Merge mm-hotfixes-stable into mm-stable to pick up depended-upon changes.

12 files changed, 133 insertions, 12 deletions

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 980483455cc0..266d45c7685b 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1805,7 +1805,11 @@ static int ep_autoremove_wake_function(struct wait_queue_entry *wq_entry,
 {
 	int ret = default_wake_function(wq_entry, mode, sync, key);
 
-	list_del_init(&wq_entry->entry);
+	/*
+	 * Pairs with list_empty_careful in ep_poll, and ensures future loop
+	 * iterations see the cause of this wakeup.
+	 */
+	list_del_init_careful(&wq_entry->entry);
 	return ret;
 }
 
diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c
index e956f886a1a1..5710833ac1cc 100644
--- a/fs/nilfs2/btnode.c
+++ b/fs/nilfs2/btnode.c
@@ -285,6 +285,14 @@ void nilfs_btnode_abort_change_key(struct address_space *btnc,
 	if (nbh == NULL) {	/* blocksize == pagesize */
 		xa_erase_irq(&btnc->i_pages, newkey);
 		unlock_page(ctxt->bh->b_page);
-	} else
-		brelse(nbh);
+	} else {
+		/*
+		 * When canceling a buffer that a prepare operation has
+		 * allocated to copy a node block to another location, use
+		 * nilfs_btnode_delete() to initialize and release the buffer
+		 * so that the buffer flags will not be in an inconsistent
+		 * state when it is reallocated.
+		 */
+		nilfs_btnode_delete(nbh);
+	}
 }
diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c
index 5cf30827f244..b4e54d079b7d 100644
--- a/fs/nilfs2/page.c
+++ b/fs/nilfs2/page.c
@@ -370,7 +370,15 @@ void nilfs_clear_dirty_pages(struct address_space *mapping, bool silent)
 			struct folio *folio = fbatch.folios[i];
 
 			folio_lock(folio);
-			nilfs_clear_dirty_page(&folio->page, silent);
+
+			/*
+			 * This folio may have been removed from the address
+			 * space by truncation or invalidation when the lock
+			 * was acquired.  Skip processing in that case.
+			 */
+			if (likely(folio->mapping == mapping))
+				nilfs_clear_dirty_page(&folio->page, silent);
+
 			folio_unlock(folio);
 		}
 		folio_batch_release(&fbatch);
diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c
index 1362ccb64ec7..6e59dc19a732 100644
--- a/fs/nilfs2/segbuf.c
+++ b/fs/nilfs2/segbuf.c
@@ -101,6 +101,12 @@ int nilfs_segbuf_extend_segsum(struct nilfs_segment_buffer *segbuf)
 	if (unlikely(!bh))
 		return -ENOMEM;
 
+	lock_buffer(bh);
+	if (!buffer_uptodate(bh)) {
+		memset(bh->b_data, 0, bh->b_size);
+		set_buffer_uptodate(bh);
+	}
+	unlock_buffer(bh);
 	nilfs_segbuf_add_segsum_buffer(segbuf, bh);
 	return 0;
 }
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index ac949fd7603f..c2553024bd25 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -981,10 +981,13 @@ static void nilfs_segctor_fill_in_super_root(struct nilfs_sc_info *sci,
 	unsigned int isz, srsz;
 
 	bh_sr = NILFS_LAST_SEGBUF(&sci->sc_segbufs)->sb_super_root;
+
+	lock_buffer(bh_sr);
 	raw_sr = (struct nilfs_super_root *)bh_sr->b_data;
 	isz = nilfs->ns_inode_size;
 	srsz = NILFS_SR_BYTES(isz);
 
+	raw_sr->sr_sum = 0;  /* Ensure initialization within this update */
 	raw_sr->sr_bytes = cpu_to_le16(srsz);
 	raw_sr->sr_nongc_ctime
 		= cpu_to_le64(nilfs_doing_gc() ?
@@ -998,6 +1001,8 @@ static void nilfs_segctor_fill_in_super_root(struct nilfs_sc_info *sci,
 	nilfs_write_inode_common(nilfs->ns_sufile, (void *)raw_sr +
 				 NILFS_SR_SUFILE_OFFSET(isz), 1);
 	memset((void *)raw_sr + srsz, 0, nilfs->ns_blocksize - srsz);
+	set_buffer_uptodate(bh_sr);
+	unlock_buffer(bh_sr);
 }
 
 static void nilfs_redirty_inodes(struct list_head *head)
@@ -1780,6 +1785,7 @@ static void nilfs_abort_logs(struct list_head *logs, int err)
 	list_for_each_entry(segbuf, logs, sb_list) {
 		list_for_each_entry(bh, &segbuf->sb_segsum_buffers,
 				    b_assoc_buffers) {
+			clear_buffer_uptodate(bh);
 			if (bh->b_page != bd_page) {
 				if (bd_page)
 					end_page_writeback(bd_page);
@@ -1791,6 +1797,7 @@ static void nilfs_abort_logs(struct list_head *logs, int err)
 				    b_assoc_buffers) {
 			clear_buffer_async_write(bh);
 			if (bh == segbuf->sb_super_root) {
+				clear_buffer_uptodate(bh);
 				if (bh->b_page != bd_page) {
 					end_page_writeback(bd_page);
 					bd_page = bh->b_page;
diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c
index dc359b56fdfa..2c6078a6b8ec 100644
--- a/fs/nilfs2/sufile.c
+++ b/fs/nilfs2/sufile.c
@@ -779,6 +779,15 @@ int nilfs_sufile_resize(struct inode *sufile, __u64 newnsegs)
 			goto out_header;
 
