Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf

Daniel Borkmann says:

====================
pull-request: bpf 2023-04-13

We've added 6 non-merge commits during the last 1 day(s) which contain
a total of 14 files changed, 205 insertions(+), 38 deletions(-).

The main changes are:

1) One late straggler fix on the XDP hints side which fixes
   bpf_xdp_metadata_rx_hash kfunc API before the release goes out
   in order to provide information on the RSS hash type,
   from Jesper Dangaard Brouer.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf:
  selftests/bpf: Adjust bpf_xdp_metadata_rx_hash for new arg
  mlx4: bpf_xdp_metadata_rx_hash add xdp rss hash type
  veth: bpf_xdp_metadata_rx_hash add xdp rss hash type
  mlx5: bpf_xdp_metadata_rx_hash add xdp rss hash type
  xdp: rss hash types representation
  selftests/bpf: xdp_hw_metadata remove bpf_printk and add counters
====================

Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>

Author: kuba-moo

drivers/net/ethernet/mellanox/mlx4/en_rx.c

@@ -681,14 +681,32 @@ 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;
+	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;
 }
 

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

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)
 {
@@ -169,14 +170,72 @@ 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)
+/* 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)),
+};
+
+/* 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;
 }
 

drivers/net/veth.c

@@ -1648,14 +1648,18 @@ 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;
+	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;
 }
 

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 {

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);
 };
 
 /**

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 +426,52 @@ 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_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,
+	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);

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;
 }

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);
 

tools/testing/selftests/bpf/progs/xdp_hw_metadata.c

@@ -12,10 +12,14 @@ struct {
 	__type(value, __u32);
 } xsk SEC(".maps");
 
+__u64 pkts_skip = 0;
+__u64 pkts_fail = 0;
+__u64 pkts_redir = 0;
+
 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)
@@ -26,7 +30,7 @@ int rx(struct xdp_md *ctx)
 	struct udphdr *udp = NULL;
 	struct iphdr *iph = NULL;
 	struct xdp_meta *meta;
-	int ret;
+	int err;
 
 	data = (void *)(long)ctx->data;
 	data_end = (void *)(long)ctx->data_end;
@@ -46,17 +50,20 @@ int rx(struct xdp_md *ctx)
 			udp = NULL;
 	}
 
-	if (!udp)
+	if (!udp) {
+		__sync_add_and_fetch(&pkts_skip, 1);
 		return XDP_PASS;
+	}
 
-	if (udp->dest != bpf_htons(9091))
+	/* Forwarding UDP:9091 to AF_XDP */
+	if (udp->dest != bpf_htons(9091)) {
+		__sync_add_and_fetch(&pkts_skip, 1);
 		return XDP_PASS;
+	}
 
-	bpf_printk("forwarding UDP:9091 to AF_XDP");
-
-	ret = bpf_xdp_adjust_meta(ctx, -(int)sizeof(struct xdp_meta));
-	if (ret != 0) {
-		bpf_printk("bpf_xdp_adjust_meta returned %d", ret);
+	err = bpf_xdp_adjust_meta(ctx, -(int)sizeof(struct xdp_meta));
+	if (err) {
+		__sync_add_and_fetch(&pkts_fail, 1);
 		return XDP_PASS;
 	}
 
@@ -65,20 +72,19 @@ int rx(struct xdp_md *ctx)
 	meta = data_meta;
 
 	if (meta + 1 > data) {
-		bpf_printk("bpf_xdp_adjust_meta doesn't appear to work");
+		__sync_add_and_fetch(&pkts_fail, 1);
 		return XDP_PASS;
 	}
 
-	if (!bpf_xdp_metadata_rx_timestamp(ctx, &meta->rx_timestamp))
-		bpf_printk("populated rx_timestamp with %llu", meta->rx_timestamp);
-	else
+	err = bpf_xdp_metadata_rx_timestamp(ctx, &meta->rx_timestamp);
+	if (err)
 		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
-		meta->rx_hash = 0; /* Used by AF_XDP as not avail signal */
+	err = bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash, &meta->rx_hash_type);
+	if (err < 0)
+		meta->rx_hash_err = err; /* Used by AF_XDP as no hash signal */
 
+	__sync_add_and_fetch(&pkts_redir, 1);
 	return bpf_redirect_map(&xsk, ctx->rx_queue_index, XDP_PASS);
 }