From 434aaeaa3e1e5d5b503ba4b3e43428c301c6e88a Mon Sep 17 00:00:00 2001 From: Petr Oros Date: Mon, 13 May 2024 13:16:07 +0200 Subject: [PATCH 1/8] xsk: add functions to fill control buffer JIRA: https://issues.redhat.com/browse/RHEL-31890 Upstream commit(s): commit b4e352ff1169ebce930c734630f9587b1677d163 Author: Maciej Fijalkowski Date: Tue Dec 5 22:08:36 2023 +0100 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 Signed-off-by: Larysa Zaremba Acked-by: Magnus Karlsson Link: https://lore.kernel.org/r/20231205210847.28460-8-larysa.zaremba@intel.com Signed-off-by: Alexei Starovoitov Signed-off-by: Petr Oros --- 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(+) 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 f05af62cc7b4..f8928ab47003 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 030763615b0e..0ae2a160029e 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; From ed77f2d9286e8760ce3eb12b44ef0034e50249e1 Mon Sep 17 00:00:00 2001 From: Petr Oros Date: Mon, 13 May 2024 13:16:07 +0200 Subject: [PATCH 2/8] xdp: Add VLAN tag hint JIRA: https://issues.redhat.com/browse/RHEL-31890 Conflicts: - adjusted conflict that was resolved upstream by commit 753c8608f3e579 ("Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next") - xmo_rx_vlan_tag is placed in netdevice.h instead of xdp.h due to missing 680ee0456a57 ("net: invert the netdevice.h vs xdp.h dependency") Upstream commit(s): commit e6795330f88b4f643c649a02662d47b779340535 Author: Larysa Zaremba Date: Tue Dec 5 22:08:38 2023 +0100 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 Signed-off-by: Larysa Zaremba Acked-by: Jesper Dangaard Brouer Link: https://lore.kernel.org/r/20231205210847.28460-10-larysa.zaremba@intel.com Signed-off-by: Alexei Starovoitov Signed-off-by: Petr Oros --- Documentation/netlink/specs/netdev.yaml | 4 +++ Documentation/networking/xdp-rx-metadata.rst | 8 ++++- include/linux/netdevice.h | 2 ++ include/net/xdp.h | 4 +++ include/uapi/linux/netdev.h | 9 ++---- net/core/xdp.c | 33 ++++++++++++++++++++ tools/include/uapi/linux/netdev.h | 6 ++-- tools/net/ynl/generated/netdev-user.c | 1 + 8 files changed, 57 insertions(+), 10 deletions(-) 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/linux/netdevice.h b/include/linux/netdevice.h index b9ae56273228..53b76ad9bee8 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1610,6 +1610,8 @@ 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); }; /** diff --git a/include/net/xdp.h b/include/net/xdp.h index 0d509462aff6..42351f22e467 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -406,6 +406,10 @@ 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, diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index e8abd14d8603..966638b08ccf 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -44,13 +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, - - /* private: */ - NETDEV_XDP_RX_METADATA_MASK = 3, + NETDEV_XDP_RX_METADATA_VLAN_TAG = 4, }; /** @@ -63,9 +63,6 @@ enum netdev_xdp_rx_metadata { enum netdev_xsk_flags { NETDEV_XSK_FLAGS_TX_TIMESTAMP = 1, NETDEV_XSK_FLAGS_TX_CHECKSUM = 2, - - /* private: */ - NETDEV_XSK_FLAGS_MASK = 3, }; enum { diff --git a/net/core/xdp.c b/net/core/xdp.c index 0e040b0b62ba..599f33dbb9e2 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -737,6 +737,39 @@ __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 e8abd14d8603..de1b63deab68 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -44,13 +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, - - /* private: */ - NETDEV_XDP_RX_METADATA_MASK = 3, + 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) From 5a34443da188a2bcd0e30f90f6cae2df75d98e72 Mon Sep 17 00:00:00 2001 From: Petr Oros Date: Mon, 13 May 2024 13:16:07 +0200 Subject: [PATCH 3/8] veth: Implement VLAN tag XDP hint JIRA: https://issues.redhat.com/browse/RHEL-31890 Upstream commit(s): commit fca783799f64ac0a4f20228ff6a6d7598db11e64 Author: Larysa Zaremba Date: Tue Dec 5 22:08:41 2023 +0100 veth: Implement VLAN tag XDP hint In order to test VLAN tag hint in hardware-independent selftests, implement newly added hint in veth driver. Acked-by: Stanislav Fomichev Signed-off-by: Larysa Zaremba Link: https://lore.kernel.org/r/20231205210847.28460-13-larysa.zaremba@intel.com Signed-off-by: Alexei Starovoitov Signed-off-by: Petr Oros --- drivers/net/veth.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 2c442893b9d8..5278a8f00579 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -1683,6 +1683,24 @@ static int veth_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash, return 0; } +static int veth_xdp_rx_vlan_tag(const struct xdp_md *ctx, __be16 *vlan_proto, + u16 *vlan_tci) +{ + const struct veth_xdp_buff *_ctx = (void *)ctx; + const struct sk_buff *skb = _ctx->skb; + int err; + + if (!skb) + return -ENODATA; + + err = __vlan_hwaccel_get_tag(skb, vlan_tci); + if (err) + return err; + + *vlan_proto = skb->vlan_proto; + return err; +} + static const struct net_device_ops veth_netdev_ops = { .ndo_init = veth_dev_init, .ndo_open = veth_open, @@ -1707,6 +1725,7 @@ static const struct net_device_ops veth_netdev_ops = { static const struct xdp_metadata_ops veth_xdp_metadata_ops = { .xmo_rx_timestamp = veth_xdp_rx_timestamp, .xmo_rx_hash = veth_xdp_rx_hash, + .xmo_rx_vlan_tag = veth_xdp_rx_vlan_tag, }; #define VETH_FEATURES (NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HW_CSUM | \ From a72922aff8321ff34507a23de92f7b99d778c4e1 Mon Sep 17 00:00:00 2001 From: Petr Oros Date: Mon, 13 May 2024 13:16:07 +0200 Subject: [PATCH 4/8] net: make vlan_get_tag() return -ENODATA instead of -EINVAL JIRA: https://issues.redhat.com/browse/RHEL-31890 Upstream commit(s): commit 537fec0733c4a72e2a2b69fee365459c5b75d92e Author: Larysa Zaremba Date: Tue Dec 5 22:08:42 2023 +0100 net: make vlan_get_tag() return -ENODATA instead of -EINVAL __vlan_hwaccel_get_tag() is used in veth XDP hints implementation, its return value (-EINVAL if skb is not VLAN tagged) is passed to bpf code, but XDP hints specification requires drivers to return -ENODATA, if a hint cannot be provided for a particular packet. Solve this inconsistency by changing error return value of __vlan_hwaccel_get_tag() from -EINVAL to -ENODATA, do the same thing to __vlan_get_tag(), because this function is supposed to follow the same convention. This, in turn, makes -ENODATA the only non-zero value vlan_get_tag() can return. We can do this with no side effects, because none of the users of the 3 above-mentioned functions rely on the exact value. Suggested-by: Jesper Dangaard Brouer Acked-by: Stanislav Fomichev Signed-off-by: Larysa Zaremba Link: https://lore.kernel.org/r/20231205210847.28460-14-larysa.zaremba@intel.com Signed-off-by: Alexei Starovoitov Signed-off-by: Petr Oros --- include/linux/if_vlan.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index c45253249543..91b8481b215a 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -543,7 +543,7 @@ static inline int __vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci) struct vlan_ethhdr *veth = skb_vlan_eth_hdr(skb); if (!eth_type_vlan(veth->h_vlan_proto)) - return -EINVAL; + return -ENODATA; *vlan_tci = ntohs(veth->h_vlan_TCI); return 0; @@ -564,7 +564,7 @@ static inline int __vlan_hwaccel_get_tag(const struct sk_buff *skb, return 0; } else { *vlan_tci = 0; - return -EINVAL; + return -ENODATA; } } From 6b2671f061591ffbc2fbda2e7b515584a1c79a94 Mon Sep 17 00:00:00 2001 From: Petr Oros Date: Mon, 13 May 2024 13:16:08 +0200 Subject: [PATCH 5/8] selftests/bpf: Allow VLAN packets in xdp_hw_metadata JIRA: https://issues.redhat.com/browse/RHEL-31890 Upstream commit(s): commit e71a9fa7fdb2effcaaed37c207ec4f634c8f4901 Author: Larysa Zaremba Date: Tue Dec 5 22:08:44 2023 +0100 selftests/bpf: Allow VLAN packets in xdp_hw_metadata Make VLAN c-tag and s-tag XDP hint testing more convenient by not skipping VLAN-ed packets. Allow both 802.1ad and 802.1Q headers. Acked-by: Stanislav Fomichev Signed-off-by: Larysa Zaremba Link: https://lore.kernel.org/r/20231205210847.28460-16-larysa.zaremba@intel.com Signed-off-by: Alexei Starovoitov Signed-off-by: Petr Oros --- tools/testing/selftests/bpf/progs/xdp_hw_metadata.c | 10 +++++++++- tools/testing/selftests/bpf/xdp_metadata.h | 8 ++++++++ 2 files changed, 17 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c index f6d1cc9ad892..8767d919c881 100644 --- a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c +++ b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c @@ -26,15 +26,23 @@ int rx(struct xdp_md *ctx) { void *data, *data_meta, *data_end; struct ipv6hdr *ip6h = NULL; - struct ethhdr *eth = NULL; struct udphdr *udp = NULL; struct iphdr *iph = NULL; struct xdp_meta *meta; + struct ethhdr *eth; int err; data = (void *)(long)ctx->data; data_end = (void *)(long)ctx->data_end; eth = data; + + if (eth + 1 < data_end && (eth->h_proto == bpf_htons(ETH_P_8021AD) || + eth->h_proto == bpf_htons(ETH_P_8021Q))) + eth = (void *)eth + sizeof(struct vlan_hdr); + + if (eth + 1 < data_end && eth->h_proto == bpf_htons(ETH_P_8021Q)) + eth = (void *)eth + sizeof(struct vlan_hdr); + if (eth + 1 < data_end) { if (eth->h_proto == bpf_htons(ETH_P_IP)) { iph = (void *)(eth + 1); diff --git a/tools/testing/selftests/bpf/xdp_metadata.h b/tools/testing/selftests/bpf/xdp_metadata.h index 938a729bd307..6664893c2c77 100644 --- a/tools/testing/selftests/bpf/xdp_metadata.h +++ b/tools/testing/selftests/bpf/xdp_metadata.h @@ -9,6 +9,14 @@ #define ETH_P_IPV6 0x86DD #endif +#ifndef ETH_P_8021Q +#define ETH_P_8021Q 0x8100 +#endif + +#ifndef ETH_P_8021AD +#define ETH_P_8021AD 0x88A8 +#endif + struct xdp_meta { __u64 rx_timestamp; __u64 xdp_timestamp; From 6620eee6c3a424b8174bfe216646e6925642350c Mon Sep 17 00:00:00 2001 From: Petr Oros Date: Mon, 13 May 2024 13:16:08 +0200 Subject: [PATCH 6/8] selftests/bpf: Add flags and VLAN hint to xdp_hw_metadata JIRA: https://issues.redhat.com/browse/RHEL-31890 Upstream commit(s): commit 8e68a4beba943bdffb342c601c649223f44b7329 Author: Larysa Zaremba Date: Tue Dec 5 22:08:45 2023 +0100 selftests/bpf: Add flags and VLAN hint to xdp_hw_metadata Add VLAN hint to the xdp_hw_metadata program. Also, to make metadata layout more straightforward, add flags field to pass information about validity of every separate hint separately. Acked-by: Stanislav Fomichev Signed-off-by: Larysa Zaremba Link: https://lore.kernel.org/r/20231205210847.28460-17-larysa.zaremba@intel.com Signed-off-by: Alexei Starovoitov Signed-off-by: Petr Oros --- .../selftests/bpf/progs/xdp_hw_metadata.c | 32 ++++++++++++----- tools/testing/selftests/bpf/xdp_hw_metadata.c | 34 ++++++++++++++++--- tools/testing/selftests/bpf/xdp_metadata.h | 26 +++++++++++++- 3 files changed, 78 insertions(+), 14 deletions(-) diff --git a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c index 8767d919c881..330ece2eabdb 100644 --- a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c +++ b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c @@ -20,6 +20,9 @@ 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, enum xdp_rss_hash_type *rss_type) __ksym; +extern int bpf_xdp_metadata_rx_vlan_tag(const struct xdp_md *ctx, + __be16 *vlan_proto, + __u16 *vlan_tci) __ksym; SEC("xdp.frags") int rx(struct xdp_md *ctx) @@ -84,15 +87,28 @@ int rx(struct xdp_md *ctx) return XDP_PASS; } - err = bpf_xdp_metadata_rx_timestamp(ctx, &meta->rx_timestamp); - if (!err) - meta->xdp_timestamp = bpf_ktime_get_tai_ns(); - else - meta->rx_timestamp = 0; /* Used by AF_XDP as not avail signal */ + meta->hint_valid = 0; - 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 */ + meta->xdp_timestamp = bpf_ktime_get_tai_ns(); + err = bpf_xdp_metadata_rx_timestamp(ctx, &meta->rx_timestamp); + if (err) + meta->rx_timestamp_err = err; + else + meta->hint_valid |= XDP_META_FIELD_TS; + + err = bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash, + &meta->rx_hash_type); + if (err) + meta->rx_hash_err = err; + else + meta->hint_valid |= XDP_META_FIELD_RSS; + + err = bpf_xdp_metadata_rx_vlan_tag(ctx, &meta->rx_vlan_proto, + &meta->rx_vlan_tci); + if (err) + meta->rx_vlan_tag_err = err; + else + meta->hint_valid |= XDP_META_FIELD_VLAN_TAG; __sync_add_and_fetch(&pkts_redir, 1); return bpf_redirect_map(&xsk, ctx->rx_queue_index, XDP_PASS); diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c index 3291625ba4fb..e3ad74eca8ec 100644 --- a/tools/testing/selftests/bpf/xdp_hw_metadata.c +++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c @@ -21,6 +21,9 @@ #include "xsk.h" #include +#include +#include +#include #include #include #include @@ -182,19 +185,31 @@ static void print_tstamp_delta(const char *name, const char *refname, (double)delta / 1000); } +#define VLAN_PRIO_MASK GENMASK(15, 13) /* Priority Code Point */ +#define VLAN_DEI_MASK GENMASK(12, 12) /* Drop Eligible Indicator */ +#define VLAN_VID_MASK GENMASK(11, 0) /* VLAN Identifier */ +static void print_vlan_tci(__u16 tag) +{ + __u16 vlan_id = FIELD_GET(VLAN_VID_MASK, tag); + __u8 pcp = FIELD_GET(VLAN_PRIO_MASK, tag); + bool dei = FIELD_GET(VLAN_DEI_MASK, tag); + + printf("PCP=%u, DEI=%d, VID=0x%X\n", pcp, dei, vlan_id); +} + static void verify_xdp_metadata(void *data, clockid_t clock_id) { struct xdp_meta *meta; meta = data - sizeof(*meta); - if (meta->rx_hash_err < 0) - printf("No rx_hash err=%d\n", meta->rx_hash_err); - else + if (meta->hint_valid & XDP_META_FIELD_RSS) printf("rx_hash: 0x%X with RSS type:0x%X\n", meta->rx_hash, meta->rx_hash_type); + else + printf("No rx_hash, err=%d\n", meta->rx_hash_err); - if (meta->rx_timestamp) { + if (meta->hint_valid & XDP_META_FIELD_TS) { __u64 ref_tstamp = gettime(clock_id); /* store received timestamps to calculate a delta at tx */ @@ -206,7 +221,16 @@ static void verify_xdp_metadata(void *data, clockid_t clock_id) print_tstamp_delta("XDP RX-time", "User RX-time", meta->xdp_timestamp, ref_tstamp); } else { - printf("No rx_timestamp\n"); + printf("No rx_timestamp, err=%d\n", meta->rx_timestamp_err); + } + + if (meta->hint_valid & XDP_META_FIELD_VLAN_TAG) { + printf("rx_vlan_proto: 0x%X\n", ntohs(meta->rx_vlan_proto)); + printf("rx_vlan_tci: "); + print_vlan_tci(meta->rx_vlan_tci); + } else { + printf("No rx_vlan_tci or rx_vlan_proto, err=%d\n", + meta->rx_vlan_tag_err); } } diff --git a/tools/testing/selftests/bpf/xdp_metadata.h b/tools/testing/selftests/bpf/xdp_metadata.h index 6664893c2c77..87318ad1117a 100644 --- a/tools/testing/selftests/bpf/xdp_metadata.h +++ b/tools/testing/selftests/bpf/xdp_metadata.h @@ -17,12 +17,36 @@ #define ETH_P_8021AD 0x88A8 #endif +#ifndef BIT +#define BIT(nr) (1 << (nr)) +#endif + +/* Non-existent checksum status */ +#define XDP_CHECKSUM_MAGIC BIT(2) + +enum xdp_meta_field { + XDP_META_FIELD_TS = BIT(0), + XDP_META_FIELD_RSS = BIT(1), + XDP_META_FIELD_VLAN_TAG = BIT(2), +}; + struct xdp_meta { - __u64 rx_timestamp; + union { + __u64 rx_timestamp; + __s32 rx_timestamp_err; + }; __u64 xdp_timestamp; __u32 rx_hash; union { __u32 rx_hash_type; __s32 rx_hash_err; }; + union { + struct { + __be16 rx_vlan_proto; + __u16 rx_vlan_tci; + }; + __s32 rx_vlan_tag_err; + }; + enum xdp_meta_field hint_valid; }; From 1db414c7d4995f394ddcc56cde26dbc721ac2729 Mon Sep 17 00:00:00 2001 From: Petr Oros Date: Mon, 13 May 2024 13:16:09 +0200 Subject: [PATCH 7/8] selftests/bpf: Add AF_INET packet generation to xdp_metadata JIRA: https://issues.redhat.com/browse/RHEL-31890 Upstream commit(s): commit a3850af4ea25dadc8b35edf132340907d523657e Author: Larysa Zaremba Date: Tue Dec 5 22:08:46 2023 +0100 selftests/bpf: Add AF_INET packet generation to xdp_metadata The easiest way to simulate stripped VLAN tag in veth is to send a packet from VLAN interface, attached to veth. Unfortunately, this approach is incompatible with AF_XDP on TX side, because VLAN interfaces do not have such feature. Check both packets sent via AF_XDP TX and regular socket. AF_INET packet will also have a filled-in hash type (XDP_RSS_TYPE_L4), unlike AF_XDP packet, so more values can be checked. Signed-off-by: Larysa Zaremba Acked-by: Stanislav Fomichev Link: https://lore.kernel.org/r/20231205210847.28460-18-larysa.zaremba@intel.com Signed-off-by: Alexei Starovoitov Signed-off-by: Petr Oros --- .../selftests/bpf/prog_tests/xdp_metadata.c | 116 +++++++++++++++--- 1 file changed, 97 insertions(+), 19 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c index 33cdf88efa6b..e7f06cbdd845 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c @@ -20,7 +20,7 @@ #define UDP_PAYLOAD_BYTES 4 -#define AF_XDP_SOURCE_PORT 1234 +#define