[PATCH 5.4.y 2/2] erofs: fix unsafe pagevec reuse of hooked pclusters

[Gao Xiang]

commit 86432a6dca9bed79111990851df5756d3eb5f57c upstream.

There are pclusters in runtime marked with Z_EROFS_PCLUSTER_TAIL
before actual I/O submission. Thus, the decompression chain can be
extended if the following pcluster chain hooks such tail pcluster.

As the related comment mentioned, if some page is made of a hooked
pcluster and another followed pcluster, it can be reused for in-place
I/O (since I/O should be submitted anyway):
 _______________________________________________________________
|  tail (partial) page |          head (partial) page           |
|_____PRIMARY_HOOKED___|____________PRIMARY_FOLLOWED____________|

However, it's by no means safe to reuse as pagevec since if such
PRIMARY_HOOKED pclusters finally move into bypass chain without I/O
submission. It's somewhat hard to reproduce with LZ4 and I just found
it (general protection fault) by ro_fsstressing a LZMA image for long
time.

I'm going to actively clean up related code together with multi-page
folio adaption in the next few months. Let's address it directly for
easier backporting for now.

Call trace for reference:
  z_erofs_decompress_pcluster+0x10a/0x8a0 [erofs]
  z_erofs_decompress_queue.isra.36+0x3c/0x60 [erofs]
  z_erofs_runqueue+0x5f3/0x840 [erofs]
  z_erofs_readahead+0x1e8/0x320 [erofs]
  read_pages+0x91/0x270
  page_cache_ra_unbounded+0x18b/0x240
  filemap_get_pages+0x10a/0x5f0
  filemap_read+0xa9/0x330
  new_sync_read+0x11b/0x1a0
  vfs_read+0xf1/0x190

Link: https://lore.kernel.org/r/20211103182006.4040-1-xiang@kernel.org
Fixes: 3883a79abd02 ("staging: erofs: introduce VLE decompression support")
Cc: <stable at vger.kernel.org> # 4.19+
Reviewed-by: Chao Yu <chao at kernel.org>
Signed-off-by: Gao Xiang <hsiangkao at linux.alibaba.com>
---
 fs/erofs/zdata.c | 13 +++++++------
 fs/erofs/zpvec.h | 13 ++++++++++---
 2 files changed, 17 insertions(+), 9 deletions(-)

diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index f784feaeb819..fdd18c250811 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -288,8 +288,8 @@ static inline bool z_erofs_try_inplace_io(struct z_erofs_collector *clt,
 
 /* callers must be with collection lock held */
 static int z_erofs_attach_page(struct z_erofs_collector *clt,
-			       struct page *page,
-			       enum z_erofs_page_type type)
+			       struct page *page, enum z_erofs_page_type type,
+			       bool pvec_safereuse)
 {
 	int ret;
 
@@ -299,9 +299,9 @@ static int z_erofs_attach_page(struct z_erofs_collector *clt,
 	    z_erofs_try_inplace_io(clt, page))
 		return 0;
 
-	ret = z_erofs_pagevec_enqueue(&clt->vector, page, type);
+	ret = z_erofs_pagevec_enqueue(&clt->vector, page, type,
+				      pvec_safereuse);
 	clt->cl->vcnt += (unsigned int)ret;
-
 	return ret ? 0 : -EAGAIN;
 }
 
@@ -652,14 +652,15 @@ static int z_erofs_do_read_page(struct z_erofs_decompress_frontend *fe,
 		tight &= (clt->mode >= COLLECT_PRIMARY_FOLLOWED);
 
 retry:
-	err = z_erofs_attach_page(clt, page, page_type);
+	err = z_erofs_attach_page(clt, page, page_type,
+				  clt->mode >= COLLECT_PRIMARY_FOLLOWED);
 	/* should allocate an additional staging page for pagevec */
 	if (err == -EAGAIN) {
 		struct page *const newpage =
 			__stagingpage_alloc(pagepool, GFP_NOFS);
 
 		err = z_erofs_attach_page(clt, newpage,
-					  Z_EROFS_PAGE_TYPE_EXCLUSIVE);
+					  Z_EROFS_PAGE_TYPE_EXCLUSIVE, true);
 		if (!err)
 			goto retry;
 	}
diff --git a/fs/erofs/zpvec.h b/fs/erofs/zpvec.h
index a38c52610367..6a20b2c3a24c 100644
--- a/fs/erofs/zpvec.h
+++ b/fs/erofs/zpvec.h
@@ -107,11 +107,18 @@ static inline void z_erofs_pagevec_ctor_init(struct z_erofs_pagevec_ctor *ctor,
 
 static inline bool z_erofs_pagevec_enqueue(struct z_erofs_pagevec_ctor *ctor,
 					   struct page *page,
-					   enum z_erofs_page_type type)
+					   enum z_erofs_page_type type,
+					   bool pvec_safereuse)
 {
-	if (!ctor->next && type)
-		if (ctor->index + 1 == ctor->nr)
+	if (!ctor->next) {
+		/* some pages cannot be reused as pvec safely without I/O */
+		if (type == Z_EROFS_PAGE_TYPE_EXCLUSIVE && !pvec_safereuse)
+			type = Z_EROFS_VLE_PAGE_TYPE_TAIL_SHARED;
+
+		if (type != Z_EROFS_PAGE_TYPE_EXCLUSIVE &&
+		    ctor->index + 1 == ctor->nr)
 			return false;
+	}
 
 	if (ctor->index >= ctor->nr)
 		z_erofs_pagevec_ctor_pagedown(ctor, false);
-- 
2.24.4