From: Yunsheng Lin <linyunsheng@huawei.com>
To: <davem@davemloft.net>, <kuba@kernel.org>, <pabeni@redhat.com>
Cc: <liuyonglong@huawei.com>, <fanghaiqing@huawei.com>,
<zhangkun09@huawei.com>, Yunsheng Lin <linyunsheng@huawei.com>,
Alexander Lobakin <aleksander.lobakin@intel.com>,
Jesper Dangaard Brouer <hawk@kernel.org>,
Ilias Apalodimas <ilias.apalodimas@linaro.org>,
Eric Dumazet <edumazet@google.com>, <netdev@vger.kernel.org>,
<linux-kernel@vger.kernel.org>
Subject: [PATCH net v2 1/2] page_pool: fix timing for checking and disabling napi_local
Date: Wed, 25 Sep 2024 15:57:06 +0800 [thread overview]
Message-ID: <20240925075707.3970187-2-linyunsheng@huawei.com> (raw)
In-Reply-To: <20240925075707.3970187-1-linyunsheng@huawei.com>
page_pool page may be freed from skb_defer_free_flush() to
softirq context, it may cause concurrent access problem for
pool->alloc cache due to the below time window, as below,
both CPU0 and CPU1 may access the pool->alloc cache
concurrently in page_pool_empty_alloc_cache_once() and
page_pool_recycle_in_cache():
CPU 0 CPU1
page_pool_destroy() skb_defer_free_flush()
. .
. page_pool_put_unrefed_page()
. .
. allow_direct = page_pool_napi_local()
. .
page_pool_disable_direct_recycling() .
. .
page_pool_empty_alloc_cache_once() page_pool_recycle_in_cache()
Use rcu mechanism to avoid the above concurrent access problem.
Note, the above was found during code reviewing on how to fix
the problem in [1].
1. https://lore.kernel.org/lkml/8067f204-1380-4d37-8ffd-007fc6f26738@kernel.org/T/
Fixes: dd64b232deb8 ("page_pool: unlink from napi during destroy")
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
CC: Alexander Lobakin <aleksander.lobakin@intel.com>
---
net/core/page_pool.c | 31 ++++++++++++++++++++++++++++---
1 file changed, 28 insertions(+), 3 deletions(-)
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index a813d30d2135..bec6e717cd22 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -818,8 +818,17 @@ static bool page_pool_napi_local(const struct page_pool *pool)
void page_pool_put_unrefed_netmem(struct page_pool *pool, netmem_ref netmem,
unsigned int dma_sync_size, bool allow_direct)
{
- if (!allow_direct)
+ bool allow_direct_orig = allow_direct;
+
+ /* page_pool_put_unrefed_netmem() is not supposed to be called with
+ * allow_direct being true after page_pool_destroy() is called, so
+ * the allow_direct being true case doesn't need synchronization.
+ */
+ DEBUG_NET_WARN_ON_ONCE(allow_direct && pool->destroy_cnt);
+ if (!allow_direct_orig) {
+ rcu_read_lock();
allow_direct = page_pool_napi_local(pool);
+ }
netmem =
__page_pool_put_page(pool, netmem, dma_sync_size, allow_direct);
@@ -828,6 +837,9 @@ void page_pool_put_unrefed_netmem(struct page_pool *pool, netmem_ref netmem,
recycle_stat_inc(pool, ring_full);
page_pool_return_page(pool, netmem);
}
+
+ if (!allow_direct_orig)
+ rcu_read_unlock();
}
EXPORT_SYMBOL(page_pool_put_unrefed_netmem);
@@ -861,6 +873,7 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data,
bool allow_direct;
bool in_softirq;
+ rcu_read_lock();
allow_direct = page_pool_napi_local(pool);
for (i = 0; i < count; i++) {
@@ -876,8 +889,10 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data,
data[bulk_len++] = (__force void *)netmem;
}
- if (!bulk_len)
+ if (!bulk_len) {
+ rcu_read_unlock();
return;
+ }
/* Bulk producer into ptr_ring page_pool cache */
in_softirq = page_pool_producer_lock(pool);
@@ -892,14 +907,18 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data,
page_pool_producer_unlock(pool, in_softirq);
/* Hopefully all pages was return into ptr_ring */
- if (likely(i == bulk_len))
+ if (likely(i == bulk_len)) {
+ rcu_read_unlock();
return;
+ }
/* ptr_ring cache full, free remaining pages outside producer lock
* since put_page() with refcnt == 1 can be an expensive operation
*/
for (; i < bulk_len; i++)
page_pool_return_page(pool, (__force netmem_ref)data[i]);
+
+ rcu_read_unlock();
}
EXPORT_SYMBOL(page_pool_put_page_bulk);
@@ -1121,6 +1140,12 @@ void page_pool_destroy(struct page_pool *pool)
return;
page_pool_disable_direct_recycling(pool);
+
+ /* Wait for the freeing side see the disabling direct recycling setting
+ * to avoid the concurrent access to the pool->alloc cache.
+ */
+ synchronize_rcu();
+
page_pool_free_frag(pool);
if (!page_pool_release(pool))
--
2.33.0
next prev parent reply other threads:[~2024-09-25 8:03 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-09-25 7:57 [PATCH net v2 0/2] fix two bugs related to page_pool Yunsheng Lin
2024-09-25 7:57 ` Yunsheng Lin [this message]
2024-09-26 20:06 ` [PATCH net v2 1/2] page_pool: fix timing for checking and disabling napi_local Joe Damato
2024-09-27 3:58 ` Yunsheng Lin
2024-10-01 11:30 ` Paolo Abeni
2024-10-02 1:52 ` Yunsheng Lin
2024-10-09 0:40 ` Jakub Kicinski
2024-10-09 3:33 ` Yunsheng Lin
2024-10-09 15:13 ` Jakub Kicinski
2024-10-10 9:14 ` Yunsheng Lin
2024-09-25 7:57 ` [PATCH net v2 2/2] page_pool: fix IOMMU crash when driver has already unbound Yunsheng Lin
2024-09-26 18:15 ` Mina Almasry
2024-09-27 3:57 ` Yunsheng Lin
2024-09-27 5:54 ` Mina Almasry
2024-09-27 7:25 ` Yunsheng Lin
2024-09-27 9:21 ` Ilias Apalodimas
2024-09-27 9:49 ` Yunsheng Lin
2024-09-27 9:58 ` Ilias Apalodimas
2024-09-27 11:29 ` Yunsheng Lin
2024-09-28 7:34 ` Ilias Apalodimas
2024-09-29 2:44 ` Yunsheng Lin
2024-09-30 8:09 ` Ilias Apalodimas
2024-09-30 8:38 ` Yunsheng Lin
2024-10-01 13:32 ` Paolo Abeni
2024-10-02 2:34 ` Yunsheng Lin
2024-10-02 7:37 ` Paolo Abeni
2024-10-02 8:23 ` Ilias Apalodimas
2024-10-05 12:38 ` Yunsheng Lin
2024-10-02 6:46 ` Ilias Apalodimas
2024-10-02 6:51 ` Ilias Apalodimas
2024-09-25 13:31 ` [PATCH net v2 0/2] fix two bugs related to page_pool Yonglong Liu
2024-10-12 12:05 ` Yunsheng Lin
2024-10-15 0:14 ` Jakub Kicinski
2024-10-15 10:52 ` Yunsheng Lin
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=20240925075707.3970187-2-linyunsheng@huawei.com \
--to=linyunsheng@huawei.com \
--cc=aleksander.lobakin@intel.com \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=fanghaiqing@huawei.com \
--cc=hawk@kernel.org \
--cc=ilias.apalodimas@linaro.org \
--cc=kuba@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=liuyonglong@huawei.com \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=zhangkun09@huawei.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
all inboxes | Powered by JetHome®