diff options
| author | Jakub Kicinski <kuba@kernel.org> | 2020-12-04 07:48:11 -0800 |
|---|---|---|
| committer | Jakub Kicinski <kuba@kernel.org> | 2020-12-04 07:48:12 -0800 |
| commit | a1dd1d86973182458da7798a95f26cfcbea599b4 (patch) | |
| tree | 1adda22ea30ccfac7651a7eed7b7c90356f8243a /samples | |
| parent | 55fd59b003f6e8fd88cf16590e79823d7ccf3026 (diff) | |
| parent | eceae70bdeaeb6b8ceb662983cf663ff352fbc96 (diff) | |
| download | lwn-a1dd1d86973182458da7798a95f26cfcbea599b4.tar.gz lwn-a1dd1d86973182458da7798a95f26cfcbea599b4.zip | |
Merge https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Alexei Starovoitov says:
====================
pull-request: bpf-next 2020-12-03
The main changes are:
1) Support BTF in kernel modules, from Andrii.
2) Introduce preferred busy-polling, from Björn.
3) bpf_ima_inode_hash() and bpf_bprm_opts_set() helpers, from KP Singh.
4) Memcg-based memory accounting for bpf objects, from Roman.
5) Allow bpf_{s,g}etsockopt from cgroup bind{4,6} hooks, from Stanislav.
* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (118 commits)
selftests/bpf: Fix invalid use of strncat in test_sockmap
libbpf: Use memcpy instead of strncpy to please GCC
selftests/bpf: Add fentry/fexit/fmod_ret selftest for kernel module
selftests/bpf: Add tp_btf CO-RE reloc test for modules
libbpf: Support attachment of BPF tracing programs to kernel modules
libbpf: Factor out low-level BPF program loading helper
bpf: Allow to specify kernel module BTFs when attaching BPF programs
bpf: Remove hard-coded btf_vmlinux assumption from BPF verifier
selftests/bpf: Add CO-RE relocs selftest relying on kernel module BTF
selftests/bpf: Add support for marking sub-tests as skipped
selftests/bpf: Add bpf_testmod kernel module for testing
libbpf: Add kernel module BTF support for CO-RE relocations
libbpf: Refactor CO-RE relocs to not assume a single BTF object
libbpf: Add internal helper to load BTF data by FD
bpf: Keep module's btf_data_size intact after load
bpf: Fix bpf_put_raw_tracepoint()'s use of __module_address()
selftests/bpf: Add Userspace tests for TCP_WINDOW_CLAMP
bpf: Adds support for setting window clamp
samples/bpf: Fix spelling mistake "recieving" -> "receiving"
bpf: Fix cold build of test_progs-no_alu32
...
====================
Link: https://lore.kernel.org/r/20201204021936.85653-1-alexei.starovoitov@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'samples')
43 files changed, 739 insertions, 1070 deletions
diff --git a/samples/bpf/.gitignore b/samples/bpf/.gitignore index b2f29bc8dc43..0b9548ea8477 100644 --- a/samples/bpf/.gitignore +++ b/samples/bpf/.gitignore @@ -52,3 +52,6 @@ xdp_tx_iptunnel xdpsock xsk_fwd testfile.img +hbm_out.log +iperf.* +*.out diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index aeebf5d12f32..26fc96ca619e 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -48,6 +48,7 @@ tprogs-y += syscall_tp tprogs-y += cpustat tprogs-y += xdp_adjust_tail tprogs-y += xdpsock +tprogs-y += xdpsock_ctrl_proc tprogs-y += xsk_fwd tprogs-y += xdp_fwd tprogs-y += task_fd_query @@ -73,16 +74,16 @@ tracex5-objs := tracex5_user.o $(TRACE_HELPERS) tracex6-objs := tracex6_user.o tracex7-objs := tracex7_user.o test_probe_write_user-objs := test_probe_write_user_user.o -trace_output-objs := trace_output_user.o $(TRACE_HELPERS) +trace_output-objs := trace_output_user.o lathist-objs := lathist_user.o offwaketime-objs := offwaketime_user.o $(TRACE_HELPERS) spintest-objs := spintest_user.o $(TRACE_HELPERS) map_perf_test-objs := map_perf_test_user.o -test_overhead-objs := bpf_load.o test_overhead_user.o +test_overhead-objs := test_overhead_user.o test_cgrp2_array_pin-objs := test_cgrp2_array_pin.o test_cgrp2_attach-objs := test_cgrp2_attach.o test_cgrp2_sock-objs := test_cgrp2_sock.o -test_cgrp2_sock2-objs := bpf_load.o test_cgrp2_sock2.o +test_cgrp2_sock2-objs := test_cgrp2_sock2.o xdp1-objs := xdp1_user.o # reuse xdp1 source intentionally xdp2-objs := xdp1_user.o @@ -91,8 +92,8 @@ test_current_task_under_cgroup-objs := $(CGROUP_HELPERS) \ test_current_task_under_cgroup_user.o trace_event-objs := trace_event_user.o $(TRACE_HELPERS) sampleip-objs := sampleip_user.o $(TRACE_HELPERS) -tc_l2_redirect-objs := bpf_load.o tc_l2_redirect_user.o -lwt_len_hist-objs := bpf_load.o lwt_len_hist_user.o +tc_l2_redirect-objs := tc_l2_redirect_user.o +lwt_len_hist-objs := lwt_len_hist_user.o xdp_tx_iptunnel-objs := xdp_tx_iptunnel_user.o test_map_in_map-objs := test_map_in_map_user.o per_socket_stats_example-objs := cookie_uid_helper_example.o @@ -105,12 +106,13 @@ syscall_tp-objs := syscall_tp_user.o cpustat-objs := cpustat_user.o xdp_adjust_tail-objs := xdp_adjust_tail_user.o xdpsock-objs := xdpsock_user.o +xdpsock_ctrl_proc-objs := xdpsock_ctrl_proc.o xsk_fwd-objs := xsk_fwd.o xdp_fwd-objs := xdp_fwd_user.o -task_fd_query-objs := bpf_load.o task_fd_query_user.o $(TRACE_HELPERS) -xdp_sample_pkts-objs := xdp_sample_pkts_user.o $(TRACE_HELPERS) -ibumad-objs := bpf_load.o ibumad_user.o $(TRACE_HELPERS) -hbm-objs := bpf_load.o hbm.o $(CGROUP_HELPERS) +task_fd_query-objs := task_fd_query_user.o $(TRACE_HELPERS) +xdp_sample_pkts-objs := xdp_sample_pkts_user.o +ibumad-objs := ibumad_user.o +hbm-objs := hbm.o $(CGROUP_HELPERS) # Tell kbuild to always build the programs always-y := $(tprogs-y) @@ -197,14 +199,12 @@ TPROGS_CFLAGS += --sysroot=$(SYSROOT) TPROGS_LDFLAGS := -L$(SYSROOT)/usr/lib endif -TPROGCFLAGS_bpf_load.o += -Wno-unused-variable - TPROGS_LDLIBS += $(LIBBPF) -lelf -lz TPROGLDLIBS_tracex4 += -lrt TPROGLDLIBS_trace_output += -lrt TPROGLDLIBS_map_perf_test += -lrt TPROGLDLIBS_test_overhead += -lrt -TPROGLDLIBS_xdpsock += -pthread +TPROGLDLIBS_xdpsock += -pthread -lcap TPROGLDLIBS_xsk_fwd += -pthread # Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline: diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c deleted file mode 100644 index c5ad528f046e..000000000000 --- a/samples/bpf/bpf_load.c +++ /dev/null @@ -1,667 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <stdio.h> -#include <sys/types.h> -#include <sys/stat.h> -#include <fcntl.h> -#include <libelf.h> -#include <gelf.h> -#include <errno.h> -#include <unistd.h> -#include <string.h> -#include <stdbool.h> -#include <stdlib.h> -#include <linux/bpf.h> -#include <linux/filter.h> -#include <linux/perf_event.h> -#include <linux/netlink.h> -#include <linux/rtnetlink.h> -#include <linux/types.h> -#include <sys/socket.h> -#include <sys/syscall.h> -#include <sys/ioctl.h> -#include <sys/mman.h> -#include <poll.h> -#include <ctype.h> -#include <assert.h> -#include <bpf/bpf.h> -#include "bpf_load.h" -#include "perf-sys.h" - -#define DEBUGFS "/sys/kernel/debug/tracing/" - -static char license[128]; -static int kern_version; -static bool processed_sec[128]; -char bpf_log_buf[BPF_LOG_BUF_SIZE]; -int map_fd[MAX_MAPS]; -int prog_fd[MAX_PROGS]; -int event_fd[MAX_PROGS]; -int prog_cnt; -int prog_array_fd = -1; - -struct bpf_map_data map_data[MAX_MAPS]; -int map_data_count; - -static int populate_prog_array(const char *event, int prog_fd) -{ - int ind = atoi(event), err; - - err = bpf_map_update_elem(prog_array_fd, &ind, &prog_fd, BPF_ANY); - if (err < 0) { - printf("failed to store prog_fd in prog_array\n"); - return -1; - } - return 0; -} - -static int write_kprobe_events(const char *val) -{ - int fd, ret, flags; - - if (val == NULL) - return -1; - else if (val[0] == '\0') - flags = O_WRONLY | O_TRUNC; - else - flags = O_WRONLY | O_APPEND; - - fd = open(DEBUGFS "kprobe_events", flags); - - ret = write(fd, val, strlen(val)); - close(fd); - - return ret; -} - -static int load_and_attach(const char *event, struct bpf_insn *prog, int size) -{ - bool is_socket = strncmp(event, "socket", 6) == 0; - bool is_kprobe = strncmp(event, "kprobe/", 7) == 0; - bool is_kretprobe = strncmp(event, "kretprobe/", 10) == 0; - bool is_tracepoint = strncmp(event, "tracepoint/", 11) == 0; - bool is_raw_tracepoint = strncmp(event, "raw_tracepoint/", 15) == 0; - bool is_xdp = strncmp(event, "xdp", 3) == 0; - bool is_perf_event = strncmp(event, "perf_event", 10) == 0; - bool is_cgroup_skb = strncmp(event, "cgroup/skb", 10) == 0; - bool is_cgroup_sk = strncmp(event, "cgroup/sock", 11) == 0; - bool is_sockops = strncmp(event, "sockops", 7) == 0; - bool is_sk_skb = strncmp(event, "sk_skb", 6) == 0; - bool is_sk_msg = strncmp(event, "sk_msg", 6) == 0; - size_t insns_cnt = size / sizeof(struct bpf_insn); - enum bpf_prog_type prog_type; - char buf[256]; - int fd, efd, err, id; - struct perf_event_attr attr = {}; - - attr.type = PERF_TYPE_TRACEPOINT; - attr.sample_type = PERF_SAMPLE_RAW; - attr.sample_period = 1; - attr.wakeup_events = 1; - - if (is_socket) { - prog_type = BPF_PROG_TYPE_SOCKET_FILTER; - } else if (is_kprobe || is_kretprobe) { - prog_type = BPF_PROG_TYPE_KPROBE; - } else if (is_tracepoint) { - prog_type = BPF_PROG_TYPE_TRACEPOINT; - } else if (is_raw_tracepoint) { - prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT; - } else if (is_xdp) { - prog_type = BPF_PROG_TYPE_XDP; - } else if (is_perf_event) { - prog_type = BPF_PROG_TYPE_PERF_EVENT; - } else if (is_cgroup_skb) { - prog_type = BPF_PROG_TYPE_CGROUP_SKB; - } else if (is_cgroup_sk) { - prog_type = BPF_PROG_TYPE_CGROUP_SOCK; - } else if (is_sockops) { - prog_type = BPF_PROG_TYPE_SOCK_OPS; - } else if (is_sk_skb) { - prog_type = BPF_PROG_TYPE_SK_SKB; - } else if (is_sk_msg) { - prog_type = BPF_PROG_TYPE_SK_MSG; - } else { - printf("Unknown event '%s'\n", event); - return -1; - } - - if (prog_cnt == MAX_PROGS) - return -1; - - fd = bpf_load_program(prog_type, prog, insns_cnt, license, kern_version, - bpf_log_buf, BPF_LOG_BUF_SIZE); - if (fd < 0) { - printf("bpf_load_program() err=%d\n%s", errno, bpf_log_buf); - return -1; - } - - prog_fd[prog_cnt++] = fd; - - if (is_xdp || is_perf_event || is_cgroup_skb || is_cgroup_sk) - return 0; - - if (is_socket || is_sockops || is_sk_skb || is_sk_msg) { - if (is_socket) - event += 6; - else - event += 7; - if (*event != '/') - return 0; - event++; - if (!isdigit(*event)) { - printf("invalid prog number\n"); - return -1; - } - return populate_prog_array(event, fd); - } - - if (is_raw_tracepoint) { - efd = bpf_raw_tracepoint_open(event + 15, fd); - if (efd < 0) { - printf("tracepoint %s %s\n", event + 15, strerror(errno)); - return -1; - } - event_fd[prog_cnt - 1] = efd; - return 0; - } - - if (is_kprobe || is_kretprobe) { - bool need_normal_check = true; - const char *event_prefix = ""; - - if (is_kprobe) - event += 7; - else - event += 10; - - if (*event == 0) { - printf("event name cannot be empty\n"); - return -1; - } - - if (isdigit(*event)) - return populate_prog_array(event, fd); - -#ifdef __x86_64__ - if (strncmp(event, "sys_", 4) == 0) { - snprintf(buf, sizeof(buf), "%c:__x64_%s __x64_%s", - is_kprobe ? 