groups"
+	depends on RESOURCE_COUNTERS && HUGETLB_PAGE && EXPERIMENTAL
+	default n
+	help
+	  Provides a cgroup Resource Controller for HugeTLB pages.
+	  When you enable this, you can put a per cgroup limit on HugeTLB usage.
+	  The limit is enforced during page fault. Since HugeTLB doesn't
+	  support page reclaim, enforcing the limit at page fault time implies
+	  that, the application will get SIGBUS signal if it tries to access
+	  HugeTLB pages beyond its limit. This requires the application to know
+	  beforehand how much HugeTLB pages it would require for its use. The
+	  control group is tracked in the third page lru pointer. This means
+	  that we cannot use the controller with huge page less than 3 pages.
+
 config CGROUP_PERF
 	bool "Enable perf_event per-cpu per-container group (cgroup) monitoring"
 	depends on PERF_EVENTS && CGROUPS

init/main.c

@@ -506,7 +506,7 @@ asmlinkage void __init start_kernel(void)
 	setup_per_cpu_areas();
 	smp_prepare_boot_cpu();	/* arch-specific boot-cpu hooks */
 
-	build_all_zonelists(NULL);
+	build_all_zonelists(NULL, NULL);
 	page_alloc_init();
 
 	printk(KERN_NOTICE "Kernel command line: %s\n", boot_command_line);

kernel/cpu.c

@@ -416,7 +416,7 @@ int __cpuinit cpu_up(unsigned int cpu)
 
 	if (pgdat->node_zonelists->_zonerefs->zone == NULL) {
 		mutex_lock(&zonelists_mutex);
-		build_all_zonelists(NULL);
+		build_all_zonelists(NULL, NULL);
 		mutex_unlock(&zonelists_mutex);
 	}
 #endif

kernel/fork.c

@@ -381,10 +381,8 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 		struct file *file;
 
 		if (mpnt->vm_flags & VM_DONTCOPY) {
-			long pages = vma_pages(mpnt);
-			mm->total_vm -= pages;
 			vm_stat_account(mm, mpnt->vm_flags, mpnt->vm_file,
-								-pages);
+							-vma_pages(mpnt));
 			continue;
 		}
 		charge = 0;
@@ -1308,7 +1306,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 #ifdef CONFIG_DEBUG_MUTEXES
 	p->blocked_on = NULL; /* not blocked yet */
 #endif
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+#ifdef CONFIG_MEMCG
 	p->memcg_batch.do_batch = 0;
 	p->memcg_batch.memcg = NULL;
 #endif

kernel/softirq.c

@@ -210,6 +210,14 @@ asmlinkage void __do_softirq(void)
 	__u32 pending;
 	int max_restart = MAX_SOFTIRQ_RESTART;
 	int cpu;
+	unsigned long old_flags = current->flags;
+
+	/*
+	 * Mask out PF_MEMALLOC s current task context is borrowed for the
+	 * softirq. A softirq handled such as network RX might set PF_MEMALLOC
+	 * again if the socket is related to swap
+	 */
+	current->flags &= ~PF_MEMALLOC;
 
 	pending = local_softirq_pending();
 	account_system_vtime(current);
@@ -265,6 +273,7 @@ restart:
 
 	account_system_vtime(current);
 	__local_bh_enable(SOFTIRQ_OFFSET);
+	tsk_restore_flags(current, old_flags, PF_MEMALLOC);
 }
 
 #ifndef __ARCH_HAS_DO_SOFTIRQ

kernel/sysctl.c

@@ -1101,11 +1101,9 @@ static struct ctl_table vm_table[] = {
 		.extra1		= &zero,
 	},
 	{
-		.procname	= "nr_pdflush_threads",
-		.data		= &nr_pdflush_threads,
-		.maxlen		= sizeof nr_pdflush_threads,
-		.mode		= 0444 /* read-only*/,
-		.proc_handler	= proc_dointvec,
+		.procname       = "nr_pdflush_threads",
+		.mode           = 0444 /* read-only */,
+		.proc_handler   = pdflush_proc_obsolete,
 	},
 	{
 		.procname	= "swappiness",

kernel/sysctl_binary.c

@@ -147,7 +147,7 @@ static const struct bin_table bin_vm_table[] = {
 	{ CTL_INT,	VM_DIRTY_RATIO,			"dirty_ratio" },
 	/* VM_DIRTY_WB_CS "dirty_writeback_centisecs" no longer used */
 	/* VM_DIRTY_EXPIRE_CS "dirty_expire_centisecs" no longer used */
-	{ CTL_INT,	VM_NR_PDFLUSH_THREADS,		"nr_pdflush_threads" },
+	/* VM_NR_PDFLUSH_THREADS "nr_pdflush_threads" no longer used */
 	{ CTL_INT,	VM_OVERCOMMIT_RATIO,		"overcommit_ratio" },
 	/* VM_PAGEBUF unused */
 	/* VM_HUGETLB_PAGES "nr_hugepages" no longer used */

mm/Kconfig

@@ -140,9 +140,13 @@ config ARCH_DISCARD_MEMBLOCK
 config NO_BOOTMEM
 	boolean
 
+config MEMORY_ISOLATION
+	boolean
+
 # eventually, we can have this option just 'select SPARSEMEM'
 config MEMORY_HOTPLUG
 	bool "Allow for memory hot-add"
+	select MEMORY_ISOLATION
 	depends on SPARSEMEM || X86_64_ACPI_NUMA
 	depends on HOTPLUG && ARCH_ENABLE_MEMORY_HOTPLUG
 	depends on (IA64 || X86 || PPC_BOOK3S_64 || SUPERH || S390)
@@ -272,6 +276,7 @@ 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

mm/Makefile

@@ -15,8 +15,8 @@ obj-y			:= filemap.o mempool.o oom_kill.o fadvise.o \
 			   maccess.o page_alloc.o page-writeback.o \
 			   readahead.o swap.o truncate.o vmscan.o shmem.o \
 			   prio_tree.o util.o mmzone.o vmstat.o backing-dev.o \
-			   page_isolation.o mm_init.o mmu_context.o percpu.o \
-			   compaction.o slab_common.o $(mmu-y)
+			   mm_init.o mmu_context.o percpu.o slab_common.o \
+			   compaction.o $(mmu-y)
 
 obj-y += init-mm.o
 
@@ -49,9 +49,11 @@ 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-$(CONFIG_CGROUP_MEM_RES_CTLR) += memcontrol.o page_cgroup.o
+obj-$(CONFIG_MEMCG) += memcontrol.o page_cgroup.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

mm/backing-dev.c

@@ -886,3 +886,23 @@ out:
 	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 = 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/compaction.c

@@ -422,6 +422,17 @@ static void isolate_freepages(struct zone *zone,
 					pfn -= pageblock_nr_pages) {
 		unsigned long isolated;
 
+		/*
+		 * Skip ahead if another thread is compacting in the area
+		 * simultaneously. If we wrapped around, we can only skip
+		 * ahead if zone->compact_cached_free_pfn also wrapped to
+		 * above our starting point.
+		 */
+		if (cc->order > 0 && (!cc->wrapped ||
+				      zone->compact_cached_free_pfn >
+				      cc->start_free_pfn))
+			pfn = min(pfn, zone->compact_cached_free_pfn);
+
 		if (!pfn_valid(pfn))
 			continue;
 
@@ -461,8 +472,11 @@ static void isolate_freepages(struct zone *zone,
 		 * looking for free pages, the search will restart here as
 		 * page migration may have returned some pages to the allocator
 		 */
-		if (isolated)
+		if (isolated) {
 			high_pfn = max(high_pfn, pfn);
+			if (cc->order > 0)
+				zone->compact_cached_free_pfn = high_pfn;
+		}
 	}
 
 	/* split_free_page does not map the pages */
@@ -556,6 +570,20 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 	return ISOLATE_SUCCESS;
 }
 
+/*
+ * Returns the start pfn of the last page block in a zone.  This is the starting
+ * point for full compaction of a zone.  Compaction searches for free pages from
+ * the end of each zone, while isolate_freepages_block scans forward inside each
+ * page block.
+ */
+static unsigned long start_free_pfn(struct zone *zone)
+{
+	unsigned long free_pfn;
+	free_pfn = zone->zone_start_pfn + zone->spanned_pages;
+	free_pfn &= ~(pageblock_nr_pages-1);
+	return free_pfn;
+}
+
 static int compact_finished(struct zone *zone,
 			    struct compact_control *cc)
 {
@@ -565,8 +593,26 @@ static int compact_finished(struct zone *zone,
 	if (fatal_signal_pending(current))
 		return COMPACT_PARTIAL;
 
-	/* Compaction run completes if the migrate and free scanner meet */
-	if (cc->free_pfn <= cc->migrate_pfn)
+	/*
+	 * A full (order == -1) compaction run starts at the beginning and
+	 * end of a zone; it completes when the migrate and free scanner meet.
+	 * A partial (order > 0) compaction can start with the free scanner
+	 * at a random point in the zone, and may have to restart.
+	 */
+	if (cc->free_pfn <= cc->migrate_pfn) {
+		if (cc->order > 0 && !cc->wrapped) {
+			/* We started partway through; restart at the end. */
+			unsigned long free_pfn = start_free_pfn(zone);
+			zone->compact_cached_free_pfn = free_pfn;
+			cc->free_pfn = free_pfn;
+			cc->wrapped = 1;
+			return COMPACT_CONTINUE;
+		}
+		return COMPACT_COMPLETE;
+	}
+
+	/* We wrapped around and ended up where we started. */
+	if (cc->wrapped && cc->free_pfn <= cc->start_free_pfn)
 		return COMPACT_COMPLETE;
 
 	/*
@@ -664,8 +710,15 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 
 	/* Setup to move all movable pages to the end of the zone */
 	cc->migrate_pfn = zone->zone_start_pfn;
-	cc->free_pfn = cc->migrate_pfn + zone->spanned_pages;
-	cc->free_pfn &= ~(pageblock_nr_pages-1);
+
+	if (cc->order > 0) {
+		/* Incremental compaction. Start where the last one stopped. */
+		cc->free_pfn = zone->compact_cached_free_pfn;
+		cc->start_free_pfn = cc->free_pfn;
+	} else {
+		/* Order == -1 starts at the end of the zone. */
+		cc->free_pfn = start_free_pfn(zone);
+	}
 
 	migrate_prep_local();
 

mm/fadvise.c

@@ -93,11 +93,6 @@ SYSCALL_DEFINE(fadvise64_64)(int fd, loff_t offset, loff_t len, int advice)
 		spin_unlock(&file->f_lock);
 		break;
 	case POSIX_FADV_WILLNEED:
-		if (!mapping->a_ops->readpage) {
-			ret = -EINVAL;
-			break;
-		}
-
 		/* First and last PARTIAL page! */
 		start_index = offset >> PAGE_CACHE_SHIFT;
 		end_index = endbyte >> PAGE_CACHE_SHIFT;
@@ -106,12 +101,13 @@ SYSCALL_DEFINE(fadvise64_64)(int fd, loff_t offset, loff_t len, int advice)
 		nrpages = end_index - start_index + 1;
 		if (!nrpages)
 			nrpages = ~0UL;
-		
-		ret = force_page_cache_readahead(mapping, file,
-				start_index,
-				nrpages);
-		if (ret > 0)
-			ret = 0;
+
+		/*
+		 * Ignore return value because fadvise() shall return
+		 * success even if filesystem can't retrieve a hint,
+		 */
+		force_page_cache_readahead(mapping, file, start_index,
+					   nrpages);
 		break;
 	case POSIX_FADV_NOREUSE:
 		break;

mm/highmem.c

@@ -94,6 +94,18 @@ static DECLARE_WAIT_QUEUE_HEAD(pkmap_map_wait);
 		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 = (addr - PKMAP_ADDR(0)) >> PAGE_SHIFT;
+		return pte_page(pkmap_page_table[i]);
+	}
+
+	return virt_to_page(addr);
+}
+
 static void flush_all_zero_pkmaps(void)
 {
 	int i;

mm/hugetlb.c

@@ -24,17 +24,20 @@
 
 #include <asm/page.h>
 #include <asm/pgtable.h>
-#include <linux/io.h>
+#include <asm/tlb.h>
 
+#include <linux/io.h>
 #include <linux/hugetlb.h>
+#include <linux/hugetlb_cgroup.h>
 #include <linux/node.h>
+#include <linux/hugetlb_cgroup.h>
 #include "internal.h"
 
 const unsigned long hugetlb_zero = 0, hugetlb_infinity = ~0UL;
 static gfp_t htlb_alloc_mask = GFP_HIGHUSER;
 unsigned long hugepages_treat_as_movable;
 
-static int max_hstate;
+int hugetlb_max_hstate __read_mostly;
 unsigned int default_hstate_idx;
 struct hstate hstates[HUGE_MAX_HSTATE];
 
@@ -45,13 +48,10 @@ static struct hstate * __initdata parsed_hstate;
 static unsigned long __initdata default_hstate_max_huge_pages;
 static unsigned long __initdata default_hstate_size;
 