UDP_SOURCE_PORT 1234 #define AF_XDP_CONSUMER_PORT 8080 #define UMEM_NUM 16 @@ -33,6 +33,12 @@ #define RX_ADDR "10.0.0.2" #define PREFIX_LEN "8" #define FAMILY AF_INET +#define TX_NETNS_NAME "xdp_metadata_tx" +#define RX_NETNS_NAME "xdp_metadata_rx" +#define TX_MAC "00:00:00:00:00:01" +#define RX_MAC "00:00:00:00:00:02" + +#define XDP_RSS_TYPE_L4 BIT(3) struct xsk { void *umem_area; @@ -181,7 +187,7 @@ static int generate_packet(struct xsk *xsk, __u16 dst_port) ASSERT_EQ(inet_pton(FAMILY, RX_ADDR, &iph->daddr), 1, "inet_pton(RX_ADDR)"); ip_csum(iph); - udph->source = htons(AF_XDP_SOURCE_PORT); + udph->source = htons(UDP_SOURCE_PORT); udph->dest = htons(dst_port); udph->len = htons(sizeof(*udph) + UDP_PAYLOAD_BYTES); udph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, @@ -204,6 +210,30 @@ static int generate_packet(struct xsk *xsk, __u16 dst_port) return 0; } +static int generate_packet_inet(void) +{ + char udp_payload[UDP_PAYLOAD_BYTES]; + struct sockaddr_in rx_addr; + int sock_fd, err = 0; + + /* Build a packet */ + memset(udp_payload, 0xAA, UDP_PAYLOAD_BYTES); + rx_addr.sin_addr.s_addr = inet_addr(RX_ADDR); + rx_addr.sin_family = AF_INET; + rx_addr.sin_port = htons(AF_XDP_CONSUMER_PORT); + + sock_fd = socket(AF_INET, SOCK_DGRAM, IPPROTO_UDP); + if (!ASSERT_GE(sock_fd, 0, "socket(AF_INET, SOCK_DGRAM, IPPROTO_UDP)")) + return sock_fd; + + err = sendto(sock_fd, udp_payload, UDP_PAYLOAD_BYTES, MSG_DONTWAIT, + (void *)&rx_addr, sizeof(rx_addr)); + ASSERT_GE(err, 0, "sendto"); + + close(sock_fd); + return err; +} + static void complete_tx(struct xsk *xsk) { struct xsk_tx_metadata *meta; @@ -236,7 +266,7 @@ static void refill_rx(struct xsk *xsk, __u64 addr) } } -static int verify_xsk_metadata(struct xsk *xsk) +static int verify_xsk_metadata(struct xsk *xsk, bool sent_from_af_xdp) { const struct xdp_desc *rx_desc; struct pollfd fds = {}; @@ -290,17 +320,36 @@ static int verify_xsk_metadata(struct xsk *xsk) if (!ASSERT_NEQ(meta->rx_hash, 0, "rx_hash")) return -1; + if (!sent_from_af_xdp) { + if (!ASSERT_NEQ(meta->rx_hash_type & XDP_RSS_TYPE_L4, 0, "rx_hash_type")) + return -1; + goto done; + } + ASSERT_EQ(meta->rx_hash_type, 0, "rx_hash_type"); /* checksum offload */ ASSERT_EQ(udph->check, htons(0x721c), "csum"); +done: xsk_ring_cons__release(&xsk->rx, 1); refill_rx(xsk, comp_addr); return 0; } +static void switch_ns_to_rx(struct nstoken **tok) +{ + close_netns(*tok); + *tok = open_netns(RX_NETNS_NAME); +} + +static void switch_ns_to_tx(struct nstoken **tok) +{ + close_netns(*tok); + *tok = open_netns(TX_NETNS_NAME); +} + void test_xdp_metadata(void) { struct xdp_metadata2 *bpf_obj2 = NULL; @@ -318,27 +367,31 @@ void test_xdp_metadata(void) int sock_fd; int ret; - /* Setup new networking namespace, with a veth pair. */ + /* Setup new networking namespaces, with a veth pair. */ + SYS(out, "ip netns add " TX_NETNS_NAME); + SYS(out, "ip netns add " RX_NETNS_NAME); - SYS(out, "ip netns add xdp_metadata"); - tok = open_netns("xdp_metadata"); + tok = open_netns(TX_NETNS_NAME); SYS(out, "ip link add numtxqueues 1 numrxqueues 1 " TX_NAME " type veth peer " RX_NAME " numtxqueues 1 numrxqueues 1"); - SYS(out, "ip link set dev " TX_NAME " address 00:00:00:00:00:01"); - SYS(out, "ip link set dev " RX_NAME " address 00:00:00:00:00:02"); + SYS(out, "ip