diff options
| author | Jakub Kicinski <kuba@kernel.org> | 2023-02-11 04:51:27 +0300 |
|---|---|---|
| committer | Jakub Kicinski <kuba@kernel.org> | 2023-02-11 04:51:27 +0300 |
| commit | de4287336794f49323a5223c8b6e131f4840a866 (patch) | |
| tree | 9a2dfaf47fc689cdae5a45a728d0529d27c77d98 /tools | |
| parent | d12f9ad028062ff3ee2bfca3247f8812269d1f06 (diff) | |
| parent | 17bcd27a08a21397698edf143084d7c87ce17946 (diff) | |
| download | linux-de4287336794f49323a5223c8b6e131f4840a866.tar.xz | |
Daniel Borkmann says:
====================
pull-request: bpf-next 2023-02-11
We've added 96 non-merge commits during the last 14 day(s) which contain
a total of 152 files changed, 4884 insertions(+), 962 deletions(-).
There is a minor conflict in drivers/net/ethernet/intel/ice/ice_main.c
between commit 5b246e533d01 ("ice: split probe into smaller functions")
from the net-next tree and commit 66c0e13ad236 ("drivers: net: turn on
XDP features") from the bpf-next tree. Remove the hunk given ice_cfg_netdev()
is otherwise there a 2nd time, and add XDP features to the existing
ice_cfg_netdev() one:
[...]
ice_set_netdev_features(netdev);
netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
NETDEV_XDP_ACT_XSK_ZEROCOPY;
ice_set_ops(netdev);
[...]
Stephen's merge conflict mail:
https://lore.kernel.org/bpf/20230207101951.21a114fa@canb.auug.org.au/
The main changes are:
1) Add support for BPF trampoline on s390x which finally allows to remove many
test cases from the BPF CI's DENYLIST.s390x, from Ilya Leoshkevich.
2) Add multi-buffer XDP support to ice driver, from Maciej Fijalkowski.
3) Add capability to export the XDP features supported by the NIC.
Along with that, add a XDP compliance test tool,
from Lorenzo Bianconi & Marek Majtyka.
4) Add __bpf_kfunc tag for marking kernel functions as kfuncs,
from David Vernet.
5) Add a deep dive documentation about the verifier's register
liveness tracking algorithm, from Eduard Zingerman.
6) Fix and follow-up cleanups for resolve_btfids to be compiled
as a host program to avoid cross compile issues,
from Jiri Olsa & Ian Rogers.
7) Batch of fixes to the BPF selftest for xdp_hw_metadata which resulted
when testing on different NICs, from Jesper Dangaard Brouer.
8) Fix libbpf to better detect kernel version code on Debian, from Hao Xiang.
9) Extend libbpf to add an option for when the perf buffer should
wake up, from Jon Doron.
10) Follow-up fix on xdp_metadata selftest to just consume on TX
completion, from Stanislav Fomichev.
11) Extend the kfuncs.rst document with description on kfunc
lifecycle & stability expectations, from David Vernet.
12) Fix bpftool prog profile to skip attaching to offline CPUs,
from Tonghao Zhang.
====================
Link: https://lore.kernel.org/r/20230211002037.8489-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'tools')
59 files changed, 1753 insertions, 268 deletions
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index cfc9fdc1e863..e87738dbffc1 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -2233,10 +2233,38 @@ static void profile_close_perf_events(struct profiler_bpf *obj) profile_perf_event_cnt = 0; } +static int profile_open_perf_event(int mid, int cpu, int map_fd) +{ + int pmu_fd; + + pmu_fd = syscall(__NR_perf_event_open, &metrics[mid].attr, + -1 /*pid*/, cpu, -1 /*group_fd*/, 0); + if (pmu_fd < 0) { + if (errno == ENODEV) { + p_info("cpu %d may be offline, skip %s profiling.", + cpu, metrics[mid].name); + profile_perf_event_cnt++; + return 0; + } + return -1; + } + + if (bpf_map_update_elem(map_fd, + &profile_perf_event_cnt, + &pmu_fd, BPF_ANY) || + ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0)) { + close(pmu_fd); + return -1; + } + + profile_perf_events[profile_perf_event_cnt++] = pmu_fd; + return 0; +} + static int profile_open_perf_events(struct profiler_bpf *obj) { unsigned int cpu, m; - int map_fd, pmu_fd; + int map_fd; profile_perf_events = calloc( sizeof(int), obj->rodata->num_cpu * obj->rodata->num_metric); @@ -2255,17 +2283,11 @@ static int profile_open_perf_events(struct profiler_bpf *obj) if (!metrics[m].selected) continue; for (cpu = 0; cpu < obj->rodata->num_cpu; cpu++) { - pmu_fd = syscall(__NR_perf_event_open, &metrics[m].attr, - -1/*pid*/, cpu, -1/*group_fd*/, 0); - if (pmu_fd < 0 || - bpf_map_update_elem(map_fd, &profile_perf_event_cnt, - &pmu_fd, BPF_ANY) || - ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0)) { + if (profile_open_perf_event(m, cpu, map_fd)) { p_err("failed to create event %s on cpu %d", metrics[m].name, cpu); return -1; } - profile_perf_events[profile_perf_event_cnt++] = pmu_fd; } } return 0; diff --git a/tools/bpf/resolve_btfids/Build b/tools/bpf/resolve_btfids/Build index ae82da03f9bf..077de3829c72 100644 --- a/tools/bpf/resolve_btfids/Build +++ b/tools/bpf/resolve_btfids/Build @@ -1,3 +1,5 @@ +hostprogs := resolve_btfids + resolve_btfids-y += main.o resolve_btfids-y += rbtree.o resolve_btfids-y += zalloc.o @@ -7,4 +9,4 @@ resolve_btfids-y += str_error_r.o $(OUTPUT)%.o: ../../lib/%.c FORCE $(call rule_mkdir) - $(call if_changed_dep,cc_o_c) + $(call if_changed_dep,host_cc_o_c) diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile index daed388aa5d7..ac548a7baa73 100644 --- a/tools/bpf/resolve_btfids/Makefile +++ b/tools/bpf/resolve_btfids/Makefile @@ -17,11 +17,14 @@ else MAKEFLAGS=--no-print-directory endif -# always use the host compiler +# Overrides for the prepare step libraries. HOST_OVERRIDES := AR="$(HOSTAR)" CC="$(HOSTCC)" LD="$(HOSTLD)" ARCH="$(HOSTARCH)" \ - EXTRA_CFLAGS="$(HOSTCFLAGS) $(KBUILD_HOSTCFLAGS)" + CROSS_COMPILE="" EXTRA_CFLAGS="$(HOSTCFLAGS)" RM ?= rm +HOSTCC ?= gcc +HOSTLD ?= ld +HOSTAR ?= ar CROSS_COMPILE = OUTPUT ?= $(srctree)/tools/bpf/resolve_btfids/ @@ -64,7 +67,7 @@ $(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(LIBBPF_OU LIBELF_FLAGS := $(shell $(HOSTPKG_CONFIG) libelf --cflags 2>/dev/null) LIBELF_LIBS := $(shell $(HOSTPKG_CONFIG) libelf --libs 2>/dev/null || echo -lelf) -CFLAGS += -g \ +HOSTCFLAGS += -g \ -I$(srctree)/tools/include \ -I$(srctree)/tools/include/uapi \ -I$(LIBBPF_INCLUDE) \ @@ -73,11 +76,11 @@ CFLAGS += -g \ LIBS = $(LIBELF_LIBS) -lz -export srctree OUTPUT CFLAGS Q +export srctree OUTPUT HOSTCFLAGS Q HOSTCC HOSTLD HOSTAR include $(srctree)/tools/build/Makefile.include $(BINARY_IN): fixdep FORCE prepare | $(OUTPUT) - $(Q)$(MAKE) $(build)=resolve_btfids $(HOST_OVERRIDES) + $(Q)$(MAKE) $(build)=resolve_btfids $(BINARY): $(BPFOBJ) $(SUBCMDOBJ) $(BINARY_IN) $(call msg,LINK,$@) diff --git a/tools/bpf/runqslower/Makefile b/tools/bpf/runqslower/Makefile index 8b3d87b82b7a..47acf6936516 100644 --- a/tools/bpf/runqslower/Makefile +++ b/tools/bpf/runqslower/Makefile @@ -13,6 +13,8 @@ BPF_DESTDIR := $(BPFOBJ_OUTPUT) BPF_INCLUDE := $(BPF_DESTDIR)/include INCLUDES := -I$(OUTPUT) -I$(BPF_INCLUDE) -I$(abspath ../../include/uapi) CFLAGS := -g -Wall $(CLANG_CROSS_FLAGS) +CFLAGS += $(EXTRA_CFLAGS) +LDFLAGS += $(EXTRA_LDFLAGS) # Try to detect best kernel BTF source KERNEL_REL := $(shell uname -r) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 7f024ac22edd..17afd2b35ee5 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -2801,7 +2801,7 @@ union bpf_attr { * * long bpf_perf_prog_read_value(struct bpf_perf_event_data *ctx, struct bpf_perf_event_value *buf, u32 buf_size) * Description - * For en eBPF program attached to a perf event, retrieve the + * For an eBPF program attached to a perf event, retrieve the * value of the event counter associated to *ctx* and store it in * the structure pointed by *buf* and of size *buf_size*. Enabled * and running times are also stored in the structure (see @@ -5817,8 +5817,8 @@ enum { BPF_F_ADJ_ROOM_ENCAP_L4_UDP = (1ULL << 4), BPF_F_ADJ_ROOM_NO_CSUM_RESET = (1ULL << 5), BPF_F_ADJ_ROOM_ENCAP_L2_ETH = (1ULL << 6), - BPF_F_ADJ_ROOM_DECAP_L3_IPV4 = (1ULL << 7), - BPF_F_ADJ_ROOM_DECAP_L3_IPV6 = (1ULL << 8), + BPF_F_ADJ_ROOM_DECAP_L3_IPV4 = (1ULL << 7), + BPF_F_ADJ_ROOM_DECAP_L3_IPV6 = (1ULL << 8), }; enum { diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h new file mode 100644 index 000000000000..9ee459872600 --- /dev/null +++ b/tools/include/uapi/linux/netdev.h @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/netdev.yaml */ +/* YNL-GEN uapi header */ + +#ifndef _UAPI_LINUX_NETDEV_H +#define _UAPI_LINUX_NETDEV_H + +#define NETDEV_FAMILY_NAME "netdev" +#define NETDEV_FAMILY_VERSION 1 + +/** + * enum netdev_xdp_act + * @NETDEV_XDP_ACT_BASIC: XDP feautues set supported by all drivers + * (XDP_ABORTED, XDP_DROP, XDP_PASS, XDP_TX) + * @NETDEV_XDP_ACT_REDIRECT: The netdev supports XDP_REDIRECT + * @NETDEV_XDP_ACT_NDO_XMIT: This feature informs if netdev implements + * ndo_xdp_xmit callback. + * @NETDEV_XDP_ACT_XSK_ZEROCOPY: This feature informs if netdev supports AF_XDP + * in zero copy mode. + * @NETDEV_XDP_ACT_HW_OFFLOAD: This feature informs if netdev supports XDP hw + * oflloading. + * @NETDEV_XDP_ACT_RX_SG: This feature informs if netdev implements non-linear + * XDP buffer support in the driver napi callback. + * @NETDEV_XDP_ACT_NDO_XMIT_SG: This feature informs if netdev implements + * non-linear XDP buffer support in ndo_xdp_xmit callback. + */ +enum netdev_xdp_act { + NETDEV_XDP_ACT_BASIC = 1, + NETDEV_XDP_ACT_REDIRECT = 2, + NETDEV_XDP_ACT_NDO_XMIT = 4, + NETDEV_XDP_ACT_XSK_ZEROCOPY = 8, + NETDEV_XDP_ACT_HW_OFFLOAD = 16, + NETDEV_XDP_ACT_RX_SG = 32, + NETDEV_XDP_ACT_NDO_XMIT_SG = 64, +}; + +enum { + NETDEV_A_DEV_IFINDEX = 1, + NETDEV_A_DEV_PAD, + NETDEV_A_DEV_XDP_FEATURES, + + __NETDEV_A_DEV_MAX, + NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1) +}; + +enum { + NETDEV_CMD_DEV_GET = 1, + NETDEV_CMD_DEV_ADD_NTF, + NETDEV_CMD_DEV_DEL_NTF, + NETDEV_CMD_DEV_CHANGE_NTF, + + __NETDEV_CMD_MAX, + NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1) +}; + +#define NETDEV_MCGRP_MGMT "mgmt" + +#endif /* _UAPI_LINUX_NETDEV_H */ diff --git a/tools/lib/bpf/bpf_core_read.h b/tools/lib/bpf/bpf_core_read.h index 496e6a8ee0dc..1ac57bb7ac55 100644 --- a/tools/lib/bpf/bpf_core_read.h +++ b/tools/lib/bpf/bpf_core_read.h @@ -364,7 +364,7 @@ enum bpf_enum_value_kind { /* Non-CO-RE variant of BPF_CORE_READ_INTO() */ #define BPF_PROBE_READ_INTO(dst, src, a, ...) ({ \ - ___core_read(bpf_probe_read, bpf_probe_read, \ + ___core_read(bpf_probe_read_kernel, bpf_probe_read_kernel, \ dst, (src), a, ##__VA_ARGS__) \ }) @@ -400,7 +400,7 @@ enum bpf_enum_value_kind { /* Non-CO-RE variant of BPF_CORE_READ_STR_INTO() */ #define BPF_PROBE_READ_STR_INTO(dst, src, a, ...) ({ \ - ___core_read(bpf_probe_read_str, bpf_probe_read, \ + ___core_read(bpf_probe_read_kernel_str, bpf_probe_read_kernel, \ dst, (src), a, ##__VA_ARGS__) \ }) diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h index d37c4fe2849d..5ec1871acb2f 100644 --- a/tools/lib/bpf/bpf_helpers.h +++ b/tools/lib/bpf/bpf_helpers.h @@ -109,7 +109,7 @@ * This is a variable-specific variant of more global barrier(). */ #ifndef barrier_var -#define barrier_var(var) asm volatile("" : "=r"(var) : "0"(var)) +#define barrier_var(var) asm volatile("" : "+r"(var)) #endif /* diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index eed5cec6f510..35a698eb825d 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -34,7 +34,6 @@ #include <linux/limits.h> #include <linux/perf_event.h> #include <linux/ring_buffer.h> -#include <linux/version.h> #include <sys/epoll.h> #include <sys/ioctl.h> #include <sys/mman.h> @@ -870,42 +869,6 @@ bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data, return 0; } -__u32 get_kernel_version(void) -{ - /* On Ubuntu LINUX_VERSION_CODE doesn't correspond to info.release, - * but Ubuntu provides /proc/version_signature file, as described at - * https://ubuntu.com/kernel, with an example contents below, which we - * can use to get a proper LINUX_VERSION_CODE. - * - * Ubuntu 5.4.0-12.15-generic 5.4.8 - * - * In the above, 5.4.8 is what kernel is actually expecting, while - * uname() call will return 5.4.0 in info.release. - */ - const char *ubuntu_kver_file = "/proc/version_signature"; - __u32 major, minor, patch; - struct utsname info; - - if (faccessat(AT_FDCWD, ubuntu_kver_file, R_OK, AT_EACCESS) == 0) { - FILE *f; - - f = fopen(ubuntu_kver_file, "r"); - if (f) { - if (fscanf(f, "%*s %*s %d.%d.%d\n", &major, &minor, &patch) == 3) { - fclose(f); - return KERNEL_VERSION(major, minor, patch); - } - fclose(f); - } - /* something went wrong, fall back to uname() approach */ - } - - uname(&info); - if (sscanf(info.release, "%u.%u.%u", &major, &minor, &patch) != 3) - return 0; - return KERNEL_VERSION(major, minor, patch); -} - static const struct btf_member * find_member_by_offset(const struct btf_type *t, __u32 bit_offset) { @@ -11710,17 +11673,22 @@ struct perf_buffer *perf_buffer__new(int map_fd, size_t page_cnt, const size_t attr_sz = sizeof(struct perf_event_attr); struct perf_buffer_params p = {}; struct perf_event_attr attr; + __u32 sample_period; if (!OPTS_VALID(opts, perf_buffer_opts)) return libbpf_err_ptr(-EINVAL); + sample_period = OPTS_GET(opts, sample_period, 1); + if (!sample_period) + sample_period = 1; + memset(&attr, 0, attr_sz); attr.size = attr_sz; attr.config = PERF_COUNT_SW_BPF_OUTPUT; attr.type = PERF_TYPE_SOFTWARE; attr.sample_type = PERF_SAMPLE_RAW; - attr.sample_period = 1; - attr.wakeup_events = 1; + attr.sample_period = sample_period; + attr.wakeup_events = sample_period; p.attr = &attr; p.sample_cb = sample_cb; diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 8777ff21ea1d..2efd80f6f7b9 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -1048,9 +1048,10 @@ struct bpf_xdp_query_opts { __u32 hw_prog_id; /* output */ __u32 skb_prog_id; /* output */ __u8 attach_mode; /* output */ + __u64 feature_flags; /* output */ size_t :0; }; -#define bpf_xdp_query_opts__last_field attach_mode +#define bpf_xdp_query_opts__last_field feature_flags LIBBPF_API int bpf_xdp_attach(int ifindex, int prog_fd, __u32 flags, const struct bpf_xdp_attach_opts *opts); @@ -1246,8 +1247,10 @@ typedef void (*perf_buffer_lost_fn)(void *ctx, int cpu, __u64 cnt); /* common use perf buffer options */ struct perf_buffer_opts { size_t sz; + __u32 sample_period; + size_t :0; }; -#define perf_buffer_opts__last_field sz +#define perf_buffer_opts__last_field sample_period /** * @brief **perf_buffer__new()** creates BPF perfbuf manager for a specified diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index b44fcbb4b42e..4f3bc968ff8e 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -12,11 +12,94 @@ #include <linux/btf.h> #include <linux/filter.h> #include <linux/kernel.h> +#include <linux/version.h> #include "bpf.h" #include "libbpf.h" #include "libbpf_internal.h" +/* On Ubuntu LINUX_VERSION_CODE doesn't correspond to info.release, + * but Ubuntu provides /proc/version_signature file, as described at + * https://ubuntu.com/kernel, with an example contents below, which we + * can use to get a proper LINUX_VERSION_CODE. + * + * Ubuntu 5.4.0-12.15-generic 5.4.8 + * + * In the above, 5.4.8 is what kernel is actually expecting, while + * uname() call will return 5.4.0 in info.release. + */ +static __u32 get_ubuntu_kernel_version(void) +{ + const char *ubuntu_kver_file = "/proc/version_signature"; + __u32 major, minor, patch; + int ret; + FILE *f; + + if (faccessat(AT_FDCWD, ubuntu_kver_file, R_OK, AT_EACCESS) != 0) + return 0; + + f = fopen(ubuntu_kver_file, "r"); + if (!f) + return 0; + + ret = fscanf(f, "%*s %*s %u.%u.%u\n", &major, &minor, &patch); + fclose(f); + if (ret != 3) + return 0; + + return KERNEL_VERSION(major, minor, patch); +} + +/* On Debian LINUX_VERSION_CODE doesn't correspond to info.release. + * Instead, it is provided in info.version. An example content of + * Debian 10 looks like the below. + * + * utsname::release 4.19.0-22-amd64 + * utsname::version #1 SMP Debian 4.19.260-1 (2022-09-29) + * + * In the above, 4.19.260 is what kernel is actually expecting, while + * uname() call will return 4.19.0 in info.release. + */ +static __u32 get_debian_kernel_version(struct utsname *info) +{ + __u32 major, minor, patch; + char *p; + + p = strstr(info->version, "Debian "); + if (!p) { + /* This is not a Debian kernel. */ + return 0; + } + + if (sscanf(p, "Debian %u.%u.%u", &major, &minor, &patch) != 3) + return 0; + + return KERNEL_VERSION(major, minor, patch); +} + +__u32 get_kernel_version(void) +{ + __u32 major, minor, patch, version; + struct utsname info; + + /* Check if this is an Ubuntu kernel. */ + version = get_ubuntu_kernel_version(); + if (version != 0) + return version; + + uname(&info); + + /* Check if this is a Debian kernel. */ + version = get_debian_kernel_version(&info); + if (version != 0) + return version; + + if (sscanf(info.release, "%u.%u.%u", &major, &minor, &patch) != 3) + return 0; + + return KERNEL_VERSION(major, minor, patch); +} + static int probe_prog_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, size_t insns_cnt, char *log_buf, size_t log_buf_sz) diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c index 35104580870c..cb082a04ffa8 100644 --- a/tools/lib/bpf/netlink.c +++ b/tools/lib/bpf/netlink.c @@ -9,6 +9,7 @@ #include <linux/if_ether.h> #include <linux/pkt_cls.h> #include <linux/rtnetlink.h> +#include <linux/netdev.h> #include <sys/socket.h> #include <errno.h> #include <time.h> @@ -39,9 +40,15 @@ struct xdp_id_md { int ifindex; __u32 flags; struct xdp_link_info info; + __u64 feature_flags; }; -static int libbpf_netlink_open(__u32 *nl_pid) +struct xdp_features_md { + int ifindex; + __u64 flags; +}; + +static int libbpf_netlink_open(__u32 *nl_pid, int proto) { struct sockaddr_nl sa; socklen_t addrlen; @@ -51,7 +58,7 @@ static int libbpf_netlink_open(__u32 *nl_pid) memset(&sa, 0, sizeof(sa)); sa.nl_family = AF_NETLINK; - sock = socket(AF_NETLINK, SOCK_RAW | SOCK_CLOEXEC, NETLINK_ROUTE); + sock = socket(AF_NETLINK, SOCK_RAW | SOCK_CLOEXEC, proto); if (sock < 0) return -errno; @@ -212,14 +219,14 @@ done: } static int libbpf_netlink_send_recv(struct libbpf_nla_req *req, - __dump_nlmsg_t parse_msg, + int proto, __dump_nlmsg_t parse_msg, libbpf_dump_nlmsg_t parse_attr, void *cookie) { __u32 nl_pid = 0; int sock, ret; - sock = libbpf_netlink_open(&nl_pid); + sock = libbpf_netlink_open(&nl_pid, proto); if (sock < 0) return sock; @@ -238,6 +245,43 @@ out: return ret; } +static int parse_genl_family_id(struct nlmsghdr *nh, libbpf_dump_nlmsg_t fn, + void *cookie) +{ + struct genlmsghdr *gnl = NLMSG_DATA(nh); + struct nlattr *na = (struct nlattr *)((void *)gnl + GENL_HDRLEN); + struct nlattr *tb[CTRL_ATTR_FAMILY_ID + 1]; + __u16 *id = cookie; + + libbpf_nla_parse(tb, CTRL_ATTR_FAMILY_ID, na, + NLMSG_PAYLOAD(nh, sizeof(*gnl)), NULL); + if (!tb[CTRL_ATTR_FAMILY_ID]) + return NL_CONT; + + *id = libbpf_nla_getattr_u16(tb[CTRL_ATTR_FAMILY_ID]); + return NL_DONE; +} + +static int libbpf_netlink_resolve_genl_family_id(const char *name, + __u16 len, __u16 *id) +{ + struct libbpf_nla_req req = { + .nh.nlmsg_len = NLMSG_LENGTH(GENL_HDRLEN), + .nh.nlmsg_type = GENL_ID_CTRL, + .nh.nlmsg_flags = NLM_F_REQUEST, + .gnl.cmd = CTRL_CMD_GETFAMILY, + .gnl.version = 2, + }; + int err; + + err = nlattr_add(&req, CTRL_ATTR_FAMILY_NAME, name, len); + if (err < 0) + return err; + + return libbpf_netlink_send_recv(&req, NETLINK_GENERIC, + parse_genl_family_id, NULL, id); +} + static int __bpf_set_link_xdp_fd_replace(int ifindex, int fd, int old_fd, __u32 flags) { @@ -271,7 +315,7 @@ static int __bpf_set_link_xdp_fd_replace(int ifindex, int fd, int old_fd, } nlattr_end_nested(&req, nla); - return libbpf_netlink_send_recv(&req, NULL, NULL, NULL); + return libbpf_netlink_send_recv(&req, NETLINK_ROUTE, NULL, NULL, NULL); } int bpf_xdp_attach(int ifindex, int prog_fd, __u32 flags, const struct bpf_xdp_attach_opts *opts) @@ -357,6 +401,29 @@ static int get_xdp_info(void *cookie, void *msg, struct nlattr **tb) return 0; } +static int parse_xdp_features(struct nlmsghdr *nh, libbpf_dump_nlmsg_t fn, + void *cookie) +{ + struct genlmsghdr *gnl = NLMSG_DATA(nh); + struct nlattr *na = (struct nlattr *)((void *)gnl + GENL_HDRLEN); + struct nlattr *tb[NETDEV_CMD_MAX + 1]; + struct xdp_features_md *md = cookie; + __u32 ifindex; + + libbpf_nla_parse(tb, NETDEV_CMD_MAX, na, + NLMSG_PAYLOAD(nh, sizeof(*gnl)), NULL); + + if (!tb[NETDEV_A_DEV_IFINDEX] || !tb[NETDEV_A_DEV_XDP_FEATURES]) + return NL_CONT; + + ifindex = libbpf_nla_getattr_u32(tb[NETDEV_A_DEV_IFINDEX]); + if (ifindex != md->ifindex) + return NL_CONT; + + md->flags = libbpf_nla_getattr_u64(tb[NETDEV_A_DEV_XDP_FEATURES]); + return NL_DONE; +} + int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts) { struct libbpf_nla_req req = { @@ -366,6 +433,10 @@ int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts) .ifinfo.ifi_family = AF_PACKET, }; struct xdp_id_md xdp_id = {}; + struct xdp_features_md md = { + .ifindex = ifindex, + }; + __u16 id; int err; if (!OPTS_VALID(opts, bpf_xdp_query_opts)) @@ -382,7 +453,7 @@ int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts) xdp_id.ifindex = ifindex; xdp_id.flags = xdp_flags; - err = libbpf_netlink_send_recv(&req, __dump_link_nlmsg, + err = libbpf_netlink_send_recv(&req, NETLINK_ROUTE, __dump_link_nlmsg, get_xdp_info, &xdp_id); if (err) return libbpf_err(err); @@ -393,6 +464,31 @@ int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts) OPTS_SET(opts, skb_prog_id, xdp_id.info.skb_prog_id); OPTS_SET(opts, attach_mode, xdp_id.info.attach_mode); + if (!OPTS_HAS(opts, feature_flags)) + return 0; + + err = libbpf_netlink_resolve_genl_family_id("netdev", sizeof("netdev"), &id); + if (err < 0) + return libbpf_err(err); + + memset(&req, 0, sizeof(req)); + req.nh.nlmsg_len = NLMSG_LENGTH(GENL_HDRLEN); + req.nh.nlmsg_flags = NLM_F_REQUEST; + req.nh.nlmsg_type = id; + req.gnl.cmd = NETDEV_CMD_DEV_GET; + req.gnl.version = 2; + + err = nlattr_add(&req, NETDEV_A_DEV_IFINDEX, &ifindex, sizeof(ifindex)); + if (err < 0) + return libbpf_err(err); + + err = libbpf_netlink_send_recv(&req, NETLINK_GENERIC, + parse_xdp_features, NULL, &md); + if (err) + return libbpf_err(err); + + opts->feature_flags = md.flags; + return 0; } @@ -493,7 +589,7 @@ static int tc_qdisc_modify(struct bpf_tc_hook *hook, int cmd, int flags) if (ret < 0) return ret; - return libbpf_netlink_send_recv(&req, NULL, NULL, NULL); + return libbpf_netlink_send_recv(&req, NETLINK_ROUTE, NULL, NULL, NULL); } static int tc_qdisc_create_excl(struct bpf_tc_hook *hook) @@ -673,7 +769,8 @@ int bpf_tc_attach(const struct bpf_tc_hook *hook, struct bpf_tc_opts *opts) info.opts = opts; - ret = libbpf_netlink_send_recv(&req, get_tc_info, NULL, &info); + ret = libbpf_netlink_send_recv(&req, NETLINK_ROUTE, get_tc_info, NULL, + &info); if (ret < 0) return libbpf_err(ret); if (!info.processed) @@ -739,7 +836,7 @@ static int __bpf_tc_detach(const struct bpf_tc_hook *hook, return ret; } - return libbpf_netlink_send_recv(&req, NULL, NULL, NULL); + return libbpf_netlink_send_recv(&req, NETLINK_ROUTE, NULL, NULL, NULL); } int bpf_tc_detach(const struct bpf_tc_hook *hook, @@ -804,7 +901,8 @@ int bpf_tc_query(const struct bpf_tc_hook *hook, struct bpf_tc_opts *opts) info.opts = opts; - ret = libbpf_netlink_send_recv(&req, get_tc_info, NULL, &info); + ret = libbpf_netlink_send_recv(&req, NETLINK_ROUTE, get_tc_info, NULL, + &info); if (ret < 0) return libbpf_err(ret); if (!info.processed) diff --git a/tools/lib/bpf/nlattr.c b/tools/lib/bpf/nlattr.c index 3900d052ed19..975e265eab3b 100644 --- a/tools/lib/bpf/nlattr.c +++ b/tools/lib/bpf/nlattr.c @@ -178,7 +178,7 @@ int libbpf_nla_dump_errormsg(struct nlmsghdr *nlh) hlen += nlmsg_len(&err->msg); attr = (struct nlattr *) ((void *) err + hlen); - alen = nlh->nlmsg_len - hlen; + alen = (void *)nlh + nlh->nlmsg_len - (void *)attr; if (libbpf_nla_parse(tb, NLMSGERR_ATTR_MAX, attr, alen, extack_policy) != 0) { diff --git a/tools/lib/bpf/nlattr.h b/tools/lib/bpf/nlattr.h index 4d15ae2ff812..d92d1c1de700 100644 --- a/tools/lib/bpf/nlattr.h +++ b/tools/lib/bpf/nlattr.h @@ -14,6 +14,7 @@ #include <errno.h> #include <linux/netlink.h> #include <linux/rtnetlink.h> +#include <linux/genetlink.h> /* avoid multiple definition of netlink features */ #define __LINUX_NETLINK_H @@ -58,6 +59,7 @@ struct libbpf_nla_req { union { struct ifinfomsg ifinfo; struct tcmsg tc; + struct genlmsghdr gnl; }; char buf[128]; }; @@ -89,11 +91,21 @@ static inline uint8_t libbpf_nla_getattr_u8(const struct nlattr *nla) return *(uint8_t *)libbpf_nla_data(nla); } +static inline uint16_t libbpf_nla_getattr_u16(const struct nlattr *nla) +{ + return *(uint16_t *)libbpf_nla_data(nla); +} + static inline uint32_t libbpf_nla_getattr_u32(const struct nlattr *nla) { return *(uint32_t *)libbpf_nla_data(nla); } +static inline uint64_t libbpf_nla_getattr_u64(const struct nlattr *nla) +{ + return *(uint64_t *)libbpf_nla_data(nla); +} + static inline const char *libbpf_nla_getattr_str(const struct nlattr *nla) { return (const char *)libbpf_nla_data(nla); diff --git a/tools/lib/bpf/usdt.bpf.h b/tools/lib/bpf/usdt.bpf.h index fdfd235e52c4..0bd4c135acc2 100644 --- a/tools/lib/bpf/usdt.bpf.h +++ b/tools/lib/bpf/usdt.bpf.h @@ -130,7 +130,10 @@ int bpf_usdt_arg(struct pt_regs *ctx, __u64 arg_num, long *res) if (!spec) return -ESRCH; - if (arg_num >= BPF_USDT_MAX_ARG_CNT || arg_num >= spec->arg_cnt) + if (arg_num >= BPF_USDT_MAX_ARG_CNT) + return -ENOENT; + barrier_var(arg_num); + if (arg_num >= spec->arg_cnt) return -ENOENT; arg_spec = &spec->args[arg_num]; diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index 4aa5bba956ff..116fecf80ca1 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -48,3 +48,4 @@ xskxceiver xdp_redirect_multi xdp_synproxy xdp_hw_metadata +xdp_features diff --git a/tools/testing/selftests/bpf/DENYLIST.s390x b/tools/testing/selftests/bpf/DENYLIST.s390x index 50924611e5bb..b89eb87034e4 100644 --- a/tools/testing/selftests/bpf/DENYLIST.s390x +++ b/tools/testing/selftests/bpf/DENYLIST.s390x @@ -1,93 +1,24 @@ # TEMPORARY # Alphabetical order -atomics # attach(add): actual -524 <= expected 0 (trampoline) bloom_filter_map # failed to find kernel BTF type ID of '__x64_sys_getpgid': -3 (?) bpf_cookie # failed to open_and_load program: -524 (trampoline) -bpf_iter_setsockopt # JIT does not support calling kernel function (kfunc) bpf_loop # attaches to __x64_sys_nanosleep -bpf_mod_race # BPF trampoline -bpf_nf # JIT does not support calling kernel function -bpf_tcp_ca # JIT does not support calling kernel function (kfunc) -cb_refs # expected error message unexpected error: -524 (trampoline) -cgroup_hierarchical_stats # JIT does not support calling kernel function (kfunc) -cgrp_kfunc # JIT does not support calling kernel function cgrp_local_storage # prog_attach unexpected error: -524 (trampoline) -core_read_macros # unknown func bpf_probe_read#4 (overlapping) -cpumask # JIT does not support calling kernel function -d_path # failed to auto-attach program 'prog_stat': -524 (trampoline) -decap_sanity # JIT does not support calling kernel function (kfunc) -deny_namespace # failed to attach: ERROR: strerror_r(-524)=22 (trampoline) -dummy_st_ops # test_run unexpected error: -524 (errno 524) (trampoline) -fentry_fexit # fentry attach failed: -524 (trampoline) -fentry_test # fentry_first_attach unexpected error: -524 (trampoline) -fexit_bpf2bpf # freplace_attach_trace unexpected error: -524 (trampoline) fexit_sleep # fexit_skel_load fexit skeleton failed (trampoline) -fexit_stress # fexit attach failed prog 0 failed: -524 (trampoline) -fexit_test # fexit_first_attach unexpected error: -524 (trampoline) -get_func_args_test # trampoline -get_func_ip_test # get_func_ip_test__attach unexpected error: -524 (trampoline) get_stack_raw_tp # user_stack corrupted user stack (no backchain userspace) -htab_update # failed to attach: ERROR: strerror_r(-524)=22 (trampoline) -jit_probe_mem # jit_probe_mem__open_and_load unexpected error: -524 (kfunc) -kfree_skb # attach fentry unexpected error: -524 (trampoline) -kfunc_call # 'bpf_prog_active': not found in kernel BTF (?) -kfunc_dynptr_param # JIT does not support calling kernel function (kfunc) kprobe_multi_bench_attach # bpf_program__attach_kprobe_multi_opts unexpected error: -95 kprobe_multi_test # relies on fentry ksyms_module # test_ksyms_module__open_and_load unexpected error: -9 (?) ksyms_module_libbpf # JIT does not support calling kernel function (kfunc) ksyms_module_lskel # test_ksyms_module_lskel__open_and_load unexpected error: -9 (?) -libbpf_get_fd_by_id_opts # failed to attach: ERROR: strerror_r(-524)=22 (trampoline) -linked_list # JIT does not support calling kernel function (kfunc) -lookup_key # JIT does not support calling kernel function (kfunc) -lru_bug # prog 'printk': failed to auto-attach: -524 -map_kptr # failed to open_and_load program: -524 (trampoline) -modify_return # modify_return attach failed: -524 (trampoline) module_attach # skel_attach skeleton attach failed: -524 (trampoline) -mptcp -nested_trust # JIT does not support calling kernel function -netcnt # failed to load BPF skeleton 'netcnt_prog': -7 (?) -probe_user # check_kprobe_res wrong kprobe res from probe read (?) -rcu_read_lock # failed to find kernel BTF type ID of '__x64_sys_getpgid': -3 (?) -recursion # skel_attach unexpected error: -524 (trampoline) ringbuf # skel_load skeleton load failed (?) -select_reuseport # intermittently fails on new s390x setup -send_signal # intermittently fails to receive signal -setget_sockopt # attach unexpected error: -524 (trampoline) -sk_assign # Can't read on server: Invalid argument (?) -sk_lookup # endianness problem -sk_storage_tracing # test_sk_storage_tracing__attach unexpected error: -524 (trampoline) -skc_to_unix_sock # could not attach BPF object unexpected error: -524 (trampoline) -socket_cookie # prog_attach unexpected error: -524 (trampoline) stacktrace_build_id # compare_map_keys stackid_hmap vs. stackmap err -2 errno 2 (?) -tailcalls # tail_calls are not allowed in non-JITed programs with bpf-to-bpf calls (?) -task_kfunc # JIT does not support calling kernel function -task_local_storage # failed to auto-attach program 'trace_exit_creds': -524 (trampoline) -test_bpffs # bpffs test failed 255 (iterator) -test_bprm_opts # failed to auto-attach program 'secure_exec': -524 (trampoline) -test_ima # failed to auto-attach program 'ima': -524 (trampoline) -test_local_storage # failed to auto-attach program 'unlink_hook': -524 (trampoline) test_lsm # attach unexpected error: -524 (trampoline) -test_overhead # attach_fentry unexpected error: -524 (trampoline) -test_profiler # unknown func bpf_probe_read_str#45 (overlapping) -timer # failed to auto-attach program 'test1': -524 (trampoline) -timer_crash # trampoline -timer_mim # failed to auto-attach program 'test1': -524 (trampoline) -trace_ext # failed to auto-attach program 'test_pkt_md_access_new': -524 (trampoline) trace_printk # trace_printk__load unexpected error: -2 (errno 2) (?) trace_vprintk # trace_vprintk__open_and_load unexpected error: -9 (?) -tracing_struct # failed to auto-attach: -524 (trampoline) -trampoline_count # prog 'prog1': failed to attach: ERROR: strerror_r(-524)=22 (trampoline) -type_cast # JIT does not support calling kernel function unpriv_bpf_disabled # fentry user_ringbuf # failed to find kernel BTF type ID of '__s390x_sys_prctl': -3 (?) verif_stats # trace_vprintk__open_and_load unexpected error: -9 (?) -verify_pkcs7_sig # JIT does not support calling kernel function (kfunc) -vmlinux # failed to auto-attach program 'handle__fentry': -524 (trampoline) -xdp_adjust_tail # case-128 err 0 errno 28 retval 1 size 128 expect-size 3520 (?) xdp_bonding # failed to auto-attach program 'trace_on_entry': -524 (trampoline) -xdp_bpf2bpf # failed to auto-attach program 'trace_on_entry': -524 (trampoline) -xdp_do_redirect # prog_run_max_size unexpected error: -22 (errno 22) xdp_metadata # JIT does not support calling kernel function (kfunc) -xdp_synproxy # JIT does not support calling kernel function (kfunc) -xfrm_info # JIT does not support calling kernel function (kfunc) diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 53eae7be8dff..c4b5c44cdee2 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -22,10 +22,11 @@ endif BPF_GCC ?= $(shell command -v bpf-gcc;) SAN_CFLAGS ?= +SAN_LDFLAGS ?= $(SAN_CFLAGS) CFLAGS += -g -O0 -rdynamic -Wall -Werror $(GENFLAGS) $(SAN_CFLAGS) \ -I$(CURDIR) -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR) \ -I$(TOOLSINCDIR) -I$(APIDIR) -I$(OUTPUT) -LDFLAGS += $(SAN_CFLAGS) +LDFLAGS += $(SAN_LDFLAGS) LDLIBS += -lelf -lz -lrt -lpthread # Silence some warnings when compiled with clang @@ -73,7 +74,8 @@ TEST_PROGS := test_kmod.sh \ test_bpftool.sh \ test_bpftool_metadata.sh \ test_doc_build.sh \ - test_xsk.sh + test_xsk.sh \ + test_xdp_features.sh TEST_PROGS_EXTENDED := with_addr.sh \ with_tunnels.sh ima_setup.sh verify_sig_setup.sh \ @@ -83,7 +85,8 @@ TEST_PROGS_EXTENDED := with_addr.sh \ TEST_GEN_PROGS_EXTENDED = test_sock_addr test_skb_cgroup_id_user \ flow_dissector_load test_flow_dissector test_tcp_check_syncookie_user \ test_lirc_mode2_user xdping test_cpp runqslower bench bpf_testmod.ko \ - xskxceiver xdp_redirect_multi xdp_synproxy veristat xdp_hw_metadata + xskxceiver xdp_redirect_multi xdp_synproxy veristat xdp_hw_metadata \ + xdp_features TEST_CUSTOM_PROGS = $(OUTPUT)/urandom_read $(OUTPUT)/sign-file TEST_GEN_FILES += liburandom_read.so @@ -189,7 +192,7 @@ $(OUTPUT)/liburandom_read.so: urandom_read_lib1.c urandom_read_lib2.c $(OUTPUT)/urandom_read: urandom_read.c urandom_read_aux.c $(OUTPUT)/liburandom_read.so $(call msg,BINARY,,$@) $(Q)$(CLANG) $(filter-out -static,$(CFLAGS) $(LDFLAGS)) $(filter %.c,$^) \ - liburandom_read.so $(filter-out -static,$(LDLIBS)) \ + -lurandom_read $(filter-out -static,$(LDLIBS)) -L$(OUTPUT) \ -fuse-ld=$(LLD) -Wl,-znoseparate-code -Wl,--build-id=sha1 \ -Wl,-rpath=. -o $@ @@ -212,7 +215,9 @@ $(OUTPUT)/runqslower: $(BPFOBJ) | $(DEFAULT_BPFTOOL) $(RUNQSLOWER_OUTPUT) OUTPUT=$(RUNQSLOWER_OUTPUT) VMLINUX_BTF=$(VMLINUX_BTF) \ BPFTOOL_OUTPUT=$(HOST_BUILD_DIR)/bpftool/ \ BPFOBJ_OUTPUT=$(BUILD_DIR)/libbpf \ - BPFOBJ=$(BPFOBJ) BPF_INCLUDE=$(INCLUDE_DIR) && \ + BPFOBJ=$(BPFOBJ) BPF_INCLUDE=$(INCLUDE_DIR) \ + EXTRA_CFLAGS='-g -O0 $(SAN_CFLAGS)' \ + EXTRA_LDFLAGS='$(SAN_LDFLAGS)' && \ cp $(RUNQSLOWER_OUTPUT)runqslower $@ TEST_GEN_PROGS_EXTENDED += $(DEFAULT_BPFTOOL) @@ -246,7 +251,7 @@ BPFTOOL ?= $(DEFAULT_BPFTOOL) $(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile) \ $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/bpftool $(Q)$(MAKE) $(submake_extras) -C $(BPFTOOLDIR) \ - ARCH= CROSS_COMPILE= CC=$(HOSTCC) LD=$(HOSTLD) \ + ARCH= CROSS_COMPILE= CC="$(HOSTCC)" LD="$(HOSTLD)" \ EXTRA_CFLAGS='-g -O0' \ OUTPUT=$(HOST_BUILD_DIR)/bpftool/ \ LIBBPF_OUTPUT=$(HOST_BUILD_DIR)/libbpf/ \ @@ -269,7 +274,8 @@ $(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile) \ $(APIDIR)/linux/bpf.h \ | $(BUILD_DIR)/libbpf $(Q)$(MAKE) $(submake_extras) -C $(BPFDIR) OUTPUT=$(BUILD_DIR)/libbpf/ \ - EXTRA_CFLAGS='-g -O0' \ + EXTRA_CFLAGS='-g -O0 $(SAN_CFLAGS)' \ + EXTRA_LDFLAGS='$(SAN_LDFLAGS)' \ DESTDIR=$(SCRATCH_DIR) prefix= all install_headers ifneq ($(BPFOBJ),$(HOST_BPFOBJ)) @@ -278,7 +284,8 @@ $(HOST_BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile) \ | $(HOST_BUILD_DIR)/libbpf $(Q)$(MAKE) $(submake_extras) -C $(BPFDIR) \ EXTRA_CFLAGS='-g -O0' ARCH= CROSS_COMPILE= \ - OUTPUT=$(HOST_BUILD_DIR)/libbpf/ CC=$(HOSTCC) LD=$(HOSTLD) \ + OUTPUT=$(HOST_BUILD_DIR)/libbpf/ \ + CC="$(HOSTCC)" LD="$(HOSTLD)" \ DESTDIR=$(HOST_SCRATCH_DIR)/ prefix= all install_headers endif @@ -299,7 +306,7 @@ $(RESOLVE_BTFIDS): $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/resolve_btfids \ $(TOOLSDIR)/lib/ctype.c \ $(TOOLSDIR)/lib/str_error_r.c $(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/resolve_btfids \ - CC=$(HOSTCC) LD=$(HOSTLD) AR=$(HOSTAR) \ + CC="$(HOSTCC)" LD="$(HOSTLD)" AR="$(HOSTAR)" \ LIBBPF_INCLUDE=$(HOST_INCLUDE_DIR) \ OUTPUT=$(HOST_BUILD_DIR)/resolve_btfids/ BPFOBJ=$(HOST_BPFOBJ) @@ -385,6 +392,7 @@ test_subskeleton_lib.skel.h-deps := test_subskeleton_lib2.bpf.o test_subskeleton test_usdt.skel.h-deps := test_usdt.bpf.o test_usdt_multispec.bpf.o xsk_xdp_progs.skel.h-deps := xsk_xdp_progs.bpf.o xdp_hw_metadata.skel.h-deps := xdp_hw_metadata.bpf.o +xdp_features.skel.h-deps := xdp_features.bpf.o LINKED_BPF_SRCS := $(patsubst %.bpf.o,%.c,$(foreach skel,$(LINKED_SKELS),$($(skel)-deps))) @@ -519,7 +527,8 @@ $(OUTPUT)/$(TRUNNER_BINARY): $(TRUNNER_TEST_OBJS) \ $$(call msg,BINARY,,$$@) $(Q)$$(CC) $$(CFLAGS) $$(filter %.a %.o,$$^) $$(LDLIBS) -o $$@ $(Q)$(RESOLVE_BTFIDS) --btf $(TRUNNER_OUTPUT)/btf_data.bpf.o $$@ - $(Q)ln -sf $(if $2,..,.)/tools/build/bpftool/bootstrap/bpftool $(if $2,$2/)bpftool + $(Q)ln -sf $(if $2,..,.)/tools/build/bpftool/bootstrap/bpftool \ + $(OUTPUT)/$(if $2,$2/)bpftool endef @@ -586,6 +595,10 @@ $(OUTPUT)/xdp_hw_metadata: xdp_hw_metadata.c $(OUTPUT)/network_helpers.o $(OUTPU $(call msg,BINARY,,$@) $(Q)$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@ +$(OUTPUT)/xdp_features: xdp_features.c $(OUTPUT)/network_helpers.o $(OUTPUT)/xdp_features.skel.h | $(OUTPUT) + $(call msg,BINARY,,$@) + $(Q)$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@ + # Make sure we are able to include and link libbpf against c++. $(OUTPUT)/test_cpp: test_cpp.cpp $(OUTPUT)/test_core_extern.skel.h $(BPFOBJ) $(call msg,CXX,,$@) diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c index 5085fea3cac5..46500636d8cd 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c @@ -59,7 +59,7 @@ bpf_testmod_test_struct_arg_5(void) { return bpf_testmod_test_struct_arg_result; } -noinline void +__bpf_kfunc void bpf_testmod_test_mod_kfunc(int i) { *(int *)this_cpu_ptr(&bpf_testmod_ksym_percpu) = i; diff --git a/tools/testing/selftests/bpf/netcnt_common.h b/tools/testing/selftests/bpf/netcnt_common.h index 0ab1c88041cd..2d4a58e4e39c 100644 --- a/tools/testing/selftests/bpf/netcnt_common.h +++ b/tools/testing/selftests/bpf/netcnt_common.h @@ -8,11 +8,11 @@ /* sizeof(struct bpf_local_storage_elem): * - * It really is about 128 bytes on x86_64, but allocate more to account for - * possible layout changes, different architectures, etc. + * It is about 128 bytes on x86_64 and 512 bytes on s390x, but allocate more to + * account for possible layout changes, different architectures, etc. * The kernel will wrap up to PAGE_SIZE internally anyway. */ -#define SIZEOF_BPF_LOCAL_STORAGE_ELEM 256 +#define SIZEOF_BPF_LOCAL_STORAGE_ELEM 768 /* Try to estimate kernel's BPF_LOCAL_STORAGE_MAX_VALUE_SIZE: */ #define BPF_LOCAL_STORAGE_MAX_VALUE_SIZE (0xFFFF - \ diff --git a/tools/testing/selftests/bpf/prog_tests/attach_probe.c b/tools/testing/selftests/bpf/prog_tests/attach_probe.c index 9566d9d2f6ee..56374c8b5436 100644 --- a/tools/testing/selftests/bpf/prog_tests/attach_probe.c +++ b/tools/testing/selftests/bpf/prog_tests/attach_probe.c @@ -33,8 +33,8 @@ void test_attach_probe(void) struct test_attach_probe* skel; ssize_t uprobe_offset, ref_ctr_offset; struct bpf_link *uprobe_err_link; + FILE *devnull; bool legacy; - char *mem; /* Check if new-style kprobe/uprobe API is supported. * Kernels that support new FD-based kprobe and uprobe BPF attachment @@ -147,7 +147,7 @@ void test_attach_probe(void) /* test attach by name for a library function, using the library * as the binary argument. libc.so.6 will be resolved via dlopen()/dlinfo(). */ - uprobe_opts.func_name = "malloc"; + uprobe_opts.func_name = "fopen"; uprobe_opts.retprobe = false; skel->links.handle_uprobe_byname2 = bpf_program__attach_uprobe_opts(skel->progs.handle_uprobe_byname2, @@ -157,7 +157,7 @@ void test_attach_probe(void) if (!ASSERT_OK_PTR(skel->links.handle_uprobe_byname2, "attach_uprobe_byname2")) goto cleanup; - uprobe_opts.func_name = "free"; + uprobe_opts.func_name = "fclose"; uprobe_opts.retprobe = true; skel->links.handle_uretprobe_byname2 = bpf_program__attach_uprobe_opts(skel->progs.handle_uretprobe_byname2, @@ -195,8 +195,8 @@ void test_attach_probe(void) usleep(1); /* trigger & validate shared library u[ret]probes attached by name */ - mem = malloc(1); - free(mem); + devnull = fopen("/dev/null", "r"); + fclose(devnull); /* trigger & validate uprobe & uretprobe */ trigger_func(); diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c index 2be2d61954bc..26b2d1bffdfd 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c @@ -472,6 +472,7 @@ static void lsm_subtest(struct test_bpf_cookie *skel) int prog_fd; int lsm_fd = -1; LIBBPF_OPTS(bpf_link_create_opts, link_opts); + int err; skel->bss->lsm_res = 0; @@ -482,8 +483,9 @@ static void lsm_subtest(struct test_bpf_cookie *skel) if (!ASSERT_GE(lsm_fd, 0, "lsm.link_create")) goto cleanup; - stack_mprotect(); - if (!ASSERT_EQ(errno, EPERM, "stack_mprotect")) + err = stack_mprotect(); + if (!ASSERT_EQ(err, -1, "stack_mprotect") || + !ASSERT_EQ(errno, EPERM, "stack_mprotect")) goto cleanup; usleep(1); diff --git a/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c b/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c index 33a2776737e7..2cc759956e3b 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c +++ b/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c @@ -16,7 +16,7 @@ struct socket_cookie { __u64 cookie_key; - __u32 cookie_value; + __u64 cookie_value; }; static void test_tp_btf(int cgroup_fd) diff --git a/tools/testing/selftests/bpf/prog_tests/decap_sanity.c b/tools/testing/selftests/bpf/prog_tests/decap_sanity.c index 0b2f73b88c53..2853883b7cbb 100644 --- a/tools/testing/selftests/bpf/prog_tests/decap_sanity.c +++ b/tools/testing/selftests/bpf/prog_tests/decap_sanity.c @@ -80,6 +80,6 @@ fail: bpf_tc_hook_destroy(&qdisc_hook); close_netns(nstoken); } - system("ip netns del " NS_TEST " >& /dev/null"); + system("ip netns del " NS_TEST " &> /dev/null"); decap_sanity__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_stress.c b/tools/testing/selftests/bpf/prog_tests/fexit_stress.c index 5a7e6011f6bf..596536def43d 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_stress.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_stress.c @@ -2,14 +2,19 @@ /* Copyright (c) 2019 Facebook */ #include <test_progs.h> -/* that's kernel internal BPF_MAX_TRAMP_PROGS define */ -#define CNT 38 - void serial_test_fexit_stress(void) { - int fexit_fd[CNT] = {}; - int link_fd[CNT] = {}; - int err, i; + int bpf_max_tramp_links, err, i; + int *fd, *fexit_fd, *link_fd; + + bpf_max_tramp_links = get_bpf_max_tramp_links(); + if (!ASSERT_GE(bpf_max_tramp_links, 1, "bpf_max_tramp_links")) + return; + fd = calloc(bpf_max_tramp_links * 2, sizeof(*fd)); + if (!ASSERT_OK_PTR(fd, "fd")) + return; + fexit_fd = fd; + link_fd = fd + bpf_max_tramp_links; const struct bpf_insn trace_program[] = { BPF_MOV64_IMM(BPF_REG_0, 0), @@ -28,7 +33,7 @@ void serial_test_fexit_stress(void) goto out; trace_opts.attach_btf_id = err; - for (i = 0; i < CNT; i++) { + for (i = 0; i < bpf_max_tramp_links; i++) { fexit_fd[i] = bpf_prog_load(BPF_PROG_TYPE_TRACING, NULL, "GPL", trace_program, sizeof(trace_program) / sizeof(struct bpf_insn), @@ -44,10 +49,11 @@ void serial_test_fexit_stress(void) ASSERT_OK(err, "bpf_prog_test_run_opts"); out: - for (i = 0; i < CNT; i++) { + for (i = 0; i < bpf_max_tramp_links; i++) { if (link_fd[i]) close(link_fd[i]); if (fexit_fd[i]) close(fexit_fd[i]); } + free(fd); } diff --git a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c index 73579370bfbd..c07991544a78 100644 --- a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c +++ b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c @@ -36,7 +36,7 @@ static void on_sample(void *ctx, int cpu, void *data, __u32 size) "cb32_0 %x != %x\n", meta->cb32_0, cb.cb32[0])) return; - if (CHECK(pkt_v6->eth.h_proto != 0xdd86, "check_eth", + if (CHECK(pkt_v6->eth.h_proto != htons(ETH_P_IPV6), "check_eth", "h_proto %x\n", pkt_v6->eth.h_proto)) return; if (CHECK(pkt_v6->iph.nexthdr != 6, "check_ip", diff --git a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c index 5af1ee8f0e6e..a543742cd7bd 100644 --- a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c +++ b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c @@ -72,10 +72,12 @@ static struct kfunc_test_params kfunc_tests[] = { /* success cases */ TC_TEST(kfunc_call_test1, 12), TC_TEST(kfunc_call_test2, 3), + TC_TEST(kfunc_call_test4, -1234), TC_TEST(kfunc_call_test_ref_btf_id, 0), TC_TEST(kfunc_call_test_get_mem, 42), SYSCALL_TEST(kfunc_syscall_test, 0), SYSCALL_NULL_CTX_TEST(kfunc_syscall_test_null, 0), + TC_TEST(kfunc_call_test_static_unused_arg, 0), }; struct syscall_test_args { diff --git a/tools/testing/selftests/bpf/prog_tests/sk_assign.c b/tools/testing/selftests/bpf/prog_tests/sk_assign.c index 3e190ed63976..1374b626a985 100644 --- a/tools/testing/selftests/bpf/prog_tests/sk_assign.c +++ b/tools/testing/selftests/bpf/prog_tests/sk_assign.c @@ -29,7 +29,23 @@ static int stop, duration; static bool configure_stack(void) { + char tc_version[128]; char tc_cmd[BUFSIZ]; + char *prog; + FILE *tc; + + /* Check whether tc is built with libbpf. */ + tc = popen("tc -V", "r"); + if (CHECK_FAIL(!tc)) + return false; + if (CHECK_FAIL(!fgets(tc_version, sizeof(tc_version), tc))) + return false; + if (strstr(tc_version, ", libbpf ")) + prog = "test_sk_assign_libbpf.bpf.o"; + else + prog = "test_sk_assign.bpf.o"; + if (CHECK_FAIL(pclose(tc))) + return false; /* Move to a new networking namespace */ if (CHECK_FAIL(unshare(CLONE_NEWNET))) @@ -46,8 +62,8 @@ configure_stack(void) /* Load qdisc, BPF program */ if (CHECK_FAIL(system("tc qdisc add dev lo clsact"))) return false; - sprintf(tc_cmd, "%s %s %s %s", "tc filter add dev lo ingress bpf", - "direct-action object-file ./test_sk_assign.bpf.o", + sprintf(tc_cmd, "%s %s %s %s %s", "tc filter add dev lo ingress bpf", + "direct-action object-file", prog, "section tc", (env.verbosity < VERBOSE_VERY) ? " 2>/dev/null" : "verbose"); if (CHECK(system(tc_cmd), "BPF load failed;", @@ -129,15 +145,12 @@ get_port(int fd) static ssize_t rcv_msg(int srv_client, int type) { - struct sockaddr_storage ss; char buf[BUFSIZ]; - socklen_t slen; if (type == SOCK_STREAM) return read(srv_client, &buf, sizeof(buf)); else - return recvfrom(srv_client, &buf, sizeof(buf), 0, - (struct sockaddr *)&ss, &slen); + return recvfrom(srv_client, &buf, sizeof(buf), 0, NULL, NULL); } static int diff --git a/tools/testing/selftests/bpf/prog_tests/test_lsm.c b/tools/testing/selftests/bpf/prog_tests/test_lsm.c index 244c01125126..16175d579bc7 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_lsm.c +++ b/tools/testing/selftests/bpf/prog_tests/test_lsm.c @@ -75,7 +75,8 @@ static int test_lsm(struct lsm *skel) skel->bss->monitored_pid = getpid(); err = stack_mprotect(); - if (!ASSERT_EQ(errno, EPERM, "stack_mprotect")) + if (!ASSERT_EQ(err, -1, "stack_mprotect") || + !ASSERT_EQ(errno, EPERM, "stack_mprotect")) return err; ASSERT_EQ(skel->bss->mprotect_count, 1, "mprotect_count"); diff --git a/tools/testing/selftests/bpf/prog_tests/trampoline_count.c b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c index 564b75bc087f..8fd4c0d78089 100644 --- a/tools/testing/selftests/bpf/prog_tests/trampoline_count.c +++ b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c @@ -2,8 +2,6 @@ #define _GNU_SOURCE #include <test_progs.h> -#define MAX_TRAMP_PROGS 38 - struct inst { struct bpf_object *obj; struct bpf_link *link; @@ -37,14 +35,21 @@ void serial_test_trampoline_count(void) { char *file = "test_trampoline_count.bpf.o"; char *const progs[] = { "fentry_test", "fmod_ret_test", "fexit_test" }; - struct inst inst[MAX_TRAMP_PROGS + 1] = {}; + int bpf_max_tramp_links, err, i, prog_fd; struct bpf_program *prog; struct bpf_link *link; - int prog_fd, err, i; + struct inst *inst; LIBBPF_OPTS(bpf_test_run_opts, opts); + bpf_max_tramp_links = get_bpf_max_tramp_links(); + if (!ASSERT_GE(bpf_max_tramp_links, 1, "bpf_max_tramp_links")) + return; + inst = calloc(bpf_max_tramp_links + 1, sizeof(*inst)); + if (!ASSERT_OK_PTR(inst, "inst")) + return; + /* attach 'allowed' trampoline programs */ - for (i = 0; i < MAX_TRAMP_PROGS; i++) { + for (i = 0; i < bpf_max_tramp_links; i++) { prog = load_prog(file, progs[i % ARRAY_SIZE(progs)], &inst[i]); if (!prog) goto cleanup; @@ -91,4 +96,5 @@ cleanup: bpf_link__destroy(inst[i].link); bpf_object__close(inst[i].obj); } + free(inst); } diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_autoattach.c b/tools/testing/selftests/bpf/prog_tests/uprobe_autoattach.c index 82807def0d24..6558c857e620 100644 --- a/tools/testing/selftests/bpf/prog_tests/uprobe_autoattach.c +++ b/tools/testing/selftests/bpf/prog_tests/uprobe_autoattach.c @@ -16,10 +16,10 @@ static noinline int autoattach_trigger_func(int arg1, int arg2, int arg3, void test_uprobe_autoattach(void) { + const char *devnull_str = "/dev/null"; struct test_uprobe_autoattach *skel; int trigger_ret; - size_t malloc_sz = 1; - char *mem; + FILE *devnull; skel = test_uprobe_autoattach__open_and_load(); if (!ASSERT_OK_PTR(skel, "skel_open")) @@ -36,16 +36,18 @@ void test_uprobe_autoattach(void) skel->bss->test_pid = getpid(); /* trigger & validate shared library u[ret]probes attached by name */ - mem = malloc(malloc_sz); + devnull = fopen(devnull_str, "r"); ASSERT_EQ(skel->bss->uprobe_byname_parm1, 1, "check_uprobe_byname_parm1"); ASSERT_EQ(skel->bss->uprobe_byname_ran, 1, "check_uprobe_byname_ran"); ASSERT_EQ(skel->bss->uretprobe_byname_rc, trigger_ret, "check_uretprobe_byname_rc"); ASSERT_EQ(skel->bss->uretprobe_byname_ret, trigger_ret, "check_uretprobe_byname_ret"); ASSERT_EQ(skel->bss->uretprobe_byname_ran, 2, "check_uretprobe_byname_ran"); - ASSERT_EQ(skel->bss->uprobe_byname2_parm1, malloc_sz, "check_uprobe_byname2_parm1"); + ASSERT_EQ(skel->bss->uprobe_byname2_parm1, (__u64)(long)devnull_str, + "check_uprobe_byname2_parm1"); ASSERT_EQ(skel->bss->uprobe_byname2_ran, 3, "check_uprobe_byname2_ran"); - ASSERT_EQ(skel->bss->uretprobe_byname2_rc, mem, "check_uretprobe_byname2_rc"); + ASSERT_EQ(skel->bss->uretprobe_byname2_rc, (__u64)(long)devnull, + "check_uretprobe_byname2_rc"); ASSERT_EQ(skel->bss->uretprobe_byname2_ran, 4, "check_uretprobe_byname2_ran"); ASSERT_EQ(skel->bss->a[0], 1, "arg1"); @@ -67,7 +69,7 @@ void test_uprobe_autoattach(void) ASSERT_EQ(skel->bss->a[7], 8, "arg8"); #endif - free(mem); + fclose(devnull); cleanup: test_uprobe_autoattach__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/usdt.c b/tools/testing/selftests/bpf/prog_tests/usdt.c index 9ad9da0f215e..56ed1eb9b527 100644 --- a/tools/testing/selftests/bpf/prog_tests/usdt.c +++ b/tools/testing/selftests/bpf/prog_tests/usdt.c @@ -314,6 +314,7 @@ static FILE *urand_spawn(int *pid) if (fscanf(f, "%d", pid) != 1) { pclose(f); + errno = EINVAL; return NULL; } diff --git a/tools/testing/selftests/bpf/prog_tests/verify_pkcs7_sig.c b/tools/testing/selftests/bpf/prog_tests/verify_pkcs7_sig.c index 579d6ee83ce0..dd7f2bc70048 100644 --- a/tools/testing/selftests/bpf/prog_tests/verify_pkcs7_sig.c +++ b/tools/testing/selftests/bpf/prog_tests/verify_pkcs7_sig.c @@ -61,6 +61,9 @@ static bool kfunc_not_supported; static int libbpf_print_cb(enum libbpf_print_level level, const char *fmt, va_list args) { + if (level == LIBBPF_WARN) + vprintf(fmt, args); + if (strcmp(fmt, "libbpf: extern (func ksym) '%s': not found in kernel or module BTFs\n")) return 0; diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c index 39973ea1ce43..f09505f8b038 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c @@ -76,10 +76,15 @@ static void test_xdp_adjust_tail_grow2(void) { const char *file = "./test_xdp_adjust_tail_grow.bpf.o"; char buf[4096]; /* avoid segfault: large buf to hold grow results */ - int tailroom = 320; /* SKB_DATA_ALIGN(sizeof(struct skb_shared_info))*/; struct bpf_object *obj; int err, cnt, i; int max_grow, prog_fd; + /* SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) */ +#if defined(__s390x__) + int tailroom = 512; +#else + int tailroom = 320; +#endif LIBBPF_OPTS(bpf_test_run_opts, tattr, .repeat = 1, diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c index a50971c6cf4a..2666c84dbd01 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c @@ -4,10 +4,12 @@ #include <net/if.h> #include <linux/if_ether.h> #include <linux/if_packet.h> +#include <linux/if_link.h> #include <linux/ipv6.h> #include <linux/in6.h> #include <linux/udp.h> #include <bpf/bpf_endian.h> +#include <uapi/linux/netdev.h> #include "test_xdp_do_redirect.skel.h" #define SYS(fmt, ...) \ @@ -65,7 +67,11 @@ static int attach_tc_prog(struct bpf_tc_hook *hook, int fd) /* The maximum permissible size is: PAGE_SIZE - sizeof(struct xdp_page_head) - * sizeof(struct skb_shared_info) - XDP_PACKET_HEADROOM = 3368 bytes */ +#if defined(__s390x__) +#define MAX_PKT_SIZE 3176 +#else #define MAX_PKT_SIZE 3368 +#endif static void test_max_pkt_size(int fd) { char data[MAX_PKT_SIZE + 1] = {}; @@ -92,7 +98,7 @@ void test_xdp_do_redirect(void) struct test_xdp_do_redirect *skel = NULL; struct nstoken *nstoken = NULL; struct bpf_link *link; - + LIBBPF_OPTS(bpf_xdp_query_opts, query_opts); struct xdp_md ctx_in = { .data = sizeof(__u32), .data_end = sizeof(data) }; DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts, @@ -153,6 +159,29 @@ void test_xdp_do_redirect(void) !ASSERT_NEQ(ifindex_dst, 0, "ifindex_dst")) goto out; + /* Check xdp features supported by veth driver */ + err = bpf_xdp_query(ifindex_src, XDP_FLAGS_DRV_MODE, &query_opts); + if (!ASSERT_OK(err, "veth_src bpf_xdp_query")) + goto out; + + if (!ASSERT_EQ(query_opts.feature_flags, + NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_RX_SG | + NETDEV_XDP_ACT_NDO_XMIT_SG, + "veth_src query_opts.feature_flags")) + goto out; + + err = bpf_xdp_query(ifindex_dst, XDP_FLAGS_DRV_MODE, &query_opts); + if (!ASSERT_OK(err, "veth_dst bpf_xdp_query")) + goto out; + + if (!ASSERT_EQ(query_opts.feature_flags, + NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_RX_SG | + NETDEV_XDP_ACT_NDO_XMIT_SG, + "veth_dst query_opts.feature_flags")) + goto out; + memcpy(skel->rodata->expect_dst, &pkt_udp.eth.h_dest, ETH_ALEN); skel->rodata->ifindex_out = ifindex_src; /* redirect back to the same iface */ skel->rodata->ifindex_in = ifindex_src; diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_info.c b/tools/testing/selftests/bpf/prog_tests/xdp_info.c index cd3aa340e65e..286c21ecdc65 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_info.