Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:
 "257 patches.

  Subsystems affected by this patch series: scripts, ocfs2, vfs, and
  mm (slab-generic, slab, slub, kconfig, dax, kasan, debug, pagecache,
  gup, swap, memcg, pagemap, mprotect, mremap, iomap, tracing, vmalloc,
  pagealloc, memory-failure, hugetlb, userfaultfd, vmscan, tools,
  memblock, oom-kill, hugetlbfs, migration, thp, readahead, nommu, ksm,
  vmstat, madvise, memory-hotplug, rmap, zsmalloc, highmem, zram,
  cleanups, kfence, and damon)"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (257 commits)
  mm/damon: remove return value from before_terminate callback
  mm/damon: fix a few spelling mistakes in comments and a pr_debug message
  mm/damon: simplify stop mechanism
  Docs/admin-guide/mm/pagemap: wordsmith page flags descriptions
  Docs/admin-guide/mm/damon/start: simplify the content
  Docs/admin-guide/mm/damon/start: fix a wrong link
  Docs/admin-guide/mm/damon/start: fix wrong example commands
  mm/damon/dbgfs: add adaptive_targets list check before enable monitor_on
  mm/damon: remove unnecessary variable initialization
  Documentation/admin-guide/mm/damon: add a document for DAMON_RECLAIM
  mm/damon: introduce DAMON-based Reclamation (DAMON_RECLAIM)
  selftests/damon: support watermarks
  mm/damon/dbgfs: support watermarks
  mm/damon/schemes: activate schemes based on a watermarks mechanism
  tools/selftests/damon: update for regions prioritization of schemes
  mm/damon/dbgfs: support prioritization weights
  mm/damon/vaddr,paddr: support pageout prioritization
  mm/damon/schemes: prioritize regions within the quotas
  mm/damon/selftests: support schemes quotas
  mm/damon/dbgfs: support quotas of schemes
  ...

12 files changed, 84 insertions, 77 deletions

diff --git a/fs/d_path.c b/fs/d_path.c
index cd60c7535181..e4e0ebad1f15 100644
--- a/fs/d_path.c
+++ b/fs/d_path.c
@@ -77,9 +77,8 @@ static bool prepend(struct prepend_buffer *p, const char *str, int namelen)
 
 /**
  * prepend_name - prepend a pathname in front of current buffer pointer
- * @buffer: buffer pointer
- * @buflen: allocated length of the buffer
- * @name:   name string and length qstr structure
+ * @p: prepend buffer which contains buffer pointer and allocated length
+ * @name: name string and length qstr structure
  *
  * With RCU path tracing, it may race with d_move(). Use READ_ONCE() to
  * make sure that either the old or the new name pointer and length are
@@ -141,8 +140,7 @@ static int __prepend_path(const struct dentry *dentry, const struct mount *mnt,
  * prepend_path - Prepend path string to a buffer
  * @path: the dentry/vfsmount to report
  * @root: root vfsmnt/dentry
- * @buffer: pointer to the end of the buffer
- * @buflen: pointer to buffer length
+ * @p: prepend buffer which contains buffer pointer and allocated length
  *
  * The function will first try to write out the pathname without taking any
  * lock other than the RCU read lock to make sure that dentries won't go away.
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index 5d9ae17bd443..bb247bc349e4 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -5940,6 +5940,7 @@ static int ocfs2_replay_truncate_records(struct ocfs2_super *osb,
 		status = ocfs2_journal_access_di(handle, INODE_CACHE(tl_inode), tl_bh,
 						 OCFS2_JOURNAL_ACCESS_WRITE);
 		if (status < 0) {
+			ocfs2_commit_trans(osb, handle);
 			mlog_errno(status);
 			goto bail;
 		}
@@ -5964,6 +5965,7 @@ static int ocfs2_replay_truncate_records(struct ocfs2_super *osb,
 						     data_alloc_bh, start_blk,
 						     num_clusters);
 			if (status < 0) {
+				ocfs2_commit_trans(osb, handle);
 				mlog_errno(status);
 				goto bail;
 			}
@@ -6921,13 +6923,12 @@ static int ocfs2_grab_eof_pages(struct inode *inode, loff_t start, loff_t end,
 }
 
 /*
- * Zero the area past i_size but still within an allocated
- * cluster. This avoids exposing nonzero data on subsequent file
- * extends.
+ * Zero partial cluster for a hole punch or truncate. This avoids exposing
+ * nonzero data on subsequent file extends.
  *
  * We need to call this before i_size is updated on the inode because
  * otherwise block_write_full_page() will skip writeout of pages past
- * i_size. The new_i_size parameter is passed for this reason.
+ * i_size.
  */
 int ocfs2_zero_range_for_truncate(struct inode *inode, handle_t *handle,
 				  u64 range_start, u64 range_end)
@@ -6945,6 +6946,15 @@ int ocfs2_zero_range_for_truncate(struct inode *inode, handle_t *handle,
 	if (!ocfs2_sparse_alloc(OCFS2_SB(sb)))
 		return 0;
 
+	/*
+	 * Avoid zeroing pages fully beyond current i_size. It is pointless as
+	 * underlying blocks of those pages should be already zeroed out and
+	 * page writeback will skip them anyway.
+	 */
+	range_end = min_t(u64, range_end, i_size_read(inode));
+	if (range_start >= range_end)
+		return 0;
+
 	pages = kcalloc(ocfs2_pages_per_cluster(sb),
 			sizeof(struct page *), GFP_NOFS);
 	if (pages == NULL) {
@@ -6953,9 +6963,6 @@ int ocfs2_zero_range_for_truncate(struct inode *inode, handle_t *handle,
 		goto out;
 	}
 
-	if (range_start == range_end)
-		goto out;
-
 	ret = ocfs2_extent_map_get_blocks(inode,
 					  range_start >> sb->s_blocksize_bits,
 					  &phys, NULL, &ext_flags);
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index 0e7aad1b11cc..5cd5f7511dac 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -2698,7 +2698,6 @@ static int dlm_send_begin_reco_message(struct dlm_ctxt *dlm, u8 dead_node)
 			continue;
 		}
 retry:
-		ret = -EINVAL;
 		mlog(0, "attempting to send begin reco msg to %d\n",
 			  nodenum);
 		ret = o2net_send_message(DLM_BEGIN_RECO_MSG, dlm->key,
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 54d7843c0211..fc5f780fa235 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -476,10 +476,11 @@ int ocfs2_truncate_file(struct inode *inode,
 	 * greater than page size, so we have to truncate them
 	 * anyway.
 	 */
-	unmap_mapping_range(inode->i_mapping, new_i_size + PAGE_SIZE - 1, 0, 1);
-	truncate_inode_pages(inode->i_mapping, new_i_size);
 
 	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
+		unmap_mapping_range(inode->i_mapping,
+				    new_i_size + PAGE_SIZE - 1, 0, 1);
+		truncate_inode_pages(inode->i_mapping, new_i_size);
 		status = ocfs2_truncate_inline(inode, di_bh, new_i_size,
 					       i_size_read(inode), 1);
 		if (status)
@@ -498,6 +499,9 @@ int ocfs2_truncate_file(struct inode *inode,
 		goto bail_unlock_sem;
 	}
 
+	unmap_mapping_range(inode->i_mapping, new_i_size + PAGE_SIZE - 1, 0, 1);
+	truncate_inode_pages(inode->i_mapping, new_i_size);
+
 	status = ocfs2_commit_truncate(osb, inode, di_bh);
 	if (status < 0) {
 		mlog_errno(status);
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index bc8f32fab964..6c2411c2afcf 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -125,7 +125,6 @@ struct inode *ocfs2_iget(struct ocfs2_super *osb, u64 blkno, unsigned flags,
 	struct inode *inode = NULL;
 	struct super_block *sb = osb->sb;
 	struct ocfs2_find_inode_args args;
-	journal_t *journal = OCFS2_SB(sb)->journal->j_journal;
 
 	trace_ocfs2_iget_begin((unsigned long long)blkno, flags,
 			       sysfile_type);
@@ -172,10 +171,11 @@ struct inode *ocfs2_iget(struct ocfs2_super *osb, u64 blkno, unsigned flags,
 	 * part of the transaction - the inode could have been reclaimed and
 	 * now it is reread from disk.
 	 */
-	if (journal) {
+	if (osb->journal) {
 		transaction_t *transaction;
 		tid_t tid;
 		struct ocfs2_inode_info *oi = OCFS2_I(inode);
+		journal_t *journal = osb->journal->j_journal;
 
 		read_lock(&journal->j_state_lock);
 		if (journal->j_running_transaction)
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 4f15750aac5d..b9c339335a53 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -810,19 +810,34 @@ void ocfs2_set_journal_params(struct ocfs2_super *osb)
 	write_unlock(&journal->j_state_lock);
 }
 
-int ocfs2_journal_init(struct ocfs2_journal *journal, int *dirty)
+int ocfs2_journal_init(struct ocfs2_super *osb, int *dirty)
 {
 	int status = -1;
 	struct inode *inode = NULL; /* the journal inode */
 	journal_t *j_journal = NULL;
+	struct ocfs2_journal *journal = NULL;
 	struct ocfs2_dinode *di = NULL;
 	struct buffer_head *bh = NULL;
-	struct ocfs2_super *osb;
 	int inode_lock = 0;
 
-	BUG_ON(!journal);
+	/* initialize our journal structure */
+	journal = kzalloc(sizeof(struct ocfs2_journal), GFP_KERNEL);
+	if (!journal) {
+		mlog(ML_ERROR, "unable to alloc journal\n");
+		status = -ENOMEM;
+		goto done;
+	}
+	osb->journal = journal;
+	journal->j_osb = osb;
 
-	osb = journal->j_osb;
+	atomic_set(&journal->j_num_trans, 0);
+	init_rwsem(&journal->j_trans_barrier);
+	init_waitqueue_head(&journal->j_checkpointed);
+	spin_lock_init(&journal->j_lock);
+	journal->j_trans_id = 1UL;
+	INIT_LIST_HEAD(&journal->j_la_cleanups);
+	INIT_WORK(&journal->j_recovery_work, ocfs2_complete_recovery);
+	journal->j_state = OCFS2_JOURNAL_FREE;
 
 	/* already have the inode for our journal */
 	inode = ocfs2_get_system_file_inode(osb, JOURNAL_SYSTEM_INODE,
@@ -1028,9 +1043,10 @@ void ocfs2_journal_shutdown(struct ocfs2_super *osb)
 
 	journal->j_state = OCFS2_JOURNAL_FREE;
 
-//	up_write(&journal->j_trans_barrier);
 done:
 	iput(inode);
+	kfree(journal);
+	osb->journal = NULL;
 }
 
 static void ocfs2_clear_journal_error(struct super_block *sb,
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index d158acb8b38a..8dcb2f2cadbc 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -167,8 +167,7 @@ int ocfs2_compute_replay_slots(struct ocfs2_super *osb);
  *  ocfs2_start_checkpoint - Kick the commit thread to do a checkpoint.
  */
 void   ocfs2_set_journal_params(struct ocfs2_super *osb);
-int    ocfs2_journal_init(struct ocfs2_journal *journal,
-			  int *dirty);
+int    ocfs2_journal_init(struct ocfs2_super *osb, int *dirty);
 void   ocfs2_journal_shutdown(struct ocfs2_super *osb);
 int    ocfs2_journal_wipe(struct ocfs2_journal *journal,
 			  int full);
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 5c914ce9b3ac..1286b88b6fa1 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1894,8 +1894,6 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err)
 	/* This will disable recovery and flush any recovery work. */
 	ocfs2_recovery_exit(osb);
 
-	ocfs2_journal_shutdown(osb);
-
 	ocfs2_sync_blockdev(sb);
 
 	ocfs2_purge_refcount_trees(osb);
@@ -1918,6 +1916,8 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err)
 
 	ocfs2_release_system_inodes(osb);
 
+	ocfs2_journal_shutdown(osb);
+
 	/*
 	 * If we're dismounting due to mount error, mount.ocfs2 will clean
 	 * up heartbeat.  If we're a local mount, there is no heartbeat.
@@ -2016,7 +2016,6 @@ static int ocfs2_initialize_super(struct super_block *sb,
 	int i, cbits, bbits;
 	struct ocfs2_dinode *di = (struct ocfs2_dinode *)bh->b_data;
 	struct inode *inode = NULL;
-	struct ocfs2_journal *journal;
 	struct ocfs2_super *osb;
 	u64 total_blocks;
 
@@ -2197,33 +2196,6 @@ static int ocfs2_initialize_super(struct super_block *sb,
 
 	get_random_bytes(&osb->s_next_generation, sizeof(u32));
 
-	/* FIXME
-	 * This should be done in ocfs2_journal_init(), but unknown
-	 * ordering issues will cause the filesystem to crash.
-	 * If anyone wants to figure out what part of the code
-	 * refers to osb->journal before ocfs2_journal_init() is run,
-	 * be my guest.
-	 */
-	/* initialize our journal structure */
-
-	journal = kzalloc(sizeof(struct ocfs2_journal), GFP_KERNEL);
-	if (!journal) {
-		mlog(ML_ERROR, "unable to alloc journal\n");
-		status = -ENOMEM;
-		goto bail;
-	}
-	osb->journal = journal;
-	journal->j_osb = osb;
-
-	atomic_set(&journal->j_num_trans, 0);
-	init_rwsem(&journal->j_trans_barrier);
-	init_waitqueue_head(&journal->j_checkpointed);
-	spin_lock_init(&journal->j_lock);
-	journal->j_trans_id = (unsigned long) 1;
-	INIT_LIST_HEAD(&journal->j_la_cleanups);
-	INIT_WORK(&journal->j_recovery_work, ocfs2_complete_recovery);
-	journal->j_state = OCFS2_JOURNAL_FREE;
-
 	INIT_WORK(&osb->dquot_drop_work, ocfs2_drop_dquot_refs);
 	init_llist_head(&osb->dquot_drop_list);
 
@@ -2404,7 +2376,7 @@ static int ocfs2_check_volume(struct ocfs2_super *osb)
 						  * ourselves. */
 
 	/* Init our journal object. */
-	status = ocfs2_journal_init(osb->journal, &dirty);
+	status = ocfs2_journal_init(osb, &dirty);
 	if (status < 0) {
 		mlog(ML_ERROR, "Could not initialize journal!\n");
 		goto finally;
@@ -2513,12 +2485,6 @@ static void ocfs2_delete_osb(struct ocfs2_super *osb)
 
 	kfree(osb->osb_orphan_wipes);
 	kfree(osb->slot_recovery_generations);
-	/* FIXME
-	 * This belongs in journal shutdown, but because we have to
-	 * allocate osb->journal at the start of ocfs2_initialize_osb(),
-	 * we free it here.
-	 */
-	kfree(osb->journal);
 	kfree(osb->local_alloc_copy);
 	kfree(osb->uuid_str);
 	kfree(osb->vol_label);
diff --git a/fs/open.c b/fs/open.c
index a7f6cab81267..f732fb94600c 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -856,8 +856,20 @@ static int do_dentry_open(struct file *f,
 		 * of THPs into the page cache will fail.
 		 */
 		smp_mb();
-		if (filemap_nr_thps(inode->i_mapping))
-			truncate_pagecache(inode, 0);
+		if (filemap_nr_thps(inode->i_mapping)) {
+			struct address_space *mapping = inode->i_mapping;
+
+			filemap_invalidate_lock(inode->i_mapping);
+			/*
+			 * unmap_mapping_range just need to be called once
+			 * here, because the private pages is not need to be
+			 * unmapped mapping (e.g. data segment of dynamic
+			 * shared libraries here).
+			 */
+			unmap_mapping_range(mapping, 0, 0, 0);
+			truncate_inode_pages(mapping, 0);
+			filemap_invalidate_unlock(inode->i_mapping);
+		}
 	}
 
 	return 0;
diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index f5c25f580dd9..9323a854a60a 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -134,8 +134,7 @@ struct posix_acl *get_acl(struct inode *inode, int type)
 	 * to just call ->get_acl to fetch the ACL ourself.  (This is going to
 	 * be an unlikely race.)
 	 */
-	if (cmpxchg(p, ACL_NOT_CACHED, sentinel) != ACL_NOT_CACHED)
-		/* fall through */ ;
+	cmpxchg(p, ACL_NOT_CACHED, sentinel);
 
