erofs: fix unsafe pagevec reuse of hooked pclusters

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@vger.kernel.org> # 4.19+
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/drivers/staging/erofs/unzip_pagevec.h b/drivers/staging/erofs/unzip_pagevec.h
index 64724dd1e04e4afa3fa53b2d04a2c03484b4b9da..efbf541e11bb8f0f7410f599ee7a300c4c4a44be 100644 (file)
--- a/drivers/staging/erofs/unzip_pagevec.h
+++ b/drivers/staging/erofs/unzip_pagevec.h
@@ -117,11 +117,18 @@ static inline void z_erofs_pagevec_ctor_init(struct z_erofs_pagevec_ctor *ctor,
 static inline bool
 z_erofs_pagevec_ctor_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 (unlikely(ctor->next == NULL && 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 (unlikely(ctor->index >= ctor->nr))
                z_erofs_pagevec_ctor_pagedown(ctor, false);

diff --git a/drivers/staging/erofs/unzip_vle.c b/drivers/staging/erofs/unzip_vle.c
index 48c21a4d5dc8b8917d0e1858adad1b448f3d7e58..83e4d9384bd2d5c523cf230735ef49e6a9fca3c5 100644 (file)
--- a/drivers/staging/erofs/unzip_vle.c
+++ b/drivers/staging/erofs/unzip_vle.c
@@ -228,10 +228,10 @@ static inline bool try_to_reuse_as_compressed_page(
 }
 
 /* callers must be with work->lock held */
-static int z_erofs_vle_work_add_page(
-       struct z_erofs_vle_work_builder *builder,
-       struct page *page,
-       enum z_erofs_page_type type)
+static int z_erofs_vle_work_add_page(struct z_erofs_vle_work_builder *builder,
+                                    struct page *page,
+                                    enum z_erofs_page_type type,
+                                    bool pvec_safereuse)
 {
        int ret;
 
@@ -241,9 +241,9 @@ static int z_erofs_vle_work_add_page(
                try_to_reuse_as_compressed_page(builder, page))
                return 0;
 
-       ret = z_erofs_pagevec_ctor_enqueue(&builder->vector, page, type);
+       ret = z_erofs_pagevec_ctor_enqueue(&builder->vector, page, type,
+                                          pvec_safereuse);
        builder->work->vcnt += (unsigned)ret;
-
        return ret ? 0 : -EAGAIN;
 }
 
@@ -688,14 +688,15 @@ hitted:
                tight &= builder_is_followed(builder);
 
 retry:
-       err = z_erofs_vle_work_add_page(builder, page, page_type);
+       err = z_erofs_vle_work_add_page(builder, page, page_type,
+                                       builder_is_followed(builder));
        /* should allocate an additional staging page for pagevec */
        if (err == -EAGAIN) {
                struct page *const newpage =
                        __stagingpage_alloc(page_pool, GFP_NOFS);
 
                err = z_erofs_vle_work_add_page(builder,
-                       newpage, Z_EROFS_PAGE_TYPE_EXCLUSIVE);
+                       newpage, Z_EROFS_PAGE_TYPE_EXCLUSIVE, true);
                if (likely(!err))
                        goto retry;
        }