ip_tunnel: convert __be16 tunnel flags to bitmaps

Historically, tunnel flags like TUNNEL_CSUM or TUNNEL_ERSPAN_OPT
have been defined as __be16. Now all of those 16 bits are occupied
and there's no more free space for new flags.
It can't be simply switched to a bigger container with no
adjustments to the values, since it's an explicit Endian storage,
and on LE systems (__be16)0x0001 equals to
(__be64)0x0001000000000000.
We could probably define new 64-bit flags depending on the
Endianness, i.e. (__be64)0x0001 on BE and (__be64)0x00010000... on
LE, but that would introduce an Endianness dependency and spawn a
ton of Sparse warnings. To mitigate them, all of those places which
were adjusted with this change would be touched anyway, so why not
define stuff properly if there's no choice.

Define IP_TUNNEL_*_BIT counterparts as a bit number instead of the
value already coded and a fistful of <16 <-> bitmap> converters and
helpers. The two flags which have a different bit position are
SIT_ISATAP_BIT and VTI_ISVTI_BIT, as they were defined not as
__cpu_to_be16(), but as (__force __be16), i.e. had different
positions on LE and BE. Now they both have strongly defined places.
Change all __be16 fields which were used to store those flags, to
IP_TUNNEL_DECLARE_FLAGS() -> DECLARE_BITMAP(__IP_TUNNEL_FLAG_NUM) ->
unsigned long[1] for now, and replace all TUNNEL_* occurrences to
their bitmap counterparts. Use the converters in the places which talk
to the userspace, hardware (NFP) or other hosts (GRE header). The rest
must explicitly use the new flags only. This must be done at once,
otherwise there will be too many conversions throughout the code in
the intermediate commits.
Finally, disable the old __be16 flags for use in the kernel code
(except for the two 'irregular' flags mentioned above), to prevent
any accidental (mis)use of them. For the userspace, nothing is
changed, only additions were made.

Most noticeable bloat-o-meter difference (.text):

vmlinux:	307/-1 (306)
gre.ko:		62/0 (62)
ip_gre.ko:	941/-217 (724)	[*]
ip_tunnel.ko:	390/-900 (-510)	[**]
ip_vti.ko:	138/0 (138)
ip6_gre.ko:	534/-18 (516)	[*]
ip6_tunnel.ko:	118/-10 (108)

[*] gre_flags_to_tnl_flags() grew, but still is inlined
[**] ip_tunnel_find() got uninlined, hence such decrease

The average code size increase in non-extreme case is 100-200 bytes
per module, mostly due to sizeof(long) > sizeof(__be16), as
%__IP_TUNNEL_FLAG_NUM is less than %BITS_PER_LONG and the compilers
are able to expand the majority of bitmap_*() calls here into direct
operations on scalars.

Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 21 insertions, 6 deletions

diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c
index 2c3f62907958..aca2a7417af3 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/action.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/action.c
@@ -396,6 +396,17 @@ nfp_fl_push_geneve_options(struct nfp_fl_payload *nfp_fl, int *list_len,
 	return 0;
 }
 
+#define NFP_FL_CHECK(flag) ({				\
+	IP_TUNNEL_DECLARE_FLAGS(__check) = { };		\
+	__be16 __res;					\
+							\
+	__set_bit(IP_TUNNEL_##flag##_BIT, __check);	\
+	__res = ip_tunnel_flags_to_be16(__check);	\
+							\
+	BUILD_BUG_ON(__builtin_constant_p(__res) &&	\
+		     NFP_FL_TUNNEL_##flag != __res);	\
+})
+
 static int
 nfp_fl_set_tun(struct nfp_app *app, struct nfp_fl_set_tun *set_tun,
 	       const struct flow_action_entry *act,
@@ -410,6 +421,7 @@ nfp_fl_set_tun(struct nfp_app *app, struct nfp_fl_set_tun *set_tun,
 	u32 tmp_set_ip_tun_type_index = 0;
 	/* Currently support one pre-tunnel so index is always 0. */
 	int pretun_idx = 0;
+	__be16 tun_flags;
 
 	if (!IS_ENABLED(CONFIG_IPV6) && ipv6)
 		return -EOPNOTSUPP;
@@ -417,9 +429,10 @@ nfp_fl_set_tun(struct nfp_app *app, struct nfp_fl_set_tun *set_tun,
 	if (ipv6 && !(priv->flower_ext_feats & NFP_FL_FEATS_IPV6_TUN))
 		return -EOPNOTSUPP;
 
-	BUILD_BUG_ON(NFP_FL_TUNNEL_CSUM != TUNNEL_CSUM ||
-		     NFP_FL_TUNNEL_KEY	!= TUNNEL_KEY ||
-		     NFP_FL_TUNNEL_GENEVE_OPT != TUNNEL_GENEVE_OPT);
+	NFP_FL_CHECK(CSUM);
+	NFP_FL_CHECK(KEY);
+	NFP_FL_CHECK(GENEVE_OPT);
+
 	if (ip_tun->options_len &&
 	    (tun_type != NFP_FL_TUNNEL_GENEVE ||
 	    !(priv->flower_ext_feats & NFP_FL_FEATS_GENEVE_OPT))) {
@@ -427,7 +440,9 @@ nfp_fl_set_tun(struct nfp_app *app, struct nfp_fl_set_tun *set_tun,
 		return -EOPNOTSUPP;
 	}
 
-	if (ip_tun->key.tun_flags & ~NFP_FL_SUPPORTED_UDP_TUN_FLAGS) {
+	tun_flags = ip_tunnel_flags_to_be16(ip_tun->key.tun_flags);
+	if (!ip_tunnel_flags_is_be16_compat(ip_tun->key.tun_flags) ||
+	    (tun_flags & ~NFP_FL_SUPPORTED_UDP_TUN_FLAGS)) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "unsupported offload: loaded firmware does not support tunnel flag offload");
 		return -EOPNOTSUPP;
@@ -442,7 +457,7 @@ nfp_fl_set_tun(struct nfp_app *app, struct nfp_fl_set_tun *set_tun,
 		FIELD_PREP(NFP_FL_PRE_TUN_INDEX, pretun_idx);
 
 	set_tun->tun_type_index = cpu_to_be32(tmp_set_ip_tun_type_index);
-	if (ip_tun->key.tun_flags & NFP_FL_TUNNEL_KEY)
+	if (tun_flags & NFP_FL_TUNNEL_KEY)
 		set_tun->tun_id = ip_tun->key.tun_id;
 
 	if (ip_tun->key.ttl) {
@@ -486,7 +501,7 @@ nfp_fl_set_tun(struct nfp_app *app, struct nfp_fl_set_tun *set_tun,
 	}
 
 	set_tun->tos = ip_tun->key.tos;
-	set_tun->tun_flags = ip_tun->key.tun_flags;
+	set_tun->tun_flags = tun_flags;
 
 	if (tun_type == NFP_FL_TUNNEL_GENEVE) {
 		set_tun->tun_proto = htons(ETH_P_TEB);