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 <[e-mail]>: (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

···
+What:		/proc/sys/vm/nr_pdflush_threads
+Date:		June 2012
+Contact:	Wanpeng Li <[e-mail]>
+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

···
+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

···
 
  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
 
···
 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.
···
   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
···
 
 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

···
 
 ---------------------------
 
+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 <[e-mail]>
+
+---------------------------
+
 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

···
 	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
···
 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).
···
 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:

Documentation/filesystems/vfs.txt

···
 	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.
···
 	is ok for this address space. Used for memory failure handling.
 	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

···
 - 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
···
 
 ==============================================================
 
-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.
···
 
 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
···
 
 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.
 
 =============================================================
 

arch/ia64/kernel/perfmon.c

···
 	 */
 	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

···
 	 * 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

···
 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

···
 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

···
 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

···
 # 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

···
 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

···
 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

···
 # 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

···
 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

···
 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

···
 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

···
 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

···
 	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

···
 	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),
···
 	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;
···
 	} while (size > 0);
 
 	sigprocmask(SIG_SETMASK, &oldset, NULL);
+	tsk_restore_flags(current, pflags, PF_MEMALLOC);
 
 	return result;
 }
···
 
 	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

···
 #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

···
 
 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

···
 		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

···
 
 	/* 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

···
 				adapter->alloc_rx_buff_failed++;
 				goto no_buffers;
 			}
-
 			bi->skb = skb;
 		}
 		if (!bi->dma) {

drivers/net/usb/cdc-phonet.c

···
 	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

···
 
 	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;
 	}
···
 out_rtc:
 	pm80x_free_irq(chip, info->irq, info);
 out:
-	devm_kfree(&pdev->dev, info);
 	return ret;
 }
 
···
 	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

···
 	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

···
 	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

···
 		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

···
 
 	  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

···
  * @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)
···
  */
 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;
···
 					  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) {
···
 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;
···
 
 	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;
···
 }
 
 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;
···
 	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;
···
  */
 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;
···
 		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;
···
 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;
···
 
 	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;
···
 
 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;
···
 	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:
···
  * 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;
···
 
 	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;
 
···
  * 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;
···
 
 	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

···
 	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,
···
 	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);
 }
···
  */
 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",
···
 	nfs_fscache_wait_on_page_write(nfsi, 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,
···
 	.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
 };
 
 /*
···
 	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;
 
···
 	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

···
 	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

···
 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

···
 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;
···
 	 * 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

···
 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);
 
···
 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

···
 
 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));
···
 
 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;
···
 	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;
 }
···
 /* 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);
···
 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
···
 	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) >
···
 
 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);
···
 
 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))
···
 
 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);
···
 	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);
···
 	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);
···
 	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);
···
 	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);
···
 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
···
 	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;
 
···
 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);
···
 		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;
 }
···
 		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);
···
 	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
···
 		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);
···
  */
 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

···
 		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

···
 #include <linux/timer.h>
 #include <linux/writeback.h>
 #include <linux/atomic.h>
+#include <linux/sysctl.h>
 
 struct page;
 struct device;
···
 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

···
 	__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 */
 };
 
···
 #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

···
 
 /* */
 
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+#ifdef CONFIG_MEMCG
 SUBSYS(mem_cgroup)
 #endif
 
···
 
 #ifdef CONFIG_NETPRIO_CGROUP
 SUBSYS(net_prio)
+#endif
+
+/* */
+
+#ifdef CONFIG_CGROUP_HUGETLB
+SUBSYS(hugetlb)
 #endif
 
 /* */

include/linux/compaction.h

···
 	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
···
 
 static inline bool compaction_deferred(struct zone *zone, int order)
 {
-	return 1;
+	return true;
 }
 
 #endif /* CONFIG_COMPACTION */

include/linux/fs.h

···
 #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)
···
 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);
···
 	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

···
 #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
···
 #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 */
···
 /* 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))
···
  * devices are suspended.
  */
 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

···
 
 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
 

include/linux/hugetlb.h

···
 #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
 
···
 	long count;
 	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);
···
 			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 *);
···
 #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)
 {
 }
···
 #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 */
 
···
 	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];
 };
 
···
 	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
···
 	return 1;
 }
 #define hstate_index_to_shift(index) 0
+#define hstate_index(h) 0
 #endif
 
 #endif /* _LINUX_HUGETLB_H */

include/linux/hugetlb_cgroup.h

···
+/*
+ * Copyright IBM Corporation, 2012
+ * Author Aneesh Kumar K.V <[e-mail]>
+ *
+ * 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

···
 	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
···
 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);
···
 
 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);
 
···
 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
 
···
 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
···
 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,
···
 	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,
···
 	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)
 {
 }
···
 				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)
 {
···
 };
 
 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
···
 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

···
 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);
 
···
 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

···
 	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;
···
 {
 	if (unlikely(PageSwapCache(page)))
 		return page_private(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;
 }
 
···
 			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);
···
 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;
···
 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

···
 		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

···
 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
 };
···
 /* 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 */
···
 	 */
 	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;
···
 	 * 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 {
···
 	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
···
 					     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;
···
 #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);
···
 
 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);
···
 
 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;
···
 
 	/* 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

···
 			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

···
 	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);

include/linux/page-flags.h

···
 
 #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>
···
 	return 0;
 }
 #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)

include/linux/page-isolation.h

···
 #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,
···
  * 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);
 
···
  * 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);
 
···
 /*
  * 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

···
 #ifndef __GENERATING_BOUNDS_H
 #include <generated/bounds.h>
 
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+#ifdef CONFIG_MEMCG
 #include <linux/bit_spinlock.h>
 
 /*
···
 	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)
···
 {
 }
 
-#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);
···
 	return;
 }
 
-#endif /* CONFIG_CGROUP_MEM_RES_CTLR_SWAP */
+#endif /* CONFIG_MEMCG_SWAP */
 
 #endif /* !__GENERATING_BOUNDS_H */
 

include/linux/pagemap.h

···
 	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

···
 	/* 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 */
···
 }
 
 #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,

include/linux/shrinker.h

···
  * '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

···
 #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;
···
  */
 #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.
···
 			     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)
···
 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);
···
 {
 	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);
···
 		unsigned int length)
 {
 	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;
 }
 
 /**

include/linux/sunrpc/xprt.h

···
 	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 */
 
 	/*
···
 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

···
 	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 */
 };
···
 
 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)
···
 	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)
···
 /* 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;
···
 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

···
 		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

···
 #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

···
 
 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

···
 	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 */
···
 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)
···
 	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);
 }
 
···
 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);
 
···
 #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.
···
 #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)
···
 		__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

···
 	{(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

···
 	  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
···
 	  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,
···
 	  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
···
 	  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
···
 	  Memory Controller, which are page-based, and can be swapped. Users of
 	  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"

init/main.c

···
 	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

···
 
 	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

···
 		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;
···
 #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

···
 	__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);
···
 
 	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

···
 		.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

···
 	{ 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

···
 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)
···
 	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

···
 			   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
 
···
 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

···
 	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

···
 					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;
 
···
 		 * 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 */
···
 	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)
 {
···
 	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;
 
 	/*
···
 
 	/* 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

···
 		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;
···
 		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

···
 		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

···
 
 #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];
 
···
 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)
 {
···
 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]++;
 }
···
 	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]--;
···
 				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);
···
 	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]--;
···
 
 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);
···
 
 	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
 		 */
···
 	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.
···
 	/* 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);
 		}
 	}
···
 	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
···
 	 */
 	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;
 }
 
···
 				    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])
···
 	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;
···
 	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);
···
 		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;
 
···
 		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;
 }
···
 	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;
···
 	 * 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;
···
 		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);
···
 		}
 
 		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);
 }
 
 /*
···
 		 * 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);
 
···
 	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);
 
 		/*
···
 
 		/* 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;
 	}
 
 	/*
···
 			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));
···
 		 */
 		if (unlikely(PageHWPoison(page))) {
 			ret = VM_FAULT_HWPOISON |
-			      VM_FAULT_SET_HINDEX(h - hstates);
+				VM_FAULT_SET_HINDEX(hstate_index(h));
 			goto backout_unlocked;
 		}
 	}
···
 			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));
···
 		}
 	}
 	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

···
+/*
+ *
+ * Copyright IBM Corporation, 2012
+ * Author Aneesh Kumar K.V <[e-mail]>
+ *
+ * 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

···
 	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

···
 	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 */
···
 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

···
 	/* 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);
···
 						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;
 	}
···
 		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);
···
 	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

···
 #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;
···
 	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,
 };
 
···
 
 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,
···
 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>
 
···
 }
 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))
···
 					 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,
···
 
 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)
···
 	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)
···
 		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();
···
 /*
  * 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;
···
 	 * to this memcg, return that limit.
 	 */
 	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,
···
 		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.
 	 */
···
 	/*
 	 * 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);
 }
···
 	 * 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;
···
 	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)
···
 	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.
···
 		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;
···
 
 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;
···
 	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);
 }
 
 /*
···
  * 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)
···
 		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
···
 				     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,
···
  * 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;
···
 	if (mem_cgroup_disabled())
 		return NULL;
 
-	if (PageSwapCache(page))
-		return NULL;
+	VM_BUG_ON(PageSwapCache(page));
 
 	if (PageTransHuge(page)) {
 		nr_pages <<= compound_order(page);
···
 	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
···
 		/* 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:
···
 		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;
···
 	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);
 }
 
 /*
···
 	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,
···
 }
 #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.
···
  * 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);
···
 	 * 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
···
 	 * 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*/
···
 		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.
···
 	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
···
 	 */
 	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
···
 		/*
 		 * 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);
···
 		/*
 		 * 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);
···
 }
 
 /*
- * 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;
···
 	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);
···
 		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);
···
 
 		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);
 }
 
 /*
···
 		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);
···
 		}
 		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);
···
 		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
···
 			retval = -EBUSY;
 	} else
 		retval = -EINVAL;
+
+out:
 	cgroup_unlock();
 
 	return retval;
···
 	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;
 }
···
 #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;
···
 	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);
···
 	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);
···
 	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;
···
 	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);
···
 	},
 	{
 		.name = "stat",
-		.read_seq_string = mem_control_stat_show,
+		.read_seq_string = memcg_stat_show,
 	},
 	{
 		.name = "force_empty",
···
 #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),
···
 }
 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)
···
 	.__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

···
  * 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)
···
 	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)
···
 	}
 
 	/* 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

···
 			 * 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);
 	}
···
 			free_page((unsigned long)buf);
 		}
 	}
-	up_read(&current->mm->mmap_sem);
+	up_read(&mm->mmap_sem);
 }
 
 #ifdef CONFIG_PROVE_LOCKING

mm/memory_hotplug.c

···
 
 	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();
 
···
 	 * 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;
···
 	totalram_pages -= offlined_pages;
 
 	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);

mm/migrate.c

···
 #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>
···
 {
 	int rc = -EAGAIN;
 	int remap_swapcache = 1;
-	int charge = 0;
 	struct mem_cgroup *mem;
 	struct anon_vma *anon_vma = NULL;
 
