Merging upstream version 4.19.289.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

9 files changed, 140 insertions, 10 deletions

diff --git a/fs/nilfs2/bmap.c b/fs/nilfs2/bmap.c
index fb5a9a8a1..2ba57e4b4 100644
--- a/fs/nilfs2/bmap.c
+++ b/fs/nilfs2/bmap.c
@@ -67,20 +67,28 @@ int nilfs_bmap_lookup_at_level(struct nilfs_bmap *bmap, __u64 key, int level,
 
 	down_read(&bmap->b_sem);
 	ret = bmap->b_ops->bop_lookup(bmap, key, level, ptrp);
-	if (ret < 0) {
-		ret = nilfs_bmap_convert_error(bmap, __func__, ret);
+	if (ret < 0)
 		goto out;
-	}
+
 	if (NILFS_BMAP_USE_VBN(bmap)) {
 		ret = nilfs_dat_translate(nilfs_bmap_get_dat(bmap), *ptrp,
 					  &blocknr);
 		if (!ret)
 			*ptrp = blocknr;
+		else if (ret == -ENOENT) {
+			/*
+			 * If there was no valid entry in DAT for the block
+			 * address obtained by b_ops->bop_lookup, then pass
+			 * internal code -EINVAL to nilfs_bmap_convert_error
+			 * to treat it as metadata corruption.
+			 */
+			ret = -EINVAL;
+		}
 	}
 
  out:
 	up_read(&bmap->b_sem);
-	return ret;
+	return nilfs_bmap_convert_error(bmap, __func__, ret);
 }
 
 int nilfs_bmap_lookup_contig(struct nilfs_bmap *bmap, __u64 key, __u64 *ptrp,
diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c
index 138ebbb7a..677ff78d5 100644
--- a/fs/nilfs2/btnode.c
+++ b/fs/nilfs2/btnode.c
@@ -295,6 +295,14 @@ void nilfs_btnode_abort_change_key(struct address_space *btnc,
 		radix_tree_delete(&btnc->i_pages, newkey);
 		xa_unlock_irq(&btnc->i_pages);
 		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/inode.c b/fs/nilfs2/inode.c
index cf01aa55d..53ec342eb 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -930,6 +930,7 @@ void nilfs_evict_inode(struct inode *inode)
 	struct nilfs_transaction_info ti;
 	struct super_block *sb = inode->i_sb;
 	struct nilfs_inode_info *ii = NILFS_I(inode);
+	struct the_nilfs *nilfs;
 	int ret;
 
 	if (inode->i_nlink || !ii->i_root || unlikely(is_bad_inode(inode))) {
@@ -942,6 +943,23 @@ void nilfs_evict_inode(struct inode *inode)
 
 	truncate_inode_pages_final(&inode->i_data);
 
+	nilfs = sb->s_fs_info;
+	if (unlikely(sb_rdonly(sb) || !nilfs->ns_writer)) {
+		/*
+		 * If this inode is about to be disposed after the file system
+		 * has been degraded to read-only due to file system corruption
+		 * or after the writer has been detached, do not make any
+		 * changes that cause writes, just clear it.
+		 * Do this check after read-locking ns_segctor_sem by
+		 * nilfs_transaction_begin() in order to avoid a race with
+		 * the writer detach operation.
+		 */
+		clear_inode(inode);
+		nilfs_clear_inode(inode);
+		nilfs_transaction_abort(sb);
+		return;
+	}
+
 	/* TODO: some of the following operations may fail.  */
 	nilfs_truncate_bmap(ii, 0);
 	nilfs_mark_inode_dirty(inode);
diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c
index c726b42ca..e5fee7fac 100644
--- a/fs/nilfs2/page.c
+++ b/fs/nilfs2/page.c
@@ -372,7 +372,15 @@ void nilfs_clear_dirty_pages(struct address_space *mapping, bool silent)
 			struct page *page = pvec.pages[i];
 
 			lock_page(page);
-			nilfs_clear_dirty_page(page, silent);
+
+			/*
+			 * This page may have been removed from the address
+			 * space by truncation or invalidation when the lock
+			 * was acquired.  Skip processing in that case.
+			 */
+			if (likely(page->mapping == mapping))
+				nilfs_clear_dirty_page(page, silent);
+
 			unlock_page(page);
 		}
 		pagevec_release(&pvec);
diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c
index 20c479b5e..e72466fc8 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 b23ed9a35..d9e0b2b2b 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -984,10 +984,13 @@ 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() ?
@@ -1001,6 +1004,8 @@ 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)
@@ -1778,6 +1783,7 @@ 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);
@@ -1789,6 +1795,7 @@ 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;
@@ -2039,6 +2046,9 @@ static int nilfs_segctor_do_construct(struct nilfs_sc_info *sci, int mode)
 	struct the_nilfs *nilfs = sci->sc_super->s_fs_info;
 	int err;
 
+	if (sb_rdonly(sci->sc_super))
+		return -EROFS;
+
 	nilfs_sc_cstage_set(sci, NILFS_ST_INIT);
 	sci->sc_cno = nilfs->ns_cno;
 
@@ -2724,7 +2734,7 @@ static void nilfs_segctor_write_out(struct nilfs_sc_info *sci)
 
 		flush_work(&sci->sc_iput_work);
 
-	} while (ret && retrycount-- > 0);
+	} while (ret && ret != -EROFS && retrycount-- > 0);
 }
 
 /**
diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c
index 150845a43..d85d3c758 100644
--- a/fs/nilfs2/sufile.c
+++ b/fs/nilfs2/sufile.c
@@ -782,6 +782,15 @@ 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 221a54faa..99bcb4ab4 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -374,10 +374,31 @@ 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 24f626e7d..d550a5646 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -375,6 +375,18 @@ 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;
@@ -384,6 +396,8 @@ 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_msg(nilfs->ns_sb, KERN_ERR,
 			  "unsupported revision (superblock rev.=%d.%d, current rev.=%d.%d). Please check the version of mkfs.nilfs(2).",
@@ -430,7 +444,35 @@ 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_msg(nilfs->ns_sb, KERN_ERR,
+			  "segment count %llu exceeds upper limit (%llu segments)",
+			  (unsigned long long)nsegments,
+			  (unsigned long long)nilfs_max_segment_count(nilfs));
+		return -EINVAL;
+	}
+
+	nblocks = (u64)i_size_read(nilfs->ns_sb->s_bdev->bd_inode) >>
+		nilfs->ns_sb->s_blocksize_bits;
+	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_msg(nilfs->ns_sb, KERN_ERR,
+				  "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;
 }