From: Bibo Mao <maobibo@loongson.cn>
To: Huacai Chen <chenhuacai@kernel.org>,
Andrey Ryabinin <ryabinin.a.a@gmail.com>,
Andrew Morton <akpm@linux-foundation.org>
Cc: David Hildenbrand <david@redhat.com>,
Barry Song <baohua@kernel.org>,
loongarch@lists.linux.dev, linux-kernel@vger.kernel.org,
kasan-dev@googlegroups.com, linux-mm@kvack.org
Subject: [PATCH 0/4] LoongArch: Fix vmalloc test issue
Date: Thu, 10 Oct 2024 11:50:44 +0800 [thread overview]
Message-ID: <20241010035048.3422527-1-maobibo@loongson.cn> (raw)
On LoongArch 3C5000 Dual-Way machine, there are 32 CPUs and 128G RAM,
there are some errors with run vmalloc test with command like this
insmod test_vmalloc.ko nr_threads=32 run_test_mask=0x3af
Here is part of error message,
WARNING: CPU: 13 PID: 1457 at mm/vmalloc.c:503 vmap_small_pages_range_noflush+0x388/0x510
CPU: 13 UID: 0 PID: 1457 Comm: vmalloc_test/15 Not tainted 6.12.0-rc2+ #93
Trying to vfree() nonexistent vm area (000000004dec9ced)
WARNING: CPU: 3 PID: 1444 at mm/vmalloc.c:3345 vfree+0x1e8/0x4c8
CPU: 3 UID: 0 PID: 1444 Comm: vmalloc_test/2
Trying to vfree() bad address (00000000fc7c9da5)
WARNING: CPU: 10 PID: 1552 at mm/vmalloc.c:3210 remove_vm_area+0x88/0x98
CPU: 10 UID: 0 PID: 1552 Comm: kworker/u144:3
The mainly problem is that function set_pte() and pte_free() is atomic,
there is contension between them. Since these functions need modify
two consecutive pte entries for kernel space area, to assure that both
pte entries with PAGE_GLOBAL bit set.
With this patchset, vmalloc test case passes to run with command
insmod test_vmalloc.ko nr_threads=32 run_test_mask=0x3af
Bibo Mao (4):
LoongArch: Set pte entry with PAGE_GLOBAL for kernel space
mm/sparse-vmemmap: set pte_init when vmemmap is created
LoongArch: Add barrier between set_pte and memory access
LoongArch: Use atomic operation with set_pte and pte_clear function
arch/loongarch/include/asm/cacheflush.h | 14 +++++++-
arch/loongarch/include/asm/pgalloc.h | 13 +++++++
arch/loongarch/include/asm/pgtable.h | 45 +++++++++----------------
arch/loongarch/mm/init.c | 4 ++-
arch/loongarch/mm/kasan_init.c | 4 ++-
arch/loongarch/mm/pgtable.c | 22 ++++++++++++
mm/sparse-vmemmap.c | 5 +++
7 files changed, 75 insertions(+), 32 deletions(-)
base-commit: 87d6aab2389e5ce0197d8257d5f8ee965a67c4cd
--
2.39.3
next reply other threads:[~2024-10-10 3:50 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-10-10 3:50 Bibo Mao [this message]
2024-10-10 3:50 ` [PATCH 1/4] LoongArch: Set pte entry with PAGE_GLOBAL for kernel space Bibo Mao
2024-10-12 2:15 ` Huacai Chen
2024-10-12 2:40 ` maobibo
2024-10-10 3:50 ` [PATCH 2/4] mm/sparse-vmemmap: set pte_init when vmemmap is created Bibo Mao
2024-10-11 4:42 ` kernel test robot
2024-10-11 4:42 ` kernel test robot
2024-10-12 2:17 ` Huacai Chen
2024-10-10 3:50 ` [PATCH 3/4] LoongArch: Add barrier between set_pte and memory access Bibo Mao
2024-10-12 2:16 ` Huacai Chen
2024-10-12 2:48 ` maobibo
2024-10-10 3:50 ` [PATCH 4/4] LoongArch: Use atomic operation with set_pte and pte_clear function Bibo Mao
2024-10-12 2:16 ` Huacai Chen
2024-10-12 2:51 ` maobibo
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20241010035048.3422527-1-maobibo@loongson.cn \
--to=maobibo@loongson.cn \
--cc=akpm@linux-foundation.org \
--cc=baohua@kernel.org \
--cc=chenhuacai@kernel.org \
--cc=david@redhat.com \
--cc=kasan-dev@googlegroups.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=loongarch@lists.linux.dev \
--cc=ryabinin.a.a@gmail.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox