[PATCH net-next 0/3] gro: inline tcp6_gro_{receive,complete}

[PATCH net-next 0/3] gro: inline tcp6_gro_{receive,complete}

[Eric Dumazet]

On some platforms, GRO stack is too deep and causes cpu stalls.

Decreasing call depths by one shows a 1.5 % gain on Zen 2 cpus.
(32 RX queues, 100Gbit NIC, RFS enabled, tcp_rr with 128 threads and 10,000 flows)

We can go further by inlining ipv6_gro_{receive,complete}
and take care of IPv4 if there is interest.

Cumulative size increase for this series (of 3):

$ scripts/bloat-o-meter -t vmlinux.0 vmlinux.3
add/remove: 2/2 grow/shrink: 5/1 up/down: 1572/-471 (1101)
Function                                     old     new   delta
ipv6_gro_receive                            1069    1846    +777
ipv6_gro_complete                            433     733    +300
tcp6_check_fraglist_gro                        -     272    +272
tcp6_gro_complete                            227     306     +79
tcp4_gro_complete                            325     397     +72
ipv6_offload_init                            218     274     +56
__pfx_tcp6_check_fraglist_gro                  -      16     +16
__pfx___skb_incr_checksum_unnecessary         32       -     -32
__skb_incr_checksum_unnecessary              186       -    -186
tcp6_gro_receive                             959     706    -253
Total: Before=22592724, After=22593825, chg +0.00%


Eric Dumazet (3):
  net: always inline __skb_incr_checksum_unnecessary()
  gro: inline tcp6_gro_receive()
  gro: inline tcp6_gro_complete()

 include/linux/skbuff.h   |  2 +-
 include/net/tcp.h        |  2 --
 net/ipv6/Makefile        |  2 +-
 net/ipv6/ip6_offload.c   | 43 ++++++++++++++++++++--------------------
 net/ipv6/tcpv6_offload.c | 12 +++++------
 5 files changed, 29 insertions(+), 32 deletions(-)

-- 
2.52.0.457.g6b5491de43-goog

[PATCH net-next 1/3] net: always inline __skb_incr_checksum_unnecessary()

[Eric Dumazet]

clang does not inline this helper in GRO fast path.

We can save space and cpu cycles.

$ scripts/bloat-o-meter -t vmlinux.0 vmlinux.1
add/remove: 0/2 grow/shrink: 2/0 up/down: 156/-218 (-62)
Function                                     old     new   delta
tcp6_gro_complete                            227     311     +84
tcp4_gro_complete                            325     397     +72
__pfx___skb_incr_checksum_unnecessary         32       -     -32
__skb_incr_checksum_unnecessary              186       -    -186
Total: Before=22592724, After=22592662, chg -0.00%

Signed-off-by: Eric Dumazet <edumazet@google.com>
---
 include/linux/skbuff.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 86737076101d4a8452e90fe78adcdcfdefb79169..e6bfe5d0c5252b2e7540e1fef9317aab83feced2 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -4763,7 +4763,7 @@ static inline void __skb_decr_checksum_unnecessary(struct sk_buff *skb)
 	}
 }
 
-static inline void __skb_incr_checksum_unnecessary(struct sk_buff *skb)
+static __always_inline void __skb_incr_checksum_unnecessary(struct sk_buff *skb)
 {
 	if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
 		if (skb->csum_level < SKB_MAX_CSUM_LEVEL)
-- 
2.52.0.457.g6b5491de43-goog

[PATCH net-next 2/3] gro: inline tcp6_gro_receive()

[Eric Dumazet]

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>
---
 include/net/tcp.h        |  1 -
 net/ipv6/Makefile        |  2 +-
 net/ipv6/ip6_offload.c   | 22 +++++++++++++---------
 net/ipv6/tcpv6_offload.c | 10 ++++------
 4 files changed, 18 insertions(+), 17 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index ef0fee58fde82620399df49a35c7ecae8e34068e..2a7744de226ed0a378719fd60fa2a3830bef2e7e 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -2328,7 +2328,6 @@ 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
--- 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
--- 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 @@ INDIRECT_CALLABLE_SCOPE struct sk_buff *ipv6_gro_receive(struct list_head *head,
 
 	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
--- 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);
 
