Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Sasha Levin <sashal@kernel.org>
To:     linux-kernel@vger.kernel.org, stable@vger.kernel.org
Cc:     Xu Yu <xuyu@linux.alibaba.com>, Hugh Dickins <hughd@google.com>,
        Gang Deng <gavin.dg@linux.alibaba.com>,
        "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>,
        Matthew Wilcox <willy@infradead.org>,
        Andrew Morton <akpm@linux-foundation.org>,
        Linus Torvalds <torvalds@linux-foundation.org>,
        Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Subject: [PATCH 5.12 082/110] mm, thp: use head page in __migration_entry_wait()
Date:   Mon, 28 Jun 2021 10:18:00 -0400
Message-Id: <20210628141828.31757-83-sashal@kernel.org>
In-Reply-To: <20210628141828.31757-1-sashal@kernel.org>
References: <20210628141828.31757-1-sashal@kernel.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: Xu Yu <xuyu@linux.alibaba.com>

commit ffc90cbb2970ab88b66ea51dd580469eede57b67 upstream.

We notice that hung task happens in a corner but practical scenario when
CONFIG_PREEMPT_NONE is enabled, as follows.

Process 0                       Process 1                     Process 2..Inf
split_huge_page_to_list
    unmap_page
        split_huge_pmd_address
                                __migration_entry_wait(head)
                                                              __migration_entry_wait(tail)
    remap_page (roll back)
        remove_migration_ptes
            rmap_walk_anon
                cond_resched

Where __migration_entry_wait(tail) is occurred in kernel space, e.g.,
copy_to_user in fstat, which will immediately fault again without
rescheduling, and thus occupy the cpu fully.

When there are too many processes performing __migration_entry_wait on
tail page, remap_page will never be done after cond_resched.

This makes __migration_entry_wait operate on the compound head page,
thus waits for remap_page to complete, whether the THP is split
successfully or roll back.

Note that put_and_wait_on_page_locked helps to drop the page reference
acquired with get_page_unless_zero, as soon as the page is on the wait
queue, before actually waiting.  So splitting the THP is only prevented
for a brief interval.

Link: https://lkml.kernel.org/r/b9836c1dd522e903891760af9f0c86a2cce987eb.1623144009.git.xuyu@linux.alibaba.com
Fixes: ba98828088ad ("thp: add option to setup migration entries during PMD split")
Suggested-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Gang Deng <gavin.dg@linux.alibaba.com>
Signed-off-by: Xu Yu <xuyu@linux.alibaba.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 mm/migrate.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/mm/migrate.c b/mm/migrate.c
index 773622cffe77..40455e753c5b 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -322,6 +322,7 @@ void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
 		goto out;
 
 	page = migration_entry_to_page(entry);
+	page = compound_head(page);
 
 	/*
 	 * Once page cache replacement of page migration started, page_count
-- 
2.30.2