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

MAINTAINERS

@@ -6421,8 +6421,9 @@ F:	Documentation/kbuild/kconfig-language.txt
 F:	scripts/kconfig/
 
 KDUMP
-M:	Vivek Goyal <vgoyal@redhat.com>
+M:	Dave Young <dyoung@redhat.com>
-M:	Haren Myneni <hbabu@us.ibm.com>
+M:	Baoquan He <bhe@redhat.com>
+R:	Vivek Goyal <vgoyal@redhat.com>
 L:	kexec@lists.infradead.org
 W:	http://lse.sourceforge.net/kdump/
 S:	Maintained
@@ -6568,7 +6569,7 @@ L:	kexec@lists.infradead.org
 S:	Maintained
 F:	include/linux/kexec.h
 F:	include/uapi/linux/kexec.h
-F:	kernel/kexec.c
+F:	kernel/kexec*
 
 KEYS/KEYRINGS:
 M:	David Howells <dhowells@redhat.com>

fs/direct-io.c

@@ -628,11 +628,11 @@ static int get_more_blocks(struct dio *dio, struct dio_submit *sdio,
 		map_bh->b_size = fs_count << i_blkbits;
 
 		/*
-		 * For writes inside i_size on a DIO_SKIP_HOLES filesystem we
+		 * For writes that could fill holes inside i_size on a
-		 * forbid block creations: only overwrites are permitted.
+		 * DIO_SKIP_HOLES filesystem we forbid block creations: only
-		 * We will return early to the caller once we see an
+		 * overwrites are permitted. We will return early to the caller
-		 * unmapped buffer head returned, and the caller will fall
+		 * once we see an unmapped buffer head returned, and the caller
-		 * back to buffered I/O.
+		 * will fall back to buffered I/O.
 		 *
 		 * Otherwise the decision is left to the get_blocks method,
 		 * which may decide to handle it or also return an unmapped
@@ -640,8 +640,8 @@ static int get_more_blocks(struct dio *dio, struct dio_submit *sdio,
 		 */
 		create = dio->rw & WRITE;
 		if (dio->flags & DIO_SKIP_HOLES) {
-			if (sdio->block_in_file < (i_size_read(dio->inode) >>
+			if (fs_startblk <= ((i_size_read(dio->inode) - 1) >>
-							sdio->blkbits))
+							i_blkbits))
 				create = 0;
 		}
 

fs/ocfs2/cluster/heartbeat.c

@@ -272,10 +272,21 @@ struct o2hb_region {
 	struct delayed_work	hr_write_timeout_work;
 	unsigned long		hr_last_timeout_start;
 
+	/* negotiate timer, used to negotiate extending hb timeout. */
+	struct delayed_work	hr_nego_timeout_work;
+	unsigned long		hr_nego_node_bitmap[BITS_TO_LONGS(O2NM_MAX_NODES)];
+
 	/* Used during o2hb_check_slot to hold a copy of the block
 	 * being checked because we temporarily have to zero out the
 	 * crc field. */
 	struct o2hb_disk_heartbeat_block *hr_tmp_block;
+
+	/* Message key for negotiate timeout message. */
+	unsigned int		hr_key;
+	struct list_head	hr_handler_list;
+
+	/* last hb status, 0 for success, other value for error. */
+	int			hr_last_hb_status;
 };
 
 struct o2hb_bio_wait_ctxt {
@@ -284,6 +295,17 @@ struct o2hb_bio_wait_ctxt {
 	int               wc_error;
 };
 
+#define O2HB_NEGO_TIMEOUT_MS (O2HB_MAX_WRITE_TIMEOUT_MS/2)
+
+enum {
+	O2HB_NEGO_TIMEOUT_MSG = 1,
+	O2HB_NEGO_APPROVE_MSG = 2,
+};
+
+struct o2hb_nego_msg {
+	u8 node_num;
+};
+
 static void o2hb_write_timeout(struct work_struct *work)
 {
 	int failed, quorum;
@@ -319,7 +341,7 @@ static void o2hb_write_timeout(struct work_struct *work)
 	o2quo_disk_timeout();
 }
 
