From ad0bcbd2d19f9ee29bc4287d151920676076a36d Mon Sep 17 00:00:00 2001 From: Andrew Yang Date: Fri, 21 Jul 2023 14:37:01 +0800 Subject: [PATCH] zsmalloc: fix races between modifications of fullness and isolated commit 4b5d1e47b69426c0f7491d97d73ad0152d02d437 upstream. 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 Reviewed-by: Sergey Senozhatsky Cc: AngeloGioacchino Del Regno Cc: Matthias Brugger Cc: Minchan Kim Cc: Sebastian Andrzej Siewior Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/zsmalloc.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 02f7f414aade..4def13ee071c 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -1977,6 +1977,7 @@ 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; /* @@ -1986,9 +1987,10 @@ 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; } @@ -2054,12 +2056,12 @@ 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); @@ -2076,14 +2078,16 @@ 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 = {