-- 
2.52.0.457.g6b5491de43-goog

Re: [PATCH net-next 2/3] gro: inline tcp6_gro_receive()

[kernel test robot]

Hi Eric,

kernel test robot noticed the following build errors:

[auto build test ERROR on net-next/main]

url:    https://github.com/intel-lab-lkp/linux/commits/Eric-Dumazet/net-always-inline-__skb_incr_checksum_unnecessary/20260116-233745
base:   net-next/main
patch link:    https://lore.kernel.org/r/20260116152957.1825626-3-edumazet%40google.com
patch subject: [PATCH net-next 2/3] gro: inline tcp6_gro_receive()
config: i386-randconfig-011-20260117 (https://download.01.org/0day-ci/archive/20260117/202601170955.0wVpALLC-lkp@intel.com/config)
compiler: clang version 20.1.8 (https://github.com/llvm/llvm-project 87f0227cb60147a26a1eeb4fb06e3b505e9c7261)
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20260117/202601170955.0wVpALLC-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202601170955.0wVpALLC-lkp@intel.com/

All errors (new ones prefixed by >>):

>> net/ipv6/ip6_offload.c:304:8: error: call to undeclared function 'udp6_gro_receive'; ISO C99 and later do not support implicit function declarations [-Wimplicit-function-declaration]
     304 |                 pp = udp6_gro_receive(head, skb);
         |                      ^
   net/ipv6/ip6_offload.c:304:8: note: did you mean 'udp_gro_receive'?
   include/net/gro.h:419:17: note: 'udp_gro_receive' declared here
     419 | struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
         |                 ^
>> net/ipv6/ip6_offload.c:304:6: error: incompatible integer to pointer conversion assigning to 'struct sk_buff *' from 'int' [-Wint-conversion]
     304 |                 pp = udp6_gro_receive(head, skb);
         |                    ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~
   2 errors generated.


vim +/udp6_gro_receive +304 net/ipv6/ip6_offload.c

   215	
   216	INDIRECT_CALLABLE_SCOPE struct sk_buff *ipv6_gro_receive(struct list_head *head,
   217								 struct sk_buff *skb)
   218	{
   219		const struct net_offload *ops;
   220		struct sk_buff *pp = NULL;
   221		struct sk_buff *p;
   222		struct ipv6hdr *iph;
   223		unsigned int nlen;
   224		unsigned int hlen;
   225		unsigned int off;
   226		u16 flush = 1;
   227		int proto;
   228	
   229		off = skb_gro_offset(skb);
   230		hlen = off + sizeof(*iph);
   231		iph = skb_gro_header(skb, hlen, off);
   232		if (unlikely(!iph))
   233			goto out;
   234	
   235		NAPI_GRO_CB(skb)->network_offsets[NAPI_GRO_CB(skb)->encap_mark] = off;
   236	
   237		flush += ntohs(iph->payload_len) != skb->len - hlen;
   238	
   239		proto = iph->nexthdr;
   240		ops = rcu_dereference(inet6_offloads[proto]);
   241		if (!ops || !ops->callbacks.gro_receive) {
   242			proto = ipv6_gro_pull_exthdrs(skb, hlen, proto);
   243	
   244			ops = rcu_dereference(inet6_offloads[proto]);
   245			if (!ops || !ops->callbacks.gro_receive)
   246				goto out;
   247	
   248			iph = skb_gro_network_header(skb);
   249		} else {
   250			skb_gro_pull(skb, sizeof(*iph));
   251		}
   252	
   253		skb_set_transport_header(skb, skb_gro_offset(skb));
   254	
   255		NAPI_GRO_CB(skb)->proto = proto;
   256	
   257		flush--;
   258		nlen = skb_gro_offset(skb) - off;
   259	
   260		list_for_each_entry(p, head, list) {
   261			const struct ipv6hdr *iph2;
   262			__be32 first_word; /* <Version:4><Traffic_Class:8><Flow_Label:20> */
   263	
   264			if (!NAPI_GRO_CB(p)->same_flow)
   265				continue;
   266	
   267			iph2 = (struct ipv6hdr *)(p->data + off);
   268			first_word = *(__be32 *)iph ^ *(__be32 *)iph2;
   269	
   270			/* All fields must match except length and Traffic Class.
   271			 * XXX skbs on the gro_list have all been parsed and pulled
   272			 * already so we don't need to compare nlen
   273			 * (nlen != (sizeof(*iph2) + ipv6_exthdrs_len(iph2, &ops)))
   274			 * memcmp() alone below is sufficient, right?
   275			 */
   276			 if ((first_word & htonl(0xF00FFFFF)) ||
   277			     !ipv6_addr_equal(&iph->saddr, &iph2->saddr) ||
   278			     !ipv6_addr_equal(&iph->daddr, &iph2->daddr) ||
   279			     iph->nexthdr != iph2->nexthdr) {
   280	not_same_flow:
   281				NAPI_GRO_CB(p)->same_flow = 0;
   282				continue;
   283			}
   284			if (unlikely(nlen > sizeof(struct ipv6hdr))) {
   285				if (memcmp(iph + 1, iph2 + 1,
   286					   nlen - sizeof(struct ipv6hdr)))
   287					goto not_same_flow;
   288			}
   289		}
   290	
   291		NAPI_GRO_CB(skb)->flush |= flush;
   292	
   293		skb_gro_postpull_rcsum(skb, iph, nlen);
   294	
   295		if (unlikely(gro_recursion_inc_test(skb))) {
   296			flush = 1;
   297			goto out;
   298		}
   299	
   300		if (likely(proto == IPPROTO_TCP))
   301			pp = tcp6_gro_receive(head, skb);
   302	#if IS_BUILTIN(CONFIG_IPV6)
   303		else if (likely(proto == IPPROTO_UDP))
 > 304			pp = udp6_gro_receive(head, skb);
   305	#endif
   306		else
   307			pp = ops->callbacks.gro_receive(head, skb);
   308	out:
   309		skb_gro_flush_final(skb, pp, flush);
   310	
   311		return pp;
   312	}
   313	

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

Re: [PATCH net-next 2/3] gro: inline tcp6_gro_receive()

[kernel test robot]

Hi Eric,

kernel test robot noticed the following build warnings:

[auto build test WARNING on net-next/main]

url:    https://github.com/intel-lab-lkp/linux/commits/Eric-Dumazet/net-always-inline-__skb_incr_checksum_unnecessary/20260116-233745
base:   net-next/main
patch link:    https://lore.kernel.org/r/20260116152957.1825626-3-edumazet%40google.com
patch subject: [PATCH net-next 2/3] gro: inline tcp6_gro_receive()
config: i386-randconfig-015-20260117 (https://download.01.org/0day-ci/archive/20260117/202601170903.keV6lwyg-lkp@intel.com/config)
compiler: gcc-12 (Debian 12.4.0-5) 12.4.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20260117/202601170903.keV6lwyg-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202601170903.keV6lwyg-lkp@intel.com/

All warnings (new ones prefixed by >>):

   net/ipv6/ip6_offload.c: In function 'ipv6_gro_receive':
   net/ipv6/ip6_offload.c:304:22: error: implicit declaration of function 'udp6_gro_receive'; did you mean 'udp_gro_receive'? [-Werror=implicit-function-declaration]
     304 |                 pp = udp6_gro_receive(head, skb);
         |                      ^~~~~~~~~~~~~~~~
         |                      udp_gro_receive
>> net/ipv6/ip6_offload.c:304:20: warning: assignment to 'struct sk_buff *' from 'int' makes pointer from integer without a cast [-Wint-conversion]
     304 |                 pp = udp6_gro_receive(head, skb);
         |                    ^
   cc1: some warnings being treated as errors


vim +304 net/ipv6/ip6_offload.c

   215	
   216	INDIRECT_CALLABLE_SCOPE struct sk_buff *ipv6_gro_receive(struct list_head *head,
   217								 struct sk_buff *skb)
   218	{
   219		const struct net_offload *ops;
   220		struct sk_buff *pp = NULL;
   221		struct sk_buff *p;
   222		struct ipv6hdr *iph;
   223		unsigned int nlen;
   224		unsigned int hlen;
   225		unsigned int off;
   226		u16 flush = 1;
   227		int proto;
   228	
   229		off = skb_gro_offset(skb);
   230		hlen = off + sizeof(*iph);
   231		iph = skb_gro_header(skb, hlen, off);
   232		if (unlikely(!iph))
   233			goto out;
   234	
   235		NAPI_GRO_CB(skb)->network_offsets[NAPI_GRO_CB(skb)->encap_mark] = off;
   236	
   237		flush += ntohs(iph->payload_len) != skb->len - hlen;
   238	
   239		proto = iph->nexthdr;
   240		ops = rcu_dereference(inet6_offloads[proto]);
   241		if (!ops || !ops->callbacks.gro_receive) {
   242			proto = ipv6_gro_pull_exthdrs(skb, hlen, proto);
   243	
   244			ops = rcu_dereference(inet6_offloads[proto]);
   245			if (!ops || !ops->callbacks.gro_receive)
   246				goto out;
   247	
   248			iph = skb_gro_network_header(skb);
   249		} else {
   250			skb_gro_pull(skb, sizeof(*iph));
   251		}
   252	
   253		skb_set_transport_header(skb, skb_gro_offset(skb));
   254	
   255		NAPI_GRO_CB(skb)->proto = proto;
   256	
   257		flush--;
   258		nlen = skb_gro_offset(skb) - off;
   259	
   260		list_for_each_entry(p, head, list) {
   261			const struct ipv6hdr *iph2;
   262			__be32 first_word; /* <Version:4><Traffic_Class:8><Flow_Label:20> */
   263	
   264			if (!NAPI_GRO_CB(p)->same_flow)
   265				continue;
   266	
   267			iph2 = (struct ipv6hdr *)(p->data + off);
   268			first_word = *(__be32 *)iph ^ *(__be32 *)iph2;
   269	
   270			/* All fields must match except length and Traffic Class.
   271			 * XXX skbs on the gro_list have all been parsed and pulled
   272			 * already so we don't need to compare nlen
   273			 * (nlen != (sizeof(*iph2) + ipv6_exthdrs_len(iph2, &ops)))
   274			 * memcmp() alone below is sufficient, right?
   275			 */
   276			 if ((first_word & htonl(0xF00FFFFF)) ||
   277			     !ipv6_addr_equal(&iph->saddr, &iph2->saddr) ||
   278			     !ipv6_addr_equal(&iph->daddr, &iph2->daddr) ||
   279			     iph->nexthdr != iph2->nexthdr) {
   280	not_same_flow:
   281				NAPI_GRO_CB(p)->same_flow = 0;
   282				continue;
   283			}
   284			if (unlikely(nlen > sizeof(struct ipv6hdr))) {
   285				if (memcmp(iph + 1, iph2 + 1,
   286					   nlen - sizeof(struct ipv6hdr)))
   287					goto not_same_flow;
   288			}
   289		}
   290	
   291		NAPI_GRO_CB(skb)->flush |= flush;
   292	
   293		skb_gro_postpull_rcsum(skb, iph, nlen);
   294	
   295		if (unlikely(gro_recursion_inc_test(skb))) {
   296			flush = 1;
   297			goto out;
   298		}
   299	
   300		if (likely(proto == IPPROTO_TCP))
   301			pp = tcp6_gro_receive(head, skb);
   302	#if IS_BUILTIN(CONFIG_IPV6)
   303		else if (likely(proto == IPPROTO_UDP))
 > 304			pp = udp6_gro_receive(head, skb);
   305	#endif
   306		else
   307			pp = ops->callbacks.gro_receive(head, skb);
   308	out:
   309		skb_gro_flush_final(skb, pp, flush);
   310	
   311		return pp;
   312	}
   313	

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

Re: [PATCH net-next 2/3] gro: inline tcp6_gro_receive()

[kernel test robot]

Hi Eric,

kernel test robot noticed the following build errors:

[auto build test ERROR on net-next/main]

url:    https://github.com/intel-lab-lkp/linux/commits/Eric-Dumazet/net-always-inline-__skb_incr_checksum_unnecessary/20260116-233745
base:   net-next/main
patch link:    https://lore.kernel.org/r/20260116152957.1825626-3-edumazet%40google.com
patch subject: [PATCH net-next 2/3] gro: inline tcp6_gro_receive()
config: powerpc-ge_imp3a_defconfig (https://download.01.org/0day-ci/archive/20260117/202601170958.L4uFo8qq-lkp@intel.com/config)
compiler: powerpc-linux-gcc (GCC) 15.2.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20260117/202601170958.L4uFo8qq-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202601170958.L4uFo8qq-lkp@intel.com/

All errors (new ones prefixed by >>):

   net/ipv6/ip6_offload.c: In function 'ipv6_gro_receive':
>> net/ipv6/ip6_offload.c:304:22: error: implicit declaration of function 'udp6_gro_receive'; did you mean 'udp_gro_receive'? [-Wimplicit-function-declaration]
     304 |                 pp = udp6_gro_receive(head, skb);
         |                      ^~~~~~~~~~~~~~~~
         |                      udp_gro_receive
>> net/ipv6/ip6_offload.c:304:20: error: assignment to 'struct sk_buff *' from 'int' makes pointer from integer without a cast [-Wint-conversion]
     304 |                 pp = udp6_gro_receive(head, skb);
         |                    ^


vim +304 net/ipv6/ip6_offload.c

   215	
   216	INDIRECT_CALLABLE_SCOPE struct sk_buff *ipv6_gro_receive(struct list_head *head,
   217								 struct sk_buff *skb)
   218	{
   219		const struct net_offload *ops;
   220		struct sk_buff *pp = NULL;
   221		struct sk_buff *p;
   222		struct ipv6hdr *iph;
   223		unsigned int nlen;
   224		unsigned int hlen;
   225		unsigned int off;
   226		u16 flush = 1;
   227		int proto;
   228	
   229		off = skb_gro_offset(skb);
   230		hlen = off + sizeof(*iph);
   231		iph = skb_gro_header(skb, hlen, off);
   232		if (unlikely(!iph))
   233			goto out;
   234	
   235		NAPI_GRO_CB(skb)->network_offsets[NAPI_GRO_CB(skb)->encap_mark] = off;
   236	
   237		flush += ntohs(iph->payload_len) != skb->len - hlen;
   238	
   239		proto = iph->nexthdr;
   240		ops = rcu_dereference(inet6_offloads[proto]);
   241		if (!ops || !ops->callbacks.gro_receive) {
   242			proto = ipv6_gro_pull_exthdrs(skb, hlen, proto);
   243	
   244			ops = rcu_dereference(inet6_offloads[proto]);
   245			if (!ops || !ops->callbacks.gro_receive)
   246				goto out;
   247	
   248			iph = skb_gro_network_header(skb);
   249		} else {
   250			skb_gro_pull(skb, sizeof(*iph));
   251		}
   252	
   253		skb_set_transport_header(skb, skb_gro_offset(skb));
   254	
   255		NAPI_GRO_CB(skb)->proto = proto;
   256	
   257		flush--;
   258		nlen = skb_gro_offset(skb) - off;
   259	
   260		list_for_each_entry(p, head, list) {
   261			const struct ipv6hdr *iph2;
   262			__be32 first_word; /* <Version:4><Traffic_Class:8><Flow_Label:20> */
   263	
   264			if (!NAPI_GRO_CB(p)->same_flow)
   265				continue;
   266	
   267			iph2 = (struct ipv6hdr *)(p->data + off);
   268			first_word = *(__be32 *)iph ^ *(__be32 *)iph2;
   269	
   270			/* All fields must match except length and Traffic Class.
   271			 * XXX skbs on the gro_list have all been parsed and pulled
   272			 * already so we don't need to compare nlen
   273			 * (nlen != (sizeof(*iph2) + ipv6_exthdrs_len(iph2, &ops)))
   274			 * memcmp() alone below is sufficient, right?
   275			 */
   276			 if ((first_word & htonl(0xF00FFFFF)) ||
   277			     !ipv6_addr_equal(&iph->saddr, &iph2->saddr) ||
   278			     !ipv6_addr_equal(&iph->daddr, &iph2->daddr) ||
   279			     iph->nexthdr != iph2->nexthdr) {
   280	not_same_flow:
   281				NAPI_GRO_CB(p)->same_flow = 0;
   282				continue;
   283			}
   284			if (unlikely(nlen > sizeof(struct ipv6hdr))) {
   285				if (memcmp(iph + 1, iph2 + 1,
   286					   nlen - sizeof(struct ipv6hdr)))
   287					goto not_same_flow;
   288			}
   289		}
   290	
   291		NAPI_GRO_CB(skb)->flush |= flush;
   292	
   293		skb_gro_postpull_rcsum(skb, iph, nlen);
   294	
   295		if (unlikely(gro_recursion_inc_test(skb))) {
   296			flush = 1;
   297			goto out;
   298		}
   299	
   300		if (likely(proto == IPPROTO_TCP))
   301			pp = tcp6_gro_receive(head, skb);
   302	#if IS_BUILTIN(CONFIG_IPV6)
   303		else if (likely(proto == IPPROTO_UDP))
 > 304			pp = udp6_gro_receive(head, skb);
   305	#endif
   306		else
   307			pp = ops->callbacks.gro_receive(head, skb);
   308	out:
   309		skb_gro_flush_final(skb, pp, flush);
   310	
   311		return pp;
   312	}
   313	