 		sui->ncleansegs -= nsegs - newnsegs;
+
+		/*
+		 * If the sufile is successfully truncated, immediately adjust
+		 * the segment allocation space while locking the semaphore
+		 * "mi_sem" so that nilfs_sufile_alloc() never allocates
+		 * segments in the truncated space.
+		 */
+		sui->allocmax = newnsegs - 1;
+		sui->allocmin = 0;
 	}
 
 	kaddr = kmap_atomic(header_bh->b_page);
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 77f1e5778d1c..9ba4933087af 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -372,10 +372,31 @@ static int nilfs_move_2nd_super(struct super_block *sb, loff_t sb2off)
 		goto out;
 	}
 	nsbp = (void *)nsbh->b_data + offset;
-	memset(nsbp, 0, nilfs->ns_blocksize);
 
+	lock_buffer(nsbh);
 	if (sb2i >= 0) {
+		/*
+		 * The position of the second superblock only changes by 4KiB,
+		 * which is larger than the maximum superblock data size
+		 * (= 1KiB), so there is no need to use memmove() to allow
+		 * overlap between source and destination.
+		 */
 		memcpy(nsbp, nilfs->ns_sbp[sb2i], nilfs->ns_sbsize);
+
+		/*
+		 * Zero fill after copy to avoid overwriting in case of move
+		 * within the same block.
+		 */
+		memset(nsbh->b_data, 0, offset);
+		memset((void *)nsbp + nilfs->ns_sbsize, 0,
+		       nsbh->b_size - offset - nilfs->ns_sbsize);
+	} else {
+		memset(nsbh->b_data, 0, nsbh->b_size);
+	}
+	set_buffer_uptodate(nsbh);
+	unlock_buffer(nsbh);
+
+	if (sb2i >= 0) {
 		brelse(nilfs->ns_sbh[sb2i]);
 		nilfs->ns_sbh[sb2i] = nsbh;
 		nilfs->ns_sbp[sb2i] = nsbp;
diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index 2894152a6b25..0f0667957c81 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -405,6 +405,18 @@ unsigned long nilfs_nrsvsegs(struct the_nilfs *nilfs, unsigned long nsegs)
 				  100));
 }
 
+/**
+ * nilfs_max_segment_count - calculate the maximum number of segments
+ * @nilfs: nilfs object
+ */
+static u64 nilfs_max_segment_count(struct the_nilfs *nilfs)
+{
+	u64 max_count = U64_MAX;
+
+	do_div(max_count, nilfs->ns_blocks_per_segment);
+	return min_t(u64, max_count, ULONG_MAX);
+}
+
 void nilfs_set_nsegments(struct the_nilfs *nilfs, unsigned long nsegs)
 {
 	nilfs->ns_nsegments = nsegs;
@@ -414,6 +426,8 @@ void nilfs_set_nsegments(struct the_nilfs *nilfs, unsigned long nsegs)
 static int nilfs_store_disk_layout(struct the_nilfs *nilfs,
 				   struct nilfs_super_block *sbp)
 {
+	u64 nsegments, nblocks;
+
 	if (le32_to_cpu(sbp->s_rev_level) < NILFS_MIN_SUPP_REV) {
 		nilfs_err(nilfs->ns_sb,
 			  "unsupported revision (superblock rev.=%d.%d, current rev.=%d.%d). Please check the version of mkfs.nilfs(2).",
@@ -457,7 +471,34 @@ static int nilfs_store_disk_layout(struct the_nilfs *nilfs,
 		return -EINVAL;
 	}
 
-	nilfs_set_nsegments(nilfs, le64_to_cpu(sbp->s_nsegments));
+	nsegments = le64_to_cpu(sbp->s_nsegments);
+	if (nsegments > nilfs_max_segment_count(nilfs)) {
+		nilfs_err(nilfs->ns_sb,
+			  "segment count %llu exceeds upper limit (%llu segments)",
+			  (unsigned long long)nsegments,
+			  (unsigned long long)nilfs_max_segment_count(nilfs));
+		return -EINVAL;
+	}
+
+	nblocks = sb_bdev_nr_blocks(nilfs->ns_sb);
+	if (nblocks) {
+		u64 min_block_count = nsegments * nilfs->ns_blocks_per_segment;
+		/*
+		 * To avoid failing to mount early device images without a
+		 * second superblock, exclude that block count from the
+		 * "min_block_count" calculation.
+		 */
+
+		if (nblocks < min_block_count) {
+			nilfs_err(nilfs->ns_sb,
+				  "total number of segment blocks %llu exceeds device size (%llu blocks)",
+				  (unsigned long long)min_block_count,
+				  (unsigned long long)nblocks);
+			return -EINVAL;
+		}
+	}
+
+	nilfs_set_nsegments(nilfs, nsegments);
 	nilfs->ns_crc_seed = le32_to_cpu(sbp->s_crc_seed);
 	return 0;
 }
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index efb09de4343d..b173c36bcab3 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2100,14 +2100,20 @@ static long ocfs2_fallocate(struct file *file, int mode, loff_t offset,
 	struct ocfs2_space_resv sr;
 	int change_size = 1;
 	int cmd = OCFS2_IOC_RESVSP64;
+	int ret = 0;
 
 	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
 		return -EOPNOTSUPP;
 	if (!ocfs2_writes_unwritten_extents(osb))
 		return -EOPNOTSUPP;
 
-	if (mode & FALLOC_FL_KEEP_SIZE)
+	if (mode & FALLOC_FL_KEEP_SIZE) {
 		change_size = 0;
+	} else {
+		ret = inode_newsize_ok(inode, offset + len);
+		if (ret)
+			return ret;
+	}
 
 	if (mode & FALLOC_FL_PUNCH_HOLE)
 		cmd = OCFS2_IOC_UNRESVSP64;
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 0b0e6a132101..988d1c076861 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -952,8 +952,10 @@ static void ocfs2_disable_quotas(struct ocfs2_super *osb)
 	for (type = 0; type < OCFS2_MAXQUOTAS; type++) {
 		if (!sb_has_quota_loaded(sb, type))
 			continue;
-		oinfo = sb_dqinfo(sb, type)->dqi_priv;
-		cancel_delayed_work_sync(&oinfo->dqi_sync_work);
+		if (!sb_has_quota_suspended(sb, type)) {
+			oinfo = sb_dqinfo(sb, type)->dqi_priv;
+			cancel_delayed_work_sync(&oinfo->dqi_sync_work);
+		}
 		inode = igrab(sb->s_dquot.files[type]);
 		/* Turn off quotas. This will remove all dquot structures from
 		 * memory and so they will be automatically synced to global
diff --git a/fs/super.c b/fs/super.c
index 34afe411cf2b..04bc62ab7dfe 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -54,7 +54,7 @@ static char *sb_writers_name[SB_FREEZE_LEVELS] = {
  * One thing we have to be careful of with a per-sb shrinker is that we don't
  * drop the last active reference to the superblock from within the shrinker.
  * If that happens we could trigger unregistering the shrinker from within the
- * shrinker path and that leads to deadlock on the shrinker_mutex. Hence we
+ * shrinker path and that leads to deadlock on the shrinker_rwsem. Hence we
  * take a passive reference to the superblock to avoid this from occurring.
  */
 static unsigned long super_cache_scan(struct shrinker *shrink,
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 0aa5caac5164..7cecd49e078b 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -1322,6 +1322,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 	bool basic_ioctls;
 	unsigned long start, end, vma_end;
 	struct vma_iterator vmi;
+	pgoff_t pgoff;
 
 	user_uffdio_register = (struct uffdio_register __user *) arg;
 
@@ -1449,6 +1450,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 
 	vma_iter_set(&vmi, start);
 	prev = vma_prev(&vmi);
+	if (vma->vm_start < start)
+		prev = vma;
 
 	ret = 0;
 	for_each_vma_range(vmi, vma, end) {
@@ -1472,8 +1475,9 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 		vma_end = min(end, vma->vm_end);
 
 		new_flags = (vma->vm_flags & ~__VM_UFFD_FLAGS) | vm_flags;
+		pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
 		prev = vma_merge(&vmi, mm, prev, start, vma_end, new_flags,
-				 vma->anon_vma, vma->vm_file, vma->vm_pgoff,
+				 vma->anon_vma, vma->vm_file, pgoff,
 				 vma_policy(vma),
 				 ((struct vm_userfaultfd_ctx){ ctx }),
 				 anon_vma_name(vma));
@@ -1553,6 +1557,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 	unsigned long start, end, vma_end;
 	const void __user *buf = (void __user *)arg;
 	struct vma_iterator vmi;
+	pgoff_t pgoff;
 
 	ret = -EFAULT;
 	if (copy_from_user(&uffdio_unregister, buf, sizeof(uffdio_unregister)))
@@ -1615,6 +1620,9 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 
 	vma_iter_set(&vmi, start);
 	prev = vma_prev(&vmi);
+	if (vma->vm_start < start)
+		prev = vma;
+
 	ret = 0;
 	for_each_vma_range(vmi, vma, end) {
 		cond_resched();
@@ -1652,8 +1660,9 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 			uffd_wp_range(vma, start, vma_end - start, false);
 
 		new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS;
+		pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
 		prev = vma_merge(&vmi, mm, prev, start, vma_end, new_flags,
-				 vma->anon_vma, vma->vm_file, vma->vm_pgoff,
+				 vma->anon_vma, vma->vm_file, pgoff,
 				 vma_policy(vma),
 				 NULL_VM_UFFD_CTX, anon_vma_name(vma));
 		if (prev) {