Merge branch 'akpm' (patches from Andrew)

Merge first patch-bomb from Andrew Morton:

 - A few hotfixes which missed 4.4 becasue I was asleep.  cc'ed to
   -stable

 - A few misc fixes

 - OCFS2 updates

 - Part of MM.  Including pretty large changes to page-flags handling
   and to thp management which have been buffered up for 2-3 cycles now.

  I have a lot of MM material this time.

[ It turns out the THP part wasn't quite ready, so that got dropped from
  this series  - Linus ]

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (117 commits)
  zsmalloc: reorganize struct size_class to pack 4 bytes hole
  mm/zbud.c: use list_last_entry() instead of list_tail_entry()
  zram/zcomp: do not zero out zcomp private pages
  zram: pass gfp from zcomp frontend to backend
  zram: try vmalloc() after kmalloc()
  zram/zcomp: use GFP_NOIO to allocate streams
  mm: add tracepoint for scanning pages
  drivers/base/memory.c: fix kernel warning during memory hotplug on ppc64
  mm/page_isolation: use macro to judge the alignment
  mm: fix noisy sparse warning in LIBCFS_ALLOC_PRE()
  mm: rework virtual memory accounting
  include/linux/memblock.h: fix ordering of 'flags' argument in comments
  mm: move lru_to_page to mm_inline.h
  Documentation/filesystems: describe the shared memory usage/accounting
  memory-hotplug: don't BUG() in register_memory_resource()
  hugetlb: make mm and fs code explicitly non-modular
  mm/swapfile.c: use list_for_each_entry_safe in free_swap_count_continuations
  mm: /proc/pid/clear_refs: no need to clear VM_SOFTDIRTY in clear_soft_dirty_pmd()
  mm: make sure isolate_lru_page() is never called for tail page
  vmstat: make vmstat_updater deferrable again and shut down on idle
  ...

4 files changed, 30 insertions, 33 deletions

diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h
index e88ccf8c83ff..68c607e63ff6 100644
--- a/fs/ocfs2/dlm/dlmcommon.h
+++ b/fs/ocfs2/dlm/dlmcommon.h
@@ -376,17 +376,6 @@ struct dlm_lock
 		 lksb_kernel_allocated:1;
 };
 
-
-#define DLM_LKSB_UNUSED1           0x01
-#define DLM_LKSB_PUT_LVB           0x02
-#define DLM_LKSB_GET_LVB           0x04
-#define DLM_LKSB_UNUSED2           0x08
-#define DLM_LKSB_UNUSED3           0x10
-#define DLM_LKSB_UNUSED4           0x20
-#define DLM_LKSB_UNUSED5           0x40
-#define DLM_LKSB_UNUSED6           0x80
-
-
 enum dlm_lockres_list {
 	DLM_GRANTED_LIST = 0,
 	DLM_CONVERTING_LIST = 1,
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 84f2f8079466..9477d6e1de37 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -2388,8 +2388,8 @@ static void dlm_deref_lockres_worker(struct dlm_work_item *item, void *data)
 
 	spin_lock(&res->spinlock);
 	BUG_ON(res->state & DLM_LOCK_RES_DROPPING_REF);
+	__dlm_wait_on_lockres_flags(res, DLM_LOCK_RES_SETREF_INPROG);
 	if (test_bit(node, res->refmap)) {
-		__dlm_wait_on_lockres_flags(res, DLM_LOCK_RES_SETREF_INPROG);
 		dlm_lockres_clear_refmap_bit(dlm, res, node);
 		cleared = 1;
 	}
@@ -2519,6 +2519,11 @@ static int dlm_migrate_lockres(struct dlm_ctxt *dlm,
 	spin_lock(&dlm->master_lock);
 	ret = dlm_add_migration_mle(dlm, res, mle, &oldmle, name,
 				    namelen, target, dlm->node_num);
+	/* get an extra reference on the mle.
+	 * otherwise the assert_master from the new
+	 * master will destroy this.
+	 */
+	dlm_get_mle_inuse(mle);
 	spin_unlock(&dlm->master_lock);
 	spin_unlock(&dlm->spinlock);
 
@@ -2544,7 +2549,7 @@ static int dlm_migrate_lockres(struct dlm_ctxt *dlm,
 	}
 
 fail:
-	if (oldmle) {
+	if (ret != -EEXIST && oldmle) {
 		/* master is known, detach if not already detached */
 		dlm_mle_detach_hb_events(dlm, oldmle);
 		dlm_put_mle(oldmle);
@@ -2554,6 +2559,7 @@ fail:
 		if (mle_added) {
 			dlm_mle_detach_hb_events(dlm, mle);
 			dlm_put_mle(mle);
+			dlm_put_mle_inuse(mle);
 		} else if (mle) {
 			kmem_cache_free(dlm_mle_cache, mle);
 			mle = NULL;
@@ -2571,17 +2577,6 @@ fail:
 	 * ensure that all assert_master work is flushed. */
 	flush_workqueue(dlm->dlm_worker);
 
