From: Qi Zhang <qi.z.zhang@intel.com>
To: dev@dpdk.org
Cc: magnus.karlsson@intei.com, bjorn.topel@intel.com,
Qi Zhang <qi.z.zhang@intel.com>
Subject: [dpdk-dev] [RFC 6/7] net/af_xdp: load BPF file
Date: Tue, 27 Feb 2018 17:33:05 +0800 [thread overview]
Message-ID: <20180227093306.23854-7-qi.z.zhang@intel.com> (raw)
In-Reply-To: <20180227093306.23854-1-qi.z.zhang@intel.com>
Add libbpf and libelf dependency in Makefile.
Durring initialization, bpf file "xdpsock_kern.o" will be loaded.
Then the driver will always try to link XDP fd with DRV mode first,
then SKB mode if failed in previoius.
Link will be released during dev_close.
Note: this is workaround solution, af_xdp may remove BPF dependency
in future.
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
---
drivers/net/af_xdp/Makefile | 6 +-
drivers/net/af_xdp/bpf_load.c | 798 ++++++++++++++++++++++++++++++++++++
drivers/net/af_xdp/bpf_load.h | 65 +++
drivers/net/af_xdp/libbpf.h | 199 +++++++++
drivers/net/af_xdp/rte_eth_af_xdp.c | 31 +-
mk/rte.app.mk | 2 +-
6 files changed, 1097 insertions(+), 4 deletions(-)
create mode 100644 drivers/net/af_xdp/bpf_load.c
create mode 100644 drivers/net/af_xdp/bpf_load.h
create mode 100644 drivers/net/af_xdp/libbpf.h
diff --git a/drivers/net/af_xdp/Makefile b/drivers/net/af_xdp/Makefile
index ac38e20bf..a642786de 100644
--- a/drivers/net/af_xdp/Makefile
+++ b/drivers/net/af_xdp/Makefile
@@ -42,7 +42,10 @@ EXPORT_MAP := rte_pmd_af_xdp_version.map
LIBABIVER := 1
-CFLAGS += -O3 -I/opt/af_xdp/linux_headers/include
+LINUX_HEADER_DIR := /opt/af_xdp/linux_headers/include
+TOOLS_DIR := /root/af_xdp/npg_dna-dna-linux/tools
+
+CFLAGS += -O3 -I$(LINUX_HEADER_DIR) -I$(TOOLS_DIR)/perf -I$(TOOLS_DIR)/include -Wno-error=sign-compare -Wno-error=cast-qual
CFLAGS += $(WERROR_FLAGS)
LDLIBS += -lrte_eal -lrte_mbuf -lrte_mempool -lrte_ring
LDLIBS += -lrte_ethdev -lrte_net -lrte_kvargs
@@ -52,5 +55,6 @@ LDLIBS += -lrte_bus_vdev
# all source are stored in SRCS-y
#
SRCS-$(CONFIG_RTE_LIBRTE_PMD_AF_XDP) += rte_eth_af_xdp.c
+SRCS-$(CONFIG_RTE_LIBRTE_PMD_AF_XDP) += bpf_load.c
include $(RTE_SDK)/mk/rte.lib.mk
diff --git a/drivers/net/af_xdp/bpf_load.c b/drivers/net/af_xdp/bpf_load.c
new file mode 100644
index 000000000..aa632207f
--- /dev/null
+++ b/drivers/net/af_xdp/bpf_load.c
@@ -0,0 +1,798 @@
+// 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/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 "libbpf.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 = 0;
+
+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 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_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;
+ 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_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 {
+ printf("Unknown event '%s'\n", event);
+ 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) {
+ 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_kprobe || is_kretprobe) {
+ 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);
+
+ snprintf(buf, sizeof(buf),
+ "echo '%c:%s %s' >> /sys/kernel/debug/tracing/kprobe_events",
+ is_kprobe ? 'p' : 'r', event, event);
+ err = system(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);
+ 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 a map: %d %s\n",
+ 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 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;
+
+ 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_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_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++) {
+ unsigned char *addr, *end;
+ struct bpf_map_def *def;
+ 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_map_def *)((uint8_t *)data_maps->d_buf + offset);
+ maps[i].elf_offset = offset;
+ memset(&maps[i].def, 0, sizeof(struct bpf_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 = system("echo \"\" > /sys/kernel/debug/tracing/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));
+ ret = 1;
+ 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, "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) {
+ ret = load_and_attach(shname, data->d_buf,
+ data->d_size);
+ if (ret != 0)
+ goto done;
+ }
+ }
+
+ ret = 0;
+done:
+ close(fd);
+ return ret;
+}
+
+int load_bpf_file(const 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);
+}
+
+void read_trace_pipe(void)
+{
+ int trace_fd;
+
+ trace_fd = open(DEBUGFS "trace_pipe", O_RDONLY, 0);
+ if (trace_fd < 0)
+ return;
+
+ while (1) {
+ static char buf[4096];
+ ssize_t sz;
+
+ sz = read(trace_fd, buf, sizeof(buf));
+ if (sz > 0) {
+ buf[sz] = 0;
+ puts(buf);
+ }
+ }
+}
+
+#define MAX_SYMS 300000
+static struct ksym syms[MAX_SYMS];
+static int sym_cnt;
+
+static int ksym_cmp(const void *p1, const void *p2)
+{
+ return ((struct ksym *)p1)->addr - ((struct ksym *)p2)->addr;
+}
+
+int load_kallsyms(void)
+{
+ FILE *f = fopen("/proc/kallsyms", "r");
+ char func[256], buf[256];
+ char symbol;
+ void *addr;
+ int i = 0;
+
+ if (!f)
+ return -ENOENT;
+
+ while (!feof(f)) {
+ if (!fgets(buf, sizeof(buf), f))
+ break;
+ if (sscanf(buf, "%p %c %s", &addr, &symbol, func) != 3)
+ break;
+ if (!addr)
+ continue;
+ syms[i].addr = (long) addr;
+ syms[i].name = strdup(func);
+ i++;
+ }
+ sym_cnt = i;
+ qsort(syms, sym_cnt, sizeof(struct ksym), ksym_cmp);
+ return 0;
+}
+
+struct ksym *ksym_search(long key)
+{
+ int start = 0, end = sym_cnt;
+ int result;
+
+ while (start < end) {
+ size_t mid = start + (end - start) / 2;
+
+ result = key - syms[mid].addr;
+ if (result < 0)
+ end = mid;
+ else if (result > 0)
+ start = mid + 1;
+ else
+ return &syms[mid];
+ }
+
+ if (start >= 1 && syms[start - 1].addr < key &&
+ key < syms[start].addr)
+ /* valid ksym */
+ return &syms[start - 1];
+
+ /* out of range. return _stext */
+ return &syms[0];
+}
+
+int set_link_xdp_fd(int ifindex, int fd, __u32 flags)
+{
+ struct sockaddr_nl sa;
+ int sock, seq = 0, len, ret = -1;
+ char buf[4096];
+ struct nlattr *nla, *nla_xdp;
+ struct {
+ struct nlmsghdr nh;
+ struct ifinfomsg ifinfo;
+ char attrbuf[64];
+ } req;
+ struct nlmsghdr *nh;
+ struct nlmsgerr *err;
+
+ memset(&sa, 0, sizeof(sa));
+ sa.nl_family = AF_NETLINK;
+
+ sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
+ if (sock < 0) {
+ printf("open netlink socket: %s\n", strerror(errno));
+ return -1;
+ }
+
+ if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) {
+ printf("bind to netlink: %s\n", strerror(errno));
+ goto cleanup;
+ }
+
+ memset(&req, 0, sizeof(req));
+ req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg));
+ req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
+ req.nh.nlmsg_type = RTM_SETLINK;
+ req.nh.nlmsg_pid = 0;
+ req.nh.nlmsg_seq = ++seq;
+ req.ifinfo.ifi_family = AF_UNSPEC;
+ req.ifinfo.ifi_index = ifindex;
+
+ /* started nested attribute for XDP */
+ nla = (struct nlattr *)(((char *)&req)
+ + NLMSG_ALIGN(req.nh.nlmsg_len));
+ nla->nla_type = NLA_F_NESTED | 43/*IFLA_XDP*/;
+ nla->nla_len = NLA_HDRLEN;
+
+ /* add XDP fd */
+ nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
+ nla_xdp->nla_type = 1/*IFLA_XDP_FD*/;
+ nla_xdp->nla_len = NLA_HDRLEN + sizeof(int);
+ memcpy((char *)nla_xdp + NLA_HDRLEN, &fd, sizeof(fd));
+ nla->nla_len += nla_xdp->nla_len;
+
+ /* if user passed in any flags, add those too */
+ if (flags) {
+ nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
+ nla_xdp->nla_type = 3/*IFLA_XDP_FLAGS*/;
+ nla_xdp->nla_len = NLA_HDRLEN + sizeof(flags);
+ memcpy((char *)nla_xdp + NLA_HDRLEN, &flags, sizeof(flags));
+ nla->nla_len += nla_xdp->nla_len;
+ }
+
+ req.nh.nlmsg_len += NLA_ALIGN(nla->nla_len);
+
+ if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) {
+ printf("send to netlink: %s\n", strerror(errno));
+ goto cleanup;
+ }
+
+ len = recv(sock, buf, sizeof(buf), 0);
+ if (len < 0) {
+ printf("recv from netlink: %s\n", strerror(errno));
+ goto cleanup;
+ }
+
+ for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, len);
+ nh = NLMSG_NEXT(nh, len)) {
+ if (nh->nlmsg_pid != getpid()) {
+ printf("Wrong pid %d, expected %d\n",
+ nh->nlmsg_pid, getpid());
+ goto cleanup;
+ }
+ if (nh->nlmsg_seq != seq) {
+ printf("Wrong seq %d, expected %d\n",
+ nh->nlmsg_seq, seq);
+ goto cleanup;
+ }
+ switch (nh->nlmsg_type) {
+ case NLMSG_ERROR:
+ err = (struct nlmsgerr *)NLMSG_DATA(nh);
+ if (!err->error)
+ continue;
+ printf("nlmsg error %s\n", strerror(-err->error));
+ goto cleanup;
+ case NLMSG_DONE:
+ break;
+ }
+ }
+
+ ret = 0;
+
+cleanup:
+ close(sock);
+ return ret;
+}
diff --git a/drivers/net/af_xdp/bpf_load.h b/drivers/net/af_xdp/bpf_load.h
new file mode 100644
index 000000000..5450e8b19
--- /dev/null
+++ b/drivers/net/af_xdp/bpf_load.h
@@ -0,0 +1,65 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __BPF_LOAD_H
+#define __BPF_LOAD_H
+
+#include "libbpf.h"
+
+#define MAX_MAPS 32
+#define MAX_PROGS 32
+
+struct bpf_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_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(const char *path);
+int load_bpf_file_fixup_map(const char *path, fixup_map_cb fixup_map);
+
+void read_trace_pipe(void);
+struct ksym {
+ long addr;
+ char *name;
+};
+
+int load_kallsyms(void);
+struct ksym *ksym_search(long key);
+int set_link_xdp_fd(int ifindex, int fd, __u32 flags);
+#endif
diff --git a/drivers/net/af_xdp/libbpf.h b/drivers/net/af_xdp/libbpf.h
new file mode 100644
index 000000000..18bfee5aa
--- /dev/null
+++ b/drivers/net/af_xdp/libbpf.h
@@ -0,0 +1,199 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* eBPF mini library */
+#ifndef __LIBBPF_H
+#define __LIBBPF_H
+
+#include <bpf/bpf.h>
+
+struct bpf_insn;
+
+/* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */
+
+#define BPF_ALU64_REG(OP, DST, SRC) \
+ ((struct bpf_insn) { \
+ .code = BPF_ALU64 | BPF_OP(OP) | BPF_X, \
+ .dst_reg = DST, \
+ .src_reg = SRC, \
+ .off = 0, \
+ .imm = 0 })
+
+#define BPF_ALU32_REG(OP, DST, SRC) \
+ ((struct bpf_insn) { \
+ .code = BPF_ALU | BPF_OP(OP) | BPF_X, \
+ .dst_reg = DST, \
+ .src_reg = SRC, \
+ .off = 0, \
+ .imm = 0 })
+
+/* ALU ops on immediates, bpf_add|sub|...: dst_reg += imm32 */
+
+#define BPF_ALU64_IMM(OP, DST, IMM) \
+ ((struct bpf_insn) { \
+ .code = BPF_ALU64 | BPF_OP(OP) | BPF_K, \
+ .dst_reg = DST, \
+ .src_reg = 0, \
+ .off = 0, \
+ .imm = IMM })
+
+#define BPF_ALU32_IMM(OP, DST, IMM) \
+ ((struct bpf_insn) { \
+ .code = BPF_ALU | BPF_OP(OP) | BPF_K, \
+ .dst_reg = DST, \
+ .src_reg = 0, \
+ .off = 0, \
+ .imm = IMM })
+
+/* Short form of mov, dst_reg = src_reg */
+
+#define BPF_MOV64_REG(DST, SRC) \
+ ((struct bpf_insn) { \
+ .code = BPF_ALU64 | BPF_MOV | BPF_X, \
+ .dst_reg = DST, \
+ .src_reg = SRC, \
+ .off = 0, \
+ .imm = 0 })
+
+#define BPF_MOV32_REG(DST, SRC) \
+ ((struct bpf_insn) { \
+ .code = BPF_ALU | BPF_MOV | BPF_X, \
+ .dst_reg = DST, \
+ .src_reg = SRC, \
+ .off = 0, \
+ .imm = 0 })
+
+/* Short form of mov, dst_reg = imm32 */
+
+#define BPF_MOV64_IMM(DST, IMM) \
+ ((struct bpf_insn) { \
+ .code = BPF_ALU64 | BPF_MOV | BPF_K, \
+ .dst_reg = DST, \
+ .src_reg = 0, \
+ .off = 0, \
+ .imm = IMM })
+
+#define BPF_MOV32_IMM(DST, IMM) \
+ ((struct bpf_insn) { \
+ .code = BPF_ALU | BPF_MOV | BPF_K, \
+ .dst_reg = DST, \
+ .src_reg = 0, \
+ .off = 0, \
+ .imm = IMM })
+
+/* BPF_LD_IMM64 macro encodes single 'load 64-bit immediate' insn */
+#define BPF_LD_IMM64(DST, IMM) \
+ BPF_LD_IMM64_RAW(DST, 0, IMM)
+
+#define BPF_LD_IMM64_RAW(DST, SRC, IMM) \
+ ((struct bpf_insn) { \
+ .code = BPF_LD | BPF_DW | BPF_IMM, \
+ .dst_reg = DST, \
+ .src_reg = SRC, \
+ .off = 0, \
+ .imm = (__u32) (IMM) }), \
+ ((struct bpf_insn) { \
+ .code = 0, /* zero is reserved opcode */ \
+ .dst_reg = 0, \
+ .src_reg = 0, \
+ .off = 0, \
+ .imm = ((__u64) (IMM)) >> 32 })
+
+#ifndef BPF_PSEUDO_MAP_FD
+# define BPF_PSEUDO_MAP_FD 1
+#endif
+
+/* pseudo BPF_LD_IMM64 insn used to refer to process-local map_fd */
+#define BPF_LD_MAP_FD(DST, MAP_FD) \
+ BPF_LD_IMM64_RAW(DST, BPF_PSEUDO_MAP_FD, MAP_FD)
+
+
+/* Direct packet access, R0 = *(uint *) (skb->data + imm32) */
+
+#define BPF_LD_ABS(SIZE, IMM) \
+ ((struct bpf_insn) { \
+ .code = BPF_LD | BPF_SIZE(SIZE) | BPF_ABS, \
+ .dst_reg = 0, \
+ .src_reg = 0, \
+ .off = 0, \
+ .imm = IMM })
+
+/* Memory load, dst_reg = *(uint *) (src_reg + off16) */
+
+#define BPF_LDX_MEM(SIZE, DST, SRC, OFF) \
+ ((struct bpf_insn) { \
+ .code = BPF_LDX | BPF_SIZE(SIZE) | BPF_MEM, \
+ .dst_reg = DST, \
+ .src_reg = SRC, \
+ .off = OFF, \
+ .imm = 0 })
+
+/* Memory store, *(uint *) (dst_reg + off16) = src_reg */
+
+#define BPF_STX_MEM(SIZE, DST, SRC, OFF) \
+ ((struct bpf_insn) { \
+ .code = BPF_STX | BPF_SIZE(SIZE) | BPF_MEM, \
+ .dst_reg = DST, \
+ .src_reg = SRC, \
+ .off = OFF, \
+ .imm = 0 })
+
+/* Atomic memory add, *(uint *)(dst_reg + off16) += src_reg */
+
+#define BPF_STX_XADD(SIZE, DST, SRC, OFF) \
+ ((struct bpf_insn) { \
+ .code = BPF_STX | BPF_SIZE(SIZE) | BPF_XADD, \
+ .dst_reg = DST, \
+ .src_reg = SRC, \
+ .off = OFF, \
+ .imm = 0 })
+
+/* Memory store, *(uint *) (dst_reg + off16) = imm32 */
+
+#define BPF_ST_MEM(SIZE, DST, OFF, IMM) \
+ ((struct bpf_insn) { \
+ .code = BPF_ST | BPF_SIZE(SIZE) | BPF_MEM, \
+ .dst_reg = DST, \
+ .src_reg = 0, \
+ .off = OFF, \
+ .imm = IMM })
+
+/* Conditional jumps against registers, if (dst_reg 'op' src_reg) goto pc + off16 */
+
+#define BPF_JMP_REG(OP, DST, SRC, OFF) \
+ ((struct bpf_insn) { \
+ .code = BPF_JMP | BPF_OP(OP) | BPF_X, \
+ .dst_reg = DST, \
+ .src_reg = SRC, \
+ .off = OFF, \
+ .imm = 0 })
+
+/* Conditional jumps against immediates, if (dst_reg 'op' imm32) goto pc + off16 */
+
+#define BPF_JMP_IMM(OP, DST, IMM, OFF) \
+ ((struct bpf_insn) { \
+ .code = BPF_JMP | BPF_OP(OP) | BPF_K, \
+ .dst_reg = DST, \
+ .src_reg = 0, \
+ .off = OFF, \
+ .imm = IMM })
+
+/* Raw code statement block */
+
+#define BPF_RAW_INSN(CODE, DST, SRC, OFF, IMM) \
+ ((struct bpf_insn) { \
+ .code = CODE, \
+ .dst_reg = DST, \
+ .src_reg = SRC, \
+ .off = OFF, \
+ .imm = IMM })
+
+/* Program exit */
+
+#define BPF_EXIT_INSN() \
+ ((struct bpf_insn) { \
+ .code = BPF_JMP | BPF_EXIT, \
+ .dst_reg = 0, \
+ .src_reg = 0, \
+ .off = 0, \
+ .imm = 0 })
+
+#endif
diff --git a/drivers/net/af_xdp/rte_eth_af_xdp.c b/drivers/net/af_xdp/rte_eth_af_xdp.c
index d0939022b..903ca0d01 100644
--- a/drivers/net/af_xdp/rte_eth_af_xdp.c
+++ b/drivers/net/af_xdp/rte_eth_af_xdp.c
@@ -15,6 +15,7 @@
#include <linux/if_ether.h>
#include <linux/if_xdp.h>
+#include <linux/if_link.h>
#include <arpa/inet.h>
#include <net/if.h>
#include <sys/types.h>
@@ -24,6 +25,7 @@
#include <unistd.h>
#include <poll.h>
#include "xdpsock_queue.h"
+#include "bpf_load.h"
#ifndef SOL_XDP
#define SOL_XDP 283
@@ -85,6 +87,8 @@ struct pmd_internals {
uint16_t port_id;
uint16_t queue_idx;
int ring_size;
+
+ uint32_t xdp_flags;
};
static const char * const valid_arguments[] = {
@@ -382,8 +386,12 @@ eth_stats_reset(struct rte_eth_dev *dev)
}
static void
-eth_dev_close(struct rte_eth_dev *dev __rte_unused)
+eth_dev_close(struct rte_eth_dev *dev)
{
+ struct pmd_internals *internals = dev->data->dev_private;
+
+ if (internals->xdp_flags)
+ set_link_xdp_fd(internals->if_index, -1, internals->xdp_flags);
}
static void
@@ -745,9 +753,25 @@ init_internals(struct rte_vdev_device *dev,
if (ret)
goto error_3;
+ /* need fix: hard coded bpf file */
+ if (load_bpf_file("xdpsock_kern.o")) {
+ printf("load bpf file failed\n");
+ goto error_3;
+ }
+ RTE_ASSERT(prog_fd[0]);
+
+ if (!set_link_xdp_fd(internals->if_index, prog_fd[0],
+ XDP_FLAGS_DRV_MODE))
+ internals->xdp_flags = XDP_FLAGS_DRV_MODE;
+ else if (!set_link_xdp_fd(internals->if_index, prog_fd[0],
+ XDP_FLAGS_SKB_MODE))
+ internals->xdp_flags = XDP_FLAGS_SKB_MODE;
+ else
+ goto error_3;
+
eth_dev = rte_eth_vdev_allocate(dev, 0);
if (!eth_dev)
- goto error_3;
+ goto error_4;
rte_memcpy(data, eth_dev->data, sizeof(*data));
internals->port_id = eth_dev->data->port_id;
@@ -765,6 +789,9 @@ init_internals(struct rte_vdev_device *dev,
return 0;
+error_4:
+ set_link_xdp_fd(internals->if_index, -1, internals->xdp_flags);
+
error_3:
close(internals->sfd);
diff --git a/mk/rte.app.mk b/mk/rte.app.mk
index bc26e1457..d05e6c0e4 100644
--- a/mk/rte.app.mk
+++ b/mk/rte.app.mk
@@ -120,7 +120,7 @@ ifeq ($(CONFIG_RTE_BUILD_SHARED_LIB),n)
_LDLIBS-$(CONFIG_RTE_DRIVER_MEMPOOL_STACK) += -lrte_mempool_stack
_LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_AF_PACKET) += -lrte_pmd_af_packet
-_LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_AF_XDP) += -lrte_pmd_af_xdp
+_LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_AF_XDP) += -lrte_pmd_af_xdp -lelf -lbpf
_LDLIBS-$(CONFIG_RTE_LIBRTE_ARK_PMD) += -lrte_pmd_ark
_LDLIBS-$(CONFIG_RTE_LIBRTE_AVF_PMD) += -lrte_pmd_avf
_LDLIBS-$(CONFIG_RTE_LIBRTE_AVP_PMD) += -lrte_pmd_avp
--
2.13.6
next prev parent reply other threads:[~2018-02-27 9:33 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-02-27 9:32 [dpdk-dev] [RFC 0/7] PMD driver for AF_XDP Qi Zhang
2018-02-27 9:33 ` [dpdk-dev] [RFC 1/7] net/af_xdp: new PMD driver Qi Zhang
2018-02-28 23:40 ` Stephen Hemminger
2018-02-28 23:42 ` Stephen Hemminger
2018-03-01 1:51 ` Zhang, Qi Z
2018-02-28 23:42 ` Stephen Hemminger
2018-02-28 23:45 ` Stephen Hemminger
2018-03-01 1:59 ` Zhang, Qi Z
2018-02-27 9:33 ` [dpdk-dev] [RFC 2/7] lib/mbuf: enable parse flags when create mempool Qi Zhang
2018-02-27 9:33 ` [dpdk-dev] [RFC 3/7] lib/mempool: allow page size aligned mempool Qi Zhang
2018-02-27 9:33 ` [dpdk-dev] [RFC 4/7] net/af_xdp: use mbuf mempool for buffer management Qi Zhang
2018-03-01 2:08 ` Stephen Hemminger
2018-02-27 9:33 ` [dpdk-dev] [RFC 5/7] net/af_xdp: enable share mempool Qi Zhang
2018-02-27 9:33 ` Qi Zhang [this message]
2018-03-01 2:10 ` [dpdk-dev] [RFC 6/7] net/af_xdp: load BPF file Stephen Hemminger
2018-02-27 9:33 ` [dpdk-dev] [RFC 7/7] app/testpmd: enable parameter for mempool flags Qi Zhang
2018-03-01 2:52 ` [dpdk-dev] [RFC 0/7] PMD driver for AF_XDP Jason Wang
2018-03-01 4:18 ` Zhang, Qi Z
2018-03-01 4:20 ` Zhang, Qi Z
2018-03-01 7:46 ` Jason Wang
2018-03-01 12:56 ` Zhang, Qi Z
2018-03-01 13:18 ` Jason Wang
2018-03-02 4:05 ` Zhang, Qi Z
2018-02-27 9:35 Qi Zhang
2018-02-27 9:35 ` [dpdk-dev] [RFC 6/7] net/af_xdp: load BPF file Qi Zhang
2018-02-28 21:10 ` Stephen Hemminger
2018-02-28 21:12 ` Stephen Hemminger
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20180227093306.23854-7-qi.z.zhang@intel.com \
--to=qi.z.zhang@intel.com \
--cc=bjorn.topel@intel.com \
--cc=dev@dpdk.org \
--cc=magnus.karlsson@intei.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).