···
 	}
 
 	/* 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)) {
 		/*
···
 		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:
···
 
 	if (anon_vma)
 		put_anon_vma(anon_vma);
+
+	if (!rc)
+		hugetlb_cgroup_migrate(hpage, new_hpage);
+
 	unlock_page(hpage);
-
 out:
-	if (rc != -EAGAIN) {
-		list_del(&hpage->lru);
-		put_page(hpage);
-	}
-
 	put_page(new_hpage);
-
 	if (result) {
 		if (rc)
 			*result = rc;
···
 	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;
+	int pass, rc;
 
-	for (pass = 0; pass < 10 && retry; pass++) {
-		retry = 0;
-
-		list_for_each_entry_safe(page, page2, from, lru) {
+	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

···
 	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)
···
 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))
···
 		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);
···
 
 		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

···
 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))) {
···
 		 * 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);
 
···
 {
 	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
···
 		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

···
 	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

···
 	 * 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) {
···
 				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

···
 }
 #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)
+		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 (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)
-			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;
···
  * 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;
···
 			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,
···
 }
 
 #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;
···
 	 */
 	if (p->flags & PF_EXITING) {
 		set_tsk_thread_flag(p, TIF_MEMDIE);
+		put_task_struct(p);
 		return;
 	}
 
···
 	 * 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;
···
 			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;
···
 			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;
···
 		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);
 
···
 	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;
 
···
 	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) {
···
 		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);
 }
 
 /*
···
 		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

···
 #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>
···
 
 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))
···
 	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;
···
 		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
···
 }
 __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);
 }
···
 
 #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 */
···
 {
 	/* 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;
···
 	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 */
···
 	}
 	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)
···
 	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);
 }
···
 
 		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;
···
 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
···
 		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 *
···
 
 	/* 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 */
···
 got_pg:
 	if (kmemcheck_enabled)
 		kmemcheck_pagealloc_alloc(page, order, gfp_mask);
-	return page;
 
+	return page;
 }
 
 /*
···
 		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);
 
···
 			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);
 		}
 	}
···
 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);
 
···
  * 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();
 
···
 		/* 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();
···
 	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;
···
 		pcp->batch = PAGE_SHIFT * 8;
 }
 
-static void setup_zone_pageset(struct zone *zone)
+static void __meminit setup_zone_pageset(struct zone *zone)
 {
 	int cpu;
 
···
 	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)
 {
 	/*
···
 					 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)
···
 #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;
 
···
  * 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)
 {
 }
 
···
  *   - 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)
···
 	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++) {
···
 
 		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)
···
 
 		zone_pcp_init(zone);
 		lruvec_init(&zone->lruvec, zone);
-		zap_zone_vm_stats(zone);
-		zone->flags = 0;
 		if (!size)
 			continue;
 
···
 		unsigned long node_start_pfn, unsigned long *zholes_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;
···
 }
 
 /* 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;
···
 }
 
 /*
- * 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++) {
···
 			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++;
 		/*
···
 		 * page at boot.
 		 */
 		if (found > count)
-			return false;
+			return true;
 	}
-	return true;
+	return false;
 }
 
 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
···
 }
 #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.
  */

mm/page_cgroup.c

···
 #endif
 
 
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+#ifdef CONFIG_MEMCG_SWAP
 
 static DEFINE_MUTEX(swap_cgroup_mutex);
 struct swap_cgroup_ctrl {

mm/page_io.c

···
 #include <linux/swap.h>
 #include <linux/bio.h>
 #include <linux/swapops.h>
+#include <linux/buffer_head.h>
 #include <linux/writeback.h>
 #include <linux/frontswap.h>
 #include <asm/pgtable.h>
···
 	bio_put(bio);
 }
 
+int generic_swapfile_activate(struct swap_info_struct *sis,
+				struct file *swap_file,
+				sector_t *span)
+{
+	struct address_space *mapping = swap_file->f_mapping;
+	struct inode *inode = mapping->host;
+	unsigned blocks_per_page;
+	unsigned long page_no;
+	unsigned blkbits;
+	sector_t probe_block;
+	sector_t last_block;
+	sector_t lowest_block = -1;
+	sector_t highest_block = 0;
+	int nr_extents = 0;
+	int ret;
+
+	blkbits = inode->i_blkbits;
+	blocks_per_page = PAGE_SIZE >> blkbits;
+
+	/*
+	 * Map all the blocks into the extent list.  This code doesn't try
+	 * to be very smart.
+	 */
+	probe_block = 0;
+	page_no = 0;
+	last_block = i_size_read(inode) >> blkbits;
+	while ((probe_block + blocks_per_page) <= last_block &&
+			page_no < sis->max) {
+		unsigned block_in_page;
+		sector_t first_block;
+
+		first_block = bmap(inode, probe_block);
+		if (first_block == 0)
+			goto bad_bmap;
+
+		/*
+		 * It must be PAGE_SIZE aligned on-disk
+		 */
+		if (first_block & (blocks_per_page - 1)) {
+			probe_block++;
+			goto reprobe;
+		}
+
+		for (block_in_page = 1; block_in_page < blocks_per_page;
+					block_in_page++) {
+			sector_t block;
+
+			block = bmap(inode, probe_block + block_in_page);
+			if (block == 0)
+				goto bad_bmap;
+			if (block != first_block + block_in_page) {
+				/* Discontiguity */
+				probe_block++;
+				goto reprobe;
+			}
+		}
+
+		first_block >>= (PAGE_SHIFT - blkbits);
+		if (page_no) {	/* exclude the header page */
+			if (first_block < lowest_block)
+				lowest_block = first_block;
+			if (first_block > highest_block)
+				highest_block = first_block;
+		}
+
+		/*
+		 * We found a PAGE_SIZE-length, PAGE_SIZE-aligned run of blocks
+		 */
+		ret = add_swap_extent(sis, page_no, 1, first_block);
+		if (ret < 0)
+			goto out;
+		nr_extents += ret;
+		page_no++;
+		probe_block += blocks_per_page;
+reprobe:
+		continue;
+	}
+	ret = nr_extents;
+	*span = 1 + highest_block - lowest_block;
+	if (page_no == 0)
+		page_no = 1;	/* force Empty message */
+	sis->max = page_no;
+	sis->pages = page_no - 1;
+	sis->highest_bit = page_no - 1;
+out:
+	return ret;
+bad_bmap:
+	printk(KERN_ERR "swapon: swapfile has holes\n");
+	ret = -EINVAL;
+	goto out;
+}
+
 /*
  * We may have stale swap cache pages in memory: notice
  * them here and get rid of the unnecessary final write.
···
 {
 	struct bio *bio;
 	int ret = 0, rw = WRITE;
+	struct swap_info_struct *sis = page_swap_info(page);
 
 	if (try_to_free_swap(page)) {
 		unlock_page(page);
···
 		end_page_writeback(page);
 		goto out;
 	}
+
+	if (sis->flags & SWP_FILE) {
+		struct kiocb kiocb;
+		struct file *swap_file = sis->swap_file;
+		struct address_space *mapping = swap_file->f_mapping;
+		struct iovec iov = {
+			.iov_base = kmap(page),
+			.iov_len  = PAGE_SIZE,
+		};
+
+		init_sync_kiocb(&kiocb, swap_file);
+		kiocb.ki_pos = page_file_offset(page);
+		kiocb.ki_left = PAGE_SIZE;
+		kiocb.ki_nbytes = PAGE_SIZE;
+
+		unlock_page(page);
+		ret = mapping->a_ops->direct_IO(KERNEL_WRITE,
+						&kiocb, &iov,
+						kiocb.ki_pos, 1);
+		kunmap(page);
+		if (ret == PAGE_SIZE) {
+			count_vm_event(PSWPOUT);
+			ret = 0;
+		}
+		return ret;
+	}
+
 	bio = get_swap_bio(GFP_NOIO, page, end_swap_bio_write);
 	if (bio == NULL) {
 		set_page_dirty(page);
···
 {
 	struct bio *bio;
 	int ret = 0;
+	struct swap_info_struct *sis = page_swap_info(page);
 
 	VM_BUG_ON(!PageLocked(page));
 	VM_BUG_ON(PageUptodate(page));
···
 		unlock_page(page);
 		goto out;
 	}
+
+	if (sis->flags & SWP_FILE) {
+		struct file *swap_file = sis->swap_file;
+		struct address_space *mapping = swap_file->f_mapping;
+
+		ret = mapping->a_ops->readpage(swap_file, page);
+		if (!ret)
+			count_vm_event(PSWPIN);
+		return ret;
+	}
+
 	bio = get_swap_bio(GFP_KERNEL, page, end_swap_bio_read);
 	if (bio == NULL) {
 		unlock_page(page);
···
 	submit_bio(READ, bio);
 out:
 	return ret;
+}
+
+int swap_set_page_dirty(struct page *page)
+{
+	struct swap_info_struct *sis = page_swap_info(page);
+
+	if (sis->flags & SWP_FILE) {
+		struct address_space *mapping = sis->swap_file->f_mapping;
+		return mapping->a_ops->set_page_dirty(page);
+	} else {
+		return __set_page_dirty_no_writeback(page);
+	}
 }

mm/page_isolation.c

···
 #include <linux/mm.h>
 #include <linux/page-isolation.h>
 #include <linux/pageblock-flags.h>
+#include <linux/memory.h>
 #include "internal.h"
+
+/* called while holding zone->lock */
+static void set_pageblock_isolate(struct page *page)
+{
+	if (get_pageblock_migratetype(page) == MIGRATE_ISOLATE)
+		return;
+
+	set_pageblock_migratetype(page, MIGRATE_ISOLATE);
+	page_zone(page)->nr_pageblock_isolate++;
+}
+
+/* called while holding zone->lock */
+static void restore_pageblock_isolate(struct page *page, int migratetype)
+{
+	struct zone *zone = page_zone(page);
+	if (WARN_ON(get_pageblock_migratetype(page) != MIGRATE_ISOLATE))
+		return;
+
+	BUG_ON(zone->nr_pageblock_isolate <= 0);
+	set_pageblock_migratetype(page, migratetype);
+	zone->nr_pageblock_isolate--;
+}
+
+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 (!has_unmovable_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_isolate(page);
+		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;
+	move_freepages_block(zone, page, migratetype);
+	restore_pageblock_isolate(page, migratetype);
+out:
+	spin_unlock_irqrestore(&zone->lock, flags);
+}
 
 static inline struct page *
 __first_valid_page(unsigned long pfn, unsigned long nr_pages)

mm/shmem.c

···
 
 	/* Create a pseudo vma that just contains the policy */
 	pvma.vm_start = 0;
-	pvma.vm_pgoff = index;
+	/* Bias interleave by inode number to distribute better across nodes */
+	pvma.vm_pgoff = index + info->vfs_inode.i_ino;
 	pvma.vm_ops = NULL;
 	pvma.vm_policy = spol;
 	return swapin_readahead(swap, gfp, &pvma, 0);
···
 