-#define for_each_hstate(h) \
-	for ((h) = hstates; (h) < &hstates[max_hstate]; (h)++)
-
 /*
  * Protects updates to hugepage_freelists, nr_huge_pages, and free_huge_pages
  */
-static DEFINE_SPINLOCK(hugetlb_lock);
+DEFINE_SPINLOCK(hugetlb_lock);
 
 static inline void unlock_or_release_subpool(struct hugepage_subpool *spool)
 {
@@ -509,7 +509,7 @@ void copy_huge_page(struct page *dst, struct page *src)
 static void enqueue_huge_page(struct hstate *h, struct page *page)
 {
 	int nid = page_to_nid(page);
-	list_add(&page->lru, &h->hugepage_freelists[nid]);
+	list_move(&page->lru, &h->hugepage_freelists[nid]);
 	h->free_huge_pages++;
 	h->free_huge_pages_node[nid]++;
 }
@@ -521,7 +521,7 @@ static struct page *dequeue_huge_page_node(struct hstate *h, int nid)
 	if (list_empty(&h->hugepage_freelists[nid]))
 		return NULL;
 	page = list_entry(h->hugepage_freelists[nid].next, struct page, lru);
-	list_del(&page->lru);
+	list_move(&page->lru, &h->hugepage_activelist);
 	set_page_refcounted(page);
 	h->free_huge_pages--;
 	h->free_huge_pages_node[nid]--;
@@ -593,6 +593,7 @@ static void update_and_free_page(struct hstate *h, struct page *page)
 				1 << PG_active | 1 << PG_reserved |
 				1 << PG_private | 1 << PG_writeback);
 	}
+	VM_BUG_ON(hugetlb_cgroup_from_page(page));
 	set_compound_page_dtor(page, NULL);
 	set_page_refcounted(page);
 	arch_release_hugepage(page);
@@ -625,10 +626,13 @@ static void free_huge_page(struct page *page)
 	page->mapping = NULL;
 	BUG_ON(page_count(page));
 	BUG_ON(page_mapcount(page));
-	INIT_LIST_HEAD(&page->lru);
 
 	spin_lock(&hugetlb_lock);
+	hugetlb_cgroup_uncharge_page(hstate_index(h),
+				     pages_per_huge_page(h), page);
 	if (h->surplus_huge_pages_node[nid] && huge_page_order(h) < MAX_ORDER) {
+		/* remove the page from active list */
+		list_del(&page->lru);
 		update_and_free_page(h, page);
 		h->surplus_huge_pages--;
 		h->surplus_huge_pages_node[nid]--;
@@ -641,8 +645,10 @@ static void free_huge_page(struct page *page)
 
 static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
 {
+	INIT_LIST_HEAD(&page->lru);
 	set_compound_page_dtor(page, free_huge_page);
 	spin_lock(&hugetlb_lock);
+	set_hugetlb_cgroup(page, NULL);
 	h->nr_huge_pages++;
 	h->nr_huge_pages_node[nid]++;
 	spin_unlock(&hugetlb_lock);
@@ -889,8 +895,10 @@ static struct page *alloc_buddy_huge_page(struct hstate *h, int nid)
 
 	spin_lock(&hugetlb_lock);
 	if (page) {
+		INIT_LIST_HEAD(&page->lru);
 		r_nid = page_to_nid(page);
 		set_compound_page_dtor(page, free_huge_page);
+		set_hugetlb_cgroup(page, NULL);
 		/*
 		 * We incremented the global counters already
 		 */
@@ -993,7 +1001,6 @@ retry:
 	list_for_each_entry_safe(page, tmp, &surplus_list, lru) {
 		if ((--needed) < 0)
 			break;
-		list_del(&page->lru);
 		/*
 		 * This page is now managed by the hugetlb allocator and has
 		 * no users -- drop the buddy allocator's reference.
@@ -1008,7 +1015,6 @@ free:
 	/* Free unnecessary surplus pages to the buddy allocator */
 	if (!list_empty(&surplus_list)) {
 		list_for_each_entry_safe(page, tmp, &surplus_list, lru) {
-			list_del(&page->lru);
 			put_page(page);
 		}
 	}
@@ -1112,7 +1118,10 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma,
 	struct hstate *h = hstate_vma(vma);
 	struct page *page;
 	long chg;
+	int ret, idx;
+	struct hugetlb_cgroup *h_cg;
 
+	idx = hstate_index(h);
 	/*
 	 * Processes that did not create the mapping will have no
 	 * reserves and will not have accounted against subpool
@@ -1123,27 +1132,43 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma,
 	 */
 	chg = vma_needs_reservation(h, vma, addr);
 	if (chg < 0)
-		return ERR_PTR(-VM_FAULT_OOM);
+		return ERR_PTR(-ENOMEM);
 	if (chg)
 		if (hugepage_subpool_get_pages(spool, chg))
-			return ERR_PTR(-VM_FAULT_SIGBUS);
+			return ERR_PTR(-ENOSPC);
 
+	ret = hugetlb_cgroup_charge_cgroup(idx, pages_per_huge_page(h), &h_cg);
+	if (ret) {
+		hugepage_subpool_put_pages(spool, chg);
+		return ERR_PTR(-ENOSPC);
+	}
 	spin_lock(&hugetlb_lock);
 	page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve);
-	spin_unlock(&hugetlb_lock);
-
-	if (!page) {
+	if (page) {
+		/* update page cgroup details */
+		hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h),
+					     h_cg, page);
+		spin_unlock(&hugetlb_lock);
+	} else {
+		spin_unlock(&hugetlb_lock);
 		page = alloc_buddy_huge_page(h, NUMA_NO_NODE);
 		if (!page) {
+			hugetlb_cgroup_uncharge_cgroup(idx,
+						       pages_per_huge_page(h),
+						       h_cg);
 			hugepage_subpool_put_pages(spool, chg);
-			return ERR_PTR(-VM_FAULT_SIGBUS);
+			return ERR_PTR(-ENOSPC);
 		}
+		spin_lock(&hugetlb_lock);
+		hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h),
+					     h_cg, page);
+		list_move(&page->lru, &h->hugepage_activelist);
+		spin_unlock(&hugetlb_lock);
 	}
 
 	set_page_private(page, (unsigned long)spool);
 
 	vma_commit_reservation(h, vma, addr);
-
 	return page;
 }
 
@@ -1646,7 +1671,7 @@ static int hugetlb_sysfs_add_hstate(struct hstate *h, struct kobject *parent,
 				    struct attribute_group *hstate_attr_group)
 {
 	int retval;
-	int hi = h - hstates;
+	int hi = hstate_index(h);
 
 	hstate_kobjs[hi] = kobject_create_and_add(h->name, parent);
 	if (!hstate_kobjs[hi])
@@ -1741,11 +1766,13 @@ void hugetlb_unregister_node(struct node *node)
 	if (!nhs->hugepages_kobj)
 		return;		/* no hstate attributes */
 
-	for_each_hstate(h)
-		if (nhs->hstate_kobjs[h - hstates]) {
-			kobject_put(nhs->hstate_kobjs[h - hstates]);
-			nhs->hstate_kobjs[h - hstates] = NULL;
+	for_each_hstate(h) {
+		int idx = hstate_index(h);
+		if (nhs->hstate_kobjs[idx]) {
+			kobject_put(nhs->hstate_kobjs[idx]);
+			nhs->hstate_kobjs[idx] = NULL;
 		}
+	}
 
 	kobject_put(nhs->hugepages_kobj);
 	nhs->hugepages_kobj = NULL;
@@ -1848,7 +1875,7 @@ static void __exit hugetlb_exit(void)
 	hugetlb_unregister_all_nodes();
 
 	for_each_hstate(h) {
-		kobject_put(hstate_kobjs[h - hstates]);
+		kobject_put(hstate_kobjs[hstate_index(h)]);
 	}
 
 	kobject_put(hugepages_kobj);
@@ -1869,7 +1896,7 @@ static int __init hugetlb_init(void)
 		if (!size_to_hstate(default_hstate_size))
 			hugetlb_add_hstate(HUGETLB_PAGE_ORDER);
 	}
-	default_hstate_idx = size_to_hstate(default_hstate_size) - hstates;
+	default_hstate_idx = hstate_index(size_to_hstate(default_hstate_size));
 	if (default_hstate_max_huge_pages)
 		default_hstate.max_huge_pages = default_hstate_max_huge_pages;
 
@@ -1897,19 +1924,27 @@ void __init hugetlb_add_hstate(unsigned order)
 		printk(KERN_WARNING "hugepagesz= specified twice, ignoring\n");
 		return;
 	}
-	BUG_ON(max_hstate >= HUGE_MAX_HSTATE);
+	BUG_ON(hugetlb_max_hstate >= HUGE_MAX_HSTATE);
 	BUG_ON(order == 0);
-	h = &hstates[max_hstate++];
+	h = &hstates[hugetlb_max_hstate++];
 	h->order = order;
 	h->mask = ~((1ULL << (order + PAGE_SHIFT)) - 1);
 	h->nr_huge_pages = 0;
 	h->free_huge_pages = 0;
 	for (i = 0; i < MAX_NUMNODES; ++i)
 		INIT_LIST_HEAD(&h->hugepage_freelists[i]);
+	INIT_LIST_HEAD(&h->hugepage_activelist);
 	h->next_nid_to_alloc = first_node(node_states[N_HIGH_MEMORY]);
 	h->next_nid_to_free = first_node(node_states[N_HIGH_MEMORY]);
 	snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB",
 					huge_page_size(h)/1024);
+	/*
+	 * 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 cgoup details.
+	 */
+	if (order >= HUGETLB_CGROUP_MIN_ORDER)
+		hugetlb_cgroup_file_init(hugetlb_max_hstate - 1);
 
 	parsed_hstate = h;
 }
@@ -1920,10 +1955,10 @@ static int __init hugetlb_nrpages_setup(char *s)
 	static unsigned long *last_mhp;
 
 	/*
-	 * !max_hstate means we haven't parsed a hugepagesz= parameter yet,
+	 * !hugetlb_max_hstate means we haven't parsed a hugepagesz= parameter yet,
 	 * so this hugepages= parameter goes to the "default hstate".
 	 */
-	if (!max_hstate)
+	if (!hugetlb_max_hstate)
 		mhp = &default_hstate_max_huge_pages;
 	else
 		mhp = &parsed_hstate->max_huge_pages;
@@ -1942,7 +1977,7 @@ static int __init hugetlb_nrpages_setup(char *s)
 	 * But we need to allocate >= MAX_ORDER hstates here early to still
 	 * use the bootmem allocator.
 	 */
-	if (max_hstate && parsed_hstate->order >= MAX_ORDER)
+	if (hugetlb_max_hstate && parsed_hstate->order >= MAX_ORDER)
 		hugetlb_hstate_alloc_pages(parsed_hstate);
 
 	last_mhp = mhp;
@@ -2308,30 +2343,26 @@ static int is_hugetlb_entry_hwpoisoned(pte_t pte)
 		return 0;
 }
 
-void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
-			    unsigned long end, struct page *ref_page)
+void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
+			    unsigned long start, unsigned long end,
+			    struct page *ref_page)
 {
+	int force_flush = 0;
 	struct mm_struct *mm = vma->vm_mm;
 	unsigned long address;
 	pte_t *ptep;
 	pte_t pte;
 	struct page *page;
-	struct page *tmp;
 	struct hstate *h = hstate_vma(vma);
 	unsigned long sz = huge_page_size(h);
 
-	/*
-	 * A page gathering list, protected by per file i_mmap_mutex. The
-	 * lock is used to avoid list corruption from multiple unmapping
-	 * of the same page since we are using page->lru.
-	 */
-	LIST_HEAD(page_list);
-
 	WARN_ON(!is_vm_hugetlb_page(vma));
 	BUG_ON(start & ~huge_page_mask(h));
 	BUG_ON(end & ~huge_page_mask(h));
 
+	tlb_start_vma(tlb, vma);
 	mmu_notifier_invalidate_range_start(mm, start, end);
+again:
 	spin_lock(&mm->page_table_lock);
 	for (address = start; address < end; address += sz) {
 		ptep = huge_pte_offset(mm, address);
@@ -2370,30 +2401,64 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 		}
 
 		pte = huge_ptep_get_and_clear(mm, address, ptep);
+		tlb_remove_tlb_entry(tlb, ptep, address);
 		if (pte_dirty(pte))
 			set_page_dirty(page);
-		list_add(&page->lru, &page_list);
 
+		page_remove_rmap(page);
+		force_flush = !__tlb_remove_page(tlb, page);
+		if (force_flush)
+			break;
 		/* Bail out after unmapping reference page if supplied */
 		if (ref_page)
 			break;
 	}
-	flush_tlb_range(vma, start, end);
 	spin_unlock(&mm->page_table_lock);
-	mmu_notifier_invalidate_range_end(mm, start, end);
-	list_for_each_entry_safe(page, tmp, &page_list, lru) {
-		page_remove_rmap(page);
-		list_del(&page->lru);
-		put_page(page);
+	/*
+	 * mmu_gather ran out of room to batch pages, we break out of
+	 * the PTE lock to avoid doing the potential expensive TLB invalidate
+	 * and page-free while holding it.
+	 */
+	if (force_flush) {
+		force_flush = 0;
+		tlb_flush_mmu(tlb);
+		if (address < end && !ref_page)
+			goto again;
 	}
+	mmu_notifier_invalidate_range_end(mm, start, end);
+	tlb_end_vma(tlb, vma);
+}
+
+void __unmap_hugepage_range_final(struct mmu_gather *tlb,
+			  struct vm_area_struct *vma, unsigned long start,
+			  unsigned long end, struct page *ref_page)
+{
+	__unmap_hugepage_range(tlb, vma, start, end, ref_page);
+
+	/*
+	 * Clear this flag so that x86's huge_pmd_share page_table_shareable
+	 * test will fail on a vma being torn down, and not grab a page table
+	 * on its way out.  We're lucky that the flag has such an appropriate
+	 * name, and can in fact be safely cleared here. We could clear it
+	 * before the __unmap_hugepage_range above, but all that's necessary
+	 * is to clear it before releasing the i_mmap_mutex. This works
+	 * because in the context this is called, the VMA is about to be
+	 * destroyed and the i_mmap_mutex is held.
+	 */
+	vma->vm_flags &= ~VM_MAYSHARE;
 }
 
 void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 			  unsigned long end, struct page *ref_page)
 {
-	mutex_lock(&vma->vm_file->f_mapping->i_mmap_mutex);
-	__unmap_hugepage_range(vma, start, end, ref_page);
-	mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex);
+	struct mm_struct *mm;
+	struct mmu_gather tlb;
+
+	mm = vma->vm_mm;
+
+	tlb_gather_mmu(&tlb, mm, 0);
+	__unmap_hugepage_range(&tlb, vma, start, end, ref_page);
+	tlb_finish_mmu(&tlb, start, end);
 }
 
 /*
@@ -2438,9 +2503,8 @@ static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
 		 * from the time of fork. This would look like data corruption
 		 */
 		if (!is_vma_resv_set(iter_vma, HPAGE_RESV_OWNER))
-			__unmap_hugepage_range(iter_vma,
-				address, address + huge_page_size(h),
-				page);
+			unmap_hugepage_range(iter_vma, address,
+					     address + huge_page_size(h), page);
 	}
 	mutex_unlock(&mapping->i_mmap_mutex);
 
@@ -2496,6 +2560,7 @@ retry_avoidcopy:
 	new_page = alloc_huge_page(vma, address, outside_reserve);
 
 	if (IS_ERR(new_page)) {
+		long err = PTR_ERR(new_page);
 		page_cache_release(old_page);
 
 		/*
@@ -2524,7 +2589,10 @@ retry_avoidcopy:
 
 		/* Caller expects lock to be held */
 		spin_lock(&mm->page_table_lock);
-		return -PTR_ERR(new_page);
+		if (err == -ENOMEM)
+			return VM_FAULT_OOM;
+		else
+			return VM_FAULT_SIGBUS;
 	}
 
 	/*
@@ -2642,7 +2710,11 @@ retry:
 			goto out;
 		page = alloc_huge_page(vma, address, 0);
 		if (IS_ERR(page)) {
-			ret = -PTR_ERR(page);
+			ret = PTR_ERR(page);
+			if (ret == -ENOMEM)
+				ret = VM_FAULT_OOM;
+			else
+				ret = VM_FAULT_SIGBUS;
 			goto out;
 		}
 		clear_huge_page(page, address, pages_per_huge_page(h));
@@ -2679,7 +2751,7 @@ retry:
 		 */
 		if (unlikely(PageHWPoison(page))) {
 			ret = VM_FAULT_HWPOISON |
-			      VM_FAULT_SET_HINDEX(h - hstates);
+				VM_FAULT_SET_HINDEX(hstate_index(h));
 			goto backout_unlocked;
 		}
 	}
@@ -2752,7 +2824,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 			return 0;
 		} else if (unlikely(is_hugetlb_entry_hwpoisoned(entry)))
 			return VM_FAULT_HWPOISON_LARGE |
-			       VM_FAULT_SET_HINDEX(h - hstates);
+				VM_FAULT_SET_HINDEX(hstate_index(h));
 	}
 
 	ptep = huge_pte_alloc(mm, address, huge_page_size(h));
@@ -2959,9 +3031,14 @@ void hugetlb_change_protection(struct vm_area_struct *vma,
 		}
 	}
 	spin_unlock(&mm->page_table_lock);
-	mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex);
-
+	/*
+	 * Must flush TLB before releasing i_mmap_mutex: x86's huge_pmd_unshare
+	 * may have cleared our pud entry and done put_page on the page table:
+	 * once we release i_mmap_mutex, another task can do the final put_page
+	 * and that page table be reused and filled with junk.
+	 */
 	flush_tlb_range(vma, start, end);
+	mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex);
 }
 
 int hugetlb_reserve_pages(struct inode *inode,

mm/hugetlb_cgroup.c

@@ -0,0 +1,418 @@
+/*
+ *
+ * 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)
+
+struct cgroup_subsys hugetlb_subsys __read_mostly;
+static struct hugetlb_cgroup *root_h_cgroup __read_mostly;
+
+static inline
+struct hugetlb_cgroup *hugetlb_cgroup_from_css(struct cgroup_subsys_state *s)
+{
+	return container_of(s, struct hugetlb_cgroup, css);
+}
+
+static inline
+struct hugetlb_cgroup *hugetlb_cgroup_from_cgroup(struct cgroup *cgroup)
+{
+	return hugetlb_cgroup_from_css(cgroup_subsys_state(cgroup,
+							   hugetlb_subsys_id));
+}
+
+static inline
+struct hugetlb_cgroup *hugetlb_cgroup_from_task(struct task_struct *task)
+{
+	return hugetlb_cgroup_from_css(task_subsys_state(task,
+							 hugetlb_subsys_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 cgroup *cg)
+{
+	if (!cg->parent)
+		return NULL;
+	return hugetlb_cgroup_from_cgroup(cg->parent);
+}
+
+static inline bool hugetlb_cgroup_have_usage(struct cgroup *cg)
+{
+	int idx;
+	struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_cgroup(cg);
+
+	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_create(struct cgroup *cgroup)
+{
+	int idx;
+	struct cgroup *parent_cgroup;
+	struct hugetlb_cgroup *h_cgroup, *parent_h_cgroup;
+
+	h_cgroup = kzalloc(sizeof(*h_cgroup), GFP_KERNEL);
+	if (!h_cgroup)
+		return ERR_PTR(-ENOMEM);
+
+	parent_cgroup = cgroup->parent;
+	if (parent_cgroup) {
+		parent_h_cgroup = hugetlb_cgroup_from_cgroup(parent_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_destroy(struct cgroup *cgroup)
+{
+	struct hugetlb_cgroup *h_cgroup;
+
+	h_cgroup = hugetlb_cgroup_from_cgroup(cgroup);
+	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 cgroup *cgroup,
+				       struct page *page)
+{
+	int csize;
+	struct res_counter *counter;
+	struct res_counter *fail_res;
+	struct hugetlb_cgroup *page_hcg;
+	struct hugetlb_cgroup *h_cg   = hugetlb_cgroup_from_cgroup(cgroup);
+	struct hugetlb_cgroup *parent = parent_hugetlb_cgroup(cgroup);
+
+	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 int hugetlb_cgroup_pre_destroy(struct cgroup *cgroup)
+{
+	struct hstate *h;
+	struct page *page;
+	int ret = 0, idx = 0;
+
+	do {
+		if (cgroup_task_count(cgroup) ||
+		    !list_empty(&cgroup->children)) {
+			ret = -EBUSY;
+			goto out;
+		}
+		for_each_hstate(h) {
+			spin_lock(&hugetlb_lock);
+			list_for_each_entry(page, &h->hugepage_activelist, lru)
+				hugetlb_cgroup_move_parent(idx, cgroup, page);
+
+			spin_unlock(&hugetlb_lock);
+			idx++;
+		}
+		cond_resched();
+	} while (hugetlb_cgroup_have_usage(cgroup));
+out:
+	return ret;
+}
+
+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(&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;
+	VM_BUG_ON(!spin_is_locked(&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 ssize_t hugetlb_cgroup_read(struct cgroup *cgroup, struct cftype *cft,
+				   struct file *file, char __user *buf,
+				   size_t nbytes, loff_t *ppos)
+{
+	u64 val;
+	char str[64];
+	int idx, name, len;
+	struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_cgroup(cgroup);
+
+	idx = MEMFILE_IDX(cft->private);
+	name = MEMFILE_ATTR(cft->private);
+
+	val = res_counter_read_u64(&h_cg->hugepage[idx], name);
+	len = scnprintf(str, sizeof(str), "%llu\n", (unsigned long long)val);
+	return simple_read_from_buffer(buf, nbytes, ppos, str, len);
+}
+
+static int hugetlb_cgroup_write(struct cgroup *cgroup, struct cftype *cft,
+				const char *buffer)
+{
+	int idx, name, ret;
+	unsigned long long val;
+	struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_cgroup(cgroup);
+
+	idx = MEMFILE_IDX(cft->private);
+	name = MEMFILE_ATTR(cft->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(buffer, &val);
+		if (ret)
+			break;
+		ret = res_counter_set_limit(&h_cg->hugepage[idx], val);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+	return ret;
+}
+
+static int hugetlb_cgroup_reset(struct cgroup *cgroup, unsigned int event)
+{
+	int idx, name, ret = 0;
+	struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_cgroup(cgroup);
+
+	idx = MEMFILE_IDX(event);
+	name = MEMFILE_ATTR(event);
+
+	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;
+}
+
+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;
+}
+
+int __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 = hugetlb_cgroup_read;
+	cft->write_string = 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 = hugetlb_cgroup_read;
+
+	/* 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->trigger = hugetlb_cgroup_reset;
+	cft->read = hugetlb_cgroup_read;
+
+	/* 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->trigger  = hugetlb_cgroup_reset;
+	cft->read = hugetlb_cgroup_read;
+
+	/* NULL terminate the last cft */
+	cft = &h->cgroup_files[4];
+	memset(cft, 0, sizeof(*cft));
+
+	WARN_ON(cgroup_add_cftypes(&hugetlb_subsys, h->cgroup_files));
+
+	return 0;
+}
+
+/*
+ * 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(!PageHuge(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_subsys = {
+	.name = "hugetlb",
+	.create     = hugetlb_cgroup_create,
+	.pre_destroy = hugetlb_cgroup_pre_destroy,
+	.destroy    = hugetlb_cgroup_destroy,
+	.subsys_id  = hugetlb_subsys_id,
+};

mm/hwpoison-inject.c

@@ -123,7 +123,7 @@ static int pfn_inject_init(void)
 	if (!dentry)
 		goto fail;
 
-#ifdef	CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+#ifdef CONFIG_MEMCG_SWAP
 	dentry = debugfs_create_u64("corrupt-filter-memcg", 0600,
 				    hwpoison_dir, &hwpoison_filter_memcg);
 	if (!dentry)

mm/internal.h

@@ -118,8 +118,14 @@ struct compact_control {
 	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 start_free_pfn;	/* where we started the search */
 	unsigned long migrate_pfn;	/* isolate_migratepages search base */
 	bool sync;			/* Synchronous migration */
+	bool wrapped;			/* Order > 0 compactions are
+					   incremental, once free_pfn
+					   and migrate_pfn meet, we restart
+					   from the top of the zone;
+					   remember we wrapped around. */
 
 	int order;			/* order a direct compactor needs */
 	int migratetype;		/* MOVABLE, RECLAIMABLE etc */
@@ -347,3 +353,5 @@ 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);

mm/memblock.c

@@ -222,13 +222,13 @@ static int __init_memblock memblock_double_array(struct memblock_type *type,
 	/* Try to find some space for it.
 	 *
 	 * WARNING: We assume that either slab_is_available() and we use it or
-	 * we use MEMBLOCK for allocations. That means that this is unsafe to use
-	 * when bootmem is currently active (unless bootmem itself is implemented
-	 * on top of MEMBLOCK which isn't the case yet)
+	 * we use MEMBLOCK for allocations. That means that this is unsafe to
+	 * use when bootmem is currently active (unless bootmem itself is
+	 * implemented on top of MEMBLOCK which isn't the case yet)
 	 *
 	 * This should however not be an issue for now, as we currently only
-	 * call into MEMBLOCK while it's still active, or much later when slab is
-	 * active for memory hotplug operations
+	 * call into MEMBLOCK while it's still active, or much later when slab
+	 * is active for memory hotplug operations
 	 */
 	if (use_slab) {
 		new_array = kmalloc(new_size, GFP_KERNEL);
@@ -243,8 +243,8 @@ static int __init_memblock memblock_double_array(struct memblock_type *type,
 						new_alloc_size, PAGE_SIZE);
 		if (!addr && new_area_size)
 			addr = memblock_find_in_range(0,
-					min(new_area_start, memblock.current_limit),
-					new_alloc_size, PAGE_SIZE);
+				min(new_area_start, memblock.current_limit),
+				new_alloc_size, PAGE_SIZE);
 
 		new_array = addr ? __va(addr) : 0;
 	}
@@ -254,12 +254,14 @@ static int __init_memblock memblock_double_array(struct memblock_type *type,
 		return -1;
 	}
 
-	memblock_dbg("memblock: %s array is doubled to %ld at [%#010llx-%#010llx]",
-		 memblock_type_name(type), type->max * 2, (u64)addr, (u64)addr + new_size - 1);
+	memblock_dbg("memblock: %s is doubled to %ld at [%#010llx-%#010llx]",
+			memblock_type_name(type), type->max * 2, (u64)addr,
+			(u64)addr + new_size - 1);
 
-	/* Found space, we now need to move the array over before
-	 * we add the reserved region since it may be our reserved
-	 * array itself that is full.
+	/*
+	 * Found space, we now need to move the array over before we add the
+	 * reserved region since it may be our reserved array itself that is
+	 * full.
 	 */
 	memcpy(new_array, type->regions, old_size);
 	memset(new_array + type->max, 0, old_size);
@@ -267,17 +269,16 @@ static int __init_memblock memblock_double_array(struct memblock_type *type,
 	type->regions = new_array;
 	type->max <<= 1;
 
-	/* Free old array. We needn't free it if the array is the
-	 * static one
-	 */
+	/* Free old array. We needn't free it if the array is the static one */
 	if (*in_slab)
 		kfree(old_array);
 	else if (old_array != memblock_memory_init_regions &&
 		 old_array != memblock_reserved_init_regions)
 		memblock_free(__pa(old_array), old_alloc_size);
 
-	/* Reserve the new array if that comes from the memblock.
-	 * Otherwise, we needn't do it
+	/*
+	 * Reserve the new array if that comes from the memblock.  Otherwise, we
+	 * needn't do it
 	 */
 	if (!use_slab)
 		BUG_ON(memblock_reserve(addr, new_alloc_size));

mm/memcontrol.c

@@ -61,12 +61,12 @@ struct cgroup_subsys mem_cgroup_subsys __read_mostly;
 #define MEM_CGROUP_RECLAIM_RETRIES	5
 static struct mem_cgroup *root_mem_cgroup __read_mostly;
 
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+#ifdef CONFIG_MEMCG_SWAP
 /* Turned on only when memory cgroup is enabled && really_do_swap_account = 1 */
 int do_swap_account __read_mostly;
 
 /* for remember boot option*/
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP_ENABLED
+#ifdef CONFIG_MEMCG_SWAP_ENABLED
 static int really_do_swap_account __initdata = 1;
 #else
 static int really_do_swap_account __initdata = 0;
@@ -87,7 +87,7 @@ enum mem_cgroup_stat_index {
 	MEM_CGROUP_STAT_CACHE, 	   /* # of pages charged as cache */
 	MEM_CGROUP_STAT_RSS,	   /* # of pages charged as anon rss */
 	MEM_CGROUP_STAT_FILE_MAPPED,  /* # of pages charged as file rss */
-	MEM_CGROUP_STAT_SWAPOUT, /* # of pages, swapped out */
+	MEM_CGROUP_STAT_SWAP, /* # of pages, swapped out */
 	MEM_CGROUP_STAT_NSTATS,
 };
 
@@ -378,9 +378,7 @@ static bool move_file(void)
 
 enum charge_type {
 	MEM_CGROUP_CHARGE_TYPE_CACHE = 0,
-	MEM_CGROUP_CHARGE_TYPE_MAPPED,
-	MEM_CGROUP_CHARGE_TYPE_SHMEM,	/* used by page migration of shmem */
-	MEM_CGROUP_CHARGE_TYPE_FORCE,	/* used by force_empty */
+	MEM_CGROUP_CHARGE_TYPE_ANON,
 	MEM_CGROUP_CHARGE_TYPE_SWAPOUT,	/* for accounting swapcache */
 	MEM_CGROUP_CHARGE_TYPE_DROP,	/* a page was unused swap cache */
 	NR_CHARGE_TYPE,
@@ -407,8 +405,14 @@ enum charge_type {
 static void mem_cgroup_get(struct mem_cgroup *memcg);
 static void mem_cgroup_put(struct mem_cgroup *memcg);
 
+static inline
+struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *s)
+{
+	return container_of(s, struct mem_cgroup, css);
+}
+
 /* Writing them here to avoid exposing memcg's inner layout */
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+#ifdef CONFIG_MEMCG_KMEM
 #include <net/sock.h>
 #include <net/ip.h>
 
@@ -467,9 +471,9 @@ struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg)
 }
 EXPORT_SYMBOL(tcp_proto_cgroup);
 #endif /* CONFIG_INET */
-#endif /* CONFIG_CGROUP_MEM_RES_CTLR_KMEM */
+#endif /* CONFIG_MEMCG_KMEM */
 
-#if defined(CONFIG_INET) && defined(CONFIG_CGROUP_MEM_RES_CTLR_KMEM)
+#if defined(CONFIG_INET) && defined(CONFIG_MEMCG_KMEM)
 static void disarm_sock_keys(struct mem_cgroup *memcg)
 {
 	if (!memcg_proto_activated(&memcg->tcp_mem.cg_proto))
@@ -703,7 +707,7 @@ static void mem_cgroup_swap_statistics(struct mem_cgroup *memcg,
 					 bool charge)
 {
 	int val = (charge) ? 1 : -1;
-	this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_SWAPOUT], val);
+	this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_SWAP], val);
 }
 
 static unsigned long mem_cgroup_read_events(struct mem_cgroup *memcg,
@@ -864,9 +868,8 @@ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page)
 
 struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont)
 {
-	return container_of(cgroup_subsys_state(cont,
-				mem_cgroup_subsys_id), struct mem_cgroup,
-				css);
+	return mem_cgroup_from_css(
+		cgroup_subsys_state(cont, mem_cgroup_subsys_id));
 }
 
 struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
@@ -879,8 +882,7 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
 	if (unlikely(!p))
 		return NULL;
 
-	return container_of(task_subsys_state(p, mem_cgroup_subsys_id),
-				struct mem_cgroup, css);
+	return mem_cgroup_from_css(task_subsys_state(p, mem_cgroup_subsys_id));
 }
 
 struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm)
@@ -966,8 +968,7 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 		css = css_get_next(&mem_cgroup_subsys, id + 1, &root->css, &id);
 		if (css) {
 			if (css == &root->css || css_tryget(css))
-				memcg = container_of(css,
-						     struct mem_cgroup, css);
+				memcg = mem_cgroup_from_css(css);
 		} else
 			id = 0;
 		rcu_read_unlock();
@@ -1454,7 +1455,7 @@ static int mem_cgroup_count_children(struct mem_cgroup *memcg)
 /*
  * Return the memory (and swap, if configured) limit for a memcg.
  */
-u64 mem_cgroup_get_limit(struct mem_cgroup *memcg)
+static u64 mem_cgroup_get_limit(struct mem_cgroup *memcg)
 {
 	u64 limit;
 	u64 memsw;
@@ -1470,6 +1471,73 @@ u64 mem_cgroup_get_limit(struct mem_cgroup *memcg)
 	return min(limit, memsw);
 }
 
+void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
+			      int order)
+{
+	struct mem_cgroup *iter;
+	unsigned long chosen_points = 0;
+	unsigned long totalpages;
+	unsigned int points = 0;
+	struct task_struct *chosen = NULL;
+
+	/*
+	 * If current has a pending SIGKILL, 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)) {
+		set_thread_flag(TIF_MEMDIE);
+		return;
+	}
+
+	check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, order, NULL);
+	totalpages = mem_cgroup_get_limit(memcg) >> PAGE_SHIFT ? : 1;
+	for_each_mem_cgroup_tree(iter, memcg) {
+		struct cgroup *cgroup = iter->css.cgroup;
+		struct cgroup_iter it;
+		struct task_struct *task;
+
+		cgroup_iter_start(cgroup, &it);
+		while ((task = cgroup_iter_next(cgroup, &it))) {
+			switch (oom_scan_process_thread(task, totalpages, NULL,
+							false)) {
+			case OOM_SCAN_SELECT:
+				if (chosen)
+					put_task_struct(chosen);
+				chosen = task;
+				chosen_points = ULONG_MAX;
+				get_task_struct(chosen);
+				/* fall through */
+			case OOM_SCAN_CONTINUE:
+				continue;
+			case OOM_SCAN_ABORT:
+				cgroup_iter_end(cgroup, &it);
+				mem_cgroup_iter_break(memcg, iter);
+				if (chosen)
+					put_task_struct(chosen);
+				return;
+			case OOM_SCAN_OK:
+				break;
+			};
+			points = oom_badness(task, memcg, NULL, totalpages);
+			if (points > chosen_points) {
+				if (chosen)
+					put_task_struct(chosen);
+				chosen = task;
+				chosen_points = points;
+				get_task_struct(chosen);
+			}
+		}
+		cgroup_iter_end(cgroup, &it);
+	}
+
+	if (!chosen)
+		return;
+	points = chosen_points * 1000 / totalpages;
+	oom_kill_process(chosen, gfp_mask, order, points, totalpages, memcg,
+			 NULL, "Memory cgroup out of memory");
+}
+
 static unsigned long mem_cgroup_reclaim(struct mem_cgroup *memcg,
 					gfp_t gfp_mask,
 					unsigned long flags)
@@ -1899,7 +1967,7 @@ again:
 		return;
 	/*
 	 * If this memory cgroup is not under account moving, we don't
-	 * need to take move_lock_page_cgroup(). Because we already hold
+	 * need to take move_lock_mem_cgroup(). Because we already hold
 	 * rcu_read_lock(), any calls to move_account will be delayed until
 	 * rcu_read_unlock() if mem_cgroup_stolen() == true.
 	 */
@@ -1921,7 +1989,7 @@ void __mem_cgroup_end_update_page_stat(struct page *page, unsigned long *flags)
 	/*
 	 * It's guaranteed that pc->mem_cgroup never changes while
 	 * lock is held because a routine modifies pc->mem_cgroup
-	 * should take move_lock_page_cgroup().
+	 * should take move_lock_mem_cgroup().
 	 */
 	move_unlock_mem_cgroup(pc->mem_cgroup, flags);
 }
@@ -2268,7 +2336,7 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
 	 * We always charge the cgroup the mm_struct belongs to.
 	 * The mm_struct's mem_cgroup changes on task migration if the
 	 * thread group leader migrates. It's possible that mm is not
-	 * set, if so charge the init_mm (happens for pagecache usage).
+	 * set, if so charge the root memcg (happens for pagecache usage).
 	 */
 	if (!*ptr && !mm)
 		*ptr = root_mem_cgroup;
@@ -2429,7 +2497,7 @@ static struct mem_cgroup *mem_cgroup_lookup(unsigned short id)
 	css = css_lookup(&mem_cgroup_subsys, id);
 	if (!css)
 		return NULL;
-	return container_of(css, struct mem_cgroup, css);
+	return mem_cgroup_from_css(css);
 }
 
 struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page)
@@ -2473,11 +2541,7 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
 	bool anon;
 
 	lock_page_cgroup(pc);
-	if (unlikely(PageCgroupUsed(pc))) {
-		unlock_page_cgroup(pc);
-		__mem_cgroup_cancel_charge(memcg, nr_pages);
-		return;
-	}
+	VM_BUG_ON(PageCgroupUsed(pc));
 	/*
 	 * we don't need page_cgroup_lock about tail pages, becase they are not
 	 * accessed by any other context at this point.
@@ -2519,7 +2583,7 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
 		spin_unlock_irq(&zone->lru_lock);
 	}
 
-	if (ctype == MEM_CGROUP_CHARGE_TYPE_MAPPED)
+	if (ctype == MEM_CGROUP_CHARGE_TYPE_ANON)
 		anon = true;
 	else
 		anon = false;
@@ -2644,8 +2708,7 @@ out:
 
 static int mem_cgroup_move_parent(struct page *page,
 				  struct page_cgroup *pc,
-				  struct mem_cgroup *child,
-				  gfp_t gfp_mask)
+				  struct mem_cgroup *child)
 {
 	struct mem_cgroup *parent;
 	unsigned int nr_pages;
@@ -2728,38 +2791,7 @@ int mem_cgroup_newpage_charge(struct page *page,
 	VM_BUG_ON(page->mapping && !PageAnon(page));
 	VM_BUG_ON(!mm);
 	return mem_cgroup_charge_common(page, mm, gfp_mask,
-					MEM_CGROUP_CHARGE_TYPE_MAPPED);
-}
-
-static void
-__mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr,
-					enum charge_type ctype);
-
-int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
-				gfp_t gfp_mask)
-{
-	struct mem_cgroup *memcg = NULL;
-	enum charge_type type = MEM_CGROUP_CHARGE_TYPE_CACHE;
-	int ret;
-
-	if (mem_cgroup_disabled())
-		return 0;
-	if (PageCompound(page))
-		return 0;
-
-	if (unlikely(!mm))
-		mm = &init_mm;
-	if (!page_is_file_cache(page))
-		type = MEM_CGROUP_CHARGE_TYPE_SHMEM;
-
-	if (!PageSwapCache(page))
-		ret = mem_cgroup_charge_common(page, mm, gfp_mask, type);
-	else { /* page is swapcache/shmem */
-		ret = mem_cgroup_try_charge_swapin(mm, page, gfp_mask, &memcg);
-		if (!ret)
-			__mem_cgroup_commit_charge_swapin(page, memcg, type);
-	}
-	return ret;
+					MEM_CGROUP_CHARGE_TYPE_ANON);
 }
 
 /*
@@ -2768,27 +2800,26 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
  * struct page_cgroup is acquired. This refcnt will be consumed by
  * "commit()" or removed by "cancel()"
  */
-int mem_cgroup_try_charge_swapin(struct mm_struct *mm,
-				 struct page *page,
-				 gfp_t mask, struct mem_cgroup **memcgp)
+static int __mem_cgroup_try_charge_swapin(struct mm_struct *mm,
+					  struct page *page,
+					  gfp_t mask,
+					  struct mem_cgroup **memcgp)
 {
 	struct mem_cgroup *memcg;
+	struct page_cgroup *pc;
 	int ret;
 
-	*memcgp = NULL;
-
-	if (mem_cgroup_disabled())
-		return 0;
-
-	if (!do_swap_account)
-		goto charge_cur_mm;
+	pc = lookup_page_cgroup(page);
 	/*
-	 * A racing thread's fault, or swapoff, may have already updated
-	 * the pte, and even removed page from swap cache: in those cases
-	 * do_swap_page()'s pte_same() test will fail; but there's also a
-	 * KSM case which does need to charge the page.
+	 * Every swap fault against a single page tries to charge the
+	 * page, bail as early as possible.  shmem_unuse() encounters
+	 * already charged pages, too.  The USED bit is protected by
+	 * the page lock, which serializes swap cache removal, which
+	 * in turn serializes uncharging.
 	 */
-	if (!PageSwapCache(page))
+	if (PageCgroupUsed(pc))
+		return 0;
+	if (!do_swap_account)
 		goto charge_cur_mm;
 	memcg = try_get_mem_cgroup_from_page(page);
 	if (!memcg)
@@ -2800,14 +2831,44 @@ int mem_cgroup_try_charge_swapin(struct mm_struct *mm,
 		ret = 0;
 	return ret;
 charge_cur_mm:
-	if (unlikely(!mm))
-		mm = &init_mm;
 	ret = __mem_cgroup_try_charge(mm, mask, 1, memcgp, true);
 	if (ret == -EINTR)
 		ret = 0;
 	return ret;
 }
 
+int mem_cgroup_try_charge_swapin(struct mm_struct *mm, struct page *page,
+				 gfp_t gfp_mask, struct mem_cgroup **memcgp)
+{
+	*memcgp = NULL;
+	if (mem_cgroup_disabled())
+		return 0;
+	/*
+	 * A racing thread's fault, or swapoff, may have already
+	 * updated the pte, and even removed page from swap cache: in
+	 * those cases unuse_pte()'s pte_same() test will fail; but
+	 * there's also a KSM case which does need to charge the page.
+	 */
+	if (!PageSwapCache(page)) {
+		int ret;
+
+		ret = __mem_cgroup_try_charge(mm, gfp_mask, 1, memcgp, true);
+		if (ret == -EINTR)
+			ret = 0;
+		return ret;
+	}
+	return __mem_cgroup_try_charge_swapin(mm, page, gfp_mask, memcgp);
+}
+
+void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *memcg)
+{
+	if (mem_cgroup_disabled())
+		return;
+	if (!memcg)
+		return;
+	__mem_cgroup_cancel_charge(memcg, 1);
+}
+
 static void
 __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *memcg,
 					enum charge_type ctype)
@@ -2842,16 +2903,30 @@ void mem_cgroup_commit_charge_swapin(struct page *page,
 				     struct mem_cgroup *memcg)
 {
 	__mem_cgroup_commit_charge_swapin(page, memcg,
-					  MEM_CGROUP_CHARGE_TYPE_MAPPED);
+					  MEM_CGROUP_CHARGE_TYPE_ANON);
 }
 
-void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *memcg)
+int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
+				gfp_t gfp_mask)
 {
+	struct mem_cgroup *memcg = NULL;
+	enum charge_type type = MEM_CGROUP_CHARGE_TYPE_CACHE;
+	int ret;
+
 	if (mem_cgroup_disabled())
-		return;
-	if (!memcg)
-		return;
-	__mem_cgroup_cancel_charge(memcg, 1);
+		return 0;
+	if (PageCompound(page))
+		return 0;
+
+	if (!PageSwapCache(page))
+		ret = mem_cgroup_charge_common(page, mm, gfp_mask, type);
+	else { /* page is swapcache/shmem */
+		ret = __mem_cgroup_try_charge_swapin(mm, page,
+						     gfp_mask, &memcg);
+		if (!ret)
+			__mem_cgroup_commit_charge_swapin(page, memcg, type);
+	}
+	return ret;
 }
 
 static void mem_cgroup_do_uncharge(struct mem_cgroup *memcg,
@@ -2911,7 +2986,8 @@ direct_uncharge:
  * uncharge if !page_mapped(page)
  */
 static struct mem_cgroup *
-__mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
+__mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype,
+			     bool end_migration)
 {
 	struct mem_cgroup *memcg = NULL;
 	unsigned int nr_pages = 1;
@@ -2921,8 +2997,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
 	if (mem_cgroup_disabled())
 		return NULL;
 
-	if (PageSwapCache(page))
-		return NULL;
+	VM_BUG_ON(PageSwapCache(page));
 
 	if (PageTransHuge(page)) {
 		nr_pages <<= compound_order(page);
@@ -2945,7 +3020,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
 	anon = PageAnon(page);
 
 	switch (ctype) {
-	case MEM_CGROUP_CHARGE_TYPE_MAPPED:
+	case MEM_CGROUP_CHARGE_TYPE_ANON:
 		/*
 		 * Generally PageAnon tells if it's the anon statistics to be
 		 * updated; but sometimes e.g. mem_cgroup_uncharge_page() is
@@ -2955,7 +3030,16 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
 		/* fallthrough */
 	case MEM_CGROUP_CHARGE_TYPE_DROP:
 		/* See mem_cgroup_prepare_migration() */
-		if (page_mapped(page) || PageCgroupMigration(pc))
+		if (page_mapped(page))
+			goto unlock_out;
+		/*
+		 * Pages under migration may not be uncharged.  But
+		 * end_migration() /must/ be the one uncharging the
+		 * unused post-migration page and so it has to call
+		 * here with the migration bit still set.  See the
+		 * res_counter handling below.
+		 */
+		if (!end_migration && PageCgroupMigration(pc))
 			goto unlock_out;
 		break;
 	case MEM_CGROUP_CHARGE_TYPE_SWAPOUT:
@@ -2989,7 +3073,12 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
 		mem_cgroup_swap_statistics(memcg, true);
 		mem_cgroup_get(memcg);
 	}
-	if (!mem_cgroup_is_root(memcg))
+	/*
+	 * Migration does not charge the res_counter for the
+	 * replacement page, so leave it alone when phasing out the
+	 * page that is unused after the migration.
+	 */
+	if (!end_migration && !mem_cgroup_is_root(memcg))
 		mem_cgroup_do_uncharge(memcg, nr_pages, ctype);
 
 	return memcg;
@@ -3005,14 +3094,16 @@ void mem_cgroup_uncharge_page(struct page *page)
 	if (page_mapped(page))
 		return;
 	VM_BUG_ON(page->mapping && !PageAnon(page));
-	__mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_MAPPED);
+	if (PageSwapCache(page))
+		return;
+	__mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_ANON, false);
 }
 
 void mem_cgroup_uncharge_cache_page(struct page *page)
 {
 	VM_BUG_ON(page_mapped(page));
 	VM_BUG_ON(page->mapping);
-	__mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_CACHE);
+	__mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_CACHE, false);
 }
 
 /*
@@ -3076,7 +3167,7 @@ mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout)
 	if (!swapout) /* this was a swap cache but the swap is unused ! */
 		ctype = MEM_CGROUP_CHARGE_TYPE_DROP;
 
-	memcg = __mem_cgroup_uncharge_common(page, ctype);
+	memcg = __mem_cgroup_uncharge_common(page, ctype, false);
 
 	/*
 	 * record memcg information,  if swapout && memcg != NULL,
@@ -3087,7 +3178,7 @@ mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout)
 }
 #endif
 
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+#ifdef CONFIG_MEMCG_SWAP
 /*
  * called from swap_entry_free(). remove record in swap_cgroup and
  * uncharge "memsw" account.
@@ -3166,19 +3257,18 @@ static inline int mem_cgroup_move_swap_account(swp_entry_t entry,
  * Before starting migration, account PAGE_SIZE to mem_cgroup that the old
  * page belongs to.
  */
-int mem_cgroup_prepare_migration(struct page *page,
-	struct page *newpage, struct mem_cgroup **memcgp, gfp_t gfp_mask)
+void mem_cgroup_prepare_migration(struct page *page, struct page *newpage,
+				  struct mem_cgroup **memcgp)
 {
 	struct mem_cgroup *memcg = NULL;
 	struct page_cgroup *pc;
 	enum charge_type ctype;
-	int ret = 0;
 
 	*memcgp = NULL;
 
 	VM_BUG_ON(PageTransHuge(page));
 	if (mem_cgroup_disabled())
-		return 0;
+		return;
 
 	pc = lookup_page_cgroup(page);
 	lock_page_cgroup(pc);
@@ -3223,24 +3313,9 @@ int mem_cgroup_prepare_migration(struct page *page,
 	 * we return here.
 	 */
 	if (!memcg)
-		return 0;
+		return;
 
 	*memcgp = memcg;
-	ret = __mem_cgroup_try_charge(NULL, gfp_mask, 1, memcgp, false);
-	css_put(&memcg->css);/* drop extra refcnt */
-	if (ret) {
-		if (PageAnon(page)) {
-			lock_page_cgroup(pc);
-			ClearPageCgroupMigration(pc);
-			unlock_page_cgroup(pc);
-			/*
-			 * The old page may be fully unmapped while we kept it.
-			 */
-			mem_cgroup_uncharge_page(page);
-		}
-		/* we'll need to revisit this error code (we have -EINTR) */
-		return -ENOMEM;
-	}
 	/*
 	 * We charge new page before it's used/mapped. So, even if unlock_page()
 	 * is called before end_migration, we can catch all events on this new
@@ -3248,13 +3323,15 @@ int mem_cgroup_prepare_migration(struct page *page,
 	 * mapcount will be finally 0 and we call uncharge in end_migration().
 	 */
 	if (PageAnon(page))
-		ctype = MEM_CGROUP_CHARGE_TYPE_MAPPED;
-	else if (page_is_file_cache(page))
-		ctype = MEM_CGROUP_CHARGE_TYPE_CACHE;
+		ctype = MEM_CGROUP_CHARGE_TYPE_ANON;
 	else
-		ctype = MEM_CGROUP_CHARGE_TYPE_SHMEM;
+		ctype = MEM_CGROUP_CHARGE_TYPE_CACHE;
+	/*
+	 * The page is committed to the memcg, but it's not actually
+	 * charged to the res_counter since we plan on replacing the
+	 * old one and only one page is going to be left afterwards.
+	 */
 	__mem_cgroup_commit_charge(memcg, newpage, 1, ctype, false);
-	return ret;
 }
 
 /* remove redundant charge if migration failed*/
@@ -3276,6 +3353,12 @@ void mem_cgroup_end_migration(struct mem_cgroup *memcg,
 		used = newpage;
 		unused = oldpage;
 	}
+	anon = PageAnon(used);
+	__mem_cgroup_uncharge_common(unused,
+				     anon ? MEM_CGROUP_CHARGE_TYPE_ANON
+				     : MEM_CGROUP_CHARGE_TYPE_CACHE,
+				     true);
+	css_put(&memcg->css);
 	/*
 	 * We disallowed uncharge of pages under migration because mapcount
 	 * of the page goes down to zero, temporarly.
@@ -3285,10 +3368,6 @@ void mem_cgroup_end_migration(struct mem_cgroup *memcg,
 	lock_page_cgroup(pc);
 	ClearPageCgroupMigration(pc);
 	unlock_page_cgroup(pc);
-	anon = PageAnon(used);
-	__mem_cgroup_uncharge_common(unused,
-		anon ? MEM_CGROUP_CHARGE_TYPE_MAPPED
-		     : MEM_CGROUP_CHARGE_TYPE_CACHE);
 
 	/*
 	 * If a page is a file cache, radix-tree replacement is very atomic
@@ -3340,10 +3419,6 @@ void mem_cgroup_replace_page_cache(struct page *oldpage,
 	 */
 	if (!memcg)
 		return;
-
-	if (PageSwapBacked(oldpage))
-		type = MEM_CGROUP_CHARGE_TYPE_SHMEM;
-
 	/*
 	 * Even if newpage->mapping was NULL before starting replacement,
 	 * the newpage may be on LRU(or pagevec for LRU) already. We lock
@@ -3418,7 +3493,7 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
 		/*
 		 * Rather than hide all in some function, I do this in
 		 * open coded manner. You see what this really does.
-		 * We have to guarantee memcg->res.limit < memcg->memsw.limit.
+		 * We have to guarantee memcg->res.limit <= memcg->memsw.limit.
 		 */
 		mutex_lock(&set_limit_mutex);
 		memswlimit = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
@@ -3479,7 +3554,7 @@ static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg,
 		/*
 		 * Rather than hide all in some function, I do this in
 		 * open coded manner. You see what this really does.
-		 * We have to guarantee memcg->res.limit < memcg->memsw.limit.
+		 * We have to guarantee memcg->res.limit <= memcg->memsw.limit.
 		 */
 		mutex_lock(&set_limit_mutex);
 		memlimit = res_counter_read_u64(&memcg->res, RES_LIMIT);
@@ -3611,10 +3686,12 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
 }
 
 /*
- * This routine traverse page_cgroup in given list and drop them all.
- * *And* this routine doesn't reclaim page itself, just removes page_cgroup.
+ * Traverse a specified page_cgroup list and try to drop them all.  This doesn't
+ * reclaim the pages page themselves - it just removes the page_cgroups.
+ * Returns true if some page_cgroups were not freed, indicating that the caller
+ * must retry this operation.
  */
-static int mem_cgroup_force_empty_list(struct mem_cgroup *memcg,
+static bool mem_cgroup_force_empty_list(struct mem_cgroup *memcg,
 				int node, int zid, enum lru_list lru)
 {
 	struct mem_cgroup_per_zone *mz;
@@ -3622,7 +3699,6 @@ static int mem_cgroup_force_empty_list(struct mem_cgroup *memcg,
 	struct list_head *list;
 	struct page *busy;
 	struct zone *zone;
-	int ret = 0;
 
 	zone = &NODE_DATA(node)->node_zones[zid];
 	mz = mem_cgroup_zoneinfo(memcg, node, zid);
@@ -3636,7 +3712,6 @@ static int mem_cgroup_force_empty_list(struct mem_cgroup *memcg,
 		struct page_cgroup *pc;
 		struct page *page;
 
-		ret = 0;
 		spin_lock_irqsave(&zone->lru_lock, flags);
 		if (list_empty(list)) {
 			spin_unlock_irqrestore(&zone->lru_lock, flags);
@@ -3653,21 +3728,14 @@ static int mem_cgroup_force_empty_list(struct mem_cgroup *memcg,
 
 		pc = lookup_page_cgroup(page);
 
-		ret = mem_cgroup_move_parent(page, pc, memcg, GFP_KERNEL);
-		if (ret == -ENOMEM || ret == -EINTR)
-			break;
-
-		if (ret == -EBUSY || ret == -EINVAL) {
+		if (mem_cgroup_move_parent(page, pc, memcg)) {
 			/* found lock contention or "pc" is obsolete. */
 			busy = page;
 			cond_resched();
 		} else
 			busy = NULL;
 	}
-
-	if (!ret && !list_empty(list))
-		return -EBUSY;
-	return ret;
+	return !list_empty(list);
 }
 
 /*
@@ -3692,9 +3760,6 @@ move_account:
 		ret = -EBUSY;
 		if (cgroup_task_count(cgrp) || !list_empty(&cgrp->children))
 			goto out;
-		ret = -EINTR;
-		if (signal_pending(current))
-			goto out;
 		/* This is for making all *used* pages to be on LRU. */
 		lru_add_drain_all();
 		drain_all_stock_sync(memcg);
@@ -3715,9 +3780,6 @@ move_account:
 		}
 		mem_cgroup_end_move(memcg);
 		memcg_oom_recover(memcg);
-		/* it seems parent cgroup doesn't have enough mem */
-		if (ret == -ENOMEM)
-			goto try_to_free;
 		cond_resched();
 	/* "ret" should also be checked to ensure all lists are empty. */
 	} while (res_counter_read_u64(&memcg->res, RES_USAGE) > 0 || ret);
@@ -3779,6 +3841,10 @@ static int mem_cgroup_hierarchy_write(struct cgroup *cont, struct cftype *cft,
 		parent_memcg = mem_cgroup_from_cont(parent);
 
 	cgroup_lock();
+
+	if (memcg->use_hierarchy == val)
+		goto out;
+
 	/*
 	 * If parent's use_hierarchy is set, we can't make any modifications
 	 * in the child subtrees. If it is unset, then the change can
@@ -3795,6 +3861,8 @@ static int mem_cgroup_hierarchy_write(struct cgroup *cont, struct cftype *cft,
 			retval = -EBUSY;
 	} else
 		retval = -EINVAL;
+
+out:
 	cgroup_unlock();
 
 	return retval;
@@ -3831,7 +3899,7 @@ static inline u64 mem_cgroup_usage(struct mem_cgroup *memcg, bool swap)
 	val += mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_RSS);
 
 	if (swap)
-		val += mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_SWAPOUT);
+		val += mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_SWAP);
 
 	return val << PAGE_SHIFT;
 }
@@ -4015,7 +4083,7 @@ static int mem_cgroup_move_charge_write(struct cgroup *cgrp,
 #endif
 
 #ifdef CONFIG_NUMA
-static int mem_control_numa_stat_show(struct cgroup *cont, struct cftype *cft,
+static int memcg_numa_stat_show(struct cgroup *cont, struct cftype *cft,
 				      struct seq_file *m)
 {
 	int nid;
@@ -4074,7 +4142,7 @@ static inline void mem_cgroup_lru_names_not_uptodate(void)
 	BUILD_BUG_ON(ARRAY_SIZE(mem_cgroup_lru_names) != NR_LRU_LISTS);
 }
 
-static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
+static int memcg_stat_show(struct cgroup *cont, struct cftype *cft,
 				 struct seq_file *m)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
@@ -4082,7 +4150,7 @@ static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
 	unsigned int i;
 
 	for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
-		if (i == MEM_CGROUP_STAT_SWAPOUT && !do_swap_account)
+		if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account)
 			continue;
 		seq_printf(m, "%s %ld\n", mem_cgroup_stat_names[i],
 			   mem_cgroup_read_stat(memcg, i) * PAGE_SIZE);
@@ -4109,7 +4177,7 @@ static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
 	for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
 		long long val = 0;
 
-		if (i == MEM_CGROUP_STAT_SWAPOUT && !do_swap_account)
+		if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account)
 			continue;
 		for_each_mem_cgroup_tree(mi, memcg)
 			val += mem_cgroup_read_stat(mi, i) * PAGE_SIZE;
@@ -4533,7 +4601,7 @@ static int mem_cgroup_oom_control_write(struct cgroup *cgrp,
 	return 0;
 }
 
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+#ifdef CONFIG_MEMCG_KMEM
 static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 {
 	return mem_cgroup_sockets_init(memcg, ss);
@@ -4588,7 +4656,7 @@ static struct cftype mem_cgroup_files[] = {
 	},
 	{
 		.name = "stat",
-		.read_seq_string = mem_control_stat_show,
+		.read_seq_string = memcg_stat_show,
 	},
 	{
 		.name = "force_empty",
@@ -4620,10 +4688,10 @@ static struct cftype mem_cgroup_files[] = {
 #ifdef CONFIG_NUMA
 	{
 		.name = "numa_stat",
-		.read_seq_string = mem_control_numa_stat_show,
+		.read_seq_string = memcg_numa_stat_show,
 	},
 #endif
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+#ifdef CONFIG_MEMCG_SWAP
 	{
 		.name = "memsw.usage_in_bytes",
 		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_USAGE),
@@ -4810,7 +4878,7 @@ struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
 }
 EXPORT_SYMBOL(parent_mem_cgroup);
 
