Re: [PATCH bpf RFC-V3 1/5] xdp: rss hash types representation
From: Stanislav Fomichev
Date: Thu Mar 30 2023 - 14:35:45 EST
On 03/30, Jesper Dangaard Brouer wrote:
The RSS hash type specifies what portion of packet data NIC hardware used
when calculating RSS hash value. The RSS types are focused on Internet
traffic protocols at OSI layers L3 and L4. L2 (e.g. ARP) often get hash
value zero and no RSS type. For L3 focused on IPv4 vs. IPv6, and L4
primarily TCP vs UDP, but some hardware supports SCTP.
Hardware RSS types are differently encoded for each hardware NIC. Most
hardware represent RSS hash type as a number. Determining L3 vs L4 often
requires a mapping table as there often isn't a pattern or sorting
according to ISO layer.
The patch introduce a XDP RSS hash type (enum xdp_rss_hash_type) that
contain combinations to be used by drivers, which gets build up with bits
from enum xdp_rss_type_bits. Both enum xdp_rss_type_bits and
xdp_rss_hash_type get exposed to BPF via BTF, and it is up to the
BPF-programmer to match using these defines.
This proposal change the kfunc API bpf_xdp_metadata_rx_hash() adding
a pointer value argument for provide the RSS hash type.
Signed-off-by: Jesper Dangaard Brouer <brouer@xxxxxxxxxx>
---
include/linux/netdevice.h | 3 ++-
include/net/xdp.h | 46
+++++++++++++++++++++++++++++++++++++++++++++
net/core/xdp.c | 10 +++++++++-
3 files changed, 57 insertions(+), 2 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 470085b121d3..c35f04f636f1 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1624,7 +1624,8 @@ struct net_device_ops {
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);
+ int (*xmo_rx_hash)(const struct xdp_md *ctx, u32 *hash,
+ enum xdp_rss_hash_type *rss_type);
};
/**
diff --git a/include/net/xdp.h b/include/net/xdp.h
index 41c57b8b1671..130091a55a6f 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -8,6 +8,7 @@
#include <linux/skbuff.h> /* skb_shared_info */
#include <uapi/linux/netdev.h>
+#include <linux/bitfield.h>
/**
* DOC: XDP RX-queue information
@@ -425,6 +426,51 @@ XDP_METADATA_KFUNC_xxx
MAX_XDP_METADATA_KFUNC,
};
+enum xdp_rss_type_bits {
+ XDP_RSS_L3_IPV4 = BIT(0),
+ XDP_RSS_L3_IPV6 = BIT(1),
+
+ /* The fixed (L3) IPv4 and IPv6 headers can both be followed by
+ * variable/dynamic headers, IPv4 called Options and IPv6 called
+ * Extension Headers. HW RSS type can contain this info.
+ */
+ XDP_RSS_L3_DYNHDR = BIT(2),
+
+ /* When RSS hash covers L4 then drivers MUST set XDP_RSS_L4 bit in
+ * addition to the protocol specific bit. This ease interaction with
+ * SKBs and avoids reserving a fixed mask for future L4 protocol bits.
+ */
+ XDP_RSS_L4 = BIT(3), /* L4 based hash, proto can be unknown */
+ XDP_RSS_L4_TCP = BIT(4),
+ XDP_RSS_L4_UDP = BIT(5),
+ XDP_RSS_L4_SCTP = BIT(6),
+ XDP_RSS_L4_IPSEC = BIT(7), /* L4 based hash include IPSEC SPI */
+};
+
+/* RSS hash type combinations used for driver HW mapping */
+enum xdp_rss_hash_type {
+ XDP_RSS_TYPE_NONE = 0,
+ XDP_RSS_TYPE_L2 = XDP_RSS_TYPE_NONE,
+
+ XDP_RSS_TYPE_L3_IPV4 = XDP_RSS_L3_IPV4,
+ XDP_RSS_TYPE_L3_IPV6 = XDP_RSS_L3_IPV6,
+ XDP_RSS_TYPE_L3_IPV4_OPT = XDP_RSS_L3_IPV4 | XDP_RSS_L3_DYNHDR,
+ XDP_RSS_TYPE_L3_IPV6_EX = XDP_RSS_L3_IPV6 | XDP_RSS_L3_DYNHDR,
+
+ XDP_RSS_TYPE_L4_ANY = XDP_RSS_L4,
+ XDP_RSS_TYPE_L4_IPV4_TCP = XDP_RSS_L3_IPV4 | XDP_RSS_L4 |
XDP_RSS_L4_TCP,
+ 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_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_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,
+ XDP_RSS_TYPE_L4_IPV6_SCTP_EX = XDP_RSS_TYPE_L4_IPV6_SCTP|
XDP_RSS_L3_DYNHDR,
+};
+
#ifdef CONFIG_NET
u32 bpf_xdp_metadata_kfunc_id(int id);
bool bpf_dev_bound_kfunc_id(u32 btf_id);
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 528d4b37983d..38d2dee16b47 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -734,14 +734,22 @@ __bpf_kfunc int bpf_xdp_metadata_rx_timestamp(const
struct xdp_md *ctx, u64 *tim
* bpf_xdp_metadata_rx_hash - Read XDP frame RX hash.
* @ctx: XDP context pointer.
* @hash: Return value pointer.
+ * @rss_type: Return value pointer for RSS type.
+ *
+ * The RSS hash type (@rss_type) specifies what portion of packet
headers NIC
+ * hardware were used when calculating RSS hash value. The type
combinations
+ * are defined via &enum xdp_rss_hash_type and individual bits can be
decoded
+ * via &enum xdp_rss_type_bits.
*
* Return:
* * Returns 0 on success or ``-errno`` on error.
* * ``-EOPNOTSUPP`` : means device driver doesn't implement kfunc
* * ``-ENODATA`` : means no RX-hash available for this frame
*/
-__bpf_kfunc int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32
*hash)
+__bpf_kfunc int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32
*hash,
+ enum xdp_rss_hash_type *rss_type)
{
[..]
+ BTF_TYPE_EMIT(enum xdp_rss_type_bits);
nit: Do we still need this with an extra argument?
return -EOPNOTSUPP;
}