'p' : 'r', event, event); - err = write_kprobe_events(buf); - if (err >= 0) { - need_normal_check = false; - event_prefix = "__x64_"; - } - } -#endif - if (need_normal_check) { - snprintf(buf, sizeof(buf), "%c:%s %s", - is_kprobe ? 'p' : 'r', event, event); - err = write_kprobe_events(buf); - if (err < 0) { - printf("failed to create kprobe '%s' error '%s'\n", - event, strerror(errno)); - return -1; - } - } - - strcpy(buf, DEBUGFS); - strcat(buf, "events/kprobes/"); - strcat(buf, event_prefix); - strcat(buf, event); - strcat(buf, "/id"); - } else if (is_tracepoint) { - event += 11; - - if (*event == 0) { - printf("event name cannot be empty\n"); - return -1; - } - strcpy(buf, DEBUGFS); - strcat(buf, "events/"); - strcat(buf, event); - strcat(buf, "/id"); - } - - efd = open(buf, O_RDONLY, 0); - if (efd < 0) { - printf("failed to open event %s\n", event); - return -1; - } - - err = read(efd, buf, sizeof(buf)); - if (err < 0 || err >= sizeof(buf)) { - printf("read from '%s' failed '%s'\n", event, strerror(errno)); - return -1; - } - - close(efd); - - buf[err] = 0; - id = atoi(buf); - attr.config = id; - - efd = sys_perf_event_open(&attr, -1/*pid*/, 0/*cpu*/, -1/*group_fd*/, 0); - if (efd < 0) { - printf("event %d fd %d err %s\n", id, efd, strerror(errno)); - return -1; - } - event_fd[prog_cnt - 1] = efd; - err = ioctl(efd, PERF_EVENT_IOC_ENABLE, 0); - if (err < 0) { - printf("ioctl PERF_EVENT_IOC_ENABLE failed err %s\n", - strerror(errno)); - return -1; - } - err = ioctl(efd, PERF_EVENT_IOC_SET_BPF, fd); - if (err < 0) { - printf("ioctl PERF_EVENT_IOC_SET_BPF failed err %s\n", - strerror(errno)); - return -1; - } - - return 0; -} - -static int load_maps(struct bpf_map_data *maps, int nr_maps, - fixup_map_cb fixup_map) -{ - int i, numa_node; - - for (i = 0; i < nr_maps; i++) { - if (fixup_map) { - fixup_map(&maps[i], i); - /* Allow userspace to assign map FD prior to creation */ - if (maps[i].fd != -1) { - map_fd[i] = maps[i].fd; - continue; - } - } - - numa_node = maps[i].def.map_flags & BPF_F_NUMA_NODE ? - maps[i].def.numa_node : -1; - - if (maps[i].def.type == BPF_MAP_TYPE_ARRAY_OF_MAPS || - maps[i].def.type == BPF_MAP_TYPE_HASH_OF_MAPS) { - int inner_map_fd = map_fd[maps[i].def.inner_map_idx]; - - map_fd[i] = bpf_create_map_in_map_node(maps[i].def.type, - maps[i].name, - maps[i].def.key_size, - inner_map_fd, - maps[i].def.max_entries, - maps[i].def.map_flags, - numa_node); - } else { - map_fd[i] = bpf_create_map_node(maps[i].def.type, - maps[i].name, - maps[i].def.key_size, - maps[i].def.value_size, - maps[i].def.max_entries, - maps[i].def.map_flags, - numa_node); - } - if (map_fd[i] < 0) { - printf("failed to create map %d (%s): %d %s\n", - i, maps[i].name, errno, strerror(errno)); - return 1; - } - maps[i].fd = map_fd[i]; - - if (maps[i].def.type == BPF_MAP_TYPE_PROG_ARRAY) - prog_array_fd = map_fd[i]; - } - return 0; -} - -static int get_sec(Elf *elf, int i, GElf_Ehdr *ehdr, char **shname, - GElf_Shdr *shdr, Elf_Data **data) -{ - Elf_Scn *scn; - - scn = elf_getscn(elf, i); - if (!scn) - return 1; - - if (gelf_getshdr(scn, shdr) != shdr) - return 2; - - *shname = elf_strptr(elf, ehdr->e_shstrndx, shdr->sh_name); - if (!*shname || !shdr->sh_size) - return 3; - - *data = elf_getdata(scn, 0); - if (!*data || elf_getdata(scn, *data) != NULL) - return 4; - - return 0; -} - -static int parse_relo_and_apply(Elf_Data *data, Elf_Data *symbols, - GElf_Shdr *shdr, struct bpf_insn *insn, - struct bpf_map_data *maps, int nr_maps) -{ - int i, nrels; - - nrels = shdr->sh_size / shdr->sh_entsize; - - for (i = 0; i < nrels; i++) { - GElf_Sym sym; - GElf_Rel rel; - unsigned int insn_idx; - bool match = false; - int j, map_idx; - - gelf_getrel(data, i, &rel); - - insn_idx = rel.r_offset / sizeof(struct bpf_insn); - - gelf_getsym(symbols, GELF_R_SYM(rel.r_info), &sym); - - if (insn[insn_idx].code != (BPF_LD | BPF_IMM | BPF_DW)) { - printf("invalid relo for insn[%d].code 0x%x\n", - insn_idx, insn[insn_idx].code); - return 1; - } - insn[insn_idx].src_reg = BPF_PSEUDO_MAP_FD; - - /* Match FD relocation against recorded map_data[] offset */ - for (map_idx = 0; map_idx < nr_maps; map_idx++) { - if (maps[map_idx].elf_offset == sym.st_value) { - match = true; - break; - } - } - if (match) { - insn[insn_idx].imm = maps[map_idx].fd; - } else { - printf("invalid relo for insn[%d] no map_data match\n", - insn_idx); - return 1; - } - } - - return 0; -} - -static int cmp_symbols(const void *l, const void *r) -{ - const GElf_Sym *lsym = (const GElf_Sym *)l; - const GElf_Sym *rsym = (const GElf_Sym *)r; - - if (lsym->st_value < rsym->st_value) - return -1; - else if (lsym->st_value > rsym->st_value) - return 1; - else - return 0; -} - -static int load_elf_maps_section(struct bpf_map_data *maps, int maps_shndx, - Elf *elf, Elf_Data *symbols, int strtabidx) -{ - int map_sz_elf, map_sz_copy; - bool validate_zero = false; - Elf_Data *data_maps; - int i, nr_maps; - GElf_Sym *sym; - Elf_Scn *scn; - int copy_sz; - - if (maps_shndx < 0) - return -EINVAL; - if (!symbols) - return -EINVAL; - - /* Get data for maps section via elf index */ - scn = elf_getscn(elf, maps_shndx); - if (scn) - data_maps = elf_getdata(scn, NULL); - if (!scn || !data_maps) { - printf("Failed to get Elf_Data from maps section %d\n", - maps_shndx); - return -EINVAL; - } - - /* For each map get corrosponding symbol table entry */ - sym = calloc(MAX_MAPS+1, sizeof(GElf_Sym)); - for (i = 0, nr_maps = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) { - assert(nr_maps < MAX_MAPS+1); - if (!gelf_getsym(symbols, i, &sym[nr_maps])) - continue; - if (sym[nr_maps].st_shndx != maps_shndx) - continue; - /* Only increment iif maps section */ - nr_maps++; - } - - /* Align to map_fd[] order, via sort on offset in sym.st_value */ - qsort(sym, nr_maps, sizeof(GElf_Sym), cmp_symbols); - - /* Keeping compatible with ELF maps section changes - * ------------------------------------------------ - * The program size of struct bpf_load_map_def is known by loader - * code, but struct stored in ELF file can be different. - * - * Unfortunately sym[i].st_size is zero. To calculate the - * struct size stored in the ELF file, assume all struct have - * the same size, and simply divide with number of map - * symbols. - */ - map_sz_elf = data_maps->d_size / nr_maps; - map_sz_copy = sizeof(struct bpf_load_map_def); - if (map_sz_elf < map_sz_copy) { - /* - * Backward compat, loading older ELF file with - * smaller struct, keeping remaining bytes zero. - */ - map_sz_copy = map_sz_elf; - } else if (map_sz_elf > map_sz_copy) { - /* - * Forward compat, loading newer ELF file with larger - * struct with unknown features. Assume zero means - * feature not used. Thus, validate rest of struct - * data is zero. - */ - validate_zero = true; - } - - /* Memcpy relevant part of ELF maps data to loader maps */ - for (i = 0; i < nr_maps; i++) { - struct bpf_load_map_def *def; - unsigned char *addr, *end; - const char *map_name; - size_t offset; - - map_name = elf_strptr(elf, strtabidx, sym[i].st_name); - maps[i].name = strdup(map_name); - if (!maps[i].name) { - printf("strdup(%s): %s(%d)\n", map_name, - strerror(errno), errno); - free(sym); - return -errno; - } - - /* Symbol value is offset into ELF maps section data area */ - offset = sym[i].st_value; - def = (struct bpf_load_map_def *)(data_maps->d_buf + offset); - maps[i].elf_offset = offset; - memset(&maps[i].def, 0, sizeof(struct bpf_load_map_def)); - memcpy(&maps[i].def, def, map_sz_copy); - - /* Verify no newer features were requested */ - if (validate_zero) { - addr = (unsigned char *) def + map_sz_copy; - end = (unsigned char *) def + map_sz_elf; - for (; addr < end; addr++) { - if (*addr != 0) { - free(sym); - return -EFBIG; - } - } - } - } - - free(sym); - return nr_maps; -} - -static int do_load_bpf_file(const char *path, fixup_map_cb fixup_map) -{ - int fd, i, ret, maps_shndx = -1, strtabidx = -1; - Elf *elf; - GElf_Ehdr ehdr; - GElf_Shdr shdr, shdr_prog; - Elf_Data *data, *data_prog, *data_maps = NULL, *symbols = NULL; - char *shname, *shname_prog; - int nr_maps = 0; - - /* reset global variables */ - kern_version = 0; - memset(license, 0, sizeof(license)); - memset(processed_sec, 0, sizeof(processed_sec)); - - if (elf_version(EV_CURRENT) == EV_NONE) - return 1; - - fd = open(path, O_RDONLY, 0); - if (fd < 0) - return 1; - - elf = elf_begin(fd, ELF_C_READ, NULL); - - if (!elf) - return 1; - - if (gelf_getehdr(elf, &ehdr) != &ehdr) - return 1; - - /* clear all kprobes */ - i = write_kprobe_events(""); - - /* scan over all elf sections to get license and map info */ - for (i = 1; i < ehdr.e_shnum; i++) { - - if (get_sec(elf, i, &ehdr, &shname, &shdr, &data)) - continue; - - if (0) /* helpful for llvm debugging */ - printf("section %d:%s data %p size %zd link %d flags %d\n", - i, shname, data->d_buf, data->d_size, - shdr.sh_link, (int) shdr.sh_flags); - - if (strcmp(shname, "license") == 0) { - processed_sec[i] = true; - memcpy(license, data->d_buf, data->d_size); - } else if (strcmp(shname, "version") == 0) { - processed_sec[i] = true; - if (data->d_size != sizeof(int)) { - printf("invalid size of version section %zd\n", - data->d_size); - return 1; - } - memcpy(&kern_version, data->d_buf, sizeof(int)); - } else if (strcmp(shname, "maps") == 0) { - int j; - - maps_shndx = i; - data_maps = data; - for (j = 0; j < MAX_MAPS; j++) - map_data[j].fd = -1; - } else if (shdr.sh_type == SHT_SYMTAB) { - strtabidx = shdr.sh_link; - symbols = data; - } - } - - ret = 1; - - if (!symbols) { - printf("missing SHT_SYMTAB section\n"); - goto done; - } - - if (data_maps) { - nr_maps = load_elf_maps_section(map_data, maps_shndx, - elf, symbols, strtabidx); - if (nr_maps < 0) { - printf("Error: Failed loading ELF maps (errno:%d):%s\n", - nr_maps, strerror(-nr_maps)); - goto done; - } - if (load_maps(map_data, nr_maps, fixup_map)) - goto done; - map_data_count = nr_maps; - - processed_sec[maps_shndx] = true; - } - - /* process all relo sections, and rewrite bpf insns for maps */ - for (i = 1; i < ehdr.e_shnum; i++) { - if (processed_sec[i]) - continue; - - if (get_sec(elf, i, &ehdr, &shname, &shdr, &data)) - continue; - - if (shdr.sh_type == SHT_REL) { - struct bpf_insn *insns; - - /* locate prog sec that need map fixup (relocations) */ - if (get_sec(elf, shdr.sh_info, &ehdr, &shname_prog, - &shdr_prog, &data_prog)) - continue; - - if (shdr_prog.sh_type != SHT_PROGBITS || - !