2023-04-02 08:31:36

by Jesper Dangaard Brouer

[permalink] [raw]
Subject: [PATCH bpf V6 0/5] XDP-hints: API change for RX-hash kfunc bpf_xdp_metadata_rx_hash

Current API for bpf_xdp_metadata_rx_hash() returns the raw RSS hash value,
but doesn't provide information on the RSS hash type (part of 6.3-rc).

This patchset proposal is to change the function call signature via adding
a pointer value argument for providing the RSS hash type.

---
V6:
- Resend: selftest failure is unrelated (in xdp_do_redirect)
Issue in fccca038f300 ("veth: take into account device reconfiguration for xdp_features flag")
V5:
- Fixes for checkpatch.pl
- Change function signature for all xmo_rx_hash calls

Jesper Dangaard Brouer (5):
xdp: rss hash types representation
mlx5: bpf_xdp_metadata_rx_hash add xdp rss hash type
veth: bpf_xdp_metadata_rx_hash add xdp rss hash type
mlx4: bpf_xdp_metadata_rx_hash add xdp rss hash type
selftests/bpf: Adjust bpf_xdp_metadata_rx_hash for new arg


drivers/net/ethernet/mellanox/mlx4/en_rx.c | 22 ++++++-
drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 3 +-
.../net/ethernet/mellanox/mlx5/core/en/xdp.c | 63 ++++++++++++++++++-
drivers/net/veth.c | 10 ++-
include/linux/mlx5/device.h | 14 ++++-
include/linux/netdevice.h | 3 +-
include/net/xdp.h | 47 ++++++++++++++
net/core/xdp.c | 10 ++-
.../selftests/bpf/prog_tests/xdp_metadata.c | 2 +
.../selftests/bpf/progs/xdp_hw_metadata.c | 14 +++--
.../selftests/bpf/progs/xdp_metadata.c | 6 +-
.../selftests/bpf/progs/xdp_metadata2.c | 7 ++-
tools/testing/selftests/bpf/xdp_hw_metadata.c | 2 +-
tools/testing/selftests/bpf/xdp_metadata.h | 1 +
14 files changed, 180 insertions(+), 24 deletions(-)

--


2023-04-02 08:31:49

by Jesper Dangaard Brouer

[permalink] [raw]
Subject: [PATCH bpf V6 2/5] mlx5: bpf_xdp_metadata_rx_hash add xdp rss hash type

Update API for bpf_xdp_metadata_rx_hash() with arg for xdp rss hash type
via mapping table.

The mlx5 hardware can also identify and RSS hash IPSEC. This indicate
hash includes SPI (Security Parameters Index) as part of IPSEC hash.

Extend xdp core enum xdp_rss_hash_type with IPSEC hash type.

Fixes: bc8d405b1ba9 ("net/mlx5e: Support RX XDP metadata")
Signed-off-by: Jesper Dangaard Brouer <[email protected]>
Acked-by: Toke Høiland-Jørgensen <[email protected]>
Acked-by: Stanislav Fomichev <[email protected]>
---
drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c | 60 ++++++++++++++++++++++
include/linux/mlx5/device.h | 14 ++++-
include/net/xdp.h | 2 +
3 files changed, 73 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index efe609f8e3aa..97ef1df94d50 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -34,6 +34,7 @@
#include <net/xdp_sock_drv.h>
#include "en/xdp.h"
#include "en/params.h"
+#include <linux/bitfield.h>

int mlx5e_xdp_max_mtu(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk)
{
@@ -169,15 +170,72 @@ static int mlx5e_xdp_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp)
return 0;
}

+/* Mapping HW RSS Type bits CQE_RSS_HTYPE_IP + CQE_RSS_HTYPE_L4 into 4-bits*/
+#define RSS_TYPE_MAX_TABLE 16 /* 4-bits max 16 entries */
+#define RSS_L4 GENMASK(1, 0)
+#define RSS_L3 GENMASK(3, 2) /* Same as CQE_RSS_HTYPE_IP */
+
+/* Valid combinations of CQE_RSS_HTYPE_IP + CQE_RSS_HTYPE_L4 sorted numerical */
+enum mlx5_rss_hash_type {
+ RSS_TYPE_NO_HASH = (FIELD_PREP_CONST(RSS_L3, CQE_RSS_IP_NONE) |
+ FIELD_PREP_CONST(RSS_L4, CQE_RSS_L4_NONE)),
+ RSS_TYPE_L3_IPV4 = (FIELD_PREP_CONST(RSS_L3, CQE_RSS_IPV4) |
+ FIELD_PREP_CONST(RSS_L4, CQE_RSS_L4_NONE)),
+ RSS_TYPE_L4_IPV4_TCP = (FIELD_PREP_CONST(RSS_L3, CQE_RSS_IPV4) |
+ FIELD_PREP_CONST(RSS_L4, CQE_RSS_L4_TCP)),
+ RSS_TYPE_L4_IPV4_UDP = (FIELD_PREP_CONST(RSS_L3, CQE_RSS_IPV4) |
+ FIELD_PREP_CONST(RSS_L4, CQE_RSS_L4_UDP)),
+ RSS_TYPE_L4_IPV4_IPSEC = (FIELD_PREP_CONST(RSS_L3, CQE_RSS_IPV4) |
+ FIELD_PREP_CONST(RSS_L4, CQE_RSS_L4_IPSEC)),
+ RSS_TYPE_L3_IPV6 = (FIELD_PREP_CONST(RSS_L3, CQE_RSS_IPV6) |
+ FIELD_PREP_CONST(RSS_L4, CQE_RSS_L4_NONE)),
+ RSS_TYPE_L4_IPV6_TCP = (FIELD_PREP_CONST(RSS_L3, CQE_RSS_IPV6) |
+ FIELD_PREP_CONST(RSS_L4, CQE_RSS_L4_TCP)),
+ RSS_TYPE_L4_IPV6_UDP = (FIELD_PREP_CONST(RSS_L3, CQE_RSS_IPV6) |
+ FIELD_PREP_CONST(RSS_L4, CQE_RSS_L4_UDP)),
+ RSS_TYPE_L4_IPV6_IPSEC = (FIELD_PREP_CONST(RSS_L3, CQE_RSS_IPV6) |
+ FIELD_PREP_CONST(RSS_L4, CQE_RSS_L4_IPSEC)),
+} mlx5_rss_hash_type;
+
+/* Invalid combinations will simply return zero, allows no boundary checks */
+static const enum xdp_rss_hash_type mlx5_xdp_rss_type[RSS_TYPE_MAX_TABLE] = {
+ [RSS_TYPE_NO_HASH] = XDP_RSS_TYPE_NONE,
+ [1] = XDP_RSS_TYPE_NONE, /* Implicit zero */
+ [2] = XDP_RSS_TYPE_NONE, /* Implicit zero */
+ [3] = XDP_RSS_TYPE_NONE, /* Implicit zero */
+ [RSS_TYPE_L3_IPV4] = XDP_RSS_TYPE_L3_IPV4,
+ [RSS_TYPE_L4_IPV4_TCP] = XDP_RSS_TYPE_L4_IPV4_TCP,
+ [RSS_TYPE_L4_IPV4_UDP] = XDP_RSS_TYPE_L4_IPV4_UDP,
+ [RSS_TYPE_L4_IPV4_IPSEC] = XDP_RSS_TYPE_L4_IPV4_IPSEC,
+ [RSS_TYPE_L3_IPV6] = XDP_RSS_TYPE_L3_IPV6,
+ [RSS_TYPE_L4_IPV6_TCP] = XDP_RSS_TYPE_L4_IPV6_TCP,
+ [RSS_TYPE_L4_IPV6_UDP] = XDP_RSS_TYPE_L4_IPV6_UDP,
+ [RSS_TYPE_L4_IPV6_IPSEC] = XDP_RSS_TYPE_L4_IPV6_IPSEC,
+ [12] = XDP_RSS_TYPE_NONE, /* Implicit zero */
+ [13] = XDP_RSS_TYPE_NONE, /* Implicit zero */
+ [14] = XDP_RSS_TYPE_NONE, /* Implicit zero */
+ [15] = XDP_RSS_TYPE_NONE, /* Implicit zero */
+};
+
static int mlx5e_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash,
enum xdp_rss_hash_type *rss_type)
{
const struct mlx5e_xdp_buff *_ctx = (void *)ctx;
+ const struct mlx5_cqe64 *cqe = _ctx->cqe;
+ u32 hash_type, l4_type, ip_type, lookup;

