samples: bpf: elf_bpf file loader

simple .o parser and loader using BPF syscall.
.o is a standard ELF generated by LLVM backend

It 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.

int load_bpf_file(char *path);
populates prog_fd[] and map_fd[] with FDs received from bpf syscall

bpf_helpers.h - helper functions available to eBPF programs written in C

Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/samples/bpf/bpf_helpers.h b/samples/bpf/bpf_helpers.h
new file mode 100644 (file)
index 0000000..ca03331
--- /dev/null
+++ b/samples/bpf/bpf_helpers.h
@@ -0,0 +1,40 @@
+#ifndef __BPF_HELPERS_H
+#define __BPF_HELPERS_H
+
+/* helper macro to place programs, maps, license in
+ * different sections in elf_bpf file. Section names
+ * are interpreted by elf_bpf loader
+ */
+#define SEC(NAME) __attribute__((section(NAME), used))
+
+/* helper functions called from eBPF programs written in C */
+static void *(*bpf_map_lookup_elem)(void *map, void *key) =
+       (void *) BPF_FUNC_map_lookup_elem;
+static int (*bpf_map_update_elem)(void *map, void *key, void *value,
+                                 unsigned long long flags) =
+       (void *) BPF_FUNC_map_update_elem;
+static int (*bpf_map_delete_elem)(void *map, void *key) =
+       (void *) BPF_FUNC_map_delete_elem;
+
+/* llvm builtin functions that eBPF C program may use to
+ * emit BPF_LD_ABS and BPF_LD_IND instructions
+ */
+struct sk_buff;
+unsigned long long load_byte(void *skb,
+                            unsigned long long off) asm("llvm.bpf.load.byte");
+unsigned long long load_half(void *skb,
+                            unsigned long long off) asm("llvm.bpf.load.half");
+unsigned long long load_word(void *skb,
+                            unsigned long long off) asm("llvm.bpf.load.word");
+
+/* a helper structure used by eBPF C program
+ * to describe map attributes to elf_bpf loader
+ */
+struct bpf_map_def {
+       unsigned int type;
+       unsigned int key_size;
+       unsigned int value_size;
+       unsigned int max_entries;
+};
+
+#endif

diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c
new file mode 100644 (file)
index 0000000..1831d23
--- /dev/null
+++ b/samples/bpf/bpf_load.c
@@ -0,0 +1,203 @@
+#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 <linux/bpf.h>
+#include <linux/filter.h>
+#include "libbpf.h"
+#include "bpf_helpers.h"
+#include "bpf_load.h"
+
+static char license[128];
+static bool processed_sec[128];
+int map_fd[MAX_MAPS];
+int prog_fd[MAX_PROGS];
+int prog_cnt;
+
+static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
+{
+       int fd;
+       bool is_socket = strncmp(event, "socket", 6) == 0;
+
+       if (!is_socket)
+               /* tracing events tbd */
+               return -1;
+
+       fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER,
+                          prog, size, license);
+
+       if (fd < 0) {
+               printf("bpf_prog_load() err=%d\n%s", errno, bpf_log_buf);
+               return -1;
+       }
+
+       prog_fd[prog_cnt++] = fd;
+
+       return 0;
+}
+
+static int load_maps(struct bpf_map_def *maps, int len)
+{
+       int i;
+
+       for (i = 0; i < len / sizeof(struct bpf_map_def); i++) {
+
+               map_fd[i] = bpf_create_map(maps[i].type,
+                                          maps[i].key_size,
+                                          maps[i].value_size,
+                                          maps[i].max_entries);
+               if (map_fd[i] < 0)
+                       return 1;
+       }
+       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)
+{
+       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;
+
+               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;
+               insn[insn_idx].imm = map_fd[sym.st_value / sizeof(struct bpf_map_def)];
+       }
+
+       return 0;
+}
+
+int load_bpf_file(char *path)
+{
+       int fd, i;
+       Elf *elf;
+       GElf_Ehdr ehdr;
+       GElf_Shdr shdr, shdr_prog;
+       Elf_Data *data, *data_prog, *symbols = NULL;
+       char *shname, *shname_prog;
+
+       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;
+
+       /* 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, "maps") == 0) {
+                       processed_sec[i] = true;
+                       if (load_maps(data->d_buf, data->d_size))
+                               return 1;
+               } else if (shdr.sh_type == SHT_SYMTAB) {
+                       symbols = data;
+               }
+       }
+
+       /* load programs that need map fixup (relocations) */
+       for (i = 1; i < ehdr.e_shnum; i++) {
+
+               if (get_sec(elf, i, &ehdr, &shname, &shdr, &data))
+                       continue;
+               if (shdr.sh_type == SHT_REL) {
+                       struct bpf_insn *insns;
+
+                       if (get_sec(elf, shdr.sh_info, &ehdr, &shname_prog,
+                                   &shdr_prog, &data_prog))
+                               continue;
+
+                       insns = (struct bpf_insn *) data_prog->d_buf;
+
+                       processed_sec[shdr.sh_info] = true;
+                       processed_sec[i] = true;
+
+                       if (parse_relo_and_apply(data, symbols, &shdr, insns))
+                               continue;
+
+                       if (memcmp(shname_prog, "events/", 7) == 0 ||
+                           memcmp(shname_prog, "socket", 6) == 0)
+                               load_and_attach(shname_prog, insns, data_prog->d_size);
+               }
+       }
+
+       /* load programs that don't use 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 (memcmp(shname, "events/", 7) == 0 ||
+                   memcmp(shname, "socket", 6) == 0)
+                       load_and_attach(shname, data->d_buf, data->d_size);
+       }
+
+       close(fd);
+       return 0;
+}

diff --git a/samples/bpf/bpf_load.h b/samples/bpf/bpf_load.h
new file mode 100644 (file)
index 0000000..27789a3
--- /dev/null
+++ b/samples/bpf/bpf_load.h
@@ -0,0 +1,24 @@
+#ifndef __BPF_LOAD_H
+#define __BPF_LOAD_H
+
+#define MAX_MAPS 32
+#define MAX_PROGS 32
+
+extern int map_fd[MAX_MAPS];
+extern int prog_fd[MAX_PROGS];
+
+/* 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);
+
+#endif