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_info.c @@ -8,6 +8,7 @@ void serial_test_xdp_info(void) { __u32 len = sizeof(struct bpf_prog_info), duration = 0, prog_id; const char *file = "./xdp_dummy.bpf.o"; + LIBBPF_OPTS(bpf_xdp_query_opts, opts); struct bpf_prog_info info = {}; struct bpf_object *obj; int err, prog_fd; @@ -61,6 +62,13 @@ void serial_test_xdp_info(void) if (CHECK(prog_id, "prog_id_drv", "unexpected prog_id=%u\n", prog_id)) goto out; + /* Check xdp features supported by lo device */ + opts.feature_flags = ~0; + err = bpf_xdp_query(IFINDEX_LO, XDP_FLAGS_DRV_MODE, &opts); + if (!ASSERT_OK(err, "bpf_xdp_query")) + goto out; + + ASSERT_EQ(opts.feature_flags, 0, "opts.feature_flags"); out: bpf_xdp_detach(IFINDEX_LO, 0, NULL); out_close: diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c index e033d48288c0..aa4beae99f4f 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c @@ -121,7 +121,7 @@ static void close_xsk(struct xsk *xsk) xsk_umem__delete(xsk->umem); if (xsk->socket) xsk_socket__delete(xsk->socket); - munmap(xsk->umem, UMEM_SIZE); + munmap(xsk->umem_area, UMEM_SIZE); } static void ip_csum(struct iphdr *iph) @@ -205,9 +205,8 @@ static void complete_tx(struct xsk *xsk) if (ASSERT_EQ(xsk_ring_cons__peek(&xsk->comp, 1, &idx), 1, "xsk_ring_cons__peek")) { addr = *xsk_ring_cons__comp_addr(&xsk->comp, idx); - printf("%p: refill idx=%u addr=%llx\n", xsk, idx, addr); - *xsk_ring_prod__fill_addr(&xsk->fill, idx) = addr; - xsk_ring_prod__submit(&xsk->fill, 1); + printf("%p: complete tx idx=%u addr=%llx\n", xsk, idx, addr); + xsk_ring_cons__release(&xsk->comp, 1); } } diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_test.c b/tools/testing/selftests/bpf/progs/kfunc_call_test.c index f636e50be259..7daa8f5720b9 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_test.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_test.c @@ -3,6 +3,7 @@ #include <vmlinux.h> #include <bpf/bpf_helpers.h> +extern long bpf_kfunc_call_test4(signed char a, short b, int c, long d) __ksym; extern int bpf_kfunc_call_test2(struct sock *sk, __u32 a, __u32 b) __ksym; extern __u64 bpf_kfunc_call_test1(struct sock *sk, __u32 a, __u64 b, __u32 c, __u64 d) __ksym; @@ -16,6 +17,24 @@ extern void bpf_kfunc_call_test_mem_len_pass1(void *mem, int len) __ksym; extern void bpf_kfunc_call_test_mem_len_fail2(__u64 *mem, int len) __ksym; extern int *bpf_kfunc_call_test_get_rdwr_mem(struct prog_test_ref_kfunc *p, const int rdwr_buf_size) __ksym; extern int *bpf_kfunc_call_test_get_rdonly_mem(struct prog_test_ref_kfunc *p, const int rdonly_buf_size) __ksym; +extern u32 bpf_kfunc_call_test_static_unused_arg(u32 arg, u32 unused) __ksym; + +SEC("tc") +int kfunc_call_test4(struct __sk_buff *skb) +{ + struct bpf_sock *sk = skb->sk; + long tmp; + + if (!sk) + return -1; + + sk = bpf_sk_fullsock(sk); + if (!sk) + return -1; + + tmp = bpf_kfunc_call_test4(-3, -30, -200, -1000); + return (tmp >> 32) + tmp; +} SEC("tc") int kfunc_call_test2(struct __sk_buff *skb) @@ -163,4 +182,14 @@ int kfunc_call_test_get_mem(struct __sk_buff *skb) return ret; } +SEC("tc") +int kfunc_call_test_static_unused_arg(struct __sk_buff *skb) +{ + + u32 expected = 5, actual; + + actual = bpf_kfunc_call_test_static_unused_arg(expected, 0xdeadbeef); + return actual != expected ? -1 : 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/lsm.c b/tools/testing/selftests/bpf/progs/lsm.c index d8d8af623bc2..dc93887ed34c 100644 --- a/tools/testing/selftests/bpf/progs/lsm.c +++ b/tools/testing/selftests/bpf/progs/lsm.c @@ -6,9 +6,10 @@ #include "bpf_misc.h" #include "vmlinux.h" +#include <bpf/bpf_core_read.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> -#include <errno.h> +#include <errno.h> struct { __uint(type, BPF_MAP_TYPE_ARRAY); @@ -164,8 +165,8 @@ int copy_test = 0; SEC("fentry.s/" SYS_PREFIX "sys_setdomainname") int BPF_PROG(test_sys_setdomainname, struct pt_regs *regs) { - void *ptr = (void *)PT_REGS_PARM1(regs); - int len = PT_REGS_PARM2(regs); + void *ptr = (void *)PT_REGS_PARM1_SYSCALL(regs); + int len = PT_REGS_PARM2_SYSCALL(regs); int buf = 0; long ret; diff --git a/tools/testing/selftests/bpf/progs/profiler.inc.h b/tools/testing/selftests/bpf/progs/profiler.inc.h index 92331053dba3..68a3fd7387a4 100644 --- a/tools/testing/selftests/bpf/progs/profiler.inc.h +++ b/tools/testing/selftests/bpf/progs/profiler.inc.h @@ -156,10 +156,10 @@ probe_read_lim(void* dst, void* src, unsigned long len, unsigned long max) { len = len < max ? len : max; if (len > 1) { - if (bpf_probe_read(dst, len, src)) + if (bpf_probe_read_kernel(dst, len, src)) return 0; } else if (len == 1) { - if (bpf_probe_read(dst, 1, src)) + if (bpf_probe_read_kernel(dst, 1, src)) return 0; } return len; @@ -216,7 +216,8 @@ static INLINE void* read_full_cgroup_path(struct kernfs_node* cgroup_node, #endif for (int i = 0; i < MAX_CGROUPS_PATH_DEPTH; i++) { filepart_length = - bpf_probe_read_str(payload, MAX_PATH, BPF_CORE_READ(cgroup_node, name)); + bpf_probe_read_kernel_str(payload, MAX_PATH, + BPF_CORE_READ(cgroup_node, name)); if (!cgroup_node) return payload; if (cgroup_node == cgroup_root_node) @@ -303,7 +304,8 @@ static INLINE void* populate_cgroup_info(struct cgroup_data_t* cgroup_data, cgroup_data->cgroup_full_length = 0; size_t cgroup_root_length = - bpf_probe_read_str(payload, MAX_PATH, BPF_CORE_READ(root_kernfs, name)); + bpf_probe_read_kernel_str(payload, MAX_PATH, + BPF_CORE_READ(root_kernfs, name)); barrier_var(cgroup_root_length); if (cgroup_root_length <= MAX_PATH) { barrier_var(cgroup_root_length); @@ -312,7 +314,8 @@ static INLINE void* populate_cgroup_info(struct cgroup_data_t* cgroup_data, } size_t cgroup_proc_length = - bpf_probe_read_str(payload, MAX_PATH, BPF_CORE_READ(proc_kernfs, name)); + bpf_probe_read_kernel_str(payload, MAX_PATH, + BPF_CORE_READ(proc_kernfs, name)); barrier_var(cgroup_proc_length); if (cgroup_proc_length <= MAX_PATH) { barrier_var(cgroup_proc_length); @@ -395,7 +398,8 @@ static INLINE int trace_var_sys_kill(void* ctx, int tpid, int sig) arr_struct = bpf_map_lookup_elem(&data_heap, &zero); if (arr_struct == NULL) return 0; - bpf_probe_read(&arr_struct->array[0], sizeof(arr_struct->array[0]), kill_data); + bpf_probe_read_kernel(&arr_struct->array[0], + sizeof(arr_struct->array[0]), kill_data); } else { int index = get_var_spid_index(arr_struct, spid); @@ -409,8 +413,9 @@ static INLINE int trace_var_sys_kill(void* ctx, int tpid, int sig) #endif for (int i = 0; i < ARRAY_SIZE(arr_struct->array); i++) if (arr_struct->array[i].meta.pid == 0) { - bpf_probe_read(&arr_struct->array[i], - sizeof(arr_struct->array[i]), kill_data); + bpf_probe_read_kernel(&arr_struct->array[i], + sizeof(arr_struct->array[i]), + kill_data); bpf_map_update_elem(&var_tpid_to_data, &tpid, arr_struct, 0); @@ -427,17 +432,17 @@ static INLINE int trace_var_sys_kill(void* ctx, int tpid, int sig) if (delta_sec < STALE_INFO) { kill_data->kill_count++; kill_data->last_kill_time = bpf_ktime_get_ns(); - bpf_probe_read(&arr_struct->array[index], - sizeof(arr_struct->array[index]), - kill_data); + bpf_probe_read_kernel(&arr_struct->array[index], + sizeof(arr_struct->array[index]), + kill_data); } else { struct var_kill_data_t* kill_data = get_var_kill_data(ctx, spid, tpid, sig); if (kill_data == NULL) return 0; - bpf_probe_read(&arr_struct->array[index], - sizeof(arr_struct->array[index]), - kill_data); + bpf_probe_read_kernel(&arr_struct->array[index], + sizeof(arr_struct->array[index]), + kill_data); } } bpf_map_update_elem(&var_tpid_to_data, &tpid, arr_struct, 0); @@ -487,8 +492,9 @@ read_absolute_file_path_from_dentry(struct dentry* filp_dentry, void* payload) #pragma unroll #endif for (int i = 0; i < MAX_PATH_DEPTH; i++) { - filepart_length = bpf_probe_read_str(payload, MAX_PATH, - BPF_CORE_READ(filp_dentry, d_name.name)); + filepart_length = + bpf_probe_read_kernel_str(payload, MAX_PATH, + BPF_CORE_READ(filp_dentry, d_name.name)); barrier_var(filepart_length); if (filepart_length > MAX_PATH) break; @@ -572,7 +578,8 @@ ssize_t BPF_KPROBE(kprobe__proc_sys_write, sysctl_data->sysctl_val_length = 0; sysctl_data->sysctl_path_length = 0; - size_t sysctl_val_length = bpf_probe_read_str(payload, CTL_MAXNAME, buf); + size_t sysctl_val_length = bpf_probe_read_kernel_str(payload, + CTL_MAXNAME, buf); barrier_var(sysctl_val_length); if (sysctl_val_length <= CTL_MAXNAME) { barrier_var(sysctl_val_length); @@ -580,8 +587,10 @@ ssize_t BPF_KPROBE(kprobe__proc_sys_write, payload += sysctl_val_length; } - size_t sysctl_path_length = bpf_probe_read_str(payload, MAX_PATH, - BPF_CORE_READ(filp, f_path.dentry, d_name.name)); + size_t sysctl_path_length = + bpf_probe_read_kernel_str(payload, MAX_PATH, + BPF_CORE_READ(filp, f_path.dentry, + d_name.name)); barrier_var(sysctl_path_length); if (sysctl_path_length <= MAX_PATH) { barrier_var(sysctl_path_length); @@ -638,7 +647,8 @@ int raw_tracepoint__sched_process_exit(void* ctx) struct var_kill_data_t* past_kill_data = &arr_struct->array[i]; if (past_kill_data != NULL && past_kill_data->kill_target_pid == tpid) { - bpf_probe_read(kill_data, sizeof(*past_kill_data), past_kill_data); + bpf_probe_read_kernel(kill_data, sizeof(*past_kill_data), + past_kill_data); void* payload = kill_data->payload; size_t offset = kill_data->payload_length; if (offset >= MAX_METADATA_PAYLOAD_LEN + MAX_CGROUP_PAYLOAD_LEN) @@ -656,8 +666,10 @@ int raw_tracepoint__sched_process_exit(void* ctx) payload += comm_length; } - size_t cgroup_proc_length = bpf_probe_read_str(payload, KILL_TARGET_LEN, - BPF_CORE_READ(proc_kernfs, name)); + size_t cgroup_proc_length = + bpf_probe_read_kernel_str(payload, + KILL_TARGET_LEN, + BPF_CORE_READ(proc_kernfs, name)); barrier_var(cgroup_proc_length); if (cgroup_proc_length <= KILL_TARGET_LEN) { barrier_var(cgroup_proc_length); @@ -718,7 +730,8 @@ int raw_tracepoint__sched_process_exec(struct bpf_raw_tracepoint_args* ctx) proc_exec_data->parent_start_time = BPF_CORE_READ(parent_task, start_time); const char* filename = BPF_CORE_READ(bprm, filename); - size_t bin_path_length = bpf_probe_read_str(payload, MAX_FILENAME_LEN, filename); + size_t bin_path_length = + bpf_probe_read_kernel_str(payload, MAX_FILENAME_LEN, filename); barrier_var(bin_path_length); if (bin_path_length <= MAX_FILENAME_LEN) { barrier_var(bin_path_length); @@ -922,7 +935,8 @@ int BPF_KPROBE(kprobe__vfs_symlink, struct inode* dir, struct dentry* dentry, filemod_data->payload); payload = populate_cgroup_info(&filemod_data->cgroup_data, task, payload); - size_t len = bpf_probe_read_str(payload, MAX_FILEPATH_LENGTH, oldname); + size_t len = bpf_probe_read_kernel_str(payload, MAX_FILEPATH_LENGTH, + oldname); barrier_var(len); if (len <= MAX_FILEPATH_LENGTH) { barrier_var(len); diff --git a/tools/testing/selftests/bpf/progs/test_attach_probe.c b/tools/testing/selftests/bpf/progs/test_attach_probe.c index a1e45fec8938..3b5dc34d23e9 100644 --- a/tools/testing/selftests/bpf/progs/test_attach_probe.c +++ b/tools/testing/selftests/bpf/progs/test_attach_probe.c @@ -92,18 +92,19 @@ int handle_uretprobe_byname(struct pt_regs *ctx) } SEC("uprobe") -int handle_uprobe_byname2(struct pt_regs *ctx) +int BPF_UPROBE(handle_uprobe_byname2, const char *pathname, const char *mode) { - unsigned int size = PT_REGS_PARM1(ctx); + char mode_buf[2] = {}; - /* verify malloc size */ - if (size == 1) + /* verify fopen mode */ + bpf_probe_read_user(mode_buf, sizeof(mode_buf), mode); + if (mode_buf[0] == 'r' && mode_buf[1] == 0) uprobe_byname2_res = 7; return 0; } SEC("uretprobe") -int handle_uretprobe_byname2(struct pt_regs *ctx) +int BPF_URETPROBE(handle_uretprobe_byname2, void *ret) { uretprobe_byname2_res = 8; return 0; diff --git a/tools/testing/selftests/bpf/progs/test_sk_assign.c b/tools/testing/selftests/bpf/progs/test_sk_assign.c index 98c6493d9b91..21b19b758c4e 100644 --- a/tools/testing/selftests/bpf/progs/test_sk_assign.c +++ b/tools/testing/selftests/bpf/progs/test_sk_assign.c @@ -16,6 +16,16 @@ #include <bpf/bpf_helpers.h> #include <bpf/bpf_endian.h> +#if defined(IPROUTE2_HAVE_LIBBPF) +/* Use a new-style map definition. */ +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __type(key, int); + __type(value, __u64); + __uint(pinning, LIBBPF_PIN_BY_NAME); + __uint(max_entries, 1); +} server_map SEC(".maps"); +#else /* Pin map under /sys/fs/bpf/tc/globals/<map name> */ #define PIN_GLOBAL_NS 2 @@ -35,6 +45,7 @@ struct { .max_elem = 1, .pinning = PIN_GLOBAL_NS, }; +#endif char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sk_assign_libbpf.c b/tools/testing/selftests/bpf/progs/test_sk_assign_libbpf.c new file mode 100644 index 000000000000..dcf46adfda04 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sk_assign_libbpf.c @@ -0,0 +1,3 @@ +// SPDX-License-Identifier: GPL-2.0 +#define IPROUTE2_HAVE_LIBBPF +#include "test_sk_assign.c" diff --git a/tools/testing/selftests/bpf/progs/test_uprobe_autoattach.c b/tools/testing/selftests/bpf/progs/test_uprobe_autoattach.c index 774ddeb45898..da4bf89d004c 100644 --- a/tools/testing/selftests/bpf/progs/test_uprobe_autoattach.c +++ b/tools/testing/selftests/bpf/progs/test_uprobe_autoattach.c @@ -13,9 +13,9 @@ int uprobe_byname_ran = 0; int uretprobe_byname_rc = 0; int uretprobe_byname_ret = 0; int uretprobe_byname_ran = 0; -size_t uprobe_byname2_parm1 = 0; +u64 uprobe_byname2_parm1 = 0; int uprobe_byname2_ran = 0; -char *uretprobe_byname2_rc = NULL; +u64 uretprobe_byname2_rc = 0; int uretprobe_byname2_ran = 0; int test_pid; @@ -88,28 +88,28 @@ int BPF_URETPROBE(handle_uretprobe_byname, int ret) } -SEC("uprobe/libc.so.6:malloc") -int handle_uprobe_byname2(struct pt_regs *ctx) +SEC("uprobe/libc.so.6:fopen") +int BPF_UPROBE(handle_uprobe_byname2, const char *pathname, const char *mode) { int pid = bpf_get_current_pid_tgid() >> 32; /* ignore irrelevant invocations */ if (test_pid != pid) return 0; - uprobe_byname2_parm1 = PT_REGS_PARM1_CORE(ctx); + uprobe_byname2_parm1 = (u64)(long)pathname; uprobe_byname2_ran = 3; return 0; } -SEC("uretprobe/libc.so.6:malloc") -int handle_uretprobe_byname2(struct pt_regs *ctx) +SEC("uretprobe/libc.so.6:fopen") +int BPF_URETPROBE(handle_uretprobe_byname2, void *ret) { int pid = bpf_get_current_pid_tgid() >> 32; /* ignore irrelevant invocations */ if (test_pid != pid) return 0; - uretprobe_byname2_rc = (char *)PT_REGS_RC_CORE(ctx); + uretprobe_byname2_rc = (u64)(long)ret; uretprobe_byname2_ran = 4; return 0; } diff --git a/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c b/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c index ce419304ff1f..7748cc23de8a 100644 --- a/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c +++ b/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c @@ -59,10 +59,14 @@ int BPF_PROG(bpf, int cmd, union bpf_attr *attr, unsigned int size) if (!data_val) return 0; - bpf_probe_read(&value, sizeof(value), &attr->value); - - bpf_copy_from_user(data_val, sizeof(struct data), - (void *)(unsigned long)value); + ret = bpf_probe_read_kernel(&value, sizeof(value), &attr->value); + if (ret) + return ret; + + ret = bpf_copy_from_user(data_val, sizeof(struct data), + (void *)(unsigned long)value); + if (ret) + return ret; if (data_val->data_len > sizeof(data_val->data)) return -EINVAL; diff --git a/tools/testing/selftests/bpf/progs/test_vmlinux.c b/tools/testing/selftests/bpf/progs/test_vmlinux.c index e9dfa0313d1b..4b8e37f7fd06 100644 --- a/tools/testing/selftests/bpf/progs/test_vmlinux.c +++ b/tools/testing/selftests/bpf/progs/test_vmlinux.c @@ -42,7 +42,7 @@ int BPF_PROG(handle__raw_tp, struct pt_regs *regs, long id) if (id != __NR_nanosleep) return 0; - ts = (void *)PT_REGS_PARM1_CORE(regs); + ts = (void *)PT_REGS_PARM1_CORE_SYSCALL(regs); if (bpf_probe_read_user(&tv_nsec, sizeof(ts->tv_nsec), &ts->tv_nsec) || tv_nsec != MY_TV_NSEC) return 0; @@ -60,7 +60,7 @@ int BPF_PROG(handle__tp_btf, struct pt_regs *regs, long id) if (id != __NR_nanosleep) return 0; - ts = (void *)PT_REGS_PARM1_CORE(regs); + ts = (void *)PT_REGS_PARM1_CORE_SYSCALL(regs); if (bpf_probe_read_user(&tv_nsec, sizeof(ts->tv_nsec), &ts->tv_nsec) || tv_nsec != MY_TV_NSEC) return 0; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c index 53b64c999450..297c260fc364 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c @@ -9,6 +9,12 @@ int _xdp_adjust_tail_grow(struct xdp_md *xdp) void *data = (void *)(long)xdp->data; int data_len = bpf_xdp_get_buff_len(xdp); int offset = 0; + /* SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) */ +#if defined(__TARGET_ARCH_s390) + int tailroom = 512; +#else + int tailroom = 320; +#endif /* Data length determine test case */ @@ -20,7 +26,7 @@ int _xdp_adjust_tail_grow(struct xdp_md *xdp) offset = 128; } else if (data_len == 128) { /* Max tail grow 3520 */ - offset = 4096 - 256 - 320 - data_len; + offset = 4096 - 256 - tailroom - data_len; } else if (data_len == 9000) { offset = 10; } else if (data_len == 9001) { diff --git a/tools/testing/selftests/bpf/progs/xdp_features.c b/tools/testing/selftests/bpf/progs/xdp_features.c new file mode 100644 index 000000000000..87c247d56f72 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/xdp_features.c @@ -0,0 +1,269 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <stdbool.h> +#include <linux/bpf.h> +#include <linux/netdev.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> +#include <bpf/bpf_tracing.h> +#include <linux/if_ether.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/in.h> +#include <linux/in6.h> +#include <linux/udp.h> +#include <asm-generic/errno-base.h> + +#include "xdp_features.h" + +#define ipv6_addr_equal(a, b) ((a).s6_addr32[0] == (b).s6_addr32[0] && \ + (a).s6_addr32[1] == (b).s6_addr32[1] && \ + (a).s6_addr32[2] == (b).s6_addr32[2] && \ + (a).s6_addr32[3] == (b).s6_addr32[3]) + +struct net_device; +struct bpf_prog; + +struct xdp_cpumap_stats { + unsigned int redirect; + unsigned int pass; + unsigned int drop; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, __u32); + __type(value, __u32); + __uint(max_entries, 1); +} stats SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, __u32); + __type(value, __u32); + __uint(max_entries, 1); +} dut_stats SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_CPUMAP); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_cpumap_val)); + __uint(max_entries, 1); +} cpu_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_DEVMAP); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_devmap_val)); + __uint(max_entries, 1); +} dev_map SEC(".maps"); + +const volatile struct in6_addr tester_addr; +const volatile struct in6_addr dut_addr; + +static __always_inline int +xdp_process_echo_packet(struct xdp_md *xdp, bool dut) +{ + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + struct ethhdr *eh = data; + struct tlv_hdr *tlv; + struct udphdr *uh; + __be16 port; + __u8 *cmd; + + if (eh + 1 > (struct ethhdr *)data_end) + return -EINVAL; + + if (eh->h_proto == bpf_htons(ETH_P_IP)) { + struct iphdr *ih = (struct iphdr *)(eh + 1); + __be32 saddr = dut ? tester_addr.s6_addr32[3] + : dut_addr.s6_addr32[3]; + __be32 daddr = dut ? dut_addr.s6_addr32[3] + : tester_addr.s6_addr32[3]; + + ih = (struct iphdr *)(eh + 1); + if (ih + 1 > (struct iphdr *)data_end) + return -EINVAL; + + if (saddr != ih->saddr) + return -EINVAL; + + if (daddr != ih->daddr) + return -EINVAL; + + if (ih->protocol != IPPROTO_UDP) + return -EINVAL; + + uh = (struct udphdr *)(ih + 1); + } else if (eh->h_proto == bpf_htons(ETH_P_IPV6)) { + struct in6_addr saddr = dut ? tester_addr : dut_addr; + struct in6_addr daddr = dut ? dut_addr : tester_addr; + struct ipv6hdr *ih6 = (struct ipv6hdr *)(eh + 1); + + if (ih6 + 1 > (struct ipv6hdr *)data_end) + return -EINVAL; + + if (!ipv6_addr_equal(saddr, ih6->saddr)) + return -EINVAL; + + if (!ipv6_addr_equal(daddr, ih6->daddr)) + return -EINVAL; + + if (ih6->nexthdr != IPPROTO_UDP) + return -EINVAL; + + uh = (struct udphdr *)(ih6 + 1); + } else { + return -EINVAL; + } + + if (uh + 1 > (struct udphdr *)data_end) + return -EINVAL; + + port = dut ? uh->dest : uh->source; + if (port != bpf_htons(DUT_ECHO_PORT)) + return -EINVAL; + + tlv = (struct tlv_hdr *)(uh + 1); + if (tlv + 1 > data_end) + return -EINVAL; + + return bpf_htons(tlv->type) == CMD_ECHO ? 0 : -EINVAL; +} + +static __always_inline int +xdp_update_stats(struct xdp_md *xdp, bool tx, bool dut) +{ + __u32 *val, key = 0; + + if (xdp_process_echo_packet(xdp, tx)) + return -EINVAL; + + if (dut) + val = bpf_map_lookup_elem(&dut_stats, &key); + else + val = bpf_map_lookup_elem(&stats, &key); + + if (val) + __sync_add_and_fetch(val, 1); + + return 0; +} + +/* Tester */ + +SEC("xdp") +int xdp_tester_check_tx(struct xdp_md *xdp) +{ + xdp_update_stats(xdp, true, false); + + return XDP_PASS; +} + +SEC("xdp") +int xdp_tester_check_rx(struct xdp_md *xdp) +{ + xdp_update_stats(xdp, false, false); + + return XDP_PASS; +} + +/* DUT */ + +SEC("xdp") +int xdp_do_pass(struct xdp_md *xdp) +{ + xdp_update_stats(xdp, true, true); + + return XDP_PASS; +} + +SEC("xdp") +int xdp_do_drop(struct xdp_md *xdp) +{ + if (xdp_update_stats(xdp, true, true)) + return XDP_PASS; + + return XDP_DROP; +} + +SEC("xdp") +int xdp_do_aborted(struct xdp_md *xdp) +{ + if (xdp_process_echo_packet(xdp, true)) + return XDP_PASS; + + return XDP_ABORTED; +} + +SEC("xdp") +int xdp_do_tx(struct xdp_md *xdp) +{ + void *data = (void *)(long)xdp->data; + struct ethhdr *eh = data; + __u8 tmp_mac[ETH_ALEN]; + + if (xdp_update_stats(xdp, true, true)) + return XDP_PASS; + + __builtin_memcpy(tmp_mac, eh->h_source, ETH_ALEN); + __builtin_memcpy(eh->h_source, eh->h_dest, ETH_ALEN); + __builtin_memcpy(eh->h_dest, tmp_mac, ETH_ALEN); + + return XDP_TX; +} + +SEC("xdp") +int xdp_do_redirect(struct xdp_md *xdp) +{ + if (xdp_process_echo_packet(xdp, true)) + return XDP_PASS; + + return bpf_redirect_map(&cpu_map, 0, 0); +} + +SEC("tp_btf/xdp_exception") +int BPF_PROG(xdp_exception, const struct net_device *dev, + const struct bpf_prog *xdp, __u32 act) +{ + __u32 *val, key = 0; + + val = bpf_map_lookup_elem(&dut_stats, &key); + if (val) + __sync_add_and_fetch(val, 1); + + return 0; +} + +SEC("tp_btf/xdp_cpumap_kthread") +int BPF_PROG(tp_xdp_cpumap_kthread, int map_id, unsigned int processed, + unsigned int drops, int sched, struct xdp_cpumap_stats *xdp_stats) +{ + __u32 *val, key = 0; + + val = bpf_map_lookup_elem(&dut_stats, &key); + if (val) + __sync_add_and_fetch(val, 1); + + return 0; +} + +SEC("xdp/cpumap") +int xdp_do_redirect_cpumap(struct xdp_md *xdp) +{ + void *data = (void *)(long)xdp->data; + struct ethhdr *eh = data; + __u8 tmp_mac[ETH_ALEN]; + + if (xdp_process_echo_packet(xdp, true)) + return XDP_PASS; + + __builtin_memcpy(tmp_mac, eh->h_source, ETH_ALEN); + __builtin_memcpy(eh->h_source, eh->h_dest, ETH_ALEN); + __builtin_memcpy(eh->h_dest, tmp_mac, ETH_ALEN); + + return bpf_redirect_map(&dev_map, 0, 0); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c index 25b8178735ee..4c55b4d79d3d 100644 --- a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c +++ b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c @@ -70,10 +70,14 @@ int rx(struct xdp_md *ctx) } if (!bpf_xdp_metadata_rx_timestamp(ctx, &meta->rx_timestamp)) - bpf_printk("populated rx_timestamp with %u", meta->rx_timestamp); + bpf_printk("populated rx_timestamp with %llu", meta->rx_timestamp); + else + meta->rx_timestamp = 0; /* Used by AF_XDP as not avail signal */ if (!bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash)) bpf_printk("populated rx_hash with %u", meta->rx_hash); + else + meta->rx_hash = 0; /* Used by AF_XDP as not avail signal */ return bpf_redirect_map(&xsk, ctx->rx_queue_index, XDP_PASS); } diff --git a/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c b/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c index 736686e903f6..07d786329105 100644 --- a/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c +++ b/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c @@ -310,7 +310,7 @@ static __always_inline void values_get_tcpipopts(__u16 *mss, __u8 *wscale, static __always_inline void values_inc_synacks(void) { __u32 key = 1; - __u32 *value; + __u64 *value; value = bpf_map_lookup_elem(&values, &key); if (value) diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index c5f852163246..6d5e3022c75f 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -17,6 +17,7 @@ #include <sys/select.h> #include <sys/socket.h> #include <sys/un.h> +#include <bpf/btf.h> static bool verbose(void) { @@ -967,6 +968,43 @@ int write_sysctl(const char *sysctl, const char *value) return 0; } +int get_bpf_max_tramp_links_from(struct btf *btf) +{ + const struct btf_enum *e; + const struct btf_type *t; + __u32 i, type_cnt; + const char *name; + __u16 j, vlen; + + for (i = 1, type_cnt = btf__type_cnt(btf); i < type_cnt; i++) { + t = btf__type_by_id(btf, i); + if (!t || !btf_is_enum(t) || t->name_off) + continue; + e = btf_enum(t); + for (j = 0, vlen = btf_vlen(t); j < vlen; j++, e++) { + name = btf__str_by_offset(btf, e->name_off); + if (name && !strcmp(name, "BPF_MAX_TRAMP_LINKS")) + return e->val; + } + } + + return -1; +} + +int get_bpf_max_tramp_links(void) +{ + struct btf *vmlinux_btf; + int ret; + + vmlinux_btf = btf__load_vmlinux_btf(); + if (!ASSERT_OK_PTR(vmlinux_btf, "vmlinux btf")) + return -1; + ret = get_bpf_max_tramp_links_from(vmlinux_btf); + btf__free(vmlinux_btf); + + return ret; +} + #define MAX_BACKTRACE_SZ 128 void crash_handler(int signum) { diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h index 3f058dfadbaf..d5d51ec97ec8 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -394,6 +394,8 @@ int kern_sync_rcu(void); int trigger_module_test_read(int read_sz); int trigger_module_test_write(int write_sz); int write_sysctl(const char *sysctl, const char *value); +int get_bpf_max_tramp_links_from(struct btf *btf); +int get_bpf_max_tramp_links(void); #ifdef __x86_64__ #define SYS_NANOSLEEP_KPROBE_NAME "__x64_sys_nanosleep" diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 8c808551dfd7..887c49dc5abd 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -209,7 +209,7 @@ loop: insn[i++] = BPF_MOV64_IMM(BPF_REG_2, 1); insn[i++] = BPF_MOV64_IMM(BPF_REG_3, 2); insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, - BPF_FUNC_skb_vlan_push), + BPF_FUNC_skb_vlan_push); insn[i] = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, len - i - 3); i++; } @@ -220,7 +220,7 @@ loop: i++; insn[i++] = BPF_MOV64_REG(BPF_REG_1, BPF_REG_6); insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, - BPF_FUNC_skb_vlan_pop), + BPF_FUNC_skb_vlan_pop); insn[i] = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, len - i - 3); i++; } diff --git a/tools/testing/selftests/bpf/test_xdp_features.sh b/tools/testing/selftests/bpf/test_xdp_features.sh new file mode 100755 index 000000000000..0aa71c4455c0 --- /dev/null +++ b/tools/testing/selftests/bpf/test_xdp_features.sh @@ -0,0 +1,107 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +readonly NS="ns1-$(mktemp -u XXXXXX)" +readonly V0_IP4=10.10.0.11 +readonly V1_IP4=10.10.0.1 +readonly V0_IP6=2001:db8::11 +readonly V1_IP6=2001:db8::1 + +ret=1 + +setup() { + { + ip netns add ${NS} + + ip link add v1 type veth peer name v0 netns ${NS} + + ip link set v1 up + ip addr add $V1_IP4/24 dev v1 + ip addr add $V1_IP6/64 nodad dev v1 + ip -n ${NS} link set dev v0 up + ip -n ${NS} addr add $V0_IP4/24 dev v0 + ip -n ${NS} addr add $V0_IP6/64 nodad dev v0 + + # Enable XDP mode and disable checksum offload + ethtool -K v1 gro on + ethtool -K v1 tx-checksumming off + ip netns exec ${NS} ethtool -K v0 gro on + ip netns exec ${NS} ethtool -K v0 tx-checksumming off + } > /dev/null 2>&1 +} + +cleanup() { + ip link del v1 2> /dev/null + ip netns del ${NS} 2> /dev/null + [ "$(pidof xdp_features)" = "" ] || kill $(pidof xdp_features) 2> /dev/null +} + +wait_for_dut_server() { + while sleep 1; do + ss -tlp | grep -q xdp_features + [ $? -eq 0 ] && break + done +} + +test_xdp_features() { + setup + + ## XDP_PASS + ./xdp_features -f XDP_PASS -D $V1_IP6 -T $V0_IP6 v1 & + wait_for_dut_server + ip netns exec ${NS} ./xdp_features -t -f XDP_PASS \ + -D $V1_IP6 -C $V1_IP6 \ + -T $V0_IP6 v0 + [ $? -ne 0 ] && exit + + ## XDP_DROP + ./xdp_features -f XDP_DROP -D ::ffff:$V1_IP4 -T ::ffff:$V0_IP4 v1 & + wait_for_dut_server + ip netns exec ${NS} ./xdp_features -t -f XDP_DROP \ + -D ::ffff:$V1_IP4 \ + -C ::ffff:$V1_IP4 \ + -T ::ffff:$V0_IP4 v0 + [ $? -ne 0 ] && exit + + ## XDP_ABORTED + ./xdp_features -f XDP_ABORTED -D $V1_IP6 -T $V0_IP6 v1 & + wait_for_dut_server + ip netns exec ${NS} ./xdp_features -t -f XDP_ABORTED \ + -D $V1_IP6 -C $V1_IP6 \ + -T $V0_IP6 v0 + [ $? -ne 0 ] && exit + + ## XDP_TX + ./xdp_features -f XDP_TX -D ::ffff:$V1_IP4 -T ::ffff:$V0_IP4 v1 & + wait_for_dut_server + ip netns exec ${NS} ./xdp_features -t -f XDP_TX \ + -D ::ffff:$V1_IP4 \ + -C ::ffff:$V1_IP4 \ + -T ::ffff:$V0_IP4 v0 + [ $? -ne 0 ] && exit + + ## XDP_REDIRECT + ./xdp_features -f XDP_REDIRECT -D $V1_IP6 -T $V0_IP6 v1 & + wait_for_dut_server + ip netns exec ${NS} ./xdp_features -t -f XDP_REDIRECT \ + -D $V1_IP6 -C $V1_IP6 \ + -T $V0_IP6 v0 + [ $? -ne 0 ] && exit + + ## XDP_NDO_XMIT + ./xdp_features -f XDP_NDO_XMIT -D ::ffff:$V1_IP4 -T ::ffff:$V0_IP4 v1 & + wait_for_dut_server + ip netns exec ${NS} ./xdp_features -t -f XDP_NDO_XMIT \ + -D ::ffff:$V1_IP4 \ + -C ::ffff:$V1_IP4 \ + -T ::ffff:$V0_IP4 v0 + ret=$? + cleanup +} + +set -e +trap cleanup 2 3 6 9 + +test_xdp_features + +exit $ret diff --git a/tools/testing/selftests/bpf/vmtest.sh b/tools/testing/selftests/bpf/vmtest.sh index 316a56d680f2..685034528018 100755 --- a/tools/testing/selftests/bpf/vmtest.sh +++ b/tools/testing/selftests/bpf/vmtest.sh @@ -13,7 +13,7 @@ s390x) QEMU_BINARY=qemu-system-s390x QEMU_CONSOLE="ttyS1" QEMU_FLAGS=(-smp 2) - BZIMAGE="arch/s390/boot/compressed/vmlinux" + BZIMAGE="arch/s390/boot/vmlinux" ;; x86_64) QEMU_BINARY=qemu-system-x86_64 diff --git a/tools/testing/selftests/bpf/xdp_features.c b/tools/testing/selftests/bpf/xdp_features.c new file mode 100644 index 000000000000..fce12165213b --- /dev/null +++ b/tools/testing/selftests/bpf/xdp_features.c @@ -0,0 +1,699 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <uapi/linux/bpf.h> +#include <uapi/linux/netdev.h> +#include <linux/if_link.h> +#include <signal.h> +#include <argp.h> +#include <net/if.h> +#include <sys/socket.h> +#include <netinet/in.h> +#include <netinet/tcp.h> +#include <unistd.h> +#include <arpa/inet.h> +#include <bpf/bpf.h> +#include <bpf/libbpf.h> +#include <pthread.h> + +#include <network_helpers.h> + +#include "xdp_features.skel.h" +#include "xdp_features.h" + +#define RED(str) "\033[0;31m" str "\033[0m" +#define GREEN(str) "\033[0;32m" str "\033[0m" +#define YELLOW(str) "\033[0;33m" str "\033[0m" + +static struct env { + bool verbosity; + int ifindex; + bool is_tester; + struct { + enum netdev_xdp_act drv_feature; + enum xdp_action action; + } feature; + struct sockaddr_storage dut_ctrl_addr; + struct sockaddr_storage dut_addr; + struct sockaddr_storage tester_addr; +} env; + +#define BUFSIZE 128 + +void test__fail(void) { /* for network_helpers.c */ } + +static int libbpf_print_fn(enum libbpf_print_level level, + const char *format, va_list args) +{ + if (level == LIBBPF_DEBUG && !env.verbosity) + return 0; + return vfprintf(stderr, format, args); +} + +static volatile bool exiting; + +static void sig_handler(int sig) +{ + exiting = true; +} + +const char *argp_program_version = "xdp-features 0.0"; +const char argp_program_doc[] = +"XDP features detection application.\n" +"\n" +"XDP features application checks the XDP advertised features match detected ones.\n" +"\n" +"USAGE: ./xdp-features [-vt] [-f <xdp-feature>] [-D <dut-data-ip>] [-T <tester-data-ip>] [-C <dut-ctrl-ip>] <iface-name>\n" +"\n" +"dut-data-ip, tester-data-ip, dut-ctrl-ip: IPv6 or IPv4-mapped-IPv6 addresses;\n" +"\n" +"XDP features\n:" +"- XDP_PASS\n" +"- XDP_DROP\n" +"- XDP_ABORTED\n" +"- XDP_REDIRECT\n" +"- XDP_NDO_XMIT\n" +"- XDP_TX\n"; + +static const struct argp_option opts[] = { + { "verbose", 'v', NULL, 0, "Verbose debug output" }, + { "tester", 't', NULL, 0, "Tester mode" }, + { "feature", 'f', "XDP-FEATURE", 0, "XDP feature to test" }, + { "dut_data_ip", 'D', "DUT-DATA-IP", 0, "DUT IP data channel" }, + { "dut_ctrl_ip", 'C', "DUT-CTRL-IP", 0, "DUT IP control channel" }, + { "tester_data_ip", 'T', "TESTER-DATA-IP", 0, "Tester IP data channel" }, + {}, +}; + +static int get_xdp_feature(const char *arg) +{ + if (!strcmp(arg, "XDP_PASS")) { + env.feature.action = XDP_PASS; + env.feature.drv_feature = NETDEV_XDP_ACT_BASIC; + } else if (!strcmp(arg, "XDP_DROP")) { + env.feature.drv_feature = NETDEV_XDP_ACT_BASIC; + env.feature.action = XDP_DROP; + } else if (!strcmp(arg, "XDP_ABORTED")) { + env.feature.drv_feature = NETDEV_XDP_ACT_BASIC; + env.feature.action = XDP_ABORTED; + } else if (!strcmp(arg, "XDP_TX")) { + env.feature.drv_feature = NETDEV_XDP_ACT_BASIC; + env.feature.action = XDP_TX; + } else if (!strcmp(arg, "XDP_REDIRECT")) { + env.feature.drv_feature = NETDEV_XDP_ACT_REDIRECT; + env.feature.action = XDP_REDIRECT; + } else if (!strcmp(arg, "XDP_NDO_XMIT")) { + env.feature.drv_feature = NETDEV_XDP_ACT_NDO_XMIT; + } else { + return -EINVAL; + } + + return 0; +} + +static char *get_xdp_feature_str(void) +{ + switch (env.feature.action) { + case XDP_PASS: + return YELLOW("XDP_PASS"); + case XDP_DROP: + return YELLOW("XDP_DROP"); + case XDP_ABORTED: + return YELLOW("XDP_ABORTED"); + case XDP_TX: + return YELLOW("XDP_TX"); + case XDP_REDIRECT: + return YELLOW("XDP_REDIRECT"); + default: + break; + } + + if (env.feature.drv_feature == NETDEV_XDP_ACT_NDO_XMIT) + return YELLOW("XDP_NDO_XMIT"); + + return ""; +} + +static error_t parse_arg(int key, char *arg, struct argp_state *state) +{ + switch (key) { + case 'v': + env.verbosity = true; + break; + case 't': + env.is_tester = true; + break; + case 'f': + if (get_xdp_feature(arg) < 0) { + fprintf(stderr, "Invalid xdp feature: %s\n", arg); + argp_usage(state); + return ARGP_ERR_UNKNOWN; + } + break; + case 'D': + if (make_sockaddr(AF_INET6, arg, DUT_ECHO_PORT, + &env.dut_addr, NULL)) { + fprintf(stderr, "Invalid DUT address: %s\n", arg); + return ARGP_ERR_UNKNOWN; + } + break; + case 'C': + if (make_sockaddr(AF_INET6, arg, DUT_CTRL_PORT, + &env.dut_ctrl_addr, NULL)) { + fprintf(stderr, "Invalid DUT CTRL address: %s\n", arg); + return ARGP_ERR_UNKNOWN; + } + break; + case 'T': + if (make_sockaddr(AF_INET6, arg, 0, &env.tester_addr, NULL)) { + fprintf(stderr, "Invalid Tester address: %s\n", arg); + return ARGP_ERR_UNKNOWN; + } + break; + case ARGP_KEY_ARG: + errno = 0; + if (strlen(arg) >= IF_NAMESIZE) { + fprintf(stderr, "Invalid device name: %s\n", arg); + argp_usage(state); + return ARGP_ERR_UNKNOWN; + } + + env.ifindex = if_nametoindex(arg); + if (!env.ifindex) + env.ifindex = strtoul(arg, NULL, 0); + if (!env.ifindex) { + fprintf(stderr, + "Bad interface index or name (%d): %s\n", + errno, strerror(errno)); + argp_usage(state); + return ARGP_ERR_UNKNOWN; + } + break; + default: + return ARGP_ERR_UNKNOWN; + } + + return 0; +} + +static const struct argp argp = { + .options = opts, + .parser = parse_arg, + .doc = argp_program_doc, +}; + +static void set_env_default(void) +{ + env.feature.drv_feature = NETDEV_XDP_ACT_NDO_XMIT; + env.feature.action = -EINVAL; + env.ifindex = -ENODEV; + make_sockaddr(AF_INET6, "::ffff:127.0.0.1", DUT_CTRL_PORT, + &env.dut_ctrl_addr, NULL); + make_sockaddr(AF_INET6, "::ffff:127.0.0.1", DUT_ECHO_PORT, + &env.dut_addr, NULL); + make_sockaddr(AF_INET6, "::ffff:127.0.0.1", 0, &env.tester_addr, NULL); +} + +static void *dut_echo_thread(void *arg) +{ + unsigned char buf[sizeof(struct tlv_hdr)]; + int sockfd = *(int *)arg; + + while (!exiting) { + struct tlv_hdr *tlv = (struct tlv_hdr *)buf; + struct sockaddr_storage addr; + socklen_t addrlen; + size_t n; + + n = recvfrom(sockfd, buf, sizeof(buf), MSG_WAITALL, + (struct sockaddr *)&addr, &addrlen); + if (n != ntohs(tlv->len)) + continue; + + if (ntohs(tlv->type) != CMD_ECHO) + continue; + + sendto(sockfd, buf, sizeof(buf), MSG_NOSIGNAL | MSG_CONFIRM, + (struct sockaddr *)&addr, addrlen); + } + + pthread_exit((void *)0); + close(sockfd); + + return NULL; +} + +static int dut_run_echo_thread(pthread_t *t, int *sockfd) +{ + int err; + + sockfd = start_reuseport_server(AF_INET6, SOCK_DGRAM, NULL, + DUT_ECHO_PORT, 0, 1); + if (!sockfd) { + fprintf(stderr, "Failed to create echo socket\n"); + return -errno; + } + + /* start echo channel */ + err = pthread_create(t, NULL, dut_echo_thread, sockfd); + if (err) { + fprintf(stderr, "Failed creating dut_echo thread: %s\n", + strerror(-err)); + free_fds(sockfd, 1); + return -EINVAL; + } + + return 0; +} + +static int dut_attach_xdp_prog(struct xdp_features *skel, int flags) +{ + enum xdp_action action = env.feature.action; + struct bpf_program *prog; + unsigned int key = 0; + int err, fd = 0; + + if (env.feature.drv_feature == NETDEV_XDP_ACT_NDO_XMIT) { + struct bpf_devmap_val entry = { + .ifindex = env.ifindex, + }; + + err = bpf_map__update_elem(skel->maps.dev_map, + &key, sizeof(key), + &entry, sizeof(entry), 0); + if (err < 0) + return err; + + fd = bpf_program__fd(skel->progs.xdp_do_redirect_cpumap); + action = XDP_REDIRECT; + } + + switch (action) { + case XDP_TX: + prog = skel->progs.xdp_do_tx; + break; + case XDP_DROP: + prog = skel->progs.xdp_do_drop; + break; + case XDP_ABORTED: + prog = skel->progs.xdp_do_aborted; + break; + case XDP_PASS: + prog = skel->progs.xdp_do_pass; + break; + case XDP_REDIRECT: { + struct bpf_cpumap_val entry = { + .qsize = 2048, + .bpf_prog.fd = fd, + }; + + err = bpf_map__update_elem(skel->maps.cpu_map, + &key, sizeof(key), + &entry, sizeof(entry), 0); + if (err < 0) + return err; + + prog = skel->progs.xdp_do_redirect; + break; + } + default: + return -EINVAL; + } + + err = bpf_xdp_attach(env.ifindex, bpf_program__fd(prog), flags, NULL); + if (err) + fprintf(stderr, + "Failed to attach XDP program to ifindex %d\n", + env.ifindex); + return err; +} + +static int recv_msg(int sockfd, void *buf, size_t bufsize, void *val, + size_t val_size) +{ + struct tlv_hdr *tlv = (struct tlv_hdr *)buf; + size_t len; + + len = recv(sockfd, buf, bufsize, 0); + if (len != ntohs(tlv->len) || len < sizeof(*tlv)) + return -EINVAL; + + if (val) { + len -= sizeof(*tlv); + if (len > val_size) + return -ENOMEM; + + memcpy(val, tlv->data, len); + } + + return 0; +} + +static int dut_run(struct xdp_features *skel) +{ + int flags = XDP_FLAGS_UPDATE_IF_NOEXIST | XDP_FLAGS_DRV_MODE; + int state, err, *sockfd, ctrl_sockfd, echo_sockfd; + struct sockaddr_storage ctrl_addr; + pthread_t dut_thread; + socklen_t addrlen; + + sockfd = start_reuseport_server(AF_INET6, SOCK_STREAM, NULL, + DUT_CTRL_PORT, 0, 1); + if (!sockfd) { + fprintf(stderr, "Failed to create DUT socket\n"); + return -errno; + } + + ctrl_sockfd = accept(*sockfd, (struct sockaddr *)&ctrl_addr, &addrlen); + if (ctrl_sockfd < 0) { + fprintf(stderr, "Failed to accept connection on DUT socket\n"); + free_fds(sockfd, 1); + return -errno; + } + + /* CTRL loop */ + while (!exiting) { + unsigned char buf[BUFSIZE] = {}; + struct tlv_hdr *tlv = (struct tlv_hdr *)buf; + + err = recv_msg(ctrl_sockfd, buf, BUFSIZE, NULL, 0); + if (err) + continue; + + switch (ntohs(tlv->type)) { + case CMD_START: { + if (state == CMD_START) + continue; + + state = CMD_START; + /* Load the XDP program on the DUT */ + err = dut_attach_xdp_prog(skel, flags); + if (err) + goto out; + + err = dut_run_echo_thread(&dut_thread, &echo_sockfd); + if (err < 0) + goto out; + + tlv->type = htons(CMD_ACK); + tlv->len = htons(sizeof(*tlv)); + err = send(ctrl_sockfd, buf, sizeof(*tlv), 0); + if (err < 0) + goto end_thread; + break; + } + case CMD_STOP: + if (state != CMD_START) + break; + + state = CMD_STOP; + + exiting = true; + bpf_xdp_detach(env.ifindex, flags, NULL); + + tlv->type = htons(CMD_ACK); + tlv->len = htons(sizeof(*tlv)); + err = send(ctrl_sockfd, buf, sizeof(*tlv), 0); + goto end_thread; + case CMD_GET_XDP_CAP: { + LIBBPF_OPTS(bpf_xdp_query_opts, opts); + unsigned long long val; + size_t n; + + err = bpf_xdp_query(env.ifindex, XDP_FLAGS_DRV_MODE, + &opts); + if (err) { + fprintf(stderr, + "Failed to query XDP cap for ifindex %d\n", + env.ifindex); + goto end_thread; + } + + tlv->type = htons(CMD_ACK); + n = sizeof(*tlv) + sizeof(opts.feature_flags); + tlv->len = htons(n); + + val = htobe64(opts.feature_flags); + memcpy(tlv->data, &val, sizeof(val)); + + err = send(ctrl_sockfd, buf, n, 0); + if (err < 0) + goto end_thread; + break; + } + case CMD_GET_STATS: { + unsigned int key = 0, val; + size_t n; + + err = bpf_map__lookup_elem(skel->maps.dut_stats, + &key, sizeof(key), + &val, sizeof(val), 0); + if (err) { + fprintf(stderr, "bpf_map_lookup_elem failed\n"); + goto end_thread; + } + + tlv->type = htons(CMD_ACK); + n = sizeof(*tlv) + sizeof(val); + tlv->len = htons(n); + + val = htonl(val); + memcpy(tlv->data, &val, sizeof(val)); + + err = send(ctrl_sockfd, buf, n, 0); + if (err < 0) + goto end_thread; + break; + } + default: + break; + } + } + +end_thread: + pthread_join(dut_thread, NULL); +out: + bpf_xdp_detach(env.ifindex, flags, NULL); + close(ctrl_sockfd); + free_fds(sockfd, 1); + + return err; +} + +static bool tester_collect_detected_cap(struct xdp_features *skel, + unsigned int dut_stats) +{ + unsigned int err, key = 0, val; + + if (!dut_stats) + return false; + + err = bpf_map__lookup_elem(skel->maps.stats, &key, sizeof(key), + &val, sizeof(val), 0); + if (err) { + fprintf(stderr, "bpf_map_lookup_elem failed\n"); + return false; + } + + switch (env.feature.action) { + case XDP_PASS: + case XDP_TX: + case XDP_REDIRECT: + return val > 0; + case XDP_DROP: + case XDP_ABORTED: + return val == 0; + default: + break; + } + + if (env.feature.drv_feature == NETDEV_XDP_ACT_NDO_XMIT) + return val > 0; + + return false; +} + +static int send_and_recv_msg(int sockfd, enum test_commands cmd, void *val, + size_t val_size) +{ + unsigned char buf[BUFSIZE] = {}; + struct tlv_hdr *tlv = (struct tlv_hdr *)buf; + int err; + + tlv->type = htons(cmd); + tlv->len = htons(sizeof(*tlv)); + + err = send(sockfd, buf, sizeof(*tlv), 0); + if (err < 0) + return err; + + err = recv_msg(sockfd, buf, BUFSIZE, val, val_size); + if (err < 0) + return err; + + return ntohs(tlv->type) == CMD_ACK ? 0 : -EINVAL; +} + +static int send_echo_msg(void) +{ + unsigned char buf[sizeof(struct tlv_hdr)]; + struct tlv_hdr *tlv = (struct tlv_hdr *)buf; + int sockfd, n; + + sockfd = socket(AF_INET6, SOCK_DGRAM, 0); + if (sockfd < 0) { + fprintf(stderr, "Failed to create echo socket\n"); + return -errno; + } + + tlv->type = htons(CMD_ECHO); + tlv->len = htons(sizeof(*tlv)); + + n = sendto(sockfd, buf, sizeof(*tlv), MSG_NOSIGNAL | MSG_CONFIRM, + (struct sockaddr *)&env.dut_addr, sizeof(env.dut_addr)); + close(sockfd); + + return n == ntohs(tlv->len) ? 0 : -EINVAL; +} + +static int tester_run(struct xdp_features *skel) +{ + int flags = XDP_FLAGS_UPDATE_IF_NOEXIST | XDP_FLAGS_DRV_MODE; + unsigned long long advertised_feature; + struct bpf_program *prog; + unsigned int stats; + int i, err, sockfd; + bool detected_cap; + + sockfd = socket(AF_INET6, SOCK_STREAM, 0); + if (sockfd < 0) { + fprintf(stderr, "Failed to create tester socket\n"); + return -errno; + } + + if (settimeo(sockfd, 1000) < 0) + return -EINVAL; + + err = connect(sockfd, (struct sockaddr *)&env.dut_ctrl_addr, + sizeof(env.dut_ctrl_addr)); + if (err) { + fprintf(stderr, "Failed to connect to the DUT\n"); + return -errno; + } + + err = send_and_recv_msg(sockfd, CMD_GET_XDP_CAP, &advertised_feature, + sizeof(advertised_feature)); + if (err < 0) { + close(sockfd); + return err; + } + + advertised_feature = be64toh(advertised_feature); + + if (env.feature.drv_feature == NETDEV_XDP_ACT_NDO_XMIT || + env.feature.action == XDP_TX) + prog = skel->progs.xdp_tester_check_tx; + else + prog = skel->progs.xdp_tester_check_rx; + + err = bpf_xdp_attach(env.ifindex, bpf_program__fd(prog), flags, NULL); + if (err) { + fprintf(stderr, "Failed to attach XDP program to ifindex %d\n", + env.ifindex); + goto out; + } + + err = send_and_recv_msg(sockfd, CMD_START, NULL, 0); + if (err) + goto out; + + for (i = 0; i < 10 && !exiting; i++) { + err = send_echo_msg(); + if (err < 0) + goto out; + + sleep(1); + } + + err = send_and_recv_msg(sockfd, CMD_GET_STATS, &stats, sizeof(stats)); + if (err) + goto out; + + /* stop the test */ + err = send_and_recv_msg(sockfd, CMD_STOP, NULL, 0); + /* send a new echo message to wake echo thread of the dut */ + send_echo_msg(); + + detected_cap = tester_collect_detected_cap(skel, ntohl(stats)); + + fprintf(stdout, "Feature %s: [%s][%s]\n", get_xdp_feature_str(), + detected_cap ? GREEN("DETECTED") : RED("NOT DETECTED"), + env.feature.drv_feature & advertised_feature ? GREEN("ADVERTISED") + : RED("NOT ADVERTISED")); +out: + bpf_xdp_detach(env.ifindex, flags, NULL); + close(sockfd); + return err < 0 ? err : 0; +} + +int main(int argc, char **argv) +{ + struct xdp_features *skel; + int err; + + libbpf_set_strict_mode(LIBBPF_STRICT_ALL); + libbpf_set_print(libbpf_print_fn); + + signal(SIGINT, sig_handler); + signal(SIGTERM, sig_handler); + + set_env_default(); + + /* Parse command line arguments */ + err = argp_parse(&argp, argc, argv, 0, NULL, NULL); + if (err) + return err; + + if (env.ifindex < 0) { + fprintf(stderr, "Invalid ifindex\n"); + return -ENODEV; + } + + /* Load and verify BPF application */ + skel = xdp_features__open(); + if (!skel) { + fprintf(stderr, "Failed to open and load BPF skeleton\n"); + return -EINVAL; + } + + skel->rodata->tester_addr = + ((struct sockaddr_in6 *)&env.tester_addr)->sin6_addr; + skel->rodata->dut_addr = + ((struct sockaddr_in6 *)&env.dut_addr)->sin6_addr; + + /* Load & verify BPF programs */ + err = xdp_features__load(skel); + if (err) { + fprintf(stderr, "Failed to load and verify BPF skeleton\n"); + goto cleanup; + } + + err = xdp_features__attach(skel); + if (err) { + fprintf(stderr, "Failed to attach BPF skeleton\n"); + goto cleanup; + } + + if (env.is_tester) { + /* Tester */ + fprintf(stdout, "Starting tester on device %d\n", env.ifindex); + err = tester_run(skel); + } else { + /* DUT */ + fprintf(stdout, "Starting DUT on device %d\n", env.ifindex); + err = dut_run(skel); + } + +cleanup: + xdp_features__destroy(skel); + + return err < 0 ? -err : 0; +} diff --git a/tools/testing/selftests/bpf/xdp_features.h b/tools/testing/selftests/bpf/xdp_features.h new file mode 100644 index 000000000000..2670c541713b --- /dev/null +++ b/tools/testing/selftests/bpf/xdp_features.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* test commands */ +enum test_commands { + CMD_STOP, /* CMD */ + CMD_START, /* CMD */ + CMD_ECHO, /* CMD */ + CMD_ACK, /* CMD + data */ + CMD_GET_XDP_CAP, /* CMD */ + CMD_GET_STATS, /* CMD */ +}; + +#define DUT_CTRL_PORT 12345 +#define DUT_ECHO_PORT 12346 + +struct tlv_hdr { + __be16 type; + __be16 len; + __u8 data[]; +}; diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c index 3823b1c499cc..1c8acb68b977 100644 --- a/tools/testing/selftests/bpf/xdp_hw_metadata.c +++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c @@ -24,7 +24,6 @@ #include <linux/net_tstamp.h> #include <linux/udp.h> #include <linux/sockios.h> -#include <linux/net_tstamp.h> #include <sys/mman.h> #include <net/if.h> #include <poll.h> @@ -121,7 +120,7 @@ static void close_xsk(struct xsk *xsk) xsk_umem__delete(xsk->umem); if (xsk->socket) xsk_socket__delete(xsk->socket); - munmap(xsk->umem, UMEM_SIZE); + munmap(xsk->umem_area, UMEM_SIZE); } static void refill_rx(struct xsk *xsk, __u64 addr) @@ -165,7 +164,7 @@ static void verify_skb_metadata(int fd) hdr.msg_controllen = sizeof(cmsg_buf); if (recvmsg(fd, &hdr, 0) < 0) - error(-1, errno, "recvmsg"); + error(1, errno, "recvmsg"); for (cmsg = CMSG_FIRSTHDR(&hdr); cmsg != NULL; cmsg = CMSG_NXTHDR(&hdr, cmsg)) { @@ -270,16 +269,16 @@ static int rxq_num(const char *ifname) struct ifreq ifr = { .ifr_data = (void *)&ch, }; - strcpy(ifr.ifr_name, ifname); + strncpy(ifr.ifr_name, ifname, IF_NAMESIZE - 1); int fd, ret; fd = socket(AF_UNIX, SOCK_DGRAM, 0); if (fd < 0) - error(-1, errno, "socket"); + error(1, errno, "socket"); ret = ioctl(fd, SIOCETHTOOL, &ifr); if (ret < 0) - error(-1, errno, "ioctl(SIOCETHTOOL)"); + error(1, errno, "ioctl(SIOCETHTOOL)"); close(fd); @@ -291,16 +290,16 @@ static void hwtstamp_ioctl(int op, const char *ifname, struct hwtstamp_config *c struct ifreq ifr = { .ifr_data = (void *)cfg, }; - strcpy(ifr.ifr_name, ifname); + strncpy(ifr.ifr_name, ifname, IF_NAMESIZE - 1); int fd, ret; fd = socket(AF_UNIX, SOCK_DGRAM, 0); if (fd < 0) - error(-1, errno, "socket"); + error(1, errno, "socket"); ret = ioctl(fd, op, &ifr); if (ret < 0) - error(-1, errno, "ioctl(%d)", op); + error(1, errno, "ioctl(%d)", op); close(fd); } @@ -360,7 +359,7 @@ static void timestamping_enable(int fd, int val) ret = setsockopt(fd, SOL_SOCKET, SO_TIMESTAMPING, &val, sizeof(val)); if (ret < 0) - error(-1, errno, "setsockopt(SO_TIMESTAMPING)"); + error(1, errno, "setsockopt(SO_TIMESTAMPING)"); } int main(int argc, char *argv[]) @@ -386,13 +385,13 @@ int main(int argc, char *argv[]) rx_xsk = malloc(sizeof(struct xsk) * rxq); if (!rx_xsk) - error(-1, ENOMEM, "malloc"); + error(1, ENOMEM, "malloc"); for (i = 0; i < rxq; i++) { printf("open_xsk(%s, %p, %d)\n", ifname, &rx_xsk[i], i); ret = open_xsk(ifindex, &rx_xsk[i], i); if (ret) - error(-1, -ret, "open_xsk"); + error(1, -ret, "open_xsk"); printf("xsk_socket__fd() -> %d\n", xsk_socket__fd(rx_xsk[i].socket)); } @@ -400,7 +399,7 @@ int main(int argc, char *argv[]) printf("open bpf program...\n"); bpf_obj = xdp_hw_metadata__open(); if (libbpf_get_error(bpf_obj)) - error(-1, libbpf_get_error(bpf_obj), "xdp_hw_metadata__open"); + error(1, libbpf_get_error(bpf_obj), "xdp_hw_metadata__open"); prog = bpf_object__find_program_by_name(bpf_obj->obj, "rx"); bpf_program__set_ifindex(prog, ifindex); @@ -409,12 +408,12 @@ int main(int argc, char *argv[]) printf("load bpf program...\n"); ret = xdp_hw_metadata__load(bpf_obj); if (ret) - error(-1, -ret, "xdp_hw_metadata__load"); + error(1, -ret, "xdp_hw_metadata__load"); printf("prepare skb endpoint...\n"); server_fd = start_server(AF_INET6, SOCK_DGRAM, NULL, 9092, 1000); if (server_fd < 0) - error(-1, errno, "start_server"); + error(1, errno, "start_server"); timestamping_enable(server_fd, SOF_TIMESTAMPING_SOFTWARE | SOF_TIMESTAMPING_RAW_HARDWARE); @@ -427,7 +426,7 @@ int main(int argc, char *argv[]) printf("map[%d] = %d\n", queue_id, sock_fd); ret = bpf_map_update_elem(bpf_map__fd(bpf_obj->maps.xsk), &queue_id, &sock_fd, 0); if (ret) - error(-1, -ret, "bpf_map_update_elem"); + error(1, -ret, "bpf_map_update_elem"); } printf("attach bpf program...\n"); @@ -435,12 +434,12 @@ int main(int argc, char *argv[]) bpf_program__fd(bpf_obj->progs.rx), XDP_FLAGS, NULL); if (ret) - error(-1, -ret, "bpf_xdp_attach"); + error(1, -ret, "bpf_xdp_attach"); signal(SIGINT, handle_signal); ret = verify_metadata(rx_xsk, rxq, server_fd); close(server_fd); cleanup(); if (ret) - error(-1, -ret, "verify_metadata"); + error(1, -ret, "verify_metadata"); } diff --git a/tools/testing/selftests/bpf/xdp_synproxy.c b/tools/testing/selftests/bpf/xdp_synproxy.c index 410a1385a01d..6dbe0b745198 100644 --- a/tools/testing/selftests/bpf/xdp_synproxy.c +++ b/tools/testing/selftests/bpf/xdp_synproxy.c @@ -116,6 +116,7 @@ static void parse_options(int argc, char *argv[], unsigned int *ifindex, __u32 * *tcpipopts = 0; *ports = NULL; *single = false; + *tc = false; while (true) { int opt; |