Merge branch 'akpm' (patches from Andrew)

Merge updates from Andrew Morton:
 "Am experimenting with splitting MM up into identifiable subsystems
  perhaps with a view to gitifying it in complex ways. Also with more
  verbose "incoming" emails.

  Most of MM is here and a few other trees.

  Subsystems affected by this patch series:
   - hotfixes
   - iommu
   - scripts
   - arch/sh
   - ocfs2
   - mm:slab-generic
   - mm:slub
   - mm:kmemleak
   - mm:kasan
   - mm:cleanups
   - mm:debug
   - mm:pagecache
   - mm:swap
   - mm:memcg
   - mm:gup
   - mm:pagemap
   - mm:infrastructure
   - mm:vmalloc
   - mm:initialization
   - mm:pagealloc
   - mm:vmscan
   - mm:tools
   - mm:proc
   - mm:ras
   - mm:oom-kill

  hotfixes:
      mm: vmscan: scan anonymous pages on file refaults
      mm/nvdimm: add is_ioremap_addr and use that to check ioremap address
      mm/memcontrol: fix wrong statistics in memory.stat
      mm/z3fold.c: lock z3fold page before  __SetPageMovable()
      nilfs2: do not use unexported cpu_to_le32()/le32_to_cpu() in uapi header
      MAINTAINERS: nilfs2: update email address

  iommu:
      include/linux/dmar.h: replace single-char identifiers in macros

  scripts:
      scripts/decode_stacktrace: match basepath using shell prefix operator, not regex
      scripts/decode_stacktrace: look for modules with .ko.debug extension
      scripts/spelling.txt: drop "sepc" from the misspelling list
      scripts/spelling.txt: add spelling fix for prohibited
      scripts/decode_stacktrace: Accept dash/underscore in modules
      scripts/spelling.txt: add more spellings to spelling.txt

  arch/sh:
      arch/sh/configs/sdk7786_defconfig: remove CONFIG_LOGFS
      sh: config: remove left-over BACKLIGHT_LCD_SUPPORT
      sh: prevent warnings when using iounmap

  ocfs2:
      fs: ocfs: fix spelling mistake "hearbeating" -> "heartbeat"
      ocfs2/dlm: use struct_size() helper
      ocfs2: add last unlock times in locking_state
      ocfs2: add locking filter debugfs file
      ocfs2: add first lock wait time in locking_state
      ocfs: no need to check return value of debugfs_create functions
      fs/ocfs2/dlmglue.c: unneeded variable: "status"
      ocfs2: use kmemdup rather than duplicating its implementation

  mm:slab-generic:
    Patch series "mm/slab: Improved sanity checking":
      mm/slab: validate cache membership under freelist hardening
      mm/slab: sanity-check page type when looking up cache
      lkdtm/heap: add tests for freelist hardening

  mm:slub:
      mm/slub.c: avoid double string traverse in kmem_cache_flags()
      slub: don't panic for memcg kmem cache creation failure

  mm:kmemleak:
      mm/kmemleak.c: fix check for softirq context
      mm/kmemleak.c: change error at _write when kmemleak is disabled
      docs: kmemleak: add more documentation details

  mm:kasan:
      mm/kasan: print frame description for stack bugs
      Patch series "Bitops instrumentation for KASAN", v5:
        lib/test_kasan: add bitops tests
        x86: use static_cpu_has in uaccess region to avoid instrumentation
        asm-generic, x86: add bitops instrumentation for KASAN
      Patch series "mm/kasan: Add object validation in ksize()", v3:
        mm/kasan: introduce __kasan_check_{read,write}
        mm/kasan: change kasan_check_{read,write} to return boolean
        lib/test_kasan: Add test for double-kzfree detection
        mm/slab: refactor common ksize KASAN logic into slab_common.c
        mm/kasan: add object validation in ksize()

  mm:cleanups:
      include/linux/pfn_t.h: remove pfn_t_to_virt()
      Patch series "remove ARCH_SELECT_MEMORY_MODEL where it has no effect":
        arm: remove ARCH_SELECT_MEMORY_MODEL
        s390: remove ARCH_SELECT_MEMORY_MODEL
        sparc: remove ARCH_SELECT_MEMORY_MODEL
      mm/gup.c: make follow_page_mask() static
      mm/memory.c: trivial clean up in insert_page()
      mm: make !CONFIG_HUGE_PAGE wrappers into static inlines
      include/linux/mm_types.h: ifdef struct vm_area_struct::swap_readahead_info
      mm: remove the account_page_dirtied export
      mm/page_isolation.c: change the prototype of undo_isolate_page_range()
      include/linux/vmpressure.h: use spinlock_t instead of struct spinlock
      mm: remove the exporting of totalram_pages
      include/linux/pagemap.h: document trylock_page() return value