link set " RX_NAME " netns " RX_NETNS_NAME); + + SYS(out, "ip link set dev " TX_NAME " address " TX_MAC); SYS(out, "ip link set dev " TX_NAME " up"); - SYS(out, "ip link set dev " RX_NAME " up"); SYS(out, "ip addr add " TX_ADDR "/" PREFIX_LEN " dev " TX_NAME); + + /* Avoid ARP calls */ + SYS(out, "ip -4 neigh add " RX_ADDR " lladdr " RX_MAC " dev " TX_NAME); + + switch_ns_to_rx(&tok); + + SYS(out, "ip link set dev " RX_NAME " address " RX_MAC); + SYS(out, "ip link set dev " RX_NAME " up"); SYS(out, "ip addr add " RX_ADDR "/" PREFIX_LEN " dev " RX_NAME); rx_ifindex = if_nametoindex(RX_NAME); - tx_ifindex = if_nametoindex(TX_NAME); - /* Setup separate AF_XDP for TX and RX interfaces. */ - - ret = open_xsk(tx_ifindex, &tx_xsk); - if (!ASSERT_OK(ret, "open_xsk(TX_NAME)")) - goto out; + /* Setup separate AF_XDP for RX interface. */ ret = open_xsk(rx_ifindex, &rx_xsk); if (!ASSERT_OK(ret, "open_xsk(RX_NAME)")) @@ -379,18 +432,38 @@ void test_xdp_metadata(void) if (!ASSERT_GE(ret, 0, "bpf_map_update_elem")) goto out; - /* Send packet destined to RX AF_XDP socket. */ + switch_ns_to_tx(&tok); + + /* Setup separate AF_XDP for TX interface nad send packet to the RX socket. */ + tx_ifindex = if_nametoindex(TX_NAME); + ret = open_xsk(tx_ifindex, &tx_xsk); + if (!ASSERT_OK(ret, "open_xsk(TX_NAME)")) + goto out; + if (!ASSERT_GE(generate_packet(&tx_xsk, AF_XDP_CONSUMER_PORT), 0, "generate AF_XDP_CONSUMER_PORT")) goto out; - /* Verify AF_XDP RX packet has proper metadata. */ - if (!ASSERT_GE(verify_xsk_metadata(&rx_xsk), 0, + switch_ns_to_rx(&tok); + + /* Verify packet sent from AF_XDP has proper metadata. */ + if (!ASSERT_GE(verify_xsk_metadata(&rx_xsk, true), 0, "verify_xsk_metadata")) goto out; + switch_ns_to_tx(&tok); complete_tx(&tx_xsk); + /* Now check metadata of packet, generated with network stack */ + if (!ASSERT_GE(generate_packet_inet(), 0, "generate UDP packet")) + goto out; + + switch_ns_to_rx(&tok); + + if (!ASSERT_GE(verify_xsk_metadata(&rx_xsk, false), 0, + "verify_xsk_metadata")) + goto out; + /* Make sure freplace correctly picks up original bound device * and doesn't crash. */ @@ -408,11 +481,15 @@ void test_xdp_metadata(void) if (!ASSERT_OK(xdp_metadata2__attach(bpf_obj2), "attach freplace")) goto out; + switch_ns_to_tx(&tok); + /* Send packet to trigger . */ if (!ASSERT_GE(generate_packet(&tx_xsk, AF_XDP_CONSUMER_PORT), 0, "generate freplace packet")) goto out; + switch_ns_to_rx(&tok); + while (!retries--) { if (bpf_obj2->bss->called) break; @@ -427,5 +504,6 @@ out: xdp_metadata__destroy(bpf_obj); if (tok) close_netns(tok); - SYS_NOFAIL("ip netns del xdp_metadata"); + SYS_NOFAIL("ip netns del " RX_NETNS_NAME); + SYS_NOFAIL("ip netns del " TX_NETNS_NAME); } From fab17b9882b4161b9f8b02255fd06a3cf0c847fc Mon Sep 17 00:00:00 2001 From: Petr Oros Date: Mon, 13 May 2024 13:16:09 +0200 Subject: [PATCH 8/8] selftests/bpf: Check VLAN tag and proto in xdp_metadata JIRA: https://issues.redhat.com/browse/RHEL-31890 Upstream commit(s): commit 4c6612f6100c2d85212865dbd1a5d8a7e391d3cb Author: Larysa Zaremba Date: Tue Dec 5 22:08:47 2023 +0100 selftests/bpf: Check VLAN tag and proto in xdp_metadata Verify, whether VLAN tag and proto are set correctly. To simulate "stripped" VLAN tag on veth, send test packet from VLAN interface. Also, add TO_STR() macro