if (unlikely(!(_ctx->xdp.rxq->dev->features & NETIF_F_RXHASH)))
return -ENODATA;

- *hash = be32_to_cpu(_ctx->cqe->rss_hash_result);
+ *hash = be32_to_cpu(cqe->rss_hash_result);
+
+ hash_type = cqe->rss_hash_type;
+ BUILD_BUG_ON(CQE_RSS_HTYPE_IP != RSS_L3); /* same mask */
+ ip_type = hash_type & CQE_RSS_HTYPE_IP;
+ l4_type = FIELD_GET(CQE_RSS_HTYPE_L4, hash_type);
+ lookup = ip_type | l4_type;
+ *rss_type = mlx5_xdp_rss_type[lookup];
+
return 0;
}

diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 71b06ebad402..1db19a9d26e3 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -36,6 +36,7 @@
#include <linux/types.h>
#include <rdma/ib_verbs.h>
#include <linux/mlx5/mlx5_ifc.h>
+#include <linux/bitfield.h>

#if defined(__LITTLE_ENDIAN)
#define MLX5_SET_HOST_ENDIANNESS 0
@@ -980,14 +981,23 @@ enum {
};

enum {
- CQE_RSS_HTYPE_IP = 0x3 << 2,
+ CQE_RSS_HTYPE_IP = GENMASK(3, 2),
/* cqe->rss_hash_type[3:2] - IP destination selected for hash
* (00 = none, 01 = IPv4, 10 = IPv6, 11 = Reserved)
*/
- CQE_RSS_HTYPE_L4 = 0x3 << 6,
+ CQE_RSS_IP_NONE = 0x0,
+ CQE_RSS_IPV4 = 0x1,
+ CQE_RSS_IPV6 = 0x2,
+ CQE_RSS_RESERVED = 0x3,
+
+ CQE_RSS_HTYPE_L4 = GENMASK(7, 6),
/* cqe->rss_hash_type[7:6] - L4 destination selected for hash
* (00 = none, 01 = TCP. 10 = UDP, 11 = IPSEC.SPI
*/
+ CQE_RSS_L4_NONE = 0x0,
+ CQE_RSS_L4_TCP = 0x1,
+ CQE_RSS_L4_UDP = 0x2,
+ CQE_RSS_L4_IPSEC = 0x3,
};

enum {
diff --git a/include/net/xdp.h b/include/net/xdp.h
index a76c4ea203ea..76aa748e7923 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -460,10 +460,12 @@ enum xdp_rss_hash_type {
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_IPV4_IPSEC = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_IPSEC,

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_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,


2023-04-02 08:32:37

by Jesper Dangaard Brouer

[permalink] [raw]
Subject: [PATCH bpf V6 4/5] mlx4: bpf_xdp_metadata_rx_hash add xdp rss hash type

Update API for bpf_xdp_metadata_rx_hash() with arg for xdp rss hash type
via matching indiviual Completion Queue Entry (CQE) status bits.

Fixes: ab46182d0dcb ("net/mlx4_en: Support RX XDP metadata")
Signed-off-by: Jesper Dangaard Brouer <[email protected]>
Acked-by: Toke Høiland-Jørgensen <[email protected]>
Acked-by: Stanislav Fomichev <[email protected]>
---
drivers/net/ethernet/mellanox/mlx4/en_rx.c | 19 ++++++++++++++++++-
drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 3 ++-
2 files changed, 20 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 73d10aa4c503..332472fe4990 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -685,11 +685,28 @@ int mlx4_en_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash,
enum xdp_rss_hash_type *rss_type)
{
struct mlx4_en_xdp_buff *_ctx = (void *)ctx;
+ struct mlx4_cqe *cqe = _ctx->cqe;
+ enum xdp_rss_hash_type xht = 0;
+ __be16 status;

if (unlikely(!(_ctx->dev->features & NETIF_F_RXHASH)))
return -ENODATA;

- *hash = be32_to_cpu(_ctx->cqe->immed_rss_invalid);
+ *hash = be32_to_cpu(cqe->immed_rss_invalid);
+ status = cqe->status;
+ if (status & cpu_to_be16(MLX4_CQE_STATUS_TCP))
+ xht = XDP_RSS_L4_TCP;
+ if (status & cpu_to_be16(MLX4_CQE_STATUS_UDP))
+ xht = XDP_RSS_L4_UDP;
+ if (status & cpu_to_be16(MLX4_CQE_STATUS_IPV4 | MLX4_CQE_STATUS_IPV4F))
+ xht |= XDP_RSS_L3_IPV4;
+ if (status & cpu_to_be16(MLX4_CQE_STATUS_IPV6)) {
+ xht |= XDP_RSS_L3_IPV6;
+ if (cqe->ipv6_ext_mask)
+ xht |= XDP_RSS_L3_DYNHDR;
+ }
+ *rss_type = xht;
+
return 0;
}

diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 544e09b97483..4ac4d883047b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -798,7 +798,8 @@ int mlx4_en_netdev_event(struct notifier_block *this,

struct xdp_md;
int mlx4_en_xdp_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp);
-int mlx4_en_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash);
+int mlx4_en_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash,
+ enum xdp_rss_hash_type *rss_type);

/*
* Functions for time stamping


2023-04-02 08:32:37

by Jesper Dangaard Brouer

[permalink] [raw]
Subject: [PATCH bpf V6 3/5] veth: bpf_xdp_metadata_rx_hash add xdp rss hash type

Update API for bpf_xdp_metadata_rx_hash() with arg for xdp rss hash type.

The veth driver currently only support XDP-hints based on SKB code path.
The SKB have lost information about the RSS hash type, by compressing
the information down to a single bitfield skb->l4_hash, that only knows
if this was a L4 hash value.

In preparation for veth, the xdp_rss_hash_type have an L4 indication
bit that allow us to return a meaningful L4 indication when working
with SKB based packets.

Fixes: 306531f0249f ("veth: Support RX XDP metadata")
Signed-off-by: Jesper Dangaard Brouer <[email protected]>
Acked-by: Toke Høiland-Jørgensen <[email protected]>
Acked-by: Stanislav Fomichev <[email protected]>
---
drivers/net/veth.c | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 424e8876a16b..e1b38fbf1dd9 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -1652,11 +1652,14 @@ static int veth_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash,
enum xdp_rss_hash_type *rss_type)
{
struct veth_xdp_buff *_ctx = (void *)ctx;
+ struct sk_buff *skb = _ctx->skb;

- if (!_ctx->skb)
+ if (!skb)
return -ENODATA;

- *hash = skb_get_hash(_ctx->skb);
+ *hash = skb_get_hash(skb);
+ *rss_type = skb->l4_hash ? XDP_RSS_TYPE_L4_ANY : XDP_RSS_TYPE_NONE;
+
return 0;
}



2023-04-02 08:32:41

by Jesper Dangaard Brouer

[permalink] [raw]
Subject: [PATCH bpf V6 1/5] xdp: rss hash types representation

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.

Change function signature for all xmo_rx_hash calls in drivers to make it
compile. The RSS type implementations for each driver comes as separate
patches.

Fixes: 3d76a4d3d4e5 ("bpf: XDP metadata RX kfuncs")
Signed-off-by: Jesper Dangaard Brouer <[email protected]>
Acked-by: Toke Høiland-Jørgensen <[email protected]>
Acked-by: Stanislav Fomichev <[email protected]>
---
drivers/net/ethernet/mellanox/mlx4/en_rx.c | 3 +
drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c | 3 +
drivers/net/veth.c | 3 +
include/linux/netdevice.h | 3 +
include/net/xdp.h | 45 ++++++++++++++++++++++
net/core/xdp.c | 10 ++++-
6 files changed, 62 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 4b5e459b6d49..73d10aa4c503 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -681,7 +681,8 @@ int mlx4_en_xdp_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp)
return 0;
}

-int mlx4_en_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash)
+int mlx4_en_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash,
+ enum xdp_rss_hash_type *rss_type)
{
struct mlx4_en_xdp_buff *_ctx = (void *)ctx;

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index c5dae48b7932..efe609f8e3aa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -169,7 +169,8 @@ static int mlx5e_xdp_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp)
return 0;
}

-static int mlx5e_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash)
+static int mlx5e_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash,
+ enum xdp_rss_hash_type *rss_type)
{
const struct mlx5e_xdp_buff *_ctx = (void *)ctx;

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index c1178915496d..424e8876a16b 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -1648,7 +1648,8 @@ static int veth_xdp_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp)
return 0;
}

-static int veth_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash)
+static int veth_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash,
+ enum xdp_rss_hash_type *rss_type)
{
struct veth_xdp_buff *_ctx = (void *)ctx;

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..a76c4ea203ea 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 +426,50 @@ XDP_METADATA_KFUNC_xxx
MAX_XDP_METADATA_KFUNC,
};

+enum xdp_rss_hash_type {
+ /* First part: Individual bits for L3/L4 types */
+ 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 */
+
+ /* Second part: RSS hash type combinations used for driver HW mapping */
+ 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..fb85aca81961 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -734,13 +734,21 @@ __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 used when calculating RSS hash value. The RSS type can be decoded
+ * via &enum xdp_rss_hash_type either matching on individual L3/L4 bits
+ * ``XDP_RSS_L*`` or by combined traditional *RSS Hashing Types*
+ * ``XDP_RSS_TYPE_L*``.
*
* 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)
{
return -EOPNOTSUPP;
}


2023-04-02 09:13:36

by Jesper Dangaard Brouer

[permalink] [raw]
Subject: [PATCH bpf V6 5/5] selftests/bpf: Adjust bpf_xdp_metadata_rx_hash for new arg

Update BPF selftests to use the new RSS type argument for kfunc
bpf_xdp_metadata_rx_hash.

Signed-off-by: Jesper Dangaard Brouer <[email protected]>
Acked-by: Toke Høiland-Jørgensen <[email protected]>
Acked-by: Stanislav Fomichev <[email protected]>
---
.../selftests/bpf/prog_tests/xdp_metadata.c | 2 ++
.../testing/selftests/bpf/progs/xdp_hw_metadata.c | 14 +++++++++-----
tools/testing/selftests/bpf/progs/xdp_metadata.c | 6 +++---
tools/testing/selftests/bpf/progs/xdp_metadata2.c | 7 ++++---
tools/testing/selftests/bpf/xdp_hw_metadata.c | 2 +-
tools/testing/selftests/bpf/xdp_metadata.h | 1 +
6 files changed, 20 insertions(+), 12 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
index aa4beae99f4f..8c5e98da9ae9 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
@@ -273,6 +273,8 @@ static int verify_xsk_metadata(struct xsk *xsk)
if (!ASSERT_NEQ(meta->rx_hash, 0, "rx_hash"))
return -1;

