Merge branch 'flexible-array-for-ip-tunnel-options'

Gal Pressman says:

====================
Flexible array for ip tunnel options

Remove the hidden assumption that options are allocated at the end of
the struct, and teach the compiler about them using a flexible array.

First patch is converting hard-coded 'info + 1' to use ip_tunnel_info()
helper.
Second patch adds the 'options' flexible array and changes the helper to
use it.

v4: https://lore.kernel.org/20250217202503.265318-1-gal@nvidia.com
v3: https://lore.kernel.org/20250212140953.107533-1-gal@nvidia.com
v2: https://lore.kernel.org/20250209101853.15828-1-gal@nvidia.com
====================

Link: https://patch.msgid.link/20250219143256.370277-1-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

4 files changed, 14 insertions, 14 deletions

diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h
index 84c15402931c..4160731dcb6e 100644
--- a/include/net/dst_metadata.h
+++ b/include/net/dst_metadata.h
@@ -163,11 +163,8 @@ static inline struct metadata_dst *tun_dst_unclone(struct sk_buff *skb)
 	if (!new_md)
 		return ERR_PTR(-ENOMEM);
 
-	unsafe_memcpy(&new_md->u.tun_info, &md_dst->u.tun_info,
-		      sizeof(struct ip_tunnel_info) + md_size,
-		      /* metadata_dst_alloc() reserves room (md_size bytes) for
-		       * options right after the ip_tunnel_info struct.
-		       */);
+	memcpy(&new_md->u.tun_info, &md_dst->u.tun_info,
+	       sizeof(struct ip_tunnel_info) + md_size);
 #ifdef CONFIG_DST_CACHE
 	/* Unclone the dst cache if there is one */
 	if (new_md->u.tun_info.dst_cache.cache) {
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 1aa31bdb2b31..e041e4865373 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -95,8 +95,8 @@ struct ip_tunnel_encap {
 
 #define ip_tunnel_info_opts(info)				\
 	_Generic(info,						\
-		 const struct ip_tunnel_info * : ((const void *)((info) + 1)),\
-		 struct ip_tunnel_info * : ((void *)((info) + 1))\
+		 const struct ip_tunnel_info * : ((const void *)(info)->options),\
+		 struct ip_tunnel_info * : ((void *)(info)->options)\
 	)
 
 struct ip_tunnel_info {
@@ -107,6 +107,7 @@ struct ip_tunnel_info {
 #endif
 	u8			options_len;
 	u8			mode;
+	u8			options[] __aligned_largest __counted_by(options_len);
 };
 
 /* 6rd prefix/relay information */
@@ -650,7 +651,7 @@ static inline void iptunnel_xmit_stats(struct net_device *dev, int pkt_len)
 static inline void ip_tunnel_info_opts_get(void *to,
 					   const struct ip_tunnel_info *info)
 {
-	memcpy(to, info + 1, info->options_len);
+	memcpy(to, ip_tunnel_info_opts(info), info->options_len);
 }
 
 static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info,
diff --git a/net/core/dst.c b/net/core/dst.c
index 9552a90d4772..c99b95cf9cbb 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -286,7 +286,8 @@ struct metadata_dst *metadata_dst_alloc(u8 optslen, enum metadata_type type,
 {
 	struct metadata_dst *md_dst;
 
-	md_dst = kmalloc(sizeof(*md_dst) + optslen, flags);
+	md_dst = kmalloc(struct_size(md_dst, u.tun_info.options, optslen),
+			 flags);
 	if (!md_dst)
 		return NULL;
 
@@ -314,7 +315,8 @@ metadata_dst_alloc_percpu(u8 optslen, enum metadata_type type, gfp_t flags)
 	int cpu;
 	struct metadata_dst __percpu *md_dst;
 
-	md_dst = __alloc_percpu_gfp(sizeof(struct metadata_dst) + optslen,
+	md_dst = __alloc_percpu_gfp(struct_size(md_dst, u.tun_info.options,
+						optslen),
 				    __alignof__(struct metadata_dst), flags);
 	if (!md_dst)
 		return NULL;
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index af7c99845948..ae5dea7c48a8 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -571,8 +571,8 @@ static void tunnel_key_release(struct tc_action *a)
 static int tunnel_key_geneve_opts_dump(struct sk_buff *skb,
 				       const struct ip_tunnel_info *info)
 {
+	const u8 *src = ip_tunnel_info_opts(info);
 	int len = info->options_len;
-	u8 *src = (u8 *)(info + 1);
 	struct nlattr *start;
 
 	start = nla_nest_start_noflag(skb, TCA_TUNNEL_KEY_ENC_OPTS_GENEVE);
@@ -580,7 +580,7 @@ static int tunnel_key_geneve_opts_dump(struct sk_buff *skb,
 		return -EMSGSIZE;
 
 	while (len > 0) {
-		struct geneve_opt *opt = (struct geneve_opt *)src;
+		const struct geneve_opt *opt = (const struct geneve_opt *)src;
 
 		if (nla_put_be16(skb, TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS,
 				 opt->opt_class) ||
@@ -603,7 +603,7 @@ static int tunnel_key_geneve_opts_dump(struct sk_buff *skb,
 static int tunnel_key_vxlan_opts_dump(struct sk_buff *skb,
 				      const struct ip_tunnel_info *info)
 {
-	struct vxlan_metadata *md = (struct vxlan_metadata *)(info + 1);
+	const struct vxlan_metadata *md = ip_tunnel_info_opts(info);
 	struct nlattr *start;
 
 	start = nla_nest_start_noflag(skb, TCA_TUNNEL_KEY_ENC_OPTS_VXLAN);
@@ -622,7 +622,7 @@ static int tunnel_key_vxlan_opts_dump(struct sk_buff *skb,
 static int tunnel_key_erspan_opts_dump(struct sk_buff *skb,
 				       const struct ip_tunnel_info *info)
 {
-	struct erspan_metadata *md = (struct erspan_metadata *)(info + 1);
+	const struct erspan_metadata *md = ip_tunnel_info_opts(info);
 	struct nlattr *start;
 
 	start = nla_nest_start_noflag(skb, TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN);