samples/bpf: Add simple non-portable kprobe filter example

tracex1_kern.c - C program compiled into BPF.

It attaches to kprobe:netif_receive_skb()

When skb->dev->name == "lo", it prints sample debug message into
trace_pipe via bpf_trace_printk() helper function.

tracex1_user.c - corresponding user space component that:
  - loads BPF program via bpf() syscall
  - opens kprobes:netif_receive_skb event via perf_event_open()
    syscall
  - attaches the program to event via ioctl(event_fd,
    PERF_EVENT_IOC_SET_BPF, prog_fd);
  - prints from trace_pipe

Note, this BPF program is non-portable. It must be recompiled
with current kernel headers. kprobe is not a stable ABI and
BPF+kprobe scripts may no longer be meaningful when kernel
internals change.

No matter in what way the kernel changes, neither the kprobe,
nor the BPF program can ever crash or corrupt the kernel,
assuming the kprobes, perf and BPF subsystem has no bugs.

The verifier will detect that the program is using
bpf_trace_printk() and the kernel will print 'this is a DEBUG
kernel' warning banner, which means that bpf_trace_printk()
should be used for debugging of the BPF program only.

Usage:
$ sudo tracex1
            ping-19826 [000] d.s2 63103.382648: : skb ffff880466b1ca00 len 84
            ping-19826 [000] d.s2 63103.382684: : skb ffff880466b1d300 len 84

            ping-19826 [000] d.s2 63104.382533: : skb ffff880466b1ca00 len 84
            ping-19826 [000] d.s2 63104.382594: : skb ffff880466b1d300 len 84

Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: David S. Miller <davem@davemloft.net>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1427312966-8434-7-git-send-email-ast@plumgrid.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

10 files changed, 224 insertions, 12 deletions

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index b5b3600..51f6f01 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -6,23 +6,27 @@ hostprogs-y := test_verifier test_maps
 hostprogs-y += sock_example
 hostprogs-y += sockex1
 hostprogs-y += sockex2
+hostprogs-y += tracex1
 
 test_verifier-objs := test_verifier.o libbpf.o
 test_maps-objs := test_maps.o libbpf.o
 sock_example-objs := sock_example.o libbpf.o
 sockex1-objs := bpf_load.o libbpf.o sockex1_user.o
 sockex2-objs := bpf_load.o libbpf.o sockex2_user.o
+tracex1-objs := bpf_load.o libbpf.o tracex1_user.o
 
 # Tell kbuild to always build the programs
 always := $(hostprogs-y)
 always += sockex1_kern.o
 always += sockex2_kern.o
+always += tracex1_kern.o
 
 HOSTCFLAGS += -I$(objtree)/usr/include
 
 HOSTCFLAGS_bpf_load.o += -I$(objtree)/usr/include -Wno-unused-variable
 HOSTLOADLIBES_sockex1 += -lelf
 HOSTLOADLIBES_sockex2 += -lelf
+HOSTLOADLIBES_tracex1 += -lelf
 
 # point this to your LLVM backend with bpf support
 LLC=$(srctree)/tools/bpf/llvm/bld/Debug+Asserts/bin/llc
diff --git a/samples/bpf/bpf_helpers.h b/samples/bpf/bpf_helpers.h
index ca03331..1c872bc 100644
--- a/samples/bpf/bpf_helpers.h
+++ b/samples/bpf/bpf_helpers.h
@@ -15,6 +15,12 @@ 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 int (*bpf_probe_read)(void *dst, int size, void *unsafe_ptr) =
+	(void *) BPF_FUNC_probe_read;
+static unsigned long long (*bpf_ktime_get_ns)(void) =
+	(void *) BPF_FUNC_ktime_get_ns;
+static int (*bpf_trace_printk)(const char *fmt, int fmt_size, ...) =
+	(void *) BPF_FUNC_trace_printk;
 
 /* llvm builtin functions that eBPF C program may use to
  * emit BPF_LD_ABS and BPF_LD_IND instructions
diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c
index 1831d23..38dac5a 100644
--- a/samples/bpf/bpf_load.c
+++ b/samples/bpf/bpf_load.c
@@ -8,29 +8,70 @@
 #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 <sys/syscall.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <poll.h>
 #include "libbpf.h"
 #include "bpf_helpers.h"
 #include "bpf_load.h"
 
+#define DEBUGFS "/sys/kernel/debug/tracing/"
+
 static char license[128];
+static int kern_version;
 static bool processed_sec[128];
 int map_fd[MAX_MAPS];
 int prog_fd[MAX_PROGS];
+int event_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 */
+	bool is_kprobe = strncmp(event, "kprobe/", 7) == 0;
+	bool is_kretprobe = strncmp(event, "kretprobe/", 10) == 0;
+	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 {
+		printf("Unknown event '%s'\n", event);
 		return -1;
+	}
+
+	if (is_kprobe || is_kretprobe) {
+		if (is_kprobe)
+			event += 7;
+		else
+			event += 10;
+
+		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;
+		}
+	}
 
-	fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER,
-			   prog, size, license);
+	fd = bpf_prog_load(prog_type, prog, size, license, kern_version);
 
 	if (fd < 0) {
 		printf("bpf_prog_load() err=%d\n%s", errno, bpf_log_buf);
@@ -39,6 +80,41 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
 
 	prog_fd[prog_cnt++] = fd;
 
+	if (is_socket)
+		return 0;
+
+	strcpy(buf, DEBUGFS);
+	strcat(buf, "events/kprobes/");
+	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 = 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;
+	ioctl(efd, PERF_EVENT_IOC_ENABLE, 0);
+	ioctl(efd, PERF_EVENT_IOC_SET_BPF, fd);
+
 	return 0;
 }
 
@@ -135,6 +211,9 @@ int load_bpf_file(char *path)
 	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++) {
 
@@ -149,6 +228,14 @@ int load_bpf_file(char *path)
 		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) {
 			processed_sec[i] = true;
 			if (load_maps(data->d_buf, data->d_size))
@@ -178,7 +265,8 @@ int load_bpf_file(char *path)
 			if (parse_relo_and_apply(data, symbols, &shdr, insns))
 				continue;
 
-			if (memcmp(shname_prog, "events/", 7) == 0 ||
+			if (memcmp(shname_prog, "kprobe/", 7) == 0 ||
+			    memcmp(shname_prog, "kretprobe/", 10) == 0 ||
 			    memcmp(shname_prog, "socket", 6) == 0)
 				load_and_attach(shname_prog, insns, data_prog->d_size);
 		}
@@ -193,7 +281,8 @@ int load_bpf_file(char *path)
 		if (get_sec(elf, i, &ehdr, &shname, &shdr, &data))
 			continue;
 
-		if (memcmp(shname, "events/", 7) == 0 ||
+		if (memcmp(shname, "kprobe/", 7) == 0 ||
+		    memcmp(shname, "kretprobe/", 10) == 0 ||
 		    memcmp(shname, "socket", 6) == 0)
 			load_and_attach(shname, data->d_buf, data->d_size);
 	}
@@ -201,3 +290,23 @@ int load_bpf_file(char *path)
 	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 > 0) {
+			buf[sz] = 0;
+			puts(buf);
+		}
+	}
+}
diff --git a/samples/bpf/bpf_load.h b/samples/bpf/bpf_load.h
index 27789a3..cbd7c2b 100644
--- a/samples/bpf/bpf_load.h
+++ b/samples/bpf/bpf_load.h
@@ -6,6 +6,7 @@
 
 extern int map_fd[MAX_MAPS];
 extern int prog_fd[MAX_PROGS];
+extern int event_fd[MAX_PROGS];
 
 /* parses elf file compiled by llvm .c->.o
  * . parses 'maps' section and creates maps via BPF syscall
@@ -21,4 +22,6 @@ extern int prog_fd[MAX_PROGS];
  */
 int load_bpf_file(char *path);
 
+void read_trace_pipe(void);
+
 #endif
diff --git a/samples/bpf/libbpf.c b/samples/bpf/libbpf.c
index 46d50b7..7e1efa7 100644
--- a/samples/bpf/libbpf.c
+++ b/samples/bpf/libbpf.c
@@ -81,7 +81,7 @@ char bpf_log_buf[LOG_BUF_SIZE];
 
 int bpf_prog_load(enum bpf_prog_type prog_type,
 		  const struct bpf_insn *insns, int prog_len,
-		  const char *license)
+		  const char *license, int kern_version)
 {
 	union bpf_attr attr = {
 		.prog_type = prog_type,
@@ -93,6 +93,11 @@ int bpf_prog_load(enum bpf_prog_type prog_type,
 		.log_level = 1,
 	};
 
+	/* assign one field outside of struct init to make sure any
+	 * padding is zero initialized
+	 */
+	attr.kern_version = kern_version;
+
 	bpf_log_buf[0] = 0;
 
 	return syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr));
@@ -121,3 +126,10 @@ int open_raw_sock(const char *name)
 
 	return sock;
 }
+
+int perf_event_open(struct perf_event_attr *attr, int pid, int cpu,
+		    int group_fd, unsigned long flags)
+{
+	return syscall(__NR_perf_event_open, attr, pid, cpu,
+		       group_fd, flags);
+}
diff --git a/samples/bpf/libbpf.h b/samples/bpf/libbpf.h
index 58c5fe1..ac7b096 100644
--- a/samples/bpf/libbpf.h
+++ b/samples/bpf/libbpf.h
@@ -13,7 +13,7 @@ int bpf_get_next_key(int fd, void *key, void *next_key);
 
 int bpf_prog_load(enum bpf_prog_type prog_type,
 		  const struct bpf_insn *insns, int insn_len,
-		  const char *license);
+		  const char *license, int kern_version);
 
 #define LOG_BUF_SIZE 65536
 extern char bpf_log_buf[LOG_BUF_SIZE];
@@ -182,4 +182,7 @@ extern char bpf_log_buf[LOG_BUF_SIZE];
 /* create RAW socket and bind to interface 'name' */
 int open_raw_sock(const char *name);
 
+struct perf_event_attr;
+int perf_event_open(struct perf_event_attr *attr, int pid, int cpu,
+		    int group_fd, unsigned long flags);
 #endif
diff --git a/samples/bpf/sock_example.c b/samples/bpf/sock_example.c
index c8ad040..a0ce251 100644
--- a/samples/bpf/sock_example.c
+++ b/samples/bpf/sock_example.c
@@ -56,7 +56,7 @@ static int test_sock(void)
 	};
 
 	prog_fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, prog, sizeof(prog),
-				"GPL");
+				"GPL", 0);
 	if (prog_fd < 0) {
 		printf("failed to load prog '%s'\n", strerror(errno));
 		goto cleanup;
diff --git a/samples/bpf/test_verifier.c b/samples/bpf/test_verifier.c
index b96175e..740ce97 100644
--- a/samples/bpf/test_verifier.c
+++ b/samples/bpf/test_verifier.c
@@ -689,7 +689,7 @@ static int test(void)
 
 		prog_fd = bpf_prog_load(BPF_PROG_TYPE_UNSPEC, prog,
 					prog_len * sizeof(struct bpf_insn),
-					"GPL");
+					"GPL", 0);
 
 		if (tests[i].result == ACCEPT) {
 			if (prog_fd < 0) {
diff --git a/samples/bpf/tracex1_kern.c b/samples/bpf/tracex1_kern.c
new file mode 100644
index 0000000..3162046
--- /dev/null
+++ b/samples/bpf/tracex1_kern.c
@@ -0,0 +1,50 @@
+/* Copyright (c) 2013-2015 PLUMgrid, http://plumgrid.com
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include <uapi/linux/bpf.h>
+#include <linux/version.h>
+#include "bpf_helpers.h"
+
+#define _(P) ({typeof(P) val = 0; bpf_probe_read(&val, sizeof(val), &P); val;})
+
+/* kprobe is NOT a stable ABI
+ * kernel functions can be removed, renamed or completely change semantics.
+ * Number of arguments and their positions can change, etc.
+ * In such case this bpf+kprobe example will no longer be meaningful
+ */
+SEC("kprobe/__netif_receive_skb_core")
+int bpf_prog1(struct pt_regs *ctx)
+{
+	/* attaches to kprobe netif_receive_skb,
+	 * looks for packets on loobpack device and prints them
+	 */
+	char devname[IFNAMSIZ] = {};
+	struct net_device *dev;
+	struct sk_buff *skb;
+	int len;
+
+	/* non-portable! works for the given kernel only */
+	skb = (struct sk_buff *) ctx->di;
+
+	dev = _(skb->dev);
+
+	len = _(skb->len);
+
+	bpf_probe_read(devname, sizeof(devname), dev->name);
+
+	if (devname[0] == 'l' && devname[1] == 'o') {
+		char fmt[] = "skb %p len %d\n";
+		/* using bpf_trace_printk() for DEBUG ONLY */
+		bpf_trace_printk(fmt, sizeof(fmt), skb, len);
+	}
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
+u32 _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/samples/bpf/tracex1_user.c b/samples/bpf/tracex1_user.c
new file mode 100644
index 0000000..31a4818
--- /dev/null
+++ b/samples/bpf/tracex1_user.c
@@ -0,0 +1,25 @@
+#include <stdio.h>
+#include <linux/bpf.h>
+#include <unistd.h>
+#include "libbpf.h"
+#include "bpf_load.h"
+
+int main(int ac, char **argv)
+{
+	FILE *f;
+	char filename[256];
+
+	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+
+	if (load_bpf_file(filename)) {
+		printf("%s", bpf_log_buf);
+		return 1;
+	}
+
+	f = popen("taskset 1 ping -c5 localhost", "r");
+	(void) f;
+
+	read_trace_pipe();
+
+	return 0;
+}