(shdr_prog.sh_flags & SHF_EXECINSTR)) - continue; - - insns = (struct bpf_insn *) data_prog->d_buf; - processed_sec[i] = true; /* relo section */ - - if (parse_relo_and_apply(data, symbols, &shdr, insns, - map_data, nr_maps)) - continue; - } - } - - /* load programs */ - for (i = 1; i < ehdr.e_shnum; i++) { - - if (processed_sec[i]) - continue; - - if (get_sec(elf, i, &ehdr, &shname, &shdr, &data)) - continue; - - if (memcmp(shname, "kprobe/", 7) == 0 || - memcmp(shname, "kretprobe/", 10) == 0 || - memcmp(shname, "tracepoint/", 11) == 0 || - memcmp(shname, "raw_tracepoint/", 15) == 0 || - memcmp(shname, "xdp", 3) == 0 || - memcmp(shname, "perf_event", 10) == 0 || - memcmp(shname, "socket", 6) == 0 || - memcmp(shname, "cgroup/", 7) == 0 || - memcmp(shname, "sockops", 7) == 0 || - memcmp(shname, "sk_skb", 6) == 0 || - memcmp(shname, "sk_msg", 6) == 0) { - ret = load_and_attach(shname, data->d_buf, - data->d_size); - if (ret != 0) - goto done; - } - } - -done: - close(fd); - return ret; -} - -int load_bpf_file(char *path) -{ - return do_load_bpf_file(path, NULL); -} - -int load_bpf_file_fixup_map(const char *path, fixup_map_cb fixup_map) -{ - return do_load_bpf_file(path, fixup_map); -} diff --git a/samples/bpf/bpf_load.h b/samples/bpf/bpf_load.h deleted file mode 100644 index 4fcd258c616f..000000000000 --- a/samples/bpf/bpf_load.h +++ /dev/null @@ -1,57 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __BPF_LOAD_H -#define __BPF_LOAD_H - -#include <bpf/bpf.h> - -#define MAX_MAPS 32 -#define MAX_PROGS 32 - -struct bpf_load_map_def { - unsigned int type; - unsigned int key_size; - unsigned int value_size; - unsigned int max_entries; - unsigned int map_flags; - unsigned int inner_map_idx; - unsigned int numa_node; -}; - -struct bpf_map_data { - int fd; - char *name; - size_t elf_offset; - struct bpf_load_map_def def; -}; - -typedef void (*fixup_map_cb)(struct bpf_map_data *map, int idx); - -extern int prog_fd[MAX_PROGS]; -extern int event_fd[MAX_PROGS]; -extern char bpf_log_buf[BPF_LOG_BUF_SIZE]; -extern int prog_cnt; - -/* There is a one-to-one mapping between map_fd[] and map_data[]. - * The map_data[] just contains more rich info on the given map. - */ -extern int map_fd[MAX_MAPS]; -extern struct bpf_map_data map_data[MAX_MAPS]; -extern int map_data_count; - -/* parses elf file compiled by llvm .c->.o - * . parses 'maps' section and creates maps via BPF syscall - * . parses 'license' section and passes it to syscall - * . parses elf relocations for BPF maps and adjusts BPF_LD_IMM64 insns by - * storing map_fd into insn->imm and marking such insns as BPF_PSEUDO_MAP_FD - * . loads eBPF programs via BPF syscall - * - * One ELF file can contain multiple BPF programs which will be loaded - * and their FDs stored stored in prog_fd array - * - * returns zero on success - */ -int load_bpf_file(char *path); -int load_bpf_file_fixup_map(const char *path, fixup_map_cb fixup_map); - -int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags); -#endif diff --git a/samples/bpf/do_hbm_test.sh b/samples/bpf/do_hbm_test.sh index ffe4c0607341..21790ea5c460 100755 --- a/samples/bpf/do_hbm_test.sh +++ b/samples/bpf/do_hbm_test.sh @@ -91,6 +91,16 @@ qdisc="" flags="" do_stats=0 +BPFFS=/sys/fs/bpf +function config_bpffs () { + if mount | grep $BPFFS > /dev/null; then + echo "bpffs already mounted" + else + echo "bpffs not mounted. Mounting..." + mount -t bpf none $BPFFS + fi +} + function start_hbm () { rm -f hbm.out echo "./hbm $dir -n $id -r $rate -t $dur $flags $dbg $prog" > hbm.out @@ -192,6 +202,7 @@ processArgs () { } processArgs +config_bpffs if [ $debug_flag -eq 1 ] ; then rm -f hbm_out.log @@ -201,7 +212,7 @@ hbm_pid=$(start_hbm) usleep 100000 host=`hostname` -cg_base_dir=/sys/fs/cgroup +cg_base_dir=/sys/fs/cgroup/unified cg_dir="$cg_base_dir/cgroup-test-work-dir/hbm$id" echo $$ >> $cg_dir/cgroup.procs @@ -411,23 +422,8 @@ fi sleep 1 -# Detach any BPF programs that may have lingered -ttx=`bpftool cgroup tree | grep hbm` -v=2 -for x in $ttx ; do - if [ "${x:0:36}" == "/sys/fs/cgroup/cgroup-test-work-dir/" ] ; then - cg=$x ; v=0 - else - if [ $v -eq 0 ] ; then - id=$x ; v=1 - else - if [ $v -eq 1 ] ; then - type=$x ; bpftool cgroup detach $cg $type id $id - v=0 - fi - fi - fi -done +# Detach any pinned BPF programs that may have lingered +rm -rf $BPFFS/hbm* if [ $use_netperf -ne 0 ] ; then if [ "$server" == "" ] ; then diff --git a/samples/bpf/hbm.c b/samples/bpf/hbm.c index 400e741a56eb..b0c18efe7928 100644 --- a/samples/bpf/hbm.c +++ b/samples/bpf/hbm.c @@ -46,7 +46,6 @@ #include <bpf/bpf.h> #include <getopt.h> -#include "bpf_load.h" #include "bpf_rlimit.h" #include "cgroup_helpers.h" #include "hbm.h" @@ -70,9 +69,9 @@ static void do_error(char *msg, bool errno_flag); #define DEBUGFS "/sys/kernel/debug/tracing/" -struct bpf_object *obj; -int bpfprog_fd; -int cgroup_storage_fd; +static struct bpf_program *bpf_prog; +static struct bpf_object *obj; +static int queue_stats_fd; static void read_trace_pipe2(void) { @@ -121,56 +120,50 @@ static void do_error(char *msg, bool errno_flag) static int prog_load(char *prog) { - struct bpf_prog_load_attr prog_load_attr = { - .prog_type = BPF_PROG_TYPE_CGROUP_SKB, - .file = prog, - .expected_attach_type = BPF_CGROUP_INET_EGRESS, - }; - int map_fd; - struct bpf_map *map; - - int ret = 0; - - if (access(prog, O_RDONLY) < 0) { - printf("Error accessing file %s: %s\n", prog, strerror(errno)); + obj = bpf_object__open_file(prog, NULL); + if (libbpf_get_error(obj)) { + printf("ERROR: opening BPF object file failed\n"); return 1; } - if (bpf_prog_load_xattr(&prog_load_attr, &obj, &bpfprog_fd)) - ret = 1; - if (!ret) { - map = bpf_object__find_map_by_name(obj, "queue_stats"); - map_fd = bpf_map__fd(map); - if (map_fd < 0) { - printf("Map not found: %s\n", strerror(map_fd)); - ret = 1; - } + + /* load BPF program */ + if (bpf_object__load(obj)) { + printf("ERROR: loading BPF object file failed\n"); + goto err; } - if (ret) { - printf("ERROR: bpf_prog_load_xattr failed for: %s\n", prog); - printf(" Output from verifier:\n%s\n------\n", bpf_log_buf); - ret = -1; - } else { - ret = map_fd; + bpf_prog = bpf_object__find_program_by_title(obj, "cgroup_skb/egress"); + if (!bpf_prog) { + printf("ERROR: finding a prog in obj file failed\n"); + goto err; + } + + queue_stats_fd = bpf_object__find_map_fd_by_name(obj, "queue_stats"); + if (queue_stats_fd < 0) { + printf("ERROR: finding a map in obj file failed\n"); + goto err; } - return ret; + return 0; + +err: + bpf_object__close(obj); + return 1; } static int run_bpf_prog(char *prog, int cg_id) { - int map_fd; - int rc = 0; + struct hbm_queue_stats qstats = {0}; + char cg_dir[100], cg_pin_path[100]; + struct bpf_link *link = NULL; int key = 0; int cg1 = 0; - int type = BPF_CGROUP_INET_EGRESS; - char cg_dir[100]; - struct hbm_queue_stats qstats = {0}; + int rc = 0; sprintf(cg_dir, "/hbm%d", cg_id); - map_fd = prog_load(prog); - if (map_fd == -1) - return 1; + rc = prog_load(prog); + if (rc != 0) + return rc; if (setup_cgroup_environment()) { printf("ERROR: setting cgroup environment\n"); @@ -190,16 +183,24 @@ static int run_bpf_prog(char *prog, int cg_id) qstats.stats = stats_flag ? 1 : 0; qstats.loopback = loopback_flag ? 1 : 0; qstats.no_cn = no_cn_flag ? 1 : 0; - if (bpf_map_update_elem(map_fd, &key, &qstats, BPF_ANY)) { + if (bpf_map_update_elem(queue_stats_fd, &key, &qstats, BPF_ANY)) { printf("ERROR: Could not update map element\n"); goto err; } if (!outFlag) - type = BPF_CGROUP_INET_INGRESS; - if (bpf_prog_attach(bpfprog_fd, cg1, type, 0)) { - printf("ERROR: bpf_prog_attach fails!\n"); - log_err("Attaching prog"); + bpf_program__set_expected_attach_type(bpf_prog, BPF_CGROUP_INET_INGRESS); + + link = bpf_program__attach_cgroup(bpf_prog, cg1); + if (libbpf_get_error(link)) { + fprintf(stderr, "ERROR: bpf_program__attach_cgroup failed\n"); + goto err; + } + + sprintf(cg_pin_path, "/sys/fs/bpf/hbm%d", cg_id); + rc = bpf_link__pin(link, cg_pin_path); + if (rc < 0) { + printf("ERROR: bpf_link__pin failed: %d\n", rc); goto err; } @@ -213,7 +214,7 @@ static int run_bpf_prog(char *prog, int cg_id) #define DELTA_RATE_CHECK 10000 /* in us */ #define RATE_THRESHOLD 9500000000 /* 9.5 Gbps */ - bpf_map_lookup_elem(map_fd, &key, &qstats); + bpf_map_lookup_elem(queue_stats_fd, &key, &qstats); if (gettimeofday(&t0, NULL) < 0) do_error("gettimeofday failed", true); t_last = t0; @@ -242,7 +243,7 @@ static int run_bpf_prog(char *prog, int cg_id) fclose(fin); printf(" new_eth_tx_bytes:%llu\n", new_eth_tx_bytes); - bpf_map_lookup_elem(map_fd, &key, &qstats); + bpf_map_lookup_elem(queue_stats_fd, &key, &qstats); new_cg_tx_bytes = qstats.bytes_total; delta_bytes = new_eth_tx_bytes - last_eth_tx_bytes; last_eth_tx_bytes = new_eth_tx_bytes; @@ -289,14 +290,14 @@ static int run_bpf_prog(char *prog, int cg_id) rate = minRate; qstats.rate = rate; } - if (bpf_map_update_elem(map_fd, &key, &qstats, BPF_ANY)) + if (bpf_map_update_elem(queue_stats_fd, &key, &qstats, BPF_ANY)) do_error("update map element fails", false); } } else { sleep(dur); } // Get stats! - if (stats_flag && bpf_map_lookup_elem(map_fd, &key, &qstats)) { + if (stats_flag && bpf_map_lookup_elem(queue_stats_fd, &key, &qstats)) { char fname[100]; FILE *fout; @@ -394,14 +395,20 @@ static int run_bpf_prog(char *prog, int cg_id) if (debugFlag) read_trace_pipe2(); - return rc; + goto cleanup; + err: rc = 1; - if (cg1) +cleanup: + bpf_link__destroy(link); + bpf_object__close(obj); + + if (cg1 != -1) close(cg1); - cleanup_cgroup_environment(); + if (rc != 0) + cleanup_cgroup_environment(); return rc; } diff --git a/samples/bpf/hbm_kern.h b/samples/bpf/hbm_kern.h