diff options
author | Jakub Kicinski <kuba@kernel.org> | 2023-10-27 06:02:40 +0300 |
---|---|---|
committer | Jakub Kicinski <kuba@kernel.org> | 2023-10-27 06:02:41 +0300 |
commit | c6f9b7138bf5c6b826175c9e0ad5f5dbfff4fa36 (patch) | |
tree | c7bf02f5524d49f829258fbda2cedab62e25efbd /tools/testing/selftests | |
parent | cc33a80b816406f900a53c7f98a50f6eacdd2e31 (diff) | |
parent | ea41b880cc85f0a992571f66e4554a69f7806246 (diff) | |
download | linux-c6f9b7138bf5c6b826175c9e0ad5f5dbfff4fa36.tar.xz |
Merge tag 'for-netdev' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Daniel Borkmann says:
====================
pull-request: bpf-next 2023-10-26
We've added 51 non-merge commits during the last 10 day(s) which contain
a total of 75 files changed, 5037 insertions(+), 200 deletions(-).
The main changes are:
1) Add open-coded task, css_task and css iterator support.
One of the use cases is customizable OOM victim selection via BPF,
from Chuyi Zhou.
2) Fix BPF verifier's iterator convergence logic to use exact states
comparison for convergence checks, from Eduard Zingerman,
Andrii Nakryiko and Alexei Starovoitov.
3) Add BPF programmable net device where bpf_mprog defines the logic
of its xmit routine. It can operate in L3 and L2 mode,
from Daniel Borkmann and Nikolay Aleksandrov.
4) Batch of fixes for BPF per-CPU kptr and re-enable unit_size checking
for global per-CPU allocator, from Hou Tao.
5) Fix libbpf which eagerly assumed that SHT_GNU_verdef ELF section
was going to be present whenever a binary has SHT_GNU_versym section,
from Andrii Nakryiko.
6) Fix BPF ringbuf correctness to fold smp_mb__before_atomic() into
atomic_set_release(), from Paul E. McKenney.
7) Add a warning if NAPI callback missed xdp_do_flush() under
CONFIG_DEBUG_NET which helps checking if drivers were missing
the former, from Sebastian Andrzej Siewior.
8) Fix missed RCU read-lock in bpf_task_under_cgroup() which was throwing
a warning under sleepable programs, from Yafang Shao.
9) Avoid unnecessary -EBUSY from htab_lock_bucket by disabling IRQ before
checking map_locked, from Song Liu.
10) Make BPF CI linked_list failure test more robust,
from Kumar Kartikeya Dwivedi.
11) Enable samples/bpf to be built as PIE in Fedora, from Viktor Malik.
12) Fix xsk starving when multiple xsk sockets were associated with
a single xsk_buff_pool, from Albert Huang.
13) Clarify the signed modulo implementation for the BPF ISA standardization
document that it uses truncated division, from Dave Thaler.
14) Improve BPF verifier's JEQ/JNE branch taken logic to also consider
signed bounds knowledge, from Andrii Nakryiko.
15) Add an option to XDP selftests to use multi-buffer AF_XDP
xdp_hw_metadata and mark used XDP programs as capable to use frags,
from Larysa Zaremba.
16) Fix bpftool's BTF dumper wrt printing a pointer value and another
one to fix struct_ops dump in an array, from Manu Bretelle.
* tag 'for-netdev' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (51 commits)
netkit: Remove explicit active/peer ptr initialization
selftests/bpf: Fix selftests broken by mitigations=off
samples/bpf: Allow building with custom bpftool
samples/bpf: Fix passing LDFLAGS to libbpf
samples/bpf: Allow building with custom CFLAGS/LDFLAGS
bpf: Add more WARN_ON_ONCE checks for mismatched alloc and free
selftests/bpf: Add selftests for netkit
selftests/bpf: Add netlink helper library
bpftool: Extend net dump with netkit progs
bpftool: Implement link show support for netkit
libbpf: Add link-based API for netkit
tools: Sync if_link uapi header
netkit, bpf: Add bpf programmable net device
bpf: Improve JEQ/JNE branch taken logic
bpf: Fold smp_mb__before_atomic() into atomic_set_release()
bpf: Fix unnecessary -EBUSY from htab_lock_bucket
xsk: Avoid starving the xsk further down the list
bpf: print full verifier states on infinite loop detection
selftests/bpf: test if state loops are detected in a tricky case
bpf: correct loop detection for iterators convergence
...
====================
Link: https://lore.kernel.org/r/20231026150509.2824-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'tools/testing/selftests')
27 files changed, 2725 insertions, 48 deletions
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 4225f975fce3..9c27b67bc7b1 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -585,11 +585,20 @@ endef # Define test_progs test runner. TRUNNER_TESTS_DIR := prog_tests TRUNNER_BPF_PROGS_DIR := progs -TRUNNER_EXTRA_SOURCES := test_progs.c cgroup_helpers.c trace_helpers.c \ - network_helpers.c testing_helpers.c \ - btf_helpers.c flow_dissector_load.h \ - cap_helpers.c test_loader.c xsk.c disasm.c \ - json_writer.c unpriv_helpers.c \ +TRUNNER_EXTRA_SOURCES := test_progs.c \ + cgroup_helpers.c \ + trace_helpers.c \ + network_helpers.c \ + testing_helpers.c \ + btf_helpers.c \ + cap_helpers.c \ + unpriv_helpers.c \ + netlink_helpers.c \ + test_loader.c \ + xsk.c \ + disasm.c \ + json_writer.c \ + flow_dissector_load.h \ ip_check_defrag_frags.h TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read $(OUTPUT)/bpf_testmod.ko \ $(OUTPUT)/liburandom_read.so \ diff --git a/tools/testing/selftests/bpf/bpf_experimental.h b/tools/testing/selftests/bpf/bpf_experimental.h index 2c8cb3f61529..1386baf9ae4a 100644 --- a/tools/testing/selftests/bpf/bpf_experimental.h +++ b/tools/testing/selftests/bpf/bpf_experimental.h @@ -458,4 +458,23 @@ extern void bpf_throw(u64 cookie) __ksym; __bpf_assert_op(LHS, <=, END, value, false); \ }) +struct bpf_iter_css_task; +struct cgroup_subsys_state; +extern int bpf_iter_css_task_new(struct bpf_iter_css_task *it, + struct cgroup_subsys_state *css, unsigned int flags) __weak __ksym; +extern struct task_struct *bpf_iter_css_task_next(struct bpf_iter_css_task *it) __weak __ksym; +extern void bpf_iter_css_task_destroy(struct bpf_iter_css_task *it) __weak __ksym; + +struct bpf_iter_task; +extern int bpf_iter_task_new(struct bpf_iter_task *it, + struct task_struct *task, unsigned int flags) __weak __ksym; +extern struct task_struct *bpf_iter_task_next(struct bpf_iter_task *it) __weak __ksym; +extern void bpf_iter_task_destroy(struct bpf_iter_task *it) __weak __ksym; + +struct bpf_iter_css; +extern int bpf_iter_css_new(struct bpf_iter_css *it, + struct cgroup_subsys_state *start, unsigned int flags) __weak __ksym; +extern struct cgroup_subsys_state *bpf_iter_css_next(struct bpf_iter_css *it) __weak __ksym; +extern void bpf_iter_css_destroy(struct bpf_iter_css *it) __weak __ksym; + #endif diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index 02dd4409200e..3ec5927ec3e5 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -71,6 +71,7 @@ CONFIG_NETFILTER_SYNPROXY=y CONFIG_NETFILTER_XT_CONNMARK=y CONFIG_NETFILTER_XT_MATCH_STATE=y CONFIG_NETFILTER_XT_TARGET_CT=y +CONFIG_NETKIT=y CONFIG_NF_CONNTRACK=y CONFIG_NF_CONNTRACK_MARK=y CONFIG_NF_DEFRAG_IPV4=y diff --git a/tools/testing/selftests/bpf/netlink_helpers.c b/tools/testing/selftests/bpf/netlink_helpers.c new file mode 100644 index 000000000000..caf36eb1d032 --- /dev/null +++ b/tools/testing/selftests/bpf/netlink_helpers.c @@ -0,0 +1,358 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Taken & modified from iproute2's libnetlink.c + * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> + */ +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <errno.h> +#include <time.h> +#include <sys/socket.h> + +#include "netlink_helpers.h" + +static int rcvbuf = 1024 * 1024; + +void rtnl_close(struct rtnl_handle *rth) +{ + if (rth->fd >= 0) { + close(rth->fd); + rth->fd = -1; + } +} + +int rtnl_open_byproto(struct rtnl_handle *rth, unsigned int subscriptions, + int protocol) +{ + socklen_t addr_len; + int sndbuf = 32768; + int one = 1; + + memset(rth, 0, sizeof(*rth)); + rth->proto = protocol; + rth->fd = socket(AF_NETLINK, SOCK_RAW | SOCK_CLOEXEC, protocol); + if (rth->fd < 0) { + perror("Cannot open netlink socket"); + return -1; + } + if (setsockopt(rth->fd, SOL_SOCKET, SO_SNDBUF, + &sndbuf, sizeof(sndbuf)) < 0) { + perror("SO_SNDBUF"); + goto err; + } + if (setsockopt(rth->fd, SOL_SOCKET, SO_RCVBUF, + &rcvbuf, sizeof(rcvbuf)) < 0) { + perror("SO_RCVBUF"); + goto err; + } + + /* Older kernels may no support extended ACK reporting */ + setsockopt(rth->fd, SOL_NETLINK, NETLINK_EXT_ACK, + &one, sizeof(one)); + + memset(&rth->local, 0, sizeof(rth->local)); + rth->local.nl_family = AF_NETLINK; + rth->local.nl_groups = subscriptions; + + if (bind(rth->fd, (struct sockaddr *)&rth->local, + sizeof(rth->local)) < 0) { + perror("Cannot bind netlink socket"); + goto err; + } + addr_len = sizeof(rth->local); + if (getsockname(rth->fd, (struct sockaddr *)&rth->local, + &addr_len) < 0) { + perror("Cannot getsockname"); + goto err; + } + if (addr_len != sizeof(rth->local)) { + fprintf(stderr, "Wrong address length %d\n", addr_len); + goto err; + } + if (rth->local.nl_family != AF_NETLINK) { + fprintf(stderr, "Wrong address family %d\n", + rth->local.nl_family); + goto err; + } + rth->seq = time(NULL); + return 0; +err: + rtnl_close(rth); + return -1; +} + +int rtnl_open(struct rtnl_handle *rth, unsigned int subscriptions) +{ + return rtnl_open_byproto(rth, subscriptions, NETLINK_ROUTE); +} + +static int __rtnl_recvmsg(int fd, struct msghdr *msg, int flags) +{ + int len; + + do { + len = recvmsg(fd, msg, flags); + } while (len < 0 && (errno == EINTR || errno == EAGAIN)); + if (len < 0) { + fprintf(stderr, "netlink receive error %s (%d)\n", + strerror(errno), errno); + return -errno; + } + if (len == 0) { + fprintf(stderr, "EOF on netlink\n"); + return -ENODATA; + } + return len; +} + +static int rtnl_recvmsg(int fd, struct msghdr *msg, char **answer) +{ + struct iovec *iov = msg->msg_iov; + char *buf; + int len; + + iov->iov_base = NULL; + iov->iov_len = 0; + + len = __rtnl_recvmsg(fd, msg, MSG_PEEK | MSG_TRUNC); + if (len < 0) + return len; + if (len < 32768) + len = 32768; + buf = malloc(len); + if (!buf) { + fprintf(stderr, "malloc error: not enough buffer\n"); + return -ENOMEM; + } + iov->iov_base = buf; + iov->iov_len = len; + len = __rtnl_recvmsg(fd, msg, 0); + if (len < 0) { + free(buf); + return len; + } + if (answer) + *answer = buf; + else + free(buf); + return len; +} + +static void rtnl_talk_error(struct nlmsghdr *h, struct nlmsgerr *err, + nl_ext_ack_fn_t errfn) +{ + fprintf(stderr, "RTNETLINK answers: %s\n", + strerror(-err->error)); +} + +static int __rtnl_talk_iov(struct rtnl_handle *rtnl, struct iovec *iov, + size_t iovlen, struct nlmsghdr **answer, + bool show_rtnl_err, nl_ext_ack_fn_t errfn) +{ + struct sockaddr_nl nladdr = { .nl_family = AF_NETLINK }; + struct iovec riov; + struct msghdr msg = { + .msg_name = &nladdr, + .msg_namelen = sizeof(nladdr), + .msg_iov = iov, + .msg_iovlen = iovlen, + }; + unsigned int seq = 0; + struct nlmsghdr *h; + int i, status; + char *buf; + + for (i = 0; i < iovlen; i++) { + h = iov[i].iov_base; + h->nlmsg_seq = seq = ++rtnl->seq; + if (answer == NULL) + h->nlmsg_flags |= NLM_F_ACK; + } + status = sendmsg(rtnl->fd, &msg, 0); + if (status < 0) { + perror("Cannot talk to rtnetlink"); + return -1; + } + /* change msg to use the response iov */ + msg.msg_iov = &riov; + msg.msg_iovlen = 1; + i = 0; + while (1) { +next: + status = rtnl_recvmsg(rtnl->fd, &msg, &buf); + ++i; + if (status < 0) + return status; + if (msg.msg_namelen != sizeof(nladdr)) { + fprintf(stderr, + "Sender address length == %d!\n", + msg.msg_namelen); + exit(1); + } + for (h = (struct nlmsghdr *)buf; status >= sizeof(*h); ) { + int len = h->nlmsg_len; + int l = len - sizeof(*h); + + if (l < 0 || len > status) { + if (msg.msg_flags & MSG_TRUNC) { + fprintf(stderr, "Truncated message!\n"); + free(buf); + return -1; + } + fprintf(stderr, + "Malformed message: len=%d!\n", + len); + exit(1); + } + if (nladdr.nl_pid != 0 || + h->nlmsg_pid != rtnl->local.nl_pid || + h->nlmsg_seq > seq || h->nlmsg_seq < seq - iovlen) { + /* Don't forget to skip that message. */ + status -= NLMSG_ALIGN(len); + h = (struct nlmsghdr *)((char *)h + NLMSG_ALIGN(len)); + continue; + } + if (h->nlmsg_type == NLMSG_ERROR) { + struct nlmsgerr *err = (struct nlmsgerr *)NLMSG_DATA(h); + int error = err->error; + + if (l < sizeof(struct nlmsgerr)) { + fprintf(stderr, "ERROR truncated\n"); + free(buf); + return -1; + } + if (error) { + errno = -error; + if (rtnl->proto != NETLINK_SOCK_DIAG && + show_rtnl_err) + rtnl_talk_error(h, err, errfn); + } + if (i < iovlen) { + free(buf); + goto next; + } + if (error) { + free(buf); + return -i; + } + if (answer) + *answer = (struct nlmsghdr *)buf; + else + free(buf); + return 0; + } + if (answer) { + *answer = (struct nlmsghdr *)buf; + return 0; + } + fprintf(stderr, "Unexpected reply!\n"); + status -= NLMSG_ALIGN(len); + h = (struct nlmsghdr *)((char *)h + NLMSG_ALIGN(len)); + } + free(buf); + if (msg.msg_flags & MSG_TRUNC) { + fprintf(stderr, "Message truncated!\n"); + continue; + } + if (status) { + fprintf(stderr, "Remnant of size %d!\n", status); + exit(1); + } + } +} + +static int __rtnl_talk(struct rtnl_handle *rtnl, struct nlmsghdr *n, + struct nlmsghdr **answer, bool show_rtnl_err, + nl_ext_ack_fn_t errfn) +{ + struct iovec iov = { + .iov_base = n, + .iov_len = n->nlmsg_len, + }; + + return __rtnl_talk_iov(rtnl, &iov, 1, answer, show_rtnl_err, errfn); +} + +int rtnl_talk(struct rtnl_handle *rtnl, struct nlmsghdr *n, + struct nlmsghdr **answer) +{ + return __rtnl_talk(rtnl, n, answer, true, NULL); +} + +int addattr(struct nlmsghdr *n, int maxlen, int type) +{ + return addattr_l(n, maxlen, type, NULL, 0); +} + +int addattr8(struct nlmsghdr *n, int maxlen, int type, __u8 data) +{ + return addattr_l(n, maxlen, type, &data, sizeof(__u8)); +} + +int addattr16(struct nlmsghdr *n, int maxlen, int type, __u16 data) +{ + return addattr_l(n, maxlen, type, &data, sizeof(__u16)); +} + +int addattr32(struct nlmsghdr *n, int maxlen, int type, __u32 data) +{ + return addattr_l(n, maxlen, type, &data, sizeof(__u32)); +} + +int addattr64(struct nlmsghdr *n, int maxlen, int type, __u64 data) +{ + return addattr_l(n, maxlen, type, &data, sizeof(__u64)); +} + +int addattrstrz(struct nlmsghdr *n, int maxlen, int type, const char *str) +{ + return addattr_l(n, maxlen, type, str, strlen(str)+1); +} + +int addattr_l(struct nlmsghdr *n, int maxlen, int type, const void *data, + int alen) +{ + int len = RTA_LENGTH(alen); + struct rtattr *rta; + + if (NLMSG_ALIGN(n->nlmsg_len) + RTA_ALIGN(len) > maxlen) { + fprintf(stderr, "%s: Message exceeded bound of %d\n", + __func__, maxlen); + return -1; + } + rta = NLMSG_TAIL(n); + rta->rta_type = type; + rta->rta_len = len; + if (alen) + memcpy(RTA_DATA(rta), data, alen); + n->nlmsg_len = NLMSG_ALIGN(n->nlmsg_len) + RTA_ALIGN(len); + return 0; +} + +int addraw_l(struct nlmsghdr *n, int maxlen, const void *data, int len) +{ + if (NLMSG_ALIGN(n->nlmsg_len) + NLMSG_ALIGN(len) > maxlen) { + fprintf(stderr, "%s: Message exceeded bound of %d\n", + __func__, maxlen); + return -1; + } + + memcpy(NLMSG_TAIL(n), data, len); + memset((void *) NLMSG_TAIL(n) + len, 0, NLMSG_ALIGN(len) - len); + n->nlmsg_len = NLMSG_ALIGN(n->nlmsg_len) + NLMSG_ALIGN(len); + return 0; +} + +struct rtattr *addattr_nest(struct nlmsghdr *n, int maxlen, int type) +{ + struct rtattr *nest = NLMSG_TAIL(n); + + addattr_l(n, maxlen, type, NULL, 0); + return nest; +} + +int addattr_nest_end(struct nlmsghdr *n, struct rtattr *nest) +{ + nest->rta_len = (void *)NLMSG_TAIL(n) - (void *)nest; + return n->nlmsg_len; +} diff --git a/tools/testing/selftests/bpf/netlink_helpers.h b/tools/testing/selftests/bpf/netlink_helpers.h new file mode 100644 index 000000000000..68116818a47e --- /dev/null +++ b/tools/testing/selftests/bpf/netlink_helpers.h @@ -0,0 +1,46 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef NETLINK_HELPERS_H +#define NETLINK_HELPERS_H + +#include <string.h> +#include <linux/netlink.h> +#include <linux/rtnetlink.h> + +struct rtnl_handle { + int fd; + struct sockaddr_nl local; + struct sockaddr_nl peer; + __u32 seq; + __u32 dump; + int proto; + FILE *dump_fp; +#define RTNL_HANDLE_F_LISTEN_ALL_NSID 0x01 +#define RTNL_HANDLE_F_SUPPRESS_NLERR 0x02 +#define RTNL_HANDLE_F_STRICT_CHK 0x04 + int flags; +}; + +#define NLMSG_TAIL(nmsg) \ + ((struct rtattr *) (((void *) (nmsg)) + NLMSG_ALIGN((nmsg)->nlmsg_len))) + +typedef int (*nl_ext_ack_fn_t)(const char *errmsg, uint32_t off, + const struct nlmsghdr *inner_nlh); + +int rtnl_open(struct rtnl_handle *rth, unsigned int subscriptions) + __attribute__((warn_unused_result)); +void rtnl_close(struct rtnl_handle *rth); +int rtnl_talk(struct rtnl_handle *rtnl, struct nlmsghdr *n, + struct nlmsghdr **answer) + __attribute__((warn_unused_result)); + +int addattr(struct nlmsghdr *n, int maxlen, int type); +int addattr8(struct nlmsghdr *n, int maxlen, int type, __u8 data); +int addattr16(struct nlmsghdr *n, int maxlen, int type, __u16 data); +int addattr32(struct nlmsghdr *n, int maxlen, int type, __u32 data); +int addattr64(struct nlmsghdr *n, int maxlen, int type, __u64 data); +int addattrstrz(struct nlmsghdr *n, int maxlen, int type, const char *data); +int addattr_l(struct nlmsghdr *n, int maxlen, int type, const void *data, int alen); +int addraw_l(struct nlmsghdr *n, int maxlen, const void *data, int len); +struct rtattr *addattr_nest(struct nlmsghdr *n, int maxlen, int type); +int addattr_nest_end(struct nlmsghdr *n, struct rtattr *nest); +#endif /* NETLINK_HELPERS_H */ diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c index 41aba139b20b..e3498f607b49 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c @@ -7,7 +7,7 @@ #include "bpf_iter_ipv6_route.skel.h" #include "bpf_iter_netlink.skel.h" #include "bpf_iter_bpf_map.skel.h" -#include "bpf_iter_task.skel.h" +#include "bpf_iter_tasks.skel.h" #include "bpf_iter_task_stack.skel.h" #include "bpf_iter_task_file.skel.h" #include "bpf_iter_task_vmas.skel.h" @@ -215,12 +215,12 @@ static void *do_nothing_wait(void *arg) static void test_task_common_nocheck(struct bpf_iter_attach_opts *opts, int *num_unknown, int *num_known) { - struct bpf_iter_task *skel; + struct bpf_iter_tasks *skel; pthread_t thread_id; void *ret; - skel = bpf_iter_task__open_and_load(); - if (!ASSERT_OK_PTR(skel, "bpf_iter_task__open_and_load")) + skel = bpf_iter_tasks__open_and_load(); + if (!ASSERT_OK_PTR(skel, "bpf_iter_tasks__open_and_load")) return; ASSERT_OK(pthread_mutex_lock(&do_nothing_mutex), "pthread_mutex_lock"); @@ -239,7 +239,7 @@ static void test_task_common_nocheck(struct bpf_iter_attach_opts *opts, ASSERT_FALSE(pthread_join(thread_id, &ret) || ret != NULL, "pthread_join"); - bpf_iter_task__destroy(skel); + bpf_iter_tasks__destroy(skel); } static void test_task_common(struct bpf_iter_attach_opts *opts, int num_unknown, int num_known) @@ -307,10 +307,10 @@ static void test_task_pidfd(void) static void test_task_sleepable(void) { - struct bpf_iter_task *skel; + struct bpf_iter_tasks *skel; - skel = bpf_iter_task__open_and_load(); - if (!ASSERT_OK_PTR(skel, "bpf_iter_task__open_and_load")) + skel = bpf_iter_tasks__open_and_load(); + if (!ASSERT_OK_PTR(skel, "bpf_iter_tasks__open_and_load")) return; do_dummy_read(skel->progs.dump_task_sleepable); @@ -320,7 +320,7 @@ static void test_task_sleepable(void) ASSERT_GT(skel->bss->num_success_copy_from_user_task, 0, "num_success_copy_from_user_task"); - bpf_iter_task__destroy(skel); + bpf_iter_tasks__destroy(skel); } static void test_task_stack(void) diff --git a/tools/testing/selftests/bpf/prog_tests/iters.c b/tools/testing/selftests/bpf/prog_tests/iters.c index b696873c5455..c2425791c923 100644 --- a/tools/testing/selftests/bpf/prog_tests/iters.c +++ b/tools/testing/selftests/bpf/prog_tests/iters.c @@ -1,7 +1,14 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ +#include <sys/syscall.h> +#include <sys/mman.h> +#include <sys/wait.h> +#include <unistd.h> +#include <malloc.h> +#include <stdlib.h> #include <test_progs.h> +#include "cgroup_helpers.h" #include "iters.skel.h" #include "iters_state_safety.skel.h" @@ -9,6 +16,10 @@ #include "iters_num.skel.h" #include "iters_testmod_seq.skel.h" #include "iters_task_vma.skel.h" +#include "iters_task.skel.h" +#include "iters_css_task.skel.h" +#include "iters_css.skel.h" +#include "iters_task_failure.skel.h" static void subtest_num_iters(void) { @@ -146,6 +157,138 @@ cleanup: iters_task_vma__destroy(skel); } +static pthread_mutex_t do_nothing_mutex; + +static void *do_nothing_wait(void *arg) +{ + pthread_mutex_lock(&do_nothing_mutex); + pthread_mutex_unlock(&do_nothing_mutex); + + pthread_exit(arg); +} + +#define thread_num 2 + +static void subtest_task_iters(void) +{ + struct iters_task *skel = NULL; + pthread_t thread_ids[thread_num]; + void *ret; + int err; + + skel = iters_task__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + goto cleanup; + skel->bss->target_pid = getpid(); + err = iters_task__attach(skel); + if (!ASSERT_OK(err, "iters_task__attach")) + goto cleanup; + pthread_mutex_lock(&do_nothing_mutex); + for (int i = 0; i < thread_num; i++) + ASSERT_OK(pthread_create(&thread_ids[i], NULL, &do_nothing_wait, NULL), + "pthread_create"); + + syscall(SYS_getpgid); + iters_task__detach(skel); + ASSERT_EQ(skel->bss->procs_cnt, 1, "procs_cnt"); + ASSERT_EQ(skel->bss->threads_cnt, thread_num + 1, "threads_cnt"); + ASSERT_EQ(skel->bss->proc_threads_cnt, thread_num + 1, "proc_threads_cnt"); + pthread_mutex_unlock(&do_nothing_mutex); + for (int i = 0; i < thread_num; i++) + ASSERT_OK(pthread_join(thread_ids[i], &ret), "pthread_join"); +cleanup: + iters_task__destroy(skel); +} + +extern int stack_mprotect(void); + +static void subtest_css_task_iters(void) +{ + struct iters_css_task *skel = NULL; + int err, cg_fd, cg_id; + const char *cgrp_path = "/cg1"; + + err = setup_cgroup_environment(); + if (!ASSERT_OK(err, "setup_cgroup_environment")) + goto cleanup; + cg_fd = create_and_get_cgroup(cgrp_path); + if (!ASSERT_GE(cg_fd, 0, "create_and_get_cgroup")) + goto cleanup; + cg_id = get_cgroup_id(cgrp_path); + err = join_cgroup(cgrp_path); + if (!ASSERT_OK(err, "join_cgroup")) + goto cleanup; + + skel = iters_css_task__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + goto cleanup; + + skel->bss->target_pid = getpid(); + skel->bss->cg_id = cg_id; + err = iters_css_task__attach(skel); + if (!ASSERT_OK(err, "iters_task__attach")) + goto cleanup; + err = stack_mprotect(); + if (!ASSERT_EQ(err, -1, "stack_mprotect") || + !ASSERT_EQ(errno, EPERM, "stack_mprotect")) + goto cleanup; + iters_css_task__detach(skel); + ASSERT_EQ(skel->bss->css_task_cnt, 1, "css_task_cnt"); + +cleanup: + cleanup_cgroup_environment(); + iters_css_task__destroy(skel); +} + +static void subtest_css_iters(void) +{ + struct iters_css *skel = NULL; + struct { + const char *path; + int fd; + } cgs[] = { + { "/cg1" }, + { "/cg1/cg2" }, + { "/cg1/cg2/cg3" }, + { "/cg1/cg2/cg3/cg4" }, + }; + int err, cg_nr = ARRAY_SIZE(cgs); + int i; + + err = setup_cgroup_environment(); + if (!ASSERT_OK(err, "setup_cgroup_environment")) + goto cleanup; + for (i = 0; i < cg_nr; i++) { + cgs[i].fd = create_and_get_cgroup(cgs[i].path); + if (!ASSERT_GE(cgs[i].fd, 0, "create_and_get_cgroup")) + goto cleanup; + } + + skel = iters_css__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + goto