The proper place for finding bpf structures and functions is
in linux/bpf.h. The original version was trying to workaround the
case where the build environment was running on old pre BPF
version of Glibc, but the target environment had BPF.
Having own private (and divergent) version headers leads to future
problems when BPF definitions evolve.
If the build infrastructure is so old that TC flower is not
supported, then the TAP device will build without any flow support.
Signed-off-by: Stephen Hemminger <step...@networkplumber.org>
---
drivers/net/tap/bpf/bpf_extract.py | 1 -
drivers/net/tap/meson.build | 17 ++--
drivers/net/tap/rte_eth_tap.c | 38 +++++++--
drivers/net/tap/rte_eth_tap.h | 7 +-
drivers/net/tap/tap_bpf.h | 121 -----------------------------
drivers/net/tap/tap_bpf_api.c | 20 +++--
drivers/net/tap/tap_bpf_insns.h | 2 -
drivers/net/tap/tap_flow.c | 90 ---------------------
8 files changed, 60 insertions(+), 236 deletions(-)
delete mode 100644 drivers/net/tap/tap_bpf.h
diff --git a/drivers/net/tap/bpf/bpf_extract.py
b/drivers/net/tap/bpf/bpf_extract.py
index b630c42b80..73c4dafe4e 100644
--- a/drivers/net/tap/bpf/bpf_extract.py
+++ b/drivers/net/tap/bpf/bpf_extract.py
@@ -65,7 +65,6 @@ def write_header(out, source):
print(f' * Auto-generated from {source}', file=out)
print(" * This not the original source file. Do NOT edit it.", file=out)
print(" */\n", file=out)
- print("#include <tap_bpf.h>", file=out)
def main():
diff --git a/drivers/net/tap/meson.build b/drivers/net/tap/meson.build
index 5099ccdff1..66647a1c62 100644
--- a/drivers/net/tap/meson.build
+++ b/drivers/net/tap/meson.build
@@ -7,13 +7,19 @@ if not is_linux
endif
sources = files(
'rte_eth_tap.c',
- 'tap_bpf_api.c',
- 'tap_flow.c',
'tap_intr.c',
'tap_netlink.c',
- 'tap_tcmsgs.c',
)
+if cc.has_header_symbol('linux/pkt_cls.h', 'TCA_FLOWER_ACT')
+ cflags += '-DHAVE_TCA_FLOWER'
+ sources += files(
+ 'tap_bpf_api.c',
+ 'tap_flow.c',
+ 'tap_tcmsgs.c',
+ )
+endif
+
deps = ['bus_vdev', 'gso', 'hash']
cflags += '-DTAP_MAX_QUEUES=16'
@@ -23,12 +29,7 @@ cflags += '-DTAP_MAX_QUEUES=16'
# "enum/define", "symbol to search" ]
#
args = [
- [ 'HAVE_TC_FLOWER', 'linux/pkt_cls.h', 'TCA_FLOWER_UNSPEC' ],
- [ 'HAVE_TC_VLAN_ID', 'linux/pkt_cls.h', 'TCA_FLOWER_KEY_VLAN_PRIO' ],
- [ 'HAVE_TC_BPF', 'linux/pkt_cls.h', 'TCA_BPF_UNSPEC' ],
- [ 'HAVE_TC_BPF_FD', 'linux/pkt_cls.h', 'TCA_BPF_FD' ],
[ 'HAVE_TC_ACT_BPF', 'linux/tc_act/tc_bpf.h', 'TCA_ACT_BPF_UNSPEC' ],
- [ 'HAVE_TC_ACT_BPF_FD', 'linux/tc_act/tc_bpf.h', 'TCA_ACT_BPF_FD' ],
]
config = configuration_data()
foreach arg:args
diff --git a/drivers/net/tap/rte_eth_tap.c b/drivers/net/tap/rte_eth_tap.c
index 38a1b2d825..3f4fe95a09 100644
--- a/drivers/net/tap/rte_eth_tap.c
+++ b/drivers/net/tap/rte_eth_tap.c
@@ -1124,12 +1124,15 @@ tap_dev_close(struct rte_eth_dev *dev)
if (!internals->persist)
tap_link_set_down(dev);
+
+#ifdef HAVE_TCA_FLOWER
if (internals->nlsk_fd != -1) {
tap_flow_flush(dev, NULL);
tap_flow_implicit_flush(internals, NULL);
tap_nl_final(internals->nlsk_fd);
internals->nlsk_fd = -1;
}
+#endif
for (i = 0; i < RTE_PMD_TAP_MAX_QUEUES; i++) {
struct rx_queue *rxq = &internals->rxq[i];
@@ -1265,6 +1268,7 @@ tap_promisc_enable(struct rte_eth_dev *dev)
if (ret != 0)
return ret;
+#ifdef HAVE_TCA_FLOWER
if (pmd->remote_if_index && !pmd->flow_isolate) {
dev->data->promiscuous = 1;
ret = tap_flow_implicit_create(pmd, TAP_REMOTE_PROMISC);
@@ -1278,7 +1282,7 @@ tap_promisc_enable(struct rte_eth_dev *dev)
return ret;
}
}
-
+#endif
return 0;
}
@@ -1293,6 +1297,7 @@ tap_promisc_disable(struct rte_eth_dev *dev)
if (ret != 0)
return ret;
+#ifdef HAVE_TCA_FLOWER
if (pmd->remote_if_index && !pmd->flow_isolate) {
dev->data->promiscuous = 0;
ret = tap_flow_implicit_destroy(pmd, TAP_REMOTE_PROMISC);
@@ -1306,6 +1311,7 @@ tap_promisc_disable(struct rte_eth_dev *dev)
return ret;
}
}
+#endif
return 0;
}
@@ -1321,6 +1327,7 @@ tap_allmulti_enable(struct rte_eth_dev *dev)
if (ret != 0)
return ret;
+#ifdef HAVE_TCA_FLOWER
if (pmd->remote_if_index && !pmd->flow_isolate) {
dev->data->all_multicast = 1;
ret = tap_flow_implicit_create(pmd, TAP_REMOTE_ALLMULTI);
@@ -1334,6 +1341,7 @@ tap_allmulti_enable(struct rte_eth_dev *dev)
return ret;
}
}
+#endif
return 0;
}
@@ -1349,6 +1357,7 @@ tap_allmulti_disable(struct rte_eth_dev *dev)
if (ret != 0)
return ret;
+#ifdef HAVE_TCA_FLOWER
if (pmd->remote_if_index && !pmd->flow_isolate) {
dev->data->all_multicast = 0;
ret = tap_flow_implicit_destroy(pmd, TAP_REMOTE_ALLMULTI);
@@ -1362,6 +1371,7 @@ tap_allmulti_disable(struct rte_eth_dev *dev)
return ret;
}
}
+#endif
return 0;
}
@@ -1407,6 +1417,8 @@ tap_mac_set(struct rte_eth_dev *dev, struct
rte_ether_addr *mac_addr)
if (ret < 0)
return ret;
rte_memcpy(&pmd->eth_addr, mac_addr, RTE_ETHER_ADDR_LEN);
+
+#ifdef HAVE_TCA_FLOWER
if (pmd->remote_if_index && !pmd->flow_isolate) {
/* Replace MAC redirection rule after a MAC change */
ret = tap_flow_implicit_destroy(pmd, TAP_REMOTE_LOCAL_MAC);
@@ -1424,6 +1436,7 @@ tap_mac_set(struct rte_eth_dev *dev, struct
rte_ether_addr *mac_addr)
return ret;
}
}
+#endif
return 0;
}
@@ -1901,7 +1914,9 @@ static const struct eth_dev_ops ops = {
.stats_reset = tap_stats_reset,
.dev_supported_ptypes_get = tap_dev_supported_ptypes_get,
.rss_hash_update = tap_rss_hash_update,
+#ifdef HAVE_TCA_FLOWER
.flow_ops_get = tap_dev_flow_ops_get,
+#endif
};
static int
@@ -1941,7 +1956,9 @@ eth_dev_tap_create(struct rte_vdev_device *vdev, const
char *tap_name,
strlcpy(pmd->name, tap_name, sizeof(pmd->name));
pmd->type = type;
pmd->ka_fd = -1;
+#ifdef HAVE_TCA_FLOWER
pmd->nlsk_fd = -1;
+#endif
pmd->gso_ctx_mp = NULL;
pmd->ioctl_sock = socket(AF_INET, SOCK_DGRAM, 0);
@@ -2021,6 +2038,14 @@ eth_dev_tap_create(struct rte_vdev_device *vdev, const
char *tap_name,
/* Make network device persist after application exit */
pmd->persist = persist;
+ pmd->if_index = if_nametoindex(pmd->name);
+ if (!pmd->if_index) {
+ TAP_LOG(ERR, "%s: failed to get if_index.", pmd->name);
+ goto disable_rte_flow;
+ }
+
+
+#ifdef HAVE_TCA_FLOWER
/*
* Set up everything related to rte_flow:
* - netlink socket
@@ -2035,11 +2060,6 @@ eth_dev_tap_create(struct rte_vdev_device *vdev, const
char *tap_name,
pmd->name);
goto disable_rte_flow;
}
- pmd->if_index = if_nametoindex(pmd->name);
- if (!pmd->if_index) {
- TAP_LOG(ERR, "%s: failed to get if_index.", pmd->name);
- goto disable_rte_flow;
- }
if (qdisc_create_multiq(pmd->nlsk_fd, pmd->if_index) < 0) {
TAP_LOG(ERR, "%s: failed to create multiq qdisc.",
pmd->name);
@@ -2050,6 +2070,7 @@ eth_dev_tap_create(struct rte_vdev_device *vdev, const
char *tap_name,
pmd->name);
goto disable_rte_flow;
}
+
LIST_INIT(&pmd->flows);
if (strlen(remote_iface)) {
@@ -2102,6 +2123,7 @@ eth_dev_tap_create(struct rte_vdev_device *vdev, const
char *tap_name,
goto error_remote;
}
}
+#endif
rte_eth_dev_probing_finish(dev);
return 0;
@@ -2116,14 +2138,18 @@ eth_dev_tap_create(struct rte_vdev_device *vdev, const
char *tap_name,
rte_eth_dev_probing_finish(dev);
return 0;
+#ifdef HAVE_TCA_FLOWER
error_remote:
TAP_LOG(ERR, " Can't set up remote feature: %s(%d)",
strerror(errno), errno);
tap_flow_implicit_flush(pmd, NULL);
+#endif
error_exit:
+#ifdef HAVE_TCA_FLOWER
if (pmd->nlsk_fd != -1)
close(pmd->nlsk_fd);
+#endif
if (pmd->ka_fd != -1)
close(pmd->ka_fd);
if (pmd->ioctl_sock != -1)
diff --git a/drivers/net/tap/rte_eth_tap.h b/drivers/net/tap/rte_eth_tap.h
index 1bcf92ce80..af18b29090 100644
--- a/drivers/net/tap/rte_eth_tap.h
+++ b/drivers/net/tap/rte_eth_tap.h
@@ -16,6 +16,7 @@
#include <ethdev_driver.h>
#include <rte_ether.h>
#include <rte_gso.h>
+
#include "tap_log.h"
#ifdef IFF_MULTI_QUEUE
@@ -70,15 +71,17 @@ struct pmd_internals {
char remote_iface[RTE_ETH_NAME_MAX_LEN]; /* Remote netdevice name */
char name[RTE_ETH_NAME_MAX_LEN]; /* Internal Tap device name */
int type; /* Type field - TUN|TAP */
+ int persist; /* 1 if keep link up, else 0 */
struct rte_ether_addr eth_addr; /* Mac address of the device port */
struct ifreq remote_initial_flags;/* Remote netdevice flags on init */
int remote_if_index; /* remote netdevice IF_INDEX */
int if_index; /* IF_INDEX for the port */
int ioctl_sock; /* socket for ioctl calls */
+
+#ifdef HAVE_TCA_FLOWER
int nlsk_fd; /* Netlink socket fd */
int flow_isolate; /* 1 if flow isolation is enabled */
int rss_enabled; /* 1 if RSS is enabled, else 0 */
- int persist; /* 1 if keep link up, else 0 */
/* implicit rules set when RSS is enabled */
int map_fd; /* BPF RSS map fd */
int bpf_fd[RTE_PMD_TAP_MAX_QUEUES];/* List of bpf fds per queue */
@@ -86,6 +89,8 @@ struct pmd_internals {
LIST_HEAD(tap_flows, rte_flow) flows; /* rte_flow rules */
/* implicit rte_flow rules set when a remote device is active */
LIST_HEAD(tap_implicit_flows, rte_flow) implicit_flows;
+#endif
+
struct rx_queue rxq[RTE_PMD_TAP_MAX_QUEUES]; /* List of RX queues */
struct tx_queue txq[RTE_PMD_TAP_MAX_QUEUES]; /* List of TX queues */
struct rte_intr_handle *intr_handle; /* LSC interrupt handle. */
diff --git a/drivers/net/tap/tap_bpf.h b/drivers/net/tap/tap_bpf.h
deleted file mode 100644
index d8437927ef..0000000000
--- a/drivers/net/tap/tap_bpf.h
+++ /dev/null
@@ -1,121 +0,0 @@
-/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
- * Copyright 2017 Mellanox Technologies, Ltd
- */
-
-#ifndef __TAP_BPF_H__
-#define __TAP_BPF_H__
-
-#include <tap_autoconf.h>
-
-/* Do not #include <linux/bpf.h> since eBPF must compile on different
- * distros which may include partial definitions for eBPF (while the
- * kernel itself may support eBPF). Instead define here all that is needed
- */
-
-/* BPF_MAP_UPDATE_ELEM command flags */
-#define BPF_ANY 0 /* create a new element or update an existing */
-
-/* BPF architecture instruction struct */
-struct bpf_insn {
- __u8 code;
- __u8 dst_reg:4;
- __u8 src_reg:4;
- __s16 off;
- __s32 imm; /* immediate value */
-};
-
-/* BPF program types */
-enum bpf_prog_type {
- BPF_PROG_TYPE_UNSPEC,
- BPF_PROG_TYPE_SOCKET_FILTER,
- BPF_PROG_TYPE_KPROBE,
- BPF_PROG_TYPE_SCHED_CLS,
- BPF_PROG_TYPE_SCHED_ACT,
-};
-
-/* BPF commands types */
-enum bpf_cmd {
- BPF_MAP_CREATE,
- BPF_MAP_LOOKUP_ELEM,
- BPF_MAP_UPDATE_ELEM,
- BPF_MAP_DELETE_ELEM,
- BPF_MAP_GET_NEXT_KEY,
- BPF_PROG_LOAD,
-};
-
-/* BPF maps types */
-enum bpf_map_type {
- BPF_MAP_TYPE_UNSPEC,
- BPF_MAP_TYPE_HASH,
-};
-
-/* union of anonymous structs used with TAP BPF commands */
-union __rte_aligned(8) bpf_attr {
- /* BPF_MAP_CREATE command */
- struct {
- __u32 map_type;
- __u32 key_size;
- __u32 value_size;
- __u32 max_entries;
- __u32 map_flags;
- __u32 inner_map_fd;
- };
-
- /* BPF_MAP_UPDATE_ELEM, BPF_MAP_DELETE_ELEM commands */
- struct {
- __u32 map_fd;
- __aligned_u64 key;
- union {
- __aligned_u64 value;
- __aligned_u64 next_key;
- };
- __u64 flags;
- };
-
- /* BPF_PROG_LOAD command */
- struct {
- __u32 prog_type;
- __u32 insn_cnt;
- __aligned_u64 insns;
- __aligned_u64 license;