index e00f26f6afba..722b3fadb467 100644 --- a/samples/bpf/hbm_kern.h +++ b/samples/bpf/hbm_kern.h @@ -69,7 +69,7 @@ struct { __uint(type, BPF_MAP_TYPE_ARRAY); __uint(max_entries, 1); __type(key, u32); - __type(value, struct hvm_queue_stats); + __type(value, struct hbm_queue_stats); } queue_stats SEC(".maps"); struct hbm_pkt_info { diff --git a/samples/bpf/ibumad_kern.c b/samples/bpf/ibumad_kern.c index 3a91b4c1989a..26dcd4dde946 100644 --- a/samples/bpf/ibumad_kern.c +++ b/samples/bpf/ibumad_kern.c @@ -16,19 +16,19 @@ #include <bpf/bpf_helpers.h> -struct bpf_map_def SEC("maps") read_count = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(u32), /* class; u32 required */ - .value_size = sizeof(u64), /* count of mads read */ - .max_entries = 256, /* Room for all Classes */ -}; - -struct bpf_map_def SEC("maps") write_count = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(u32), /* class; u32 required */ - .value_size = sizeof(u64), /* count of mads written */ - .max_entries = 256, /* Room for all Classes */ -}; +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, u32); /* class; u32 required */ + __type(value, u64); /* count of mads read */ + __uint(max_entries, 256); /* Room for all Classes */ +} read_count SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, u32); /* class; u32 required */ + __type(value, u64); /* count of mads written */ + __uint(max_entries, 256); /* Room for all Classes */ +} write_count SEC(".maps"); #undef DEBUG #ifndef DEBUG diff --git a/samples/bpf/ibumad_user.c b/samples/bpf/ibumad_user.c index fa06eef31a84..d83d8102f489 100644 --- a/samples/bpf/ibumad_user.c +++ b/samples/bpf/ibumad_user.c @@ -23,10 +23,15 @@ #include <getopt.h> #include <net/if.h> -#include "bpf_load.h" +#include <bpf/bpf.h> #include "bpf_util.h" #include <bpf/libbpf.h> +static struct bpf_link *tp_links[3]; +static struct bpf_object *obj; +static int map_fd[2]; +static int tp_cnt; + static void dump_counts(int fd) { __u32 key; @@ -53,6 +58,11 @@ static void dump_all_counts(void) static void dump_exit(int sig) { dump_all_counts(); + /* Detach tracepoints */ + while (tp_cnt) + bpf_link__destroy(tp_links[--tp_cnt]); + + bpf_object__close(obj); exit(0); } @@ -73,19 +83,11 @@ static void usage(char *cmd) int main(int argc, char **argv) { + struct bpf_program *prog; unsigned long delay = 5; + char filename[256]; int longindex = 0; - int opt; - char bpf_file[256]; - - /* Create the eBPF kernel code path name. - * This follows the pattern of all of the other bpf samples - */ - snprintf(bpf_file, sizeof(bpf_file), "%s_kern.o", argv[0]); - - /* Do one final dump when exiting */ - signal(SIGINT, dump_exit); - signal(SIGTERM, dump_exit); + int opt, err = -1; while ((opt = getopt_long(argc, argv, "hd:rSw", long_options, &longindex)) != -1) { @@ -107,16 +109,51 @@ int main(int argc, char **argv) } } - if (load_bpf_file(bpf_file)) { - fprintf(stderr, "ERROR: failed to load eBPF from file : %s\n", - bpf_file); - return 1; + /* Do one final dump when exiting */ + signal(SIGINT, dump_exit); + signal(SIGTERM, dump_exit); + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) { + fprintf(stderr, "ERROR: opening BPF object file failed\n"); + return err; + } + + /* load BPF program */ + if (bpf_object__load(obj)) { + fprintf(stderr, "ERROR: loading BPF object file failed\n"); + goto cleanup; + } + + map_fd[0] = bpf_object__find_map_fd_by_name(obj, "read_count"); + map_fd[1] = bpf_object__find_map_fd_by_name(obj, "write_count"); + if (map_fd[0] < 0 || map_fd[1] < 0) { + fprintf(stderr, "ERROR: finding a map in obj file failed\n"); + goto cleanup; + } + + bpf_object__for_each_program(prog, obj) { + tp_links[tp_cnt] = bpf_program__attach(prog); + if (libbpf_get_error(tp_links[tp_cnt])) { + fprintf(stderr, "ERROR: bpf_program__attach failed\n"); + tp_links[tp_cnt] = NULL; + goto cleanup; + } + tp_cnt++; } while (1) { sleep(delay); dump_all_counts(); } + err = 0; + +cleanup: + /* Detach tracepoints */ + while (tp_cnt) + bpf_link__destroy(tp_links[--tp_cnt]); - return 0; + bpf_object__close(obj); + return err; } diff --git a/samples/bpf/lwt_len_hist.sh b/samples/bpf/lwt_len_hist.sh index 090b96eaf7f7..0eda9754f50b 100644..100755 --- a/samples/bpf/lwt_len_hist.sh +++ b/samples/bpf/lwt_len_hist.sh @@ -8,6 +8,8 @@ VETH1=tst_lwt1b TRACE_ROOT=/sys/kernel/debug/tracing function cleanup { + # To reset saved histogram, remove pinned map + rm /sys/fs/bpf/tc/globals/lwt_len_hist_map ip route del 192.168.253.2/32 dev $VETH0 2> /dev/null ip link del $VETH0 2> /dev/null ip link del $VETH1 2> /dev/null diff --git a/samples/bpf/map_perf_test_user.c b/samples/bpf/map_perf_test_user.c index 8b13230b4c46..9db949290a78 100644 --- a/samples/bpf/map_perf_test_user.c +++ b/samples/bpf/map_perf_test_user.c @@ -421,7 +421,6 @@ static void fixup_map(struct bpf_object *obj) int main(int argc, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; int nr_cpus = sysconf(_SC_NPROCESSORS_ONLN); struct bpf_link *links[8]; struct bpf_program *prog; @@ -430,11 +429,6 @@ int main(int argc, char **argv) char filename[256]; int i = 0; - if (setrlimit(RLIMIT_MEMLOCK, &r)) { - perror("setrlimit(RLIMIT_MEMLOCK)"); - return 1; - } - if (argc > 1) test_flags = atoi(argv[1]) ? : test_flags; diff --git a/samples/bpf/offwaketime_user.c b/samples/bpf/offwaketime_user.c index 5734cfdaaacb..73a986876c1a 100644 --- a/samples/bpf/offwaketime_user.c +++ b/samples/bpf/offwaketime_user.c @@ -95,18 +95,12 @@ static void int_exit(int sig) int main(int argc, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; struct bpf_object *obj = NULL; struct bpf_link *links[2]; struct bpf_program *prog; int delay = 1, i = 0; char filename[256]; - if (setrlimit(RLIMIT_MEMLOCK, &r)) { - perror("setrlimit(RLIMIT_MEMLOCK)"); - return 1; - } - if (load_kallsyms()) { printf("failed to process /proc/kallsyms\n"); return 2; diff --git a/samples/bpf/sockex2_user.c b/samples/bpf/sockex2_user.c index af925a5afd1d..bafa567b840c 100644 --- a/samples/bpf/sockex2_user.c +++ b/samples/bpf/sockex2_user.c @@ -16,7 +16,6 @@ struct pair { int main(int ac, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; struct bpf_object *obj; int map_fd, prog_fd; char filename[256]; @@ -24,7 +23,6 @@ int main(int ac, char **argv) FILE *f; snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); - setrlimit(RLIMIT_MEMLOCK, &r); if (bpf_prog_load(filename, BPF_PROG_TYPE_SOCKET_FILTER, &obj, &prog_fd)) diff --git a/samples/bpf/sockex3_user.c b/samples/bpf/sockex3_user.c index 7793f6a6ae7e..6ae99ecc766c 100644 --- a/samples/bpf/sockex3_user.c +++ b/samples/bpf/sockex3_user.c @@ -26,7 +26,6 @@ struct pair { int main(int argc, char **argv) { int i, sock, key, fd, main_prog_fd, jmp_table_fd, hash_map_fd; - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; struct bpf_program *prog; struct bpf_object *obj; const char *section; @@ -34,7 +33,6 @@ int main(int argc, char **argv) FILE *f; snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); - setrlimit(RLIMIT_MEMLOCK, &r); obj = bpf_object__open_file(filename, NULL); if (libbpf_get_error(obj)) { diff --git a/samples/bpf/spintest_user.c b/samples/bpf/spintest_user.c index f090d0dc60d6..0d7e1e5a8658 100644 --- a/samples/bpf/spintest_user.c +++ b/samples/bpf/spintest_user.c @@ -10,7 +10,6 @@ int main(int ac, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; char filename[256], symbol[256]; struct bpf_object *obj = NULL; struct bpf_link *links[20]; @@ -20,11 +19,6 @@ int main(int ac, char **argv) const char *section; struct ksym *sym; - if (setrlimit(RLIMIT_MEMLOCK, &r)) { - perror("setrlimit(RLIMIT_MEMLOCK)"); - return 1; - } - if (load_kallsyms()) { printf("failed to process /proc/kallsyms\n"); return 2; diff --git a/samples/bpf/syscall_tp_user.c b/samples/bpf/syscall_tp_user.c index 76a1d00128fb..a0ebf1833ed3 100644 --- a/samples/bpf/syscall_tp_user.c +++ b/samples/bpf/syscall_tp_user.c @@ -115,7 +115,6 @@ cleanup: int main(int argc, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; int opt, num_progs = 1; char filename[256]; @@ -131,7 +130,6 @@ int main(int argc, char **argv) } } - setrlimit(RLIMIT_MEMLOCK, &r); snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); return test(filename, num_progs); diff --git a/samples/bpf/task_fd_query_user.c b/samples/bpf/task_fd_query_user.c index b68bd2f8fdc9..a78025b0026b 100644 --- a/samples/bpf/task_fd_query_user.c +++ b/samples/bpf/task_fd_query_user.c @@ -15,12 +15,15 @@ #include <sys/stat.h> #include <linux/perf_event.h> +#include <bpf/bpf.h> #include <bpf/libbpf.h> -#include "bpf_load.h" #include "bpf_util.h" #include "perf-sys.h" #include "trace_helpers.h" +static struct bpf_program *progs[2]; +static struct bpf_link *links[2]; + #define CHECK_PERROR_RET(condition) ({ \ int __ret = !!