Re: [PATCH] net: fix sk_page_frag() recursion from memory reclaim
From: Tejun Heo <tj@kernel.org>
Date: 2019-10-19 21:19:03
Also in:
lkml
Hello, On Sat, Oct 19, 2019 at 11:15:28AM -0700, Eric Dumazet wrote:
quoted hunk ↗ jump to hunk
It seems compiler generates better code with :diff --git a/include/net/sock.h b/include/net/sock.h index ab905c4b1f0efd42ebdcae333b3f0a2c7c1b2248..56de6ac99f0952bd0bc003353c094ce3a5a852f4 100644 --- a/include/net/sock.h +++ b/include/net/sock.h@@ -2238,7 +2238,8 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp, */ static inline struct page_frag *sk_page_frag(struct sock *sk) { - if (gfpflags_allow_blocking(sk->sk_allocation)) + if (likely((sk->sk_allocation & (__GFP_DIRECT_RECLAIM | __GFP_MEMALLOC)) == + __GFP_DIRECT_RECLAIM)) return ¤t->task_frag; return &sk->sk_frag;WDYT ?
Whatever works is fine by me. gfpflags_allow_blocking() is clearer than testing __GFP_DIRECT_RECLAIM directly tho. Maybe a better way is introducing a new gfpflags_ helper? Thanks. -- tejun