+ ASSERT_EQ(meta->rx_hash_type, 0, "rx_hash_type");
+
xsk_ring_cons__release(&xsk->rx, 1);
refill_rx(xsk, comp_addr);

diff --git a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c
index 4c55b4d79d3d..7b3fc12e96d6 100644
--- a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c
+++ b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c
@@ -14,8 +14,8 @@ struct {

extern int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx,
__u64 *timestamp) __ksym;
-extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx,
- __u32 *hash) __ksym;
+extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, __u32 *hash,
+ enum xdp_rss_hash_type *rss_type) __ksym;

SEC("xdp")
int rx(struct xdp_md *ctx)
@@ -74,10 +74,14 @@ int rx(struct xdp_md *ctx)
else
meta->rx_timestamp = 0; /* Used by AF_XDP as not avail signal */

- if (!bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash))
- bpf_printk("populated rx_hash with %u", meta->rx_hash);
- else
+ if (!bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash, &meta->rx_hash_type)) {
+ bpf_printk("populated rx_hash:0x%X type:0x%X",
+ meta->rx_hash, meta->rx_hash_type);
+ if (!(meta->rx_hash_type & XDP_RSS_L4))
+ bpf_printk("rx_hash low quality L3 hash type");
+ } else {
meta->rx_hash = 0; /* Used by AF_XDP as not avail signal */
+ }

return bpf_redirect_map(&xsk, ctx->rx_queue_index, XDP_PASS);
}
diff --git a/tools/testing/selftests/bpf/progs/xdp_metadata.c b/tools/testing/selftests/bpf/progs/xdp_metadata.c
index 77678b034389..d151d406a123 100644
--- a/tools/testing/selftests/bpf/progs/xdp_metadata.c
+++ b/tools/testing/selftests/bpf/progs/xdp_metadata.c
@@ -21,8 +21,8 @@ struct {

extern int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx,
__u64 *timestamp) __ksym;
-extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx,
- __u32 *hash) __ksym;
+extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, __u32 *hash,
+ enum xdp_rss_hash_type *rss_type) __ksym;

SEC("xdp")
int rx(struct xdp_md *ctx)
@@ -56,7 +56,7 @@ int rx(struct xdp_md *ctx)
if (timestamp == 0)
meta->rx_timestamp = 1;

- bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash);
+ bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash, &meta->rx_hash_type);

return bpf_redirect_map(&xsk, ctx->rx_queue_index, XDP_PASS);
}
diff --git a/tools/testing/selftests/bpf/progs/xdp_metadata2.c b/tools/testing/selftests/bpf/progs/xdp_metadata2.c
index cf69d05451c3..85f88d9d7a78 100644
--- a/tools/testing/selftests/bpf/progs/xdp_metadata2.c
+++ b/tools/testing/selftests/bpf/progs/xdp_metadata2.c
@@ -5,17 +5,18 @@
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_endian.h>

-extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx,
- __u32 *hash) __ksym;
+extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, __u32 *hash,
+ enum xdp_rss_hash_type *rss_type) __ksym;

int called;

SEC("freplace/rx")
int freplace_rx(struct xdp_md *ctx)
{
+ enum xdp_rss_hash_type type = 0;
u32 hash = 0;
/* Call _any_ metadata function to make sure we don't crash. */
- bpf_xdp_metadata_rx_hash(ctx, &hash);
+ bpf_xdp_metadata_rx_hash(ctx, &hash, &type);
called++;
return XDP_PASS;
}
diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c
index 1c8acb68b977..4ca29e0c9646 100644
--- a/tools/testing/selftests/bpf/xdp_hw_metadata.c
+++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c
@@ -141,7 +141,7 @@ static void verify_xdp_metadata(void *data)
meta = data - sizeof(*meta);

printf("rx_timestamp: %llu\n", meta->rx_timestamp);
- printf("rx_hash: %u\n", meta->rx_hash);
+ printf("rx_hash: 0x%X RSS type:0x%X\n", meta->rx_hash, meta->rx_hash_type);
}

static void verify_skb_metadata(int fd)
diff --git a/tools/testing/selftests/bpf/xdp_metadata.h b/tools/testing/selftests/bpf/xdp_metadata.h
index f6780fbb0a21..899da872fee1 100644
--- a/tools/testing/selftests/bpf/xdp_metadata.h
+++ b/tools/testing/selftests/bpf/xdp_metadata.h
@@ -12,4 +12,5 @@
struct xdp_meta {
__u64 rx_timestamp;
__u32 rx_hash;
+ __u32 rx_hash_type;
};


