gro: inline tcp6_gro_receive()

FDO/LTO are unable to inline tcp6_gro_receive() from ipv6_gro_receive()

Make sure tcp6_check_fraglist_gro() is only called only when needed,
so that compiler can leave it out-of-line.

$ scripts/bloat-o-meter -t vmlinux.1 vmlinux.2
add/remove: 2/0 grow/shrink: 3/1 up/down: 1123/-253 (870)
Function                                     old     new   delta
ipv6_gro_receive                            1069    1846    +777
tcp6_check_fraglist_gro                        -     272    +272
ipv6_offload_init                            218     274     +56
__pfx_tcp6_check_fraglist_gro                  -      16     +16
ipv6_gro_complete                            433     435      +2
tcp6_gro_receive                             959     706    -253
Total: Before=22592662, After=22593532, chg +0.00%

Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260120164903.1912995-3-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/include/net/gro.h b/include/net/gro.h
index b65f631c521d7d9741ef86781add0038c9ce4055..85e5eeed4c90feef9440c57af9382b0e9ead1219 100644 (file)
--- a/include/net/gro.h
+++ b/include/net/gro.h
@@ -405,8 +405,7 @@ INDIRECT_CALLABLE_DECLARE(struct sk_buff *udp4_gro_receive(struct list_head *,
                                                           struct sk_buff *));
 INDIRECT_CALLABLE_DECLARE(int udp4_gro_complete(struct sk_buff *, int));
 
-INDIRECT_CALLABLE_DECLARE(struct sk_buff *udp6_gro_receive(struct list_head *,
-                                                          struct sk_buff *));
+struct sk_buff *udp6_gro_receive(struct list_head *, struct sk_buff *);
 INDIRECT_CALLABLE_DECLARE(int udp6_gro_complete(struct sk_buff *, int));
 
 #define indirect_call_gro_receive_inet(cb, f2, f1, head, skb)  \

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 25143f156957288f5b8674d4d27b805e92c592c8..0941b7b5067cb6d217cb06ae1a0b73161063ed9f 100644 (file)
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -2325,7 +2325,6 @@ struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb,
 INDIRECT_CALLABLE_DECLARE(int tcp4_gro_complete(struct sk_buff *skb, int thoff));
 INDIRECT_CALLABLE_DECLARE(struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb));
 INDIRECT_CALLABLE_DECLARE(int tcp6_gro_complete(struct sk_buff *skb, int thoff));
-INDIRECT_CALLABLE_DECLARE(struct sk_buff *tcp6_gro_receive(struct list_head *head, struct sk_buff *skb));
 #ifdef CONFIG_INET
 void tcp_gro_complete(struct sk_buff *skb);
 #else

diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile
index d283c59df4c1c421bc043056fe11e5437cc4aece..0492f1a0b4918ada8c56cf649fbec04c7114863a 100644 (file)
--- a/net/ipv6/Makefile
+++ b/net/ipv6/Makefile
@@ -45,7 +45,7 @@ obj-$(CONFIG_IPV6_FOU) += fou6.o
 
 obj-y += addrconf_core.o exthdrs_core.o ip6_checksum.o ip6_icmp.o
 obj-$(CONFIG_INET) += output_core.o protocol.o \
-                       ip6_offload.o tcpv6_offload.o exthdrs_offload.o
+                       ip6_offload.o exthdrs_offload.o
 
 obj-$(subst m,y,$(CONFIG_IPV6)) += inet6_hashtables.o
 

diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index fce91183797a60fcbf271c73e086aeb0aa9d40c6..4d96154c0dcd019322908ab6ddaa663a2a565e44 100644 (file)
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -19,6 +19,7 @@
 #include <net/gso.h>
 
 #include "ip6_offload.h"
+#include "tcpv6_offload.c"
 
 /* All GRO functions are always builtin, except UDP over ipv6, which lays in
  * ipv6 module, as it depends on UDPv6 lookup function, so we need special care
@@ -30,13 +31,6 @@
 #define INDIRECT_CALL_L4(f, f2, f1, ...) INDIRECT_CALL_1(f, f2, __VA_ARGS__)
 #endif
 
-#define indirect_call_gro_receive_l4(f2, f1, cb, head, skb)    \
-({                                                             \
-       unlikely(gro_recursion_inc_test(skb)) ?                 \
-               NAPI_GRO_CB(skb)->flush |= 1, NULL :            \
-               INDIRECT_CALL_L4(cb, f2, f1, head, skb);        \
-})
-
 static int ipv6_gro_pull_exthdrs(struct sk_buff *skb, int off, int proto)
 {
        const struct net_offload *ops = NULL;
@@ -298,9 +292,19 @@ not_same_flow:
 
        skb_gro_postpull_rcsum(skb, iph, nlen);
 
-       pp = indirect_call_gro_receive_l4(tcp6_gro_receive, udp6_gro_receive,
-                                        ops->callbacks.gro_receive, head, skb);
+       if (unlikely(gro_recursion_inc_test(skb))) {
+               flush = 1;
+               goto out;
+       }
 
+       if (likely(proto == IPPROTO_TCP))
+               pp = tcp6_gro_receive(head, skb);
+#if IS_BUILTIN(CONFIG_IPV6)
+       else if (likely(proto == IPPROTO_UDP))
+               pp = udp6_gro_receive(head, skb);
+#endif
+       else
+               pp = ops->callbacks.gro_receive(head, skb);
 out:
        skb_gro_flush_final(skb, pp, flush);
 

diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index effeba58630b5ac2593b824bd8fc10a473954b6c..7f19ce423058870f285b7f8ae2a4d116d783f9fb 100644 (file)
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -24,9 +24,6 @@ static void tcp6_check_fraglist_gro(struct list_head *head, struct sk_buff *skb,
        struct net *net;
        int iif, sdif;
 
-       if (likely(!(skb->dev->features & NETIF_F_GRO_FRAGLIST)))
-               return;
-
        p = tcp_gro_lookup(head, th);
        if (p) {
                NAPI_GRO_CB(skb)->is_flist = NAPI_GRO_CB(p)->is_flist;
@@ -45,8 +42,8 @@ static void tcp6_check_fraglist_gro(struct list_head *head, struct sk_buff *skb,
 #endif /* IS_ENABLED(CONFIG_IPV6) */
 }
 
-INDIRECT_CALLABLE_SCOPE
-struct sk_buff *tcp6_gro_receive(struct list_head *head, struct sk_buff *skb)
+static __always_inline struct sk_buff *tcp6_gro_receive(struct list_head *head,
+                                                       struct sk_buff *skb)
 {
        struct tcphdr *th;
 
@@ -60,7 +57,8 @@ struct sk_buff *tcp6_gro_receive(struct list_head *head, struct sk_buff *skb)
        if (!th)
                goto flush;
 
-       tcp6_check_fraglist_gro(head, skb, th);
+       if (unlikely(skb->dev->features & NETIF_F_GRO_FRAGLIST))
+               tcp6_check_fraglist_gro(head, skb, th);
 
        return tcp_gro_receive(head, skb, th);
 

diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index 046f13b1d77a19b9ec4e0a07f531081d174defb1..e90aaa84941c60ec0fa2e23051c422064a959096 100644 (file)
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -132,7 +132,6 @@ static struct sock *udp6_gro_lookup_skb(struct sk_buff *skb, __be16 sport,
                                 sdif, net->ipv4.udp_table, NULL);
 }
 
-INDIRECT_CALLABLE_SCOPE
 struct sk_buff *udp6_gro_receive(struct list_head *head, struct sk_buff *skb)
 {
        struct udphdr *uh = udp_gro_udphdr(skb);