erofs: handle overlapped pclusters out of crafted images properly

commit 9e2f9d34dd12e6e5b244ec488bcebd0c2d566c50 upstream.

syzbot reported a task hang issue due to a deadlock case where it is
waiting for the folio lock of a cached folio that will be used for
cache I/Os.

After looking into the crafted fuzzed image, I found it's formed with
several overlapped big pclusters as below:

 Ext:   logical offset   |  length :     physical offset    |  length
   0:        0..   16384 |   16384 :     151552..    167936 |   16384
   1:    16384..   32768 |   16384 :     155648..    172032 |   16384
   2:    32768..   49152 |   16384 :  537223168.. 537239552 |   16384
...

Here, extent 0/1 are physically overlapped although it's entirely
_impossible_ for normal filesystem images generated by mkfs.

First, managed folios containing compressed data will be marked as
up-to-date and then unlocked immediately (unlike in-place folios) when
compressed I/Os are complete.  If physical blocks are not submitted in
the incremental order, there should be separate BIOs to avoid dependency
issues.  However, the current code mis-arranges z_erofs_fill_bio_vec()
and BIO submission which causes unexpected BIO waits.

Second, managed folios will be connected to their own pclusters for
efficient inter-queries.  However, this is somewhat hard to implement
easily if overlapped big pclusters exist.  Again, these only appear in
fuzzed images so let's simply fall back to temporary short-lived pages
for correctness.

Additionally, it justifies that referenced managed folios cannot be
truncated for now and reverts part of commit 2080ca1ed3e4 ("erofs: tidy
up `struct z_erofs_bvec`") for simplicity although it shouldn't be any
difference.

[Alexey: This patch follows linux 6.6.y conflict resolution changes of
struct folio -> struct page]

Reported-by: syzbot+4fc98ed414ae63d1ada2@syzkaller.appspotmail.com
Reported-by: syzbot+de04e06b28cfecf2281c@syzkaller.appspotmail.com
Reported-by: syzbot+c8c8238b394be4a1087d@syzkaller.appspotmail.com
Tested-by: syzbot+4fc98ed414ae63d1ada2@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/r/0000000000002fda01061e334873@google.com
Fixes: 8e6c8fa9f2e9 ("erofs: enable big pcluster feature")
Link: https://lore.kernel.org/r/20240910070847.3356592-1-hsiangkao@linux.alibaba.com
Signed-off-by: Alexey Panov <apanov@astralinux.ru>
Link: https://lore.kernel.org/r/20250304110558.8315-2-apanov@astralinux.ru
Link: https://lore.kernel.org/r/20250304110558.8315-1-apanov@astralinux.ru
[ Gao Xiang: re-address the previous Alexey's backport. ]
CVE: CVE-2024-47736
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index 6d504adbf5e34936e83c536b837aab0318265623..0461c41d15b114d497351d92571597e70af279ab 100644 (file)
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -1331,14 +1331,14 @@ repeat:
                goto out;
 
        lock_page(page);
-
-       /* only true if page reclaim goes wrong, should never happen */
-       DBG_BUGON(justfound && PagePrivate(page));
-
-       /* the page is still in manage cache */
-       if (page->mapping == mc) {
+       if (likely(page->mapping == mc)) {
                WRITE_ONCE(pcl->compressed_bvecs[nr].page, page);
+               oldpage = page;
 
+               /*
+                * The cached folio is still in managed cache but without
+                * a valid `->private` pcluster hint.  Let's reconnect them.
+                */
                if (!PagePrivate(page)) {
                        /*
                         * impossible to be !PagePrivate(page) for
@@ -1352,22 +1352,24 @@ repeat:
                        SetPagePrivate(page);
                }
 
-               /* no need to submit io if it is already up-to-date */
-               if (PageUptodate(page)) {
-                       unlock_page(page);
-                       page = NULL;
+               if (likely(page->private == (unsigned long)pcl)) {
+                       /* don't submit cache I/Os again if already uptodate */
+                       if (PageUptodate(page)) {
+                               unlock_page(page);
+                               page = NULL;
+
+                       }
+                       goto out;
                }
-               goto out;
+               /*
+                * Already linked with another pcluster, which only appears in
+                * crafted images by fuzzers for now.  But handle this anyway.
+                */
+               tocache = false;        /* use temporary short-lived pages */
+       } else {
+               DBG_BUGON(1); /* referenced managed folios can't be truncated */
+               tocache = true;
        }
-
-       /*
-        * the managed page has been truncated, it's unsafe to
-        * reuse this one, let's allocate a new cache-managed page.
-        */
-       DBG_BUGON(page->mapping);
-       DBG_BUGON(!justfound);
-
-       tocache = true;
        unlock_page(page);
        put_page(page);
 out_allocpage:
@@ -1520,16 +1522,11 @@ static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f,
                end = cur + pcl->pclusterpages;
 
                do {
-                       struct page *page;
-
-                       page = pickup_page_for_submission(pcl, i++,
-                                       &f->pagepool, mc);
-                       if (!page)
-                               continue;
+                       struct page *page = NULL;
 
                        if (bio && (cur != last_index + 1 ||
                                    last_bdev != mdev.m_bdev)) {
-submit_bio_retry:
+drain_io:
                                submit_bio(bio);
                                if (memstall) {
                                        psi_memstall_leave(&pflags);
@@ -1538,6 +1535,13 @@ submit_bio_retry:
                                bio = NULL;
                        }
 
+                       if (!page) {
+                               page = pickup_page_for_submission(pcl, i++,
+                                               &f->pagepool, mc);
+                               if (!page)
+                                       continue;
+                       }
+
                        if (unlikely(PageWorkingset(page)) && !memstall) {
                                psi_memstall_enter(&pflags);
                                memstall = 1;
@@ -1558,7 +1562,7 @@ submit_bio_retry:
                        }
 
                        if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE)
-                               goto submit_bio_retry;
+                               goto drain_io;
 
                        last_index = cur;
                        bypass = false;