zsmalloc: fix races between modifications of fullness and isolated

We encountered many kernel exceptions of VM_BUG_ON(zspage->isolated ==
0) in dec_zspage_isolation() and BUG_ON(!pages[1]) in zs_unmap_object()
lately.  This issue only occurs when migration and reclamation occur at
the same time.

With our memory stress test, we can reproduce this issue several times
a day.  We have no idea why no one else encountered this issue.  BTW,
we switched to the new kernel version with this defect a few months
ago.

Since fullness and isolated share the same unsigned int, modifications of
them should be protected by the same lock.

[andrew.yang@mediatek.com: move comment]
Link: https://lkml.kernel.org/r/20230727062910.6337-1-andrew.yang@mediatek.com
Link: https://lkml.kernel.org/r/20230721063705.11455-1-andrew.yang@mediatek.com
Fixes: c4549b871102 ("zsmalloc: remove zspage isolation for migration")
Signed-off-by: Andrew Yang <andrew.yang@mediatek.com>
Reviewed-by: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Cc: Matthias Brugger <matthias.bgg@gmail.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 3f05797..32916d2 100644 (file)
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -1798,6 +1798,7 @@ static void replace_sub_page(struct size_class *class, struct zspage *zspage,
 
 static bool zs_page_isolate(struct page *page, isolate_mode_t mode)
 {
+       struct zs_pool *pool;
        struct zspage *zspage;
 
        /*
@@ -1807,9 +1808,10 @@ static bool zs_page_isolate(struct page *page, isolate_mode_t mode)
        VM_BUG_ON_PAGE(PageIsolated(page), page);
 
        zspage = get_zspage(page);
-       migrate_write_lock(zspage);
+       pool = zspage->pool;
+       spin_lock(&pool->lock);
        inc_zspage_isolation(zspage);
-       migrate_write_unlock(zspage);
+       spin_unlock(&pool->lock);
 
        return true;
 }
@@ -1875,12 +1877,12 @@ static int zs_page_migrate(struct page *newpage, struct page *page,
        kunmap_atomic(s_addr);
 
        replace_sub_page(class, zspage, newpage, page);
+       dec_zspage_isolation(zspage);
        /*
         * Since we complete the data copy and set up new zspage structure,
         * it's okay to release the pool's lock.
         */
        spin_unlock(&pool->lock);
-       dec_zspage_isolation(zspage);
        migrate_write_unlock(zspage);
 
        get_page(newpage);
@@ -1897,14 +1899,16 @@ static int zs_page_migrate(struct page *newpage, struct page *page,
 
 static void zs_page_putback(struct page *page)
 {
+       struct zs_pool *pool;
        struct zspage *zspage;
 
        VM_BUG_ON_PAGE(!PageIsolated(page), page);
 
        zspage = get_zspage(page);
-       migrate_write_lock(zspage);
+       pool = zspage->pool;
+       spin_lock(&pool->lock);
        dec_zspage_isolation(zspage);
-       migrate_write_unlock(zspage);
+       spin_unlock(&pool->lock);
 }
 
 static const struct movable_operations zsmalloc_mops = {