-static void o2hb_arm_write_timeout(struct o2hb_region *reg)
+static void o2hb_arm_timeout(struct o2hb_region *reg)
 {
 	/* Arm writeout only after thread reaches steady state */
 	if (atomic_read(&reg->hr_steady_iterations) != 0)
@@ -334,14 +356,132 @@ static void o2hb_arm_write_timeout(struct o2hb_region *reg)
 		spin_unlock(&o2hb_live_lock);
 	}
 	cancel_delayed_work(&reg->hr_write_timeout_work);
-	reg->hr_last_timeout_start = jiffies;
 	schedule_delayed_work(&reg->hr_write_timeout_work,
 			      msecs_to_jiffies(O2HB_MAX_WRITE_TIMEOUT_MS));
+
+	cancel_delayed_work(&reg->hr_nego_timeout_work);
+	/* negotiate timeout must be less than write timeout. */
+	schedule_delayed_work(&reg->hr_nego_timeout_work,
+			      msecs_to_jiffies(O2HB_NEGO_TIMEOUT_MS));
+	memset(reg->hr_nego_node_bitmap, 0, sizeof(reg->hr_nego_node_bitmap));
 }
 
-static void o2hb_disarm_write_timeout(struct o2hb_region *reg)
+static void o2hb_disarm_timeout(struct o2hb_region *reg)
 {
 	cancel_delayed_work_sync(&reg->hr_write_timeout_work);
+	cancel_delayed_work_sync(&reg->hr_nego_timeout_work);
+}
+
+static int o2hb_send_nego_msg(int key, int type, u8 target)
+{
+	struct o2hb_nego_msg msg;
+	int status, ret;
+
+	msg.node_num = o2nm_this_node();
+again:
+	ret = o2net_send_message(type, key, &msg, sizeof(msg),
+			target, &status);
+
+	if (ret == -EAGAIN || ret == -ENOMEM) {
+		msleep(100);
+		goto again;
+	}
+
+	return ret;
+}
+
+static void o2hb_nego_timeout(struct work_struct *work)
+{
+	unsigned long live_node_bitmap[BITS_TO_LONGS(O2NM_MAX_NODES)];
+	int master_node, i, ret;
+	struct o2hb_region *reg;
+
+	reg = container_of(work, struct o2hb_region, hr_nego_timeout_work.work);
+	/* don't negotiate timeout if last hb failed since it is very
+	 * possible io failed. Should let write timeout fence self.
+	 */
+	if (reg->hr_last_hb_status)
+		return;
+
+	o2hb_fill_node_map(live_node_bitmap, sizeof(live_node_bitmap));
+	/* lowest node as master node to make negotiate decision. */
+	master_node = find_next_bit(live_node_bitmap, O2NM_MAX_NODES, 0);
+
+	if (master_node == o2nm_this_node()) {
+		if (!test_bit(master_node, reg->hr_nego_node_bitmap)) {
+			printk(KERN_NOTICE "o2hb: node %d hb write hung for %ds on region %s (%s).\n",
+				o2nm_this_node(), O2HB_NEGO_TIMEOUT_MS/1000,
+				config_item_name(&reg->hr_item), reg->hr_dev_name);
+			set_bit(master_node, reg->hr_nego_node_bitmap);
+		}
+		if (memcmp(reg->hr_nego_node_bitmap, live_node_bitmap,
+				sizeof(reg->hr_nego_node_bitmap))) {
+			/* check negotiate bitmap every second to do timeout
+			 * approve decision.
+			 */
+			schedule_delayed_work(&reg->hr_nego_timeout_work,
+				msecs_to_jiffies(1000));
+
+			return;
+		}
+
+		printk(KERN_NOTICE "o2hb: all nodes hb write hung, maybe region %s (%s) is down.\n",
+			config_item_name(&reg->hr_item), reg->hr_dev_name);
+		/* approve negotiate timeout request. */
+		o2hb_arm_timeout(reg);
+
+		i = -1;
+		while ((i = find_next_bit(live_node_bitmap,
+				O2NM_MAX_NODES, i + 1)) < O2NM_MAX_NODES) {
+			if (i == master_node)
+				continue;
+
+			mlog(ML_HEARTBEAT, "send NEGO_APPROVE msg to node %d\n", i);
+			ret = o2hb_send_nego_msg(reg->hr_key,
+					O2HB_NEGO_APPROVE_MSG, i);
+			if (ret)
+				mlog(ML_ERROR, "send NEGO_APPROVE msg to node %d fail %d\n",
+					i, ret);
+		}
+	} else {
+		/* negotiate timeout with master node. */
+		printk(KERN_NOTICE "o2hb: node %d hb write hung for %ds on region %s (%s), negotiate timeout with node %d.\n",
+			o2nm_this_node(), O2HB_NEGO_TIMEOUT_MS/1000, config_item_name(&reg->hr_item),
+			reg->hr_dev_name, master_node);
+		ret = o2hb_send_nego_msg(reg->hr_key, O2HB_NEGO_TIMEOUT_MSG,
+				master_node);
+		if (ret)
+			mlog(ML_ERROR, "send NEGO_TIMEOUT msg to node %d fail %d\n",
+				master_node, ret);
+	}
+}
+
+static int o2hb_nego_timeout_handler(struct o2net_msg *msg, u32 len, void *data,
+				void **ret_data)
+{
+	struct o2hb_region *reg = data;
+	struct o2hb_nego_msg *nego_msg;
+
+	nego_msg = (struct o2hb_nego_msg *)msg->buf;
+	printk(KERN_NOTICE "o2hb: receive negotiate timeout message from node %d on region %s (%s).\n",
+		nego_msg->node_num, config_item_name(&reg->hr_item), reg->hr_dev_name);
+	if (nego_msg->node_num < O2NM_MAX_NODES)
+		set_bit(nego_msg->node_num, reg->hr_nego_node_bitmap);
+	else
+		mlog(ML_ERROR, "got nego timeout message from bad node.\n");
+
+	return 0;
+}
+
+static int o2hb_nego_approve_handler(struct o2net_msg *msg, u32 len, void *data,
+				void **ret_data)
+{
+	struct o2hb_region *reg = data;
+
+	printk(KERN_NOTICE "o2hb: negotiate timeout approved by master node on region %s (%s).\n",
+		config_item_name(&reg->hr_item), reg->hr_dev_name);
+	o2hb_arm_timeout(reg);
+	return 0;
 }
 