 	/* Create a pseudo vma that just contains the policy */
 	pvma.vm_start = 0;
-	pvma.vm_pgoff = index;
+	/* Bias interleave by inode number to distribute better across nodes */
+	pvma.vm_pgoff = index + info->vfs_inode.i_ino;
 	pvma.vm_ops = NULL;
 	pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, index);
 

mm/slab.c

···
 #include	<linux/memory.h>
 #include	<linux/prefetch.h>
 
+#include	<net/sock.h>
+
 #include	<asm/cacheflush.h>
 #include	<asm/tlbflush.h>
 #include	<asm/page.h>
 
 #include <trace/events/kmem.h>
+
+#include	"internal.h"
 
 /*
  * DEBUG	- 1 for kmem_cache_create() to honour; SLAB_RED_ZONE & SLAB_POISON.
···
 #ifndef ARCH_KMALLOC_FLAGS
 #define ARCH_KMALLOC_FLAGS SLAB_HWCACHE_ALIGN
 #endif
+
+/*
+ * true if a page was allocated from pfmemalloc reserves for network-based
+ * swap
+ */
+static bool pfmemalloc_active __read_mostly;
 
 /* Legal flag mask for kmem_cache_create(). */
 #if DEBUG
···
 			 * Must have this definition in here for the proper
 			 * alignment of array_cache. Also simplifies accessing
 			 * the entries.
+			 *
+			 * Entries should not be directly dereferenced as
+			 * entries belonging to slabs marked pfmemalloc will
+			 * have the lower bits set SLAB_OBJ_PFMEMALLOC
 			 */
 };
+
+#define SLAB_OBJ_PFMEMALLOC	1
+static inline bool is_obj_pfmemalloc(void *objp)
+{
+	return (unsigned long)objp & SLAB_OBJ_PFMEMALLOC;
+}
+
+static inline void set_obj_pfmemalloc(void **objp)
+{
+	*objp = (void *)((unsigned long)*objp | SLAB_OBJ_PFMEMALLOC);
+	return;
+}
+
+static inline void clear_obj_pfmemalloc(void **objp)
+{
+	*objp = (void *)((unsigned long)*objp & ~SLAB_OBJ_PFMEMALLOC);
+}
 
 /*
  * bootstrap: The caches do not work without cpuarrays anymore, but the
···
 	return nc;
 }
 
+static inline bool is_slab_pfmemalloc(struct slab *slabp)
+{
+	struct page *page = virt_to_page(slabp->s_mem);
+
+	return PageSlabPfmemalloc(page);
+}
+
+/* Clears pfmemalloc_active if no slabs have pfmalloc set */
+static void recheck_pfmemalloc_active(struct kmem_cache *cachep,
+						struct array_cache *ac)
+{
+	struct kmem_list3 *l3 = cachep->nodelists[numa_mem_id()];
+	struct slab *slabp;
+	unsigned long flags;
+
+	if (!pfmemalloc_active)
+		return;
+
+	spin_lock_irqsave(&l3->list_lock, flags);
+	list_for_each_entry(slabp, &l3->slabs_full, list)
+		if (is_slab_pfmemalloc(slabp))
+			goto out;
+
+	list_for_each_entry(slabp, &l3->slabs_partial, list)
+		if (is_slab_pfmemalloc(slabp))
+			goto out;
+
+	list_for_each_entry(slabp, &l3->slabs_free, list)
+		if (is_slab_pfmemalloc(slabp))
+			goto out;
+
+	pfmemalloc_active = false;
+out:
+	spin_unlock_irqrestore(&l3->list_lock, flags);
+}
+
+static void *__ac_get_obj(struct kmem_cache *cachep, struct array_cache *ac,
+						gfp_t flags, bool force_refill)
+{
+	int i;
+	void *objp = ac->entry[--ac->avail];
+
+	/* Ensure the caller is allowed to use objects from PFMEMALLOC slab */
+	if (unlikely(is_obj_pfmemalloc(objp))) {
+		struct kmem_list3 *l3;
+
+		if (gfp_pfmemalloc_allowed(flags)) {
+			clear_obj_pfmemalloc(&objp);
+			return objp;
+		}
+
+		/* The caller cannot use PFMEMALLOC objects, find another one */
+		for (i = 1; i < ac->avail; i++) {
+			/* If a !PFMEMALLOC object is found, swap them */
+			if (!is_obj_pfmemalloc(ac->entry[i])) {
+				objp = ac->entry[i];
+				ac->entry[i] = ac->entry[ac->avail];
+				ac->entry[ac->avail] = objp;
+				return objp;
+			}
+		}
+
+		/*
+		 * If there are empty slabs on the slabs_free list and we are
+		 * being forced to refill the cache, mark this one !pfmemalloc.
+		 */
+		l3 = cachep->nodelists[numa_mem_id()];
+		if (!list_empty(&l3->slabs_free) && force_refill) {
+			struct slab *slabp = virt_to_slab(objp);
+			ClearPageSlabPfmemalloc(virt_to_page(slabp->s_mem));
+			clear_obj_pfmemalloc(&objp);
+			recheck_pfmemalloc_active(cachep, ac);
+			return objp;
+		}
+
+		/* No !PFMEMALLOC objects available */
+		ac->avail++;
+		objp = NULL;
+	}
+
+	return objp;
+}
+
+static inline void *ac_get_obj(struct kmem_cache *cachep,
+			struct array_cache *ac, gfp_t flags, bool force_refill)
+{
+	void *objp;
+
+	if (unlikely(sk_memalloc_socks()))
+		objp = __ac_get_obj(cachep, ac, flags, force_refill);
+	else
+		objp = ac->entry[--ac->avail];
+
+	return objp;
+}
+
+static void *__ac_put_obj(struct kmem_cache *cachep, struct array_cache *ac,
+								void *objp)
+{
+	if (unlikely(pfmemalloc_active)) {
+		/* Some pfmemalloc slabs exist, check if this is one */
+		struct page *page = virt_to_page(objp);
+		if (PageSlabPfmemalloc(page))
+			set_obj_pfmemalloc(&objp);
+	}
+
+	return objp;
+}
+
+static inline void ac_put_obj(struct kmem_cache *cachep, struct array_cache *ac,
+								void *objp)
+{
+	if (unlikely(sk_memalloc_socks()))
+		objp = __ac_put_obj(cachep, ac, objp);
+
+	ac->entry[ac->avail++] = objp;
+}
+
 /*
  * Transfer objects in one arraycache to another.
  * Locking must be handled by the caller.
···
 			STATS_INC_ACOVERFLOW(cachep);
 			__drain_alien_cache(cachep, alien, nodeid);
 		}
-		alien->entry[alien->avail++] = objp;
+		ac_put_obj(cachep, alien, objp);
 		spin_unlock(&alien->lock);
 	} else {
 		spin_lock(&(cachep->nodelists[nodeid])->list_lock);
···
 		return NULL;
 	}
 
+	/* Record if ALLOC_NO_WATERMARKS was set when allocating the slab */
+	if (unlikely(page->pfmemalloc))
+		pfmemalloc_active = true;
+
 	nr_pages = (1 << cachep->gfporder);
 	if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
 		add_zone_page_state(page_zone(page),
···
 	else
 		add_zone_page_state(page_zone(page),
 			NR_SLAB_UNRECLAIMABLE, nr_pages);
-	for (i = 0; i < nr_pages; i++)
+	for (i = 0; i < nr_pages; i++) {
 		__SetPageSlab(page + i);
+
+		if (page->pfmemalloc)
+			SetPageSlabPfmemalloc(page + i);
+	}
 
 	if (kmemcheck_enabled && !(cachep->flags & SLAB_NOTRACK)) {
 		kmemcheck_alloc_shadow(page, cachep->gfporder, flags, nodeid);
···
 				NR_SLAB_UNRECLAIMABLE, nr_freed);
 	while (i--) {
 		BUG_ON(!PageSlab(page));
+		__ClearPageSlabPfmemalloc(page);
 		__ClearPageSlab(page);
 		page++;
 	}
···
 #define check_slabp(x,y) do { } while(0)
 #endif
 
-static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags)
+static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags,
+							bool force_refill)
 {
 	int batchcount;
 	struct kmem_list3 *l3;
 	struct array_cache *ac;
 	int node;
 
-retry:
 	check_irq_off();
 	node = numa_mem_id();
+	if (unlikely(force_refill))
+		goto force_grow;
+retry:
 	ac = cpu_cache_get(cachep);
 	batchcount = ac->batchcount;
 	if (!ac->touched && batchcount > BATCHREFILL_LIMIT) {
···
 			STATS_INC_ACTIVE(cachep);
 			STATS_SET_HIGH(cachep);
 
-			ac->entry[ac->avail++] = slab_get_obj(cachep, slabp,
-							    node);
+			ac_put_obj(cachep, ac, slab_get_obj(cachep, slabp,
+									node));
 		}
 		check_slabp(cachep, slabp);
 
···
 
 	if (unlikely(!ac->avail)) {
 		int x;
+force_grow:
 		x = cache_grow(cachep, flags | GFP_THISNODE, node, NULL);
 
 		/* cache_grow can reenable interrupts, then ac could change. */
 		ac = cpu_cache_get(cachep);
-		if (!x && ac->avail == 0)	/* no objects in sight? abort */
+
+		/* no objects in sight? abort */
+		if (!x && (ac->avail == 0 || force_refill))
 			return NULL;
 
 		if (!ac->avail)		/* objects refilled by interrupt? */
 			goto retry;
 	}
 	ac->touched = 1;
-	return ac->entry[--ac->avail];
+
+	return ac_get_obj(cachep, ac, flags, force_refill);
 }
 
 static inline void cache_alloc_debugcheck_before(struct kmem_cache *cachep,
···
 {
 	void *objp;
 	struct array_cache *ac;
+	bool force_refill = false;
 
 	check_irq_off();
 
 	ac = cpu_cache_get(cachep);
 	if (likely(ac->avail)) {
-		STATS_INC_ALLOCHIT(cachep);
 		ac->touched = 1;
-		objp = ac->entry[--ac->avail];
-	} else {
-		STATS_INC_ALLOCMISS(cachep);
-		objp = cache_alloc_refill(cachep, flags);
+		objp = ac_get_obj(cachep, ac, flags, false);
+
 		/*
-		 * the 'ac' may be updated by cache_alloc_refill(),
-		 * and kmemleak_erase() requires its correct value.
+		 * Allow for the possibility all avail objects are not allowed
+		 * by the current flags
 		 */
-		ac = cpu_cache_get(cachep);
+		if (objp) {
+			STATS_INC_ALLOCHIT(cachep);
+			goto out;
+		}
+		force_refill = true;
 	}
+
+	STATS_INC_ALLOCMISS(cachep);
+	objp = cache_alloc_refill(cachep, flags, force_refill);
+	/*
+	 * the 'ac' may be updated by cache_alloc_refill(),
+	 * and kmemleak_erase() requires its correct value.
+	 */
+	ac = cpu_cache_get(cachep);
+
+out:
 	/*
 	 * To avoid a false negative, if an object that is in one of the
 	 * per-CPU caches is leaked, we need to make sure kmemleak doesn't
···
 	struct kmem_list3 *l3;
 
 	for (i = 0; i < nr_objects; i++) {
-		void *objp = objpp[i];
+		void *objp;
 		struct slab *slabp;
+
+		clear_obj_pfmemalloc(&objpp[i]);
+		objp = objpp[i];
 
 		slabp = virt_to_slab(objp);
 		l3 = cachep->nodelists[node];
···
 		cache_flusharray(cachep, ac);
 	}
 
-	ac->entry[ac->avail++] = objp;
+	ac_put_obj(cachep, ac, objp);
 }
 
 /**

mm/slub.c

···
 
 #include <trace/events/kmem.h>
 
+#include "internal.h"
+
 /*
  * Lock order:
  *   1. slab_mutex (Global Mutex)
···
 	inc_slabs_node(s, page_to_nid(page), page->objects);
 	page->slab = s;
 	__SetPageSlab(page);
+	if (page->pfmemalloc)
+		SetPageSlabPfmemalloc(page);
 
 	start = page_address(page);
 
···
 		NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE,
 		-pages);
 
+	__ClearPageSlabPfmemalloc(page);
 	__ClearPageSlab(page);
 	reset_page_mapcount(page);
 	if (current->reclaim_state)
···
 	return freelist;
 }
 
+static inline bool pfmemalloc_match(struct page *page, gfp_t gfpflags)
+{
+	if (unlikely(PageSlabPfmemalloc(page)))
+		return gfp_pfmemalloc_allowed(gfpflags);
+
+	return true;
+}
+
 /*
  * Check the page->freelist of a page and either transfer the freelist to the per cpu freelist
  * or deactivate the page.
···
 		goto new_slab;
 	}
 
+	/*
+	 * By rights, we should be searching for a slab page that was
+	 * PFMEMALLOC but right now, we are losing the pfmemalloc
+	 * information when the page leaves the per-cpu allocator
+	 */
+	if (unlikely(!pfmemalloc_match(page, gfpflags))) {
+		deactivate_slab(s, page, c->freelist);
+		c->page = NULL;
+		c->freelist = NULL;
+		goto new_slab;
+	}
+
 	/* must check again c->freelist in case of cpu migration or IRQ */
 	freelist = c->freelist;
 	if (freelist)
···
 	}
 
 	page = c->page;
-	if (likely(!kmem_cache_debug(s)))
+	if (likely(!kmem_cache_debug(s) && pfmemalloc_match(page, gfpflags)))
 		goto load_freelist;
 
 	/* Only entered in the debug case */
-	if (!alloc_debug_processing(s, page, freelist, addr))
+	if (kmem_cache_debug(s) && !alloc_debug_processing(s, page, freelist, addr))
 		goto new_slab;	/* Slab failed checks. Next slab needed */
 
 	deactivate_slab(s, page, get_freepointer(s, freelist));
···
 	object = c->freelist;
 	page = c->page;
 	if (unlikely(!object || !node_match(page, node)))
-
 		object = __slab_alloc(s, gfpflags, node, addr, c);
 
 	else {

mm/sparse.c

···
 
 	if (slab_is_available()) {
 		if (node_state(nid, N_HIGH_MEMORY))
-			section = kmalloc_node(array_size, GFP_KERNEL, nid);
+			section = kzalloc_node(array_size, GFP_KERNEL, nid);
 		else
-			section = kmalloc(array_size, GFP_KERNEL);
-	} else
+			section = kzalloc(array_size, GFP_KERNEL);
+	} else {
 		section = alloc_bootmem_node(NODE_DATA(nid), array_size);
-
-	if (section)
-		memset(section, 0, array_size);
+	}
 
 	return section;
 }
 
 static int __meminit sparse_index_init(unsigned long section_nr, int nid)
 {
-	static DEFINE_SPINLOCK(index_init_lock);
 	unsigned long root = SECTION_NR_TO_ROOT(section_nr);
 	struct mem_section *section;
 	int ret = 0;
···
 	section = sparse_index_alloc(nid);
 	if (!section)
 		return -ENOMEM;
-	/*
-	 * This lock keeps two different sections from
-	 * reallocating for the same index
-	 */
-	spin_lock(&index_init_lock);
-
-	if (mem_section[root]) {
-		ret = -EEXIST;
-		goto out;
-	}
 
 	mem_section[root] = section;
-out:
-	spin_unlock(&index_init_lock);
+
 	return ret;
 }
 #else /* !SPARSEMEM_EXTREME */
···
 		if ((ms >= root) && (ms < (root + SECTIONS_PER_ROOT)))
 		     break;
 	}
+
+	VM_BUG_ON(root_nr == NR_SECTION_ROOTS);
 
 	return (root_nr * SECTIONS_PER_ROOT) + (ms - root);
 }
···
 	int size2;
 	struct page **map_map;
 #endif
+
+	/* Setup pageblock_order for HUGETLB_PAGE_SIZE_VARIABLE */
+	set_pageblock_order();
 
 	/*
 	 * map is using big page (aka 2M in x86 64 bit)

mm/swap.c

···
 }
 EXPORT_SYMBOL(put_pages_list);
 
+/*
+ * get_kernel_pages() - pin kernel pages in memory
+ * @kiov:	An array of struct kvec structures
+ * @nr_segs:	number of segments to pin
+ * @write:	pinning for read/write, currently ignored
+ * @pages:	array that receives pointers to the pages pinned.
+ *		Should be at least nr_segs long.
+ *
+ * Returns number of pages pinned. This may be fewer than the number
+ * requested. If nr_pages is 0 or negative, returns 0. If no pages
+ * were pinned, returns -errno. Each page returned must be released
+ * with a put_page() call when it is finished with.
+ */
+int get_kernel_pages(const struct kvec *kiov, int nr_segs, int write,
+		struct page **pages)
+{
+	int seg;
+
+	for (seg = 0; seg < nr_segs; seg++) {
+		if (WARN_ON(kiov[seg].iov_len != PAGE_SIZE))
+			return seg;
+
+		pages[seg] = kmap_to_page(kiov[seg].iov_base);
+		page_cache_get(pages[seg]);
+	}
+
+	return seg;
+}
+EXPORT_SYMBOL_GPL(get_kernel_pages);
+
+/*
+ * get_kernel_page() - pin a kernel page in memory
+ * @start:	starting kernel address
+ * @write:	pinning for read/write, currently ignored
+ * @pages:	array that receives pointer to the page pinned.
+ *		Must be at least nr_segs long.
+ *
+ * Returns 1 if page is pinned. If the page was not pinned, returns
+ * -errno. The page returned must be released with a put_page() call
+ * when it is finished with.
+ */
+int get_kernel_page(unsigned long start, int write, struct page **pages)
+{
+	const struct kvec kiov = {
+		.iov_base = (void *)start,
+		.iov_len = PAGE_SIZE
+	};
+
+	return get_kernel_pages(&kiov, 1, write, pages);
+}
+EXPORT_SYMBOL_GPL(get_kernel_page);
+
 static void pagevec_lru_move_fn(struct pagevec *pvec,
 	void (*move_fn)(struct page *page, struct lruvec *lruvec, void *arg),
 	void *arg)

mm/swap_state.c

···
 #include <linux/init.h>
 #include <linux/pagemap.h>
 #include <linux/backing-dev.h>
+#include <linux/blkdev.h>
 #include <linux/pagevec.h>
 #include <linux/migrate.h>
 #include <linux/page_cgroup.h>
···
  */
 static const struct address_space_operations swap_aops = {
 	.writepage	= swap_writepage,
-	.set_page_dirty	= __set_page_dirty_no_writeback,
+	.set_page_dirty	= swap_set_page_dirty,
 	.migratepage	= migrate_page,
 };
 
···
 	unsigned long offset = swp_offset(entry);
 	unsigned long start_offset, end_offset;
 	unsigned long mask = (1UL << page_cluster) - 1;
+	struct blk_plug plug;
 
 	/* Read a page_cluster sized and aligned cluster around offset. */
 	start_offset = offset & ~mask;
···
 	if (!start_offset)	/* First page is swap header. */
 		start_offset++;
 
+	blk_start_plug(&plug);
 	for (offset = start_offset; offset <= end_offset ; offset++) {
 		/* Ok, do the async read-ahead now */
 		page = read_swap_cache_async(swp_entry(swp_type(entry), offset),
···
 			continue;
 		page_cache_release(page);
 	}
+	blk_finish_plug(&plug);
+
 	lru_add_drain();	/* Push any new pages onto the LRU now */
 	return read_swap_cache_async(entry, gfp_mask, vma, addr);
 }

mm/swapfile.c

···
 #include <linux/oom.h>
 #include <linux/frontswap.h>
 #include <linux/swapfile.h>
+#include <linux/export.h>
 
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
···
 
 	/* free if no reference */
 	if (!usage) {
-		struct gendisk *disk = p->bdev->bd_disk;
 		if (offset < p->lowest_bit)
 			p->lowest_bit = offset;
 		if (offset > p->highest_bit)
···
 		nr_swap_pages++;
 		p->inuse_pages--;
 		frontswap_invalidate_page(p->type, offset);
-		if ((p->flags & SWP_BLKDEV) &&
-				disk->fops->swap_slot_free_notify)
-			disk->fops->swap_slot_free_notify(p->bdev, offset);
+		if (p->flags & SWP_BLKDEV) {
+			struct gendisk *disk = p->bdev->bd_disk;
+			if (disk->fops->swap_slot_free_notify)
+				disk->fops->swap_slot_free_notify(p->bdev,
+								  offset);
+		}
 	}
 
 	return usage;
···
 
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	if (unlikely(!pte_same(*pte, swp_entry_to_pte(entry)))) {
-		if (ret > 0)
-			mem_cgroup_cancel_charge_swapin(memcg);
+		mem_cgroup_cancel_charge_swapin(memcg);
 		ret = 0;
 		goto out;
 	}
···
 		list_del(&se->list);
 		kfree(se);
 	}
+
+	if (sis->flags & SWP_FILE) {
+		struct file *swap_file = sis->swap_file;
+		struct address_space *mapping = swap_file->f_mapping;
+
+		sis->flags &= ~SWP_FILE;
+		mapping->a_ops->swap_deactivate(swap_file);
+	}
 }
 
 /*
···
  *
  * This function rather assumes that it is called in ascending page order.
  */
-static int
+int
 add_swap_extent(struct swap_info_struct *sis, unsigned long start_page,
 		unsigned long nr_pages, sector_t start_block)
 {
···
  */
 static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span)
 {
-	struct inode *inode;
-	unsigned blocks_per_page;
-	unsigned long page_no;
-	unsigned blkbits;
-	sector_t probe_block;
-	sector_t last_block;
-	sector_t lowest_block = -1;
-	sector_t highest_block = 0;
-	int nr_extents = 0;
+	struct file *swap_file = sis->swap_file;
+	struct address_space *mapping = swap_file->f_mapping;
+	struct inode *inode = mapping->host;
 	int ret;
 
-	inode = sis->swap_file->f_mapping->host;
 	if (S_ISBLK(inode->i_mode)) {
 		ret = add_swap_extent(sis, 0, sis->max, 0);
 		*span = sis->pages;
-		goto out;
+		return ret;
 	}
 
-	blkbits = inode->i_blkbits;
-	blocks_per_page = PAGE_SIZE >> blkbits;
-
-	/*
-	 * Map all the blocks into the extent list.  This code doesn't try
-	 * to be very smart.
-	 */
-	probe_block = 0;
-	page_no = 0;
-	last_block = i_size_read(inode) >> blkbits;
-	while ((probe_block + blocks_per_page) <= last_block &&
-			page_no < sis->max) {
-		unsigned block_in_page;
-		sector_t first_block;
-
-		first_block = bmap(inode, probe_block);
-		if (first_block == 0)
-			goto bad_bmap;
-
-		/*
-		 * It must be PAGE_SIZE aligned on-disk
-		 */
-		if (first_block & (blocks_per_page - 1)) {
-			probe_block++;
-			goto reprobe;
+	if (mapping->a_ops->swap_activate) {
+		ret = mapping->a_ops->swap_activate(sis, swap_file, span);
+		if (!ret) {
+			sis->flags |= SWP_FILE;
+			ret = add_swap_extent(sis, 0, sis->max, 0);
+			*span = sis->pages;
 		}
-
-		for (block_in_page = 1; block_in_page < blocks_per_page;
-					block_in_page++) {
-			sector_t block;
-
-			block = bmap(inode, probe_block + block_in_page);
-			if (block == 0)
-				goto bad_bmap;
-			if (block != first_block + block_in_page) {
-				/* Discontiguity */
-				probe_block++;
-				goto reprobe;
-			}
-		}
-
-		first_block >>= (PAGE_SHIFT - blkbits);
-		if (page_no) {	/* exclude the header page */
-			if (first_block < lowest_block)
-				lowest_block = first_block;
-			if (first_block > highest_block)
-				highest_block = first_block;
-		}
-
-		/*
-		 * We found a PAGE_SIZE-length, PAGE_SIZE-aligned run of blocks
-		 */
-		ret = add_swap_extent(sis, page_no, 1, first_block);
-		if (ret < 0)
-			goto out;
-		nr_extents += ret;
-		page_no++;
-		probe_block += blocks_per_page;
-reprobe:
-		continue;
+		return ret;
 	}
-	ret = nr_extents;
-	*span = 1 + highest_block - lowest_block;
-	if (page_no == 0)
-		page_no = 1;	/* force Empty message */
-	sis->max = page_no;
-	sis->pages = page_no - 1;
-	sis->highest_bit = page_no - 1;
-out:
-	return ret;
-bad_bmap:
-	printk(KERN_ERR "swapon: swapfile has holes\n");
-	ret = -EINVAL;
-	goto out;
+
+	return generic_swapfile_activate(sis, swap_file, span);
 }
 
 static void enable_swap_info(struct swap_info_struct *p, int prio,
···
 {
 	return __swap_duplicate(entry, SWAP_HAS_CACHE);
 }
+
+struct swap_info_struct *page_swap_info(struct page *page)
+{
+	swp_entry_t swap = { .val = page_private(page) };
+	BUG_ON(!PageSwapCache(page));
+	return swap_info[swp_type(swap)];
+}
+
+/*
+ * out-of-line __page_file_ methods to avoid include hell.
+ */
+struct address_space *__page_file_mapping(struct page *page)
+{
+	VM_BUG_ON(!PageSwapCache(page));
+	return page_swap_info(page)->swap_file->f_mapping;
+}
+EXPORT_SYMBOL_GPL(__page_file_mapping);
+
+pgoff_t __page_file_index(struct page *page)
+{
+	swp_entry_t swap = { .val = page_private(page) };
+	VM_BUG_ON(!PageSwapCache(page));
+	return swp_offset(swap);
+}
+EXPORT_SYMBOL_GPL(__page_file_index);
 
 /*
  * add_swap_count_continuation - called when a swap count is duplicated

mm/vmalloc.c

···
 		if (addr + size - 1 < addr)
 			goto overflow;
 
-		n = rb_next(&first->rb_node);
-		if (n)
-			first = rb_entry(n, struct vmap_area, rb_node);
-		else
+		if (list_is_last(&first->list, &vmap_area_list))
 			goto found;
+
+		first = list_entry(first->list.next,
+				struct vmap_area, list);
 	}
 
 found:
···
 
 	BUG_ON(size & ~PAGE_MASK);
 	BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC);
+	if (WARN_ON(size == 0)) {
+		/*
+		 * Allocating 0 bytes isn't what caller wants since
+		 * get_order(0) returns funny result. Just warn and terminate
+		 * early.
+		 */
+		return NULL;
+	}
 	order = get_order(size);
 
 again:

mm/vmscan.c

···
 static LIST_HEAD(shrinker_list);
 static DECLARE_RWSEM(shrinker_rwsem);
 
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+#ifdef CONFIG_MEMCG
 static bool global_reclaim(struct scan_control *sc)
 {
 	return !sc->target_mem_cgroup;
···
 
 	cond_resched();
 
+	mem_cgroup_uncharge_start();
 	while (!list_empty(page_list)) {
 		enum page_references references;
 		struct address_space *mapping;
···
 			(PageSwapCache(page) && (sc->gfp_mask & __GFP_IO));
 
 		if (PageWriteback(page)) {
-			nr_writeback++;
-			unlock_page(page);
-			goto keep;
+			/*
+			 * memcg doesn't have any dirty pages throttling so we
+			 * could easily OOM just because too many pages are in
+			 * writeback and there is nothing else to reclaim.
+			 *
+			 * Check __GFP_IO, certainly because a loop driver
+			 * thread might enter reclaim, and deadlock if it waits
+			 * on a page for which it is needed to do the write
+			 * (loop masks off __GFP_IO|__GFP_FS for this reason);
+			 * but more thought would probably show more reasons.
+			 *
+			 * Don't require __GFP_FS, since we're not going into
+			 * the FS, just waiting on its writeback completion.
+			 * Worryingly, ext4 gfs2 and xfs allocate pages with
+			 * grab_cache_page_write_begin(,,AOP_FLAG_NOFS), so
+			 * testing may_enter_fs here is liable to OOM on them.
+			 */
+			if (global_reclaim(sc) ||
+			    !PageReclaim(page) || !(sc->gfp_mask & __GFP_IO)) {
+				/*
+				 * This is slightly racy - end_page_writeback()
+				 * might have just cleared PageReclaim, then
+				 * setting PageReclaim here end up interpreted
+				 * as PageReadahead - but that does not matter
+				 * enough to care.  What we do want is for this
+				 * page to have PageReclaim set next time memcg
+				 * reclaim reaches the tests above, so it will
+				 * then wait_on_page_writeback() to avoid OOM;
+				 * and it's also appropriate in global reclaim.
+				 */
+				SetPageReclaim(page);
+				nr_writeback++;
+				goto keep_locked;
+			}
+			wait_on_page_writeback(page);
 		}
 
 		references = page_check_references(page, sc);
···
 
 	list_splice(&ret_pages, page_list);
 	count_vm_events(PGACTIVATE, pgactivate);
+	mem_cgroup_uncharge_end();
 	*ret_nr_dirty += nr_dirty;
 	*ret_nr_writeback += nr_writeback;
 	return nr_reclaimed;
···
 	return 0;
 }
 
+static bool pfmemalloc_watermark_ok(pg_data_t *pgdat)
+{
+	struct zone *zone;
+	unsigned long pfmemalloc_reserve = 0;
+	unsigned long free_pages = 0;
+	int i;
+	bool wmark_ok;
+
+	for (i = 0; i <= ZONE_NORMAL; i++) {
+		zone = &pgdat->node_zones[i];
+		pfmemalloc_reserve += min_wmark_pages(zone);
+		free_pages += zone_page_state(zone, NR_FREE_PAGES);
+	}
+
+	wmark_ok = free_pages > pfmemalloc_reserve / 2;
+
+	/* kswapd must be awake if processes are being throttled */
+	if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) {
+		pgdat->classzone_idx = min(pgdat->classzone_idx,
+						(enum zone_type)ZONE_NORMAL);
+		wake_up_interruptible(&pgdat->kswapd_wait);
+	}
+
+	return wmark_ok;
+}
+
+/*
+ * Throttle direct reclaimers if backing storage is backed by the network
+ * and the PFMEMALLOC reserve for the preferred node is getting dangerously
+ * depleted. kswapd will continue to make progress and wake the processes
+ * when the low watermark is reached
+ */
+static void throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist,
+					nodemask_t *nodemask)
+{
+	struct zone *zone;
+	int high_zoneidx = gfp_zone(gfp_mask);
+	pg_data_t *pgdat;
+
+	/*
+	 * Kernel threads should not be throttled as they may be indirectly
+	 * responsible for cleaning pages necessary for reclaim to make forward
+	 * progress. kjournald for example may enter direct reclaim while
+	 * committing a transaction where throttling it could forcing other
+	 * processes to block on log_wait_commit().
+	 */
+	if (current->flags & PF_KTHREAD)
+		return;
+
+	/* Check if the pfmemalloc reserves are ok */
+	first_zones_zonelist(zonelist, high_zoneidx, NULL, &zone);
+	pgdat = zone->zone_pgdat;
+	if (pfmemalloc_watermark_ok(pgdat))
+		return;
+
+	/* Account for the throttling */
+	count_vm_event(PGSCAN_DIRECT_THROTTLE);
+
+	/*
+	 * If the caller cannot enter the filesystem, it's possible that it
+	 * is due to the caller holding an FS lock or performing a journal
+	 * transaction in the case of a filesystem like ext[3|4]. In this case,
+	 * it is not safe to block on pfmemalloc_wait as kswapd could be
+	 * blocked waiting on the same lock. Instead, throttle for up to a
+	 * second before continuing.
+	 */
+	if (!(gfp_mask & __GFP_FS)) {
+		wait_event_interruptible_timeout(pgdat->pfmemalloc_wait,
+			pfmemalloc_watermark_ok(pgdat), HZ);
+		return;
+	}
+
+	/* Throttle until kswapd wakes the process */
+	wait_event_killable(zone->zone_pgdat->pfmemalloc_wait,
+		pfmemalloc_watermark_ok(pgdat));
+}
+
 unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 				gfp_t gfp_mask, nodemask_t *nodemask)
 {
···
 		.gfp_mask = sc.gfp_mask,
 	};
 
+	throttle_direct_reclaim(gfp_mask, zonelist, nodemask);
+
+	/*
+	 * Do not enter reclaim if fatal signal is pending. 1 is returned so
+	 * that the page allocator does not consider triggering OOM
+	 */
+	if (fatal_signal_pending(current))
+		return 1;
+
 	trace_mm_vmscan_direct_reclaim_begin(order,
 				sc.may_writepage,
 				gfp_mask);
···
 	return nr_reclaimed;
 }
 
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+#ifdef CONFIG_MEMCG
 
 unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *memcg,
 						gfp_t gfp_mask, bool noswap,
···
 	return balanced_pages >= (present_pages >> 2);
 }
 
-/* is kswapd sleeping prematurely? */
-static bool sleeping_prematurely(pg_data_t *pgdat, int order, long remaining,
+/*
+ * Prepare kswapd for sleeping. This verifies that there are no processes
+ * waiting in throttle_direct_reclaim() and that watermarks have been met.
+ *
+ * Returns true if kswapd is ready to sleep
+ */
+static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining,
 					int classzone_idx)
 {
 	int i;
···
 
 	/* If a direct reclaimer woke kswapd within HZ/10, it's premature */
 	if (remaining)
-		return true;
+		return false;
+
+	/*
+	 * There is a potential race between when kswapd checks its watermarks
+	 * and a process gets throttled. There is also a potential race if
+	 * processes get throttled, kswapd wakes, a large process exits therby
+	 * balancing the zones that causes kswapd to miss a wakeup. If kswapd
+	 * is going to sleep, no process should be sleeping on pfmemalloc_wait
+	 * so wake them now if necessary. If necessary, processes will wake
+	 * kswapd and get throttled again
+	 */
+	if (waitqueue_active(&pgdat->pfmemalloc_wait)) {
+		wake_up(&pgdat->pfmemalloc_wait);
+		return false;
+	}
 
 	/* Check the watermark levels */
 	for (i = 0; i <= classzone_idx; i++) {
···
 	 * must be balanced
 	 */
 	if (order)
-		return !pgdat_balanced(pgdat, balanced, classzone_idx);
+		return pgdat_balanced(pgdat, balanced, classzone_idx);
 	else
-		return !all_zones_ok;
+		return all_zones_ok;
 }
 
 /*
···
 			}
 
 		}
+
+		/*
+		 * If the low watermark is met there is no need for processes
+		 * to be throttled on pfmemalloc_wait as they should not be
+		 * able to safely make forward progress. Wake them
+		 */
+		if (waitqueue_active(&pgdat->pfmemalloc_wait) &&
+				pfmemalloc_watermark_ok(pgdat))
+			wake_up(&pgdat->pfmemalloc_wait);
+
 		if (all_zones_ok || (order && pgdat_balanced(pgdat, balanced, *classzone_idx)))
 			break;		/* kswapd: all done */
 		/*
···
 	}
 
 	/*
-	 * Return the order we were reclaiming at so sleeping_prematurely()
+	 * Return the order we were reclaiming at so prepare_kswapd_sleep()
 	 * makes a decision on the order we were last reclaiming at. However,
 	 * if another caller entered the allocator slow path while kswapd
 	 * was awake, order will remain at the higher level
···
 	prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
 
 	/* Try to sleep for a short interval */
-	if (!sleeping_prematurely(pgdat, order, remaining, classzone_idx)) {
+	if (prepare_kswapd_sleep(pgdat, order, remaining, classzone_idx)) {
 		remaining = schedule_timeout(HZ/10);
 		finish_wait(&pgdat->kswapd_wait, &wait);
 		prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
···
 	 * After a short sleep, check if it was a premature sleep. If not, then
 	 * go fully to sleep until explicitly woken up.
 	 */
-	if (!sleeping_prematurely(pgdat, order, remaining, classzone_idx)) {
+	if (prepare_kswapd_sleep(pgdat, order, remaining, classzone_idx)) {
 		trace_mm_vmscan_kswapd_sleep(pgdat->node_id);
 
 		/*

mm/vmstat.c

···
 	TEXTS_FOR_ZONES("pgsteal_direct")
 	TEXTS_FOR_ZONES("pgscan_kswapd")
 	TEXTS_FOR_ZONES("pgscan_direct")
+	"pgscan_direct_throttle",
 
 #ifdef CONFIG_NUMA
 	"zone_reclaim_failed",

net/caif/caif_socket.c

···
 	err = sk_filter(sk, skb);
 	if (err)
 		return err;
-	if (!sk_rmem_schedule(sk, skb->truesize) && rx_flow_is_on(cf_sk)) {
+	if (!sk_rmem_schedule(sk, skb, skb->truesize) && rx_flow_is_on(cf_sk)) {
 		set_rx_flow_off(cf_sk);
 		net_dbg_ratelimited("sending flow OFF due to rmem_schedule\n");
 		caif_flow_ctrl(sk, CAIF_MODEMCMD_FLOW_OFF_REQ);

net/core/dev.c

···
 }
 EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister);
 
+/*
+ * Limit the use of PFMEMALLOC reserves to those protocols that implement
+ * the special handling of PFMEMALLOC skbs.
+ */
+static bool skb_pfmemalloc_protocol(struct sk_buff *skb)
+{
+	switch (skb->protocol) {
+	case __constant_htons(ETH_P_ARP):
+	case __constant_htons(ETH_P_IP):
+	case __constant_htons(ETH_P_IPV6):
+	case __constant_htons(ETH_P_8021Q):
+		return true;
+	default:
+		return false;
+	}
+}
+
 static int __netif_receive_skb(struct sk_buff *skb)
 {
 	struct packet_type *ptype, *pt_prev;
···
 	bool deliver_exact = false;
 	int ret = NET_RX_DROP;
 	__be16 type;
+	unsigned long pflags = current->flags;
 
 	net_timestamp_check(!netdev_tstamp_prequeue, skb);
 
 	trace_netif_receive_skb(skb);
 
+	/*
+	 * PFMEMALLOC skbs are special, they should
+	 * - be delivered to SOCK_MEMALLOC sockets only
+	 * - stay away from userspace
+	 * - have bounded memory usage
+	 *
+	 * Use PF_MEMALLOC as this saves us from propagating the allocation
+	 * context down to all allocation sites.
+	 */
+	if (sk_memalloc_socks() && skb_pfmemalloc(skb))
+		current->flags |= PF_MEMALLOC;
+
 	/* if we've gotten here through NAPI, check netpoll */
 	if (netpoll_receive_skb(skb))
-		return NET_RX_DROP;
+		goto out;
 
 	orig_dev = skb->dev;
 
···
 	if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) {
 		skb = vlan_untag(skb);
 		if (unlikely(!skb))
-			goto out;
+			goto unlock;
 	}
 
 #ifdef CONFIG_NET_CLS_ACT
···
 	}
 #endif
 
+	if (sk_memalloc_socks() && skb_pfmemalloc(skb))
+		goto skip_taps;
+
 	list_for_each_entry_rcu(ptype, &ptype_all, list) {
 		if (!ptype->dev || ptype->dev == skb->dev) {
 			if (pt_prev)
···
 		}
 	}
 
+skip_taps:
 #ifdef CONFIG_NET_CLS_ACT
 	skb = handle_ing(skb, &pt_prev, &ret, orig_dev);
 	if (!skb)
-		goto out;
+		goto unlock;
 ncls:
 #endif
+
+	if (sk_memalloc_socks() && skb_pfmemalloc(skb)
+				&& !skb_pfmemalloc_protocol(skb))
+		goto drop;
 
 	rx_handler = rcu_dereference(skb->dev->rx_handler);
 	if (vlan_tx_tag_present(skb)) {
···
 		if (vlan_do_receive(&skb, !rx_handler))
 			goto another_round;
 		else if (unlikely(!skb))
-			goto out;
+			goto unlock;
 	}
 
 	if (rx_handler) {
···
 		}
 		switch (rx_handler(&skb)) {
 		case RX_HANDLER_CONSUMED:
-			goto out;
+			goto unlock;
 		case RX_HANDLER_ANOTHER:
 			goto another_round;
 		case RX_HANDLER_EXACT:
···
 		else
 			ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
 	} else {
+drop:
 		atomic_long_inc(&skb->dev->rx_dropped);
 		kfree_skb(skb);
 		/* Jamal, now you will not able to escape explaining
···
 		ret = NET_RX_DROP;
 	}
 
-out:
+unlock:
 	rcu_read_unlock();
+out:
+	tsk_restore_flags(current, pflags, PF_MEMALLOC);
 	return ret;
 }
 

net/core/filter.c

···
 	int err;
 	struct sk_filter *filter;
 
+	/*
+	 * If the skb was allocated from pfmemalloc reserves, only
+	 * allow SOCK_MEMALLOC sockets to use it as this socket is
+	 * helping free memory
+	 */
+	if (skb_pfmemalloc(skb) && !sock_flag(sk, SOCK_MEMALLOC))
+		return -ENOMEM;
+
 	err = security_sock_rcv_skb(sk, skb);
 	if (err)
 		return err;

net/core/skbuff.c

···
 	BUG();
 }
 
+
+/*
+ * kmalloc_reserve is a wrapper around kmalloc_node_track_caller that tells
+ * the caller if emergency pfmemalloc reserves are being used. If it is and
+ * the socket is later found to be SOCK_MEMALLOC then PFMEMALLOC reserves
+ * may be used. Otherwise, the packet data may be discarded until enough
+ * memory is free
+ */
+#define kmalloc_reserve(size, gfp, node, pfmemalloc) \
+	 __kmalloc_reserve(size, gfp, node, _RET_IP_, pfmemalloc)
+void *__kmalloc_reserve(size_t size, gfp_t flags, int node, unsigned long ip,
+			 bool *pfmemalloc)
+{
+	void *obj;
+	bool ret_pfmemalloc = false;
+
+	/*
+	 * Try a regular allocation, when that fails and we're not entitled
+	 * to the reserves, fail.
+	 */
+	obj = kmalloc_node_track_caller(size,
+					flags | __GFP_NOMEMALLOC | __GFP_NOWARN,
+					node);
+	if (obj || !(gfp_pfmemalloc_allowed(flags)))
+		goto out;
+
+	/* Try again but now we are using pfmemalloc reserves */
+	ret_pfmemalloc = true;
+	obj = kmalloc_node_track_caller(size, flags, node);
+
+out:
+	if (pfmemalloc)
+		*pfmemalloc = ret_pfmemalloc;
+
+	return obj;
+}
+
 /* 	Allocate a new skbuff. We do this ourselves so we can fill in a few
  *	'private' fields and also do memory statistics to find all the
  *	[BEEP] leaks.
···
  *	__alloc_skb	-	allocate a network buffer
  *	@size: size to allocate
  *	@gfp_mask: allocation mask
- *	@fclone: allocate from fclone cache instead of head cache
- *		and allocate a cloned (child) skb
+ *	@flags: If SKB_ALLOC_FCLONE is set, allocate from fclone cache
+ *		instead of head cache and allocate a cloned (child) skb.
+ *		If SKB_ALLOC_RX is set, __GFP_MEMALLOC will be used for
+ *		allocations in case the data is required for writeback
  *	@node: numa node to allocate memory on
  *
  *	Allocate a new &sk_buff. The returned buffer has no headroom and a
···
  *	%GFP_ATOMIC.
  */
 struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
-			    int fclone, int node)
+			    int flags, int node)
 {
 	struct kmem_cache *cache;
 	struct skb_shared_info *shinfo;
 	struct sk_buff *skb;
 	u8 *data;
+	bool pfmemalloc;
 