2023-04-02 16:03:37

by Alexei Starovoitov

[permalink] [raw]
Subject: Re: [PATCH bpf V6 5/5] selftests/bpf: Adjust bpf_xdp_metadata_rx_hash for new arg

On Sun, Apr 2, 2023 at 1:30 AM Jesper Dangaard Brouer <[email protected]> wrote:
>
> Update BPF selftests to use the new RSS type argument for kfunc
> bpf_xdp_metadata_rx_hash.
>
> Signed-off-by: Jesper Dangaard Brouer <[email protected]>
> Acked-by: Toke Høiland-Jørgensen <[email protected]>
> Acked-by: Stanislav Fomichev <[email protected]>
> ---
> .../selftests/bpf/prog_tests/xdp_metadata.c | 2 ++
> .../testing/selftests/bpf/progs/xdp_hw_metadata.c | 14 +++++++++-----
> tools/testing/selftests/bpf/progs/xdp_metadata.c | 6 +++---
> tools/testing/selftests/bpf/progs/xdp_metadata2.c | 7 ++++---
> tools/testing/selftests/bpf/xdp_hw_metadata.c | 2 +-
> tools/testing/selftests/bpf/xdp_metadata.h | 1 +
> 6 files changed, 20 insertions(+), 12 deletions(-)
>
> diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
> index aa4beae99f4f..8c5e98da9ae9 100644
> --- a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
> +++ b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
> @@ -273,6 +273,8 @@ static int verify_xsk_metadata(struct xsk *xsk)
> if (!ASSERT_NEQ(meta->rx_hash, 0, "rx_hash"))
> return -1;
>
> + ASSERT_EQ(meta->rx_hash_type, 0, "rx_hash_type");
> +
> xsk_ring_cons__release(&xsk->rx, 1);
> refill_rx(xsk, comp_addr);
>
> diff --git a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c
> index 4c55b4d79d3d..7b3fc12e96d6 100644
> --- a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c
> +++ b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c
> @@ -14,8 +14,8 @@ struct {
>
> extern int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx,
> __u64 *timestamp) __ksym;
> -extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx,
> - __u32 *hash) __ksym;
> +extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, __u32 *hash,
> + enum xdp_rss_hash_type *rss_type) __ksym;
>
> SEC("xdp")
> int rx(struct xdp_md *ctx)
> @@ -74,10 +74,14 @@ int rx(struct xdp_md *ctx)
> else
> meta->rx_timestamp = 0; /* Used by AF_XDP as not avail signal */
>
> - if (!bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash))
> - bpf_printk("populated rx_hash with %u", meta->rx_hash);
> - else
> + if (!bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash, &meta->rx_hash_type)) {
> + bpf_printk("populated rx_hash:0x%X type:0x%X",
> + meta->rx_hash, meta->rx_hash_type);
> + if (!(meta->rx_hash_type & XDP_RSS_L4))
> + bpf_printk("rx_hash low quality L3 hash type");
> + } else {
> meta->rx_hash = 0; /* Used by AF_XDP as not avail signal */
> + }

Didn't we agree in the previous thread to remove these printks and
replace them with actual stats that user space can see?