  mm:debug:
      mm/failslab.c: by default, do not fail allocations with direct reclaim only
      Patch series "debug_pagealloc improvements":
        mm, debug_pagelloc: use static keys to enable debugging
        mm, page_alloc: more extensive free page checking with debug_pagealloc
        mm, debug_pagealloc: use a page type instead of page_ext flag

  mm:pagecache:
      Patch series "fix filler_t callback type mismatches", v2:
        mm/filemap.c: fix an overly long line in read_cache_page
        mm/filemap: don't cast ->readpage to filler_t for do_read_cache_page
        jffs2: pass the correct prototype to read_cache_page
        9p: pass the correct prototype to read_cache_page
      mm/filemap.c: correct the comment about VM_FAULT_RETRY

  mm:swap:
      mm, swap: fix race between swapoff and some swap operations
      mm/swap_state.c: simplify total_swapcache_pages() with get_swap_device()
      mm, swap: use rbtree for swap_extent
      mm/mincore.c: fix race between swapoff and mincore

  mm:memcg:
      memcg, oom: no oom-kill for __GFP_RETRY_MAYFAIL
      memcg, fsnotify: no oom-kill for remote memcg charging
      mm, memcg: introduce memory.events.local
      mm: memcontrol: dump memory.stat during cgroup OOM
      Patch series "mm: reparent slab memory on cgroup removal", v7:
        mm: memcg/slab: postpone kmem_cache memcg pointer initialization to memcg_link_cache()
        mm: memcg/slab: rename slab delayed deactivation functions and fields
        mm: memcg/slab: generalize postponed non-root kmem_cache deactivation
        mm: memcg/slab: introduce __memcg_kmem_uncharge_memcg()
        mm: memcg/slab: unify SLAB and SLUB page accounting
        mm: memcg/slab: don't check the dying flag on kmem_cache creation
        mm: memcg/slab: synchronize access to kmem_cache dying flag using a spinlock
        mm: memcg/slab: rework non-root kmem_cache lifecycle management
        mm: memcg/slab: stop setting page->mem_cgroup pointer for slab pages
        mm: memcg/slab: reparent memcg kmem_caches on cgroup removal
      mm, memcg: add a memcg_slabinfo debugfs file

  mm:gup:
      Patch series "switch the remaining architectures to use generic GUP", v4:
        mm: use untagged_addr() for get_user_pages_fast addresses
        mm: simplify gup_fast_permitted
        mm: lift the x86_32 PAE version of gup_get_pte to common code
        MIPS: use the generic get_user_pages_fast code
        sh: add the missing pud_page definition
        sh: use the generic get_user_pages_fast code
        sparc64: add the missing pgd_page definition
        sparc64: define untagged_addr()
        sparc64: use the generic get_user_pages_fast code
        mm: rename CONFIG_HAVE_GENERIC_GUP to CONFIG_HAVE_FAST_GUP
        mm: reorder code blocks in gup.c
        mm: consolidate the get_user_pages* implementations
        mm: validate get_user_pages_fast flags
        mm: move the powerpc hugepd code to mm/gup.c
        mm: switch gup_hugepte to use try_get_compound_head
        mm: mark the page referenced in gup_hugepte
      mm/gup: speed up check_and_migrate_cma_pages() on huge page
      mm/gup.c: remove some BUG_ONs from get_gate_page()
      mm/gup.c: mark undo_dev_pagemap as __maybe_unused

  mm:pagemap:
      asm-generic, x86: introduce generic pte_{alloc,free}_one[_kernel]
      alpha: switch to generic version of pte allocation
      arm: switch to generic version of pte allocation
      arm64: switch to generic version of pte allocation
      csky: switch to generic version of pte allocation
      m68k: sun3: switch to generic version of pte allocation
      mips: switch to generic version of pte allocation
      nds32: switch to generic version of pte allocation
      nios2: switch to generic version of pte allocation
      parisc: switch to generic version of pte allocation
      riscv: switch to generic version of pte allocation
      um: switch to generic version of pte allocation
      unicore32: switch to generic version of pte allocation
      mm/pgtable: drop pgtable_t variable from pte_fn_t functions
      mm/memory.c: fail when offset == num in first check of __vm_map_pages()

