@@ -795,6 +795,7 @@ __page_pool_put_page(struct page_pool *pool, netmem_ref netmem,
static bool page_pool_napi_local(const struct page_pool *pool)
{
const struct napi_struct *napi;
+ bool napi_local;
u32 cpuid;
if (unlikely(!in_softirq()))
@@ -810,9 +811,15 @@ static bool page_pool_napi_local(const struct page_pool *pool)
if (READ_ONCE(pool->cpuid) == cpuid)
return true;
+ /* Synchronizated with page_pool_destory() to avoid use-after-free
+ * for 'napi'.
+ */
+ rcu_read_lock();
napi = READ_ONCE(pool->p.napi);
+ napi_local = napi && READ_ONCE(napi->list_owner) == cpuid;
+ rcu_read_unlock();
- return napi && READ_ONCE(napi->list_owner) == cpuid;
+ return napi_local;
}
void page_pool_put_unrefed_netmem(struct page_pool *pool, netmem_ref netmem,
@@ -1126,6 +1133,12 @@ void page_pool_destroy(struct page_pool *pool)
if (!page_pool_release(pool))
return;
+ /* Paired with rcu lock in page_pool_napi_local() to enable clearing
+ * of pool->p.napi in page_pool_disable_direct_recycling() is seen
+ * before returning to driver to free the napi instance.
+ */
+ synchronize_rcu();
+
page_pool_detached(pool);
pool->defer_start = jiffies;
pool->defer_warn = jiffies + DEFER_WARN_INTERVAL;
page_pool page may be freed from skb_defer_free_flush() in softirq context without binding to any specific napi, it may cause use-after-free problem due to the below time window, as below, CPU1 may still access napi->list_owner after CPU0 free the napi memory: CPU 0 CPU1 page_pool_destroy() skb_defer_free_flush() . . . napi = READ_ONCE(pool->p.napi); . . page_pool_disable_direct_recycling() . driver free napi memory . . . . napi && READ_ONCE(napi->list_owner) == cpuid . . Use rcu mechanism to avoid the above 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> --- As the IOMMU fix patch depends on synchronize_rcu() added in this patch and the time window is so small that it doesn't seem to be an urgent fix, so target the net-next as the IOMMU fix patch does. --- net/core/page_pool.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-)