[PATCH net-next 2/8] net: reserve extra TX headroom for local egress

From: Tianyi Gao <hidden>
Date: 2026-11-07 03:34:42
Also in: bpf, linux-doc, linux-kselftest
Reply to: Tianyi Gao, 2026-11-07

From: David Keogh <redacted>

Use LL_ALLOC_SPACE() and LL_ALLOC_SPACE_EX() instead of
LL_RESERVED_SPACE() and LL_RESERVED_SPACE_EX() where the stack allocates
packets on behalf of a local sender and sizes them for the output
device:

 - __ip_append_data() and __ip6_append_data(), covering UDP, ICMP,
   ping and raw sockets without IP_HDRINCL;
 - raw_send_hdrinc() and rawv6_send_hdrinc();
 - the three AF_PACKET transmit paths;
 - AF_XDP copy mode, which open-codes its own calculation from
   needed_headroom and now uses netdev_tx_alloc_headroom().

These are the main paths where a packet's headroom is decided by the
device's advertised requirement and nothing else. Adding the
administrator's extra reservation here means such packets reach the TC
egress hook with room for additional headers already in place.

Paths that check an existing packet against LL_RESERVED_SPACE() and
expand it on demand, such as ip_finish_output2() and the tunnel
transmit functions, are deliberately left alone. Using the larger value
there would force a reallocation of every packet that lacks the full
extra reservation, including TCP segments that already have enough
room for the headers an egress program actually pushes.

ip_do_fragment() and ip6_fragment() are also left alone. They use the
same value to check the headroom of existing fragments and to size new
ones. A larger value would send more packets to the slow path, which
copies them. A local sender's fragments normally come from
__ip_append_data() or __ip6_append_data().

Signed-off-by: David Keogh <redacted>
Signed-off-by: Tianyi Gao <redacted>
---
 net/ipv4/ip_output.c   | 2 +-
 net/ipv4/raw.c         | 2 +-
 net/ipv6/ip6_output.c  | 2 +-
 net/ipv6/raw.c         | 2 +-
 net/packet/af_packet.c | 6 +++---
 net/xdp/xsk.c          | 6 ++++--
 6 files changed, 11 insertions(+), 9 deletions(-)

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 3396f177a18d..bf718b8f6f1d 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c

@@ -988,7 +988,7 @@ static int __ip_append_data(struct sock *sk,
 	mtu = cork->gso_size ? IP_MAX_MTU : cork->fragsize;
 	paged = !!cork->gso_size;
 
-	hh_len = LL_RESERVED_SPACE(rt->dst.dev);
+	hh_len = LL_ALLOC_SPACE(rt->dst.dev);
 
 	fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0);
 	maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen;

diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 9d01006d8189..a1e72e634d0e 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c

@@ -355,7 +355,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
 	if (flags&MSG_PROBE)
 		goto out;
 
-	hlen = LL_RESERVED_SPACE(rt->dst.dev);
+	hlen = LL_ALLOC_SPACE(rt->dst.dev);
 	tlen = rt->dst.dev->needed_tailroom;
 	skb = sock_alloc_send_skb(sk,
 				  length + hlen + tlen + 15,

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 25fe0ba98b1a..a3626d5f0d11 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c

@@ -1490,7 +1490,7 @@ static int __ip6_append_data(struct sock *sk,
 	mtu = cork->gso_size ? IP6_MAX_MTU : cork->fragsize;
 	orig_mtu = mtu;
 
-	hh_len = LL_RESERVED_SPACE(rt->dst.dev);
+	hh_len = LL_ALLOC_SPACE(rt->dst.dev);
 
 	fragheaderlen = sizeof(struct ipv6hdr) + rt->rt6i_nfheader_len +
 			(opt ? opt->opt_nflen : 0);

diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index bdea825434ea..06459685ec61 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c

@@ -601,7 +601,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length,
 	struct sk_buff *skb;
 	int err;
 	struct rt6_info *rt = dst_rt6_info(*dstp);
-	int hlen = LL_RESERVED_SPACE(rt->dst.dev);
+	int hlen = LL_ALLOC_SPACE(rt->dst.dev);
 	int tlen = rt->dst.dev->needed_tailroom;
 
 	if (length > rt->dst.dev->mtu) {

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 8250e6a791f6..8800da612880 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c

@@ -2032,7 +2032,7 @@ static int packet_sendmsg_spkt(struct socket *sock, struct msghdr *msg,
 		goto out_unlock;
 
 	if (!skb) {
-		size_t reserved = LL_RESERVED_SPACE_EX(dev, hard_header_len);
+		size_t reserved = LL_ALLOC_SPACE_EX(dev, hard_header_len);
 		int tlen = dev->needed_tailroom;
 		unsigned int hhlen = dev->header_ops ? hard_header_len : 0;

@@ -2860,7 +2860,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 			goto tpacket_error;
 
 		status = TP_STATUS_SEND_REQUEST;
-		hlen = LL_RESERVED_SPACE_EX(dev, hard_header_len);
+		hlen = LL_ALLOC_SPACE_EX(dev, hard_header_len);
 		tlen = dev->needed_tailroom;
 		if (vnet_hdr_sz) {
 			data += vnet_hdr_sz;

@@ -3087,7 +3087,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 		goto out_unlock;
 
 	err = -ENOBUFS;
-	hlen = LL_RESERVED_SPACE_EX(dev, hard_header_len);
+	hlen = LL_ALLOC_SPACE_EX(dev, hard_header_len);
 	tlen = dev->needed_tailroom;
 	linear = __virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len);
 	linear = max(linear, min_t(int, len, hard_header_len));

diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 781ba46eb152..3ee8ad3fd155 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c

@@ -1045,7 +1045,8 @@ static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs,
 	buffer = xsk_buff_raw_get_data(pool, addr);
 
 	if (!skb) {
-		hr = max(NET_SKB_PAD, L1_CACHE_ALIGN(xs->dev->needed_headroom));
+		hr = max(NET_SKB_PAD,
+			 L1_CACHE_ALIGN(netdev_tx_alloc_headroom(xs->dev)));
 
 		skb = sock_alloc_send_skb(&xs->sk, hr, 1, &err);
 		if (unlikely(!skb))

@@ -1128,7 +1129,8 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 		len = desc->len;
 
 		if (!skb) {
-			hr = max(NET_SKB_PAD, L1_CACHE_ALIGN(dev->needed_headroom));
+			hr = max(NET_SKB_PAD,
+				 L1_CACHE_ALIGN(netdev_tx_alloc_headroom(dev)));
 			tr = dev->needed_tailroom;
 			skb = sock_alloc_send_skb(&xs->sk, hr + len + tr, 1, &err);
 			if (unlikely(!skb))

-- 
2.56.0

`h`	back out one level
`j`	next message in thread / next series-diff position
`k`	previous message in thread / previous series-diff position
`l`	drill in
`Esc`	close help / fold thread tree
`?`	toggle this help