2023-04-03 23:22:33

by Alexei Starovoitov

[permalink] [raw]
Subject: Re: [PATCH bpf V6 5/5] selftests/bpf: Adjust bpf_xdp_metadata_rx_hash for new arg

On Mon, Apr 3, 2023 at 8:08 AM Jesper Brouer <[email protected]> wrote:
>
>
>
> søn. 2. apr. 2023 17.50 skrev Alexei Starovoitov <[email protected]>:
>>
>> On Sun, Apr 2, 2023 at 1:30 AM Jesper Dangaard Brouer <[email protected]> wrote:
>> >
>> > Update BPF selftests to use the new RSS type argument for kfunc
>> > bpf_xdp_metadata_rx_hash.
>> >
>> > Signed-off-by: Jesper Dangaard Brouer <[email protected]>
>> > Acked-by: Toke Høiland-Jørgensen <[email protected]>
>> > Acked-by: Stanislav Fomichev <[email protected]>
>> > ---
>> > .../selftests/bpf/prog_tests/xdp_metadata.c | 2 ++
>> > .../testing/selftests/bpf/progs/xdp_hw_metadata.c | 14 +++++++++-----
>> > tools/testing/selftests/bpf/progs/xdp_metadata.c | 6 +++---
>> > tools/testing/selftests/bpf/progs/xdp_metadata2.c | 7 ++++---
>> > tools/testing/selftests/bpf/xdp_hw_metadata.c | 2 +-
>> > tools/testing/selftests/bpf/xdp_metadata.h | 1 +
>> > 6 files changed, 20 insertions(+), 12 deletions(-)
>> >
>> > diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
>> > index aa4beae99f4f..8c5e98da9ae9 100644
>> > --- a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
>> > +++ b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
>> > @@ -273,6 +273,8 @@ static int verify_xsk_metadata(struct xsk *xsk)
>> > if (!ASSERT_NEQ(meta->rx_hash, 0, "rx_hash"))
>> > return -1;
>> >
>> > + ASSERT_EQ(meta->rx_hash_type, 0, "rx_hash_type");
>> > +
>> > xsk_ring_cons__release(&xsk->rx, 1);
>> > refill_rx(xsk, comp_addr);
>> >
>> > diff --git a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c
>> > index 4c55b4d79d3d..7b3fc12e96d6 100644
>> > --- a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c
>> > +++ b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c
>> > @@ -14,8 +14,8 @@ struct {
>> >
>> > extern int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx,
>> > __u64 *timestamp) __ksym;
>> > -extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx,
>> > - __u32 *hash) __ksym;
>> > +extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, __u32 *hash,
>> > + enum xdp_rss_hash_type *rss_type) __ksym;
>> >
>> > SEC("xdp")
>> > int rx(struct xdp_md *ctx)
>> > @@ -74,10 +74,14 @@ int rx(struct xdp_md *ctx)
>> > else
>> > meta->rx_timestamp = 0; /* Used by AF_XDP as not avail signal */
>> >
>> > - if (!bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash))
>> > - bpf_printk("populated rx_hash with %u", meta->rx_hash);
>> > - else
>> > + if (!bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash, &meta->rx_hash_type)) {
>> > + bpf_printk("populated rx_hash:0x%X type:0x%X",
>> > + meta->rx_hash, meta->rx_hash_type);
>> > + if (!(meta->rx_hash_type & XDP_RSS_L4))
>> > + bpf_printk("rx_hash low quality L3 hash type");
>> > + } else {
>> > meta->rx_hash = 0; /* Used by AF_XDP as not avail signal */
>> > + }
>>
>> Didn't we agree in the previous thread to remove these printks and
>> replace them with actual stats that user space can see?
>
>
> This patchset is for bpf-tree RC version of kernel.
> Thus, we keep changes to a minimum.
>
> I/we will do printk work on bpf-next.
> (Once I get home from vacation next week)

Sorry, but I insist on making them in this set.
We did bigger changes in bpf tree, so size is not an issue.
I don't want to remember to ping you every week or so to
remind you to fix this later after bpf gets merged into bpf-next.
Less work for me and less work for you to do it now.