Merge branch 'akpm' (patches from Andrew)

Merge misc updates and fixes from Andrew Morton:

 - late-breaking ocfs2 updates

 - random bunch of fixes

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  mm: disable DEFERRED_STRUCT_PAGE_INIT on !NO_BOOTMEM
  mm/memcontrol.c: move comments for get_mctgt_type() to proper position
  mm/memcontrol.c: fix the margin computation in mem_cgroup_margin()
  mm/cma: silence warnings due to max() usage
  mm: thp: avoid false positive VM_BUG_ON_PAGE in page_move_anon_rmap()
  oom_reaper: close race with exiting task
  mm: use early_pfn_to_nid in register_page_bootmem_info_node
  mm: use early_pfn_to_nid in page_ext_init
  MAINTAINERS: Kdump maintainers update
  MAINTAINERS: add kexec_core.c and kexec_file.c
  mm: oom: do not reap task if there are live threads in threadgroup
  direct-io: fix direct write stale data exposure from concurrent buffered read
  ocfs2: bump up o2cb network protocol version
  ocfs2: o2hb: fix hb hung time
  ocfs2: o2hb: don't negotiate if last hb fail
  ocfs2: o2hb: add some user/debug log
  ocfs2: o2hb: add NEGOTIATE_APPROVE message
  ocfs2: o2hb: add NEGO_TIMEOUT message
  ocfs2: o2hb: add negotiate timer

7 files changed, 56 insertions, 32 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index 22fa8189e4fc..3e2daef3c946 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -648,7 +648,7 @@ config DEFERRED_STRUCT_PAGE_INIT
 	bool "Defer initialisation of struct pages to kthreads"
 	default n
 	depends on ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
-	depends on MEMORY_HOTPLUG
+	depends on NO_BOOTMEM && MEMORY_HOTPLUG
 	depends on !FLATMEM
 	help
 	  Ordinarily all struct pages are initialised during early boot in a
diff --git a/mm/cma.c b/mm/cma.c
index ea506eb18cd6..bd0e1412475e 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -183,7 +183,8 @@ int __init cma_init_reserved_mem(phys_addr_t base, phys_addr_t size,
 		return -EINVAL;
 
 	/* ensure minimal alignment required by mm core */
-	alignment = PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order);
+	alignment = PAGE_SIZE <<
+			max_t(unsigned long, MAX_ORDER - 1, pageblock_order);
 
 	/* alignment should be aligned with order_per_bit */
 	if (!IS_ALIGNED(alignment >> PAGE_SHIFT, 1 << order_per_bit))
@@ -266,8 +267,8 @@ int __init cma_declare_contiguous(phys_addr_t base,
 	 * migratetype page by page allocator's buddy algorithm. In the case,
 	 * you couldn't get a contiguous memory, which is not what we want.
 	 */
-	alignment = max(alignment,
-		(phys_addr_t)PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order));
+	alignment = max(alignment,  (phys_addr_t)PAGE_SIZE <<
+			  max_t(unsigned long, MAX_ORDER - 1, pageblock_order));
 	base = ALIGN(base, alignment);
 	size = ALIGN(size, alignment);
 	limit &= ~(alignment - 1);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index f6477a9dbe7a..925b431f3f03 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1108,6 +1108,8 @@ static unsigned long mem_cgroup_margin(struct mem_cgroup *memcg)
 		limit = READ_ONCE(memcg->memsw.limit);
 		if (count <= limit)
 			margin = min(margin, limit - count);
+		else
+			margin = 0;
 	}
 
 	return margin;
@@ -4307,24 +4309,6 @@ static int mem_cgroup_do_precharge(unsigned long count)
 	return 0;
 }
 
-/**
- * get_mctgt_type - get target type of moving charge
- * @vma: the vma the pte to be checked belongs
- * @addr: the address corresponding to the pte to be checked
- * @ptent: the pte to be checked
- * @target: the pointer the target page or swap ent will be stored(can be NULL)
- *
- * Returns
- *   0(MC_TARGET_NONE): if the pte is not a target for move charge.
- *   1(MC_TARGET_PAGE): if the page corresponding to this pte is a target for
- *     move charge. if @target is not NULL, the page is stored in target->page
- *     with extra refcnt got(Callers should handle it).
- *   2(MC_TARGET_SWAP): if the swap entry corresponding to this pte is a
- *     target for charge migration. if @target is not NULL, the entry is stored
- *     in target->ent.
- *
- * Called with pte lock held.
- */
 union mc_target {
 	struct page	*page;
 	swp_entry_t	ent;
@@ -4513,6 +4497,25 @@ out:
 	return ret;
 }
 
