From mboxrd@z Thu Jan 1 00:00:00 1970 From: Steffen Klassert Subject: [PATCH RFC 2/3] net: Support GRO/GSO fraglist chaining. Date: Fri, 21 Dec 2018 08:53:33 +0100 Message-ID: <20181221075334.9000-3-steffen.klassert@secunet.com> References: <20181221075334.9000-1-steffen.klassert@secunet.com> Mime-Version: 1.0 Content-Type: text/plain Cc: Steffen Klassert , Willem de Bruijn , Paolo Abeni , "Jason A. Donenfeld" To: Return-path: Received: from a.mx.secunet.com ([62.96.220.36]:48882 "EHLO a.mx.secunet.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1731366AbeLUHxp (ORCPT ); Fri, 21 Dec 2018 02:53:45 -0500 In-Reply-To: <20181221075334.9000-1-steffen.klassert@secunet.com> Sender: netdev-owner@vger.kernel.org List-ID: This patch adds the core functions to chain/unchain GSO skbs at the frag_list pointer. This also adds a new GSO type SKB_GSO_FRAGLIST and a is_flist flag to napi_gro_cb which indicates that this flow will be GROed by fraglist chaining. Signed-off-by: Steffen Klassert --- include/linux/netdevice.h | 4 +- include/linux/skbuff.h | 4 ++ net/core/skbuff.c | 103 ++++++++++++++++++++++++++++++++++++++ 3 files changed, 110 insertions(+), 1 deletion(-) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index fc6ba71513be..ae907cae6461 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2294,7 +2294,8 @@ struct napi_gro_cb { /* Number of gro_receive callbacks this packet already went through */ u8 recursion_counter:4; - /* 1 bit hole */ + /* GRO is done by frag_list pointer chaining. */ + u8 is_flist:1; /* used to support CHECKSUM_COMPLETE for tunneling protocols */ __wsum csum; @@ -2648,6 +2649,7 @@ struct net_device *dev_get_by_napi_id(unsigned int napi_id); int netdev_get_name(struct net *net, char *name, int ifindex); int dev_restart(struct net_device *dev); int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb); +int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb); static inline unsigned int skb_gro_offset(const struct sk_buff *skb) { diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index b1831a5ca173..6a496c0dd0f1 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -578,6 +578,8 @@ enum { SKB_GSO_UDP = 1 << 16, SKB_GSO_UDP_L4 = 1 << 17, + + SKB_GSO_FRAGLIST = 1 << 18, }; #if BITS_PER_LONG > 32 @@ -3366,6 +3368,8 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet); bool skb_gso_validate_network_len(const struct sk_buff *skb, unsigned int mtu); bool skb_gso_validate_mac_len(const struct sk_buff *skb, unsigned int len); struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features); +struct sk_buff *skb_segment_list(struct sk_buff *skb, netdev_features_t features, + unsigned int offset); struct sk_buff *skb_vlan_untag(struct sk_buff *skb); int skb_ensure_writable(struct sk_buff *skb, int write_len); int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 40552547c69a..9ff44a3a2625 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3464,6 +3464,109 @@ static inline skb_frag_t skb_head_frag_to_page_desc(struct sk_buff *frag_skb) return head_frag; } +struct sk_buff *skb_segment_list(struct sk_buff *skb, + netdev_features_t features, + unsigned int offset) +{ + struct sk_buff *list_skb = skb_shinfo(skb)->frag_list; + unsigned int tnl_hlen = skb_tnl_header_len(skb); + unsigned int delta_truesize = 0; + unsigned int delta_len = 0; + struct sk_buff *tail = NULL; + struct sk_buff *nskb; + + skb_push(skb, -skb_network_offset(skb) + offset); + + skb_shinfo(skb)->frag_list = NULL; + + do { + nskb = list_skb; + list_skb = list_skb->next; + + if (!tail) + skb->next = nskb; + else + tail->next = nskb; + + tail = nskb; + + delta_len += nskb->len; + delta_truesize += nskb->truesize; + + skb_push(nskb, -skb_network_offset(nskb) + offset); + + if (!secpath_exists(nskb)) + nskb->sp = secpath_get(skb->sp); + + memcpy(nskb->cb, skb->cb, sizeof(skb->cb)); + + nskb->ip_summed = CHECKSUM_UNNECESSARY; + nskb->tstamp = skb->tstamp; + nskb->dev = skb->dev; + nskb->queue_mapping = skb->queue_mapping; + + nskb->mac_len = skb->mac_len; + nskb->mac_header = skb->mac_header; + nskb->transport_header = skb->transport_header; + nskb->network_header = skb->network_header; + skb_dst_copy(nskb, skb); + + skb_headers_offset_update(nskb, skb_headroom(nskb) - skb_headroom(skb)); + skb_copy_from_linear_data_offset(skb, -tnl_hlen, + nskb->data - tnl_hlen, + offset + tnl_hlen); + + if (skb_needs_linearize(nskb, features) && + __skb_linearize(nskb)) { + kfree_skb_list(skb); + return ERR_PTR(-EREMOTE); + } + } while (list_skb); + + skb->truesize = skb->truesize - delta_truesize; + skb->data_len = skb->data_len - delta_len; + skb->len = skb->len - delta_len; + + skb->ip_summed = CHECKSUM_UNNECESSARY; + + skb_gso_reset(skb); + + skb->prev = tail; + + if (skb_needs_linearize(skb, features) && + __skb_linearize(skb)) { + kfree_skb_list(skb); + return ERR_PTR(-EREMOTE); + } + + return skb; +} +EXPORT_SYMBOL_GPL(skb_segment_list); + +int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb) +{ + if (unlikely(p->len + skb->len >= 65536)) + return -E2BIG; + + if (NAPI_GRO_CB(p)->last == p) + skb_shinfo(p)->frag_list = skb; + else + NAPI_GRO_CB(p)->last->next = skb; + + skb_pull(skb, skb_gro_offset(skb)); + + NAPI_GRO_CB(p)->last = skb; + NAPI_GRO_CB(p)->count++; + p->data_len += skb->len; + p->truesize += skb->truesize; + p->len += skb->len; + + NAPI_GRO_CB(skb)->same_flow = 1; + + return 0; +} +EXPORT_SYMBOL_GPL(skb_gro_receive_list); + /** * skb_segment - Perform protocol segmentation on skb. * @head_skb: buffer to segment -- 2.17.1