cleanup; + + skel->bss->target_pid = getpid(); + skel->bss->root_cg_id = get_cgroup_id(cgs[0].path); + skel->bss->leaf_cg_id = get_cgroup_id(cgs[cg_nr - 1].path); + err = iters_css__attach(skel); + + if (!ASSERT_OK(err, "iters_task__attach")) + goto cleanup; + + syscall(SYS_getpgid); + ASSERT_EQ(skel->bss->pre_order_cnt, cg_nr, "pre_order_cnt"); + ASSERT_EQ(skel->bss->first_cg_id, get_cgroup_id(cgs[0].path), "first_cg_id"); + + ASSERT_EQ(skel->bss->post_order_cnt, cg_nr, "post_order_cnt"); + ASSERT_EQ(skel->bss->last_cg_id, get_cgroup_id(cgs[0].path), "last_cg_id"); + ASSERT_EQ(skel->bss->tree_high, cg_nr - 1, "tree_high"); + iters_css__detach(skel); +cleanup: + cleanup_cgroup_environment(); + iters_css__destroy(skel); +} + void test_iters(void) { RUN_TESTS(iters_state_safety); @@ -161,4 +304,11 @@ void test_iters(void) subtest_testmod_seq_iters(); if (test__start_subtest("task_vma")) subtest_task_vma_iters(); + if (test__start_subtest("task")) + subtest_task_iters(); + if (test__start_subtest("css_task")) + subtest_css_task_iters(); + if (test__start_subtest("css")) + subtest_css_iters(); + RUN_TESTS(iters_task_failure); } diff --git a/tools/testing/selftests/bpf/prog_tests/linked_list.c b/tools/testing/selftests/bpf/prog_tests/linked_list.c index 69dc31383b78..2fb89de63bd2 100644 --- a/tools/testing/selftests/bpf/prog_tests/linked_list.c +++ b/tools/testing/selftests/bpf/prog_tests/linked_list.c @@ -94,14 +94,8 @@ static struct { { "incorrect_head_var_off2", "variable ptr_ access var_off=(0x0; 0xffffffff) disallowed" }, { "incorrect_head_off1", "bpf_list_head not found at offset=25" }, { "incorrect_head_off2", "bpf_list_head not found at offset=1" }, - { "pop_front_off", - "15: (bf) r1 = r6 ; R1_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=48,imm=0) " - "R6_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=48,imm=0) refs=2,4\n" - "16: (85) call bpf_this_cpu_ptr#154\nR1 type=ptr_or_null_ expected=percpu_ptr_" }, - { "pop_back_off", - "15: (bf) r1 = r6 ; R1_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=48,imm=0) " - "R6_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=48,imm=0) refs=2,4\n" - "16: (85) call bpf_this_cpu_ptr#154\nR1 type=ptr_or_null_ expected=percpu_ptr_" }, + { "pop_front_off", "off 48 doesn't point to 'struct bpf_spin_lock' that is at 40" }, + { "pop_back_off", "off 48 doesn't point to 'struct bpf_spin_lock' that is at 40" }, }; static void test_linked_list_fail_prog(const char *prog_name, const char *err_msg) diff --git a/tools/testing/selftests/bpf/prog_tests/task_under_cgroup.c b/tools/testing/selftests/bpf/prog_tests/task_under_cgroup.c index 4224727fb364..626d76fe43a2 100644 --- a/tools/testing/selftests/bpf/prog_tests/task_under_cgroup.c +++ b/tools/testing/selftests/bpf/prog_tests/task_under_cgroup.c @@ -30,8 +30,15 @@ void test_task_under_cgroup(void) if (!ASSERT_OK(ret, "test_task_under_cgroup__load")) goto cleanup; - ret = test_task_under_cgroup__attach(skel); - if (!ASSERT_OK(ret, "test_task_under_cgroup__attach")) + /* First, attach the LSM program, and then it will be triggered when the + * TP_BTF program is attached. + */ + skel->links.lsm_run = bpf_program__attach_lsm(skel->progs.lsm_run); + if (!ASSERT_OK_PTR(skel->links.lsm_run, "attach_lsm")) + goto cleanup; + + skel->links.tp_btf_run = bpf_program__attach_trace(skel->progs.tp_btf_run); + if (!ASSERT_OK_PTR(skel->links.tp_btf_run, "attach_tp_btf")) goto cleanup; pid = fork(); diff --git a/tools/testing/selftests/bpf/prog_tests/tc_helpers.h b/tools/testing/selftests/bpf/prog_tests/tc_helpers.h index 67f985f7d215..924d0e25320c 100644 --- a/tools/testing/selftests/bpf/prog_tests/tc_helpers.h +++ b/tools/testing/selftests/bpf/prog_tests/tc_helpers.h @@ -4,6 +4,10 @@ #define TC_HELPERS #include <test_progs.h> +#ifndef loopback +# define loopback 1 +#endif + static inline __u32 id_from_prog_fd(int fd) { struct bpf_prog_info prog_info = {}; diff --git a/tools/testing/selftests/bpf/prog_tests/tc_netkit.c b/tools/testing/selftests/bpf/prog_tests/tc_netkit.c new file mode 100644 index 000000000000..15ee7b2fc410 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/tc_netkit.c @@ -0,0 +1,687 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Isovalent */ +#include <uapi/linux/if_link.h> +#include <net/if.h> +#include <test_progs.h> + +#define netkit_peer "nk0" +#define netkit_name "nk1" + +#define ping_addr_neigh 0x0a000002 /* 10.0.0.2 */ +#define ping_addr_noneigh 0x0a000003 /* 10.0.0.3 */ + +#include "test_tc_link.skel.h" +#include "netlink_helpers.h" +#include "tc_helpers.h" + +#define ICMP_ECHO 8 + +struct icmphdr { + __u8 type; + __u8 code; + __sum16 checksum; + struct { + __be16 id; + __be16 sequence; + } echo; +}; + +struct iplink_req { + struct nlmsghdr n; + struct ifinfomsg i; + char buf[1024]; +}; + +static int create_netkit(int mode, int policy, int peer_policy, int *ifindex, + bool same_netns) +{ + struct rtnl_handle rth = { .fd = -1 }; + struct iplink_req req = {}; + struct rtattr *linkinfo, *data; + const char *type = "netkit"; + int err; + + err = rtnl_open(&rth, 0); + if (!ASSERT_OK(err, "open_rtnetlink")) + return err; + + memset(&req, 0, sizeof(req)); + req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)); + req.n.nlmsg_flags = NLM_F_REQUEST | NLM_F_CREATE | NLM_F_EXCL; + req.n.nlmsg_type = RTM_NEWLINK; + req.i.ifi_family = AF_UNSPEC; + + addattr_l(&req.n, sizeof(req), IFLA_IFNAME, netkit_name, + strlen(netkit_name)); + linkinfo = addattr_nest(&req.n, sizeof(req), IFLA_LINKINFO); + addattr_l(&req.n, sizeof(req), IFLA_INFO_KIND, type, strlen(type)); + data = addattr_nest(&req.n, sizeof(req), IFLA_INFO_DATA); + addattr32(&req.n, sizeof(req), IFLA_NETKIT_POLICY, policy); + addattr32(&req.n, sizeof(req), IFLA_NETKIT_PEER_POLICY, peer_policy); + addattr32(&req.n, sizeof(req), IFLA_NETKIT_MODE, mode); + addattr_nest_end(&req.n, data); + addattr_nest_end(&req.n, linkinfo); + + err = rtnl_talk(&rth, &req.n, NULL); + ASSERT_OK(err, "talk_rtnetlink"); + rtnl_close(&rth); + *ifindex = if_nametoindex(netkit_name); + + ASSERT_GT(*ifindex, 0, "retrieve_ifindex"); + ASSERT_OK(system("ip netns add foo"), "create netns"); + ASSERT_OK(system("ip link set dev " netkit_name " up"), + "up primary"); + ASSERT_OK(system("ip addr add dev " netkit_name " 10.0.0.1/24"), + "addr primary"); + if (same_netns) { + ASSERT_OK(system("ip link set dev " netkit_peer " up"), + "up peer"); + ASSERT_OK(system("ip addr add dev " netkit_peer " 10.0.0.2/24"), + "addr peer"); + } else { + ASSERT_OK(system("ip link set " netkit_peer " netns foo"), + "move peer"); + ASSERT_OK(system("ip netns exec foo ip link set dev " + netkit_peer " up"), "up peer"); + ASSERT_OK(system("ip netns exec foo ip addr add dev " + netkit_peer " 10.0.0.2/24"), "addr peer"); + } + return err; +} + +static void destroy_netkit(void) +{ + ASSERT_OK(system("ip link del dev " netkit_name), "del primary"); + ASSERT_OK(system("ip netns del foo"), "delete netns"); + ASSERT_EQ(if_nametoindex(netkit_name), 0, netkit_name "_ifindex"); +} + +static int __send_icmp(__u32 dest) +{ + struct sockaddr_in addr; + struct icmphdr icmp; + int sock, ret; + + ret = write_sysctl("/proc/sys/net/ipv4/ping_group_range", "0 0"); + if (!ASSERT_OK(ret, "write_sysctl(net.ipv4.ping_group_range)")) + return ret; + + sock = socket(AF_INET, SOCK_DGRAM, IPPROTO_ICMP); + if (!ASSERT_GE(sock, 0, "icmp_socket")) + return -errno; + + ret = setsockopt(sock, SOL_SOCKET, SO_BINDTODEVICE, + netkit_name, strlen(netkit_name) + 1); + if (!ASSERT_OK(ret, "setsockopt(SO_BINDTODEVICE)")) + goto out; + + memset(&addr, 0, sizeof(addr)); + addr.sin_family = AF_INET; + addr.sin_addr.s_addr = htonl(dest); + + memset(&icmp, 0, sizeof(icmp)); + icmp.type = ICMP_ECHO; + icmp.echo.id = 1234; + icmp.echo.sequence = 1; + + ret = sendto(sock, &icmp, sizeof(icmp), 0, + (struct sockaddr *)&addr, sizeof(addr)); + if (!ASSERT_GE(ret, 0, "icmp_sendto")) + ret = -errno; + else + ret = 0; +out: + close(sock); + return ret; +} + +static int send_icmp(void) +{ + return __send_icmp(ping_addr_neigh); +} + +void serial_test_tc_netkit_basic(void) +{ + LIBBPF_OPTS(bpf_prog_query_opts, optq); + LIBBPF_OPTS(bpf_netkit_opts, optl); + __u32 prog_ids[2], link_ids[2]; + __u32 pid1, pid2, lid1, lid2; + struct test_tc_link *skel; + struct bpf_link *link; + int err, ifindex; + + err = create_netkit(NETKIT_L2, NETKIT_PASS, NETKIT_PASS, + &ifindex, false); + if (err) + return; + + skel = test_tc_link__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + goto cleanup; + + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, + BPF_NETKIT_PRIMARY), 0, "tc1_attach_type"); + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, + BPF_NETKIT_PEER), 0, "tc2_attach_type"); + + err = test_tc_link__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + + pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1)); + pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2)); + + ASSERT_NEQ(pid1, pid2, "prog_ids_1_2"); + + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 0); + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0); + + ASSERT_EQ(skel->bss->seen_tc1, false, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2"); + + link = bpf_program__attach_netkit(skel->progs.tc1, ifindex, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc1 = link; + + lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1)); + + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 1); + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0); + + optq.prog_ids = prog_ids; + optq.link_ids = link_ids; + + memset(prog_ids, 0, sizeof(prog_ids)); + memset(link_ids, 0, sizeof(link_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(ifindex, BPF_NETKIT_PRIMARY, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup; + + ASSERT_EQ(optq.count, 1, "count"); + ASSERT_EQ(optq.revision, 2, "revision"); + ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]"); + ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]"); + ASSERT_EQ(optq.link_ids[1], 0, "link_ids[1]"); + + tc_skel_reset_all_seen(skel); + ASSERT_EQ(send_icmp(), 0, "icmp_pkt"); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2"); + + link = bpf_program__attach_netkit(skel->progs.tc2, ifindex, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc2 = link; + + lid2 = id_from_link_fd(bpf_link__fd(skel->links.tc2)); + ASSERT_NEQ(lid1, lid2, "link_ids_1_2"); + + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 1); + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 1); + + memset(prog_ids, 0, sizeof(prog_ids)); + memset(link_ids, 0, sizeof(link_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(ifindex, BPF_NETKIT_PEER, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup; + + ASSERT_EQ(optq.count, 1, "count"); + ASSERT_EQ(optq.revision, 2, "revision"); + ASSERT_EQ(optq.prog_ids[0], pid2, "prog_ids[0]"); + ASSERT_EQ(optq.link_ids[0], lid2, "link_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]"); + ASSERT_EQ(optq.link_ids[1], 0, "link_ids[1]"); + + tc_skel_reset_all_seen(skel); + ASSERT_EQ(send_icmp(), 0, "icmp_pkt"); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2"); +cleanup: + test_tc_link__destroy(skel); + + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 0); + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0); + destroy_netkit(); +} + +static void serial_test_tc_netkit_multi_links_target(int mode, int target) +{ + LIBBPF_OPTS(bpf_prog_query_opts, optq); + LIBBPF_OPTS(bpf_netkit_opts, optl); + __u32 prog_ids[3], link_ids[3]; + __u32 pid1, pid2, lid1, lid2; + struct test_tc_link *skel; + struct bpf_link *link; + int err, ifindex; + + err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS, + &ifindex, false); + if (err) + return; + + skel = test_tc_link__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + goto cleanup; + + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, + target), 0, "tc1_attach_type"); + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, + target), 0, "tc2_attach_type"); + + err = test_tc_link__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + + pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1)); + pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2)); + + ASSERT_NEQ(pid1, pid2, "prog_ids_1_2"); + + assert_mprog_count_ifindex(ifindex, target, 0); + + ASSERT_EQ(skel->bss->seen_tc1, false, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_eth, false, "seen_eth"); + ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2"); + + link = bpf_program__attach_netkit(skel->progs.tc1, ifindex, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc1 = link; + + lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1)); + + assert_mprog_count_ifindex(ifindex, target, 1); + + optq.prog_ids = prog_ids; + optq.link_ids = link_ids; + + memset(prog_ids, 0, sizeof(prog_ids)); + memset(link_ids, 0, sizeof(link_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(ifindex, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup; + + ASSERT_EQ(optq.count, 1, "count"); + ASSERT_EQ(optq.revision, 2, "revision"); + ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]"); + ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]"); + ASSERT_EQ(optq.link_ids[1], 0, "link_ids[1]"); + + tc_skel_reset_all_seen(skel); + ASSERT_EQ(send_icmp(), 0, "icmp_pkt"); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_eth, true, "seen_eth"); + ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2"); + + LIBBPF_OPTS_RESET(optl, + .flags = BPF_F_BEFORE, + .relative_fd = bpf_program__fd(skel->progs.tc1), + ); + + link = bpf_program__attach_netkit(skel->progs.tc2, ifindex, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc2 = link; + + lid2 = id_from_link_fd(bpf_link__fd(skel->links.tc2)); + ASSERT_NEQ(lid1, lid2, "link_ids_1_2"); + + assert_mprog_count_ifindex(ifindex, target, 2); + + memset(prog_ids, 0, sizeof(prog_ids)); + memset(link_ids, 0, sizeof(link_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(ifindex, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup; + + ASSERT_EQ(optq.count, 2, "count"); + ASSERT_EQ(optq.revision, 3, "revision"); + ASSERT_EQ(optq.prog_ids[0], pid2, "prog_ids[0]"); + ASSERT_EQ(optq.link_ids[0], lid2, "link_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], pid1, "prog_ids[1]"); + ASSERT_EQ(optq.link_ids[1], lid1, "link_ids[1]"); + ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]"); + ASSERT_EQ(optq.link_ids[2], 0, "link_ids[2]"); + + tc_skel_reset_all_seen(skel); + ASSERT_EQ(send_icmp(), 0, "icmp_pkt"); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_eth, true, "seen_eth"); + ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2"); +cleanup: + test_tc_link__destroy(skel); + + assert_mprog_count_ifindex(ifindex, target, 0); + destroy_netkit(); +} + +void serial_test_tc_netkit_multi_links(void) +{ + serial_test_tc_netkit_multi_links_target(NETKIT_L2, BPF_NETKIT_PRIMARY); + serial_test_tc_netkit_multi_links_target(NETKIT_L3, BPF_NETKIT_PRIMARY); + serial_test_tc_netkit_multi_links_target(NETKIT_L2, BPF_NETKIT_PEER); + serial_test_tc_netkit_multi_links_target(NETKIT_L3, BPF_NETKIT_PEER); +} + +static void serial_test_tc_netkit_multi_opts_target(int mode, int target) +{ + LIBBPF_OPTS(bpf_prog_attach_opts, opta); + LIBBPF_OPTS(bpf_prog_detach_opts, optd); + LIBBPF_OPTS(bpf_prog_query_opts, optq); + __u32 pid1, pid2, fd1, fd2; + __u32 prog_ids[3]; + struct test_tc_link *skel; + int err, ifindex; + + err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS, + &ifindex, false); + if (err) + return; + + skel = test_tc_link__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_load")) + goto cleanup; + + fd1 = bpf_program__fd(skel->progs.tc1); + fd2 = bpf_program__fd(skel->progs.tc2); + + pid1 = id_from_prog_fd(fd1); + pid2 = id_from_prog_fd(fd2); + + ASSERT_NEQ(pid1, pid2, "prog_ids_1_2"); + + assert_mprog_count_ifindex(ifindex, target, 0); + + ASSERT_EQ(skel->bss->seen_tc1, false, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_eth, false, "seen_eth"); + ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2"); + + err = bpf_prog_attach_opts(fd1, ifindex, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup; + + assert_mprog_count_ifindex(ifindex, target, 1); + + optq.prog_ids = prog_ids; + + memset(prog_ids, 0, sizeof(prog_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(ifindex, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup_fd1; + + ASSERT_EQ(optq.count, 1, "count"); + ASSERT_EQ(optq.revision, 2, "revision"); + ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]"); + + tc_skel_reset_all_seen(skel); + ASSERT_EQ(send_icmp(), 0, "icmp_pkt"); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_eth, true, "seen_eth"); + ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2"); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_BEFORE, + .relative_fd = fd1, + ); + + err = bpf_prog_attach_opts(fd2, ifindex, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup_fd1; + + assert_mprog_count_ifindex(ifindex, target, 2); + + memset(prog_ids, 0, sizeof(prog_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(ifindex, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup_fd2; + + ASSERT_EQ(optq.count, 2, "count"); + ASSERT_EQ(optq.revision, 3, "revision"); + ASSERT_EQ(optq.prog_ids[0], pid2, "prog_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], pid1, "prog_ids[1]"); + ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]"); + + tc_skel_reset_all_seen(skel); + ASSERT_EQ(send_icmp(), 0, "icmp_pkt"); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_eth, true, "seen_eth"); + ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2"); + +cleanup_fd2: + err = bpf_prog_detach_opts(fd2, ifindex, target, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count_ifindex(ifindex, target, 1); +cleanup_fd1: + err = bpf_prog_detach_opts(fd1, ifindex, target, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count_ifindex(ifindex, target, 0); +cleanup: + test_tc_link__destroy(skel); + + assert_mprog_count_ifindex(ifindex, target, 0); + destroy_netkit(); +} + +void serial_test_tc_netkit_multi_opts(void) +{ + serial_test_tc_netkit_multi_opts_target(NETKIT_L2, BPF_NETKIT_PRIMARY); + serial_test_tc_netkit_multi_opts_target(NETKIT_L3, BPF_NETKIT_PRIMARY); + serial_test_tc_netkit_multi_opts_target(NETKIT_L2, BPF_NETKIT_PEER); + serial_test_tc_netkit_multi_opts_target(NETKIT_L3, BPF_NETKIT_PEER); +} + +void serial_test_tc_netkit_device(void) +{ + LIBBPF_OPTS(bpf_prog_query_opts, optq); + LIBBPF_OPTS(bpf_netkit_opts, optl); + __u32 prog_ids[2], link_ids[2]; + __u32 pid1, pid2, lid1; + struct test_tc_link *skel; + struct bpf_link *link; + int err, ifindex, ifindex2; + + err = create_netkit(NETKIT_L3, NETKIT_PASS, NETKIT_PASS, + &ifindex, true); + if (err) + return; + + ifindex2 = if_nametoindex(netkit_peer); + ASSERT_NEQ(ifindex, ifindex2, "ifindex_1_2"); + + skel = test_tc_link__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + goto cleanup; + + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, + BPF_NETKIT_PRIMARY), 0, "tc1_attach_type"); + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, + BPF_NETKIT_PEER), 0, "tc2_attach_type"); + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc3, + BPF_NETKIT_PRIMARY), 0, "tc3_attach_type"); + + err = test_tc_link__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + + pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1)); + pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2)); + + ASSERT_NEQ(pid1, pid2, "prog_ids_1_2"); + + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 0); + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0); + + ASSERT_EQ(skel->bss->seen_tc1, false, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2"); + + link = bpf_program__attach_netkit(skel->progs.tc1, ifindex, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc1 = link; + + lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1)); + + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 1); + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0); + + optq.prog_ids = prog_ids; + optq.link_ids = link_ids; + + memset(prog_ids, 0, sizeof(prog_ids)); + memset(link_ids, 0, sizeof(link_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(ifindex, BPF_NETKIT_PRIMARY, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup; + + ASSERT_EQ(optq.count, 1, "count"); + ASSERT_EQ(optq.revision, 2, "revision"); + ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]"); + ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]"); + ASSERT_EQ(optq.link_ids[1], 0, "link_ids[1]"); + + tc_skel_reset_all_seen(skel); + ASSERT_EQ(send_icmp(), 0, "icmp_pkt"); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2"); + + memset(prog_ids, 0, sizeof(prog_ids)); + memset(link_ids, 0, sizeof(link_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(ifindex2, BPF_NETKIT_PRIMARY, &optq); + ASSERT_EQ(err, -EACCES, "prog_query_should_fail"); + + err = bpf_prog_query_opts(ifindex2, BPF_NETKIT_PEER, &optq); + ASSERT_EQ(err, -EACCES, "prog_query_should_fail"); + + link = bpf_program__attach_netkit(skel->progs.tc2, ifindex2, &optl); + if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) { + bpf_link__destroy(link); + goto cleanup; + } + + link = bpf_program__attach_netkit(skel->progs.tc3, ifindex2, &optl); + if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) { + bpf_link__destroy(link); + goto cleanup; + } + + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 1); + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0); +cleanup: + test_tc_link__destroy(skel); + + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 0); + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0); + destroy_netkit(); +} + +static void serial_test_tc_netkit_neigh_links_target(int mode, int target) +{ + LIBBPF_OPTS(bpf_prog_query_opts, optq); + LIBBPF_OPTS(bpf_netkit_opts, optl); + __u32 prog_ids[2], link_ids[2]; + __u32 pid1, lid1; + struct test_tc_link *skel; + struct bpf_link *link; + int err, ifindex; + + err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS, + &ifindex, false); + if (err) + return; + + skel = test_tc_link__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + goto cleanup; + + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, + BPF_NETKIT_PRIMARY), 0, "tc1_attach_type"); + + err = test_tc_link__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + + pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1)); + + assert_mprog_count_ifindex(ifindex, target, 0); + + ASSERT_EQ(skel->bss->seen_tc1, false, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_eth, false, "seen_eth"); + + link = bpf_program__attach_netkit(skel->progs.tc1, ifindex, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc1 = link; + + lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1)); + + assert_mprog_count_ifindex(ifindex, target, 1); + + optq.prog_ids = prog_ids; + optq.link_ids = link_ids; + + memset(prog_ids, 0, sizeof(prog_ids)); + memset(link_ids, 0, sizeof(link_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(ifindex, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup; + + ASSERT_EQ(optq.count, 1, "count"); + ASSERT_EQ(optq.revision, 2, "revision"); + ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]"); + ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]"); + ASSERT_EQ(optq.link_ids[1], 0, "link_ids[1]"); + + tc_skel_reset_all_seen(skel); + ASSERT_EQ(__send_icmp(ping_addr_noneigh), 0, "icmp_pkt"); + + ASSERT_EQ(skel->bss->seen_tc1, true /* L2: ARP */, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_eth, mode == NETKIT_L3, "seen_eth"); +cleanup: + test_tc_link__destroy(skel); + + assert_mprog_count_ifindex(ifindex, target, 0); + destroy_netkit(); +} + +void serial_test_tc_netkit_neigh_links(void) +{ + serial_test_tc_netkit_neigh_links_target(NETKIT_L2, BPF_NETKIT_PRIMARY); + serial_test_tc_netkit_neigh_links_target(NETKIT_L3, BPF_NETKIT_PRIMARY); +} diff --git a/tools/testing/selftests/bpf/prog_tests/tc_opts.c b/tools/testing/selftests/bpf/prog_tests/tc_opts.c index ca506d2fcf58..51883ccb8020 100644 --- a/tools/testing/selftests/bpf/prog_tests/tc_opts.c +++ b/tools/testing/selftests/bpf/prog_tests/tc_opts.c @@ -2471,7 +2471,7 @@ static void test_tc_opts_query_target(int target) __u32 fd1, fd2, fd3, fd4, id1, id2, id3, id4; struct test_tc_link *skel; union bpf_attr attr; - __u32 prog_ids[5]; + __u32 prog_ids[10]; int err; skel = test_tc_link__open_and_load(); @@ -2599,6 +2599,135 @@ static void test_tc_opts_query_target(int target) ASSERT_EQ(attr.query.link_ids, 0, "link_ids"); ASSERT_EQ(attr.query.link_attach_flags, 0, "link_attach_flags"); + /* Test 3: Query with smaller prog_ids array */ + memset(&attr, 0, attr_size); + attr.query.target_ifindex = loopback; + attr.query.attach_type = target; + + memset(prog_ids, 0, sizeof(prog_ids)); + attr.query.prog_ids = ptr_to_u64(prog_ids); + attr.query.count = 2; + + err = syscall(__NR_bpf, BPF_PROG_QUERY, &attr, attr_size); + ASSERT_EQ(err, -1, "prog_query_should_fail"); + ASSERT_EQ(errno, ENOSPC, "prog_query_should_fail"); + + ASSERT_EQ(attr.query.count, 4, "count"); + ASSERT_EQ(attr.query.revision, 5, "revision"); + ASSERT_EQ(attr.query.query_flags, 0, "query_flags"); + ASSERT_EQ(attr.query.attach_flags, 0, "attach_flags"); + ASSERT_EQ(attr.query.target_ifindex, loopback, "target_ifindex"); + ASSERT_EQ(attr.query.attach_type, target, "attach_type"); + ASSERT_EQ(attr.query.prog_ids, ptr_to_u64(prog_ids), "prog_ids"); + ASSERT_EQ(prog_ids[0], id1, "prog_ids[0]"); + ASSERT_EQ(prog_ids[1], id2, "prog_ids[1]"); + ASSERT_EQ(prog_ids[2], 0, "prog_ids[2]"); + ASSERT_EQ(prog_ids[3], 0, "prog_ids[3]"); + ASSERT_EQ(prog_ids[4], 0, "prog_ids[4]"); + ASSERT_EQ(attr.query.prog_attach_flags, 0, "prog_attach_flags"); + ASSERT_EQ(attr.query.link_ids, 0, "link_ids"); + ASSERT_EQ(attr.query.link_attach_flags, 0, "link_attach_flags"); + + /* Test 4: Query with larger prog_ids array */ + memset(&attr, 0, attr_size); + attr.query.target_ifindex = loopback; + attr.query.attach_type = target; + + memset(prog_ids, 0, sizeof(prog_ids)); + attr.query.prog_ids = ptr_to_u64(prog_ids); + attr.query.count = 10; + + err = syscall(__NR_bpf, BPF_PROG_QUERY, &attr, attr_size); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup4; + + ASSERT_EQ(attr.query.count, 4, "count"); + ASSERT_EQ(attr.query.revision, 5, "revision"); + ASSERT_EQ(attr.query.query_flags, 0, "query_flags"); + ASSERT_EQ(attr.query.attach_flags, 0, "attach_flags"); + ASSERT_EQ(attr.query.target_ifindex, loopback, "target_ifindex"); + ASSERT_EQ(attr.query.attach_type, target, "attach_type"); + ASSERT_EQ(attr.query.prog_ids, ptr_to_u64(prog_ids), "prog_ids"); + ASSERT_EQ(prog_ids[0], id1, "prog_ids[0]"); + ASSERT_EQ(prog_ids[1], id2, "prog_ids[1]"); + ASSERT_EQ(prog_ids[2], id3, "prog_ids[2]"); + ASSERT_EQ(prog_ids[3], id4, "prog_ids[3]"); + ASSERT_EQ(prog_ids[4], 0, "prog_ids[4]"); + ASSERT_EQ(attr.query.prog_attach_flags, 0, "prog_attach_flags"); + ASSERT_EQ(attr.query.link_ids, 0, "link_ids"); + ASSERT_EQ(attr.query.link_attach_flags, 0, "link_attach_flags"); + + /* Test 5: Query with NULL prog_ids array but with count > 0 */ + memset(&attr, 0, attr_size); + attr.query.target_ifindex = loopback; + attr.query.attach_type = target; + + memset(prog_ids, 0, sizeof(prog_ids)); + attr.query.count = sizeof(prog_ids); + + err = syscall(__NR_bpf, BPF_PROG_QUERY, &attr, attr_size); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup4; + + ASSERT_EQ(attr.query.count, 4, "count"); + ASSERT_EQ(attr.query.revision, 5, "revision"); + ASSERT_EQ(attr.query.query_flags, 0, "query_flags"); + ASSERT_EQ(attr.query.attach_flags, 0, "attach_flags"); + ASSERT_EQ(attr.query.target_ifindex, loopback, "target_ifindex"); + ASSERT_EQ(attr.query.attach_type, target, "attach_type"); + ASSERT_EQ(prog_ids[0], 0, "prog_ids[0]"); + ASSERT_EQ(prog_ids[1], 0, "prog_ids[1]"); + ASSERT_EQ(prog_ids[2], 0, "prog_ids[2]"); + ASSERT_EQ(prog_ids[3], 0, "prog_ids[3]"); + ASSERT_EQ(prog_ids[4], 0, "prog_ids[4]"); + ASSERT_EQ(attr.query.prog_ids, 0, "prog_ids"); + ASSERT_EQ(attr.query.prog_attach_flags, 0, "prog_attach_flags"); + ASSERT_EQ(attr.query.link_ids, 0, "link_ids"); + ASSERT_EQ(attr.query.link_attach_flags, 0, "link_attach_flags"); + + /* Test 6: Query with non-NULL prog_ids array but with count == 0 */ + memset(&attr, 0, attr_size); + attr.query.target_ifindex = loopback; + attr.query.attach_type = target; + + memset(prog_ids, 0, sizeof(prog_ids)); + attr.query.prog_ids = ptr_to_u64(prog_ids); + + err = syscall(__NR_bpf, BPF_PROG_QUERY, &attr, attr_size); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup4; + + ASSERT_EQ(attr.query.count, 4, "count"); + ASSERT_EQ(attr.query.revision, 5, "revision"); + ASSERT_EQ(attr.query.query_flags, 0, "query_flags"); + ASSERT_EQ(attr.query.attach_flags, 0, "attach_flags"); + ASSERT_EQ(attr.query.target_ifindex, loopback, "target_ifindex"); + ASSERT_EQ(attr.query.attach_type, target, "attach_type"); + ASSERT_EQ(prog_ids[0], 0, "prog_ids[0]"); + ASSERT_EQ(prog_ids[1], 0, "prog_ids[1]"); + ASSERT_EQ(prog_ids[2], 0, "prog_ids[2]"); + ASSERT_EQ(prog_ids[3], 0, "prog_ids[3]"); + ASSERT_EQ(prog_ids[4], 0, "prog_ids[4]"); + ASSERT_EQ(attr.query.prog_ids, ptr_to_u64(prog_ids), "prog_ids"); + ASSERT_EQ(attr.query.prog_attach_flags, 0, "prog_attach_flags"); + ASSERT_EQ(attr.query.link_ids, 0, "link_ids"); + ASSERT_EQ(attr.query.link_attach_flags, 0, "link_attach_flags"); + + /* Test 7: Query with invalid flags */ + attr.query.attach_flags = 0; + attr.query.query_flags = 1; + + err = syscall(__NR_bpf, BPF_PROG_QUERY, &attr, attr_size); + ASSERT_EQ(err, -1, "prog_query_should_fail"); + ASSERT_EQ(errno, EINVAL, "prog_query_should_fail"); + + attr.query.attach_flags = 1; + attr.query.query_flags = 0; + + err = syscall(__NR_bpf, BPF_PROG_QUERY, &attr, attr_size); + ASSERT_EQ(err, -1, "prog_query_should_fail"); + ASSERT_EQ(errno, EINVAL, "prog_query_should_fail"); + cleanup4: err = bpf_prog_detach_opts(fd4, loopback, target, &optd); ASSERT_OK(err, "prog_detach"); diff --git a/tools/testing/selftests/bpf/prog_tests/test_bpf_ma.c b/tools/testing/selftests/bpf/prog_tests/test_bpf_ma.c index 0cca4e8ae38e..d3491a84b3b9 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_bpf_ma.c +++ b/tools/testing/selftests/bpf/prog_tests/test_bpf_ma.c @@ -9,9 +9,10 @@ #include "test_bpf_ma.skel.h" -void test_test_bpf_ma(void) +static void do_bpf_ma_test(const char *name) { struct test_bpf_ma *skel; + struct bpf_program *prog; struct btf *btf; int i, err; @@ -34,6 +35,11 @@ void test_test_bpf_ma(void) skel->rodata->data_btf_ids[i] = id; } + prog = bpf_object__find_program_by_name(skel->obj, name); + if (!ASSERT_OK_PTR(prog, "invalid prog name")) + goto out; + bpf_program__set_autoload(prog, true); + err = test_bpf_ma__load(skel); if (!ASSERT_OK(err, "load")) goto out; @@ -48,3 +54,15 @@ void test_test_bpf_ma(void) out: test_bpf_ma__destroy(skel); } + +void test_test_bpf_ma(void) +{ + if (test__start_subtest("batch_alloc_free")) + do_bpf_ma_test("test_batch_alloc_free"); + if (test__start_subtest("free_through_map_free")) + do_bpf_ma_test("test_free_through_map_free"); + if (test__start_subtest("batch_percpu_alloc_free")) + do_bpf_ma_test("test_batch_percpu_alloc_free"); + if (test__start_subtest("percpu_free_through_map_free")) + do_bpf_ma_test("test_percpu_free_through_map_free"); +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task.c b/tools/testing/selftests/bpf/progs/bpf_iter_tasks.c index 96131b9a1caa..96131b9a1caa 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_task.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_tasks.c diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c index 6b9b3c56f009..c20c4e38b71c 100644 --- a/tools/testing/selftests/bpf/progs/iters.c +++ b/tools/testing/selftests/bpf/progs/iters.c @@ -14,6 +14,13 @@ int my_pid; int arr[256]; int small_arr[16] SEC(".data.small_arr"); +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 10); + __type(key, int); + __type(value, int); +} amap SEC(".maps"); + #ifdef REAL_TEST #define MY_PID_GUARD() if (my_pid != (bpf_get_current_pid_tgid() >> 32)) return 0 #else @@ -716,4 +723,692 @@ int iter_pass_iter_ptr_to_subprog(const void *ctx) return 0; } +SEC("?raw_tp") +__failure +__msg("R1 type=scalar expected=fp") +__naked int delayed_read_mark(void) +{ + /* This is equivalent to C program below. + * The call to bpf_iter_num_next() is reachable with r7 values &fp[-16] and 0xdead. + * State with r7=&fp[-16] is visited first and follows r6 != 42 ... continue branch. + * At this point iterator next() call is reached with r7 that has no read mark. + * Loop body with r7=0xdead would only be visited if verifier would decide to continue + * with second loop iteration. Absence of read mark on r7 might affect state + * equivalent logic used for iterator convergence tracking. + * + * r7 = &fp[-16] + * fp[-16] = 0 + * r6 = bpf_get_prandom_u32() + * bpf_iter_num_new(&fp[-8], 0, 10) + * while (bpf_iter_num_next(&fp[-8])) { + * r6++ + * if (r6 != 42) { + * r7 = 0xdead + * continue; + * } + * bpf_probe_read_user(r7, 8, 0xdeadbeef); // this is not safe + * } + * bpf_iter_num_destroy(&fp[-8]) + * return 0 + */ + asm volatile ( + "r7 = r10;" + "r7 += -16;" + "r0 = 0;" + "*(u64 *)(r7 + 0) = r0;" + "call %[bpf_get_prandom_u32];" + "r6 = r0;" + "r1 = r10;" + "r1 += -8;" + "r2 = 0;" + "r3 = 10;" + "call %[bpf_iter_num_new];" + "1:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_next];" + "if r0 == 0 goto 2f;" + "r6 += 1;" + "if r6 != 42 goto 3f;" + "r7 = 0xdead;" + "goto 1b;" + "3:" + "r1 = r7;" + "r2 = 8;" + "r3 = 0xdeadbeef;" + "call %[bpf_probe_read_user];" + "goto 1b;" + "2:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_destroy];" + "r0 = 0;" + "exit;" + : + : __imm(bpf_get_prandom_u32), + __imm(bpf_iter_num_new), + __imm(bpf_iter_num_next), + __imm(bpf_iter_num_destroy), + __imm(bpf_probe_read_user) + : __clobber_all + ); +} + +SEC("?raw_tp") +__failure +__msg("math between fp pointer and register with unbounded") +__naked int delayed_precision_mark(void) +{ + /* This is equivalent to C program below. + * The test is similar to delayed_iter_mark but verifies that incomplete + * precision don't fool verifier. + * The call to bpf_iter_num_next() is reachable with r7 values -16 and -32. + * State with r7=-16 is visited first and follows r6 != 42 ... continue branch. + * At this point iterator next() call is reached with r7 that has no read + * and precision marks. + * Loop body with r7=-32 would only be visited if verifier would decide to continue + * with second loop iteration. Absence of precision mark on r7 might affect state + * equivalent logic used for iterator convergence tracking. + * + * r8 = 0 + * fp[-16] = 0 + * r7 = -16 + * r6 = bpf_get_prandom_u32() + * bpf_iter_num_new(&fp[-8], 0, 10) + * while (bpf_iter_num_next(&fp[-8])) { + * if (r6 != 42) { + * r7 = -32 + * r6 = bpf_get_prandom_u32() + * continue; + * } + * r0 = r10 + * r0 += r7 + * r8 = *(u64 *)(r0 + 0) // this is not safe + * r6 = bpf_get_prandom_u32() + * } + * bpf_iter_num_destroy(&fp[-8]) + * return r8 + */ + asm volatile ( + "r8 = 0;" + "*(u64 *)(r10 - 16) = r8;" + "r7 = -16;" + "call %[bpf_get_prandom_u32];" + "r6 = r0;" + "r1 = r10;" + "r1 += -8;" + "r2 = 0;" + "r3 = 10;" + "call %[bpf_iter_num_new];" + "1:" + "r1 = r10;" + "r1 += -8;\n" + "call %[bpf_iter_num_next];" + "if r0 == 0 goto 2f;" + "if r6 != 42 goto 3f;" + "r7 = -32;" + "call %[bpf_get_prandom_u32];" + "r6 = r0;" + "goto 1b;\n" + "3:" + "r0 = r10;" + "r0 += r7;" + "r8 = *(u64 *)(r0 + 0);" + "call %[bpf_get_prandom_u32];" + "r6 = r0;" + "goto 1b;\n" + "2:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_destroy];" + "r0 = r8;" + "exit;" + : + : __imm(bpf_get_prandom_u32), + __imm(bpf_iter_num_new), + __imm(bpf_iter_num_next), + __imm(bpf_iter_num_destroy), + __imm(bpf_probe_read_user) + : __clobber_all + ); +} + +SEC("?raw_tp") +__failure +__msg("math between fp pointer and register with unbounded") +__flag(BPF_F_TEST_STATE_FREQ) +__naked int loop_state_deps1(void) +{ + /* This is equivalent to C program below. + * + * The case turns out to be tricky in a sense that: + * - states with c=-25 are explored only on a second iteration + * of the outer loop; + * - states with read+precise mark on c are explored only on + * second iteration of the inner loop and in a state which + * is pushed to states stack first. + * + * Depending on the details of iterator convergence logic + * verifier might stop states traversal too early and miss + * unsafe c=-25 memory access. + * + * j = iter_new(); // fp[-16] + * a = 0; // r6 + * b = 0; // r7 + * c = -24; // r8 + * while (iter_next(j)) { + * i = iter_new(); // fp[-8] + * a = 0; // r6 + * b = 0; // r7 + * while (iter_next(i)) { + * if (a == 1) { + * a = 0; + * b = 1; + * } else if (a == 0) { + * a = 1; + * if (random() == 42) + * continue; + * if (b == 1) { + * *(r10 + c) = 7; // this is not safe + * iter_destroy(i); + * iter_destroy(j); + * return; + * } + * } + * } + * iter_destroy(i); + * a = 0; + * b = 0; + * c = -25; + * } + * iter_destroy(j); + * return; + */ + asm volatile ( + "r1 = r10;" + "r1 += -16;" + "r2 = 0;" + "r3 = 10;" + "call %[bpf_iter_num_new];" + "r6 = 0;" + "r7 = 0;" + "r8 = -24;" + "j_loop_%=:" + "r1 = r10;" + "r1 += -16;" + "call %[bpf_iter_num_next];" + "if r0 == 0 goto j_loop_end_%=;" + "r1 = r10;" + "r1 += -8;" + "r2 = 0;" + "r3 = 10;" + "call %[bpf_iter_num_new];" + "r6 = 0;" + "r7 = 0;" + "i_loop_%=:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_next];" + "if r0 == 0 goto i_loop_end_%=;" + "check_one_r6_%=:" + "if r6 != 1 goto check_zero_r6_%=;" + "r6 = 0;" + "r7 = 1;" + "goto i_loop_%=;" + "check_zero_r6_%=:" + "if r6 != 0 goto i_loop_%=;" + "r6 = 1;" + "call %[bpf_get_prandom_u32];" + "if r0 != 42 goto check_one_r7_%=;" + "goto i_loop_%=;" + "check_one_r7_%=:" + "if r7 != 1 goto i_loop_%=;" + "r0 = r10;" + "r0 += r8;" + "r1 = 7;" + "*(u64 *)(r0 + 0) = r1;" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_destroy];" + "r1 = r10;" + "r1 += -16;" + "call %[bpf_iter_num_destroy];" + "r0 = 0;" + "exit;" + "i_loop_end_%=:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_destroy];" + "r6 = 0;" + "r7 = 0;" + "r8 = -25;" + "goto j_loop_%=;" + "j_loop_end_%=:" + "r1 = r10;" + "r1 += -16;" + "call %[bpf_iter_num_destroy];" + "r0 = 0;" + "exit;" + : + : __imm(bpf_get_prandom_u32), + __imm(bpf_iter_num_new), + __imm(bpf_iter_num_next), + __imm(bpf_iter_num_destroy) + : __clobber_all + ); +} + +SEC("?raw_tp") +__failure +__msg("math between fp pointer and register with unbounded") +__flag(BPF_F_TEST_STATE_FREQ) +__naked int loop_state_deps2(void) +{ + /* This is equivalent to C program below. + * + * The case turns out to be tricky in a sense that: + * - states with read+precise mark on c are explored only on a second + * iteration of the first inner loop and in a state which is pushed to + * states stack first. + * - states with c=-25 are explored only on a second iteration of the + * second inner loop and in a state which is pushed to states stack + * first. + * + * Depending on the details of iterator convergence logic + * verifier might stop states traversal too early and miss + * unsafe c=-25 memory access. + * + * j = iter_new(); // fp[-16] + * a = 0; // r6 + * b = 0; // r7 + * c = -24; // r8 + * while (iter_next(j)) { + * i = iter_new(); // fp[-8] + * a = 0; // r6 + * b = 0; // r7 + * while (iter_next(i)) { + * if (a == 1) { + * a = 0; + * b = 1; + * } else if (a == 0) { + * a = 1; + * if (random() == 42) + * continue; + * if (b == 1) { + * *(r10 + c) = 7; // this is not safe + * iter_destroy(i); + * iter_destroy(j); + * return; + * } + * } + * } + * iter_destroy(i); + * i = iter_new(); // fp[-8] + * a = 0; // r6 + * b = 0; // r7 + * while (iter_next(i)) { + * if (a == 1) { + * a = 0; + * b = 1; + * } else if (a == 0) { + * a = 1; + * if (random() == 42) + * continue; + * if (b == 1) { + * a = 0; + * c = -25; + * } + * } + * } + * iter_destroy(i); + * } + * iter_destroy(j); + * return; + */ + asm volatile ( + "r1 = r10;" + "r1 += -16;" + "r2 = 0;" + "r3 = 10;" + "call %[bpf_iter_num_new];" + "r6 = 0;" + "r7 = 0;" + "r8 = -24;" + "j_loop_%=:" + "r1 = r10;" + "r1 += -16;" + "call %[bpf_iter_num_next];" + "if r0 == 0 goto j_loop_end_%=;" + + /* first inner loop */ + "r1 = r10;" + "r1 += -8;" + "r2 = 0;" + "r3 = 10;" + "call %[bpf_iter_num_new];" + "r6 = 0;" + "r7 = 0;" + "i_loop_%=:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_next];" + "if r0 == 0 goto i_loop_end_%=;" + "check_one_r6_%=:" + "if r6 != 1 goto check_zero_r6_%=;" + "r6 = 0;" + "r7 = 1;" + "goto i_loop_%=;" + "check_zero_r6_%=:" + "if r6 != 0 goto i_loop_%=;" + "r6 = 1;" + "call %[bpf_get_prandom_u32];" + "if r0 != 42 goto check_one_r7_%=;" + "goto i_loop_%=;" + "check_one_r7_%=:" + "if r7 != 1 goto i_loop_%=;" + "r0 = r10;" + "r0 += r8;" + "r1 = 7;" + "*(u64 *)(r0 + 0) = r1;" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_destroy];" + "r1 = r10;" + "r1 += -16;" + "call %[bpf_iter_num_destroy];" + "r0 = 0;" + "exit;" + "i_loop_end_%=:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_destroy];" + + /* second inner loop */ + "r1 = r10;" + "r1 += -8;" + "r2 = 0;" + "r3 = 10;" + "call %[bpf_iter_num_new];" + "r6 = 0;" + "r7 = 0;" + "i2_loop_%=:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_next];" + "if r0 == 0 goto i2_loop_end_%=;" + "check2_one_r6_%=:" + "if r6 != 1 goto check2_zero_r6_%=;" + "r6 = 0;" + "r7 = 1;" + "goto i2_loop_%=;" + "check2_zero_r6_%=:" + "if r6 != 0 goto i2_loop_%=;" + "r6 = 1;" + "call %[bpf_get_prandom_u32];" + "if r0 != 42 goto check2_one_r7_%=;" + "goto i2_loop_%=;" + "check2_one_r7_%=:" + "if r7 != 1 goto i2_loop_%=;" + "r6 = 0;" + "r8 = -25;" + "goto i2_loop_%=;" + "i2_loop_end_%=:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_destroy];" + + "r6 = 0;" + "r7 = 0;" + "goto j_loop_%=;" + "j_loop_end_%=:" + "r1 = r10;" + "r1 += -16;" + "call %[bpf_iter_num_destroy];" + "r0 = 0;" + "exit;" + : + : __imm(bpf_get_prandom_u32), + __imm(bpf_iter_num_new), + __imm(bpf_iter_num_next), + __imm(bpf_iter_num_destroy) + : __clobber_all + ); +} + +SEC("?raw_tp") +__success +__naked int triple_continue(void) +{ + /* This is equivalent to C program below. + * High branching factor of the loop body turned out to be + * problematic for one of the iterator convergence tracking + * algorithms explored. + * + * r6 = bpf_get_prandom_u32() + * bpf_iter_num_new(&fp[-8], 0, 10) + * while (bpf_iter_num_next(&fp[-8])) { + * if (bpf_get_prandom_u32() != 42) + * continue; + * if (bpf_get_prandom_u32() != 42) + * continue; + * if (bpf_get_prandom_u32() != 42) + * continue; + * r0 += 0; + * } + * bpf_iter_num_destroy(&fp[-8]) + * return 0 + */ + asm volatile ( + "r1 = r10;" + "r1 += -8;" + "r2 = 0;" + "r3 = 10;" + "call %[bpf_iter_num_new];" + "loop_%=:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_next];" + "if r0 == 0 goto loop_end_%=;" + "call %[bpf_get_prandom_u32];" + "if r0 != 42 goto loop_%=;" + "call %[bpf_get_prandom_u32];" + "if r0 != 42 goto loop_%=;" + "call %[bpf_get_prandom_u32];" + "if r0 != 42 goto loop_%=;" + "r0 += 0;" + "goto loop_%=;" + "loop_end_%=:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_destroy];" + "r0 = 0;" + "exit;" + : + : __imm(bpf_get_prandom_u32), + __imm(bpf_iter_num_new), + __imm(bpf_iter_num_next), + __imm(bpf_iter_num_destroy) + : __clobber_all + ); +} + +SEC("?raw_tp") +__success +__naked int widen_spill(void) +{ + /* This is equivalent to C program below. + * The counter is stored in fp[-16], if this counter is not widened + * verifier states representing loop iterations would never converge. + * + * fp[-16] = 0 + * bpf_iter_num_new(&fp[-8], 0, 10) + * while (bpf_iter_num_next(&fp[-8])) { + * r0 = fp[-16]; + * r0 += 1; + * fp[-16] = r0; + * } + * bpf_iter_num_destroy(&fp[-8]) + * return 0 + */ + asm volatile ( + "r0 = 0;" + "*(u64 *)(r10 - 16) = r0;" + "r1 = r10;" + "r1 += -8;" + "r2 = 0;" + "r3 = 10;" + "call %[bpf_iter_num_new];" + "loop_%=:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_next];" + "if r0 == 0 goto loop_end_%=;" + "r0 = *(u64 *)(r10 - 16);" + "r0 += 1;" + "*(u64 *)(r10 - 16) = r0;" + "goto loop_%=;" + "loop_end_%=:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_destroy];" + "r0 = 0;" + "exit;" + : + : __imm(bpf_iter_num_new), + __imm(bpf_iter_num_next), + __imm(bpf_iter_num_destroy) + : __clobber_all + ); +} + +SEC("raw_tp") +__success +__naked int checkpoint_states_deletion(void) +{ + /* This is equivalent to C program below. + * + * int *a, *b, *c, *d, *e, *f; + * int i, sum = 0; + * bpf_for(i, 0, 10) { + * a = bpf_map_lookup_elem(&amap, &i); + * b = bpf_map_lookup_elem(&amap, &i); + * c = bpf_map_lookup_elem(&amap, &i); + * d = bpf_map_lookup_elem(&amap, &i); + * e = bpf_map_lookup_elem(&amap, &i); + * f = bpf_map_lookup_elem(&amap, &i); + * if (a) sum += 1; + * if (b) sum += 1; + * if (c) sum += 1; + * if (d) sum += 1; + * if (e) sum += 1; + * if (f) sum += 1; + * } + * return 0; + * + * The body of the loop spawns multiple simulation paths + * with different combination of NULL/non-NULL information for a/b/c/d/e/f. + * Each combination is unique from states_equal() point of view. + * Explored states checkpoint is created after each iterator next call. + * Iterator convergence logic expects that eventually current state + * would get equal to one of the explored states and thus loop + * exploration would be finished (at-least for a specific path). + * Verifier evicts explored states with high miss to hit ratio + * to to avoid comparing current state with too many explored + * states per instruction. + * This test is designed to "stress test" eviction policy defined using formula: + * + * sl->miss_cnt > sl->hit_cnt * N + N // if true sl->state is evicted + * + * Currently N is set to 64, which allows for 6 variables in this test. + */ + asm volatile ( + "r6 = 0;" /* a */ + "r7 = 0;" /* b */ + "r8 = 0;" /* c */ + "*(u64 *)(r10 - 24) = r6;" /* d */ + "*(u64 *)(r10 - 32) = r6;" /* e */ + "*(u64 *)(r10 - 40) = r6;" /* f */ + "r9 = 0;" /* sum */ + "r1 = r10;" + "r1 += -8;" + "r2 = 0;" + "r3 = 10;" + "call %[bpf_iter_num_new];" + "loop_%=:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_next];" + "if r0 == 0 goto loop_end_%=;" + + "*(u64 *)(r10 - 16) = r0;" + + "r1 = %[amap] ll;" + "r2 = r10;" + "r2 += -16;" + "call %[bpf_map_lookup_elem];" + "r6 = r0;" + + "r1 = %[amap] ll;" + "r2 = r10;" + "r2 += -16;" + "call %[bpf_map_lookup_elem];" + "r7 = r0;" + + "r1 = %[amap] ll;" + "r2 = r10;" + "r2 += -16;" + "call %[bpf_map_lookup_elem];" + "r8 = r0;" + + "r1 = %[amap] ll;" + "r2 = r10;" + "r2 += -16;" + "call %[bpf_map_lookup_elem];" + "*(u64 *)(r10 - 24) = r0;" + + "r1 = %[amap] ll;" + "r2 = r10;" + "r2 += -16;" + "call %[bpf_map_lookup_elem];" + "*(u64 *)(r10 - 32) = r0;" + + "r1 = %[amap] ll;" + "r2 = r10;" + "r2 += -16;" + "call %[bpf_map_lookup_elem];" + "*(u64 *)(r10 - 40) = r0;" + + "if r6 == 0 goto +1;" + "r9 += 1;" + "if r7 == 0 goto +1;" + "r9 += 1;" + "if r8 == 0 goto +1;" + "r9 += 1;" + "r0 = *(u64 *)(r10 - 24);" + "if r0 == 0 goto +1;" + "r9 += 1;" + "r0 = *(u64 *)(r10 - 32);" + "if r0 == 0 goto +1;" + "r9 += 1;" + "r0 = *(u64 *)(r10 - 40);" + "if r0 == 0 goto +1;" + "r9 += 1;" + + "goto loop_%=;" + "loop_end_%=:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_destroy];" + "r0 = 0;" + "exit;" + : + : __imm(bpf_map_lookup_elem), + __imm(bpf_iter_num_new), + __imm(bpf_iter_num_next), + __imm(bpf_iter_num_destroy), + __imm_addr(amap) + : __clobber_all + ); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/iters_css.c b/tools/testing/selftests/bpf/progs/iters_css.c new file mode 100644 index 000000000000..ec1f6c2f590b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/iters_css.c @@ -0,0 +1,72 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023 Chuyi Zhou <zhouchuyi@bytedance.com> */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_misc.h" +#include "bpf_experimental.h" + +char _license[] SEC("license") = "GPL"; + +pid_t target_pid; +u64 root_cg_id, leaf_cg_id; +u64 first_cg_id, last_cg_id; + +int pre_order_cnt, post_order_cnt, tree_high; + +struct cgroup *bpf_cgroup_from_id(u64 cgid) __ksym; +void bpf_cgroup_release(struct cgroup *p) __ksym; +void bpf_rcu_read_lock(void) __ksym; +void bpf_rcu_read_unlock(void) __ksym; + +SEC("fentry.s/" SYS_PREFIX "sys_getpgid") +int iter_css_for_each(const void *ctx) +{ + struct task_struct *cur_task = bpf_get_current_task_btf(); + struct cgroup_subsys_state *root_css, *leaf_css, *pos; + struct cgroup *root_cgrp, *leaf_cgrp, *cur_cgrp; + + if (cur_task->pid != target_pid) + return 0; + + root_cgrp = bpf_cgroup_from_id(root_cg_id); + + if (!root_cgrp) + return 0; + + leaf_cgrp = bpf_cgroup_from_id(leaf_cg_id); + + if (!leaf_cgrp) { + bpf_cgroup_release(root_cgrp); + return 0; + } + root_css = &root_cgrp->self; + leaf_css = &leaf_cgrp->self; + pre_order_cnt = post_order_cnt = tree_high = 0; + first_cg_id = last_cg_id = 0; + + bpf_rcu_read_lock(); + bpf_for_each(css, pos, root_css, BPF_CGROUP_ITER_DESCENDANTS_POST) { + cur_cgrp = pos->cgroup; + post_order_cnt++; + last_cg_id = cur_cgrp->kn->id; + } + + bpf_for_each(css, pos, root_css, BPF_CGROUP_ITER_DESCENDANTS_PRE) { + cur_cgrp = pos->cgroup; + pre_order_cnt++; + if (!first_cg_id) + first_cg_id = cur_cgrp->kn->id; + } + + bpf_for_each(css, pos, leaf_css, BPF_CGROUP_ITER_ANCESTORS_UP) + tree_high++; + + bpf_for_each(css, pos, root_css, BPF_CGROUP_ITER_ANCESTORS_UP) + tree_high--; + bpf_rcu_read_unlock(); + bpf_cgroup_release(root_cgrp); + bpf_cgroup_release(leaf_cgrp); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/iters_css_task.c b/tools/testing/selftests/bpf/progs/iters_css_task.c new file mode 100644 index 000000000000..5089ce384a1c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/iters_css_task.c @@ -0,0 +1,47 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023 Chuyi Zhou <zhouchuyi@bytedance.com> */ + +#include "vmlinux.h" +#include <errno.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_misc.h" +#include "bpf_experimental.h" + +char _license[] SEC("license") = "GPL"; + +struct cgroup *bpf_cgroup_from_id(u64 cgid) __ksym; +void bpf_cgroup_release(struct cgroup *p) __ksym; + +pid_t target_pid; +int css_task_cnt; +u64 cg_id; + +SEC("lsm/file_mprotect") +int BPF_PROG(iter_css_task_for_each, struct vm_area_struct *vma, + unsigned long reqprot, unsigned long prot, int ret) +{ + struct task_struct *cur_task = bpf_get_current_task_btf(); + struct cgroup_subsys_state *css; + struct task_struct *task; + struct cgroup *cgrp; + + if (cur_task->pid != target_pid) + return ret; + + cgrp = bpf_cgroup_from_id(cg_id); + + if (!cgrp) + return -EPERM; + + css = &cgrp->self; + css_task_cnt = 0; + + bpf_for_each(css_task, task, css, CSS_TASK_ITER_PROCS) + if (task->pid == target_pid) + css_task_cnt++; + + bpf_cgroup_release(cgrp); + + return -EPERM; +} diff --git a/tools/testing/selftests/bpf/progs/iters_task.c b/tools/testing/selftests/bpf/progs/iters_task.c new file mode 100644 index 000000000000..c9b4055cd410 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/iters_task.c @@ -0,0 +1,41 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023 Chuyi Zhou <zhouchuyi@bytedance.com> */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_misc.h" +#include "bpf_experimental.h" + +char _license[] SEC("license") = "GPL"; + +pid_t target_pid; +int procs_cnt, threads_cnt, proc_threads_cnt; + +void bpf_rcu_read_lock(void) __ksym; +void bpf_rcu_read_unlock(void) __ksym; + +SEC("fentry.s/" SYS_PREFIX "sys_getpgid") +int iter_task_for_each_sleep(void *ctx) +{ + struct task_struct *cur_task = bpf_get_current_task_btf(); + struct task_struct *pos; + + if (cur_task->pid != target_pid) + return 0; + procs_cnt = threads_cnt = proc_threads_cnt = 0; + + bpf_rcu_read_lock(); + bpf_for_each(task, pos, NULL, BPF_TASK_ITER_ALL_PROCS) + if (pos->pid == target_pid) + procs_cnt++; + + bpf_for_each(task, pos, cur_task, BPF_TASK_ITER_PROC_THREADS) + proc_threads_cnt++; + + bpf_for_each(task, pos, NULL, BPF_TASK_ITER_ALL_THREADS) + if (pos->tgid == target_pid) + threads_cnt++; + bpf_rcu_read_unlock(); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/iters_task_failure.c b/tools/testing/selftests/bpf/progs/iters_task_failure.c new file mode 100644 index 000000000000..c3bf96a67dba --- /dev/null +++ b/tools/testing/selftests/bpf/progs/iters_task_failure.c @@ -0,0 +1,105 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023 Chuyi Zhou <zhouchuyi@bytedance.com> */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_misc.h" +#include "bpf_experimental.h" + +char _license[] SEC("license") = "GPL"; + +struct cgroup *bpf_cgroup_from_id(u64 cgid) __ksym; +void bpf_cgroup_release(struct cgroup *p) __ksym; +void bpf_rcu_read_lock(void) __ksym; +void bpf_rcu_read_unlock(void) __ksym; + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +__failure __msg("expected an RCU CS when using bpf_iter_task_next") +int BPF_PROG(iter_tasks_without_lock) +{ + struct task_struct *pos; + + bpf_for_each(task, pos, NULL, BPF_TASK_ITER_ALL_PROCS) { + + } + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +__failure __msg("expected an RCU CS when using bpf_iter_css_next") +int BPF_PROG(iter_css_without_lock) +{ + u64 cg_id = bpf_get_current_cgroup_id(); + struct cgroup *cgrp = bpf_cgroup_from_id(cg_id); + struct cgroup_subsys_state *root_css, *pos; + + if (!cgrp) + return 0; + root_css = &cgrp->self; + + bpf_for_each(css, pos, root_css, BPF_CGROUP_ITER_DESCENDANTS_POST) { + + } + bpf_cgroup_release(cgrp); + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +__failure __msg("expected an RCU CS when using bpf_iter_task_next") +int BPF_PROG(iter_tasks_lock_and_unlock) +{ + struct task_struct *pos; + + bpf_rcu_read_lock(); + bpf_for_each(task, pos, NULL, BPF_TASK_ITER_ALL_PROCS) { + bpf_rcu_read_unlock(); + + bpf_rcu_read_lock(); + } + bpf_rcu_read_unlock(); + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +__failure __msg("expected an RCU CS when using bpf_iter_css_next") +int BPF_PROG(iter_css_lock_and_unlock) +{ + u64 cg_id = bpf_get_current_cgroup_id(); + struct cgroup *cgrp = bpf_cgroup_from_id(cg_id); + struct cgroup_subsys_state *root_css, *pos; + + if (!cgrp) + return 0; + root_css = &cgrp->self; + + bpf_rcu_read_lock(); + bpf_for_each(css, pos, root_css, BPF_CGROUP_ITER_DESCENDANTS_POST) { + bpf_rcu_read_unlock(); + + bpf_rcu_read_lock(); + } + bpf_rcu_read_unlock(); + bpf_cgroup_release(cgrp); + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +__failure __msg("css_task_iter is only allowed in bpf_lsm and bpf iter-s") +int BPF_PROG(iter_css_task_for_each) +{ + u64 cg_id = bpf_get_current_cgroup_id(); + struct cgroup *cgrp = bpf_cgroup_from_id(cg_id); + struct cgroup_subsys_state *css; + struct task_struct *task; + + if (cgrp == NULL) + return 0; + css = &cgrp->self; + + bpf_for_each(css_task, task, css, CSS_TASK_ITER_PROCS) { + + } + bpf_cgroup_release(cgrp); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/iters_task_vma.c b/tools/testing/selftests/bpf/progs/iters_task_vma.c index 44edecfdfaee..e085a51d153e 100644 --- a/tools/testing/selftests/bpf/progs/iters_task_vma.c +++ b/tools/testing/selftests/bpf/progs/iters_task_vma.c @@ -30,6 +30,7 @@ int iter_task_vma_for_each(const void *ctx) bpf_for_each(task_vma, vma, task, 0) { if (seen >= 1000) break; + barrier_var(seen); vm_ranges[seen].vm_start = vma->vm_start; vm_ranges[seen].vm_end = vma->vm_end; diff --git a/tools/testing/selftests/bpf/progs/linked_list_fail.c b/tools/testing/selftests/bpf/progs/linked_list_fail.c index f4c63daba229..6438982b928b 100644 --- a/tools/testing/selftests/bpf/progs/linked_list_fail.c +++ b/tools/testing/selftests/bpf/progs/linked_list_fail.c @@ -591,7 +591,9 @@ int pop_ptr_off(void *(*op)(void *head)) n = op(&p->head); bpf_spin_unlock(&p->lock); - bpf_this_cpu_ptr(n); + if (!n) + return 0; + bpf_spin_lock((void *)n); return 0; } diff --git a/tools/testing/selftests/bpf/progs/test_bpf_ma.c b/tools/testing/selftests/bpf/progs/test_bpf_ma.c index ecde41ae0fc8..b685a4aba6bd 100644 --- a/tools/testing/selftests/bpf/progs/test_bpf_ma.c +++ b/tools/testing/selftests/bpf/progs/test_bpf_ma.c @@ -37,10 +37,20 @@ int pid = 0; __type(key, int); \ __type(value, struct map_value_##_size); \ __uint(max_entries, 128); \ - } array_##_size SEC(".maps"); + } array_##_size SEC(".maps") -static __always_inline void batch_alloc_free(struct bpf_map *map, unsigned int batch, - unsigned int idx) +#define DEFINE_ARRAY_WITH_PERCPU_KPTR(_size) \ + struct map_value_percpu_##_size { \ + struct bin_data_##_size __percpu_kptr * data; \ + }; \ + struct { \ + __uint(type, BPF_MAP_TYPE_ARRAY); \ + __type(key, int); \ + __type(value, struct map_value_percpu_##_size); \ + __uint(max_entries, 128); \ + } array_percpu_##_size SEC(".maps") + +static __always_inline void batch_alloc(struct bpf_map *map, unsigned int batch, unsigned int idx) { struct generic_map_value *value; unsigned int i, key; @@ -65,6 +75,14 @@ static __always_inline void batch_alloc_free(struct bpf_map *map, unsigned int b return; } } +} + +static __always_inline void batch_free(struct bpf_map *map, unsigned int batch, unsigned int idx) +{ + struct generic_map_value *value; + unsigned int i, key; + void *old; + for (i = 0; i < batch; i++) { key = i; value = bpf_map_lookup_elem(map, &key); @@ -81,8 +99,72 @@ static __always_inline void batch_alloc_free(struct bpf_map *map, unsigned int b } } +static __always_inline void batch_percpu_alloc(struct bpf_map *map, unsigned int batch, + unsigned int idx) +{ + struct generic_map_value *value; + unsigned int i, key; + void *old, *new; + + for (i = 0; i < batch; i++) { + key = i; + value = bpf_map_lookup_elem(map, &key); + if (!value) { + err = 1; + return; + } + /* per-cpu allocator may not be able to refill in time */ + new = bpf_percpu_obj_new_impl(data_btf_ids[idx], NULL); + if (!new) + continue; + + old = bpf_kptr_xchg(&value->data, new); + if (old) { + bpf_percpu_obj_drop(old); + err = 2; + return; + } + } +} + +static __always_inline void batch_percpu_free(struct bpf_map *map, unsigned int batch, + unsigned int idx) +{ + struct generic_map_value *value; + unsigned int i, key; + void *old; + + for (i = 0; i < batch; i++) { + key = i; + value = bpf_map_lookup_elem(map, &key); + if (!value) { + err = 3; + return; + } + old = bpf_kptr_xchg(&value->data, NULL); + if (!old) + continue; + bpf_percpu_obj_drop(old); + } +} + +#define CALL_BATCH_ALLOC(size, batch, idx) \ + batch_alloc((struct bpf_map *)(&array_##size), batch, idx) + #define CALL_BATCH_ALLOC_FREE(size, batch, idx) \ - batch_alloc_free((struct bpf_map *)(&array_##size), batch, idx) + do { \ + batch_alloc((struct bpf_map *)(&array_##size), batch, idx); \ + batch_free((struct bpf_map *)(&array_##size), batch, idx); \ + } while (0) + +#define CALL_BATCH_PERCPU_ALLOC(size, batch, idx) \ + batch_percpu_alloc((struct bpf_map *)(&array_percpu_##size), batch, idx) + +#define CALL_BATCH_PERCPU_ALLOC_FREE(size, batch, idx) \ + do { \ + batch_percpu_alloc((struct bpf_map *)(&array_percpu_##size), batch, idx); \ + batch_percpu_free((struct bpf_map *)(&array_percpu_##size), batch, idx); \ + } while (0) DEFINE_ARRAY_WITH_KPTR(8); DEFINE_ARRAY_WITH_KPTR(16); @@ -97,8 +179,21 @@ DEFINE_ARRAY_WITH_KPTR(1024); DEFINE_ARRAY_WITH_KPTR(2048); DEFINE_ARRAY_WITH_KPTR(4096); -SEC("fentry/" SYS_PREFIX "sys_nanosleep") -int test_bpf_mem_alloc_free(void *ctx) +/* per-cpu kptr doesn't support bin_data_8 which is a zero-sized array */ +DEFINE_ARRAY_WITH_PERCPU_KPTR(16); +DEFINE_ARRAY_WITH_PERCPU_KPTR(32); +DEFINE_ARRAY_WITH_PERCPU_KPTR(64); +DEFINE_ARRAY_WITH_PERCPU_KPTR(96); +DEFINE_ARRAY_WITH_PERCPU_KPTR(128); +DEFINE_ARRAY_WITH_PERCPU_KPTR(192); +DEFINE_ARRAY_WITH_PERCPU_KPTR(256); +DEFINE_ARRAY_WITH_PERCPU_KPTR(512); +DEFINE_ARRAY_WITH_PERCPU_KPTR(1024); +DEFINE_ARRAY_WITH_PERCPU_KPTR(2048); +DEFINE_ARRAY_WITH_PERCPU_KPTR(4096); + +SEC("?fentry/" SYS_PREFIX "sys_nanosleep") +int test_batch_alloc_free(void *ctx) { if ((u32)bpf_get_current_pid_tgid() != pid) return 0; @@ -121,3 +216,76 @@ int test_bpf_mem_alloc_free(void *ctx) return 0; } + +SEC("?fentry/" SYS_PREFIX "sys_nanosleep") +int test_free_through_map_free(void *ctx) +{ + if ((u32)bpf_get_current_pid_tgid() != pid) + return 0; + + /* Alloc 128 8-bytes objects in batch to trigger refilling, + * then free these objects through map free. + */ + CALL_BATCH_ALLOC(8, 128, 0); + CALL_BATCH_ALLOC(16, 128, 1); + CALL_BATCH_ALLOC(32, 128, 2); + CALL_BATCH_ALLOC(64, 128, 3); + CALL_BATCH_ALLOC(96, 128, 4); + CALL_BATCH_ALLOC(128, 128, 5); + CALL_BATCH_ALLOC(192, 128, 6); + CALL_BATCH_ALLOC(256, 128, 7); + CALL_BATCH_ALLOC(512, 64, 8); + CALL_BATCH_ALLOC(1024, 32, 9); + CALL_BATCH_ALLOC(2048, 16, 10); + CALL_BATCH_ALLOC(4096, 8, 11); + + return 0; +} + +SEC("?fentry/" SYS_PREFIX "sys_nanosleep") +int test_batch_percpu_alloc_free(void *ctx) +{ + if ((u32)bpf_get_current_pid_tgid() != pid) + return 0; + + /* Alloc 128 16-bytes per-cpu objects in batch to trigger refilling, + * then free 128 16-bytes per-cpu objects in batch to trigger freeing. + */ + CALL_BATCH_PERCPU_ALLOC_FREE(16, 128, 1); + CALL_BATCH_PERCPU_ALLOC_FREE(32, 128, 2); + CALL_BATCH_PERCPU_ALLOC_FREE(64, 128, 3); + CALL_BATCH_PERCPU_ALLOC_FREE(96, 128, 4); + CALL_BATCH_PERCPU_ALLOC_FREE(128, 128, 5); + CALL_BATCH_PERCPU_ALLOC_FREE(192, 128, 6); + CALL_BATCH_PERCPU_ALLOC_FREE(256, 128, 7); + CALL_BATCH_PERCPU_ALLOC_FREE(512, 64, 8); + CALL_BATCH_PERCPU_ALLOC_FREE(1024, 32, 9); + CALL_BATCH_PERCPU_ALLOC_FREE(2048, 16, 10); + CALL_BATCH_PERCPU_ALLOC_FREE(4096, 8, 11); + + return 0; +} + +SEC("?fentry/" SYS_PREFIX "sys_nanosleep") +int test_percpu_free_through_map_free(void *ctx) +{ + if ((u32)bpf_get_current_pid_tgid() != pid) + return 0; + + /* Alloc 128 16-bytes per-cpu objects in batch to trigger refilling, + * then free these object through map free. + */ + CALL_BATCH_PERCPU_ALLOC(16, 128, 1); + CALL_BATCH_PERCPU_ALLOC(32, 128, 2); + CALL_BATCH_PERCPU_ALLOC(64, 128, 3); + CALL_BATCH_PERCPU_ALLOC(96, 128, 4); + CALL_BATCH_PERCPU_ALLOC(128, 128, 5); + CALL_BATCH_PERCPU_ALLOC(192, 128, 6); + CALL_BATCH_PERCPU_ALLOC(256, 128, 7); + CALL_BATCH_PERCPU_ALLOC(512, 64, 8); + CALL_BATCH_PERCPU_ALLOC(1024, 32, 9); + CALL_BATCH_PERCPU_ALLOC(2048, 16, 10); + CALL_BATCH_PERCPU_ALLOC(4096, 8, 11); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_task_under_cgroup.c b/tools/testing/selftests/bpf/progs/test_task_under_cgroup.c index 56cdc0a553f0..7e750309ce27 100644 --- a/tools/testing/selftests/bpf/progs/test_task_under_cgroup.c +++ b/tools/testing/selftests/bpf/progs/test_task_under_cgroup.c @@ -18,7 +18,7 @@ const volatile __u64 cgid; int remote_pid; SEC("tp_btf/task_newtask") -int BPF_PROG(handle__task_newtask, struct task_struct *task, u64 clone_flags) +int BPF_PROG(tp_btf_run, struct task_struct *task, u64 clone_flags) { struct cgroup *cgrp = NULL; struct task_struct *acquired; @@ -48,4 +48,30 @@ out: return 0; } +SEC("lsm.s/bpf") +int BPF_PROG(lsm_run, int cmd, union bpf_attr *attr, unsigned int size) +{ + struct cgroup *cgrp = NULL; + struct task_struct *task; + int ret = 0; + + task = bpf_get_current_task_btf(); + if (local_pid != task->pid) + return 0; + + if (cmd != BPF_LINK_CREATE) + return 0; + + /* 1 is the root cgroup */ + cgrp = bpf_cgroup_from_id(1); + if (!cgrp) + goto out; + if (!bpf_task_under_cgroup(task, cgrp)) + ret = -1; + bpf_cgroup_release(cgrp); + +out: + return ret; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tc_link.c b/tools/testing/selftests/bpf/progs/test_tc_link.c index 30e7124c49a1..992400acb957 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_link.c +++ b/tools/testing/selftests/bpf/progs/test_tc_link.c @@ -1,7 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2023 Isovalent */ #include <stdbool.h> + #include <linux/bpf.h> +#include <linux/if_ether.h> + +#include <bpf/bpf_endian.h> #include <bpf/bpf_helpers.h> char LICENSE[] SEC("license") = "GPL"; @@ -12,10 +16,19 @@ bool seen_tc3; bool seen_tc4; bool seen_tc5; bool seen_tc6; +bool seen_eth; SEC("tc/ingress") int tc1(struct __sk_buff *skb) { + struct ethhdr eth = {}; + + if (skb->protocol != __bpf_constant_htons(ETH_P_IP)) + goto out; + if (bpf_skb_load_bytes(skb, 0, ð, sizeof(eth))) + goto out; + seen_eth = eth.h_proto == bpf_htons(ETH_P_IP); +out: seen_tc1 = true; return TCX_NEXT; } diff --git a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c index b2dfd7066c6e..f6d1cc9ad892 100644 --- a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c +++ b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c @@ -21,7 +21,7 @@ extern int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx, extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, __u32 *hash, enum xdp_rss_hash_type *rss_type) __ksym; -SEC("xdp") +SEC("xdp.frags") int rx(struct xdp_md *ctx) { void *data, *data_meta, *data_end; diff --git a/tools/testing/selftests/bpf/unpriv_helpers.c b/tools/testing/selftests/bpf/unpriv_helpers.c index 2a6efbd0401e..b6d016461fb0 100644 --- a/tools/testing/selftests/bpf/unpriv_helpers.c +++ b/tools/testing/selftests/bpf/unpriv_helpers.c @@ -4,9 +4,40 @@ #include <stdlib.h> #include <error.h> #include <stdio.h> +#include <string.h> +#include <unistd.h> +#include <fcntl.h> #include "unpriv_helpers.h" +static bool get_mitigations_off(void) +{ + char cmdline[4096], *c; + int fd, ret = false; + + fd = open("/proc/cmdline", O_RDONLY); + if (fd < 0) { + perror("open /proc/cmdline"); + return false; + } + + if (read(fd, cmdline, sizeof(cmdline) - 1) < 0) { + perror("read /proc/cmdline"); + goto out; + } + + cmdline[sizeof(cmdline) - 1] = '\0'; + for (c = strtok(cmdline, " \n"); c; c = strtok(NULL, " \n")) { + if (strncmp(c, "mitigations=off", strlen(c))) + continue; + ret = true; + break; + } +out: + close(fd); + return ret; +} + bool get_unpriv_disabled(void) { bool disabled; @@ -22,5 +53,5 @@ bool get_unpriv_disabled(void) disabled = true; } - return disabled; + return disabled ? true : get_mitigations_off(); } diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c index 17c980138796..17c0f92ff160 100644 --- a/tools/testing/selftests/bpf/xdp_hw_metadata.c +++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c @@ -26,6 +26,7 @@ #include <linux/sockios.h> #include <sys/mman.h> #include <net/if.h> +#include <ctype.h> #include <poll.h> #include <time.h> @@ -47,6 +48,7 @@ struct xsk { }; struct xdp_hw_metadata *bpf_obj; +__u16 bind_flags = XDP_COPY; struct xsk *rx_xsk; const char *ifname; int ifindex; @@ -60,7 +62,7 @@ static int open_xsk(int ifindex, struct xsk *xsk, __u32 queue_id) const struct xsk_socket_config socket_config = { .rx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS, .tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS, - .bind_flags = XDP_COPY, + .bind_flags = bind_flags, }; const struct xsk_umem_config umem_config = { .fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS, @@ -263,11 +265,14 @@ static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd, clockid_t verify_skb_metadata(server_fd); for (i = 0; i < rxq; i++) { + bool first_seg = true; + bool is_eop = true; + if (fds[i].revents == 0) continue; struct xsk *xsk = &rx_xsk[i]; - +peek: ret = xsk_ring_cons__peek(&xsk->rx, 1, &idx); printf("xsk_ring_cons__peek: %d\n", ret); if (ret != 1) @@ -276,12 +281,19 @@ static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd, clockid_t rx_desc = xsk_ring_cons__rx_desc(&xsk->rx, idx); comp_addr = xsk_umem__extract_addr(rx_desc->addr); addr = xsk_umem__add_offset_to_addr(rx_desc->addr); - printf("%p: rx_desc[%u]->addr=%llx addr=%llx comp_addr=%llx\n", - xsk, idx, rx_desc->addr, addr, comp_addr); - verify_xdp_metadata(xsk_umem__get_data(xsk->umem_area, addr), - clock_id); + is_eop = !(rx_desc->options & XDP_PKT_CONTD); + printf("%p: rx_desc[%u]->addr=%llx addr=%llx comp_addr=%llx%s\n", + xsk, idx, rx_desc->addr, addr, comp_addr, is_eop ? " EoP" : ""); + if (first_seg) { + verify_xdp_metadata(xsk_umem__get_data(xsk->umem_area, addr), + clock_id); + first_seg = false; + } + xsk_ring_cons__release(&xsk->rx, 1); refill_rx(xsk, comp_addr); + if (!is_eop) + goto peek; } } @@ -404,6 +416,53 @@ static void timestamping_enable(int fd, int val) error(1, errno, "setsockopt(SO_TIMESTAMPING)"); } +static void print_usage(void) +{ + const char *usage = + "Usage: xdp_hw_metadata [OPTIONS] [IFNAME]\n" + " -m Enable multi-buffer XDP for larger MTU\n" + " -h Display this help and exit\n\n" + "Generate test packets on the other machine with:\n" + " echo -n xdp | nc -u -q1 <dst_ip> 9091\n"; + + printf("%s", usage); +} + +static void read_args(int argc, char *argv[]) +{ + char opt; + + while ((opt = getopt(argc, argv, "mh")) != -1) { + switch (opt) { + case 'm': + bind_flags |= XDP_USE_SG; + break; + case 'h': + print_usage(); + exit(0); + case '?': + if (isprint(optopt)) + fprintf(stderr, "Unknown option: -%c\n", optopt); + fallthrough; + default: + print_usage(); + error(-1, opterr, "Command line options error"); + } + } + + if (optind >= argc) { + fprintf(stderr, "No device name provided\n"); + print_usage(); + exit(-1); + } + + ifname = argv[optind]; + ifindex = if_nametoindex(ifname); + + if (!ifname) + error(-1, errno, "Invalid interface name"); +} + int main(int argc, char *argv[]) { clockid_t clock_id = CLOCK_TAI; @@ -413,13 +472,8 @@ int main(int argc, char *argv[]) struct bpf_program *prog; - if (argc != 2) { - fprintf(stderr, "pass device name\n"); - return -1; - } + read_args(argc, argv); - ifname = argv[1]; - ifindex = if_nametoindex(ifname); rxq = rxq_num(ifname); printf("rxq: %d\n", rxq); |