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;
Date:   Sat, 13 Feb 2021 14:12:38 +0000
To:     "David S. Miller" <davem@davemloft.net>,
        Jakub Kicinski <kuba@kernel.org>
From:   Alexander Lobakin <alobakin@pm.me>
Cc:     Jonathan Lemon <jonathan.lemon@gmail.com>,
        Eric Dumazet <edumazet@google.com>,
        Dmitry Vyukov <dvyukov@google.com>,
        Willem de Bruijn <willemb@google.com>,
        Alexander Lobakin <alobakin@pm.me>,
        Randy Dunlap <rdunlap@infradead.org>,
        Kevin Hao <haokexin@gmail.com>,
        Pablo Neira Ayuso <pablo@netfilter.org>,
        Jakub Sitnicki <jakub@cloudflare.com>,
        Marco Elver <elver@google.com>,
        Dexuan Cui <decui@microsoft.com>,
        Paolo Abeni <pabeni@redhat.com>,
        Jesper Dangaard Brouer <brouer@redhat.com>,
        Alexander Duyck <alexanderduyck@fb.com>,
        Alexander Duyck <alexander.duyck@gmail.com>,
        Alexei Starovoitov <ast@kernel.org>,
        Daniel Borkmann <daniel@iogearbox.net>,
        Andrii Nakryiko <andriin@fb.com>,
        Taehee Yoo <ap420073@gmail.com>, Wei Wang <weiwan@google.com>,
        Cong Wang <xiyou.wangcong@gmail.com>,
        =?utf-8?Q?Bj=C3=B6rn_T=C3=B6pel?= <bjorn@kernel.org>,
        Miaohe Lin <linmiaohe@huawei.com>,
        Guillaume Nault <gnault@redhat.com>,
        Florian Westphal <fw@strlen.de>,
        Edward Cree <ecree.xilinx@gmail.com>,
        linux-kernel@vger.kernel.org, netdev@vger.kernel.org
Reply-To: Alexander Lobakin <alobakin@pm.me>
Subject: [PATCH v6 net-next 09/11] skbuff: allow to optionally use NAPI cache from __alloc_skb()
Message-ID: <20210213141021.87840-10-alobakin@pm.me>
In-Reply-To: <20210213141021.87840-1-alobakin@pm.me>
References: <20210213141021.87840-1-alobakin@pm.me>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: quoted-printable
Precedence: bulk

Reuse the old and forgotten SKB_ALLOC_NAPI to add an option to get
an skbuff_head from the NAPI cache instead of inplace allocation
inside __alloc_skb().
This implies that the function is called from softirq or BH-off
context, not for allocating a clone or from a distant node.

Cc: Alexander Duyck <alexander.duyck@gmail.com> # Simplified flags check
Signed-off-by: Alexander Lobakin <alobakin@pm.me>
---
 net/core/skbuff.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 9e1a8ded4acc..a80581eed7fc 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -405,7 +405,11 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t g=
fp_mask,
 =09=09gfp_mask |=3D __GFP_MEMALLOC;
=20
 =09/* Get the HEAD */
-=09skb =3D kmem_cache_alloc_node(cache, gfp_mask & ~__GFP_DMA, node);
+=09if ((flags & (SKB_ALLOC_FCLONE | SKB_ALLOC_NAPI)) =3D=3D SKB_ALLOC_NAPI=
 &&
+=09    likely(node =3D=3D NUMA_NO_NODE || node =3D=3D numa_mem_id()))
+=09=09skb =3D napi_skb_cache_get();
+=09else
+=09=09skb =3D kmem_cache_alloc_node(cache, gfp_mask & ~GFP_DMA, node);
 =09if (unlikely(!skb))
 =09=09return NULL;
 =09prefetchw(skb);
--=20
2.30.1