(condition); \ if (__ret) { \ @@ -86,21 +89,22 @@ static int bpf_get_retprobe_bit(const char *event_type) return ret; } -static int test_debug_fs_kprobe(int prog_fd_idx, const char *fn_name, +static int test_debug_fs_kprobe(int link_idx, const char *fn_name, __u32 expected_fd_type) { __u64 probe_offset, probe_addr; __u32 len, prog_id, fd_type; + int err, event_fd; char buf[256]; - int err; len = sizeof(buf); - err = bpf_task_fd_query(getpid(), event_fd[prog_fd_idx], 0, buf, &len, + event_fd = bpf_link__fd(links[link_idx]); + err = bpf_task_fd_query(getpid(), event_fd, 0, buf, &len, &prog_id, &fd_type, &probe_offset, &probe_addr); if (err < 0) { printf("FAIL: %s, for event_fd idx %d, fn_name %s\n", - __func__, prog_fd_idx, fn_name); + __func__, link_idx, fn_name); perror(" :"); return -1; } @@ -108,7 +112,7 @@ static int test_debug_fs_kprobe(int prog_fd_idx, const char *fn_name, fd_type != expected_fd_type || probe_offset != 0x0 || probe_addr != 0x0) { printf("FAIL: bpf_trace_event_query(event_fd[%d]):\n", - prog_fd_idx); + link_idx); printf("buf: %s, fd_type: %u, probe_offset: 0x%llx," " probe_addr: 0x%llx\n", buf, fd_type, probe_offset, probe_addr); @@ -125,12 +129,13 @@ static int test_nondebug_fs_kuprobe_common(const char *event_type, int is_return_bit = bpf_get_retprobe_bit(event_type); int type = bpf_find_probe_type(event_type); struct perf_event_attr attr = {}; - int fd; + struct bpf_link *link; + int fd, err = -1; if (type < 0 || is_return_bit < 0) { printf("FAIL: %s incorrect type (%d) or is_return_bit (%d)\n", __func__, type, is_return_bit); - return -1; + return err; } attr.sample_period = 1; @@ -149,14 +154,21 @@ static int test_nondebug_fs_kuprobe_common(const char *event_type, attr.type = type; fd = sys_perf_event_open(&attr, -1, 0, -1, 0); - CHECK_PERROR_RET(fd < 0); + link = bpf_program__attach_perf_event(progs[0], fd); + if (libbpf_get_error(link)) { + printf("ERROR: bpf_program__attach_perf_event failed\n"); + link = NULL; + close(fd); + goto cleanup; + } - CHECK_PERROR_RET(ioctl(fd, PERF_EVENT_IOC_ENABLE, 0) < 0); - CHECK_PERROR_RET(ioctl(fd, PERF_EVENT_IOC_SET_BPF, prog_fd[0]) < 0); CHECK_PERROR_RET(bpf_task_fd_query(getpid(), fd, 0, buf, buf_len, prog_id, fd_type, probe_offset, probe_addr) < 0); + err = 0; - return 0; +cleanup: + bpf_link__destroy(link); + return err; } static int test_nondebug_fs_probe(const char *event_type, const char *name, @@ -215,17 +227,18 @@ static int test_nondebug_fs_probe(const char *event_type, const char *name, static int test_debug_fs_uprobe(char *binary_path, long offset, bool is_return) { + char buf[256], event_alias[sizeof("test_1234567890")]; const char *event_type = "uprobe"; struct perf_event_attr attr = {}; - char buf[256], event_alias[sizeof("test_1234567890")]; __u64 probe_offset, probe_addr; __u32 len, prog_id, fd_type; - int err, res, kfd, efd; + int err = -1, res, kfd, efd; + struct bpf_link *link; ssize_t bytes; snprintf(buf, sizeof(buf), "/sys/kernel/debug/tracing/%s_events", event_type); - kfd = open(buf, O_WRONLY | O_APPEND, 0); + kfd = open(buf, O_WRONLY | O_TRUNC, 0); CHECK_PERROR_RET(kfd < 0); res = snprintf(event_alias, sizeof(event_alias), "test_%d", getpid()); @@ -254,10 +267,15 @@ static int test_debug_fs_uprobe(char *binary_path, long offset, bool is_return) attr.type = PERF_TYPE_TRACEPOINT; attr.sample_period = 1; attr.wakeup_events = 1; + kfd = sys_perf_event_open(&attr, -1, 0, -1, PERF_FLAG_FD_CLOEXEC); - CHECK_PERROR_RET(kfd < 0); - CHECK_PERROR_RET(ioctl(kfd, PERF_EVENT_IOC_SET_BPF, prog_fd[0]) < 0); - CHECK_PERROR_RET(ioctl(kfd, PERF_EVENT_IOC_ENABLE, 0) < 0); + link = bpf_program__attach_perf_event(progs[0], kfd); + if (libbpf_get_error(link)) { + printf("ERROR: bpf_program__attach_perf_event failed\n"); + link = NULL; + close(kfd); + goto cleanup; + } len = sizeof(buf); err = bpf_task_fd_query(getpid(), kfd, 0, buf, &len, @@ -283,32 +301,49 @@ static int test_debug_fs_uprobe(char *binary_path, long offset, bool is_return) probe_offset); return -1; } + err = 0; - close(kfd); - return 0; +cleanup: + bpf_link__destroy(link); + return err; } int main(int argc, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; extern char __executable_start; char filename[256], buf[256]; __u64 uprobe_file_offset; + struct bpf_program *prog; + struct bpf_object *obj; + int i = 0, err = -1; + + if (load_kallsyms()) { + printf("failed to process /proc/kallsyms\n"); + return err; + } snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); - if (setrlimit(RLIMIT_MEMLOCK, &r)) { - perror("setrlimit(RLIMIT_MEMLOCK)"); - return 1; + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) { + fprintf(stderr, "ERROR: opening BPF object file failed\n"); + return err; } - if (load_kallsyms()) { - printf("failed to process /proc/kallsyms\n"); - return 1; + /* load BPF program */ + if (bpf_object__load(obj)) { + fprintf(stderr, "ERROR: loading BPF object file failed\n"); + goto cleanup; } - if (load_bpf_file(filename)) { - printf("%s", bpf_log_buf); - return 1; + bpf_object__for_each_program(prog, obj) { + progs[i] = prog; + links[i] = bpf_program__attach(progs[i]); + if (libbpf_get_error(links[i])) { + fprintf(stderr, "ERROR: bpf_program__attach failed\n"); + links[i] = NULL; + goto cleanup; + } + i++; } /* test two functions in the corresponding *_kern.c file */ @@ -378,6 +413,12 @@ int main(int argc, char **argv) false)); CHECK_AND_RET(test_debug_fs_uprobe((char *)argv[0], uprobe_file_offset, true)); + err = 0; - return 0; +cleanup: + for (i--; i >= 0; i--) + bpf_link__destroy(links[i]); + + bpf_object__close(obj); + return err; } diff --git a/samples/bpf/test_cgrp2_sock2.c b/samples/bpf/test_cgrp2_sock2.c index a9277b118c33..e7060aaa2f5a 100644 --- a/samples/bpf/test_cgrp2_sock2.c +++ b/samples/bpf/test_cgrp2_sock2.c @@ -20,9 +20,9 @@ #include <net/if.h> #include <linux/bpf.h> #include <bpf/bpf.h> +#include <bpf/libbpf.h> #include "bpf_insn.h" -#include "bpf_load.h" static int usage(const char *argv0) { @@ -32,37 +32,64 @@ static int usage(const char *argv0) int main(int argc, char **argv) { - int cg_fd, ret, filter_id = 0; + int cg_fd, err, ret = EXIT_FAILURE, filter_id = 0, prog_cnt = 0; + const char *link_pin_path = "/sys/fs/bpf/test_cgrp2_sock2"; + struct bpf_link *link = NULL; + struct bpf_program *progs[2]; + struct bpf_program *prog; + struct bpf_object *obj; if (argc < 3) return usage(argv[0]); + if (argc > 3) + filter_id = atoi(argv[3]); + cg_fd = open(argv[1], O_DIRECTORY | O_RDONLY); if (cg_fd < 0) { printf("Failed to open cgroup path: '%s'\n", strerror(errno)); - return EXIT_FAILURE; + return ret; } - if (load_bpf_file(argv[2])) - return EXIT_FAILURE; - - printf("Output from kernel verifier:\n%s\n-------\n", bpf_log_buf); + obj = bpf_object__open_file(argv[2], NULL); + if (libbpf_get_error(obj)) { + printf("ERROR: opening BPF object file failed\n"); + return ret; + } - if (argc > 3) - filter_id = atoi(argv[3]); + bpf_object__for_each_program(prog, obj) { + progs[prog_cnt] = prog; + prog_cnt++; + } if (filter_id >= prog_cnt) { printf("Invalid program id; program not found in file\n"); - return EXIT_FAILURE; + goto cleanup; + } + + /* load BPF program */ + if (bpf_object__load(obj)) { + printf("ERROR: loading BPF object file failed\n"); + goto cleanup; } - ret = bpf_prog_attach(prog_fd[filter_id], cg_fd, - BPF_CGROUP_INET_SOCK_CREATE, 0); - if (ret < 0) { - printf("Failed to attach prog to cgroup: '%s'\n", - strerror(errno)); - return EXIT_FAILURE; + link = bpf_program__attach_cgroup(progs[filter_id], cg_fd); + if (libbpf_get_error(link)) { + printf("ERROR: bpf_program__attach failed\n"); + link = NULL; + goto cleanup; } - return EXIT_SUCCESS; + err = bpf_link__pin(link, link_pin_path); + if (err < 0) { + printf("ERROR: bpf_link__pin failed: %d\n", err); + goto cleanup; + } + + ret = EXIT_SUCCESS; + +cleanup: + bpf_link__destroy(link); + bpf_object__close(obj); + return ret; } diff --git a/samples/bpf/test_cgrp2_sock2.sh b/samples/bpf/test_cgrp2_sock2.sh index 0f396a86e0cb..6a3dbe642b2b 100755 --- a/samples/bpf/test_cgrp2_sock2.sh +++ b/samples/bpf/test_cgrp2_sock2.sh @@ -1,6 +1,9 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +BPFFS=/sys/fs/bpf +LINK_PIN=$BPFFS/test_cgrp2_sock2 + function config_device { ip netns add at_ns0 ip link add veth0 type veth peer name veth0b @@ -21,16 +24,22 @@ function config_cgroup { echo $$ >> /tmp/cgroupv2/foo/cgroup.procs } +function config_bpffs { + if mount | grep $BPFFS > /dev/null; then + echo "bpffs already mounted" + else + echo "bpffs not mounted. Mounting..." + mount -t bpf none $BPFFS + fi +} function attach_bpf { - test_cgrp2_sock2 /tmp/cgroupv2/foo sock_flags_kern.o $1 + ./test_cgrp2_sock2 /tmp/cgroupv2/foo sock_flags_kern.o $1 [ $? -ne 0 ] && exit 1 } function cleanup { - if [ -d /tmp/cgroupv2/foo ]; then - test_cgrp2_sock -d /tmp/cgroupv2/foo - fi + rm -rf $LINK_PIN ip link del veth0b ip netns delete at_ns0 umount /tmp/cgroupv2 @@ -42,6 +51,7 @@ cleanup 2>/dev/null set -e config_device config_cgroup +config_bpffs set +e # @@ -62,6 +72,9 @@ if [ $? -eq 0 ]; then exit 1 fi +rm -rf $LINK_PIN +sleep 1 # Wait for link detach + # # Test 2 - fail ping # diff --git a/samples/bpf/test_lru_dist.c b/samples/bpf/test_lru_dist.c index b313dba4111b..c92c5c06b965 100644 --- a/samples/bpf/test_lru_dist.c +++ b/samples/bpf/test_lru_dist.c @@ -489,7 +489,6 @@ static void test_parallel_lru_loss(int map_type, int map_flags, int nr_tasks) int main(int argc, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; int map_flags[] = {0, BPF_F_NO_COMMON_LRU}; const char *dist_file; int nr_tasks = 1; @@ -508,8 +507,6 @@ int main(int argc, char **argv) setbuf(stdout, NULL); - assert(!setrlimit(RLIMIT_MEMLOCK, &r)); - srand(time(NULL)); nr_cpus = bpf_num_possible_cpus(); diff --git a/samples/bpf/test_lwt_bpf.sh b/samples/bpf/test_lwt_bpf.sh index 65a976058dd3..65a976058dd3 100644..100755 --- a/samples/bpf/test_lwt_bpf.sh +++ b/samples/bpf/test_lwt_bpf.sh diff --git a/samples/bpf/test_map_in_map_user.c b/samples/bpf/test_map_in_map_user.c index 98656de56b83..472d65c70354 100644 --- a/samples/bpf/test_map_in_map_user.c +++ b/samples/bpf/test_map_in_map_user.c @@ -114,17 +114,11 @@ static void test_map_in_map(void) int main(int argc, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; struct bpf_link *link = NULL; struct bpf_program *prog; struct bpf_object *obj; char filename[256]; - if (setrlimit(RLIMIT_MEMLOCK, &r)) { - perror("setrlimit(RLIMIT_MEMLOCK)"); - return 1; - } - snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); obj = bpf_object__open_file(filename, NULL); if (libbpf_get_error(obj)) { diff --git a/samples/bpf/test_overhead_user.c b/samples/bpf/test_overhead_user.c index 94f74112a20e..4821f9d99c1f 100644 --- a/samples/bpf/test_overhead_user.c +++ b/samples/bpf/test_overhead_user.c @@ -18,10 +18,14 @@ #include <time.h> #include <sys/resource.h> #include <bpf/bpf.h> -#include "bpf_load.h" +#include <bpf/libbpf.h> #define MAX_CNT 1000000 +static struct bpf_link *links[2]; +static struct bpf_object *obj; +static int cnt; + static __u64 time_get_ns(void) { struct timespec ts; @@ -115,22 +119,54 @@ static void run_perf_test(int tasks, int flags) } } +static int load_progs(char *filename) +{ + struct bpf_program *prog; + int err = 0; + + obj = bpf_object__open_file(filename, NULL); + err = libbpf_get_error(obj); + if (err < 0) { + fprintf(stderr, "ERROR: opening BPF object file failed\n"); + return err; + } + + /* load BPF program */ + err = bpf_object__load(obj); + if (err < 0) { + fprintf(stderr, "ERROR: loading BPF object file failed\n"); + return err; + } + + bpf_object__for_each_program(prog, obj) { + links[cnt] = bpf_program__attach(prog); + err = libbpf_get_error(links[cnt]); + if (err < 0) { + fprintf(stderr, "ERROR: bpf_program__attach