-	/* get an extra reference on the mle.
-	 * otherwise the assert_master from the new
-	 * master will destroy this.
-	 * also, make sure that all callers of dlm_get_mle
-	 * take both dlm->spinlock and dlm->master_lock */
-	spin_lock(&dlm->spinlock);
-	spin_lock(&dlm->master_lock);
-	dlm_get_mle_inuse(mle);
-	spin_unlock(&dlm->master_lock);
-	spin_unlock(&dlm->spinlock);
-
 	/* notify new node and send all lock state */
 	/* call send_one_lockres with migration flag.
 	 * this serves as notice to the target node that a
@@ -3050,7 +3045,7 @@ int dlm_migrate_request_handler(struct o2net_msg *msg, u32 len, void *data,
 	int ret = 0;
 
 	if (!dlm_grab(dlm))
-		return -EINVAL;
+		return 0;
 
 	name = migrate->name;
 	namelen = migrate->namelen;
@@ -3141,7 +3136,8 @@ static int dlm_add_migration_mle(struct dlm_ctxt *dlm,
 				mlog(0, "tried to migrate %.*s, but some "
 				     "process beat me to it\n",
 				     namelen, name);
-				ret = -EEXIST;
+				spin_unlock(&tmp->spinlock);
+				return -EEXIST;
 			} else {
 				/* bad.  2 NODES are trying to migrate! */
 				mlog(ML_ERROR, "migration error  mle: "
@@ -3312,6 +3308,15 @@ top:
 			    mle->new_master != dead_node)
 				continue;
 
+			if (mle->new_master == dead_node && mle->inuse) {
+				mlog(ML_NOTICE, "%s: target %u died during "
+						"migration from %u, the MLE is "
+						"still keep used, ignore it!\n",
+						dlm->name, dead_node,
+						mle->master);
+				continue;
+			}
+
 			/* If we have reached this point, this mle needs to be
 			 * removed from the list and freed. */
 			dlm_clean_migration_mle(dlm, mle);
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index 9e4f862d20fe..c5bdf02c213b 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -1373,6 +1373,7 @@ int dlm_mig_lockres_handler(struct o2net_msg *msg, u32 len, void *data,
 	char *buf = NULL;
 	struct dlm_work_item *item = NULL;
 	struct dlm_lock_resource *res = NULL;
+	unsigned int hash;
 
 	if (!dlm_grab(dlm))
 		return -EINVAL;
@@ -1400,7 +1401,10 @@ int dlm_mig_lockres_handler(struct o2net_msg *msg, u32 len, void *data,
 	/* lookup the lock to see if we have a secondary queue for this
 	 * already...  just add the locks in and this will have its owner
 	 * and RECOVERY flag changed when it completes. */
-	res = dlm_lookup_lockres(dlm, mres->lockname, mres->lockname_len);
+	hash = dlm_lockid_hash(mres->lockname, mres->lockname_len);
+	spin_lock(&dlm->spinlock);
+	res = __dlm_lookup_lockres(dlm, mres->lockname, mres->lockname_len,
+			hash);
 	if (res) {
 	 	/* this will get a ref on res */
 		/* mark it as recovering/migrating and hash it */
@@ -1421,13 +1425,16 @@ int dlm_mig_lockres_handler(struct o2net_msg *msg, u32 len, void *data,
 				     mres->lockname_len, mres->lockname);
 				ret = -EFAULT;
 				spin_unlock(&res->spinlock);
+				spin_unlock(&dlm->spinlock);
 				dlm_lockres_put(res);
 				goto leave;
 			}
 			res->state |= DLM_LOCK_RES_MIGRATING;
 		}
 		spin_unlock(&res->spinlock);
+		spin_unlock(&dlm->spinlock);
 	} else {
+		spin_unlock(&dlm->spinlock);
 		/* need to allocate, just like if it was
 		 * mastered here normally  */
 		res = dlm_new_lockres(dlm, mres->lockname, mres->lockname_len);
@@ -2450,11 +2457,7 @@ static void __dlm_hb_node_down(struct dlm_ctxt *dlm, int idx)
 	 * perhaps later we can genericize this for other waiters. */
 	wake_up(&dlm->migration_wq);
 
-	if (test_bit(idx, dlm->recovery_map))
-		mlog(0, "domain %s, node %u already added "
-		     "to recovery map!\n", dlm->name, idx);
-	else
-		set_bit(idx, dlm->recovery_map);
+	set_bit(idx, dlm->recovery_map);
 }
 
 void dlm_hb_node_down_cb(struct o2nm_node *node, int idx, void *data)
diff --git a/fs/ocfs2/dlm/dlmunlock.c b/fs/ocfs2/dlm/dlmunlock.c
index 2e3c9dbab68c..1082b2c3014b 100644
--- a/fs/ocfs2/dlm/dlmunlock.c
+++ b/fs/ocfs2/dlm/dlmunlock.c
@@ -421,7 +421,7 @@ int dlm_unlock_lock_handler(struct o2net_msg *msg, u32 len, void *data,
 	}
 
 	if (!dlm_grab(dlm))
-		return DLM_REJECTED;
+		return DLM_FORWARD;
 
 	mlog_bug_on_msg(!dlm_domain_fully_joined(dlm),
 			"Domain %s not fully joined!\n", dlm->name);