diff options
Diffstat (limited to 'samples')
56 files changed, 748 insertions, 3629 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 ff4c533dfac2..b0c18efe7928 100644 --- a/samples/bpf/hbm.c +++ b/samples/bpf/hbm.c @@ -46,12 +46,10 @@ #include <bpf/bpf.h> #include <getopt.h> -#include "bpf_load.h" #include "bpf_rlimit.h" #include "cgroup_helpers.h" #include "hbm.h" #include "bpf_util.h" -#include <bpf/bpf.h> #include <bpf/libbpf.h> bool outFlag = true; @@ -71,9 +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) { @@ -122,56 +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"); @@ -191,16 +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; } @@ -214,7 +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; @@ -243,7 +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; @@ -290,14 +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; @@ -395,14 +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 4a74531dc403..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 = {1024*1024, 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_ipip.sh b/samples/bpf/test_ipip.sh deleted file mode 100755 index 9e507c305c6e..000000000000 --- a/samples/bpf/test_ipip.sh +++ /dev/null @@ -1,179 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -function config_device { - ip netns add at_ns0 - ip netns add at_ns1 - ip netns add at_ns2 - ip link add veth0 type veth peer name veth0b - ip link add veth1 type veth peer name veth1b - ip link add veth2 type veth peer name veth2b - ip link set veth0b up - ip link set veth1b up - ip link set veth2b up - ip link set dev veth0b mtu 1500 - ip link set dev veth1b mtu 1500 - ip link set dev veth2b mtu 1500 - ip link set veth0 netns at_ns0 - ip link set veth1 netns at_ns1 - ip link set veth2 netns at_ns2 - ip netns exec at_ns0 ip addr add 172.16.1.100/24 dev veth0 - ip netns exec at_ns0 ip addr add 2401:db00::1/64 dev veth0 nodad - ip netns exec at_ns0 ip link set dev veth0 up - ip netns exec at_ns1 ip addr add 172.16.1.101/24 dev veth1 - ip netns exec at_ns1 ip addr add 2401:db00::2/64 dev veth1 nodad - ip netns exec at_ns1 ip link set dev veth1 up - ip netns exec at_ns2 ip addr add 172.16.1.200/24 dev veth2 - ip netns exec at_ns2 ip addr add 2401:db00::3/64 dev veth2 nodad - ip netns exec at_ns2 ip link set dev veth2 up - ip link add br0 type bridge - ip link set br0 up - ip link set dev br0 mtu 1500 - ip link set veth0b master br0 - ip link set veth1b master br0 - ip link set veth2b master br0 -} - -function add_ipip_tunnel { - ip netns exec at_ns0 \ - ip link add dev $DEV_NS type ipip local 172.16.1.100 remote 172.16.1.200 - ip netns exec at_ns0 ip link set dev $DEV_NS up - ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 - ip netns exec at_ns1 \ - ip link add dev $DEV_NS type ipip local 172.16.1.101 remote 172.16.1.200 - ip netns exec at_ns1 ip link set dev $DEV_NS up - # same inner IP address in at_ns0 and at_ns1 - ip netns exec at_ns1 ip addr add dev $DEV_NS 10.1.1.100/24 - - ip netns exec at_ns2 ip link add dev $DEV type ipip external - ip netns exec at_ns2 ip link set dev $DEV up - ip netns exec at_ns2 ip addr add dev $DEV 10.1.1.200/24 -} - -function add_ipip6_tunnel { - ip netns exec at_ns0 \ - ip link add dev $DEV_NS type ip6tnl mode ipip6 local 2401:db00::1/64 remote 2401:db00::3/64 - ip netns exec at_ns0 ip link set dev $DEV_NS up - ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 - ip netns exec at_ns1 \ - ip link add dev $DEV_NS type ip6tnl mode ipip6 local 2401:db00::2/64 remote 2401:db00::3/64 - ip netns exec at_ns1 ip link set dev $DEV_NS up - # same inner IP address in at_ns0 and at_ns1 - ip netns exec at_ns1 ip addr add dev $DEV_NS 10.1.1.100/24 - - ip netns exec at_ns2 ip link add dev $DEV type ip6tnl mode ipip6 external - ip netns exec at_ns2 ip link set dev $DEV up - ip netns exec at_ns2 ip addr add dev $DEV 10.1.1.200/24 -} - -function add_ip6ip6_tunnel { - ip netns exec at_ns0 \ - ip link add dev $DEV_NS type ip6tnl mode ip6ip6 local 2401:db00::1/64 remote 2401:db00::3/64 - ip netns exec at_ns0 ip link set dev $DEV_NS up - ip netns exec at_ns0 ip addr add dev $DEV_NS 2601:646::1/64 - ip netns exec at_ns1 \ - ip link add dev $DEV_NS type ip6tnl mode ip6ip6 local 2401:db00::2/64 remote 2401:db00::3/64 - ip netns exec at_ns1 ip link set dev $DEV_NS up - # same inner IP address in at_ns0 and at_ns1 - ip netns exec at_ns1 ip addr add dev $DEV_NS 2601:646::1/64 - - ip netns exec at_ns2 ip link add dev $DEV type ip6tnl mode ip6ip6 external - ip netns exec at_ns2 ip link set dev $DEV up - ip netns exec at_ns2 ip addr add dev $DEV 2601:646::2/64 -} - -function attach_bpf { - DEV=$1 - SET_TUNNEL=$2 - GET_TUNNEL=$3 - ip netns exec at_ns2 tc qdisc add dev $DEV clsact - ip netns exec at_ns2 tc filter add dev $DEV egress bpf da obj tcbpf2_kern.o sec $SET_TUNNEL - ip netns exec at_ns2 tc filter add dev $DEV ingress bpf da obj tcbpf2_kern.o sec $GET_TUNNEL -} - -function test_ipip { - DEV_NS=ipip_std - DEV=ipip_bpf - config_device -# tcpdump -nei br0 & - cat /sys/kernel/debug/tracing/trace_pipe & - - add_ipip_tunnel - attach_bpf $DEV ipip_set_tunnel ipip_get_tunnel - - ip netns exec at_ns0 ping -c 1 10.1.1.200 - ip netns exec at_ns2 ping -c 1 10.1.1.100 - ip netns exec at_ns0 iperf -sD -p 5200 > /dev/null - ip netns exec at_ns1 iperf -sD -p 5201 > /dev/null - sleep 0.2 - # tcp check _same_ IP over different tunnels - ip netns exec at_ns2 iperf -c 10.1.1.100 -n 5k -p 5200 - ip netns exec at_ns2 iperf -c 10.1.1.100 -n 5k -p 5201 - cleanup -} - -# IPv4 over IPv6 tunnel -function test_ipip6 { - DEV_NS=ipip_std - DEV=ipip_bpf - config_device -# tcpdump -nei br0 & - cat /sys/kernel/debug/tracing/trace_pipe & - - add_ipip6_tunnel - attach_bpf $DEV ipip6_set_tunnel ipip6_get_tunnel - - ip netns exec at_ns0 ping -c 1 10.1.1.200 - ip netns exec at_ns2 ping -c 1 10.1.1.100 - ip netns exec at_ns0 iperf -sD -p 5200 > /dev/null - ip netns exec at_ns1 iperf -sD -p 5201 > /dev/null - sleep 0.2 - # tcp check _same_ IP over different tunnels - ip netns exec at_ns2 iperf -c 10.1.1.100 -n 5k -p 5200 - ip netns exec at_ns2 iperf -c 10.1.1.100 -n 5k -p 5201 - cleanup -} - -# IPv6 over IPv6 tunnel -function test_ip6ip6 { - DEV_NS=ipip_std - DEV=ipip_bpf - config_device -# tcpdump -nei br0 & - cat /sys/kernel/debug/tracing/trace_pipe & - - add_ip6ip6_tunnel - attach_bpf $DEV ip6ip6_set_tunnel ip6ip6_get_tunnel - - ip netns exec at_ns0 ping -6 -c 1 2601:646::2 - ip netns exec at_ns2 ping -6 -c 1 2601:646::1 - ip netns exec at_ns0 iperf -6sD -p 5200 > /dev/null - ip netns exec at_ns1 iperf -6sD -p 5201 > /dev/null - sleep 0.2 - # tcp check _same_ IP over different tunnels - ip netns exec at_ns2 iperf -6c 2601:646::1 -n 5k -p 5200 - ip netns exec at_ns2 iperf -6c 2601:646::1 -n 5k -p 5201 - cleanup -} - -function cleanup { - set +ex - pkill iperf - ip netns delete at_ns0 - ip netns delete at_ns1 - ip netns delete at_ns2 - ip link del veth0 - ip link del veth1 - ip link del veth2 - ip link del br0 - pkill tcpdump - pkill cat - set -ex -} - -cleanup -echo "Testing IP tunnels..." -test_ipip -test_ipip6 -test_ip6ip6 -echo "*** PASS ***" 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 3e36b3e4e3ef..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 = {1024*1024, 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 70e987775c15..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 = {1024*1024, 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 6fb8dbde62c5..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 = {10 * 1024 * 1024, 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 caa4e7ffcfc7..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 = {10 * 1024 * 1024, 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..db0cb73513a5 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; @@ -1250,6 +1275,8 @@ static void tx_only(struct xsk_socket_info *xsk, u32 *frame_nb, int batch_size) while (xsk_ring_prod__reserve(&xsk->tx, batch_size, &idx) < batch_size) { complete_tx_only(xsk, batch_size); + if (benchmark_done) + return; } for (i = 0; i < batch_size; i++) { @@ -1260,6 +1287,7 @@ 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 +1360,30 @@ 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 +1408,7 @@ 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 +1417,20 @@ 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 +1488,139 @@ 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 +1642,9 @@ 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 +1655,21 @@ 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); diff --git a/samples/ftrace/ftrace-direct-modify.c b/samples/ftrace/ftrace-direct-modify.c index c13a5bc5095b..5b9a09957c6e 100644 --- a/samples/ftrace/ftrace-direct-modify.c +++ b/samples/ftrace/ftrace-direct-modify.c @@ -21,6 +21,7 @@ static unsigned long my_ip = (unsigned long)schedule; asm ( " .pushsection .text, \"ax\", @progbits\n" " .type my_tramp1, @function\n" +" .globl my_tramp1\n" " my_tramp1:" " pushq %rbp\n" " movq %rsp, %rbp\n" @@ -29,6 +30,7 @@ asm ( " .size my_tramp1, .-my_tramp1\n" " ret\n" " .type my_tramp2, @function\n" +" .globl my_tramp2\n" " my_tramp2:" " pushq %rbp\n" " movq %rsp, %rbp\n" diff --git a/samples/ftrace/ftrace-direct-too.c b/samples/ftrace/ftrace-direct-too.c index d5c5022be664..3f0079c9bd6f 100644 --- a/samples/ftrace/ftrace-direct-too.c +++ b/samples/ftrace/ftrace-direct-too.c @@ -16,6 +16,7 @@ extern void my_tramp(void *); asm ( " .pushsection .text, \"ax\", @progbits\n" " .type my_tramp, @function\n" +" .globl my_tramp\n" " my_tramp:" " pushq %rbp\n" " movq %rsp, %rbp\n" diff --git a/samples/ftrace/ftrace-direct.c b/samples/ftrace/ftrace-direct.c index 63ca06d42c80..a2729d1ef17f 100644 --- a/samples/ftrace/ftrace-direct.c +++ b/samples/ftrace/ftrace-direct.c @@ -14,6 +14,7 @@ extern void my_tramp(void *); asm ( " .pushsection .text, \"ax\", @progbits\n" " .type my_tramp, @function\n" +" .globl my_tramp\n" " my_tramp:" " pushq %rbp\n" " movq %rsp, %rbp\n" diff --git a/samples/hidraw/hid-example.c b/samples/hidraw/hid-example.c index 37a0ffcb4d63..0f73ace3c6c3 100644 --- a/samples/hidraw/hid-example.c +++ b/samples/hidraw/hid-example.c @@ -128,7 +128,7 @@ int main(int argc, char **argv) perror("HIDIOCGFEATURE"); } else { printf("ioctl HIDIOCGFEATURE returned: %d\n", res); - printf("Report data (not containing the report number):\n\t"); + printf("Report data:\n\t"); for (i = 0; i < res; i++) printf("%hhx ", buf[i]); puts("\n"); diff --git a/samples/mic/mpssd/.gitignore b/samples/mic/mpssd/.gitignore deleted file mode 100644 index aa03f1eb37a0..000000000000 --- a/samples/mic/mpssd/.gitignore +++ /dev/null @@ -1,2 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -mpssd diff --git a/samples/mic/mpssd/Makefile b/samples/mic/mpssd/Makefile deleted file mode 100644 index a7a6e0c70424..000000000000 --- a/samples/mic/mpssd/Makefile +++ /dev/null @@ -1,28 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -ifndef CROSS_COMPILE -uname_M := $(shell uname -m 2>/dev/null || echo not) -ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/) - -ifeq ($(ARCH),x86) - -PROGS := mpssd -CC = $(CROSS_COMPILE)gcc -CFLAGS := -I../../../usr/include -I../../../tools/include - -ifdef DEBUG -CFLAGS += -DDEBUG=$(DEBUG) -endif - -all: $(PROGS) -mpssd: mpssd.c sysfs.c - $(CC) $(CFLAGS) mpssd.c sysfs.c -o mpssd -lpthread - -install: - install mpssd /usr/sbin/mpssd - install micctrl /usr/sbin/micctrl - -clean: - rm -fr $(PROGS) - -endif -endif diff --git a/samples/mic/mpssd/micctrl b/samples/mic/mpssd/micctrl deleted file mode 100755 index 030a60b04046..000000000000 --- a/samples/mic/mpssd/micctrl +++ /dev/null @@ -1,162 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0-only -# Intel MIC Platform Software Stack (MPSS) -# -# Copyright(c) 2013 Intel Corporation. -# -# Intel MIC User Space Tools. -# -# micctrl - Controls MIC boot/start/stop. -# -# chkconfig: 2345 95 05 -# description: start MPSS stack processing. -# -### BEGIN INIT INFO -# Provides: micctrl -### END INIT INFO - -# Source function library. -. /etc/init.d/functions - -sysfs="/sys/class/mic" - -_status() -{ - f=$sysfs/$1 - echo -e $1 state: "`cat $f/state`" shutdown_status: "`cat $f/shutdown_status`" -} - -status() -{ - if [ "`echo $1 | head -c3`" == "mic" ]; then - _status $1 - return $? - fi - for f in $sysfs/* - do - _status `basename $f` - RETVAL=$? - [ $RETVAL -ne 0 ] && return $RETVAL - done - return 0 -} - -_reset() -{ - f=$sysfs/$1 - echo reset > $f/state -} - -reset() -{ - if [ "`echo $1 | head -c3`" == "mic" ]; then - _reset $1 - return $? - fi - for f in $sysfs/* - do - _reset `basename $f` - RETVAL=$? - [ $RETVAL -ne 0 ] && return $RETVAL - done - return 0 -} - -_boot() -{ - f=$sysfs/$1 - echo "linux" > $f/bootmode - echo "mic/uos.img" > $f/firmware - echo "mic/$1.image" > $f/ramdisk - echo "boot" > $f/state -} - -boot() -{ - if [ "`echo $1 | head -c3`" == "mic" ]; then - _boot $1 - return $? - fi - for f in $sysfs/* - do - _boot `basename $f` - RETVAL=$? - [ $RETVAL -ne 0 ] && return $RETVAL - done - return 0 -} - -_shutdown() -{ - f=$sysfs/$1 - echo shutdown > $f/state -} - -shutdown() -{ - if [ "`echo $1 | head -c3`" == "mic" ]; then - _shutdown $1 - return $? - fi - for f in $sysfs/* - do - _shutdown `basename $f` - RETVAL=$? - [ $RETVAL -ne 0 ] && return $RETVAL - done - return 0 -} - -_wait() -{ - f=$sysfs/$1 - while [ "`cat $f/state`" != "offline" -a "`cat $f/state`" != "online" ] - do - sleep 1 - echo -e "Waiting for $1 to go offline" - done -} - -wait() -{ - if [ "`echo $1 | head -c3`" == "mic" ]; then - _wait $1 - return $? - fi - # Wait for the cards to go offline - for f in $sysfs/* - do - _wait `basename $f` - RETVAL=$? - [ $RETVAL -ne 0 ] && return $RETVAL - done - return 0 -} - -if [ ! -d "$sysfs" ]; then - echo -e $"Module unloaded " - exit 3 -fi - -case $1 in - -s) - status $2 - ;; - -r) - reset $2 - ;; - -b) - boot $2 - ;; - -S) - shutdown $2 - ;; - -w) - wait $2 - ;; - *) - echo $"Usage: $0 {-s (status) |-r (reset) |-b (boot) |-S (shutdown) |-w (wait)}" - exit 2 -esac - -exit $? diff --git a/samples/mic/mpssd/mpss b/samples/mic/mpssd/mpss deleted file mode 100755 index 248ac7313c71..000000000000 --- a/samples/mic/mpssd/mpss +++ /dev/null @@ -1,189 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0-only -# Intel MIC Platform Software Stack (MPSS) -# -# Copyright(c) 2013 Intel Corporation. -# -# Intel MIC User Space Tools. -# -# mpss Start mpssd. -# -# chkconfig: 2345 95 05 -# description: start MPSS stack processing. -# -### BEGIN INIT INFO -# Provides: mpss -# Required-Start: -# Required-Stop: -# Short-Description: MPSS stack control -# Description: MPSS stack control -### END INIT INFO - -# Source function library. -. /etc/init.d/functions - -exec=/usr/sbin/mpssd -sysfs="/sys/class/mic" -mic_modules="mic_host mic_x100_dma scif vop" - -start() -{ - [ -x $exec ] || exit 5 - - if [ "`ps -e | awk '{print $4}' | grep mpssd | head -1`" = "mpssd" ]; then - echo -e $"MPSSD already running! " - success - echo - return 0 - fi - - echo -e $"Starting MPSS Stack" - echo -e $"Loading MIC drivers:" $mic_modules - - modprobe -a $mic_modules - RETVAL=$? - if [ $RETVAL -ne 0 ]; then - failure - echo - return $RETVAL - fi - - # Start the daemon - echo -n $"Starting MPSSD " - $exec - RETVAL=$? - if [ $RETVAL -ne 0 ]; then - failure - echo - return $RETVAL - fi - success - echo - - sleep 5 - - # Boot the cards - micctrl -b - - # Wait till ping works - for f in $sysfs/* - do - count=100 - ipaddr=`cat $f/cmdline` - ipaddr=${ipaddr#*address,} - ipaddr=`echo $ipaddr | cut -d, -f1 | cut -d\; -f1` - while [ $count -ge 0 ] - do - echo -e "Pinging "`basename $f`" " - ping -c 1 $ipaddr &> /dev/null - RETVAL=$? - if [ $RETVAL -eq 0 ]; then - success - break - fi - sleep 1 - count=`expr $count - 1` - done - [ $RETVAL -ne 0 ] && failure || success - echo - done - return $RETVAL -} - -stop() -{ - echo -e $"Shutting down MPSS Stack: " - - # Bail out if module is unloaded - if [ ! -d "$sysfs" ]; then - echo -n $"Module unloaded " - success - echo - return 0 - fi - - # Shut down the cards. - micctrl -S - - # Wait for the cards to go offline - for f in $sysfs/* - do - while [ "`cat $f/state`" != "ready" ] - do - sleep 1 - echo -e "Waiting for "`basename $f`" to become ready" - done - done - - # Display the status of the cards - micctrl -s - - # Kill MPSSD now - echo -n $"Killing MPSSD" - killall -9 mpssd 2>/dev/null - RETVAL=$? - [ $RETVAL -ne 0 ] && failure || success - echo - return $RETVAL -} - -restart() -{ - stop - sleep 5 - start -} - -status() -{ - micctrl -s - if [ "`ps -e | awk '{print $4}' | grep mpssd | head -n 1`" = "mpssd" ]; then - echo "mpssd is running" - else - echo "mpssd is stopped" - fi - return 0 -} - -unload() -{ - if [ ! -d "$sysfs" ]; then - echo -n $"No MIC_HOST Module: " - success - echo - return - fi - - stop - - sleep 5 - echo -n $"Removing MIC drivers:" $mic_modules - modprobe -r $mic_modules - RETVAL=$? - [ $RETVAL -ne 0 ] && failure || success - echo - return $RETVAL -} - -case $1 in - start) - start - ;; - stop) - stop - ;; - restart) - restart - ;; - status) - status - ;; - unload) - unload - ;; - *) - echo $"Usage: $0 {start|stop|restart|status|unload}" - exit 2 -esac - -exit $? diff --git a/samples/mic/mpssd/mpssd.c b/samples/mic/mpssd/mpssd.c deleted file mode 100644 index c03a05d498f0..000000000000 --- a/samples/mic/mpssd/mpssd.c +++ /dev/null @@ -1,1815 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Intel MIC Platform Software Stack (MPSS) - * - * Copyright(c) 2013 Intel Corporation. - * - * Intel MIC User Space Tools. - */ - -#define _GNU_SOURCE - -#include <stdlib.h> -#include <fcntl.h> -#include <getopt.h> -#include <assert.h> -#include <unistd.h> -#include <stdbool.h> -#include <signal.h> -#include <poll.h> -#include <features.h> -#include <sys/types.h> -#include <sys/stat.h> -#include <sys/mman.h> -#include <sys/socket.h> -#include <linux/virtio_ring.h> -#include <linux/virtio_net.h> -#include <linux/virtio_console.h> -#include <linux/virtio_blk.h> -#include <linux/version.h> -#include "mpssd.h" -#include <linux/mic_ioctl.h> -#include <linux/mic_common.h> -#include <tools/endian.h> - -static void *init_mic(void *arg); - -static FILE *logfp; -static struct mic_info mic_list; - -#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) - -#define min_t(type, x, y) ({ \ - type __min1 = (x); \ - type __min2 = (y); \ - __min1 < __min2 ? __min1 : __min2; }) - -/* align addr on a size boundary - adjust address up/down if needed */ -#define _ALIGN_DOWN(addr, size) ((addr)&(~((size)-1))) -#define _ALIGN_UP(addr, size) _ALIGN_DOWN(addr + size - 1, size) - -/* align addr on a size boundary - adjust address up if needed */ -#define _ALIGN(addr, size) _ALIGN_UP(addr, size) - -/* to align the pointer to the (next) page boundary */ -#define PAGE_ALIGN(addr) _ALIGN(addr, PAGE_SIZE) - -#define READ_ONCE(x) (*(volatile typeof(x) *)&(x)) - -#define GSO_ENABLED 1 -#define MAX_GSO_SIZE (64 * 1024) -#define ETH_H_LEN 14 -#define MAX_NET_PKT_SIZE (_ALIGN_UP(MAX_GSO_SIZE + ETH_H_LEN, 64)) -#define MIC_DEVICE_PAGE_END 0x1000 - -#ifndef VIRTIO_NET_HDR_F_DATA_VALID -#define VIRTIO_NET_HDR_F_DATA_VALID 2 /* Csum is valid */ -#endif - -static struct { - struct mic_device_desc dd; - struct mic_vqconfig vqconfig[2]; - __u32 host_features, guest_acknowledgements; - struct virtio_console_config cons_config; -} virtcons_dev_page = { - .dd = { - .type = VIRTIO_ID_CONSOLE, - .num_vq = ARRAY_SIZE(virtcons_dev_page.vqconfig), - .feature_len = sizeof(virtcons_dev_page.host_features), - .config_len = sizeof(virtcons_dev_page.cons_config), - }, - .vqconfig[0] = { - .num = htole16(MIC_VRING_ENTRIES), - }, - .vqconfig[1] = { - .num = htole16(MIC_VRING_ENTRIES), - }, -}; - -static struct { - struct mic_device_desc dd; - struct mic_vqconfig vqconfig[2]; - __u32 host_features, guest_acknowledgements; - struct virtio_net_config net_config; -} virtnet_dev_page = { - .dd = { - .type = VIRTIO_ID_NET, - .num_vq = ARRAY_SIZE(virtnet_dev_page.vqconfig), - .feature_len = sizeof(virtnet_dev_page.host_features), - .config_len = sizeof(virtnet_dev_page.net_config), - }, - .vqconfig[0] = { - .num = htole16(MIC_VRING_ENTRIES), - }, - .vqconfig[1] = { - .num = htole16(MIC_VRING_ENTRIES), - }, -#if GSO_ENABLED - .host_features = htole32( - 1 << VIRTIO_NET_F_CSUM | - 1 << VIRTIO_NET_F_GSO | - 1 << VIRTIO_NET_F_GUEST_TSO4 | - 1 << VIRTIO_NET_F_GUEST_TSO6 | - 1 << VIRTIO_NET_F_GUEST_ECN), -#else - .host_features = 0, -#endif -}; - -static const char *mic_config_dir = "/etc/mpss"; -static const char *virtblk_backend = "VIRTBLK_BACKEND"; -static struct { - struct mic_device_desc dd; - struct mic_vqconfig vqconfig[1]; - __u32 host_features, guest_acknowledgements; - struct virtio_blk_config blk_config; -} virtblk_dev_page = { - .dd = { - .type = VIRTIO_ID_BLOCK, - .num_vq = ARRAY_SIZE(virtblk_dev_page.vqconfig), - .feature_len = sizeof(virtblk_dev_page.host_features), - .config_len = sizeof(virtblk_dev_page.blk_config), - }, - .vqconfig[0] = { - .num = htole16(MIC_VRING_ENTRIES), - }, - .host_features = - htole32(1<<VIRTIO_BLK_F_SEG_MAX), - .blk_config = { - .seg_max = htole32(MIC_VRING_ENTRIES - 2), - .capacity = htole64(0), - } -}; - -static char *myname; - -static int -tap_configure(struct mic_info *mic, char *dev) -{ - pid_t pid; - char *ifargv[7]; - char ipaddr[IFNAMSIZ]; - int ret = 0; - - pid = fork(); - if (pid == 0) { - ifargv[0] = "ip"; - ifargv[1] = "link"; - ifargv[2] = "set"; - ifargv[3] = dev; - ifargv[4] = "up"; - ifargv[5] = NULL; - mpsslog("Configuring %s\n", dev); - ret = execvp("ip", ifargv); - if (ret < 0) { - mpsslog("%s execvp failed errno %s\n", - mic->name, strerror(errno)); - return ret; - } - } - if (pid < 0) { - mpsslog("%s fork failed errno %s\n", - mic->name, strerror(errno)); - return ret; - } - - ret = waitpid(pid, NULL, 0); - if (ret < 0) { - mpsslog("%s waitpid failed errno %s\n", - mic->name, strerror(errno)); - return ret; - } - - snprintf(ipaddr, IFNAMSIZ, "172.31.%d.254/24", mic->id + 1); - - pid = fork(); - if (pid == 0) { - ifargv[0] = "ip"; - ifargv[1] = "addr"; - ifargv[2] = "add"; - ifargv[3] = ipaddr; - ifargv[4] = "dev"; - ifargv[5] = dev; - ifargv[6] = NULL; - mpsslog("Configuring %s ipaddr %s\n", dev, ipaddr); - ret = execvp("ip", ifargv); - if (ret < 0) { - mpsslog("%s execvp failed errno %s\n", - mic->name, strerror(errno)); - return ret; - } - } - if (pid < 0) { - mpsslog("%s fork failed errno %s\n", - mic->name, strerror(errno)); - return ret; - } - - ret = waitpid(pid, NULL, 0); - if (ret < 0) { - mpsslog("%s waitpid failed errno %s\n", - mic->name, strerror(errno)); - return ret; - } - mpsslog("MIC name %s %s %d DONE!\n", - mic->name, __func__, __LINE__); - return 0; -} - -static int tun_alloc(struct mic_info *mic, char *dev) -{ - struct ifreq ifr; - int fd, err; -#if GSO_ENABLED - unsigned offload; -#endif - fd = open("/dev/net/tun", O_RDWR); - if (fd < 0) { - mpsslog("Could not open /dev/net/tun %s\n", strerror(errno)); - goto done; - } - - memset(&ifr, 0, sizeof(ifr)); - - ifr.ifr_flags = IFF_TAP | IFF_NO_PI | IFF_VNET_HDR; - if (*dev) - strncpy(ifr.ifr_name, dev, IFNAMSIZ); - - err = ioctl(fd, TUNSETIFF, (void *)&ifr); - if (err < 0) { - mpsslog("%s %s %d TUNSETIFF failed %s\n", - mic->name, __func__, __LINE__, strerror(errno)); - close(fd); - return err; - } -#if GSO_ENABLED - offload = TUN_F_CSUM | TUN_F_TSO4 | TUN_F_TSO6 | TUN_F_TSO_ECN; - - err = ioctl(fd, TUNSETOFFLOAD, offload); - if (err < 0) { - mpsslog("%s %s %d TUNSETOFFLOAD failed %s\n", - mic->name, __func__, __LINE__, strerror(errno)); - close(fd); - return err; - } -#endif - strcpy(dev, ifr.ifr_name); - mpsslog("Created TAP %s\n", dev); -done: - return fd; -} - -#define NET_FD_VIRTIO_NET 0 -#define NET_FD_TUN 1 -#define MAX_NET_FD 2 - -static void set_dp(struct mic_info *mic, int type, void *dp) -{ - switch (type) { - case VIRTIO_ID_CONSOLE: - mic->mic_console.console_dp = dp; - return; - case VIRTIO_ID_NET: - mic->mic_net.net_dp = dp; - return; - case VIRTIO_ID_BLOCK: - mic->mic_virtblk.block_dp = dp; - return; - } - mpsslog("%s %s %d not found\n", mic->name, __func__, type); - assert(0); -} - -static void *get_dp(struct mic_info *mic, int type) -{ - switch (type) { - case VIRTIO_ID_CONSOLE: - return mic->mic_console.console_dp; - case VIRTIO_ID_NET: - return mic->mic_net.net_dp; - case VIRTIO_ID_BLOCK: - return mic->mic_virtblk.block_dp; - } - mpsslog("%s %s %d not found\n", mic->name, __func__, type); - assert(0); - return NULL; -} - -static struct mic_device_desc *get_device_desc(struct mic_info *mic, int type) -{ - struct mic_device_desc *d; - int i; - void *dp = get_dp(mic, type); - - for (i = sizeof(struct mic_bootparam); i < PAGE_SIZE; - i += mic_total_desc_size(d)) { - d = dp + i; - - /* End of list */ - if (d->type == 0) - break; - - if (d->type == -1) - continue; - - mpsslog("%s %s d-> type %d d %p\n", - mic->name, __func__, d->type, d); - - if (d->type == (__u8)type) - return d; - } - mpsslog("%s %s %d not found\n", mic->name, __func__, type); - return NULL; -} - -/* See comments in vhost.c for explanation of next_desc() */ -static unsigned next_desc(struct vring_desc *desc) -{ - unsigned int next; - - if (!(le16toh(desc->flags) & VRING_DESC_F_NEXT)) - return -1U; - next = le16toh(desc->next); - return next; -} - -/* Sum up all the IOVEC length */ -static ssize_t -sum_iovec_len(struct mic_copy_desc *copy) -{ - ssize_t sum = 0; - unsigned int i; - - for (i = 0; i < copy->iovcnt; i++) - sum += copy->iov[i].iov_len; - return sum; -} - -static inline void verify_out_len(struct mic_info *mic, - struct mic_copy_desc *copy) -{ - if (copy->out_len != sum_iovec_len(copy)) { - mpsslog("%s %s %d BUG copy->out_len 0x%x len 0x%zx\n", - mic->name, __func__, __LINE__, - copy->out_len, sum_iovec_len(copy)); - assert(copy->out_len == sum_iovec_len(copy)); - } -} - -/* Display an iovec */ -static void -disp_iovec(struct mic_info *mic, struct mic_copy_desc *copy, - const char *s, int line) -{ - unsigned int i; - - for (i = 0; i < copy->iovcnt; i++) - mpsslog("%s %s %d copy->iov[%d] addr %p len 0x%zx\n", - mic->name, s, line, i, - copy->iov[i].iov_base, copy->iov[i].iov_len); -} - -static inline __u16 read_avail_idx(struct mic_vring *vr) -{ - return READ_ONCE(vr->info->avail_idx); -} - -static inline void txrx_prepare(int type, bool tx, struct mic_vring *vr, - struct mic_copy_desc *copy, ssize_t len) -{ - copy->vr_idx = tx ? 0 : 1; - copy->update_used = true; - if (type == VIRTIO_ID_NET) - copy->iov[1].iov_len = len - sizeof(struct virtio_net_hdr); - else - copy->iov[0].iov_len = len; -} - -/* Central API which triggers the copies */ -static int -mic_virtio_copy(struct mic_info *mic, int fd, - struct mic_vring *vr, struct mic_copy_desc *copy) -{ - int ret; - - ret = ioctl(fd, MIC_VIRTIO_COPY_DESC, copy); - if (ret) { - mpsslog("%s %s %d errno %s ret %d\n", - mic->name, __func__, __LINE__, - strerror(errno), ret); - } - return ret; -} - -static inline unsigned _vring_size(unsigned int num, unsigned long align) -{ - return _ALIGN_UP(((sizeof(struct vring_desc) * num + sizeof(__u16) * (3 + num) - + align - 1) & ~(align - 1)) - + sizeof(__u16) * 3 + sizeof(struct vring_used_elem) * num, 4); -} - -/* - * This initialization routine requires at least one - * vring i.e. vr0. vr1 is optional. - */ -static void * -init_vr(struct mic_info *mic, int fd, int type, - struct mic_vring *vr0, struct mic_vring *vr1, int num_vq) -{ - int vr_size; - char *va; - - vr_size = PAGE_ALIGN(_vring_size(MIC_VRING_ENTRIES, - MIC_VIRTIO_RING_ALIGN) + - sizeof(struct _mic_vring_info)); - va = mmap(NULL, MIC_DEVICE_PAGE_END + vr_size * num_vq, - PROT_READ, MAP_SHARED, fd, 0); - if (MAP_FAILED == va) { - mpsslog("%s %s %d mmap failed errno %s\n", - mic->name, __func__, __LINE__, - strerror(errno)); - goto done; - } - set_dp(mic, type, va); - vr0->va = (struct mic_vring *)&va[MIC_DEVICE_PAGE_END]; - vr0->info = vr0->va + - _vring_size(MIC_VRING_ENTRIES, MIC_VIRTIO_RING_ALIGN); - vring_init(&vr0->vr, - MIC_VRING_ENTRIES, vr0->va, MIC_VIRTIO_RING_ALIGN); - mpsslog("%s %s vr0 %p vr0->info %p vr_size 0x%x vring 0x%x ", - __func__, mic->name, vr0->va, vr0->info, vr_size, - _vring_size(MIC_VRING_ENTRIES, MIC_VIRTIO_RING_ALIGN)); - mpsslog("magic 0x%x expected 0x%x\n", - le32toh(vr0->info->magic), MIC_MAGIC + type); - assert(le32toh(vr0->info->magic) == MIC_MAGIC + type); - if (vr1) { - vr1->va = (struct mic_vring *) - &va[MIC_DEVICE_PAGE_END + vr_size]; - vr1->info = vr1->va + _vring_size(MIC_VRING_ENTRIES, - MIC_VIRTIO_RING_ALIGN); - vring_init(&vr1->vr, - MIC_VRING_ENTRIES, vr1->va, MIC_VIRTIO_RING_ALIGN); - mpsslog("%s %s vr1 %p vr1->info %p vr_size 0x%x vring 0x%x ", - __func__, mic->name, vr1->va, vr1->info, vr_size, - _vring_size(MIC_VRING_ENTRIES, MIC_VIRTIO_RING_ALIGN)); - mpsslog("magic 0x%x expected 0x%x\n", - le32toh(vr1->info->magic), MIC_MAGIC + type + 1); - assert(le32toh(vr1->info->magic) == MIC_MAGIC + type + 1); - } -done: - return va; -} - -static int -wait_for_card_driver(struct mic_info *mic, int fd, int type) -{ - struct pollfd pollfd; - int err; - struct mic_device_desc *desc = get_device_desc(mic, type); - __u8 prev_status; - - if (!desc) - return -ENODEV; - prev_status = desc->status; - pollfd.fd = fd; - mpsslog("%s %s Waiting .... desc-> type %d status 0x%x\n", - mic->name, __func__, type, desc->status); - - while (1) { - pollfd.events = POLLIN; - pollfd.revents = 0; - err = poll(&pollfd, 1, -1); - if (err < 0) { - mpsslog("%s %s poll failed %s\n", - mic->name, __func__, strerror(errno)); - continue; - } - - if (pollfd.revents) { - if (desc->status != prev_status) { - mpsslog("%s %s Waiting... desc-> type %d " - "status 0x%x\n", - mic->name, __func__, type, - desc->status); - prev_status = desc->status; - } - if (desc->status & VIRTIO_CONFIG_S_DRIVER_OK) { - mpsslog("%s %s poll.revents %d\n", - mic->name, __func__, pollfd.revents); - mpsslog("%s %s desc-> type %d status 0x%x\n", - mic->name, __func__, type, - desc->status); - break; - } - } - } - return 0; -} - -/* Spin till we have some descriptors */ -static void -spin_for_descriptors(struct mic_info *mic, struct mic_vring *vr) -{ - __u16 avail_idx = read_avail_idx(vr); - - while (avail_idx == le16toh(READ_ONCE(vr->vr.avail->idx))) { -#ifdef DEBUG - mpsslog("%s %s waiting for desc avail %d info_avail %d\n", - mic->name, __func__, - le16toh(vr->vr.avail->idx), vr->info->avail_idx); -#endif - sched_yield(); - } -} - -static void * -virtio_net(void *arg) -{ - static __u8 vnet_hdr[2][sizeof(struct virtio_net_hdr)]; - static __u8 vnet_buf[2][MAX_NET_PKT_SIZE] __attribute__ ((aligned(64))); - struct iovec vnet_iov[2][2] = { - { { .iov_base = vnet_hdr[0], .iov_len = sizeof(vnet_hdr[0]) }, - { .iov_base = vnet_buf[0], .iov_len = sizeof(vnet_buf[0]) } }, - { { .iov_base = vnet_hdr[1], .iov_len = sizeof(vnet_hdr[1]) }, - { .iov_base = vnet_buf[1], .iov_len = sizeof(vnet_buf[1]) } }, - }; - struct iovec *iov0 = vnet_iov[0], *iov1 = vnet_iov[1]; - struct mic_info *mic = (struct mic_info *)arg; - char if_name[IFNAMSIZ]; - struct pollfd net_poll[MAX_NET_FD]; - struct mic_vring tx_vr, rx_vr; - struct mic_copy_desc copy; - struct mic_device_desc *desc; - int err; - - snprintf(if_name, IFNAMSIZ, "mic%d", mic->id); - mic->mic_net.tap_fd = tun_alloc(mic, if_name); - if (mic->mic_net.tap_fd < 0) - goto done; - - if (tap_configure(mic, if_name)) - goto done; - mpsslog("MIC name %s id %d\n", mic->name, mic->id); - - net_poll[NET_FD_VIRTIO_NET].fd = mic->mic_net.virtio_net_fd; - net_poll[NET_FD_VIRTIO_NET].events = POLLIN; - net_poll[NET_FD_TUN].fd = mic->mic_net.tap_fd; - net_poll[NET_FD_TUN].events = POLLIN; - - if (MAP_FAILED == init_vr(mic, mic->mic_net.virtio_net_fd, - VIRTIO_ID_NET, &tx_vr, &rx_vr, - virtnet_dev_page.dd.num_vq)) { - mpsslog("%s init_vr failed %s\n", - mic->name, strerror(errno)); - goto done; - } - - copy.iovcnt = 2; - desc = get_device_desc(mic, VIRTIO_ID_NET); - - while (1) { - ssize_t len; - - net_poll[NET_FD_VIRTIO_NET].revents = 0; - net_poll[NET_FD_TUN].revents = 0; - - /* Start polling for data from tap and virtio net */ - err = poll(net_poll, 2, -1); - if (err < 0) { - mpsslog("%s poll failed %s\n", - __func__, strerror(errno)); - continue; - } - if (!(desc->status & VIRTIO_CONFIG_S_DRIVER_OK)) { - err = wait_for_card_driver(mic, - mic->mic_net.virtio_net_fd, - VIRTIO_ID_NET); - if (err) { - mpsslog("%s %s %d Exiting...\n", - mic->name, __func__, __LINE__); - break; - } - } - /* - * Check if there is data to be read from TUN and write to - * virtio net fd if there is. - */ - if (net_poll[NET_FD_TUN].revents & POLLIN) { - copy.iov = iov0; - len = readv(net_poll[NET_FD_TUN].fd, - copy.iov, copy.iovcnt); - if (len > 0) { - struct virtio_net_hdr *hdr - = (struct virtio_net_hdr *)vnet_hdr[0]; - - /* Disable checksums on the card since we are on - a reliable PCIe link */ - hdr->flags |= VIRTIO_NET_HDR_F_DATA_VALID; -#ifdef DEBUG - mpsslog("%s %s %d hdr->flags 0x%x ", mic->name, - __func__, __LINE__, hdr->flags); - mpsslog("copy.out_len %d hdr->gso_type 0x%x\n", - copy.out_len, hdr->gso_type); -#endif -#ifdef DEBUG - disp_iovec(mic, ©, __func__, __LINE__); - mpsslog("%s %s %d read from tap 0x%lx\n", - mic->name, __func__, __LINE__, - len); -#endif - spin_for_descriptors(mic, &tx_vr); - txrx_prepare(VIRTIO_ID_NET, 1, &tx_vr, ©, - len); - - err = mic_virtio_copy(mic, - mic->mic_net.virtio_net_fd, &tx_vr, - ©); - if (err < 0) { - mpsslog("%s %s %d mic_virtio_copy %s\n", - mic->name, __func__, __LINE__, - strerror(errno)); - } - if (!err) - verify_out_len(mic, ©); -#ifdef DEBUG - disp_iovec(mic, ©, __func__, __LINE__); - mpsslog("%s %s %d wrote to net 0x%lx\n", - mic->name, __func__, __LINE__, - sum_iovec_len(©)); -#endif - /* Reinitialize IOV for next run */ - iov0[1].iov_len = MAX_NET_PKT_SIZE; - } else if (len < 0) { - disp_iovec(mic, ©, __func__, __LINE__); - mpsslog("%s %s %d read failed %s ", mic->name, - __func__, __LINE__, strerror(errno)); - mpsslog("cnt %d sum %zd\n", - copy.iovcnt, sum_iovec_len(©)); - } - } - - /* - * Check if there is data to be read from virtio net and - * write to TUN if there is. - */ - if (net_poll[NET_FD_VIRTIO_NET].revents & POLLIN) { - while (rx_vr.info->avail_idx != - le16toh(rx_vr.vr.avail->idx)) { - copy.iov = iov1; - txrx_prepare(VIRTIO_ID_NET, 0, &rx_vr, ©, - MAX_NET_PKT_SIZE - + sizeof(struct virtio_net_hdr)); - - err = mic_virtio_copy(mic, - mic->mic_net.virtio_net_fd, &rx_vr, - ©); - if (!err) { -#ifdef DEBUG - struct virtio_net_hdr *hdr - = (struct virtio_net_hdr *) - vnet_hdr[1]; - - mpsslog("%s %s %d hdr->flags 0x%x, ", - mic->name, __func__, __LINE__, - hdr->flags); - mpsslog("out_len %d gso_type 0x%x\n", - copy.out_len, - hdr->gso_type); -#endif - /* Set the correct output iov_len */ - iov1[1].iov_len = copy.out_len - - sizeof(struct virtio_net_hdr); - verify_out_len(mic, ©); -#ifdef DEBUG - disp_iovec(mic, ©, __func__, - __LINE__); - mpsslog("%s %s %d ", - mic->name, __func__, __LINE__); - mpsslog("read from net 0x%lx\n", - sum_iovec_len(©)); -#endif - len = writev(net_poll[NET_FD_TUN].fd, - copy.iov, copy.iovcnt); - if (len != sum_iovec_len(©)) { - mpsslog("Tun write failed %s ", - strerror(errno)); - mpsslog("len 0x%zx ", len); - mpsslog("read_len 0x%zx\n", - sum_iovec_len(©)); - } else { -#ifdef DEBUG - disp_iovec(mic, ©, __func__, - __LINE__); - mpsslog("%s %s %d ", - mic->name, __func__, - __LINE__); - mpsslog("wrote to tap 0x%lx\n", - len); -#endif - } - } else { - mpsslog("%s %s %d mic_virtio_copy %s\n", - mic->name, __func__, __LINE__, - strerror(errno)); - break; - } - } - } - if (net_poll[NET_FD_VIRTIO_NET].revents & POLLERR) - mpsslog("%s: %s: POLLERR\n", __func__, mic->name); - } -done: - pthread_exit(NULL); -} - -/* virtio_console */ -#define VIRTIO_CONSOLE_FD 0 -#define MONITOR_FD (VIRTIO_CONSOLE_FD + 1) -#define MAX_CONSOLE_FD (MONITOR_FD + 1) /* must be the last one + 1 */ -#define MAX_BUFFER_SIZE PAGE_SIZE - -static void * -virtio_console(void *arg) -{ - static __u8 vcons_buf[2][PAGE_SIZE]; - struct iovec vcons_iov[2] = { - { .iov_base = vcons_buf[0], .iov_len = sizeof(vcons_buf[0]) }, - { .iov_base = vcons_buf[1], .iov_len = sizeof(vcons_buf[1]) }, - }; - struct iovec *iov0 = &vcons_iov[0], *iov1 = &vcons_iov[1]; - struct mic_info *mic = (struct mic_info *)arg; - int err; - struct pollfd console_poll[MAX_CONSOLE_FD]; - int pty_fd; - char *pts_name; - ssize_t len; - struct mic_vring tx_vr, rx_vr; - struct mic_copy_desc copy; - struct mic_device_desc *desc; - - pty_fd = posix_openpt(O_RDWR); - if (pty_fd < 0) { - mpsslog("can't open a pseudoterminal master device: %s\n", - strerror(errno)); - goto _return; - } - pts_name = ptsname(pty_fd); - if (pts_name == NULL) { - mpsslog("can't get pts name\n"); - goto _close_pty; - } - printf("%s console message goes to %s\n", mic->name, pts_name); - mpsslog("%s console message goes to %s\n", mic->name, pts_name); - err = grantpt(pty_fd); - if (err < 0) { - mpsslog("can't grant access: %s %s\n", - pts_name, strerror(errno)); - goto _close_pty; - } - err = unlockpt(pty_fd); - if (err < 0) { - mpsslog("can't unlock a pseudoterminal: %s %s\n", - pts_name, strerror(errno)); - goto _close_pty; - } - console_poll[MONITOR_FD].fd = pty_fd; - console_poll[MONITOR_FD].events = POLLIN; - - console_poll[VIRTIO_CONSOLE_FD].fd = mic->mic_console.virtio_console_fd; - console_poll[VIRTIO_CONSOLE_FD].events = POLLIN; - - if (MAP_FAILED == init_vr(mic, mic->mic_console.virtio_console_fd, - VIRTIO_ID_CONSOLE, &tx_vr, &rx_vr, - virtcons_dev_page.dd.num_vq)) { - mpsslog("%s init_vr failed %s\n", - mic->name, strerror(errno)); - goto _close_pty; - } - - copy.iovcnt = 1; - desc = get_device_desc(mic, VIRTIO_ID_CONSOLE); - - for (;;) { - console_poll[MONITOR_FD].revents = 0; - console_poll[VIRTIO_CONSOLE_FD].revents = 0; - err = poll(console_poll, MAX_CONSOLE_FD, -1); - if (err < 0) { - mpsslog("%s %d: poll failed: %s\n", __func__, __LINE__, - strerror(errno)); - continue; - } - if (!(desc->status & VIRTIO_CONFIG_S_DRIVER_OK)) { - err = wait_for_card_driver(mic, - mic->mic_console.virtio_console_fd, - VIRTIO_ID_CONSOLE); - if (err) { - mpsslog("%s %s %d Exiting...\n", - mic->name, __func__, __LINE__); - break; - } - } - - if (console_poll[MONITOR_FD].revents & POLLIN) { - copy.iov = iov0; - len = readv(pty_fd, copy.iov, copy.iovcnt); - if (len > 0) { -#ifdef DEBUG - disp_iovec(mic, ©, __func__, __LINE__); - mpsslog("%s %s %d read from tap 0x%lx\n", - mic->name, __func__, __LINE__, - len); -#endif - spin_for_descriptors(mic, &tx_vr); - txrx_prepare(VIRTIO_ID_CONSOLE, 1, &tx_vr, - ©, len); - - err = mic_virtio_copy(mic, - mic->mic_console.virtio_console_fd, - &tx_vr, ©); - if (err < 0) { - mpsslog("%s %s %d mic_virtio_copy %s\n", - mic->name, __func__, __LINE__, - strerror(errno)); - } - if (!err) - verify_out_len(mic, ©); -#ifdef DEBUG - disp_iovec(mic, ©, __func__, __LINE__); - mpsslog("%s %s %d wrote to net 0x%lx\n", - mic->name, __func__, __LINE__, - sum_iovec_len(©)); -#endif - /* Reinitialize IOV for next run */ - iov0->iov_len = PAGE_SIZE; - } else if (len < 0) { - disp_iovec(mic, ©, __func__, __LINE__); - mpsslog("%s %s %d read failed %s ", - mic->name, __func__, __LINE__, - strerror(errno)); - mpsslog("cnt %d sum %zd\n", - copy.iovcnt, sum_iovec_len(©)); - } - } - - if (console_poll[VIRTIO_CONSOLE_FD].revents & POLLIN) { - while (rx_vr.info->avail_idx != - le16toh(rx_vr.vr.avail->idx)) { - copy.iov = iov1; - txrx_prepare(VIRTIO_ID_CONSOLE, 0, &rx_vr, - ©, PAGE_SIZE); - - err = mic_virtio_copy(mic, - mic->mic_console.virtio_console_fd, - &rx_vr, ©); - if (!err) { - /* Set the correct output iov_len */ - iov1->iov_len = copy.out_len; - verify_out_len(mic, ©); -#ifdef DEBUG - disp_iovec(mic, ©, __func__, - __LINE__); - mpsslog("%s %s %d ", - mic->name, __func__, __LINE__); - mpsslog("read from net 0x%lx\n", - sum_iovec_len(©)); -#endif - len = writev(pty_fd, - copy.iov, copy.iovcnt); - if (len != sum_iovec_len(©)) { - mpsslog("Tun write failed %s ", - strerror(errno)); - mpsslog("len 0x%zx ", len); - mpsslog("read_len 0x%zx\n", - sum_iovec_len(©)); - } else { -#ifdef DEBUG - disp_iovec(mic, ©, __func__, - __LINE__); - mpsslog("%s %s %d ", - mic->name, __func__, - __LINE__); - mpsslog("wrote to tap 0x%lx\n", - len); -#endif - } - } else { - mpsslog("%s %s %d mic_virtio_copy %s\n", - mic->name, __func__, __LINE__, - strerror(errno)); - break; - } - } - } - if (console_poll[NET_FD_VIRTIO_NET].revents & POLLERR) - mpsslog("%s: %s: POLLERR\n", __func__, mic->name); - } -_close_pty: - close(pty_fd); -_return: - pthread_exit(NULL); -} - -static void -add_virtio_device(struct mic_info *mic, struct mic_device_desc *dd) -{ - char path[PATH_MAX]; - int fd, err; - - snprintf(path, PATH_MAX, "/dev/vop_virtio%d", mic->id); - fd = open(path, O_RDWR); - if (fd < 0) { - mpsslog("Could not open %s %s\n", path, strerror(errno)); - return; - } - - err = ioctl(fd, MIC_VIRTIO_ADD_DEVICE, dd); - if (err < 0) { - mpsslog("Could not add %d %s\n", dd->type, strerror(errno)); - close(fd); - return; - } - switch (dd->type) { - case VIRTIO_ID_NET: - mic->mic_net.virtio_net_fd = fd; - mpsslog("Added VIRTIO_ID_NET for %s\n", mic->name); - break; - case VIRTIO_ID_CONSOLE: - mic->mic_console.virtio_console_fd = fd; - mpsslog("Added VIRTIO_ID_CONSOLE for %s\n", mic->name); - break; - case VIRTIO_ID_BLOCK: - mic->mic_virtblk.virtio_block_fd = fd; - mpsslog("Added VIRTIO_ID_BLOCK for %s\n", mic->name); - break; - } -} - -static bool -set_backend_file(struct mic_info *mic) -{ - FILE *config; - char buff[PATH_MAX], *line, *evv, *p; - - snprintf(buff, PATH_MAX, "%s/mpssd%03d.conf", mic_config_dir, mic->id); - config = fopen(buff, "r"); - if (config == NULL) - return false; - do { /* look for "virtblk_backend=XXXX" */ - line = fgets(buff, PATH_MAX, config); - if (line == NULL) - break; - if (*line == '#') - continue; - p = strchr(line, '\n'); - if (p) - *p = '\0'; - } while (strncmp(line, virtblk_backend, strlen(virtblk_backend)) != 0); - fclose(config); - if (line == NULL) - return false; - evv = strchr(line, '='); - if (evv == NULL) - return false; - mic->mic_virtblk.backend_file = malloc(strlen(evv) + 1); - if (mic->mic_virtblk.backend_file == NULL) { - mpsslog("%s %d can't allocate memory\n", mic->name, mic->id); - return false; - } - strcpy(mic->mic_virtblk.backend_file, evv + 1); - return true; -} - -#define SECTOR_SIZE 512 -static bool -set_backend_size(struct mic_info *mic) -{ - mic->mic_virtblk.backend_size = lseek(mic->mic_virtblk.backend, 0, - SEEK_END); - if (mic->mic_virtblk.backend_size < 0) { - mpsslog("%s: can't seek: %s\n", - mic->name, mic->mic_virtblk.backend_file); - return false; - } - virtblk_dev_page.blk_config.capacity = - mic->mic_virtblk.backend_size / SECTOR_SIZE; - if ((mic->mic_virtblk.backend_size % SECTOR_SIZE) != 0) - virtblk_dev_page.blk_config.capacity++; - - virtblk_dev_page.blk_config.capacity = - htole64(virtblk_dev_page.blk_config.capacity); - - return true; -} - -static bool -open_backend(struct mic_info *mic) -{ - if (!set_backend_file(mic)) - goto _error_exit; - mic->mic_virtblk.backend = open(mic->mic_virtblk.backend_file, O_RDWR); - if (mic->mic_virtblk.backend < 0) { - mpsslog("%s: can't open: %s\n", mic->name, - mic->mic_virtblk.backend_file); - goto _error_free; - } - if (!set_backend_size(mic)) - goto _error_close; - mic->mic_virtblk.backend_addr = mmap(NULL, - mic->mic_virtblk.backend_size, - PROT_READ|PROT_WRITE, MAP_SHARED, - mic->mic_virtblk.backend, 0L); - if (mic->mic_virtblk.backend_addr == MAP_FAILED) { - mpsslog("%s: can't map: %s %s\n", - mic->name, mic->mic_virtblk.backend_file, - strerror(errno)); - goto _error_close; - } - return true; - - _error_close: - close(mic->mic_virtblk.backend); - _error_free: - free(mic->mic_virtblk.backend_file); - _error_exit: - return false; -} - -static void -close_backend(struct mic_info *mic) -{ - munmap(mic->mic_virtblk.backend_addr, mic->mic_virtblk.backend_size); - close(mic->mic_virtblk.backend); - free(mic->mic_virtblk.backend_file); -} - -static bool -start_virtblk(struct mic_info *mic, struct mic_vring *vring) -{ - if (((unsigned long)&virtblk_dev_page.blk_config % 8) != 0) { - mpsslog("%s: blk_config is not 8 byte aligned.\n", - mic->name); - return false; - } - add_virtio_device(mic, &virtblk_dev_page.dd); - if (MAP_FAILED == init_vr(mic, mic->mic_virtblk.virtio_block_fd, - VIRTIO_ID_BLOCK, vring, NULL, - virtblk_dev_page.dd.num_vq)) { - mpsslog("%s init_vr failed %s\n", - mic->name, strerror(errno)); - return false; - } - return true; -} - -static void -stop_virtblk(struct mic_info *mic) -{ - int vr_size, ret; - - vr_size = PAGE_ALIGN(_vring_size(MIC_VRING_ENTRIES, - MIC_VIRTIO_RING_ALIGN) + - sizeof(struct _mic_vring_info)); - ret = munmap(mic->mic_virtblk.block_dp, - MIC_DEVICE_PAGE_END + vr_size * virtblk_dev_page.dd.num_vq); - if (ret < 0) - mpsslog("%s munmap errno %d\n", mic->name, errno); - close(mic->mic_virtblk.virtio_block_fd); -} - -static __u8 -header_error_check(struct vring_desc *desc) -{ - if (le32toh(desc->len) != sizeof(struct virtio_blk_outhdr)) { - mpsslog("%s() %d: length is not sizeof(virtio_blk_outhd)\n", - __func__, __LINE__); - return -EIO; - } - if (!(le16toh(desc->flags) & VRING_DESC_F_NEXT)) { - mpsslog("%s() %d: alone\n", - __func__, __LINE__); - return -EIO; - } - if (le16toh(desc->flags) & VRING_DESC_F_WRITE) { - mpsslog("%s() %d: not read\n", - __func__, __LINE__); - return -EIO; - } - return 0; -} - -static int -read_header(int fd, struct virtio_blk_outhdr *hdr, __u32 desc_idx) -{ - struct iovec iovec; - struct mic_copy_desc copy; - - iovec.iov_len = sizeof(*hdr); - iovec.iov_base = hdr; - copy.iov = &iovec; - copy.iovcnt = 1; - copy.vr_idx = 0; /* only one vring on virtio_block */ - copy.update_used = false; /* do not update used index */ - return ioctl(fd, MIC_VIRTIO_COPY_DESC, ©); -} - -static int -transfer_blocks(int fd, struct iovec *iovec, __u32 iovcnt) -{ - struct mic_copy_desc copy; - - copy.iov = iovec; - copy.iovcnt = iovcnt; - copy.vr_idx = 0; /* only one vring on virtio_block */ - copy.update_used = false; /* do not update used index */ - return ioctl(fd, MIC_VIRTIO_COPY_DESC, ©); -} - -static __u8 -status_error_check(struct vring_desc *desc) -{ - if (le32toh(desc->len) != sizeof(__u8)) { - mpsslog("%s() %d: length is not sizeof(status)\n", - __func__, __LINE__); - return -EIO; - } - return 0; -} - -static int -write_status(int fd, __u8 *status) -{ - struct iovec iovec; - struct mic_copy_desc copy; - - iovec.iov_base = status; - iovec.iov_len = sizeof(*status); - copy.iov = &iovec; - copy.iovcnt = 1; - copy.vr_idx = 0; /* only one vring on virtio_block */ - copy.update_used = true; /* Update used index */ - return ioctl(fd, MIC_VIRTIO_COPY_DESC, ©); -} - -#ifndef VIRTIO_BLK_T_GET_ID -#define VIRTIO_BLK_T_GET_ID 8 -#endif - -static void * -virtio_block(void *arg) -{ - struct mic_info *mic = (struct mic_info *)arg; - int ret; - struct pollfd block_poll; - struct mic_vring vring; - __u16 avail_idx; - __u32 desc_idx; - struct vring_desc *desc; - struct iovec *iovec, *piov; - __u8 status; - __u32 buffer_desc_idx; - struct virtio_blk_outhdr hdr; - void *fos; - - for (;;) { /* forever */ - if (!open_backend(mic)) { /* No virtblk */ - for (mic->mic_virtblk.signaled = 0; - !mic->mic_virtblk.signaled;) - sleep(1); - continue; - } - - /* backend file is specified. */ - if (!start_virtblk(mic, &vring)) - goto _close_backend; - iovec = malloc(sizeof(*iovec) * - le32toh(virtblk_dev_page.blk_config.seg_max)); - if (!iovec) { - mpsslog("%s: can't alloc iovec: %s\n", - mic->name, strerror(ENOMEM)); - goto _stop_virtblk; - } - - block_poll.fd = mic->mic_virtblk.virtio_block_fd; - block_poll.events = POLLIN; - for (mic->mic_virtblk.signaled = 0; - !mic->mic_virtblk.signaled;) { - block_poll.revents = 0; - /* timeout in 1 sec to see signaled */ - ret = poll(&block_poll, 1, 1000); - if (ret < 0) { - mpsslog("%s %d: poll failed: %s\n", - __func__, __LINE__, - strerror(errno)); - continue; - } - - if (!(block_poll.revents & POLLIN)) { -#ifdef DEBUG - mpsslog("%s %d: block_poll.revents=0x%x\n", - __func__, __LINE__, block_poll.revents); -#endif - continue; - } - - /* POLLIN */ - while (vring.info->avail_idx != - le16toh(vring.vr.avail->idx)) { - /* read header element */ - avail_idx = - vring.info->avail_idx & - (vring.vr.num - 1); - desc_idx = le16toh( - vring.vr.avail->ring[avail_idx]); - desc = &vring.vr.desc[desc_idx]; -#ifdef DEBUG - mpsslog("%s() %d: avail_idx=%d ", - __func__, __LINE__, - vring.info->avail_idx); - mpsslog("vring.vr.num=%d desc=%p\n", - vring.vr.num, desc); -#endif - status = header_error_check(desc); - ret = read_header( - mic->mic_virtblk.virtio_block_fd, - &hdr, desc_idx); - if (ret < 0) { - mpsslog("%s() %d %s: ret=%d %s\n", - __func__, __LINE__, - mic->name, ret, - strerror(errno)); - break; - } - /* buffer element */ - piov = iovec; - status = 0; - fos = mic->mic_virtblk.backend_addr + - (hdr.sector * SECTOR_SIZE); - buffer_desc_idx = next_desc(desc); - desc_idx = buffer_desc_idx; - for (desc = &vring.vr.desc[buffer_desc_idx]; - desc->flags & VRING_DESC_F_NEXT; - desc_idx = next_desc(desc), - desc = &vring.vr.desc[desc_idx]) { - piov->iov_len = desc->len; - piov->iov_base = fos; - piov++; - fos += desc->len; - } - /* Returning NULLs for VIRTIO_BLK_T_GET_ID. */ - if (hdr.type & ~(VIRTIO_BLK_T_OUT | - VIRTIO_BLK_T_GET_ID)) { - /* - VIRTIO_BLK_T_IN - does not do - anything. Probably for documenting. - VIRTIO_BLK_T_SCSI_CMD - for - virtio_scsi. - VIRTIO_BLK_T_FLUSH - turned off in - config space. - VIRTIO_BLK_T_BARRIER - defined but not - used in anywhere. - */ - mpsslog("%s() %d: type %x ", - __func__, __LINE__, - hdr.type); - mpsslog("is not supported\n"); - status = -ENOTSUP; - - } else { - ret = transfer_blocks( - mic->mic_virtblk.virtio_block_fd, - iovec, - piov - iovec); - if (ret < 0 && - status != 0) - status = ret; - } - /* write status and update used pointer */ - if (status != 0) - status = status_error_check(desc); - ret = write_status( - mic->mic_virtblk.virtio_block_fd, - &status); -#ifdef DEBUG - mpsslog("%s() %d: write status=%d on desc=%p\n", - __func__, __LINE__, - status, desc); -#endif - } - } - free(iovec); -_stop_virtblk: - stop_virtblk(mic); -_close_backend: - close_backend(mic); - } /* forever */ - - pthread_exit(NULL); -} - -static void -reset(struct mic_info *mic) -{ -#define RESET_TIMEOUT 120 - int i = RESET_TIMEOUT; - setsysfs(mic->name, "state", "reset"); - while (i) { - char *state; - state = readsysfs(mic->name, "state"); - if (!state) - goto retry; - mpsslog("%s: %s %d state %s\n", - mic->name, __func__, __LINE__, state); - - if (!strcmp(state, "ready")) { - free(state); - break; - } - free(state); -retry: - sleep(1); - i--; - } -} - -static int -get_mic_shutdown_status(struct mic_info *mic, char *shutdown_status) -{ - if (!strcmp(shutdown_status, "nop")) - return MIC_NOP; - if (!strcmp(shutdown_status, "crashed")) - return MIC_CRASHED; - if (!strcmp(shutdown_status, "halted")) - return MIC_HALTED; - if (!strcmp(shutdown_status, "poweroff")) - return MIC_POWER_OFF; - if (!strcmp(shutdown_status, "restart")) - return MIC_RESTART; - mpsslog("%s: BUG invalid status %s\n", mic->name, shutdown_status); - /* Invalid state */ - assert(0); -}; - -static int get_mic_state(struct mic_info *mic) -{ - char *state = NULL; - enum mic_states mic_state; - - while (!state) { - state = readsysfs(mic->name, "state"); - sleep(1); - } - mpsslog("%s: %s %d state %s\n", - mic->name, __func__, __LINE__, state); - - if (!strcmp(state, "ready")) { - mic_state = MIC_READY; - } else if (!strcmp(state, "booting")) { - mic_state = MIC_BOOTING; - } else if (!strcmp(state, "online")) { - mic_state = MIC_ONLINE; - } else if (!strcmp(state, "shutting_down")) { - mic_state = MIC_SHUTTING_DOWN; - } else if (!strcmp(state, "reset_failed")) { - mic_state = MIC_RESET_FAILED; - } else if (!strcmp(state, "resetting")) { - mic_state = MIC_RESETTING; - } else { - mpsslog("%s: BUG invalid state %s\n", mic->name, state); - assert(0); - } - - free(state); - return mic_state; -}; - -static void mic_handle_shutdown(struct mic_info *mic) -{ -#define SHUTDOWN_TIMEOUT 60 - int i = SHUTDOWN_TIMEOUT; - char *shutdown_status; - while (i) { - shutdown_status = readsysfs(mic->name, "shutdown_status"); - if (!shutdown_status) { - sleep(1); - continue; - } - mpsslog("%s: %s %d shutdown_status %s\n", - mic->name, __func__, __LINE__, shutdown_status); - switch (get_mic_shutdown_status(mic, shutdown_status)) { - case MIC_RESTART: - mic->restart = 1; - case MIC_HALTED: - case MIC_POWER_OFF: - case MIC_CRASHED: - free(shutdown_status); - goto reset; - default: - break; - } - free(shutdown_status); - sleep(1); - i--; - } -reset: - if (!i) - mpsslog("%s: %s %d timing out waiting for shutdown_status %s\n", - mic->name, __func__, __LINE__, shutdown_status); - reset(mic); -} - -static int open_state_fd(struct mic_info *mic) -{ - char pathname[PATH_MAX]; - int fd; - - snprintf(pathname, PATH_MAX - 1, "%s/%s/%s", - MICSYSFSDIR, mic->name, "state"); - - fd = open(pathname, O_RDONLY); - if (fd < 0) - mpsslog("%s: opening file %s failed %s\n", - mic->name, pathname, strerror(errno)); - return fd; -} - -static int block_till_state_change(int fd, struct mic_info *mic) -{ - struct pollfd ufds[1]; - char value[PAGE_SIZE]; - int ret; - - ufds[0].fd = fd; - ufds[0].events = POLLERR | POLLPRI; - ret = poll(ufds, 1, -1); - if (ret < 0) { - mpsslog("%s: %s %d poll failed %s\n", - mic->name, __func__, __LINE__, strerror(errno)); - return ret; - } - - ret = lseek(fd, 0, SEEK_SET); - if (ret < 0) { - mpsslog("%s: %s %d Failed to seek to 0: %s\n", - mic->name, __func__, __LINE__, strerror(errno)); - return ret; - } - - ret = read(fd, value, sizeof(value)); - if (ret < 0) { - mpsslog("%s: %s %d Failed to read sysfs entry: %s\n", - mic->name, __func__, __LINE__, strerror(errno)); - return ret; - } - - return 0; -} - -static void * -mic_config(void *arg) -{ - struct mic_info *mic = (struct mic_info *)arg; - int fd, ret, stat = 0; - - fd = open_state_fd(mic); - if (fd < 0) { - mpsslog("%s: %s %d open state fd failed %s\n", - mic->name, __func__, __LINE__, strerror(errno)); - goto exit; - } - - do { - ret = block_till_state_change(fd, mic); - if (ret < 0) { - mpsslog("%s: %s %d block_till_state_change error %s\n", - mic->name, __func__, __LINE__, strerror(errno)); - goto close_exit; - } - - switch (get_mic_state(mic)) { - case MIC_SHUTTING_DOWN: - mic_handle_shutdown(mic); - break; - case MIC_READY: - case MIC_RESET_FAILED: - ret = kill(mic->pid, SIGTERM); - mpsslog("%s: %s %d kill pid %d ret %d\n", - mic->name, __func__, __LINE__, - mic->pid, ret); - if (!ret) { - ret = waitpid(mic->pid, &stat, - WIFSIGNALED(stat)); - mpsslog("%s: %s %d waitpid ret %d pid %d\n", - mic->name, __func__, __LINE__, - ret, mic->pid); - } - if (mic->boot_on_resume) { - setsysfs(mic->name, "state", "boot"); - mic->boot_on_resume = 0; - } - goto close_exit; - default: - break; - } - } while (1); - -close_exit: - close(fd); -exit: - init_mic(mic); - pthread_exit(NULL); -} - -static void -set_cmdline(struct mic_info *mic) -{ - char buffer[PATH_MAX]; - int len; - - len = snprintf(buffer, PATH_MAX, - "clocksource=tsc highres=off nohz=off "); - len += snprintf(buffer + len, PATH_MAX - len, - "cpufreq_on;corec6_off;pc3_off;pc6_off "); - len += snprintf(buffer + len, PATH_MAX - len, - "ifcfg=static;address,172.31.%d.1;netmask,255.255.255.0", - mic->id + 1); - - setsysfs(mic->name, "cmdline", buffer); - mpsslog("%s: Command line: \"%s\"\n", mic->name, buffer); - snprintf(buffer, PATH_MAX, "172.31.%d.1", mic->id + 1); - mpsslog("%s: IPADDR: \"%s\"\n", mic->name, buffer); -} - -static void -set_log_buf_info(struct mic_info *mic) -{ - int fd; - off_t len; - char system_map[] = "/lib/firmware/mic/System.map"; - char *map, *temp, log_buf[17] = {'\0'}; - - fd = open(system_map, O_RDONLY); - if (fd < 0) { - mpsslog("%s: Opening System.map failed: %d\n", - mic->name, errno); - return; - } - len = lseek(fd, 0, SEEK_END); - if (len < 0) { - mpsslog("%s: Reading System.map size failed: %d\n", - mic->name, errno); - close(fd); - return; - } - map = mmap(NULL, len, PROT_READ, MAP_PRIVATE, fd, 0); - if (map == MAP_FAILED) { - mpsslog("%s: mmap of System.map failed: %d\n", - mic->name, errno); - close(fd); - return; - } - temp = strstr(map, "__log_buf"); - if (!temp) { - mpsslog("%s: __log_buf not found: %d\n", mic->name, errno); - munmap(map, len); - close(fd); - return; - } - strncpy(log_buf, temp - 19, 16); - setsysfs(mic->name, "log_buf_addr", log_buf); - mpsslog("%s: log_buf_addr: %s\n", mic->name, log_buf); - temp = strstr(map, "log_buf_len"); - if (!temp) { - mpsslog("%s: log_buf_len not found: %d\n", mic->name, errno); - munmap(map, len); - close(fd); - return; - } - strncpy(log_buf, temp - 19, 16); - setsysfs(mic->name, "log_buf_len", log_buf); - mpsslog("%s: log_buf_len: %s\n", mic->name, log_buf); - munmap(map, len); - close(fd); -} - -static void -change_virtblk_backend(int x, siginfo_t *siginfo, void *p) -{ - struct mic_info *mic; - - for (mic = mic_list.next; mic != NULL; mic = mic->next) - mic->mic_virtblk.signaled = 1/* true */; -} - -static void -set_mic_boot_params(struct mic_info *mic) -{ - set_log_buf_info(mic); - set_cmdline(mic); -} - -static void * -init_mic(void *arg) -{ - struct mic_info *mic = (struct mic_info *)arg; - struct sigaction ignore = { - .sa_flags = 0, - .sa_handler = SIG_IGN - }; - struct sigaction act = { - .sa_flags = SA_SIGINFO, - .sa_sigaction = change_virtblk_backend, - }; - char buffer[PATH_MAX]; - int err, fd; - - /* - * Currently, one virtio block device is supported for each MIC card - * at a time. Any user (or test) can send a SIGUSR1 to the MIC daemon. - * The signal informs the virtio block backend about a change in the - * configuration file which specifies the virtio backend file name on - * the host. Virtio block backend then re-reads the configuration file - * and switches to the new block device. This signalling mechanism may - * not be required once multiple virtio block devices are supported by - * the MIC daemon. - */ - sigaction(SIGUSR1, &ignore, NULL); -retry: - fd = open_state_fd(mic); - if (fd < 0) { - mpsslog("%s: %s %d open state fd failed %s\n", - mic->name, __func__, __LINE__, strerror(errno)); - sleep(2); - goto retry; - } - - if (mic->restart) { - snprintf(buffer, PATH_MAX, "boot"); - setsysfs(mic->name, "state", buffer); - mpsslog("%s restarting mic %d\n", - mic->name, mic->restart); - mic->restart = 0; - } - - while (1) { - while (block_till_state_change(fd, mic)) { - mpsslog("%s: %s %d block_till_state_change error %s\n", - mic->name, __func__, __LINE__, strerror(errno)); - sleep(2); - continue; - } - - if (get_mic_state(mic) == MIC_BOOTING) - break; - } - - mic->pid = fork(); - switch (mic->pid) { - case 0: - add_virtio_device(mic, &virtcons_dev_page.dd); - add_virtio_device(mic, &virtnet_dev_page.dd); - err = pthread_create(&mic->mic_console.console_thread, NULL, - virtio_console, mic); - if (err) - mpsslog("%s virtcons pthread_create failed %s\n", - mic->name, strerror(err)); - err = pthread_create(&mic->mic_net.net_thread, NULL, - virtio_net, mic); - if (err) - mpsslog("%s virtnet pthread_create failed %s\n", - mic->name, strerror(err)); - err = pthread_create(&mic->mic_virtblk.block_thread, NULL, - virtio_block, mic); - if (err) - mpsslog("%s virtblk pthread_create failed %s\n", - mic->name, strerror(err)); - sigemptyset(&act.sa_mask); - err = sigaction(SIGUSR1, &act, NULL); - if (err) - mpsslog("%s sigaction SIGUSR1 failed %s\n", - mic->name, strerror(errno)); - while (1) - sleep(60); - case -1: - mpsslog("fork failed MIC name %s id %d errno %d\n", - mic->name, mic->id, errno); - break; - default: - err = pthread_create(&mic->config_thread, NULL, - mic_config, mic); - if (err) - mpsslog("%s mic_config pthread_create failed %s\n", - mic->name, strerror(err)); - } - - return NULL; -} - -static void -start_daemon(void) -{ - struct mic_info *mic; - int err; - - for (mic = mic_list.next; mic; mic = mic->next) { - set_mic_boot_params(mic); - err = pthread_create(&mic->init_thread, NULL, init_mic, mic); - if (err) - mpsslog("%s init_mic pthread_create failed %s\n", - mic->name, strerror(err)); - } - - while (1) - sleep(60); -} - -static int -init_mic_list(void) -{ - struct mic_info *mic = &mic_list; - struct dirent *file; - DIR *dp; - int cnt = 0; - - dp = opendir(MICSYSFSDIR); - if (!dp) - return 0; - - while ((file = readdir(dp)) != NULL) { - if (!strncmp(file->d_name, "mic", 3)) { - mic->next = calloc(1, sizeof(struct mic_info)); - if (mic->next) { - mic = mic->next; - mic->id = atoi(&file->d_name[3]); - mic->name = malloc(strlen(file->d_name) + 16); - if (mic->name) - strcpy(mic->name, file->d_name); - mpsslog("MIC name %s id %d\n", mic->name, - mic->id); - cnt++; - } - } - } - - closedir(dp); - return cnt; -} - -void -mpsslog(char *format, ...) -{ - va_list args; - char buffer[4096]; - char ts[52], *ts1; - time_t t; - - if (logfp == NULL) - return; - - va_start(args, format); - vsprintf(buffer, format, args); - va_end(args); - - time(&t); - ts1 = ctime_r(&t, ts); - ts1[strlen(ts1) - 1] = '\0'; - fprintf(logfp, "%s: %s", ts1, buffer); - - fflush(logfp); -} - -int -main(int argc, char *argv[]) -{ - int cnt; - pid_t pid; - - myname = argv[0]; - - logfp = fopen(LOGFILE_NAME, "a+"); - if (!logfp) { - fprintf(stderr, "cannot open logfile '%s'\n", LOGFILE_NAME); - exit(1); - } - pid = fork(); - switch (pid) { - case 0: - break; - case -1: - exit(2); - default: - exit(0); - } - - mpsslog("MIC Daemon start\n"); - - cnt = init_mic_list(); - if (cnt == 0) { - mpsslog("MIC module not loaded\n"); - exit(3); - } - mpsslog("MIC found %d devices\n", cnt); - - start_daemon(); - - exit(0); -} diff --git a/samples/mic/mpssd/mpssd.h b/samples/mic/mpssd/mpssd.h deleted file mode 100644 index 5f98bdafe653..000000000000 --- a/samples/mic/mpssd/mpssd.h +++ /dev/null @@ -1,89 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Intel MIC Platform Software Stack (MPSS) - * - * Copyright(c) 2013 Intel Corporation. - * - * Intel MIC User Space Tools. - */ -#ifndef _MPSSD_H_ -#define _MPSSD_H_ - -#include <stdio.h> -#include <stdlib.h> -#include <string.h> -#include <fcntl.h> -#include <unistd.h> -#include <dirent.h> -#include <libgen.h> -#include <pthread.h> -#include <stdarg.h> -#include <time.h> -#include <errno.h> -#include <sys/dir.h> -#include <sys/ioctl.h> -#include <sys/poll.h> -#include <sys/types.h> -#include <sys/socket.h> -#include <sys/stat.h> -#include <sys/mman.h> -#include <sys/utsname.h> -#include <sys/wait.h> -#include <netinet/in.h> -#include <arpa/inet.h> -#include <netdb.h> -#include <signal.h> -#include <limits.h> -#include <syslog.h> -#include <getopt.h> -#include <net/if.h> -#include <linux/if_tun.h> -#include <linux/virtio_ids.h> - -#define MICSYSFSDIR "/sys/class/mic" -#define LOGFILE_NAME "/var/log/mpssd" -#define PAGE_SIZE 4096 - -struct mic_console_info { - pthread_t console_thread; - int virtio_console_fd; - void *console_dp; -}; - -struct mic_net_info { - pthread_t net_thread; - int virtio_net_fd; - int tap_fd; - void *net_dp; -}; - -struct mic_virtblk_info { - pthread_t block_thread; - int virtio_block_fd; - void *block_dp; - volatile sig_atomic_t signaled; - char *backend_file; - int backend; - void *backend_addr; - long backend_size; -}; - -struct mic_info { - int id; - char *name; - pthread_t config_thread; - pthread_t init_thread; - pid_t pid; - struct mic_console_info mic_console; - struct mic_net_info mic_net; - struct mic_virtblk_info mic_virtblk; - int restart; - int boot_on_resume; - struct mic_info *next; -}; - -__attribute__((format(printf, 1, 2))) -void mpsslog(char *format, ...); -char *readsysfs(char *dir, char *entry); -int setsysfs(char *dir, char *entry, char *value); -#endif diff --git a/samples/mic/mpssd/sysfs.c b/samples/mic/mpssd/sysfs.c deleted file mode 100644 index 3fb08eb7ed9d..000000000000 --- a/samples/mic/mpssd/sysfs.c +++ /dev/null @@ -1,91 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Intel MIC Platform Software Stack (MPSS) - * - * Copyright(c) 2013 Intel Corporation. - * - * Intel MIC User Space Tools. - */ - -#include "mpssd.h" - -#define PAGE_SIZE 4096 - -char * -readsysfs(char *dir, char *entry) -{ - char filename[PATH_MAX]; - char value[PAGE_SIZE]; - char *string = NULL; - int fd; - int len; - - if (dir == NULL) - snprintf(filename, PATH_MAX, "%s/%s", MICSYSFSDIR, entry); - else - snprintf(filename, PATH_MAX, - "%s/%s/%s", MICSYSFSDIR, dir, entry); - - fd = open(filename, O_RDONLY); - if (fd < 0) { - mpsslog("Failed to open sysfs entry '%s': %s\n", - filename, strerror(errno)); - return NULL; - } - - len = read(fd, value, sizeof(value)); - if (len < 0) { - mpsslog("Failed to read sysfs entry '%s': %s\n", - filename, strerror(errno)); - goto readsys_ret; - } - if (len == 0) - goto readsys_ret; - - value[len - 1] = '\0'; - - string = malloc(strlen(value) + 1); - if (string) - strcpy(string, value); - -readsys_ret: - close(fd); - return string; -} - -int -setsysfs(char *dir, char *entry, char *value) -{ - char filename[PATH_MAX]; - char *oldvalue; - int fd, ret = 0; - - if (dir == NULL) - snprintf(filename, PATH_MAX, "%s/%s", MICSYSFSDIR, entry); - else - snprintf(filename, PATH_MAX, "%s/%s/%s", - MICSYSFSDIR, dir, entry); - - oldvalue = readsysfs(dir, entry); - - fd = open(filename, O_RDWR); - if (fd < 0) { - ret = errno; - mpsslog("Failed to open sysfs entry '%s': %s\n", - filename, strerror(errno)); - goto done; - } - - if (!oldvalue || strcmp(value, oldvalue)) { - if (write(fd, value, strlen(value)) < 0) { - ret = errno; - mpsslog("Failed to write new sysfs entry '%s': %s\n", - filename, strerror(errno)); - } - } - close(fd); -done: - if (oldvalue) - free(oldvalue); - return ret; -} diff --git a/samples/qmi/qmi_sample_client.c b/samples/qmi/qmi_sample_client.c index c9e7276c3d83..78fcedbd25e2 100644 --- a/samples/qmi/qmi_sample_client.c +++ b/samples/qmi/qmi_sample_client.c @@ -429,7 +429,7 @@ static const struct file_operations data_fops = { .write = data_write, }; -static struct qmi_msg_handler qmi_sample_handlers[] = { +static const struct qmi_msg_handler qmi_sample_handlers[] = { { .type = QMI_RESPONSE, .msg_id = TEST_PING_REQ_MSG_ID_V01, @@ -571,7 +571,7 @@ static void qmi_sample_del_server(struct qmi_handle *qmi, static struct qmi_handle lookup_client; -static struct qmi_ops lookup_ops = { +static const struct qmi_ops lookup_ops = { .new_server = qmi_sample_new_server, .del_server = qmi_sample_del_server, }; |