 static inline void o2hb_bio_wait_init(struct o2hb_bio_wait_ctxt *wc)
@@ -1032,7 +1172,8 @@ static int o2hb_do_disk_heartbeat(struct o2hb_region *reg)
 	/* Skip disarming the timeout if own slot has stale/bad data */
 	if (own_slot_ok) {
 		o2hb_set_quorum_device(reg);
-		o2hb_arm_write_timeout(reg);
+		o2hb_arm_timeout(reg);
+		reg->hr_last_timeout_start = jiffies;
 	}
 
 bail:
@@ -1096,6 +1237,7 @@ static int o2hb_thread(void *data)
 		before_hb = ktime_get_real();
 
 		ret = o2hb_do_disk_heartbeat(reg);
+		reg->hr_last_hb_status = ret;
 
 		after_hb = ktime_get_real();
 
@@ -1114,7 +1256,7 @@ static int o2hb_thread(void *data)
 		}
 	}
 
-	o2hb_disarm_write_timeout(reg);
+	o2hb_disarm_timeout(reg);
 
 	/* unclean stop is only used in very bad situation */
 	for(i = 0; !reg->hr_unclean_stop && i < reg->hr_blocks; i++)
@@ -1451,6 +1593,7 @@ static void o2hb_region_release(struct config_item *item)
 	list_del(&reg->hr_all_item);
 	spin_unlock(&o2hb_live_lock);
 