-	cache = fclone ? skbuff_fclone_cache : skbuff_head_cache;
+	cache = (flags & SKB_ALLOC_FCLONE)
+		? skbuff_fclone_cache : skbuff_head_cache;
+
+	if (sk_memalloc_socks() && (flags & SKB_ALLOC_RX))
+		gfp_mask |= __GFP_MEMALLOC;
 
 	/* Get the HEAD */
 	skb = kmem_cache_alloc_node(cache, gfp_mask & ~__GFP_DMA, node);
···
 	 */
 	size = SKB_DATA_ALIGN(size);
 	size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
-	data = kmalloc_node_track_caller(size, gfp_mask, node);
+	data = kmalloc_reserve(size, gfp_mask, node, &pfmemalloc);
 	if (!data)
 		goto nodata;
 	/* kmalloc(size) might give us more room than requested.
···
 	memset(skb, 0, offsetof(struct sk_buff, tail));
 	/* Account for allocated memory : skb + skb->head */
 	skb->truesize = SKB_TRUESIZE(size);
+	skb->pfmemalloc = pfmemalloc;
 	atomic_set(&skb->users, 1);
 	skb->head = data;
 	skb->data = data;
···
 	atomic_set(&shinfo->dataref, 1);
 	kmemcheck_annotate_variable(shinfo->destructor_arg);
 
-	if (fclone) {
+	if (flags & SKB_ALLOC_FCLONE) {
 		struct sk_buff *child = skb + 1;
 		atomic_t *fclone_ref = (atomic_t *) (child + 1);
 
···
 		atomic_set(fclone_ref, 1);
 
 		child->fclone = SKB_FCLONE_UNAVAILABLE;
+		child->pfmemalloc = pfmemalloc;
 	}
 out:
 	return skb;
···
 
 #define NETDEV_PAGECNT_BIAS (PAGE_SIZE / SMP_CACHE_BYTES)
 
-/**
- * netdev_alloc_frag - allocate a page fragment
- * @fragsz: fragment size
- *
- * Allocates a frag from a page for receive buffer.
- * Uses GFP_ATOMIC allocations.
- */
-void *netdev_alloc_frag(unsigned int fragsz)
+static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
 {
 	struct netdev_alloc_cache *nc;
 	void *data = NULL;
···
 	nc = &__get_cpu_var(netdev_alloc_cache);
 	if (unlikely(!nc->page)) {
 refill:
-		nc->page = alloc_page(GFP_ATOMIC | __GFP_COLD);
+		nc->page = alloc_page(gfp_mask);
 		if (unlikely(!nc->page))
 			goto end;
 recycle:
···
 end:
 	local_irq_restore(flags);
 	return data;
+}
+
+/**
+ * netdev_alloc_frag - allocate a page fragment
+ * @fragsz: fragment size
+ *
+ * Allocates a frag from a page for receive buffer.
+ * Uses GFP_ATOMIC allocations.
+ */
+void *netdev_alloc_frag(unsigned int fragsz)
+{
+	return __netdev_alloc_frag(fragsz, GFP_ATOMIC | __GFP_COLD);
 }
 EXPORT_SYMBOL(netdev_alloc_frag);
 
···
 			      SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 
 	if (fragsz <= PAGE_SIZE && !(gfp_mask & (__GFP_WAIT | GFP_DMA))) {
-		void *data = netdev_alloc_frag(fragsz);
+		void *data;
+
+		if (sk_memalloc_socks())
+			gfp_mask |= __GFP_MEMALLOC;
+
+		data = __netdev_alloc_frag(fragsz, gfp_mask);
 
 		if (likely(data)) {
 			skb = build_skb(data, fragsz);
···
 				put_page(virt_to_head_page(data));
 		}
 	} else {
-		skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask, 0, NUMA_NO_NODE);
+		skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask,
+				  SKB_ALLOC_RX, NUMA_NO_NODE);
 	}
 	if (likely(skb)) {
 		skb_reserve(skb, NET_SKB_PAD);
···
 #if IS_ENABLED(CONFIG_IP_VS)
 	new->ipvs_property	= old->ipvs_property;
 #endif
+	new->pfmemalloc		= old->pfmemalloc;
 	new->protocol		= old->protocol;
 	new->mark		= old->mark;
 	new->skb_iif		= old->skb_iif;
···
 		n->fclone = SKB_FCLONE_CLONE;
 		atomic_inc(fclone_ref);
 	} else {
+		if (skb_pfmemalloc(skb))
+			gfp_mask |= __GFP_MEMALLOC;
+
 		n = kmem_cache_alloc(skbuff_head_cache, gfp_mask);
 		if (!n)
 			return NULL;
···
 	skb_shinfo(new)->gso_type = skb_shinfo(old)->gso_type;
 }
 
+static inline int skb_alloc_rx_flag(const struct sk_buff *skb)
+{
+	if (skb_pfmemalloc(skb))
+		return SKB_ALLOC_RX;
+	return 0;
+}
+
 /**
  *	skb_copy	-	create private copy of an sk_buff
  *	@skb: buffer to copy
···
 {
 	int headerlen = skb_headroom(skb);
 	unsigned int size = skb_end_offset(skb) + skb->data_len;
-	struct sk_buff *n = alloc_skb(size, gfp_mask);
+	struct sk_buff *n = __alloc_skb(size, gfp_mask,
+					skb_alloc_rx_flag(skb), NUMA_NO_NODE);
 
 	if (!n)
 		return NULL;
···
 struct sk_buff *__pskb_copy(struct sk_buff *skb, int headroom, gfp_t gfp_mask)
 {
 	unsigned int size = skb_headlen(skb) + headroom;
-	struct sk_buff *n = alloc_skb(size, gfp_mask);
+	struct sk_buff *n = __alloc_skb(size, gfp_mask,
+					skb_alloc_rx_flag(skb), NUMA_NO_NODE);
 
 	if (!n)
 		goto out;
···
 
 	size = SKB_DATA_ALIGN(size);
 
-	data = kmalloc(size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)),
-		       gfp_mask);
+	if (skb_pfmemalloc(skb))
+		gfp_mask |= __GFP_MEMALLOC;
+	data = kmalloc_reserve(size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)),
+			       gfp_mask, NUMA_NO_NODE, NULL);
 	if (!data)
 		goto nodata;
 	size = SKB_WITH_OVERHEAD(ksize(data));
···
 	/*
 	 *	Allocate the copy buffer
 	 */
-	struct sk_buff *n = alloc_skb(newheadroom + skb->len + newtailroom,
-				      gfp_mask);
+	struct sk_buff *n = __alloc_skb(newheadroom + skb->len + newtailroom,
+					gfp_mask, skb_alloc_rx_flag(skb),
+					NUMA_NO_NODE);
 	int oldheadroom = skb_headroom(skb);
 	int head_copy_len, head_copy_off;
 	int off;
···
 			skb_release_head_state(nskb);
 			__skb_push(nskb, doffset);
 		} else {
-			nskb = alloc_skb(hsize + doffset + headroom,
-					 GFP_ATOMIC);
+			nskb = __alloc_skb(hsize + doffset + headroom,
+					   GFP_ATOMIC, skb_alloc_rx_flag(skb),
+					   NUMA_NO_NODE);
 
 			if (unlikely(!nskb))
 				goto err;

net/core/sock.c

···
 static DEFINE_MUTEX(proto_list_mutex);
 static LIST_HEAD(proto_list);
 
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+#ifdef CONFIG_MEMCG_KMEM
 int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 {
 	struct proto *proto;
···
 int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512);
 EXPORT_SYMBOL(sysctl_optmem_max);
 
+struct static_key memalloc_socks = STATIC_KEY_INIT_FALSE;
+EXPORT_SYMBOL_GPL(memalloc_socks);
+
+/**
+ * sk_set_memalloc - sets %SOCK_MEMALLOC
+ * @sk: socket to set it on
+ *
+ * Set %SOCK_MEMALLOC on a socket for access to emergency reserves.
+ * It's the responsibility of the admin to adjust min_free_kbytes
+ * to meet the requirements
+ */
+void sk_set_memalloc(struct sock *sk)
+{
+	sock_set_flag(sk, SOCK_MEMALLOC);
+	sk->sk_allocation |= __GFP_MEMALLOC;
+	static_key_slow_inc(&memalloc_socks);
+}
+EXPORT_SYMBOL_GPL(sk_set_memalloc);
+
+void sk_clear_memalloc(struct sock *sk)
+{
+	sock_reset_flag(sk, SOCK_MEMALLOC);
+	sk->sk_allocation &= ~__GFP_MEMALLOC;
+	static_key_slow_dec(&memalloc_socks);
+
+	/*
+	 * SOCK_MEMALLOC is allowed to ignore rmem limits to ensure forward
+	 * progress of swapping. However, if SOCK_MEMALLOC is cleared while
+	 * it has rmem allocations there is a risk that the user of the
+	 * socket cannot make forward progress due to exceeding the rmem
+	 * limits. By rights, sk_clear_memalloc() should only be called
+	 * on sockets being torn down but warn and reset the accounting if
+	 * that assumption breaks.
+	 */
+	if (WARN_ON(sk->sk_forward_alloc))
+		sk_mem_reclaim(sk);
+}
+EXPORT_SYMBOL_GPL(sk_clear_memalloc);
+
+int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
+{
+	int ret;
+	unsigned long pflags = current->flags;
+
+	/* these should have been dropped before queueing */
+	BUG_ON(!sock_flag(sk, SOCK_MEMALLOC));
+
+	current->flags |= PF_MEMALLOC;
+	ret = sk->sk_backlog_rcv(sk, skb);
+	tsk_restore_flags(current, pflags, PF_MEMALLOC);
+
+	return ret;
+}
+EXPORT_SYMBOL(__sk_backlog_rcv);
+
 #if defined(CONFIG_CGROUPS)
 #if !defined(CONFIG_NET_CLS_CGROUP)
 int net_cls_subsys_id = -1;
···
 	if (err)
 		return err;
 
-	if (!sk_rmem_schedule(sk, skb->truesize)) {
+	if (!sk_rmem_schedule(sk, skb, skb->truesize)) {
 		atomic_inc(&sk->sk_drops);
 		return -ENOBUFS;
 	}

net/ipv4/Makefile

···
 obj-$(CONFIG_TCP_CONG_LP) += tcp_lp.o
 obj-$(CONFIG_TCP_CONG_YEAH) += tcp_yeah.o
 obj-$(CONFIG_TCP_CONG_ILLINOIS) += tcp_illinois.o
-obj-$(CONFIG_CGROUP_MEM_RES_CTLR_KMEM) += tcp_memcontrol.o
+obj-$(CONFIG_MEMCG_KMEM) += tcp_memcontrol.o
 obj-$(CONFIG_NETLABEL) += cipso_ipv4.o
 
 obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \

net/ipv4/sysctl_net_ipv4.c

···
 	int ret;
 	unsigned long vec[3];
 	struct net *net = current->nsproxy->net_ns;
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+#ifdef CONFIG_MEMCG_KMEM
 	struct mem_cgroup *memcg;
 #endif
 
···
 	if (ret)
 		return ret;
 
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+#ifdef CONFIG_MEMCG_KMEM
 	rcu_read_lock();
 	memcg = mem_cgroup_from_task(current);
 

net/ipv4/tcp_input.c

···
 static bool tcp_prune_ofo_queue(struct sock *sk);
 static int tcp_prune_queue(struct sock *sk);
 
-static int tcp_try_rmem_schedule(struct sock *sk, unsigned int size)
+static int tcp_try_rmem_schedule(struct sock *sk, struct sk_buff *skb,
+				 unsigned int size)
 {
 	if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
-	    !sk_rmem_schedule(sk, size)) {
+	    !sk_rmem_schedule(sk, skb, size)) {
 
 		if (tcp_prune_queue(sk) < 0)
 			return -1;
 
-		if (!sk_rmem_schedule(sk, size)) {
+		if (!sk_rmem_schedule(sk, skb, size)) {
 			if (!tcp_prune_ofo_queue(sk))
 				return -1;
 
-			if (!sk_rmem_schedule(sk, size))
+			if (!sk_rmem_schedule(sk, skb, size))
 				return -1;
 		}
 	}
···
 
 	TCP_ECN_check_ce(tp, skb);
 
-	if (unlikely(tcp_try_rmem_schedule(sk, skb->truesize))) {
+	if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) {
 		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPOFODROP);
 		__kfree_skb(skb);
 		return;
···
 
 int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
 {
-	struct sk_buff *skb;
+	struct sk_buff *skb = NULL;
 	struct tcphdr *th;
 	bool fragstolen;
-
-	if (tcp_try_rmem_schedule(sk, size + sizeof(*th)))
-		goto err;
 
 	skb = alloc_skb(size + sizeof(*th), sk->sk_allocation);
 	if (!skb)
 		goto err;
+
+	if (tcp_try_rmem_schedule(sk, skb, size + sizeof(*th)))
+		goto err_free;
 
 	th = (struct tcphdr *)skb_put(skb, sizeof(*th));
 	skb_reset_transport_header(skb);
···
 		if (eaten <= 0) {
 queue_and_out:
 			if (eaten < 0 &&
-			    tcp_try_rmem_schedule(sk, skb->truesize))
+			    tcp_try_rmem_schedule(sk, skb, skb->truesize))
 				goto drop;
 
 			eaten = tcp_queue_rcv(sk, skb, 0, &fragstolen);

net/ipv4/tcp_ipv4.c

···
 	.compat_setsockopt	= compat_tcp_setsockopt,
 	.compat_getsockopt	= compat_tcp_getsockopt,
 #endif
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+#ifdef CONFIG_MEMCG_KMEM
 	.init_cgroup		= tcp_init_cgroup,
 	.destroy_cgroup		= tcp_destroy_cgroup,
 	.proto_cgroup		= tcp_proto_cgroup,

net/ipv4/tcp_output.c

···
 	if (unlikely(sk->sk_state == TCP_CLOSE))
 		return;
 
-	if (tcp_write_xmit(sk, cur_mss, nonagle, 0, GFP_ATOMIC))
+	if (tcp_write_xmit(sk, cur_mss, nonagle, 0,
+			   sk_gfp_atomic(sk, GFP_ATOMIC)))
 		tcp_check_probe_timer(sk);
 }
 
···
 
 	if (cvp != NULL && cvp->s_data_constant && cvp->s_data_desired)
 		s_data_desired = cvp->s_data_desired;
-	skb = alloc_skb(MAX_TCP_HEADER + 15 + s_data_desired, GFP_ATOMIC);
+	skb = alloc_skb(MAX_TCP_HEADER + 15 + s_data_desired,
+			sk_gfp_atomic(sk, GFP_ATOMIC));
 	if (unlikely(!skb)) {
 		dst_release(dst);
 		return NULL;
···
 	 * tcp_transmit_skb() will set the ownership to this
 	 * sock.
 	 */
-	buff = alloc_skb(MAX_TCP_HEADER, GFP_ATOMIC);
+	buff = alloc_skb(MAX_TCP_HEADER, sk_gfp_atomic(sk, GFP_ATOMIC));
 	if (buff == NULL) {
 		inet_csk_schedule_ack(sk);
 		inet_csk(sk)->icsk_ack.ato = TCP_ATO_MIN;
···
 
 	/* Send it off, this clears delayed acks for us. */
 	TCP_SKB_CB(buff)->when = tcp_time_stamp;
-	tcp_transmit_skb(sk, buff, 0, GFP_ATOMIC);
+	tcp_transmit_skb(sk, buff, 0, sk_gfp_atomic(sk, GFP_ATOMIC));
 }
 
 /* This routine sends a packet with an out of date sequence
···
 	struct sk_buff *skb;
 
 	/* We don't queue it, tcp_transmit_skb() sets ownership. */
-	skb = alloc_skb(MAX_TCP_HEADER, GFP_ATOMIC);
+	skb = alloc_skb(MAX_TCP_HEADER, sk_gfp_atomic(sk, GFP_ATOMIC));
 	if (skb == NULL)
 		return -1;
 

net/ipv6/tcp_ipv6.c

···
 	/* Clone pktoptions received with SYN */
 	newnp->pktoptions = NULL;
 	if (treq->pktopts != NULL) {
-		newnp->pktoptions = skb_clone(treq->pktopts, GFP_ATOMIC);
+		newnp->pktoptions = skb_clone(treq->pktopts,
+					      sk_gfp_atomic(sk, GFP_ATOMIC));
 		consume_skb(treq->pktopts);
 		treq->pktopts = NULL;
 		if (newnp->pktoptions)
···
 		 * across. Shucks.
 		 */
 		tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newnp->daddr,
-			       AF_INET6, key->key, key->keylen, GFP_ATOMIC);
+			       AF_INET6, key->key, key->keylen,
+			       sk_gfp_atomic(sk, GFP_ATOMIC));
 	}
 #endif
 
···
 					       --ANK (980728)
 	 */
 	if (np->rxopt.all)
-		opt_skb = skb_clone(skb, GFP_ATOMIC);
+		opt_skb = skb_clone(skb, sk_gfp_atomic(sk, GFP_ATOMIC));
 
 	if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
 		sock_rps_save_rxhash(sk, skb);
···
 	.compat_setsockopt	= compat_tcp_setsockopt,
 	.compat_getsockopt	= compat_tcp_getsockopt,
 #endif
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+#ifdef CONFIG_MEMCG_KMEM
 	.proto_cgroup		= tcp_proto_cgroup,
 #endif
 };

net/sctp/ulpevent.c

···
 	if (rx_count >= asoc->base.sk->sk_rcvbuf) {
 
 		if ((asoc->base.sk->sk_userlocks & SOCK_RCVBUF_LOCK) ||
-		    (!sk_rmem_schedule(asoc->base.sk, chunk->skb->truesize)))
+		    (!sk_rmem_schedule(asoc->base.sk, chunk->skb,
+				       chunk->skb->truesize)))
 			goto fail;
 	}
 

net/sunrpc/Kconfig

···
 
 	  If unsure, say N.
 
+config SUNRPC_SWAP
+	bool
+	depends on SUNRPC
+	select NETVM
+
 config RPCSEC_GSS_KRB5
 	tristate "Secure RPC: Kerberos V mechanism"
 	depends on SUNRPC && CRYPTO

net/sunrpc/clnt.c

···
 		atomic_inc(&clnt->cl_count);
 		if (clnt->cl_softrtry)
 			task->tk_flags |= RPC_TASK_SOFT;
+		if (sk_memalloc_socks()) {
+			struct rpc_xprt *xprt;
+
+			rcu_read_lock();
+			xprt = rcu_dereference(clnt->cl_xprt);
+			if (xprt->swapper)
+				task->tk_flags |= RPC_TASK_SWAPPER;
+			rcu_read_unlock();
+		}
 		/* Add to the client's list of all tasks */
 		spin_lock(&clnt->cl_lock);
 		list_add_tail(&task->tk_task, &clnt->cl_tasks);

net/sunrpc/sched.c

···
 void *rpc_malloc(struct rpc_task *task, size_t size)
 {
 	struct rpc_buffer *buf;
-	gfp_t gfp = RPC_IS_SWAPPER(task) ? GFP_ATOMIC : GFP_NOWAIT;
+	gfp_t gfp = GFP_NOWAIT;
+
+	if (RPC_IS_SWAPPER(task))
+		gfp |= __GFP_MEMALLOC;
 
 	size += sizeof(struct rpc_buffer);
 	if (size <= RPC_BUFFER_MAXSIZE)
···
 static struct rpc_task *
 rpc_alloc_task(void)
 {
-	return (struct rpc_task *)mempool_alloc(rpc_task_mempool, GFP_NOFS);
+	return (struct rpc_task *)mempool_alloc(rpc_task_mempool, GFP_NOIO);
 }
 
 /*

net/sunrpc/xprtsock.c

···
 	current->flags &= ~PF_FSTRANS;
 }
 
+#ifdef CONFIG_SUNRPC_SWAP
+static void xs_set_memalloc(struct rpc_xprt *xprt)
+{
+	struct sock_xprt *transport = container_of(xprt, struct sock_xprt,
+			xprt);
+
+	if (xprt->swapper)
+		sk_set_memalloc(transport->inet);
+}
+
+/**
+ * xs_swapper - Tag this transport as being used for swap.
+ * @xprt: transport to tag
+ * @enable: enable/disable
+ *
+ */
+int xs_swapper(struct rpc_xprt *xprt, int enable)
+{
+	struct sock_xprt *transport = container_of(xprt, struct sock_xprt,
+			xprt);
+	int err = 0;
+
+	if (enable) {
+		xprt->swapper++;
+		xs_set_memalloc(xprt);
+	} else if (xprt->swapper) {
+		xprt->swapper--;
+		sk_clear_memalloc(transport->inet);
+	}
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(xs_swapper);
+#else
+static void xs_set_memalloc(struct rpc_xprt *xprt)
+{
+}
+#endif
+
 static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
 {
 	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
···
 		/* Reset to new socket */
 		transport->sock = sock;
 		transport->inet = sk;
+
+		xs_set_memalloc(xprt);
 
 		write_unlock_bh(&sk->sk_callback_lock);
 	}
···
 
 	if (!xprt_bound(xprt))
 		goto out;
+
+	xs_set_memalloc(xprt);
 
 	/* Tell the socket layer to start connecting... */
 	xprt->stat.connect_count++;

security/selinux/avc.c

···
 {
 	struct avc_node *node;
 
-	node = kmem_cache_zalloc(avc_node_cachep, GFP_ATOMIC);
+	node = kmem_cache_zalloc(avc_node_cachep, GFP_ATOMIC|__GFP_NOMEMALLOC);
 	if (!node)
 		goto out;
 

tools/testing/fault-injection/failcmd.sh

···
 	esac
 done
 
-[ -z "$@" ] && exit 0
+[ -z "$1" ] && exit 0
 
 echo $oom_kill_allocating_task > /proc/sys/vm/oom_kill_allocating_task
 echo $task_filter > $FAULTATTR/task-filter