  mm:infrastructure:
      mm/mmu_notifier: use hlist_add_head_rcu()

  mm:vmalloc:
      Patch series "Some cleanups for the KVA/vmalloc", v5:
        mm/vmalloc.c: remove "node" argument
        mm/vmalloc.c: preload a CPU with one object for split purpose
        mm/vmalloc.c: get rid of one single unlink_va() when merge
        mm/vmalloc.c: switch to WARN_ON() and move it under unlink_va()
      mm/vmalloc.c: spelling> s/informaion/information/

  mm:initialization:
      mm/large system hash: use vmalloc for size > MAX_ORDER when !hashdist
      mm/large system hash: clear hashdist when only one node with memory is booted

  mm:pagealloc:
      arm64: move jump_label_init() before parse_early_param()
      Patch series "add init_on_alloc/init_on_free boot options", v10:
        mm: security: introduce init_on_alloc=1 and init_on_free=1 boot options
        mm: init: report memory auto-initialization features at boot time

  mm:vmscan:
      mm: vmscan: remove double slab pressure by inc'ing sc->nr_scanned
      mm: vmscan: correct some vmscan counters for THP swapout

  mm:tools:
      tools/vm/slabinfo: order command line options
      tools/vm/slabinfo: add partial slab listing to -X
      tools/vm/slabinfo: add option to sort by partial slabs
      tools/vm/slabinfo: add sorting info to help menu

  mm:proc:
      proc: use down_read_killable mmap_sem for /proc/pid/maps
      proc: use down_read_killable mmap_sem for /proc/pid/smaps_rollup
      proc: use down_read_killable mmap_sem for /proc/pid/pagemap
      proc: use down_read_killable mmap_sem for /proc/pid/clear_refs
      proc: use down_read_killable mmap_sem for /proc/pid/map_files
      mm: use down_read_killable for locking mmap_sem in access_remote_vm
      mm: smaps: split PSS into components
      mm: vmalloc: show number of vmalloc pages in /proc/meminfo

  mm:ras:
      mm/memory-failure.c: clarify error message

  mm:oom-kill:
      mm: memcontrol: use CSS_TASK_ITER_PROCS at mem_cgroup_scan_tasks()
      mm, oom: refactor dump_tasks for memcg OOMs
      mm, oom: remove redundant task_in_mem_cgroup() check
      oom: decouple mems_allowed from oom_unkillable_task
      mm/oom_kill.c: remove redundant OOM score normalization in select_bad_process()"

* akpm: (147 commits)
  mm/oom_kill.c: remove redundant OOM score normalization in select_bad_process()
  oom: decouple mems_allowed from oom_unkillable_task
  mm, oom: remove redundant task_in_mem_cgroup() check
  mm, oom: refactor dump_tasks for memcg OOMs
  mm: memcontrol: use CSS_TASK_ITER_PROCS at mem_cgroup_scan_tasks()
  mm/memory-failure.c: clarify error message
  mm: vmalloc: show number of vmalloc pages in /proc/meminfo
  mm: smaps: split PSS into components
  mm: use down_read_killable for locking mmap_sem in access_remote_vm
  proc: use down_read_killable mmap_sem for /proc/pid/map_files
  proc: use down_read_killable mmap_sem for /proc/pid/clear_refs
  proc: use down_read_killable mmap_sem for /proc/pid/pagemap
  proc: use down_read_killable mmap_sem for /proc/pid/smaps_rollup
  proc: use down_read_killable mmap_sem for /proc/pid/maps
  tools/vm/slabinfo: add sorting info to help menu
  tools/vm/slabinfo: add option to sort by partial slabs
  tools/vm/slabinfo: add partial slab listing to -X
  tools/vm/slabinfo: order command line options
  mm: vmscan: correct some vmscan counters for THP swapout
  mm: vmscan: remove double slab pressure by inc'ing sc->nr_scanned
  ...

