From 2ebe81c814355d000fe49d9c4213983844dcb32b Mon Sep 17 00:00:00 2001
From: Aleksander Lobakin <aleksander.lobakin@intel.com>
Date: Wed, 6 Dec 2023 21:59:19 +0100
Subject: net, xdp: Allow metadata > 32

32 bytes may be not enough for some custom metadata. Relax the restriction,
allow metadata larger than 32 bytes and make __skb_metadata_differs() work
with bigger lengths.

Now size of metadata is only limited by the fact it is stored as u8 in
skb_shared_info, so maximum possible value is 255. Size still has to be
aligned to 4, so the actual upper limit becomes 252. Most driver
implementations will offer less, none can offer more.

Other important conditions, such as having enough space for xdp_frame
building, are already checked in bpf_xdp_adjust_meta().

Signed-off-by: Aleksander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/eb87653c-8ff8-447d-a7a1-25961f60518a@kernel.org
Link: https://lore.kernel.org/bpf/20231206205919.404415-3-larysa.zaremba@intel.com
---
 include/net/xdp.h | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

(limited to 'include/net')

diff --git a/include/net/xdp.h b/include/net/xdp.h
index 349c36fb5fd8..5d3673afc037 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -369,7 +369,12 @@ xdp_data_meta_unsupported(const struct xdp_buff *xdp)
 
 static inline bool xdp_metalen_invalid(unsigned long metalen)
 {
-	return (metalen & (sizeof(__u32) - 1)) || (metalen > 32);
+	unsigned long meta_max;
+
+	meta_max = type_max(typeof_member(struct skb_shared_info, meta_len));
+	BUILD_BUG_ON(!__builtin_constant_p(meta_max));
+
+	return !IS_ALIGNED(metalen, sizeof(u32)) || metalen > meta_max;
 }
 
 struct xdp_attachment_info {
-- 
cgit v1.2.3


From 0e6a7b09597011985d7aad3b747c43e9b2a43555 Mon Sep 17 00:00:00 2001
From: Larysa Zaremba <larysa.zaremba@intel.com>
Date: Tue, 5 Dec 2023 22:08:35 +0100
Subject: ice: Support RX hash XDP hint

RX hash XDP hint requests both hash value and type.
Type is XDP-specific, so we need a separate way to map
these values to the hardware ptypes, so create a lookup table.

Instead of creating a new long list, reuse contents
of ice_decode_rx_desc_ptype[] through preprocessor.

Current hash type enum does not contain ICMP packet type,
but ice devices support it, so also add a new type into core code.

Then use previously refactored code and create a function
that allows XDP code to read RX hash.

Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Link: https://lore.kernel.org/r/20231205210847.28460-7-larysa.zaremba@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h | 412 +++++++++++++------------
 drivers/net/ethernet/intel/ice/ice_txrx_lib.c  |  73 +++++
 include/net/xdp.h                              |   3 +
 3 files changed, 284 insertions(+), 204 deletions(-)

(limited to 'include/net')

diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
index 89f986a75cc8..d384ddfcb83e 100644
--- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
+++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
@@ -673,6 +673,212 @@ struct ice_tlan_ctx {
  *      Use the enum ice_rx_l2_ptype to decode the packet type
  * ENDIF
  */
+#define ICE_PTYPES								\
+	/* L2 Packet types */							\
+	ICE_PTT_UNUSED_ENTRY(0),						\
+	ICE_PTT(1, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),			\
+	ICE_PTT_UNUSED_ENTRY(2),						\
+	ICE_PTT_UNUSED_ENTRY(3),						\
+	ICE_PTT_UNUSED_ENTRY(4),						\
+	ICE_PTT_UNUSED_ENTRY(5),						\
+	ICE_PTT(6, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),			\
+	ICE_PTT(7, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),			\
+	ICE_PTT_UNUSED_ENTRY(8),						\
+	ICE_PTT_UNUSED_ENTRY(9),						\
+	ICE_PTT(10, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),		\
+	ICE_PTT(11, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),		\
+	ICE_PTT_UNUSED_ENTRY(12),						\
+	ICE_PTT_UNUSED_ENTRY(13),						\
+	ICE_PTT_UNUSED_ENTRY(14),						\
+	ICE_PTT_UNUSED_ENTRY(15),						\
+	ICE_PTT_UNUSED_ENTRY(16),						\
+	ICE_PTT_UNUSED_ENTRY(17),						\
+	ICE_PTT_UNUSED_ENTRY(18),						\
+	ICE_PTT_UNUSED_ENTRY(19),						\
+	ICE_PTT_UNUSED_ENTRY(20),						\
+	ICE_PTT_UNUSED_ENTRY(21),						\
+										\
+	/* Non Tunneled IPv4 */							\
+	ICE_PTT(22, IP, IPV4, FRG, NONE, NONE, NOF, NONE, PAY3),		\
+	ICE_PTT(23, IP, IPV4, NOF, NONE, NONE, NOF, NONE, PAY3),		\
+	ICE_PTT(24, IP, IPV4, NOF, NONE, NONE, NOF, UDP,  PAY4),		\
+	ICE_PTT_UNUSED_ENTRY(25),						\
+	ICE_PTT(26, IP, IPV4, NOF, NONE, NONE, NOF, TCP,  PAY4),		\
+	ICE_PTT(27, IP, IPV4, NOF, NONE, NONE, NOF, SCTP, PAY4),		\
+	ICE_PTT(28, IP, IPV4, NOF, NONE, NONE, NOF, ICMP, PAY4),		\
+										\
+	/* IPv4 --> IPv4 */							\
+	ICE_PTT(29, IP, IPV4, NOF, IP_IP, IPV4, FRG, NONE, PAY3),		\
+	ICE_PTT(30, IP, IPV4, NOF, IP_IP, IPV4, NOF, NONE, PAY3),		\
+	ICE_PTT(31, IP, IPV4, NOF, IP_IP, IPV4, NOF, UDP,  PAY4),		\
+	ICE_PTT_UNUSED_ENTRY(32),						\
+	ICE_PTT(33, IP, IPV4, NOF, IP_IP, IPV4, NOF, TCP,  PAY4),		\
+	ICE_PTT(34, IP, IPV4, NOF, IP_IP, IPV4, NOF, SCTP, PAY4),		\
+	ICE_PTT(35, IP, IPV4, NOF, IP_IP, IPV4, NOF, ICMP, PAY4),		\
+										\
+	/* IPv4 --> IPv6 */							\
+	ICE_PTT(36, IP, IPV4, NOF, IP_IP, IPV6, FRG, NONE, PAY3),		\
+	ICE_PTT(37, IP, IPV4, NOF, IP_IP, IPV6, NOF, NONE, PAY3),		\
+	ICE_PTT(38, IP, IPV4, NOF, IP_IP, IPV6, NOF, UDP,  PAY4),		\
+	ICE_PTT_UNUSED_ENTRY(39),						\
+	ICE_PTT(40, IP, IPV4, NOF, IP_IP, IPV6, NOF, TCP,  PAY4),		\
+	ICE_PTT(41, IP, IPV4, NOF, IP_IP, IPV6, NOF, SCTP, PAY4),		\
+	ICE_PTT(42, IP, IPV4, NOF, IP_IP, IPV6, NOF, ICMP, PAY4),		\
+										\
+	/* IPv4 --> GRE/NAT */							\
+	ICE_PTT(43, IP, IPV4, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3),		\
+										\
+	/* IPv4 --> GRE/NAT --> IPv4 */						\
+	ICE_PTT(44, IP, IPV4, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3),		\
+	ICE_PTT(45, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3),		\
+	ICE_PTT(46, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, UDP,  PAY4),		\
+	ICE_PTT_UNUSED_ENTRY(47),						\
+	ICE_PTT(48, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, TCP,  PAY4),		\
+	ICE_PTT(49, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4),		\
+	ICE_PTT(50, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4),		\
+										\
+	/* IPv4 --> GRE/NAT --> IPv6 */						\
+	ICE_PTT(51, IP, IPV4, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3),		\
+	ICE_PTT(52, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3),		\
+	ICE_PTT(53, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, UDP,  PAY4),		\
+	ICE_PTT_UNUSED_ENTRY(54),						\
+	ICE_PTT(55, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, TCP,  PAY4),		\
+	ICE_PTT(56, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4),		\
+	ICE_PTT(57, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4),		\
+										\
+	/* IPv4 --> GRE/NAT --> MAC */						\
+	ICE_PTT(58, IP, IPV4, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3),	\
+										\
+	/* IPv4 --> GRE/NAT --> MAC --> IPv4 */					\
+	ICE_PTT(59, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3),	\
+	ICE_PTT(60, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3),	\
+	ICE_PTT(61, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP,  PAY4),	\
+	ICE_PTT_UNUSED_ENTRY(62),						\
+	ICE_PTT(63, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP,  PAY4),	\
+	ICE_PTT(64, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4),	\
+	ICE_PTT(65, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4),	\
+										\
+	/* IPv4 --> GRE/NAT -> MAC --> IPv6 */					\
+	ICE_PTT(66, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3),	\
+	ICE_PTT(67, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3),	\
+	ICE_PTT(68, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP,  PAY4),	\
+	ICE_PTT_UNUSED_ENTRY(69),						\
+	ICE_PTT(70, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP,  PAY4),	\
+	ICE_PTT(71, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4),	\
+	ICE_PTT(72, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4),	\
+										\
+	/* IPv4 --> GRE/NAT --> MAC/VLAN */					\
+	ICE_PTT(73, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3),	\
+										\
+	/* IPv4 ---> GRE/NAT -> MAC/VLAN --> IPv4 */				\
+	ICE_PTT(74, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3),	\
+	ICE_PTT(75, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3),	\
+	ICE_PTT(76, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP,  PAY4),	\
+	ICE_PTT_UNUSED_ENTRY(77),						\
+	ICE_PTT(78, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP,  PAY4),	\
+	ICE_PTT(79, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4),	\
+	ICE_PTT(80, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4),	\
+										\
+	/* IPv4 -> GRE/NAT -> MAC/VLAN --> IPv6 */				\
+	ICE_PTT(81, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3),	\
+	ICE_PTT(82, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3),	\
+	ICE_PTT(83, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP,  PAY4),	\
+	ICE_PTT_UNUSED_ENTRY(84),						\
+	ICE_PTT(85, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP,  PAY4),	\
+	ICE_PTT(86, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4),	\
+	ICE_PTT(87, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4),	\
+										\
+	/* Non Tunneled IPv6 */							\
+	ICE_PTT(88, IP, IPV6, FRG, NONE, NONE, NOF, NONE, PAY3),		\
+	ICE_PTT(89, IP, IPV6, NOF, NONE, NONE, NOF, NONE, PAY3),		\
+	ICE_PTT(90, IP, IPV6, NOF, NONE, NONE, NOF, UDP,  PAY4),		\
+	ICE_PTT_UNUSED_ENTRY(91),						\
+	ICE_PTT(92, IP, IPV6, NOF, NONE, NONE, NOF, TCP,  PAY4),		\
+	ICE_PTT(93, IP, IPV6, NOF, NONE, NONE, NOF, SCTP, PAY4),		\
+	ICE_PTT(94, IP, IPV6, NOF, NONE, NONE, NOF, ICMP, PAY4),		\
+										\
+	/* IPv6 --> IPv4 */							\
+	ICE_PTT(95, IP, IPV6, NOF, IP_IP, IPV4, FRG, NONE, PAY3),		\
+	ICE_PTT(96, IP, IPV6, NOF, IP_IP, IPV4, NOF, NONE, PAY3),		\
+	ICE_PTT(97, IP, IPV6, NOF, IP_IP, IPV4, NOF, UDP,  PAY4),		\
+	ICE_PTT_UNUSED_ENTRY(98),						\
+	ICE_PTT(99, IP, IPV6, NOF, IP_IP, IPV4, NOF, TCP,  PAY4),		\
+	ICE_PTT(100, IP, IPV6, NOF, IP_IP, IPV4, NOF, SCTP, PAY4),		\
+	ICE_PTT(101, IP, IPV6, NOF, IP_IP, IPV4, NOF, ICMP, PAY4),		\
+										\
+	/* IPv6 --> IPv6 */							\
+	ICE_PTT(102, IP, IPV6, NOF, IP_IP, IPV6, FRG, NONE, PAY3),		\
+	ICE_PTT(103, IP, IPV6, NOF, IP_IP, IPV6, NOF, NONE, PAY3),		\
+	ICE_PTT(104, IP, IPV6, NOF, IP_IP, IPV6, NOF, UDP,  PAY4),		\
+	ICE_PTT_UNUSED_ENTRY(105),						\
+	ICE_PTT(106, IP, IPV6, NOF, IP_IP, IPV6, NOF, TCP,  PAY4),		\
+	ICE_PTT(107, IP, IPV6, NOF, IP_IP, IPV6, NOF, SCTP, PAY4),		\
+	ICE_PTT(108, IP, IPV6, NOF, IP_IP, IPV6, NOF, ICMP, PAY4),		\
+										\
+	/* IPv6 --> GRE/NAT */							\
+	ICE_PTT(109, IP, IPV6, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3),		\
+										\
+	/* IPv6 --> GRE/NAT -> IPv4 */						\
+	ICE_PTT(110, IP, IPV6, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3),		\
+	ICE_PTT(111, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3),		\
+	ICE_PTT(112, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, UDP,  PAY4),		\
+	ICE_PTT_UNUSED_ENTRY(113),						\
+	ICE_PTT(114, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, TCP,  PAY4),		\
+	ICE_PTT(115, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4),		\
+	ICE_PTT(116, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4),		\
+										\
+	/* IPv6 --> GRE/NAT -> IPv6 */						\
+	ICE_PTT(117, IP, IPV6, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3),		\
+	ICE_PTT(118, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3),		\
+	ICE_PTT(119, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, UDP,  PAY4),		\
+	ICE_PTT_UNUSED_ENTRY(120),						\
+	ICE_PTT(121, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, TCP,  PAY4),		\
+	ICE_PTT(122, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4),		\
+	ICE_PTT(123, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4),		\
+										\
+	/* IPv6 --> GRE/NAT -> MAC */						\
+	ICE_PTT(124, IP, IPV6, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3),	\
+										\
+	/* IPv6 --> GRE/NAT -> MAC -> IPv4 */					\
+	ICE_PTT(125, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3),	\
+	ICE_PTT(126, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3),	\
+	ICE_PTT(127, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP,  PAY4),	\
+	ICE_PTT_UNUSED_ENTRY(128),						\
+	ICE_PTT(129, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP,  PAY4),	\
+	ICE_PTT(130, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4),	\
+	ICE_PTT(131, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4),	\
+										\
+	/* IPv6 --> GRE/NAT -> MAC -> IPv6 */					\
+	ICE_PTT(132, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3),	\
+	ICE_PTT(133, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3),	\
+	ICE_PTT(134, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP,  PAY4),	\
+	ICE_PTT_UNUSED_ENTRY(135),						\
+	ICE_PTT(136, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP,  PAY4),	\
+	ICE_PTT(137, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4),	\
+	ICE_PTT(138, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4),	\
+										\
+	/* IPv6 --> GRE/NAT -> MAC/VLAN */					\
+	ICE_PTT(139, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3),	\
+										\
+	/* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv4 */				\
+	ICE_PTT(140, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3),	\
+	ICE_PTT(141, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3),	\
+	ICE_PTT(142, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP,  PAY4),	\
+	ICE_PTT_UNUSED_ENTRY(143),						\
+	ICE_PTT(144, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP,  PAY4),	\
+	ICE_PTT(145, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4),	\
+	ICE_PTT(146, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4),	\
+										\
+	/* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv6 */				\
+	ICE_PTT(147, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3),	\
+	ICE_PTT(148, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3),	\
+	ICE_PTT(149, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP,  PAY4),	\
+	ICE_PTT_UNUSED_ENTRY(150),						\
+	ICE_PTT(151, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP,  PAY4),	\
+	ICE_PTT(152, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4),	\
+	ICE_PTT(153, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4),
+
+#define ICE_NUM_DEFINED_PTYPES	154
 
 /* macro to make the table lines short, use explicit indexing with [PTYPE] */
 #define ICE_PTT(PTYPE, OUTER_IP, OUTER_IP_VER, OUTER_FRAG, T, TE, TEF, I, PL)\
@@ -695,212 +901,10 @@ struct ice_tlan_ctx {
 
 /* Lookup table mapping in the 10-bit HW PTYPE to the bit field for decoding */
 static const struct ice_rx_ptype_decoded ice_ptype_lkup[BIT(10)] = {
-	/* L2 Packet types */
-	ICE_PTT_UNUSED_ENTRY(0),
-	ICE_PTT(1, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),
-	ICE_PTT_UNUSED_ENTRY(2),
-	ICE_PTT_UNUSED_ENTRY(3),
-	ICE_PTT_UNUSED_ENTRY(4),
-	ICE_PTT_UNUSED_ENTRY(5),
-	ICE_PTT(6, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),
-	ICE_PTT(7, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),
-	ICE_PTT_UNUSED_ENTRY(8),
-	ICE_PTT_UNUSED_ENTRY(9),
-	ICE_PTT(10, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),
-	ICE_PTT(11, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),
-	ICE_PTT_UNUSED_ENTRY(12),
-	ICE_PTT_UNUSED_ENTRY(13),
-	ICE_PTT_UNUSED_ENTRY(14),
-	ICE_PTT_UNUSED_ENTRY(15),
-	ICE_PTT_UNUSED_ENTRY(16),
-	ICE_PTT_UNUSED_ENTRY(17),
-	ICE_PTT_UNUSED_ENTRY(18),
-	ICE_PTT_UNUSED_ENTRY(19),
-	ICE_PTT_UNUSED_ENTRY(20),
-	ICE_PTT_UNUSED_ENTRY(21),
-
-	/* Non Tunneled IPv4 */
-	ICE_PTT(22, IP, IPV4, FRG, NONE, NONE, NOF, NONE, PAY3),
-	ICE_PTT(23, IP, IPV4, NOF, NONE, NONE, NOF, NONE, PAY3),
-	ICE_PTT(24, IP, IPV4, NOF, NONE, NONE, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(25),
-	ICE_PTT(26, IP, IPV4, NOF, NONE, NONE, NOF, TCP,  PAY4),
-	ICE_PTT(27, IP, IPV4, NOF, NONE, NONE, NOF, SCTP, PAY4),
-	ICE_PTT(28, IP, IPV4, NOF, NONE, NONE, NOF, ICMP, PAY4),
-
-	/* IPv4 --> IPv4 */
-	ICE_PTT(29, IP, IPV4, NOF, IP_IP, IPV4, FRG, NONE, PAY3),
-	ICE_PTT(30, IP, IPV4, NOF, IP_IP, IPV4, NOF, NONE, PAY3),
-	ICE_PTT(31, IP, IPV4, NOF, IP_IP, IPV4, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(32),
-	ICE_PTT(33, IP, IPV4, NOF, IP_IP, IPV4, NOF, TCP,  PAY4),
-	ICE_PTT(34, IP, IPV4, NOF, IP_IP, IPV4, NOF, SCTP, PAY4),
-	ICE_PTT(35, IP, IPV4, NOF, IP_IP, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv4 --> IPv6 */
-	ICE_PTT(36, IP, IPV4, NOF, IP_IP, IPV6, FRG, NONE, PAY3),
-	ICE_PTT(37, IP, IPV4, NOF, IP_IP, IPV6, NOF, NONE, PAY3),
-	ICE_PTT(38, IP, IPV4, NOF, IP_IP, IPV6, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(39),
-	ICE_PTT(40, IP, IPV4, NOF, IP_IP, IPV6, NOF, TCP,  PAY4),
-	ICE_PTT(41, IP, IPV4, NOF, IP_IP, IPV6, NOF, SCTP, PAY4),
-	ICE_PTT(42, IP, IPV4, NOF, IP_IP, IPV6, NOF, ICMP, PAY4),
-
-	/* IPv4 --> GRE/NAT */
-	ICE_PTT(43, IP, IPV4, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3),
-
-	/* IPv4 --> GRE/NAT --> IPv4 */
-	ICE_PTT(44, IP, IPV4, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3),
-	ICE_PTT(45, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3),
-	ICE_PTT(46, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(47),
-	ICE_PTT(48, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, TCP,  PAY4),
-	ICE_PTT(49, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4),
-	ICE_PTT(50, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv4 --> GRE/NAT --> IPv6 */
-	ICE_PTT(51, IP, IPV4, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3),
-	ICE_PTT(52, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3),
-	ICE_PTT(53, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(54),
-	ICE_PTT(55, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, TCP,  PAY4),
-	ICE_PTT(56, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4),
-	ICE_PTT(57, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4),
-
-	/* IPv4 --> GRE/NAT --> MAC */
-	ICE_PTT(58, IP, IPV4, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3),
-
-	/* IPv4 --> GRE/NAT --> MAC --> IPv4 */
-	ICE_PTT(59, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3),
-	ICE_PTT(60, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3),
-	ICE_PTT(61, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(62),
-	ICE_PTT(63, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP,  PAY4),
-	ICE_PTT(64, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4),
-	ICE_PTT(65, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv4 --> GRE/NAT -> MAC --> IPv6 */
-	ICE_PTT(66, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3),
-	ICE_PTT(67, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3),
-	ICE_PTT(68, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(69),
-	ICE_PTT(70, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP,  PAY4),
-	ICE_PTT(71, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4),
-	ICE_PTT(72, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4),
-
-	/* IPv4 --> GRE/NAT --> MAC/VLAN */
-	ICE_PTT(73, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3),
-
-	/* IPv4 ---> GRE/NAT -> MAC/VLAN --> IPv4 */
-	ICE_PTT(74, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3),
-	ICE_PTT(75, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3),
-	ICE_PTT(76, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(77),
-	ICE_PTT(78, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP,  PAY4),
-	ICE_PTT(79, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4),
-	ICE_PTT(80, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv4 -> GRE/NAT -> MAC/VLAN --> IPv6 */
-	ICE_PTT(81, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3),
-	ICE_PTT(82, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3),
-	ICE_PTT(83, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(84),
-	ICE_PTT(85, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP,  PAY4),
-	ICE_PTT(86, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4),
-	ICE_PTT(87, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4),
-
-	/* Non Tunneled IPv6 */
-	ICE_PTT(88, IP, IPV6, FRG, NONE, NONE, NOF, NONE, PAY3),
-	ICE_PTT(89, IP, IPV6, NOF, NONE, NONE, NOF, NONE, PAY3),
-	ICE_PTT(90, IP, IPV6, NOF, NONE, NONE, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(91),
-	ICE_PTT(92, IP, IPV6, NOF, NONE, NONE, NOF, TCP,  PAY4),
-	ICE_PTT(93, IP, IPV6, NOF, NONE, NONE, NOF, SCTP, PAY4),
-	ICE_PTT(94, IP, IPV6, NOF, NONE, NONE, NOF, ICMP, PAY4),
-
-	/* IPv6 --> IPv4 */
-	ICE_PTT(95, IP, IPV6, NOF, IP_IP, IPV4, FRG, NONE, PAY3),
-	ICE_PTT(96, IP, IPV6, NOF, IP_IP, IPV4, NOF, NONE, PAY3),
-	ICE_PTT(97, IP, IPV6, NOF, IP_IP, IPV4, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(98),
-	ICE_PTT(99, IP, IPV6, NOF, IP_IP, IPV4, NOF, TCP,  PAY4),
-	ICE_PTT(100, IP, IPV6, NOF, IP_IP, IPV4, NOF, SCTP, PAY4),
-	ICE_PTT(101, IP, IPV6, NOF, IP_IP, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv6 --> IPv6 */
-	ICE_PTT(102, IP, IPV6, NOF, IP_IP, IPV6, FRG, NONE, PAY3),
-	ICE_PTT(103, IP, IPV6, NOF, IP_IP, IPV6, NOF, NONE, PAY3),
-	ICE_PTT(104, IP, IPV6, NOF, IP_IP, IPV6, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(105),
-	ICE_PTT(106, IP, IPV6, NOF, IP_IP, IPV6, NOF, TCP,  PAY4),
-	ICE_PTT(107, IP, IPV6, NOF, IP_IP, IPV6, NOF, SCTP, PAY4),
-	ICE_PTT(108, IP, IPV6, NOF, IP_IP, IPV6, NOF, ICMP, PAY4),
-
-	/* IPv6 --> GRE/NAT */
-	ICE_PTT(109, IP, IPV6, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3),
-
-	/* IPv6 --> GRE/NAT -> IPv4 */
-	ICE_PTT(110, IP, IPV6, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3),
-	ICE_PTT(111, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3),
-	ICE_PTT(112, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(113),
-	ICE_PTT(114, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, TCP,  PAY4),
-	ICE_PTT(115, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4),
-	ICE_PTT(116, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv6 --> GRE/NAT -> IPv6 */
-	ICE_PTT(117, IP, IPV6, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3),
-	ICE_PTT(118, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3),
-	ICE_PTT(119, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(120),
-	ICE_PTT(121, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, TCP,  PAY4),
-	ICE_PTT(122, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4),
-	ICE_PTT(123, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4),
-
-	/* IPv6 --> GRE/NAT -> MAC */
-	ICE_PTT(124, IP, IPV6, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3),
-
-	/* IPv6 --> GRE/NAT -> MAC -> IPv4 */
-	ICE_PTT(125, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3),
-	ICE_PTT(126, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3),
-	ICE_PTT(127, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(128),
-	ICE_PTT(129, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP,  PAY4),
-	ICE_PTT(130, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4),
-	ICE_PTT(131, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv6 --> GRE/NAT -> MAC -> IPv6 */
-	ICE_PTT(132, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3),
-	ICE_PTT(133, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3),
-	ICE_PTT(134, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(135),
-	ICE_PTT(136, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP,  PAY4),
-	ICE_PTT(137, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4),
-	ICE_PTT(138, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4),
-
-	/* IPv6 --> GRE/NAT -> MAC/VLAN */
-	ICE_PTT(139, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3),
-
-	/* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv4 */
-	ICE_PTT(140, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3),
-	ICE_PTT(141, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3),
-	ICE_PTT(142, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(143),
-	ICE_PTT(144, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP,  PAY4),
-	ICE_PTT(145, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4),
-	ICE_PTT(146, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv6 */
-	ICE_PTT(147, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3),
-	ICE_PTT(148, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3),
-	ICE_PTT(149, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(150),
-	ICE_PTT(151, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP,  PAY4),
-	ICE_PTT(152, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4),
-	ICE_PTT(153, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4),
+	ICE_PTYPES
 
 	/* unused entries */
-	[154 ... 1023] = { 0, 0, 0, 0, 0, 0, 0, 0, 0 }
+	[ICE_NUM_DEFINED_PTYPES ... 1023] = { 0, 0, 0, 0, 0, 0, 0, 0, 0 }
 };
 
 static inline struct ice_rx_ptype_decoded ice_decode_rx_desc_ptype(u16 ptype)
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
index 13b8a9addfac..09610c5615a8 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
@@ -527,6 +527,79 @@ static int ice_xdp_rx_hw_ts(const struct xdp_md *ctx, u64 *ts_ns)
 	return 0;
 }
 
+/* Define a ptype index -> XDP hash type lookup table.
+ * It uses the same ptype definitions as ice_decode_rx_desc_ptype[],
+ * avoiding possible copy-paste errors.
+ */
+#undef ICE_PTT
+#undef ICE_PTT_UNUSED_ENTRY
+
+#define ICE_PTT(PTYPE, OUTER_IP, OUTER_IP_VER, OUTER_FRAG, T, TE, TEF, I, PL)\
+	[PTYPE] = XDP_RSS_L3_##OUTER_IP_VER | XDP_RSS_L4_##I | XDP_RSS_TYPE_##PL
+
+#define ICE_PTT_UNUSED_ENTRY(PTYPE) [PTYPE] = 0
+
+/* A few supplementary definitions for when XDP hash types do not coincide
+ * with what can be generated from ptype definitions
+ * by means of preprocessor concatenation.
+ */
+#define XDP_RSS_L3_NONE		XDP_RSS_TYPE_NONE
+#define XDP_RSS_L4_NONE		XDP_RSS_TYPE_NONE
+#define XDP_RSS_TYPE_PAY2	XDP_RSS_TYPE_L2
+#define XDP_RSS_TYPE_PAY3	XDP_RSS_TYPE_NONE
+#define XDP_RSS_TYPE_PAY4	XDP_RSS_L4
+
+static const enum xdp_rss_hash_type
+ice_ptype_to_xdp_hash[ICE_NUM_DEFINED_PTYPES] = {
+	ICE_PTYPES
+};
+
+#undef XDP_RSS_L3_NONE
+#undef XDP_RSS_L4_NONE
+#undef XDP_RSS_TYPE_PAY2
+#undef XDP_RSS_TYPE_PAY3
+#undef XDP_RSS_TYPE_PAY4
+
+#undef ICE_PTT
+#undef ICE_PTT_UNUSED_ENTRY
+
+/**
+ * ice_xdp_rx_hash_type - Get XDP-specific hash type from the RX descriptor
+ * @eop_desc: End of Packet descriptor
+ */
+static enum xdp_rss_hash_type
+ice_xdp_rx_hash_type(const union ice_32b_rx_flex_desc *eop_desc)
+{
+	u16 ptype = ice_get_ptype(eop_desc);
+
+	if (unlikely(ptype >= ICE_NUM_DEFINED_PTYPES))
+		return 0;
+
+	return ice_ptype_to_xdp_hash[ptype];
+}
+
+/**
+ * ice_xdp_rx_hash - RX hash XDP hint handler
+ * @ctx: XDP buff pointer
+ * @hash: hash destination address
+ * @rss_type: XDP hash type destination address
+ *
+ * Copy RX hash (if available) and its type to the destination address.
+ */
+static int ice_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash,
+			   enum xdp_rss_hash_type *rss_type)
+{
+	const struct ice_xdp_buff *xdp_ext = (void *)ctx;
+
+	*hash = ice_get_rx_hash(xdp_ext->eop_desc);
+	*rss_type = ice_xdp_rx_hash_type(xdp_ext->eop_desc);
+	if (!likely(*hash))
+		return -ENODATA;
+
+	return 0;
+}
+
 const struct xdp_metadata_ops ice_xdp_md_ops = {
 	.xmo_rx_timestamp		= ice_xdp_rx_hw_ts,
+	.xmo_rx_hash			= ice_xdp_rx_hash,
 };
diff --git a/include/net/xdp.h b/include/net/xdp.h
index 5d3673afc037..b7d6fe61381f 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -432,6 +432,7 @@ enum xdp_rss_hash_type {
 	XDP_RSS_L4_UDP		= BIT(5),
 	XDP_RSS_L4_SCTP		= BIT(6),
 	XDP_RSS_L4_IPSEC	= BIT(7), /* L4 based hash include IPSEC SPI */
+	XDP_RSS_L4_ICMP		= BIT(8),
 
 	/* Second part: RSS hash type combinations used for driver HW mapping */
 	XDP_RSS_TYPE_NONE            = 0,
@@ -447,11 +448,13 @@ enum xdp_rss_hash_type {
 	XDP_RSS_TYPE_L4_IPV4_UDP     = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_UDP,
 	XDP_RSS_TYPE_L4_IPV4_SCTP    = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_SCTP,
 	XDP_RSS_TYPE_L4_IPV4_IPSEC   = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_IPSEC,
+	XDP_RSS_TYPE_L4_IPV4_ICMP    = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_ICMP,
 
 	XDP_RSS_TYPE_L4_IPV6_TCP     = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_TCP,
 	XDP_RSS_TYPE_L4_IPV6_UDP     = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_UDP,
 	XDP_RSS_TYPE_L4_IPV6_SCTP    = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_SCTP,
 	XDP_RSS_TYPE_L4_IPV6_IPSEC   = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_IPSEC,
+	XDP_RSS_TYPE_L4_IPV6_ICMP    = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_ICMP,
 
 	XDP_RSS_TYPE_L4_IPV6_TCP_EX  = XDP_RSS_TYPE_L4_IPV6_TCP  | XDP_RSS_L3_DYNHDR,
 	XDP_RSS_TYPE_L4_IPV6_UDP_EX  = XDP_RSS_TYPE_L4_IPV6_UDP  | XDP_RSS_L3_DYNHDR,
-- 
cgit v1.2.3


From b4e352ff1169ebce930c734630f9587b1677d163 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Tue, 5 Dec 2023 22:08:36 +0100
Subject: xsk: add functions to fill control buffer

Commit 94ecc5ca4dbf ("xsk: Add cb area to struct xdp_buff_xsk") has added
a buffer for custom data to xdp_buff_xsk. Particularly, this memory is used
for data, consumed by XDP hints kfuncs. It does not always change on
a per-packet basis and some parts can be set for example, at the same time
as RX queue info.

Add functions to fill all cbs in xsk_buff_pool with the same metadata.

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/r/20231205210847.28460-8-larysa.zaremba@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/net/xdp_sock_drv.h  | 17 +++++++++++++++++
 include/net/xsk_buff_pool.h |  2 ++
 net/xdp/xsk_buff_pool.c     | 12 ++++++++++++
 3 files changed, 31 insertions(+)

(limited to 'include/net')

diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
index 81e02de3f453..b62bb8525a5f 100644
--- a/include/net/xdp_sock_drv.h
+++ b/include/net/xdp_sock_drv.h
@@ -14,6 +14,12 @@
 
 #ifdef CONFIG_XDP_SOCKETS
 
+struct xsk_cb_desc {
+	void *src;
+	u8 off;
+	u8 bytes;
+};
+
 void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries);
 bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc);
 u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, u32 max);
@@ -47,6 +53,12 @@ static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool,
 	xp_set_rxq_info(pool, rxq);
 }
 
+static inline void xsk_pool_fill_cb(struct xsk_buff_pool *pool,
+				    struct xsk_cb_desc *desc)
+{
+	xp_fill_cb(pool, desc);
+}
+
 static inline unsigned int xsk_pool_get_napi_id(struct xsk_buff_pool *pool)
 {
 #ifdef CONFIG_NET_RX_BUSY_POLL
@@ -274,6 +286,11 @@ static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool,
 {
 }
 
+static inline void xsk_pool_fill_cb(struct xsk_buff_pool *pool,
+				    struct xsk_cb_desc *desc)
+{
+}
+
 static inline unsigned int xsk_pool_get_napi_id(struct xsk_buff_pool *pool)
 {
 	return 0;
diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index 8d48d37ab7c0..99dd7376df6a 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -12,6 +12,7 @@
 
 struct xsk_buff_pool;
 struct xdp_rxq_info;
+struct xsk_cb_desc;
 struct xsk_queue;
 struct xdp_desc;
 struct xdp_umem;
@@ -135,6 +136,7 @@ static inline void xp_init_xskb_dma(struct xdp_buff_xsk *xskb, struct xsk_buff_p
 
 /* AF_XDP ZC drivers, via xdp_sock_buff.h */
 void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq);
+void xp_fill_cb(struct xsk_buff_pool *pool, struct xsk_cb_desc *desc);
 int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev,
 	       unsigned long attrs, struct page **pages, u32 nr_pages);
 void xp_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs);
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index 4f6f538a5462..28711cc44ced 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -125,6 +125,18 @@ void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq)
 }
 EXPORT_SYMBOL(xp_set_rxq_info);
 
+void xp_fill_cb(struct xsk_buff_pool *pool, struct xsk_cb_desc *desc)
+{
+	u32 i;
+
+	for (i = 0; i < pool->heads_cnt; i++) {
+		struct xdp_buff_xsk *xskb = &pool->heads[i];
+
+		memcpy(xskb->cb + desc->off, desc->src, desc->bytes);
+	}
+}
+EXPORT_SYMBOL(xp_fill_cb);
+
 static void xp_disable_drv_zc(struct xsk_buff_pool *pool)
 {
 	struct netdev_bpf bpf;
-- 
cgit v1.2.3


From e6795330f88b4f643c649a02662d47b779340535 Mon Sep 17 00:00:00 2001
From: Larysa Zaremba <larysa.zaremba@intel.com>
Date: Tue, 5 Dec 2023 22:08:38 +0100
Subject: xdp: Add VLAN tag hint

Implement functionality that enables drivers to expose VLAN tag
to XDP code.

VLAN tag is represented by 2 variables:
- protocol ID, which is passed to bpf code in BE
- VLAN TCI, in host byte order

Acked-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Link: https://lore.kernel.org/r/20231205210847.28460-10-larysa.zaremba@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 Documentation/netlink/specs/netdev.yaml      |  4 ++++
 Documentation/networking/xdp-rx-metadata.rst |  8 ++++++-
 include/net/xdp.h                            |  6 +++++
 include/uapi/linux/netdev.h                  |  3 +++
 net/core/xdp.c                               | 33 ++++++++++++++++++++++++++++
 tools/include/uapi/linux/netdev.h            |  3 +++
 tools/net/ynl/generated/netdev-user.c        |  1 +
 7 files changed, 57 insertions(+), 1 deletion(-)

(limited to 'include/net')

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index eef6358ec587..aeec090e1387 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -54,6 +54,10 @@ definitions:
         name: hash
         doc:
           Device is capable of exposing receive packet hash via bpf_xdp_metadata_rx_hash().
+      -
+        name: vlan-tag
+        doc:
+          Device is capable of exposing receive packet VLAN tag via bpf_xdp_metadata_rx_vlan_tag().
   -
     type: flags
     name: xsk-flags
diff --git a/Documentation/networking/xdp-rx-metadata.rst b/Documentation/networking/xdp-rx-metadata.rst
index e3e9420fd817..a6e0ece18be5 100644
--- a/Documentation/networking/xdp-rx-metadata.rst
+++ b/Documentation/networking/xdp-rx-metadata.rst
@@ -20,7 +20,13 @@ Currently, the following kfuncs are supported. In the future, as more
 metadata is supported, this set will grow:
 
 .. kernel-doc:: net/core/xdp.c
-   :identifiers: bpf_xdp_metadata_rx_timestamp bpf_xdp_metadata_rx_hash
+   :identifiers: bpf_xdp_metadata_rx_timestamp
+
+.. kernel-doc:: net/core/xdp.c
+   :identifiers: bpf_xdp_metadata_rx_hash
+
+.. kernel-doc:: net/core/xdp.c
+   :identifiers: bpf_xdp_metadata_rx_vlan_tag
 
 An XDP program can use these kfuncs to read the metadata into stack
 variables for its own consumption. Or, to pass the metadata on to other
diff --git a/include/net/xdp.h b/include/net/xdp.h
index b7d6fe61381f..8cd04a74dba5 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -404,6 +404,10 @@ void xdp_attachment_setup(struct xdp_attachment_info *info,
 			   NETDEV_XDP_RX_METADATA_HASH, \
 			   bpf_xdp_metadata_rx_hash, \
 			   xmo_rx_hash) \
+	XDP_METADATA_KFUNC(XDP_METADATA_KFUNC_RX_VLAN_TAG, \
+			   NETDEV_XDP_RX_METADATA_VLAN_TAG, \
+			   bpf_xdp_metadata_rx_vlan_tag, \
+			   xmo_rx_vlan_tag) \
 
 enum xdp_rx_metadata {
 #define XDP_METADATA_KFUNC(name, _, __, ___) name,
@@ -465,6 +469,8 @@ struct xdp_metadata_ops {
 	int	(*xmo_rx_timestamp)(const struct xdp_md *ctx, u64 *timestamp);
 	int	(*xmo_rx_hash)(const struct xdp_md *ctx, u32 *hash,
 			       enum xdp_rss_hash_type *rss_type);
+	int	(*xmo_rx_vlan_tag)(const struct xdp_md *ctx, __be16 *vlan_proto,
+				   u16 *vlan_tci);
 };
 
 #ifdef CONFIG_NET
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index 6244c0164976..966638b08ccf 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -44,10 +44,13 @@ enum netdev_xdp_act {
  *   timestamp via bpf_xdp_metadata_rx_timestamp().
  * @NETDEV_XDP_RX_METADATA_HASH: Device is capable of exposing receive packet
  *   hash via bpf_xdp_metadata_rx_hash().
+ * @NETDEV_XDP_RX_METADATA_VLAN_TAG: Device is capable of exposing receive
+ *   packet VLAN tag via bpf_xdp_metadata_rx_vlan_tag().
  */
 enum netdev_xdp_rx_metadata {
 	NETDEV_XDP_RX_METADATA_TIMESTAMP = 1,
 	NETDEV_XDP_RX_METADATA_HASH = 2,
+	NETDEV_XDP_RX_METADATA_VLAN_TAG = 4,
 };
 
 /**
diff --git a/net/core/xdp.c b/net/core/xdp.c
index b6f1d6dab3f2..4869c1c2d8f3 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -736,6 +736,39 @@ __bpf_kfunc int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32 *hash,
 	return -EOPNOTSUPP;
 }
 
+/**
+ * bpf_xdp_metadata_rx_vlan_tag - Get XDP packet outermost VLAN tag
+ * @ctx: XDP context pointer.
+ * @vlan_proto: Destination pointer for VLAN Tag protocol identifier (TPID).
+ * @vlan_tci: Destination pointer for VLAN TCI (VID + DEI + PCP)
+ *
+ * In case of success, ``vlan_proto`` contains *Tag protocol identifier (TPID)*,
+ * usually ``ETH_P_8021Q`` or ``ETH_P_8021AD``, but some networks can use
+ * custom TPIDs. ``vlan_proto`` is stored in **network byte order (BE)**
+ * and should be used as follows:
+ * ``if (vlan_proto == bpf_htons(ETH_P_8021Q)) do_something();``
+ *
+ * ``vlan_tci`` contains the remaining 16 bits of a VLAN tag.
+ * Driver is expected to provide those in **host byte order (usually LE)**,
+ * so the bpf program should not perform byte conversion.
+ * According to 802.1Q standard, *VLAN TCI (Tag control information)*
+ * is a bit field that contains:
+ * *VLAN identifier (VID)* that can be read with ``vlan_tci & 0xfff``,
+ * *Drop eligible indicator (DEI)* - 1 bit,
+ * *Priority code point (PCP)* - 3 bits.
+ * For detailed meaning of DEI and PCP, please refer to other sources.
+ *
+ * Return:
+ * * Returns 0 on success or ``-errno`` on error.
+ * * ``-EOPNOTSUPP`` : device driver doesn't implement kfunc
+ * * ``-ENODATA``    : VLAN tag was not stripped or is not available
+ */
+__bpf_kfunc int bpf_xdp_metadata_rx_vlan_tag(const struct xdp_md *ctx,
+					     __be16 *vlan_proto, u16 *vlan_tci)
+{
+	return -EOPNOTSUPP;
+}
+
 __bpf_kfunc_end_defs();
 
 BTF_SET8_START(xdp_metadata_kfunc_ids)
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index 6244c0164976..966638b08ccf 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -44,10 +44,13 @@ enum netdev_xdp_act {
  *   timestamp via bpf_xdp_metadata_rx_timestamp().
  * @NETDEV_XDP_RX_METADATA_HASH: Device is capable of exposing receive packet
  *   hash via bpf_xdp_metadata_rx_hash().
+ * @NETDEV_XDP_RX_METADATA_VLAN_TAG: Device is capable of exposing receive
+ *   packet VLAN tag via bpf_xdp_metadata_rx_vlan_tag().
  */
 enum netdev_xdp_rx_metadata {
 	NETDEV_XDP_RX_METADATA_TIMESTAMP = 1,
 	NETDEV_XDP_RX_METADATA_HASH = 2,
+	NETDEV_XDP_RX_METADATA_VLAN_TAG = 4,
 };
 
 /**
diff --git a/tools/net/ynl/generated/netdev-user.c b/tools/net/ynl/generated/netdev-user.c
index 3b9dee94d4ce..e3fe748086bd 100644
--- a/tools/net/ynl/generated/netdev-user.c
+++ b/tools/net/ynl/generated/netdev-user.c
@@ -53,6 +53,7 @@ const char *netdev_xdp_act_str(enum netdev_xdp_act value)
 static const char * const netdev_xdp_rx_metadata_strmap[] = {
 	[0] = "timestamp",
 	[1] = "hash",
+	[2] = "vlan-tag",
 };
 
 const char *netdev_xdp_rx_metadata_str(enum netdev_xdp_rx_metadata value)
-- 
cgit v1.2.3


From 04d25ccea2b3199269b7e500da33023b51418fde Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 12 Dec 2023 20:37:35 -0800
Subject: net, xdp: Correct grammar

Use the correct verb form in 2 places in the XDP rx-queue comment.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Link: https://lore.kernel.org/bpf/20231213043735.30208-1-rdunlap@infradead.org
---
 include/net/xdp.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/net')

diff --git a/include/net/xdp.h b/include/net/xdp.h
index 8cd04a74dba5..e6770dd40c91 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -16,7 +16,7 @@
  *
  * The XDP RX-queue info (xdp_rxq_info) is associated with the driver
  * level RX-ring queues.  It is information that is specific to how
- * the driver have configured a given RX-ring queue.
+ * the driver has configured a given RX-ring queue.
  *
  * Each xdp_buff frame received in the driver carries a (pointer)
  * reference to this xdp_rxq_info structure.  This provides the XDP
@@ -32,7 +32,7 @@
  * The struct is not directly tied to the XDP prog.  A new XDP prog
  * can be attached as long as it doesn't change the underlying
  * RX-ring.  If the RX-ring does change significantly, the NIC driver
- * naturally need to stop the RX-ring before purging and reallocating
+ * naturally needs to stop the RX-ring before purging and reallocating
  * memory.  In that process the driver MUST call unregister (which
  * also applies for driver shutdown and unload).  The register API is
  * also mandatory during RX-ring setup.
-- 
cgit v1.2.3


From 8f0ec8c681755f523cf842bfe350ea40609b83a9 Mon Sep 17 00:00:00 2001
From: Daniel Xu <dxu@dxuuu.xyz>
Date: Thu, 14 Dec 2023 15:49:02 -0700
Subject: bpf: xfrm: Add bpf_xdp_get_xfrm_state() kfunc

This commit adds an unstable kfunc helper to access internal xfrm_state
associated with an SA. This is intended to be used for the upcoming
IPsec pcpu work to assign special pcpu SAs to a particular CPU. In other
words: for custom software RSS.

That being said, the function that this kfunc wraps is fairly generic
and used for a lot of xfrm tasks. I'm sure people will find uses
elsewhere over time.

This commit also adds a corresponding bpf_xdp_xfrm_state_release() kfunc
to release the refcnt acquired by bpf_xdp_get_xfrm_state(). The verifier
will require that all acquired xfrm_state's are released.

Co-developed-by: Antony Antony <antony.antony@secunet.com>
Signed-off-by: Antony Antony <antony.antony@secunet.com>
Acked-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: Daniel Xu <dxu@dxuuu.xyz>
Link: https://lore.kernel.org/r/a29699c42f5fad456b875c98dd11c6afc3ffb707.1702593901.git.dxu@dxuuu.xyz
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/net/xfrm.h        |   9 ++++
 net/xfrm/Makefile         |   1 +
 net/xfrm/xfrm_policy.c    |   2 +
 net/xfrm/xfrm_state_bpf.c | 134 ++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 146 insertions(+)
 create mode 100644 net/xfrm/xfrm_state_bpf.c

(limited to 'include/net')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index c9bb0f892f55..1d107241b901 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -2190,4 +2190,13 @@ static inline int register_xfrm_interface_bpf(void)
 
 #endif
 
+#if IS_ENABLED(CONFIG_DEBUG_INFO_BTF)
+int register_xfrm_state_bpf(void);
+#else
+static inline int register_xfrm_state_bpf(void)
+{
+	return 0;
+}
+#endif
+
 #endif	/* _NET_XFRM_H */
diff --git a/net/xfrm/Makefile b/net/xfrm/Makefile
index cd47f88921f5..547cec77ba03 100644
--- a/net/xfrm/Makefile
+++ b/net/xfrm/Makefile
@@ -21,3 +21,4 @@ obj-$(CONFIG_XFRM_USER_COMPAT) += xfrm_compat.o
 obj-$(CONFIG_XFRM_IPCOMP) += xfrm_ipcomp.o
 obj-$(CONFIG_XFRM_INTERFACE) += xfrm_interface.o
 obj-$(CONFIG_XFRM_ESPINTCP) += espintcp.o
+obj-$(CONFIG_DEBUG_INFO_BTF) += xfrm_state_bpf.o
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index c13dc3ef7910..1b7e75159727 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -4218,6 +4218,8 @@ void __init xfrm_init(void)
 #ifdef CONFIG_XFRM_ESPINTCP
 	espintcp_init();
 #endif
+
+	register_xfrm_state_bpf();
 }
 
 #ifdef CONFIG_AUDITSYSCALL
diff --git a/net/xfrm/xfrm_state_bpf.c b/net/xfrm/xfrm_state_bpf.c
new file mode 100644
index 000000000000..9e20d4a377f7
--- /dev/null
+++ b/net/xfrm/xfrm_state_bpf.c
@@ -0,0 +1,134 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Unstable XFRM state BPF helpers.
+ *
+ * Note that it is allowed to break compatibility for these functions since the
+ * interface they are exposed through to BPF programs is explicitly unstable.
+ */
+
+#include <linux/bpf.h>
+#include <linux/btf.h>
+#include <linux/btf_ids.h>
+#include <net/xdp.h>
+#include <net/xfrm.h>
+
+/* bpf_xfrm_state_opts - Options for XFRM state lookup helpers
+ *
+ * Members:
+ * @error      - Out parameter, set for any errors encountered
+ *		 Values:
+ *		   -EINVAL - netns_id is less than -1
+ *		   -EINVAL - opts__sz isn't BPF_XFRM_STATE_OPTS_SZ
+ *		   -ENONET - No network namespace found for netns_id
+ *		   -ENOENT - No xfrm_state found
+ * @netns_id	- Specify the network namespace for lookup
+ *		 Values:
+ *		   BPF_F_CURRENT_NETNS (-1)
+ *		     Use namespace associated with ctx
+ *		   [0, S32_MAX]
+ *		     Network Namespace ID
+ * @mark	- XFRM mark to match on
+ * @daddr	- Destination address to match on
+ * @spi		- Security parameter index to match on
+ * @proto	- IP protocol to match on (eg. IPPROTO_ESP)
+ * @family	- Protocol family to match on (AF_INET/AF_INET6)
+ */
+struct bpf_xfrm_state_opts {
+	s32 error;
+	s32 netns_id;
+	u32 mark;
+	xfrm_address_t daddr;
+	__be32 spi;
+	u8 proto;
+	u16 family;
+};
+
+enum {
+	BPF_XFRM_STATE_OPTS_SZ = sizeof(struct bpf_xfrm_state_opts),
+};
+
+__bpf_kfunc_start_defs();
+
+/* bpf_xdp_get_xfrm_state - Get XFRM state
+ *
+ * A `struct xfrm_state *`, if found, must be released with a corresponding
+ * bpf_xdp_xfrm_state_release.
+ *
+ * Parameters:
+ * @ctx	- Pointer to ctx (xdp_md) in XDP program
+ *		    Cannot be NULL
+ * @opts	- Options for lookup (documented above)
+ *		    Cannot be NULL
+ * @opts__sz	- Length of the bpf_xfrm_state_opts structure
+ *		    Must be BPF_XFRM_STATE_OPTS_SZ
+ */
+__bpf_kfunc struct xfrm_state *
+bpf_xdp_get_xfrm_state(struct xdp_md *ctx, struct bpf_xfrm_state_opts *opts, u32 opts__sz)
+{
+	struct xdp_buff *xdp = (struct xdp_buff *)ctx;
+	struct net *net = dev_net(xdp->rxq->dev);
+	struct xfrm_state *x;
+
+	if (!opts || opts__sz < sizeof(opts->error))
+		return NULL;
+
+	if (opts__sz != BPF_XFRM_STATE_OPTS_SZ) {
+		opts->error = -EINVAL;
+		return NULL;
+	}
+
+	if (unlikely(opts->netns_id < BPF_F_CURRENT_NETNS)) {
+		opts->error = -EINVAL;
+		return NULL;
+	}
+
+	if (opts->netns_id >= 0) {
+		net = get_net_ns_by_id(net, opts->netns_id);
+		if (unlikely(!net)) {
+			opts->error = -ENONET;
+			return NULL;
+		}
+	}
+
+	x = xfrm_state_lookup(net, opts->mark, &opts->daddr, opts->spi,
+			      opts->proto, opts->family);
+
+	if (opts->netns_id >= 0)
+		put_net(net);
+	if (!x)
+		opts->error = -ENOENT;
+
+	return x;
+}
+
+/* bpf_xdp_xfrm_state_release - Release acquired xfrm_state object
+ *
+ * This must be invoked for referenced PTR_TO_BTF_ID, and the verifier rejects
+ * the program if any references remain in the program in all of the explored
+ * states.
+ *
+ * Parameters:
+ * @x		- Pointer to referenced xfrm_state object, obtained using
+ *		  bpf_xdp_get_xfrm_state.
+ */
+__bpf_kfunc void bpf_xdp_xfrm_state_release(struct xfrm_state *x)
+{
+	xfrm_state_put(x);
+}
+
+__bpf_kfunc_end_defs();
+
+BTF_SET8_START(xfrm_state_kfunc_set)
+BTF_ID_FLAGS(func, bpf_xdp_get_xfrm_state, KF_RET_NULL | KF_ACQUIRE)
+BTF_ID_FLAGS(func, bpf_xdp_xfrm_state_release, KF_RELEASE)
+BTF_SET8_END(xfrm_state_kfunc_set)
+
+static const struct btf_kfunc_id_set xfrm_state_xdp_kfunc_set = {
+	.owner = THIS_MODULE,
+	.set   = &xfrm_state_kfunc_set,
+};
+
+int __init register_xfrm_state_bpf(void)
+{
+	return register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP,
+					 &xfrm_state_xdp_kfunc_set);
+}
-- 
cgit v1.2.3