+/**
+ * get_mctgt_type - get target type of moving charge
+ * @vma: the vma the pte to be checked belongs
+ * @addr: the address corresponding to the pte to be checked
+ * @ptent: the pte to be checked
+ * @target: the pointer the target page or swap ent will be stored(can be NULL)
+ *
+ * Returns
+ *   0(MC_TARGET_NONE): if the pte is not a target for move charge.
+ *   1(MC_TARGET_PAGE): if the page corresponding to this pte is a target for
+ *     move charge. if @target is not NULL, the page is stored in target->page
+ *     with extra refcnt got(Callers should handle it).
+ *   2(MC_TARGET_SWAP): if the swap entry corresponding to this pte is a
+ *     target for charge migration. if @target is not NULL, the entry is stored
+ *     in target->ent.
+ *
+ * Called with pte lock held.
+ */
+
 static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma,
 		unsigned long addr, pte_t ptent, union mc_target *target)
 {
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index caf2a14c37ad..b8ee0806415f 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -300,7 +300,7 @@ void register_page_bootmem_info_node(struct pglist_data *pgdat)
 		 * multiple nodes we check that this pfn does not already
 		 * reside in some other nodes.
 		 */
-		if (pfn_valid(pfn) && (pfn_to_nid(pfn) == node))
+		if (pfn_valid(pfn) && (early_pfn_to_nid(pfn) == node))
 			register_page_bootmem_info_section(pfn);
 	}
 }
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 5bb2f7698ad7..dfb1ab61fb23 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -443,13 +443,29 @@ static bool __oom_reap_task(struct task_struct *tsk)
 {
 	struct mmu_gather tlb;
 	struct vm_area_struct *vma;
-	struct mm_struct *mm;
+	struct mm_struct *mm = NULL;
 	struct task_struct *p;
 	struct zap_details details = {.check_swap_entries = true,
 				      .ignore_dirty = true};
 	bool ret = true;
 
 	/*
+	 * We have to make sure to not race with the victim exit path
+	 * and cause premature new oom victim selection:
+	 * __oom_reap_task		exit_mm
+	 *   atomic_inc_not_zero
+	 *				  mmput
+	 *				    atomic_dec_and_test
+	 *				  exit_oom_victim
+	 *				[...]
+	 *				out_of_memory
+	 *				  select_bad_process
+	 *				    # no TIF_MEMDIE task selects new victim
+	 *  unmap_page_range # frees some memory
+	 */
+	mutex_lock(&oom_lock);
+
+	/*
 	 * Make sure we find the associated mm_struct even when the particular
 	 * thread has already terminated and cleared its mm.
 	 * We might have race with exit path so consider our work done if there
@@ -457,19 +473,19 @@ static bool __oom_reap_task(struct task_struct *tsk)
 	 */
 	p = find_lock_task_mm(tsk);
 	if (!p)
-		return true;
+		goto unlock_oom;
 
 	mm = p->mm;
 	if (!atomic_inc_not_zero(&mm->mm_users)) {
 		task_unlock(p);
-		return true;
+		goto unlock_oom;
 	}
 
 	task_unlock(p);
 
 	if (!down_read_trylock(&mm->mmap_sem)) {
 		ret = false;
-		goto out;
+		goto unlock_oom;
 	}
 
 	tlb_gather_mmu(&tlb, mm, 0, -1);
@@ -511,13 +527,15 @@ static bool __oom_reap_task(struct task_struct *tsk)
 	 * to release its memory.
 	 */
 	set_bit(MMF_OOM_REAPED, &mm->flags);
-out:
+unlock_oom:
+	mutex_unlock(&oom_lock);
 	/*
 	 * Drop our reference but make sure the mmput slow path is called from a
 	 * different context because we shouldn't risk we get stuck there and
 	 * put the oom_reaper out of the way.
 	 */
-	mmput_async(mm);
+	if (mm)
+		mmput_async(mm);
 	return ret;
 }
 
@@ -611,8 +629,6 @@ void try_oom_reaper(struct task_struct *tsk)
 
 			if (!process_shares_mm(p, mm))
 				continue;
-			if (same_thread_group(p, tsk))
-				continue;
 			if (fatal_signal_pending(p))
 				continue;
 
diff --git a/mm/page_ext.c b/mm/page_ext.c
index 2d864e64f7fe..44a4c029c8e7 100644
--- a/mm/page_ext.c
+++ b/mm/page_ext.c
@@ -390,8 +390,10 @@ void __init page_ext_init(void)
 			 * We know some arch can have a nodes layout such as
 			 * -------------pfn-------------->
 			 * N0 | N1 | N2 | N0 | N1 | N2|....
+			 *
+			 * Take into account DEFERRED_STRUCT_PAGE_INIT.
 			 */
-			if (pfn_to_nid(pfn) != nid)
+			if (early_pfn_to_nid(pfn) != nid)
 				continue;
 			if (init_section_page_ext(pfn, nid))
 				goto oom;
diff --git a/mm/rmap.c b/mm/rmap.c
index 8a839935b18c..0ea5d9071b32 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1098,6 +1098,8 @@ void page_move_anon_rmap(struct page *page,
 
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 	VM_BUG_ON_VMA(!anon_vma, vma);
+	if (IS_ENABLED(CONFIG_DEBUG_VM) && PageTransHuge(page))
+		address &= HPAGE_PMD_MASK;
 	VM_BUG_ON_PAGE(page->index != linear_page_index(vma, address), page);
 
 	anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON;