Message-Id: <1409106582-10095-26-git-send-email-ast@plumgrid.com>
Date:	Tue, 26 Aug 2014 19:29:39 -0700
From:	Alexei Starovoitov <ast@...mgrid.com>
To:	"David S. Miller" <davem@...emloft.net>
Cc:	Ingo Molnar <mingo@...nel.org>,
	Linus Torvalds <torvalds@...ux-foundation.org>,
	Andy Lutomirski <luto@...capital.net>,
	Steven Rostedt <rostedt@...dmis.org>,
	Daniel Borkmann <dborkman@...hat.com>,
	Chema Gonzalez <chema@...gle.com>,
	Eric Dumazet <edumazet@...gle.com>,
	Peter Zijlstra <a.p.zijlstra@...llo.nl>,
	Brendan Gregg <brendan.d.gregg@...il.com>,
	Namhyung Kim <namhyung@...nel.org>,
	"H. Peter Anvin" <hpa@...or.com>,
	Andrew Morton <akpm@...ux-foundation.org>,
	Kees Cook <keescook@...omium.org>, linux-api@...r.kernel.org,
	netdev@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: [PATCH RFC v7 net-next 25/28] samples: bpf: elf 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 program via BPF syscall
- attaches program FD to tracepoint events

One ELF file can contain multiple BPF programs attached to multiple
tracepoint events

int load_bpf_file(char *path);

bpf_helpers.h is a set of in-kernel helper functions available to eBPF programs

Signed-off-by: Alexei Starovoitov <ast@...mgrid.com>
---
 samples/bpf/bpf_helpers.h |   27 ++++++
 samples/bpf/bpf_load.c    |  234 +++++++++++++++++++++++++++++++++++++++++++++
 samples/bpf/bpf_load.h    |   26 +++++
 3 files changed, 287 insertions(+)
 create mode 100644 samples/bpf/bpf_helpers.h
 create mode 100644 samples/bpf/bpf_load.c
 create mode 100644 samples/bpf/bpf_load.h

diff --git a/samples/bpf/bpf_helpers.h b/samples/bpf/bpf_helpers.h
new file mode 100644
index 000000000000..08752fad472d
--- /dev/null
+++ b/samples/bpf/bpf_helpers.h
@@ -0,0 +1,27 @@
+#ifndef __BPF_HELPERS_H
+#define __BPF_HELPERS_H
+
+#define SEC(NAME) __attribute__((section(NAME), used))
+
+static void *(*bpf_fetch_ptr)(void *unsafe_ptr) = (void *) BPF_FUNC_fetch_ptr;
+static unsigned long long (*bpf_fetch_u64)(void *unsafe_ptr) = (void *) BPF_FUNC_fetch_u64;
+static unsigned int (*bpf_fetch_u32)(void *unsafe_ptr) = (void *) BPF_FUNC_fetch_u32;
+static unsigned short (*bpf_fetch_u16)(void *unsafe_ptr) = (void *) BPF_FUNC_fetch_u16;
+static unsigned char (*bpf_fetch_u8)(void *unsafe_ptr) = (void *) BPF_FUNC_fetch_u8;
+static int (*bpf_printk)(const char *fmt, int fmt_size, ...) = (void *) BPF_FUNC_printk;
+static int (*bpf_memcmp)(void *unsafe_ptr, void *safe_ptr, int size) = (void *) BPF_FUNC_memcmp;
+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) = (void*) BPF_FUNC_map_update_elem;
+static int (*bpf_map_delete_elem)(void *map, void *key) = (void *) BPF_FUNC_map_delete_elem;
+static void (*bpf_dump_stack)(void) = (void *) BPF_FUNC_dump_stack;
+static unsigned long long (*bpf_ktime_get_ns)(void) = (void *) BPF_FUNC_ktime_get_ns;
+static void *(*bpf_get_current)(void) = (void *) BPF_FUNC_get_current;
+
+struct bpf_map_def {
+	int type;
+	int key_size;
+	int value_size;
+	int max_entries;
+};
+
+#endif
diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c
new file mode 100644
index 000000000000..a37a5cd25121
--- /dev/null
+++ b/samples/bpf/bpf_load.c
@@ -0,0 +1,234 @@
+#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"
+
+#define DEBUGFS "/sys/kernel/debug/tracing/"
+
+static char license[128];
+static bool processed_sec[128];
+int map_fd[MAX_MAPS];
+
+static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
+{
+	int fd, event_fd, err;
+	char fmt[32];
+	char path[256] = DEBUGFS;
+
+	fd = bpf_prog_load(BPF_PROG_TYPE_TRACING_FILTER, prog, size, license);
+
+	if (fd < 0) {
+		printf("bpf_prog_load() err=%d\n%s", errno, bpf_log_buf);
+		return fd;
+	}
+
+	snprintf(fmt, sizeof(fmt), "bpf-%d", fd);
+
+	strcat(path, event);
+	strcat(path, "/filter");
+
+	printf("writing %s -> %s\n", fmt, path);
+
+	event_fd = open(path, O_WRONLY, 0);
+	if (event_fd < 0) {
+		printf("failed to open event %s\n", event);
+		return event_fd;
+	}
+
+	err = write(event_fd, fmt, strlen(fmt));
+	(void) err;
+
+	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)
+			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;
+
+			if (0)
+				printf("relo %s into %s\n", shname, shname_prog);
+
+			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/", sizeof("events/") - 1) == 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/", sizeof("events/") - 1) == 0)
+			load_and_attach(shname, data->d_buf, data->d_size);
+	}
+
+	close(fd);
+	return 0;
+}
+
+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) {
+			buf[sz] = 0;
+			puts(buf);
+		}
+	}
+}
diff --git a/samples/bpf/bpf_load.h b/samples/bpf/bpf_load.h
new file mode 100644
index 000000000000..209190d793ff
--- /dev/null
+++ b/samples/bpf/bpf_load.h
@@ -0,0 +1,26 @@
+#ifndef __BPF_LOAD_H
+#define __BPF_LOAD_H
+
+#define MAX_MAPS 64
+
+extern int map_fd[MAX_MAPS];
+
+/* 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 program via BPF syscall
+ * . attaches program FD to tracepoint events
+ *
+ * One ELF file can contain multiple BPF programs attached to multiple
+ * tracepoint events
+ *
+ * returns zero on success
+ */
+int load_bpf_file(char *path);
+
+/* forever reads /sys/.../trace_pipe */
+void read_trace_pipe(void);
+
+#endif
-- 
1.7.9.5

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Powered by blists - more mailing lists