 	/*
 	 * Normally, the ACL returned by ->get_acl will be cached.
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index cf25be3e0321..ad667dbc96f5 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -397,7 +397,6 @@ struct mem_size_stats {
 	u64 pss_shmem;
 	u64 pss_locked;
 	u64 swap_pss;
-	bool check_shmem_swap;
 };
 
 static void smaps_page_accumulate(struct mem_size_stats *mss,
@@ -478,9 +477,11 @@ static int smaps_pte_hole(unsigned long addr, unsigned long end,
 			  __always_unused int depth, struct mm_walk *walk)
 {
 	struct mem_size_stats *mss = walk->private;
+	struct vm_area_struct *vma = walk->vma;
 
-	mss->swap += shmem_partial_swap_usage(
-			walk->vma->vm_file->f_mapping, addr, end);
+	mss->swap += shmem_partial_swap_usage(walk->vma->vm_file->f_mapping,
+					      linear_page_index(vma, addr),
+					      linear_page_index(vma, end));
 
 	return 0;
 }
@@ -488,6 +489,16 @@ static int smaps_pte_hole(unsigned long addr, unsigned long end,
 #define smaps_pte_hole		NULL
 #endif /* CONFIG_SHMEM */
 
+static void smaps_pte_hole_lookup(unsigned long addr, struct mm_walk *walk)
+{
+#ifdef CONFIG_SHMEM
+	if (walk->ops->pte_hole) {
+		/* depth is not used */
+		smaps_pte_hole(addr, addr + PAGE_SIZE, 0, walk);
+	}
+#endif
+}
+
 static void smaps_pte_entry(pte_t *pte, unsigned long addr,
 		struct mm_walk *walk)
 {
@@ -516,12 +527,8 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
 			}
 		} else if (is_pfn_swap_entry(swpent))
 			page = pfn_swap_entry_to_page(swpent);
-	} else if (unlikely(IS_ENABLED(CONFIG_SHMEM) && mss->check_shmem_swap
-							&& pte_none(*pte))) {
-		page = xa_load(&vma->vm_file->f_mapping->i_pages,
-						linear_page_index(vma, addr));
-		if (xa_is_value(page))
-			mss->swap += PAGE_SIZE;
+	} else {
+		smaps_pte_hole_lookup(addr, walk);
 		return;
 	}
 
@@ -735,8 +742,6 @@ static void smap_gather_stats(struct vm_area_struct *vma,
 		return;
 
 #ifdef CONFIG_SHMEM
-	/* In case of smaps_rollup, reset the value from previous vma */
-	mss->check_shmem_swap = false;
 	if (vma->vm_file && shmem_mapping(vma->vm_file->f_mapping)) {
 		/*
 		 * For shared or readonly shmem mappings we know that all
@@ -754,7 +759,6 @@ static void smap_gather_stats(struct vm_area_struct *vma,
 					!(vma->vm_flags & VM_WRITE))) {
 			mss->swap += shmem_swapped;
 		} else {
-			mss->check_shmem_swap = true;
 			ops = &smaps_shmem_walk_ops;
 		}
 	}
diff --git a/fs/super.c b/fs/super.c
index bcef3a6f4c4b..3bfc0f8fbd5b 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -476,6 +476,8 @@ void generic_shutdown_super(struct super_block *sb)
 	spin_unlock(&sb_lock);
 	up_write(&sb->s_umount);
 	if (sb->s_bdi != &noop_backing_dev_info) {
+		if (sb->s_iflags & SB_I_PERSB_BDI)
+			bdi_unregister(sb->s_bdi);
 		bdi_put(sb->s_bdi);
 		sb->s_bdi = &noop_backing_dev_info;
 	}
@@ -1562,6 +1564,7 @@ int super_setup_bdi_name(struct super_block *sb, char *fmt, ...)
 	}
 	WARN_ON(sb->s_bdi != &noop_backing_dev_info);
 	sb->s_bdi = bdi;
+	sb->s_iflags |= SB_I_PERSB_BDI;
 
 	return 0;
 }