- __u32 log_level;
- __u32 log_size;
- __aligned_u64 log_buf;
- __u32 kern_version;
- __u32 prog_flags;
- };
-};
-
-#ifndef __NR_bpf
-# if defined(__i386__)
-# define __NR_bpf 357
-# elif defined(__x86_64__)
-# define __NR_bpf 321
-# elif defined(__arm__)
-# define __NR_bpf 386
-# elif defined(__aarch64__)
-# define __NR_bpf 280
-# elif defined(__sparc__)
-# define __NR_bpf 349
-# elif defined(__s390__)
-# define __NR_bpf 351
-# elif defined(__powerpc__)
-# define __NR_bpf 361
-# elif defined(__riscv)
-# define __NR_bpf 280
-# elif defined(__loongarch__)
-# define __NR_bpf 280
-# else
-# error __NR_bpf not defined
-# endif
-#endif
-
-enum {
- BPF_MAP_ID_KEY,
- BPF_MAP_ID_SIMPLE,
-};
-
-static int bpf_load(enum bpf_prog_type type, const struct bpf_insn *insns,
- size_t insns_cnt, const char *license);
-
-#endif /* __TAP_BPF_H__ */
diff --git a/drivers/net/tap/tap_bpf_api.c b/drivers/net/tap/tap_bpf_api.c
index 15283f8917..9e05e2ddf1 100644
--- a/drivers/net/tap/tap_bpf_api.c
+++ b/drivers/net/tap/tap_bpf_api.c
@@ -2,19 +2,19 @@
* Copyright 2017 Mellanox Technologies, Ltd
*/
-#include <errno.h>
-#include <string.h>
#include <unistd.h>
-#include <sys/queue.h>
+#include <syscall.h>
+#include <linux/bpf.h>
-#include <rte_malloc.h>
-#include <rte_eth_tap.h>
#include <tap_flow.h>
#include <tap_autoconf.h>
-#include <tap_tcmsgs.h>
-#include <tap_bpf.h>
+
#include <tap_bpf_insns.h>
+
+static int bpf_load(enum bpf_prog_type type, const struct bpf_insn *insns,
+ size_t insns_cnt, const char *license);
+
/**
* Load BPF program (section cls_q) into the kernel and return a bpf fd
*
@@ -89,7 +89,13 @@ static inline __u64 ptr_to_u64(const void *ptr)
static inline int sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr,
unsigned int size)
{
+#ifdef __NR_bpf
return syscall(__NR_bpf, cmd, attr, size);
+#else
+ TAP_LOG(ERR, "No bpf syscall, kernel headers too old?\n");
+ errno = ENOSYS;
+ return -1;
+#endif
}
/**
diff --git a/drivers/net/tap/tap_bpf_insns.h b/drivers/net/tap/tap_bpf_insns.h
index 53fa76c4e6..cdf2febf05 100644
--- a/drivers/net/tap/tap_bpf_insns.h
+++ b/drivers/net/tap/tap_bpf_insns.h
@@ -3,8 +3,6 @@
* This not the original source file. Do NOT edit it.
*/
-#include <tap_bpf.h>
-
static struct bpf_insn cls_q_insns[] = {
{0x61, 2, 1, 52, 0x00000000},
{0x18, 3, 0, 0, 0xdeadbeef},
diff --git a/drivers/net/tap/tap_flow.c b/drivers/net/tap/tap_flow.c
index 8cf64364a7..5a5a4ea048 100644
--- a/drivers/net/tap/tap_flow.c
+++ b/drivers/net/tap/tap_flow.c
@@ -21,96 +21,6 @@
#include <tap_tcmsgs.h>
#include <tap_rss.h>
-#ifndef HAVE_TC_FLOWER
-/*
- * For kernels < 4.2, this enum is not defined. Runtime checks will be made to
- * avoid sending TC messages the kernel cannot understand.
- */
-enum {
- TCA_FLOWER_UNSPEC,
- TCA_FLOWER_CLASSID,
- TCA_FLOWER_INDEV,
- TCA_FLOWER_ACT,
- TCA_FLOWER_KEY_ETH_DST, /* ETH_ALEN */
- TCA_FLOWER_KEY_ETH_DST_MASK, /* ETH_ALEN */
- TCA_FLOWER_KEY_ETH_SRC, /* ETH_ALEN */
- TCA_FLOWER_KEY_ETH_SRC_MASK, /* ETH_ALEN */
- TCA_FLOWER_KEY_ETH_TYPE, /* be16 */
- TCA_FLOWER_KEY_IP_PROTO, /* u8 */
- TCA_FLOWER_KEY_IPV4_SRC, /* be32 */
- TCA_FLOWER_KEY_IPV4_SRC_MASK, /* be32 */
- TCA_FLOWER_KEY_IPV4_DST, /* be32 */
- TCA_FLOWER_KEY_IPV4_DST_MASK, /* be32 */
- TCA_FLOWER_KEY_IPV6_SRC, /* struct in6_addr */
- TCA_FLOWER_KEY_IPV6_SRC_MASK, /* struct in6_addr */
- TCA_FLOWER_KEY_IPV6_DST, /* struct in6_addr */
- TCA_FLOWER_KEY_IPV6_DST_MASK, /* struct in6_addr */
- TCA_FLOWER_KEY_TCP_SRC, /* be16 */
- TCA_FLOWER_KEY_TCP_DST, /* be16 */
- TCA_FLOWER_KEY_UDP_SRC, /* be16 */
- TCA_FLOWER_KEY_UDP_DST, /* be16 */
-};
-#endif
-#ifndef HAVE_TC_VLAN_ID
-enum {
- /* TCA_FLOWER_FLAGS, */
- TCA_FLOWER_KEY_VLAN_ID = TCA_FLOWER_KEY_UDP_DST + 2, /* be16 */
- TCA_FLOWER_KEY_VLAN_PRIO, /* u8 */
- TCA_FLOWER_KEY_VLAN_ETH_TYPE, /* be16 */
-};
-#endif
-/*
- * For kernels < 4.2 BPF related enums may not be defined.
- * Runtime checks will be carried out to gracefully report on TC messages that
- * are rejected by the kernel. Rejection reasons may be due to:
- * 1. enum is not defined
- * 2. enum is defined but kernel is not configured to support BPF system calls,
- * BPF classifications or BPF actions.
- */
-#ifndef HAVE_TC_BPF
-enum {
- TCA_BPF_UNSPEC,
- TCA_BPF_ACT,
- TCA_BPF_POLICE,
- TCA_BPF_CLASSID,
- TCA_BPF_OPS_LEN,
- TCA_BPF_OPS,
-};
-#endif
-#ifndef HAVE_TC_BPF_FD
-enum {
- TCA_BPF_FD = TCA_BPF_OPS + 1,
- TCA_BPF_NAME,
-};
-#endif
-#ifndef HAVE_TC_ACT_BPF
-#define tc_gen \
- __u32 index; \
- __u32 capab; \
- int action; \
- int refcnt; \
- int bindcnt
-
-struct tc_act_bpf {
- tc_gen;
-};
-
-enum {
- TCA_ACT_BPF_UNSPEC,
- TCA_ACT_BPF_TM,
- TCA_ACT_BPF_PARMS,
- TCA_ACT_BPF_OPS_LEN,
- TCA_ACT_BPF_OPS,
-};
-
-#endif
-#ifndef HAVE_TC_ACT_BPF_FD
-enum {
- TCA_ACT_BPF_FD = TCA_ACT_BPF_OPS + 1,
- TCA_ACT_BPF_NAME,
-};
-#endif
-
/* RSS key management */
enum bpf_rss_key_e {
KEY_CMD_GET = 1,
--
2.43.0