+	o2net_unregister_handler_list(&reg->hr_handler_list);
 	kfree(reg);
 }
 
@@ -1762,6 +1905,7 @@ static ssize_t o2hb_region_dev_store(struct config_item *item,
 	}
 
 	INIT_DELAYED_WORK(&reg->hr_write_timeout_work, o2hb_write_timeout);
+	INIT_DELAYED_WORK(&reg->hr_nego_timeout_work, o2hb_nego_timeout);
 
 	/*
 	 * A node is considered live after it has beat LIVE_THRESHOLD
@@ -1995,13 +2139,37 @@ static struct config_item *o2hb_heartbeat_group_make_item(struct config_group *g
 
 	config_item_init_type_name(&reg->hr_item, name, &o2hb_region_type);
 
+	/* this is the same way to generate msg key as dlm, for local heartbeat,
+	 * name is also the same, so make initial crc value different to avoid
+	 * message key conflict.
+	 */
+	reg->hr_key = crc32_le(reg->hr_region_num + O2NM_MAX_REGIONS,
+		name, strlen(name));
+	INIT_LIST_HEAD(&reg->hr_handler_list);
+	ret = o2net_register_handler(O2HB_NEGO_TIMEOUT_MSG, reg->hr_key,
+			sizeof(struct o2hb_nego_msg),
+			o2hb_nego_timeout_handler,
+			reg, NULL, &reg->hr_handler_list);
+	if (ret)
+		goto free;
+
+	ret = o2net_register_handler(O2HB_NEGO_APPROVE_MSG, reg->hr_key,
+			sizeof(struct o2hb_nego_msg),
+			o2hb_nego_approve_handler,
+			reg, NULL, &reg->hr_handler_list);
+	if (ret)
+		goto unregister_handler;
+
 	ret = o2hb_debug_region_init(reg, o2hb_debug_dir);
 	if (ret) {
 		config_item_put(&reg->hr_item);
-		goto free;
+		goto unregister_handler;
 	}
 
 	return &reg->hr_item;
+
+unregister_handler:
+	o2net_unregister_handler_list(&reg->hr_handler_list);
 free:
 	kfree(reg);
 	return ERR_PTR(ret);

fs/ocfs2/cluster/tcp_internal.h

@@ -44,6 +44,9 @@
  * version here in tcp_internal.h should not need to be bumped for
  * filesystem locking changes.
  *
+ * New in version 12
+ *	- Negotiate hb timeout when storage is down.
+ *
  * New in version 11
  * 	- Negotiation of filesystem locking in the dlm join.
  *
@@ -75,7 +78,7 @@
  * 	- full 64 bit i_size in the metadata lock lvbs
  * 	- introduction of "rw" lock and pushing meta/data locking down
  */
-#define O2NET_PROTOCOL_VERSION 11ULL
+#define O2NET_PROTOCOL_VERSION 12ULL
 struct o2net_handshake {
 	__be64	protocol_version;
 	__be64	connector_id;

init/main.c

@@ -607,6 +607,7 @@ asmlinkage __visible void __init start_kernel(void)
 		initrd_start = 0;
 	}
 #endif
+	page_ext_init();
 	debug_objects_mem_init();
 	kmemleak_init();
 	setup_per_cpu_pageset();
@@ -1003,8 +1004,6 @@ static noinline void __init kernel_init_freeable(void)
 	sched_init_smp();
 
 	page_alloc_init_late();
-	/* Initialize page ext after all struct pages are initializaed */
-	page_ext_init();
 
 	do_basic_setup();
 

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

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,
+	alignment = max(alignment,  (phys_addr_t)PAGE_SIZE <<
-		(phys_addr_t)PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order));
+			  max_t(unsigned long, MAX_ORDER - 1, pageblock_order));
 	base = ALIGN(base, alignment);
 	size = ALIGN(size, alignment);
 	limit &= ~(alignment - 1);

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)
 {

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);
 	}
 }

mm/oom_kill.c

@@ -443,12 +443,28 @@ 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.
@@ -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);
@@ -511,12 +527,14 @@ 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.
 	 */
+	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;
 

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;

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;