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+#ifdef CONFIG_MEMCG_SWAP
 static void __init enable_swap_cgroup(void)
 {
 	if (!mem_cgroup_disabled() && really_do_swap_account)
@@ -5541,7 +5609,7 @@ struct cgroup_subsys mem_cgroup_subsys = {
 	.__DEPRECATED_clear_css_refs = true,
 };
 
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+#ifdef CONFIG_MEMCG_SWAP
 static int __init enable_swap_account(char *s)
 {
 	/* consider enabled if no parameter or 1 is given */

mm/memory-failure.c

@@ -128,7 +128,7 @@ static int hwpoison_filter_flags(struct page *p)
  * can only guarantee that the page either belongs to the memcg tasks, or is
  * a freed page.
  */
-#ifdef	CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+#ifdef	CONFIG_MEMCG_SWAP
 u64 hwpoison_filter_memcg;
 EXPORT_SYMBOL_GPL(hwpoison_filter_memcg);
 static int hwpoison_filter_task(struct page *p)
@@ -1416,7 +1416,6 @@ static int soft_offline_huge_page(struct page *page, int flags)
 	int ret;
 	unsigned long pfn = page_to_pfn(page);
 	struct page *hpage = compound_head(page);
-	LIST_HEAD(pagelist);
 
 	ret = get_any_page(page, pfn, flags);
 	if (ret < 0)
@@ -1431,24 +1430,18 @@ static int soft_offline_huge_page(struct page *page, int flags)
 	}
 
 	/* Keep page count to indicate a given hugepage is isolated. */
-
-	list_add(&hpage->lru, &pagelist);
-	ret = migrate_huge_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, false,
+	ret = migrate_huge_page(hpage, new_page, MPOL_MF_MOVE_ALL, false,
 				MIGRATE_SYNC);
+	put_page(hpage);
 	if (ret) {
-		struct page *page1, *page2;
-		list_for_each_entry_safe(page1, page2, &pagelist, lru)
-			put_page(page1);
-
 		pr_info("soft offline: %#lx: migration failed %d, type %lx\n",
 			pfn, ret, page->flags);
-		if (ret > 0)
-			ret = -EIO;
 		return ret;
 	}
 done:
 	if (!PageHWPoison(hpage))
-		atomic_long_add(1 << compound_trans_order(hpage), &mce_bad_pages);
+		atomic_long_add(1 << compound_trans_order(hpage),
+				&mce_bad_pages);
 	set_page_hwpoison_huge_page(hpage);
 	dequeue_hwpoisoned_huge_page(hpage);
 	/* keep elevated page count for bad page */

mm/memory.c

@@ -1343,8 +1343,11 @@ static void unmap_single_vma(struct mmu_gather *tlb,
 			 * Since no pte has actually been setup, it is
 			 * safe to do nothing in this case.
 			 */
-			if (vma->vm_file)
-				unmap_hugepage_range(vma, start, end, NULL);
+			if (vma->vm_file) {
+				mutex_lock(&vma->vm_file->f_mapping->i_mmap_mutex);
+				__unmap_hugepage_range_final(tlb, vma, start, end, NULL);
+				mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex);
+			}
 		} else
 			unmap_page_range(tlb, vma, start, end, details);
 	}
@@ -3938,7 +3941,7 @@ void print_vma_addr(char *prefix, unsigned long ip)
 			free_page((unsigned long)buf);
 		}
 	}
-	up_read(&current->mm->mmap_sem);
+	up_read(&mm->mmap_sem);
 }
 
 #ifdef CONFIG_PROVE_LOCKING

mm/memory_hotplug.c

@@ -512,19 +512,20 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages)
 
 	zone->present_pages += onlined_pages;
 	zone->zone_pgdat->node_present_pages += onlined_pages;
-	if (need_zonelists_rebuild)
-		build_all_zonelists(zone);
-	else
-		zone_pcp_update(zone);
+	if (onlined_pages) {
+		node_set_state(zone_to_nid(zone), N_HIGH_MEMORY);
+		if (need_zonelists_rebuild)
+			build_all_zonelists(NULL, zone);
+		else
+			zone_pcp_update(zone);
+	}
 
 	mutex_unlock(&zonelists_mutex);
 
 	init_per_zone_wmark_min();
 
-	if (onlined_pages) {
+	if (onlined_pages)
 		kswapd_run(zone_to_nid(zone));
-		node_set_state(zone_to_nid(zone), N_HIGH_MEMORY);
-	}
 
 	vm_total_pages = nr_free_pagecache_pages();
 
@@ -562,7 +563,7 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start)
 	 * to access not-initialized zonelist, build here.
 	 */
 	mutex_lock(&zonelists_mutex);
-	build_all_zonelists(NULL);
+	build_all_zonelists(pgdat, NULL);
 	mutex_unlock(&zonelists_mutex);
 
 	return pgdat;
@@ -965,6 +966,9 @@ repeat:
 
 	init_per_zone_wmark_min();
 
+	if (!populated_zone(zone))
+		zone_pcp_reset(zone);
+
 	if (!node_present_pages(node)) {
 		node_clear_state(node, N_HIGH_MEMORY);
 		kswapd_stop(node);

mm/migrate.c

@@ -33,6 +33,7 @@
 #include <linux/memcontrol.h>
 #include <linux/syscalls.h>
 #include <linux/hugetlb.h>
+#include <linux/hugetlb_cgroup.h>
 #include <linux/gfp.h>
 
 #include <asm/tlbflush.h>
@@ -682,7 +683,6 @@ static int __unmap_and_move(struct page *page, struct page *newpage,
 {
 	int rc = -EAGAIN;
 	int remap_swapcache = 1;
-	int charge = 0;
 	struct mem_cgroup *mem;
 	struct anon_vma *anon_vma = NULL;
 
@@ -724,12 +724,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage,
 	}
 
 	/* charge against new page */
-	charge = mem_cgroup_prepare_migration(page, newpage, &mem, GFP_KERNEL);
-	if (charge == -ENOMEM) {
-		rc = -ENOMEM;
-		goto unlock;
-	}
-	BUG_ON(charge);
+	mem_cgroup_prepare_migration(page, newpage, &mem);
 
 	if (PageWriteback(page)) {
 		/*
@@ -819,8 +814,7 @@ skip_unmap:
 		put_anon_vma(anon_vma);
 
 uncharge:
-	if (!charge)
-		mem_cgroup_end_migration(mem, page, newpage, rc == 0);
+	mem_cgroup_end_migration(mem, page, newpage, rc == 0);
 unlock:
 	unlock_page(page);
 out:
@@ -931,16 +925,13 @@ static int unmap_and_move_huge_page(new_page_t get_new_page,
 
 	if (anon_vma)
 		put_anon_vma(anon_vma);
-	unlock_page(hpage);
 
-out:
-	if (rc != -EAGAIN) {
-		list_del(&hpage->lru);
-		put_page(hpage);
-	}
+	if (!rc)
+		hugetlb_cgroup_migrate(hpage, new_hpage);
 
+	unlock_page(hpage);
+out:
 	put_page(new_hpage);
-
 	if (result) {
 		if (rc)
 			*result = rc;
@@ -1016,48 +1007,32 @@ out:
 	return nr_failed + retry;
 }
 
-int migrate_huge_pages(struct list_head *from,
-		new_page_t get_new_page, unsigned long private, bool offlining,
-		enum migrate_mode mode)
+int migrate_huge_page(struct page *hpage, new_page_t get_new_page,
+		      unsigned long private, bool offlining,
+		      enum migrate_mode mode)
 {
-	int retry = 1;
-	int nr_failed = 0;
-	int pass = 0;
-	struct page *page;
-	struct page *page2;
-	int rc;
-
-	for (pass = 0; pass < 10 && retry; pass++) {
-		retry = 0;
-
-		list_for_each_entry_safe(page, page2, from, lru) {
+	int pass, rc;
+
+	for (pass = 0; pass < 10; pass++) {
+		rc = unmap_and_move_huge_page(get_new_page,
+					      private, hpage, pass > 2, offlining,
+					      mode);
+		switch (rc) {
+		case -ENOMEM:
+			goto out;
+		case -EAGAIN:
+			/* try again */
 			cond_resched();
-
-			rc = unmap_and_move_huge_page(get_new_page,
-					private, page, pass > 2, offlining,
-					mode);
-
-			switch(rc) {
-			case -ENOMEM:
-				goto out;
-			case -EAGAIN:
-				retry++;
-				break;
-			case 0:
-				break;
-			default:
-				/* Permanent failure */
-				nr_failed++;
-				break;
-			}
+			break;
+		case 0:
+			goto out;
+		default:
+			rc = -EIO;
+			goto out;
 		}
 	}
-	rc = 0;
 out:
-	if (rc)
-		return rc;
-
-	return nr_failed + retry;
+	return rc;
 }
 
 #ifdef CONFIG_NUMA

mm/mmap.c

@@ -943,6 +943,8 @@ void vm_stat_account(struct mm_struct *mm, unsigned long flags,
 	const unsigned long stack_flags
 		= VM_STACK_FLAGS & (VM_GROWSUP|VM_GROWSDOWN);
 
+	mm->total_vm += pages;
+
 	if (file) {
 		mm->shared_vm += pages;
 		if ((flags & (VM_EXEC|VM_WRITE)) == VM_EXEC)
@@ -1347,7 +1349,6 @@ munmap_back:
 out:
 	perf_event_mmap(vma);
 
-	mm->total_vm += len >> PAGE_SHIFT;
 	vm_stat_account(mm, vm_flags, file, len >> PAGE_SHIFT);
 	if (vm_flags & VM_LOCKED) {
 		if (!mlock_vma_pages_range(vma, addr, addr + len))
@@ -1707,7 +1708,6 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns
 		return -ENOMEM;
 
 	/* Ok, everything looks good - let it rip */
-	mm->total_vm += grow;
 	if (vma->vm_flags & VM_LOCKED)
 		mm->locked_vm += grow;
 	vm_stat_account(mm, vma->vm_flags, vma->vm_file, grow);
@@ -1889,7 +1889,6 @@ static void remove_vma_list(struct mm_struct *mm, struct vm_area_struct *vma)
 
 		if (vma->vm_flags & VM_ACCOUNT)
 			nr_accounted += nrpages;
-		mm->total_vm -= nrpages;
 		vm_stat_account(mm, vma->vm_flags, vma->vm_file, -nrpages);
 		vma = remove_vma(vma);
 	} while (vma);

mm/mmu_notifier.c

@@ -33,6 +33,24 @@
 void __mmu_notifier_release(struct mm_struct *mm)
 {
 	struct mmu_notifier *mn;
+	struct hlist_node *n;
+
+	/*
+	 * RCU here will block mmu_notifier_unregister until
+	 * ->release returns.
+	 */
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(mn, n, &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);
+	rcu_read_unlock();
 
 	spin_lock(&mm->mmu_notifier_mm->lock);
 	while (unlikely(!hlist_empty(&mm->mmu_notifier_mm->list))) {
@@ -46,23 +64,6 @@ void __mmu_notifier_release(struct mm_struct *mm)
 		 * mmu_notifier_unregister to return.
 		 */
 		hlist_del_init_rcu(&mn->hlist);
-		/*
-		 * RCU here will block mmu_notifier_unregister until
-		 * ->release returns.
-		 */
-		rcu_read_lock();
-		spin_unlock(&mm->mmu_notifier_mm->lock);
-		/*
-		 * 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);
-		rcu_read_unlock();
-		spin_lock(&mm->mmu_notifier_mm->lock);
 	}
 	spin_unlock(&mm->mmu_notifier_mm->lock);
 
@@ -284,16 +285,13 @@ void mmu_notifier_unregister(struct mmu_notifier *mn, struct mm_struct *mm)
 {
 	BUG_ON(atomic_read(&mm->mm_count) <= 0);
 
-	spin_lock(&mm->mmu_notifier_mm->lock);
 	if (!hlist_unhashed(&mn->hlist)) {
-		hlist_del_rcu(&mn->hlist);
-
 		/*
 		 * RCU here will force exit_mmap to wait ->release to finish
 		 * before freeing the pages.
 		 */
 		rcu_read_lock();
-		spin_unlock(&mm->mmu_notifier_mm->lock);
+
 		/*
 		 * exit_mmap will block in mmu_notifier_release to
 		 * guarantee ->release is called before freeing the
@@ -302,8 +300,11 @@ void mmu_notifier_unregister(struct mmu_notifier *mn, struct mm_struct *mm)
 		if (mn->ops->release)
 			mn->ops->release(mn, mm);
 		rcu_read_unlock();
-	} else
+
+		spin_lock(&mm->mmu_notifier_mm->lock);
+		hlist_del_rcu(&mn->hlist);
 		spin_unlock(&mm->mmu_notifier_mm->lock);
+	}
 
 	/*
 	 * Wait any running method to finish, of course including

mm/mmzone.c

@@ -96,7 +96,7 @@ void lruvec_init(struct lruvec *lruvec, struct zone *zone)
 	for_each_lru(lru)
 		INIT_LIST_HEAD(&lruvec->lists[lru]);
 
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+#ifdef CONFIG_MEMCG
 	lruvec->zone = zone;
 #endif
 }

mm/mremap.c

@@ -260,7 +260,6 @@ static unsigned long move_vma(struct vm_area_struct *vma,
 	 * If this were a serious issue, we'd add a flag to do_munmap().
 	 */
 	hiwater_vm = mm->hiwater_vm;
-	mm->total_vm += new_len >> PAGE_SHIFT;
 	vm_stat_account(mm, vma->vm_flags, vma->vm_file, new_len>>PAGE_SHIFT);
 
 	if (do_munmap(mm, old_addr, old_len) < 0) {
@@ -497,7 +496,6 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
 				goto out;
 			}
 
-			mm->total_vm += pages;
 			vm_stat_account(mm, vma->vm_flags, vma->vm_file, pages);
 			if (vma->vm_flags & VM_LOCKED) {
 				mm->locked_vm += pages;

mm/oom_kill.c

@@ -288,76 +288,93 @@ static enum oom_constraint constrained_alloc(struct zonelist *zonelist,
 }
 #endif
 
+enum oom_scan_t oom_scan_process_thread(struct task_struct *task,
+		unsigned long totalpages, const nodemask_t *nodemask,
+		bool force_kill)
+{
+	if (task->exit_state)
+		return OOM_SCAN_CONTINUE;
+	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->flags & PF_EXITING) {
+		/*
+		 * If task is current and is in the process of releasing memory,
+		 * allow the "kill" to set TIF_MEMDIE, which will allow it to
+		 * access memory reserves.  Otherwise, it may stall forever.
+		 *
+		 * The iteration isn't broken here, however, in case other
+		 * threads are found to have already been oom killed.
+		 */
+		if (task == current)
+			return OOM_SCAN_SELECT;
+		else if (!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'. We expect the caller will lock the tasklist.
+ * number of 'points'.
  *
  * (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, struct mem_cgroup *memcg,
-		const nodemask_t *nodemask, bool force_kill)
+		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();
 	do_each_thread(g, p) {
 		unsigned int points;
 
-		if (p->exit_state)
-			continue;
-		if (oom_unkillable_task(p, memcg, nodemask))
-			continue;
-
-		/*
-		 * This task already has access to memory reserves and is
-		 * being killed. Don't allow any other task access to the
-		 * memory reserve.
-		 *
-		 * Note: this may have a chance of deadlock if it gets
-		 * blocked waiting for another task which itself is waiting
-		 * for memory. Is there a better alternative?
-		 */
-		if (test_tsk_thread_flag(p, TIF_MEMDIE)) {
-			if (unlikely(frozen(p)))
-				__thaw_task(p);
-			if (!force_kill)
-				return ERR_PTR(-1UL);
-		}
-		if (!p->mm)
+		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;
-
-		if (p->flags & PF_EXITING) {
-			/*
-			 * If p is the current task and is in the process of
-			 * releasing memory, we allow the "kill" to set
-			 * TIF_MEMDIE, which will allow it to gain access to
-			 * memory reserves.  Otherwise, it may stall forever.
-			 *
-			 * The loop isn't broken here, however, in case other
-			 * threads are found to have already been oom killed.
-			 */
-			if (p == current) {
-				chosen = p;
-				chosen_points = ULONG_MAX;
-			} else if (!force_kill) {
-				/*
-				 * If this task is not being ptraced on exit,
-				 * then wait for it to finish before killing
-				 * some other task unnecessarily.
-				 */
-				if (!(p->group_leader->ptrace & PT_TRACE_EXIT))
-					return ERR_PTR(-1UL);
-			}
-		}
-
-		points = oom_badness(p, memcg, nodemask, totalpages);
+		case OOM_SCAN_ABORT:
+			rcu_read_unlock();
+			return ERR_PTR(-1UL);
+		case OOM_SCAN_OK:
+			break;
+		};
+		points = oom_badness(p, NULL, nodemask, totalpages);
 		if (points > chosen_points) {
 			chosen = p;
 			chosen_points = points;
 		}
 	} while_each_thread(g, p);
+	if (chosen)
+		get_task_struct(chosen);
+	rcu_read_unlock();
 
 	*ppoints = chosen_points * 1000 / totalpages;
 	return chosen;
@@ -371,17 +388,16 @@ static struct task_struct *select_bad_process(unsigned int *ppoints,
  * 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, cpu, oom_adj
- * value, oom_score_adj value, and name.
- *
- * Call with tasklist_lock read-locked.
+ * 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 cpu oom_adj oom_score_adj name\n");
+	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;
@@ -396,13 +412,15 @@ static void dump_tasks(const struct mem_cgroup *memcg, const nodemask_t *nodemas
 			continue;
 		}
 
-		pr_info("[%5d] %5d %5d %8lu %8lu %3u     %3d         %5d %s\n",
+		pr_info("[%5d] %5d %5d %8lu %8lu %7lu %8lu         %5d %s\n",
 			task->pid, from_kuid(&init_user_ns, task_uid(task)),
 			task->tgid, task->mm->total_vm, get_mm_rss(task->mm),
-			task_cpu(task), task->signal->oom_adj,
+			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 void dump_header(struct task_struct *p, gfp_t gfp_mask, int order,
@@ -423,10 +441,14 @@ static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order,
 }
 
 #define K(x) ((x) << (PAGE_SHIFT-10))
-static 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)
+/*
+ * 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;
@@ -442,6 +464,7 @@ static void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 	 */
 	if (p->flags & PF_EXITING) {
 		set_tsk_thread_flag(p, TIF_MEMDIE);
+		put_task_struct(p);
 		return;
 	}
 
@@ -459,6 +482,7 @@ static void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 	 * parent.  This attempts to lose the minimal amount of work done while
 	 * still freeing memory.
 	 */
+	read_lock(&tasklist_lock);
 	do {
 		list_for_each_entry(child, &t->children, sibling) {
 			unsigned int child_points;
@@ -471,15 +495,26 @@ static void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 			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);
 			}
 		}
 	} while_each_thread(p, t);
+	read_unlock(&tasklist_lock);
 
-	victim = find_lock_task_mm(victim);
-	if (!victim)
+	rcu_read_lock();
+	p = find_lock_task_mm(victim);
+	if (!p) {
+		rcu_read_unlock();
+		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;
@@ -510,17 +545,19 @@ static void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 			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.
  */
-static void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask,
-				int order, const nodemask_t *nodemask)
+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;
@@ -533,42 +570,11 @@ static void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask,
 		if (constraint != CONSTRAINT_NONE)
 			return;
 	}
-	read_lock(&tasklist_lock);
 	dump_header(NULL, gfp_mask, order, NULL, nodemask);
-	read_unlock(&tasklist_lock);
 	panic("Out of memory: %s panic_on_oom is enabled\n",
 		sysctl_panic_on_oom == 2 ? "compulsory" : "system-wide");
 }
 
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
-void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
-			      int order)
-{
-	unsigned long limit;
-	unsigned int points = 0;
-	struct task_struct *p;
-
-	/*
-	 * If current has a pending SIGKILL, 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)) {
-		set_thread_flag(TIF_MEMDIE);
-		return;
-	}
-
-	check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, order, NULL);
-	limit = mem_cgroup_get_limit(memcg) >> PAGE_SHIFT ? : 1;
-	read_lock(&tasklist_lock);
-	p = select_bad_process(&points, limit, memcg, NULL, false);
-	if (p && PTR_ERR(p) != -1UL)
-		oom_kill_process(p, gfp_mask, order, points, limit, memcg, NULL,
-				 "Memory cgroup out of memory");
-	read_unlock(&tasklist_lock);
-}
-#endif
-
 static BLOCKING_NOTIFIER_HEAD(oom_notify_list);
 
 int register_oom_notifier(struct notifier_block *nb)
@@ -690,7 +696,7 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
 	struct task_struct *p;
 	unsigned long totalpages;
 	unsigned long freed = 0;
-	unsigned int points;
+	unsigned int uninitialized_var(points);
 	enum oom_constraint constraint = CONSTRAINT_NONE;
 	int killed = 0;
 
@@ -718,22 +724,20 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
 	mpol_mask = (constraint == CONSTRAINT_MEMORY_POLICY) ? nodemask : NULL;
 	check_panic_on_oom(constraint, gfp_mask, order, mpol_mask);
 
-	read_lock(&tasklist_lock);
-	if (sysctl_oom_kill_allocating_task &&
+	if (sysctl_oom_kill_allocating_task && current->mm &&
 	    !oom_unkillable_task(current, NULL, nodemask) &&
-	    current->mm) {
+	    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, NULL, mpol_mask,
-			       force_kill);
+	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);
-		read_unlock(&tasklist_lock);
 		panic("Out of memory and no killable processes...\n");
 	}
 	if (PTR_ERR(p) != -1UL) {
@@ -742,14 +746,12 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
 		killed = 1;
 	}
 out:
-	read_unlock(&tasklist_lock);
-
 	/*
-	 * Give "p" a good chance of killing itself before we
-	 * retry to allocate memory unless "p" is current
+	 * Give the killed threads a good chance of exiting before trying to
+	 * allocate memory again.
 	 */
-	if (killed && !test_thread_flag(TIF_MEMDIE))
-		schedule_timeout_uninterruptible(1);
+	if (killed)
+		schedule_timeout_killable(1);
 }
 
 /*
@@ -764,6 +766,5 @@ void pagefault_out_of_memory(void)
 		out_of_memory(NULL, 0, 0, NULL, false);
 		clear_system_oom();
 	}
-	if (!test_thread_flag(TIF_MEMDIE))
-		schedule_timeout_uninterruptible(1);
+	schedule_timeout_killable(1);
 }

mm/page_alloc.c

@@ -51,7 +51,6 @@
 #include <linux/page_cgroup.h>
 #include <linux/debugobjects.h>
 #include <linux/kmemleak.h>
-#include <linux/memory.h>
 #include <linux/compaction.h>
 #include <trace/events/kmem.h>
 #include <linux/ftrace_event.h>
@@ -219,7 +218,12 @@ EXPORT_SYMBOL(nr_online_nodes);
 
 int page_group_by_mobility_disabled __read_mostly;
 
-static void set_pageblock_migratetype(struct page *page, int migratetype)
+/*
+ * NOTE:
+ * Don't use set_pageblock_migratetype(page, MIGRATE_ISOLATE) directly.
+ * Instead, use {un}set_pageblock_isolate.
+ */
+void set_pageblock_migratetype(struct page *page, int migratetype)
 {
 
 	if (unlikely(page_group_by_mobility_disabled))
@@ -954,7 +958,7 @@ static int move_freepages(struct zone *zone,
 	return pages_moved;
 }
 
-static int move_freepages_block(struct zone *zone, struct page *page,
+int move_freepages_block(struct zone *zone, struct page *page,
 				int migratetype)
 {
 	unsigned long start_pfn, end_pfn;
@@ -1158,8 +1162,10 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp)
 		to_drain = pcp->batch;
 	else
 		to_drain = pcp->count;
-	free_pcppages_bulk(zone, to_drain, pcp);
-	pcp->count -= to_drain;
+	if (to_drain > 0) {
+		free_pcppages_bulk(zone, to_drain, pcp);
+		pcp->count -= to_drain;
+	}
 	local_irq_restore(flags);
 }
 #endif
@@ -1529,16 +1535,16 @@ static int __init setup_fail_page_alloc(char *str)
 }
 __setup("fail_page_alloc=", setup_fail_page_alloc);
 
-static int should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
+static bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
 {
 	if (order < fail_page_alloc.min_order)
-		return 0;
+		return false;
 	if (gfp_mask & __GFP_NOFAIL)
-		return 0;
+		return false;
 	if (fail_page_alloc.ignore_gfp_highmem && (gfp_mask & __GFP_HIGHMEM))
-		return 0;
+		return false;
 	if (fail_page_alloc.ignore_gfp_wait && (gfp_mask & __GFP_WAIT))
-		return 0;
+		return false;
 
 	return should_fail(&fail_page_alloc.attr, 1 << order);
 }
@@ -1578,9 +1584,9 @@ late_initcall(fail_page_alloc_debugfs);
 
 #else /* CONFIG_FAIL_PAGE_ALLOC */
 
-static inline int should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
+static inline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
 {
-	return 0;
+	return false;
 }
 
 #endif /* CONFIG_FAIL_PAGE_ALLOC */
@@ -1594,6 +1600,7 @@ static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark,
 {
 	/* free_pages my go negative - that's OK */
 	long min = mark;
+	long lowmem_reserve = z->lowmem_reserve[classzone_idx];
 	int o;
 
 	free_pages -= (1 << order) - 1;
@@ -1602,7 +1609,7 @@ static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark,
 	if (alloc_flags & ALLOC_HARDER)
 		min -= min / 4;
 
-	if (free_pages <= min + z->lowmem_reserve[classzone_idx])
+	if (free_pages <= min + lowmem_reserve)
 		return false;
 	for (o = 0; o < order; o++) {
 		/* At the next order, this order's pages become unavailable */
@@ -1617,6 +1624,20 @@ static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark,
 	return true;
 }
 
+#ifdef CONFIG_MEMORY_ISOLATION
+static inline unsigned long nr_zone_isolate_freepages(struct zone *zone)
+{
+	if (unlikely(zone->nr_pageblock_isolate))
+		return zone->nr_pageblock_isolate * pageblock_nr_pages;
+	return 0;
+}
+#else
+static inline unsigned long nr_zone_isolate_freepages(struct zone *zone)
+{
+	return 0;
+}
+#endif
+
 bool zone_watermark_ok(struct zone *z, int order, unsigned long mark,
 		      int classzone_idx, int alloc_flags)
 {
@@ -1632,6 +1653,14 @@ bool zone_watermark_ok_safe(struct zone *z, int order, unsigned long mark,
 	if (z->percpu_drift_mark && free_pages < z->percpu_drift_mark)
 		free_pages = zone_page_state_snapshot(z, NR_FREE_PAGES);
 
+	/*
+	 * If the zone has MIGRATE_ISOLATE type free pages, we should consider
+	 * it.  nr_zone_isolate_freepages is never accurate so kswapd might not
+	 * sleep although it could do so.  But this is more desirable for memory
+	 * hotplug than sleeping which can cause a livelock in the direct
+	 * reclaim path.
+	 */
+	free_pages -= nr_zone_isolate_freepages(z);
 	return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags,
 								free_pages);
 }
@@ -2087,8 +2116,8 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 
 		page = get_page_from_freelist(gfp_mask, nodemask,
 				order, zonelist, high_zoneidx,
-				alloc_flags, preferred_zone,
-				migratetype);
+				alloc_flags & ~ALLOC_NO_WATERMARKS,
+				preferred_zone, migratetype);
 		if (page) {
 			preferred_zone->compact_considered = 0;
 			preferred_zone->compact_defer_shift = 0;
@@ -2180,8 +2209,8 @@ __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order,
 retry:
 	page = get_page_from_freelist(gfp_mask, nodemask, order,
 					zonelist, high_zoneidx,
-					alloc_flags, preferred_zone,
-					migratetype);
+					alloc_flags & ~ALLOC_NO_WATERMARKS,
+					preferred_zone, migratetype);
 
 	/*
 	 * If an allocation failed after direct reclaim, it could be because
@@ -2265,15 +2294,24 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
 		alloc_flags |= ALLOC_HARDER;
 
 	if (likely(!(gfp_mask & __GFP_NOMEMALLOC))) {
-		if (!in_interrupt() &&
-		    ((current->flags & PF_MEMALLOC) ||
-		     unlikely(test_thread_flag(TIF_MEMDIE))))
+		if (gfp_mask & __GFP_MEMALLOC)
+			alloc_flags |= ALLOC_NO_WATERMARKS;
+		else if (in_serving_softirq() && (current->flags & PF_MEMALLOC))
+			alloc_flags |= ALLOC_NO_WATERMARKS;
+		else if (!in_interrupt() &&
+				((current->flags & PF_MEMALLOC) ||
+				 unlikely(test_thread_flag(TIF_MEMDIE))))
 			alloc_flags |= ALLOC_NO_WATERMARKS;
 	}
 
 	return alloc_flags;
 }
 
+bool gfp_pfmemalloc_allowed(gfp_t gfp_mask)
+{
+	return !!(gfp_to_alloc_flags(gfp_mask) & ALLOC_NO_WATERMARKS);
+}
+
 static inline struct page *
 __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	struct zonelist *zonelist, enum zone_type high_zoneidx,
@@ -2340,11 +2378,27 @@ rebalance:
 
 	/* Allocate without watermarks if the context allows */
 	if (alloc_flags & ALLOC_NO_WATERMARKS) {
+		/*
+		 * Ignore mempolicies if ALLOC_NO_WATERMARKS on the grounds
+		 * the allocation is high priority and these type of
+		 * allocations are system rather than user orientated
+		 */
+		zonelist = node_zonelist(numa_node_id(), gfp_mask);
+
 		page = __alloc_pages_high_priority(gfp_mask, order,
 				zonelist, high_zoneidx, nodemask,
 				preferred_zone, migratetype);
-		if (page)
+		if (page) {
+			/*
+			 * page->pfmemalloc is set when ALLOC_NO_WATERMARKS was
+			 * necessary to allocate the page. The expectation is
+			 * that the caller is taking steps that will free more
+			 * memory. The caller should avoid the page being used
+			 * for !PFMEMALLOC purposes.
+			 */
+			page->pfmemalloc = true;
 			goto got_pg;
+		}
 	}
 
 	/* Atomic allocations - we can't balance anything */
@@ -2463,8 +2517,8 @@ nopage:
 got_pg:
 	if (kmemcheck_enabled)
 		kmemcheck_pagealloc_alloc(page, order, gfp_mask);
-	return page;
 
+	return page;
 }
 
 /*
@@ -2515,6 +2569,8 @@ retry_cpuset:
 		page = __alloc_pages_slowpath(gfp_mask, order,
 				zonelist, high_zoneidx, nodemask,
 				preferred_zone, migratetype);
+	else
+		page->pfmemalloc = false;
 
 	trace_mm_page_alloc(page, order, gfp_mask, migratetype);
 
@@ -3030,7 +3086,7 @@ int numa_zonelist_order_handler(ctl_table *table, int write,
 			user_zonelist_order = oldval;
 		} else if (oldval != user_zonelist_order) {
 			mutex_lock(&zonelists_mutex);
-			build_all_zonelists(NULL);
+			build_all_zonelists(NULL, NULL);
 			mutex_unlock(&zonelists_mutex);
 		}
 	}
@@ -3409,14 +3465,21 @@ static void setup_zone_pageset(struct zone *zone);
 DEFINE_MUTEX(zonelists_mutex);
 
 /* return values int ....just for stop_machine() */
-static __init_refok int __build_all_zonelists(void *data)
+static int __build_all_zonelists(void *data)
 {
 	int nid;
 	int cpu;
+	pg_data_t *self = data;
 
 #ifdef CONFIG_NUMA
 	memset(node_load, 0, sizeof(node_load));
 #endif
+
+	if (self && !node_online(self->node_id)) {
+		build_zonelists(self);
+		build_zonelist_cache(self);
+	}
+
 	for_each_online_node(nid) {
 		pg_data_t *pgdat = NODE_DATA(nid);
 
@@ -3461,7 +3524,7 @@ static __init_refok int __build_all_zonelists(void *data)
  * Called with zonelists_mutex held always
  * unless system_state == SYSTEM_BOOTING.
  */
-void __ref build_all_zonelists(void *data)
+void __ref build_all_zonelists(pg_data_t *pgdat, struct zone *zone)
 {
 	set_zonelist_order();
 
@@ -3473,10 +3536,10 @@ void __ref build_all_zonelists(void *data)
 		/* we have to stop all cpus to guarantee there is no user
 		   of zonelist */
 #ifdef CONFIG_MEMORY_HOTPLUG
-		if (data)
-			setup_zone_pageset((struct zone *)data);
+		if (zone)
+			setup_zone_pageset(zone);
 #endif
-		stop_machine(__build_all_zonelists, NULL, NULL);
+		stop_machine(__build_all_zonelists, pgdat, NULL);
 		/* cpuset refresh routine should be here */
 	}
 	vm_total_pages = nr_free_pagecache_pages();
@@ -3746,7 +3809,7 @@ static void __meminit zone_init_free_lists(struct zone *zone)
 	memmap_init_zone((size), (nid), (zone), (start_pfn), MEMMAP_EARLY)
 #endif
 
-static int zone_batchsize(struct zone *zone)
+static int __meminit zone_batchsize(struct zone *zone)
 {
 #ifdef CONFIG_MMU
 	int batch;
@@ -3828,7 +3891,7 @@ static void setup_pagelist_highmark(struct per_cpu_pageset *p,
 		pcp->batch = PAGE_SHIFT * 8;
 }
 
-static void setup_zone_pageset(struct zone *zone)
+static void __meminit setup_zone_pageset(struct zone *zone)
 {
 	int cpu;
 
@@ -3901,32 +3964,6 @@ int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages)
 	return 0;
 }
 
-static int __zone_pcp_update(void *data)
-{
-	struct zone *zone = data;
-	int cpu;
-	unsigned long batch = zone_batchsize(zone), flags;
-
-	for_each_possible_cpu(cpu) {
-		struct per_cpu_pageset *pset;
-		struct per_cpu_pages *pcp;
-
-		pset = per_cpu_ptr(zone->pageset, cpu);
-		pcp = &pset->pcp;
-
-		local_irq_save(flags);
-		free_pcppages_bulk(zone, pcp->count, pcp);
-		setup_pageset(pset, batch);
-		local_irq_restore(flags);
-	}
-	return 0;
-}
-
-void zone_pcp_update(struct zone *zone)
-{
-	stop_machine(__zone_pcp_update, zone, NULL);
-}
-
 static __meminit void zone_pcp_init(struct zone *zone)
 {
 	/*
@@ -3942,7 +3979,7 @@ static __meminit void zone_pcp_init(struct zone *zone)
 					 zone_batchsize(zone));
 }
 
-__meminit int init_currently_empty_zone(struct zone *zone,
+int __meminit init_currently_empty_zone(struct zone *zone,
 					unsigned long zone_start_pfn,
 					unsigned long size,
 					enum memmap_context context)
@@ -4301,7 +4338,7 @@ static inline void setup_usemap(struct pglist_data *pgdat,
 #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
 
 /* Initialise the number of pages represented by NR_PAGEBLOCK_BITS */
-static inline void __init set_pageblock_order(void)
+void __init set_pageblock_order(void)
 {
 	unsigned int order;
 
@@ -4329,7 +4366,7 @@ static inline void __init set_pageblock_order(void)
  * include/linux/pageblock-flags.h for the values of pageblock_order based on
  * the kernel config
  */
-static inline void set_pageblock_order(void)
+void __init set_pageblock_order(void)
 {
 }
 
@@ -4340,6 +4377,8 @@ static inline void set_pageblock_order(void)
  *   - mark all pages reserved
  *   - mark all memory queues empty
  *   - clear the memory bitmaps
+ *
+ * NOTE: pgdat should get zeroed by caller.
  */
 static void __paginginit free_area_init_core(struct pglist_data *pgdat,
 		unsigned long *zones_size, unsigned long *zholes_size)
@@ -4350,9 +4389,8 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
 	int ret;
 
 	pgdat_resize_init(pgdat);
-	pgdat->nr_zones = 0;
 	init_waitqueue_head(&pgdat->kswapd_wait);
-	pgdat->kswapd_max_order = 0;
+	init_waitqueue_head(&pgdat->pfmemalloc_wait);
 	pgdat_page_cgroup_init(pgdat);
 
 	for (j = 0; j < MAX_NR_ZONES; j++) {
@@ -4394,6 +4432,11 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
 
 		zone->spanned_pages = size;
 		zone->present_pages = realsize;
+#if defined CONFIG_COMPACTION || defined CONFIG_CMA
+		zone->compact_cached_free_pfn = zone->zone_start_pfn +
+						zone->spanned_pages;
+		zone->compact_cached_free_pfn &= ~(pageblock_nr_pages-1);
+#endif
 #ifdef CONFIG_NUMA
 		zone->node = nid;
 		zone->min_unmapped_pages = (realsize*sysctl_min_unmapped_ratio)
@@ -4408,8 +4451,6 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
 
 		zone_pcp_init(zone);
 		lruvec_init(&zone->lruvec, zone);
-		zap_zone_vm_stats(zone);
-		zone->flags = 0;
 		if (!size)
 			continue;
 
@@ -4469,6 +4510,9 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
 {
 	pg_data_t *pgdat = NODE_DATA(nid);
 
+	/* pg_data_t should be reset to zero when it's allocated */
+	WARN_ON(pgdat->nr_zones || pgdat->node_start_pfn || pgdat->classzone_idx);
+
 	pgdat->node_id = nid;
 	pgdat->node_start_pfn = node_start_pfn;
 	calculate_node_totalpages(pgdat, zones_size, zholes_size);
@@ -4750,7 +4794,7 @@ out:
 }
 
 /* Any regular memory on that node ? */
-static void check_for_regular_memory(pg_data_t *pgdat)
+static void __init check_for_regular_memory(pg_data_t *pgdat)
 {
 #ifdef CONFIG_HIGHMEM
 	enum zone_type zone_type;
@@ -5468,26 +5512,27 @@ void set_pageblock_flags_group(struct page *page, unsigned long flags,
 }
 
 /*
- * This is designed as sub function...plz see page_isolation.c also.
- * set/clear page block's type to be ISOLATE.
- * page allocater never alloc memory from ISOLATE block.
+ * This function checks whether pageblock includes unmovable pages or not.
+ * If @count is not zero, it is okay to include less @count unmovable pages
+ *
+ * PageLRU check wihtout isolation or lru_lock could race so that
+ * MIGRATE_MOVABLE block might include unmovable pages. It means you can't
+ * expect this function should be exact.
  */
-
-static int
-__count_immobile_pages(struct zone *zone, struct page *page, int count)
+bool has_unmovable_pages(struct zone *zone, struct page *page, int count)
 {
 	unsigned long pfn, iter, found;
 	int mt;
 
 	/*
 	 * For avoiding noise data, lru_add_drain_all() should be called
-	 * If ZONE_MOVABLE, the zone never contains immobile pages
+	 * If ZONE_MOVABLE, the zone never contains unmovable pages
 	 */
 	if (zone_idx(zone) == ZONE_MOVABLE)
-		return true;
+		return false;
 	mt = get_pageblock_migratetype(page);
 	if (mt == MIGRATE_MOVABLE || is_migrate_cma(mt))
-		return true;
+		return false;
 
 	pfn = page_to_pfn(page);
 	for (found = 0, iter = 0; iter < pageblock_nr_pages; iter++) {
@@ -5497,11 +5542,18 @@ __count_immobile_pages(struct zone *zone, struct page *page, int count)
 			continue;
 
 		page = pfn_to_page(check);
-		if (!page_count(page)) {
+		/*
+		 * We can't use page_count without pin a page
+		 * because another CPU can free compound page.
+		 * This check already skips compound tails of THP
+		 * because their page->_count is zero at all time.
+		 */
+		if (!atomic_read(&page->_count)) {
 			if (PageBuddy(page))
 				iter += (1 << page_order(page)) - 1;
 			continue;
 		}
+
 		if (!PageLRU(page))
 			found++;
 		/*
@@ -5518,9 +5570,9 @@ __count_immobile_pages(struct zone *zone, struct page *page, int count)
 		 * page at boot.
 		 */
 		if (found > count)
-			return false;
+			return true;
 	}
-	return true;
+	return false;
 }
 
 bool is_pageblock_removable_nolock(struct page *page)
@@ -5544,77 +5596,7 @@ bool is_pageblock_removable_nolock(struct page *page)
 			zone->zone_start_pfn + zone->spanned_pages <= pfn)
 		return false;
 
-	return __count_immobile_pages(zone, page, 0);
-}
-
-int set_migratetype_isolate(struct page *page)
-{
-	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 (__count_immobile_pages(zone, page, arg.pages_found))
-		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) {
-		set_pageblock_migratetype(page, MIGRATE_ISOLATE);
-		move_freepages_block(zone, page, MIGRATE_ISOLATE);
-	}
-
-	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;
-	zone = page_zone(page);
-	spin_lock_irqsave(&zone->lock, flags);
-	if (get_pageblock_migratetype(page) != MIGRATE_ISOLATE)
-		goto out;
-	set_pageblock_migratetype(page, migratetype);
-	move_freepages_block(zone, page, migratetype);
-out:
-	spin_unlock_irqrestore(&zone->lock, flags);
+	return !has_unmovable_pages(zone, page, 0);
 }
 
 #ifdef CONFIG_CMA
@@ -5869,7 +5851,49 @@ void free_contig_range(unsigned long pfn, unsigned nr_pages)
 }
 #endif
 
+#ifdef CONFIG_MEMORY_HOTPLUG
+static int __meminit __zone_pcp_update(void *data)
+{
+	struct zone *zone = data;
+	int cpu;
+	unsigned long batch = zone_batchsize(zone), flags;
+
+	for_each_possible_cpu(cpu) {
+		struct per_cpu_pageset *pset;
+		struct per_cpu_pages *pcp;
+
+		pset = per_cpu_ptr(zone->pageset, cpu);
+		pcp = &pset->pcp;
+
+		local_irq_save(flags);
+		if (pcp->count > 0)
+			free_pcppages_bulk(zone, pcp->count, pcp);
+		setup_pageset(pset, batch);
+		local_irq_restore(flags);
+	}
+	return 0;
+}
+
+void __meminit zone_pcp_update(struct zone *zone)
+{
+	stop_machine(__zone_pcp_update, zone, NULL);
+}
+#endif
+
 #ifdef CONFIG_MEMORY_HOTREMOVE
+void zone_pcp_reset(struct zone *zone)
+{
+	unsigned long flags;
+
+	/* avoid races with drain_pages()  */
+	local_irq_save(flags);
+	if (zone->pageset != &boot_pageset) {
+		free_percpu(zone->pageset);
+		zone->pageset = &boot_pageset;
+	}
+	local_irq_restore(flags);
+}
+
 /*
  * All pages in the range must be isolated before calling this.
  */