failed\n"); + links[cnt] = NULL; + return err; + } + cnt++; + } + + return err; +} + static void unload_progs(void) { - close(prog_fd[0]); - close(prog_fd[1]); - close(event_fd[0]); - close(event_fd[1]); + while (cnt) + bpf_link__destroy(links[--cnt]); + + bpf_object__close(obj); } int main(int argc, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; - char filename[256]; - int num_cpu = 8; + int num_cpu = sysconf(_SC_NPROCESSORS_ONLN); int test_flags = ~0; + char filename[256]; + int err = 0; - setrlimit(RLIMIT_MEMLOCK, &r); if (argc > 1) test_flags = atoi(argv[1]) ? : test_flags; @@ -145,38 +181,36 @@ int main(int argc, char **argv) if (test_flags & 0xC) { snprintf(filename, sizeof(filename), "%s_kprobe_kern.o", argv[0]); - if (load_bpf_file(filename)) { - printf("%s", bpf_log_buf); - return 1; - } + printf("w/KPROBE\n"); - run_perf_test(num_cpu, test_flags >> 2); + err = load_progs(filename); + if (!err) + run_perf_test(num_cpu, test_flags >> 2); + unload_progs(); } if (test_flags & 0x30) { snprintf(filename, sizeof(filename), "%s_tp_kern.o", argv[0]); - if (load_bpf_file(filename)) { - printf("%s", bpf_log_buf); - return 1; - } printf("w/TRACEPOINT\n"); - run_perf_test(num_cpu, test_flags >> 4); + err = load_progs(filename); + if (!err) + run_perf_test(num_cpu, test_flags >> 4); + unload_progs(); } if (test_flags & 0xC0) { snprintf(filename, sizeof(filename), "%s_raw_tp_kern.o", argv[0]); - if (load_bpf_file(filename)) { - printf("%s", bpf_log_buf); - return 1; - } printf("w/RAW_TRACEPOINT\n"); - run_perf_test(num_cpu, test_flags >> 6); + err = load_progs(filename); + if (!err) + run_perf_test(num_cpu, test_flags >> 6); + unload_progs(); } - return 0; + return err; } diff --git a/samples/bpf/trace_event_user.c b/samples/bpf/trace_event_user.c index ac1ba368195c..9664749bf618 100644 --- a/samples/bpf/trace_event_user.c +++ b/samples/bpf/trace_event_user.c @@ -294,13 +294,11 @@ static void test_bpf_perf_event(void) int main(int argc, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; struct bpf_object *obj = NULL; char filename[256]; int error = 1; snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); - setrlimit(RLIMIT_MEMLOCK, &r); signal(SIGINT, err_exit); signal(SIGTERM, err_exit); diff --git a/samples/bpf/tracex2_user.c b/samples/bpf/tracex2_user.c index 3d6eab711d23..1626d51dfffd 100644 --- a/samples/bpf/tracex2_user.c +++ b/samples/bpf/tracex2_user.c @@ -116,7 +116,6 @@ static void int_exit(int sig) int main(int ac, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; long key, next_key, value; struct bpf_link *links[2]; struct bpf_program *prog; @@ -125,11 +124,6 @@ int main(int ac, char **argv) int i, j = 0; FILE *f; - if (setrlimit(RLIMIT_MEMLOCK, &r)) { - perror("setrlimit(RLIMIT_MEMLOCK)"); - return 1; - } - snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); obj = bpf_object__open_file(filename, NULL); if (libbpf_get_error(obj)) { diff --git a/samples/bpf/tracex3_user.c b/samples/bpf/tracex3_user.c index 83e0fecbb01a..33e16ba39f25 100644 --- a/samples/bpf/tracex3_user.c +++ b/samples/bpf/tracex3_user.c @@ -107,7 +107,6 @@ static void print_hist(int fd) int main(int ac, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; struct bpf_link *links[2]; struct bpf_program *prog; struct bpf_object *obj; @@ -127,11 +126,6 @@ int main(int ac, char **argv) } } - if (setrlimit(RLIMIT_MEMLOCK, &r)) { - perror("setrlimit(RLIMIT_MEMLOCK)"); - return 1; - } - snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); obj = bpf_object__open_file(filename, NULL); if (libbpf_get_error(obj)) { diff --git a/samples/bpf/tracex4_user.c b/samples/bpf/tracex4_user.c index e8faf8f184ae..cea399424bca 100644 --- a/samples/bpf/tracex4_user.c +++ b/samples/bpf/tracex4_user.c @@ -48,18 +48,12 @@ static void print_old_objects(int fd) int main(int ac, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; struct bpf_link *links[2]; struct bpf_program *prog; struct bpf_object *obj; char filename[256]; int map_fd, i, j = 0; - if (setrlimit(RLIMIT_MEMLOCK, &r)) { - perror("setrlimit(RLIMIT_MEMLOCK, RLIM_INFINITY)"); - return 1; - } - snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); obj = bpf_object__open_file(filename, NULL); if (libbpf_get_error(obj)) { diff --git a/samples/bpf/tracex5_user.c b/samples/bpf/tracex5_user.c index c17d3fb5fd64..08dfdc77ad2a 100644 --- a/samples/bpf/tracex5_user.c +++ b/samples/bpf/tracex5_user.c @@ -34,7 +34,6 @@ static void install_accept_all_seccomp(void) int main(int ac, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; struct bpf_link *link = NULL; struct bpf_program *prog; struct bpf_object *obj; @@ -43,8 +42,6 @@ int main(int ac, char **argv) char filename[256]; FILE *f; - setrlimit(RLIMIT_MEMLOCK, &r); - snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); obj = bpf_object__open_file(filename, NULL); if (libbpf_get_error(obj)) { diff --git a/samples/bpf/tracex6_user.c b/samples/bpf/tracex6_user.c index 33df9784775d..28296f40c133 100644 --- a/samples/bpf/tracex6_user.c +++ b/samples/bpf/tracex6_user.c @@ -175,15 +175,12 @@ static void test_bpf_perf_event(void) int main(int argc, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; struct bpf_link *links[2]; struct bpf_program *prog; struct bpf_object *obj; char filename[256]; int i = 0; - setrlimit(RLIMIT_MEMLOCK, &r); - snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); obj = bpf_object__open_file(filename, NULL); if (libbpf_get_error(obj)) { diff --git a/samples/bpf/xdp1_user.c b/samples/bpf/xdp1_user.c index c447ad9e3a1d..116e39f6b666 100644 --- a/samples/bpf/xdp1_user.c +++ b/samples/bpf/xdp1_user.c @@ -79,7 +79,6 @@ static void usage(const char *prog) int main(int argc, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; struct bpf_prog_load_attr prog_load_attr = { .prog_type = BPF_PROG_TYPE_XDP, }; @@ -117,11 +116,6 @@ int main(int argc, char **argv) return 1; } - if (setrlimit(RLIMIT_MEMLOCK, &r)) { - perror("setrlimit(RLIMIT_MEMLOCK)"); - return 1; - } - ifindex = if_nametoindex(argv[optind]); if (!ifindex) { perror("if_nametoindex"); diff --git a/samples/bpf/xdp2skb_meta_kern.c b/samples/bpf/xdp2skb_meta_kern.c index 9b783316e860..d5631014a176 100644 --- a/samples/bpf/xdp2skb_meta_kern.c +++ b/samples/bpf/xdp2skb_meta_kern.c @@ -6,7 +6,7 @@ * This uses the XDP data_meta infrastructure, and is a cooperation * between two bpf-programs (1) XDP and (2) clsact at TC-ingress hook. * - * Notice: This example does not use the BPF C-loader (bpf_load.c), + * Notice: This example does not use the BPF C-loader, * but instead rely on the iproute2 TC tool for loading BPF-objects. */ #include <uapi/linux/bpf.h> diff --git a/samples/bpf/xdp_adjust_tail_user.c b/samples/bpf/xdp_adjust_tail_user.c index ba482dc3da33..a70b094c8ec5 100644 --- a/samples/bpf/xdp_adjust_tail_user.c +++ b/samples/bpf/xdp_adjust_tail_user.c @@ -82,7 +82,6 @@ static void usage(const char *cmd) int main(int argc, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; struct bpf_prog_load_attr prog_load_attr = { .prog_type = BPF_PROG_TYPE_XDP, }; @@ -143,11 +142,6 @@ int main(int argc, char **argv) } } - if (setrlimit(RLIMIT_MEMLOCK, &r)) { - perror("setrlimit(RLIMIT_MEMLOCK, RLIM_INFINITY)"); - return 1; - } - if (!ifindex) { fprintf(stderr, "Invalid ifname\n"); return 1; diff --git a/samples/bpf/xdp_monitor_user.c b/samples/bpf/xdp_monitor_user.c index 03d0a182913f..49ebc49aefc3 100644 --- a/samples/bpf/xdp_monitor_user.c +++ b/samples/bpf/xdp_monitor_user.c @@ -687,7 +687,6 @@ static void print_bpf_prog_info(void) int main(int argc, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; struct bpf_program *prog; int longindex = 0, opt; int ret = EXIT_FAILURE; @@ -719,10 +718,6 @@ int main(int argc, char **argv) } snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); - if (setrlimit(RLIMIT_MEMLOCK, &r)) { - perror("setrlimit(RLIMIT_MEMLOCK)"); - return ret; - } /* Remove tracepoint program when program is interrupted or killed */ signal(SIGINT, int_exit); diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c index f78cb18319aa..576411612523 100644 --- a/samples/bpf/xdp_redirect_cpu_user.c +++ b/samples/bpf/xdp_redirect_cpu_user.c @@ -765,7 +765,6 @@ static int load_cpumap_prog(char *file_name, char *prog_name, int main(int argc, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; char *prog_name = "xdp_cpu_map5_lb_hash_ip_pairs"; char *mprog_filename = "xdp_redirect_kern.o"; char *redir_interface = NULL, *redir_map = NULL; @@ -804,11 +803,6 @@ int main(int argc, char **argv) snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); prog_load_attr.file = filename; - if (setrlimit(RLIMIT_MEMLOCK, &r)) { - perror("setrlimit(RLIMIT_MEMLOCK)"); - return 1; - } - if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd)) return err; diff --git a/samples/bpf/xdp_redirect_map_user.c b/samples/bpf/xdp_redirect_map_user.c index 35e16dee613e..31131b6e7782 100644 --- a/samples/bpf/xdp_redirect_map_user.c +++ b/samples/bpf/xdp_redirect_map_user.c @@ -96,7 +96,6 @@ static void usage(const char *prog) int main(int argc, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; struct bpf_prog_load_attr prog_load_attr = { .prog_type = BPF_PROG_TYPE_XDP, }; @@ -135,11 +134,6 @@ int main(int argc, char **argv) return 1; } - if (setrlimit(RLIMIT_MEMLOCK, &r)) { - perror("setrlimit(RLIMIT_MEMLOCK)"); - return 1; - } - ifindex_in = if_nametoindex(argv[optind]); if (!ifindex_in) ifindex_in = strtoul(argv[optind], NULL, 0); diff --git a/samples/bpf/xdp_redirect_user.c b/samples/bpf/xdp_redirect_user.c index 9ca2bf457cda..41d705c3a1f7 100644 --- a/samples/bpf/xdp_redirect_user.c +++ b/samples/bpf/xdp_redirect_user.c @@ -97,7 +97,6 @@ static void usage(const char *prog) int main(int argc, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; struct bpf_prog_load_attr prog_load_attr = { .prog_type = BPF_PROG_TYPE_XDP, }; @@ -136,11 +135,6 @@ int main(int argc, char **argv) return 1; } - if (setrlimit(RLIMIT_MEMLOCK, &r)) { - perror("setrlimit(RLIMIT_MEMLOCK)"); - return 1; - } - ifindex_in = if_nametoindex(argv[optind]); if (!ifindex_in) ifindex_in = strtoul(argv[optind], NULL, 0); diff --git a/samples/bpf/xdp_router_ipv4_user.c b/samples/bpf/xdp_router_ipv4_user.c index c2da1b51ff95..b5f03cb17a3c 100644 --- a/samples/bpf/xdp_router_ipv4_user.c +++ b/samples/bpf/xdp_router_ipv4_user.c @@ -625,7 +625,6 @@ static void usage(const char *prog) int main(int ac, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; struct bpf_prog_load_attr prog_load_attr = { .prog_type = BPF_PROG_TYPE_XDP, }; @@ -670,11 +669,6 @@ int main(int ac, char **argv) return 1; } - if (setrlimit(RLIMIT_MEMLOCK, &r)) { - perror("setrlimit(RLIMIT_MEMLOCK)"); - return 1; - } - if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd)) return 1; diff --git a/samples/bpf/xdp_rxq_info_user.c b/samples/bpf/xdp_rxq_info_user.c index 93fa1bc54f13..74a2926eba08 100644 --- a/samples/bpf/xdp_rxq_info_user.c +++ b/samples/bpf/xdp_rxq_info_user.c @@ -450,7 +450,6 @@ static void stats_poll(int interval, int action, __u32 cfg_opt) int main(int argc, char **argv) { __u32 cfg_options= NO_TOUCH ; /* Default: Don't touch packet memory */ - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; struct bpf_prog_load_attr prog_load_attr = { .prog_type = BPF_PROG_TYPE_XDP, }; @@ -474,11 +473,6 @@ int main(int argc, char **argv) snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); prog_load_attr.file = filename; - if (setrlimit(RLIMIT_MEMLOCK, &r)) { - perror("setrlimit(RLIMIT_MEMLOCK)"); - return 1; - } - if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd)) return EXIT_FAIL; diff --git a/samples/bpf/xdp_sample_pkts_user.c b/samples/bpf/xdp_sample_pkts_user.c index 4b2a300c750c..706475e004cb 100644 --- a/samples/bpf/xdp_sample_pkts_user.c +++ b/samples/bpf/xdp_sample_pkts_user.c @@ -109,7 +109,6 @@ static void usage(const char *prog) int main(int argc, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; struct bpf_prog_load_attr prog_load_attr = { .prog_type = BPF_PROG_TYPE_XDP, }; @@ -143,11 +142,6 @@ int main(int argc, char **argv) return 1; } - if (setrlimit(RLIMIT_MEMLOCK, &r)) { - perror("setrlimit(RLIMIT_MEMLOCK)"); - return 1; - } - snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); prog_load_attr.file = filename; diff --git a/samples/bpf/xdp_tx_iptunnel_user.c b/samples/bpf/xdp_tx_iptunnel_user.c index a419bee151a8..1d4f305d02aa 100644 --- a/samples/bpf/xdp_tx_iptunnel_user.c +++ b/samples/bpf/xdp_tx_iptunnel_user.c @@ -155,7 +155,6 @@ int main(int argc, char **argv) struct bpf_prog_load_attr prog_load_attr = { .prog_type = BPF_PROG_TYPE_XDP, }; - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; int min_port = 0, max_port = 0, vip2tnl_map_fd; const char *optstr = "i:a:p:s:d:m:T:P:FSNh"; unsigned char opt_flags[256] = {}; @@ -254,11 +253,6 @@ int main(int argc, char **argv) } } - if (setrlimit(RLIMIT_MEMLOCK, &r)) { - perror("setrlimit(RLIMIT_MEMLOCK, RLIM_INFINITY)"); - return 1; - } - if (!ifindex) { fprintf(stderr, "Invalid ifname\n"); return 1; diff --git a/samples/bpf/xdpsock.h b/samples/bpf/xdpsock.h index b7eca15c78cc..fd70cce60712 100644 --- a/samples/bpf/xdpsock.h +++ b/samples/bpf/xdpsock.h @@ -8,4 +8,12 @@ #define MAX_SOCKS 4 +#define SOCKET_NAME "sock_cal_bpf_fd" +#define MAX_NUM_OF_CLIENTS 10 + +#define CLOSE_CONN 1 + +typedef __u64 u64; +typedef __u32 u32; + #endif /* XDPSOCK_H */ diff --git a/samples/bpf/xdpsock_ctrl_proc.c b/samples/bpf/xdpsock_ctrl_proc.c new file mode 100644 index 000000000000..384e62e3c6d6 --- /dev/null +++ b/samples/bpf/xdpsock_ctrl_proc.c @@ -0,0 +1,187 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2017 - 2018 Intel Corporation. */ + +#include <errno.h> +#include <getopt.h> +#include <libgen.h> +#include <net/if.h> +#include <stdio.h> +#include <stdlib.h> +#include <sys/socket.h> +#include <sys/un.h> +#include <unistd.h> + +#include <bpf/bpf.h> +#include <bpf/xsk.h> +#include "xdpsock.h" + +static const char *opt_if = ""; + +static struct option long_options[] = { + {"interface", required_argument, 0, 'i'}, + {0, 0, 0, 0} +}; + +static void usage(const char *prog) +{ + const char *str = + " Usage: %s [OPTIONS]\n" + " Options:\n" + " -i, --interface=n Run on interface n\n" + "\n"; + fprintf(stderr, "%s\n", str); + + exit(0); +} + +static void parse_command_line(int argc, char **argv) +{ + int option_index, c; + + opterr = 0; + + for (;;) { + c = getopt_long(argc, argv, "i:", + long_options, &option_index); + if (c == -1) + break; + + switch (c) { + case 'i': + opt_if = optarg; + break; + default: + usage(basename(argv[0])); + } + } +} + +static int send_xsks_map_fd(int sock, int fd) +{ + char cmsgbuf[CMSG_SPACE(sizeof(int))]; + struct msghdr msg; + struct iovec iov; + int value = 0; + + if (fd == -1) { + fprintf(stderr, "Incorrect fd = %d\n", fd); + return -1; + } + iov.iov_base = &value; + iov.iov_len = sizeof(int); + + msg.msg_name = NULL; + msg.msg_namelen = 0; + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + msg.msg_flags = 0; + msg.msg_control = cmsgbuf; + msg.msg_controllen = CMSG_LEN(sizeof(int)); + + struct cmsghdr *cmsg = CMSG_FIRSTHDR(&msg); + + cmsg->cmsg_level = SOL_SOCKET; + cmsg->cmsg_type = SCM_RIGHTS; + cmsg->cmsg_len = CMSG_LEN(sizeof(int)); + + *(int *)CMSG_DATA(cmsg) = fd; + int ret = sendmsg(sock, &msg, 0); + + if (ret == -1) { + fprintf(stderr, "Sendmsg failed with %s", strerror(errno)); + return -errno; + } + + return ret; +} + +int +main(int argc, char **argv) +{ + struct sockaddr_un server; + int listening = 1; + int rval, msgsock; + int ifindex = 0; + int flag = 1; + int cmd = 0; + int sock; + int err; + int xsks_map_fd; + + parse_command_line(argc, argv); + + ifindex = if_nametoindex(opt_if); + if (ifindex == 0) { + fprintf(stderr, "Unable to get ifindex for Interface %s. Reason:%s", + opt_if, strerror(errno)); + return -errno; + } + + sock = socket(AF_UNIX, SOCK_STREAM, 0); + if (sock < 0) { + fprintf(stderr, "Opening socket stream failed: %s", strerror(errno)); + return -errno; + } + + server.sun_family = AF_UNIX; + strcpy(server.sun_path, SOCKET_NAME); + + setsockopt(sock, SOL_SOCKET, SO_REUSEADDR, &flag, sizeof(int)); + + if (bind(sock, (struct sockaddr *)&server, sizeof(struct sockaddr_un))) { + fprintf(stderr, "Binding to socket stream failed: %s", strerror(errno)); + return -errno; + } + + listen(sock, MAX_NUM_OF_CLIENTS); + + err = xsk_setup_xdp_prog(ifindex, &xsks_map_fd); + if (err) { + fprintf(stderr, "Setup of xdp program failed\n"); + goto close_sock; + } + + while (listening) { + msgsock = accept(sock, 0, 0); + if (msgsock == -1) { + fprintf(stderr, "Error accepting connection: %s", strerror(errno)); + err = -errno; + goto close_sock; + } + err = send_xsks_map_fd(msgsock, xsks_map_fd); + if (err <= 0) { + fprintf(stderr, "Error %d sending xsks_map_fd\n", err); + goto cleanup; + } + do { + rval = read(msgsock, &cmd, sizeof(int)); + if (rval < 0) { + fprintf(stderr, "Error reading stream message"); + } else { + if (cmd != CLOSE_CONN) + fprintf(stderr, "Recv unknown cmd = %d\n", cmd); + listening = 0; + break; + } + } while (rval > 0); + } + close(msgsock); + close(sock); + unlink(SOCKET_NAME); + + /* Unset fd for given ifindex */ + err = bpf_set_link_xdp_fd(ifindex, -1, 0); + if (err) { + fprintf(stderr, "Error when unsetting bpf prog_fd for ifindex(%d)\n", ifindex); + return err; + } + + return 0; + +cleanup: + close(msgsock); +close_sock: + close(sock); + unlink(SOCKET_NAME); + return err; +} diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c index 1149e94ca32f..568f9815bb1b 100644 --- a/samples/bpf/xdpsock_user.c +++ b/samples/bpf/xdpsock_user.c @@ -24,10 +24,12 @@ #include <stdio.h> #include <stdlib.h> #include <string.h> +#include <sys/capability.h> #include <sys/mman.h> #include <sys/resource.h> #include <sys/socket.h> #include <sys/types.h> +#include <sys/un.h> #include <time.h> #include <unistd.h> @@ -95,6 +97,8 @@ static int opt_timeout = 1000; static bool opt_need_wakeup = true; static u32 opt_num_xsks = 1; static u32 prog_id; +static bool opt_busy_poll; +static bool opt_reduced_cap; struct xsk_ring_stats { unsigned long rx_npkts; @@ -153,6 +157,7 @@ struct xsk_socket_info { static int num_socks; struct xsk_socket_info *xsks[MAX_SOCKS]; +int sock; static unsigned long get_nsecs(void) { @@ -460,6 +465,7 @@ static void *poller(void *arg) static void remove_xdp_program(void) { u32 curr_prog_id = 0; + int cmd = CLOSE_CONN; if (bpf_get_link_xdp_id(opt_ifindex, &curr_prog_id, opt_xdp_flags)) { printf("bpf_get_link_xdp_id failed\n"); @@ -471,6 +477,13 @@ static void remove_xdp_program(void) printf("couldn't find a prog id on a given interface\n"); else printf("program on interface changed, not removing\n"); + + if (opt_reduced_cap) { + if (write(sock, &cmd, sizeof(int)) < 0) { + fprintf(stderr, "Error writing into stream socket: %s", strerror(errno)); + exit(EXIT_FAILURE); + } + } } static void int_exit(int sig) @@ -853,7 +866,7 @@ static struct xsk_socket_info *xsk_configure_socket(struct xsk_umem_info *umem, xsk->umem = umem; cfg.rx_size = XSK_RING_CONS__DEFAULT_NUM_DESCS; cfg.tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS; - if (opt_num_xsks > 1) + if (opt_num_xsks > 1 || opt_reduced_cap) cfg.libbpf_flags = XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD; else cfg.libbpf_flags = 0; @@ -911,6 +924,8 @@ static struct option long_options[] = { {"quiet", no_argument, 0, 'Q'}, {"app-stats", no_argument, 0, 'a'}, {"irq-string", no_argument, 0, 'I'}, + {"busy-poll", no_argument, 0, 'B'}, + {"reduce-cap", no_argument, 0, 'R'}, {0, 0, 0, 0} }; @@ -933,7 +948,7 @@ static void usage(const char *prog) " -m, --no-need-wakeup Turn off use of driver need wakeup flag.\n" " -f, --frame-size=n Set the frame size (must be a power of two in aligned mode, default is %d).\n" " -u, --unaligned Enable unaligned chunk placement\n" - " -M, --shared-umem Enable XDP_SHARED_UMEM\n" + " -M, --shared-umem Enable XDP_SHARED_UMEM (cannot be used with -R)\n" " -F, --force Force loading the XDP prog\n" " -d, --duration=n Duration in secs to run command.\n" " Default: forever.\n" @@ -949,6 +964,8 @@ static void usage(const char *prog) " -Q, --quiet Do not display any stats.\n" " -a, --app-stats Display application (syscall) statistics.\n" " -I, --irq-string Display driver interrupt statistics for interface associated with irq-string.\n" + " -B, --busy-poll Busy poll.\n" + " -R, --reduce-cap Use reduced capabilities (cannot be used with -M)\n" "\n"; fprintf(stderr, str, prog, XSK_UMEM__DEFAULT_FRAME_SIZE, opt_batch_size, MIN_PKT_SIZE, MIN_PKT_SIZE, @@ -964,7 +981,7 @@ static void parse_command_line(int argc, char **argv) opterr = 0; for (;;) { - c = getopt_long(argc, argv, "Frtli:q:pSNn:czf:muMd:b:C:s:P:xQaI:", + c = getopt_long(argc, argv, "Frtli:q:pSNn:czf:muMd:b:C:s:P:xQaI:BR", long_options, &option_index); if (c == -1) break; @@ -1062,7 +1079,12 @@ static void parse_command_line(int argc, char **argv) fprintf(stderr, "ERROR: Failed to get irqs for %s\n", opt_irq_str); usage(basename(argv[0])); } - + break; + case 'B': + opt_busy_poll = 1; + break; + case 'R': + opt_reduced_cap = true; break; default: usage(basename(argv[0])); @@ -1085,6 +1107,11 @@ static void parse_command_line(int argc, char **argv) opt_xsk_frame_size); usage(basename(argv[0])); } + + if (opt_reduced_cap && opt_num_xsks > 1) { + fprintf(stderr, "ERROR: -M and -R cannot be used together\n"); + usage(basename(argv[0])); + } } static void kick_tx(struct xsk_socket_info *xsk) @@ -1098,8 +1125,7 @@ static void kick_tx(struct xsk_socket_info *xsk) exit_with_error(errno); } -static inline void complete_tx_l2fwd(struct xsk_socket_info *xsk, - struct pollfd *fds) +static inline void complete_tx_l2fwd(struct xsk_socket_info *xsk) { struct xsk_umem_info *umem = xsk->umem; u32 idx_cq = 0, idx_fq = 0; @@ -1132,9 +1158,10 @@ static inline void complete_tx_l2fwd(struct xsk_socket_info *xsk, while (ret != rcvd) { if (ret < 0) exit_with_error(-ret); - if (xsk_ring_prod__needs_wakeup(&umem->fq)) { + if (opt_busy_poll || xsk_ring_prod__needs_wakeup(&umem->fq)) { xsk->app_stats.fill_fail_polls++; - ret = poll(fds, num_socks, opt_timeout); + recvfrom(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, + NULL); } ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq); } @@ -1146,7 +1173,6 @@ static inline void complete_tx_l2fwd(struct xsk_socket_info *xsk, xsk_ring_prod__submit(&xsk->umem->fq, rcvd); xsk_ring_cons__release(&xsk->umem->cq, rcvd); xsk->outstanding_tx -= rcvd; - xsk->ring_stats.tx_npkts += rcvd; } } @@ -1168,11 +1194,10 @@ static inline void complete_tx_only(struct xsk_socket_info *xsk, if (rcvd > 0) { xsk_ring_cons__release(&xsk->umem->cq, rcvd); xsk->outstanding_tx -= rcvd; - xsk->ring_stats.tx_npkts += rcvd; } } -static void rx_drop(struct xsk_socket_info *xsk, struct pollfd *fds) +static void rx_drop(struct xsk_socket_info *xsk) { unsigned int rcvd, i; u32 idx_rx = 0, idx_fq = 0; @@ -1180,9 +1205,9 @@ static void rx_drop(struct xsk_socket_info *xsk, struct pollfd *fds) rcvd = xsk_ring_cons__peek(&xsk->rx, opt_batch_size, &idx_rx); if (!rcvd) { - if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) { + if (opt_busy_poll || xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) { xsk->app_stats.rx_empty_polls++; - ret = poll(fds, num_socks, opt_timeout); + recvfrom(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, NULL); } return; } @@ -1191,9 +1216,9 @@ static void rx_drop(struct xsk_socket_info *xsk, struct pollfd *fds) while (ret != rcvd) { if (ret < 0) exit_with_error(-ret); - if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) { + if (opt_busy_poll || xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) { xsk->app_stats.fill_fail_polls++; - ret = poll(fds, num_socks, opt_timeout); + recvfrom(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, NULL); } ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, &idx_fq); } @@ -1235,7 +1260,7 @@ static void rx_drop_all(void) } for (i = 0; i < num_socks; i++) - rx_drop(xsks[i], fds); + rx_drop(xsks[i]); if (benchmark_done) break; @@ -1260,6 +1285,7 @@ static void tx_only(struct xsk_socket_info *xsk, u32 *frame_nb, int batch_size) } xsk_ring_prod__submit(&xsk->tx, batch_size); + xsk->ring_stats.tx_npkts += batch_size; xsk->outstanding_tx += batch_size; *frame_nb += batch_size; *frame_nb %= NUM_FRAMES; @@ -1332,29 +1358,30 @@ static void tx_only_all(void) complete_tx_only_all(); } -static void l2fwd(struct xsk_socket_info *xsk, struct pollfd *fds) +static void l2fwd(struct xsk_socket_info *xsk) { unsigned int rcvd, i; u32 idx_rx = 0, idx_tx = 0; int ret; - complete_tx_l2fwd(xsk, fds); + complete_tx_l2fwd(xsk); rcvd = xsk_ring_cons__peek(&xsk->rx, opt_batch_size, &idx_rx); if (!rcvd) { - if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) { + if (opt_busy_poll || xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) { xsk->app_stats.rx_empty_polls++; - ret = poll(fds, num_socks, opt_timeout); + recvfrom(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, NULL); } return; } + xsk->ring_stats.rx_npkts += rcvd; ret = xsk_ring_prod__reserve(&xsk->tx, rcvd, &idx_tx); while (ret != rcvd) { if (ret < 0) exit_with_error(-ret); - complete_tx_l2fwd(xsk, fds); - if (xsk_ring_prod__needs_wakeup(&xsk->tx)) { + complete_tx_l2fwd(xsk); + if (opt_busy_poll || xsk_ring_prod__needs_wakeup(&xsk->tx)) { xsk->app_stats.tx_wakeup_sendtos++; kick_tx(xsk); } @@ -1379,7 +1406,7 @@ static void l2fwd(struct xsk_socket_info *xsk, struct pollfd *fds) xsk_ring_prod__submit(&xsk->tx, rcvd); xsk_ring_cons__release(&xsk->rx, rcvd); - xsk->ring_stats.rx_npkts += rcvd; + xsk->ring_stats.tx_npkts += rcvd; xsk->outstanding_tx += rcvd; } @@ -1388,22 +1415,20 @@ static void l2fwd_all(void) struct pollfd fds[MAX_SOCKS] = {}; int i, ret; - for (i = 0; i < num_socks; i++) { - fds[i].fd = xsk_socket__fd(xsks[i]->xsk); - fds[i].events = POLLOUT | POLLIN; - } - for (;;) { if (opt_poll) { - for (i = 0; i < num_socks; i++) + for (i = 0; i < num_socks; i++) { + fds[i].fd = xsk_socket__fd(xsks[i]->xsk); + fds[i].events = POLLOUT | POLLIN; xsks[i]->app_stats.opt_polls++; + } ret = poll(fds, num_socks, opt_timeout); if (ret <= 0) continue; } for (i = 0; i < num_socks; i++) - l2fwd(xsks[i], fds); + l2fwd(xsks[i]); if (benchmark_done) break; @@ -1461,26 +1486,139 @@ static void enter_xsks_into_map(struct bpf_object *obj) } } +static void apply_setsockopt(struct xsk_socket_info *xsk) +{ + int sock_opt; + + if (!opt_busy_poll) + return; + + sock_opt = 1; + if (setsockopt(xsk_socket__fd(xsk->xsk), SOL_SOCKET, SO_PREFER_BUSY_POLL, + (void *)&sock_opt, sizeof(sock_opt)) < 0) + exit_with_error(errno); + + sock_opt = 20; + if (setsockopt(xsk_socket__fd(xsk->xsk), SOL_SOCKET, SO_BUSY_POLL, + (void *)&sock_opt, sizeof(sock_opt)) < 0) + exit_with_error(errno); + + sock_opt = opt_batch_size; + if (setsockopt(xsk_socket__fd(xsk->xsk), SOL_SOCKET, SO_BUSY_POLL_BUDGET, + (void *)&sock_opt, sizeof(sock_opt)) < 0) + exit_with_error(errno); +} + +static int recv_xsks_map_fd_from_ctrl_node(int sock, int *_fd) +{ + char cms[CMSG_SPACE(sizeof(int))]; + struct cmsghdr *cmsg; + struct msghdr msg; + struct iovec iov; + int value; + int len; + + iov.iov_base = &value; + iov.iov_len = sizeof(int); + + msg.msg_name = 0; + msg.msg_namelen = 0; + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + msg.msg_flags = 0; + msg.msg_control = (caddr_t)cms; + msg.msg_controllen = sizeof(cms); + + len = recvmsg(sock, &msg, 0); + + if (len < 0) { + fprintf(stderr, "Recvmsg failed length incorrect.\n"); + return -EINVAL; + } + + if (len == 0) { + fprintf(stderr, "Recvmsg failed no data\n"); + return -EINVAL; + } + + cmsg = CMSG_FIRSTHDR(&msg); + *_fd = *(int *)CMSG_DATA(cmsg); + + return 0; +} + +static int +recv_xsks_map_fd(int *xsks_map_fd) +{ + struct sockaddr_un server; + int err; + + sock = socket(AF_UNIX, SOCK_STREAM, 0); + if (sock < 0) { + fprintf(stderr, "Error opening socket stream: %s", strerror(errno)); + return errno; + } + + server.sun_family = AF_UNIX; + strcpy(server.sun_path, SOCKET_NAME); + + if (connect(sock, (struct sockaddr *)&server, sizeof(struct sockaddr_un)) < 0) { + close(sock); + fprintf(stderr, "Error connecting stream socket: %s", strerror(errno)); + return errno; + } + + err = recv_xsks_map_fd_from_ctrl_node(sock, xsks_map_fd); + if (err) { + fprintf(stderr, "Error %d receiving fd\n", err); + return err; + } + return 0; +} + int main(int argc, char **argv) { + struct __user_cap_header_struct hdr = { _LINUX_CAPABILITY_VERSION_3, 0 }; + struct __user_cap_data_struct data[2] = { { 0 } }; struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; bool rx = false, tx = false; struct xsk_umem_info *umem; struct bpf_object *obj; + int xsks_map_fd = 0; pthread_t pt; int i, ret; void *bufs; parse_command_line(argc, argv); - if (setrlimit(RLIMIT_MEMLOCK, &r)) { - fprintf(stderr, "ERROR: setrlimit(RLIMIT_MEMLOCK) \"%s\"\n", - strerror(errno)); - exit(EXIT_FAILURE); - } + if (opt_reduced_cap) { + if (capget(&hdr, data) < 0) + fprintf(stderr, "Error getting capabilities\n"); + + data->effective &= CAP_TO_MASK(CAP_NET_RAW); + data->permitted &= CAP_TO_MASK(CAP_NET_RAW); + + if (capset(&hdr, data) < 0) + fprintf(stderr, "Setting capabilities failed\n"); - if (opt_num_xsks > 1) - load_xdp_program(argv, &obj); + if (capget(&hdr, data) < 0) { + fprintf(stderr, "Error getting capabilities\n"); + } else { + fprintf(stderr, "Capabilities EFF %x Caps INH %x Caps Per %x\n", + data[0].effective, data[0].inheritable, data[0].permitted); + fprintf(stderr, "Capabilities EFF %x Caps INH %x Caps Per %x\n", + data[1].effective, data[1].inheritable, data[1].permitted); + } + } else { + if (setrlimit(RLIMIT_MEMLOCK, &r)) { + fprintf(stderr, "ERROR: setrlimit(RLIMIT_MEMLOCK) \"%s\"\n", + strerror(errno)); + exit(EXIT_FAILURE); + } + + if (opt_num_xsks > 1) + load_xdp_program(argv, &obj); + } /* Reserve memory for the umem. Use hugepages if unaligned chunk mode */ bufs = mmap(NULL, NUM_FRAMES * opt_xsk_frame_size, @@ -1502,6 +1640,9 @@ int main(int argc, char **argv) for (i = 0; i < opt_num_xsks; i++) xsks[num_socks++] = xsk_configure_socket(umem, rx, tx); + for (i = 0; i < opt_num_xsks; i++) + apply_setsockopt(xsks[i]); + if (opt_bench == BENCH_TXONLY) { gen_eth_hdr_data(); @@ -1512,6 +1653,21 @@ int main(int argc, char **argv) if (opt_num_xsks > 1 && opt_bench != BENCH_TXONLY) enter_xsks_into_map(obj); + if (opt_reduced_cap) { + ret = recv_xsks_map_fd(&xsks_map_fd); + if (ret) { + fprintf(stderr, "Error %d receiving xsks_map_fd\n", ret); + exit_with_error(ret); + } + if (xsks[0]->xsk) { + ret = xsk_socket__update_xskmap(xsks[0]->xsk, xsks_map_fd); + if (ret) { + fprintf(stderr, "Update of BPF map failed(%d)\n", ret); + exit_with_error(ret); + } + } + } + signal(SIGINT, int_exit); signal(SIGTERM, int_exit); signal(SIGABRT, int_exit); |