for convenience. Acked-by: Stanislav Fomichev Signed-off-by: Larysa Zaremba Link: https://lore.kernel.org/r/20231205210847.28460-19-larysa.zaremba@intel.com Signed-off-by: Alexei Starovoitov Signed-off-by: Petr Oros --- .../selftests/bpf/prog_tests/xdp_metadata.c | 20 +++++++++++++++++-- .../selftests/bpf/progs/xdp_metadata.c | 5 +++++ tools/testing/selftests/bpf/testing_helpers.h | 3 +++ 3 files changed, 26 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c index e7f06cbdd845..05edcf32f528 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c @@ -38,7 +38,13 @@ #define TX_MAC "00:00:00:00:00:01" #define RX_MAC "00:00:00:00:00:02" +#define VLAN_ID 59 +#define VLAN_PROTO "802.1Q" +#define VLAN_PID htons(ETH_P_8021Q) +#define TX_NAME_VLAN TX_NAME "." TO_STR(VLAN_ID) + #define XDP_RSS_TYPE_L4 BIT(3) +#define VLAN_VID_MASK 0xfff struct xsk { void *umem_area; @@ -323,6 +329,12 @@ static int verify_xsk_metadata(struct xsk *xsk, bool sent_from_af_xdp) if (!sent_from_af_xdp) { if (!ASSERT_NEQ(meta->rx_hash_type & XDP_RSS_TYPE_L4, 0, "rx_hash_type")) return -1; + + if (!ASSERT_EQ(meta->rx_vlan_tci & VLAN_VID_MASK, VLAN_ID, "rx_vlan_tci")) + return -1; + + if (!ASSERT_EQ(meta->rx_vlan_proto, VLAN_PID, "rx_vlan_proto")) + return -1; goto done; } @@ -378,10 +390,14 @@ void test_xdp_metadata(void) SYS(out, "ip link set dev " TX_NAME " address " TX_MAC); SYS(out, "ip link set dev " TX_NAME " up"); - SYS(out, "ip addr add " TX_ADDR "/" PREFIX_LEN " dev " TX_NAME); + + SYS(out, "ip link add link " TX_NAME " " TX_NAME_VLAN + " type vlan proto " VLAN_PROTO " id " TO_STR(VLAN_ID)); + SYS(out, "ip link set dev " TX_NAME_VLAN " up"); + SYS(out, "ip addr add " TX_ADDR "/" PREFIX_LEN " dev " TX_NAME_VLAN); /* Avoid ARP calls */ - SYS(out, "ip -4 neigh add " RX_ADDR " lladdr " RX_MAC " dev " TX_NAME); + SYS(out, "ip -4 neigh add " RX_ADDR " lladdr " RX_MAC " dev " TX_NAME_VLAN); switch_ns_to_rx(&tok); diff --git a/tools/testing/selftests/bpf/progs/xdp_metadata.c b/tools/testing/selftests/bpf/progs/xdp_metadata.c index d151d406a123..2c6c46ef8502 100644 --- a/tools/testing/selftests/bpf/progs/xdp_metadata.c +++ b/tools/testing/selftests/bpf/progs/xdp_metadata.c @@ -23,6 +23,9 @@ 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, enum xdp_rss_hash_type *rss_type) __ksym; +extern int bpf_xdp_metadata_rx_vlan_tag(const struct xdp_md *ctx, + __be16 *vlan_proto, + __u16 *vlan_tci) __ksym; SEC("xdp") int rx(struct xdp_md *ctx) @@ -57,6 +60,8 @@ int rx(struct xdp_md *ctx) meta->rx_timestamp = 1; bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash, &meta->rx_hash_type); + bpf_xdp_metadata_rx_vlan_tag(ctx, &meta->rx_vlan_proto, + &meta->rx_vlan_tci); return bpf_redirect_map(&xsk, ctx->rx_queue_index, XDP_PASS); } diff --git a/tools/testing/selftests/bpf/testing_helpers.h b/tools/testing/selftests/bpf/testing_helpers.h index 5b7a55136741..35284faff4f2 100644 --- a/tools/testing/selftests/bpf/testing_helpers.h +++ b/tools/testing/selftests/bpf/testing_helpers.h @@ -9,6 +9,9 @@ #include #include +#define __TO_STR(x) #x +#define TO_STR(x) __TO_STR(x) + int parse_num_list(const char *s, bool **set, int *set_len); __u32 link_info_prog_id(const struct bpf_link *link, struct bpf_link_info *info); int bpf_prog_test_load(const char *file, enum bpf_prog_type type,