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

[PATCH net-next 3/3] gro: inline tcp6_gro_complete()

[Eric Dumazet]

Remove one function call from GRO stack for native IPv6 + TCP packets.

$ scripts/bloat-o-meter -t vmlinux.2 vmlinux.3
add/remove: 0/0 grow/shrink: 1/1 up/down: 298/-5 (293)
Function                                     old     new   delta
ipv6_gro_complete                            435     733    +298
tcp6_gro_complete                            311     306      -5
Total: Before=22593532, After=22593825, chg +0.00%

Signed-off-by: Eric Dumazet <edumazet@google.com>
---
 include/net/tcp.h        |  1 -
 net/ipv6/ip6_offload.c   | 21 +++++++++------------
 net/ipv6/tcpv6_offload.c |  2 +-
 3 files changed, 10 insertions(+), 14 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 2a7744de226ed0a378719fd60fa2a3830bef2e7e..68bc08c40d5435ce196dd492b46b5d81f8e29b3f 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -2327,7 +2327,6 @@ struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb,
 				struct tcphdr *th);
 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));
 #ifdef CONFIG_INET
 void tcp_gro_complete(struct sk_buff *skb);
 #else
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 4d96154c0dcd019322908ab6ddaa663a2a565e44..32a104ead8760d33e152e0b0a6a6896d70d155b5 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -21,16 +21,6 @@
 #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
- * when ipv6 is built as a module
- */
-#if IS_BUILTIN(CONFIG_IPV6)
-#define INDIRECT_CALL_L4(f, f2, f1, ...) INDIRECT_CALL_2(f, f2, f1, __VA_ARGS__)
-#else
-#define INDIRECT_CALL_L4(f, f2, f1, ...) INDIRECT_CALL_1(f, f2, __VA_ARGS__)
-#endif
-
 static int ipv6_gro_pull_exthdrs(struct sk_buff *skb, int off, int proto)
 {
 	const struct net_offload *ops = NULL;
@@ -383,11 +373,18 @@ INDIRECT_CALLABLE_SCOPE int ipv6_gro_complete(struct sk_buff *skb, int nhoff)
 	}
 
 	nhoff += sizeof(*iph) + ipv6_exthdrs_len(iph, &ops);
+
+	if (likely(ops == &net_hotdata.tcpv6_offload))
+		return tcp6_gro_complete(skb, nhoff);
+#if IS_BUILTIN(CONFIG_IPV6)
+	if (ops == &net_hotdata.udpv6_offload)
+		return udp6_gro_complete(skb, nhoff);
+#endif
+
 	if (WARN_ON(!ops || !ops->callbacks.gro_complete))
 		goto out;
 
-	err = INDIRECT_CALL_L4(ops->callbacks.gro_complete, tcp6_gro_complete,
-			       udp6_gro_complete, skb, nhoff);
+	err = ops->callbacks.gro_complete(skb, nhoff);
 
 out:
 	return err;
diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index 7f19ce423058870f285b7f8ae2a4d116d783f9fb..46fa2069d321663ed232e2836db77e3fcb1f4f07 100644
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -67,7 +67,7 @@ static __always_inline struct sk_buff *tcp6_gro_receive(struct list_head *head,
 	return NULL;
 }
 
-INDIRECT_CALLABLE_SCOPE int tcp6_gro_complete(struct sk_buff *skb, int thoff)
+static __always_inline int tcp6_gro_complete(struct sk_buff *skb, int thoff)
 {
 	const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation];
 	const struct ipv6hdr *iph = (struct ipv6hdr *)(skb->data + offset);
-- 
2.52.0.457.g6b5491de43-goog