1 files changed, 70 insertions, 61 deletions

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index f719b64741d6..eda2e2a0bdc6 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -64,21 +64,33 @@ int sysctl_oom_dump_tasks = 1;
  */
 DEFINE_MUTEX(oom_lock);
 
+static inline bool is_memcg_oom(struct oom_control *oc)
+{
+	return oc->memcg != NULL;
+}
+
 #ifdef CONFIG_NUMA
 /**
- * has_intersects_mems_allowed() - check task eligiblity for kill
+ * oom_cpuset_eligible() - check task eligiblity for kill
  * @start: task struct of which task to consider
  * @mask: nodemask passed to page allocator for mempolicy ooms
  *
  * Task eligibility is determined by whether or not a candidate task, @tsk,
  * shares the same mempolicy nodes as current if it is bound by such a policy
  * and whether or not it has the same set of allowed cpuset nodes.
+ *
+ * This function is assuming oom-killer context and 'current' has triggered
+ * the oom-killer.
  */
-static bool has_intersects_mems_allowed(struct task_struct *start,
-					const nodemask_t *mask)
+static bool oom_cpuset_eligible(struct task_struct *start,
+				struct oom_control *oc)
 {
 	struct task_struct *tsk;
 	bool ret = false;
+	const nodemask_t *mask = oc->nodemask;
+
+	if (is_memcg_oom(oc))
+		return true;
 
 	rcu_read_lock();
 	for_each_thread(start, tsk) {
@@ -105,8 +117,7 @@ static bool has_intersects_mems_allowed(struct task_struct *start,
 	return ret;
 }
 #else
-static bool has_intersects_mems_allowed(struct task_struct *tsk,
-					const nodemask_t *mask)
+static bool oom_cpuset_eligible(struct task_struct *tsk, struct oom_control *oc)
 {
 	return true;
 }
@@ -146,28 +157,13 @@ static inline bool is_sysrq_oom(struct oom_control *oc)
 	return oc->order == -1;
 }
 
-static inline bool is_memcg_oom(struct oom_control *oc)
-{
-	return oc->memcg != NULL;
-}
-
 /* return true if the task is not adequate as candidate victim task. */
-static bool oom_unkillable_task(struct task_struct *p,
-		struct mem_cgroup *memcg, const nodemask_t *nodemask)
+static bool oom_unkillable_task(struct task_struct *p)
 {
 	if (is_global_init(p))
 		return true;
 	if (p->flags & PF_KTHREAD)
 		return true;
-
-	/* When mem_cgroup_out_of_memory() and p is not member of the group */
-	if (memcg && !task_in_mem_cgroup(p, memcg))
-		return true;
-
-	/* p may not have freeable memory in nodemask */
-	if (!has_intersects_mems_allowed(p, nodemask))
-		return true;
-
 	return false;
 }
 
@@ -194,20 +190,17 @@ static bool is_dump_unreclaim_slabs(void)
  * oom_badness - heuristic function to determine which candidate task to kill
  * @p: task struct of which task we should calculate
  * @totalpages: total present RAM allowed for page allocation
- * @memcg: task's memory controller, if constrained
- * @nodemask: nodemask passed to page allocator for mempolicy ooms
  *
  * The heuristic for determining which task to kill is made to be as simple and
  * predictable as possible.  The goal is to return the highest value for the
  * task consuming the most memory to avoid subsequent oom failures.
  */
-unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
-			  const nodemask_t *nodemask, unsigned long totalpages)
+unsigned long oom_badness(struct task_struct *p, unsigned long totalpages)
 {
 	long points;
 	long adj;
 
-	if (oom_unkillable_task(p, memcg, nodemask))
+	if (oom_unkillable_task(p))
 		return 0;
 
 	p = find_lock_task_mm(p);
@@ -318,7 +311,11 @@ static int oom_evaluate_task(struct task_struct *task, void *arg)
 	struct oom_control *oc = arg;
 	unsigned long points;
 
-	if (oom_unkillable_task(task, NULL, oc->nodemask))
+	if (oom_unkillable_task(task))
+		goto next;
+
+	/* p may not have freeable memory in nodemask */
+	if (!is_memcg_oom(oc) && !oom_cpuset_eligible(task, oc))
 		goto next;
 
 	/*
@@ -342,13 +339,10 @@ static int oom_evaluate_task(struct task_struct *task, void *arg)
 		goto select;
 	}
 
-	points = oom_badness(task, NULL, oc->nodemask, oc->totalpages);
+	points = oom_badness(task, oc->totalpages);
 	if (!points || points < oc->chosen_points)
 		goto next;
 
-	/* Prefer thread group leaders for display purposes */
-	if (points == oc->chosen_points && thread_group_leader(oc->chosen))
-		goto next;
 select:
 	if (oc->chosen)
 		put_task_struct(oc->chosen);
@@ -381,14 +375,44 @@ static void select_bad_process(struct oom_control *oc)
 				break;
 		rcu_read_unlock();
 	}
+}
 
-	oc->chosen_points = oc->chosen_points * 1000 / oc->totalpages;
+static int dump_task(struct task_struct *p, void *arg)
+{
+	struct oom_control *oc = arg;
+	struct task_struct *task;
+
+	if (oom_unkillable_task(p))
+		return 0;
+
+	/* p may not have freeable memory in nodemask */
+	if (!is_memcg_oom(oc) && !oom_cpuset_eligible(p, oc))
+		return 0;
+
+	task = find_lock_task_mm(p);
+	if (!task) {
+		/*
+		 * This is a kthread or all of p's threads have already
+		 * detached their mm's.  There's no need to report
+		 * them; they can't be oom killed anyway.
+		 */
+		return 0;
+	}
+
+	pr_info("[%7d] %5d %5d %8lu %8lu %8ld %8lu         %5hd %s\n",
+		task->pid, from_kuid(&init_user_ns, task_uid(task)),
+		task->tgid, task->mm->total_vm, get_mm_rss(task->mm),
+		mm_pgtables_bytes(task->mm),
+		get_mm_counter(task->mm, MM_SWAPENTS),
+		task->signal->oom_score_adj, task->comm);
+	task_unlock(task);
+
+	return 0;
 }
 
 /**
  * dump_tasks - dump current memory state of all system tasks
- * @memcg: current's memory controller, if constrained
- * @nodemask: nodemask passed to page allocator for mempolicy ooms
+ * @oc: pointer to struct oom_control
  *
  * 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
@@ -396,37 +420,21 @@ static void select_bad_process(struct oom_control *oc)
  * State information includes task's pid, uid, tgid, vm size, rss,
  * pgtables_bytes, swapents, oom_score_adj value, and name.
  */
-static void dump_tasks(struct mem_cgroup *memcg, const nodemask_t *nodemask)
+static void dump_tasks(struct oom_control *oc)
 {
-	struct task_struct *p;
-	struct task_struct *task;
-
 	pr_info("Tasks state (memory values in pages):\n");
 	pr_info("[  pid  ]   uid  tgid total_vm      rss pgtables_bytes swapents oom_score_adj name\n");
-	rcu_read_lock();
-	for_each_process(p) {
-		if (oom_unkillable_task(p, memcg, nodemask))
-			continue;
 
-		task = find_lock_task_mm(p);
-		if (!task) {
-			/*
-			 * This is a kthread or all of p's threads have already
-			 * detached their mm's.  There's no need to report
-			 * them; they can't be oom killed anyway.
-			 */
-			continue;
-		}
+	if (is_memcg_oom(oc))
+		mem_cgroup_scan_tasks(oc->memcg, dump_task, oc);
+	else {
+		struct task_struct *p;
 
-		pr_info("[%7d] %5d %5d %8lu %8lu %8ld %8lu         %5hd %s\n",
-			task->pid, from_kuid(&init_user_ns, task_uid(task)),
-			task->tgid, task->mm->total_vm, get_mm_rss(task->mm),
-			mm_pgtables_bytes(task->mm),
-			get_mm_counter(task->mm, MM_SWAPENTS),
-			task->signal->oom_score_adj, task->comm);
-		task_unlock(task);
+		rcu_read_lock();
+		for_each_process(p)
+			dump_task(p, oc);
+		rcu_read_unlock();
 	}
-	rcu_read_unlock();
 }
 
 static void dump_oom_summary(struct oom_control *oc, struct task_struct *victim)
@@ -458,7 +466,7 @@ static void dump_header(struct oom_control *oc, struct task_struct *p)
 			dump_unreclaimable_slab();
 	}
 	if (sysctl_oom_dump_tasks)
-		dump_tasks(oc->memcg, oc->nodemask);
+		dump_tasks(oc);
 	if (p)
 		dump_oom_summary(oc, p);
 }
@@ -1075,7 +1083,8 @@ bool out_of_memory(struct oom_control *oc)
 	check_panic_on_oom(oc);
 
 	if (!is_memcg_oom(oc) && sysctl_oom_kill_allocating_task &&
-	    current->mm && !oom_unkillable_task(current, NULL, oc->nodemask) &&
+	    current->mm && !oom_unkillable_task(current) &&
+	    oom_cpuset_eligible(current, oc) &&
 	    current->signal->oom_score_adj != OOM_SCORE_ADJ_MIN) {
 		get_task_struct(current);
 		oc->chosen = current;