linux/samples/bpf/libbpf.c

156 lines
3.4 KiB
C
Raw Normal View History

/* eBPF mini library */
#include <stdlib.h>
#include <stdio.h>
#include <linux/unistd.h>
#include <unistd.h>
#include <string.h>
#include <linux/netlink.h>
#include <linux/bpf.h>
#include <errno.h>
#include <net/ethernet.h>
#include <net/if.h>
#include <linux/if_packet.h>
#include <arpa/inet.h>
#include "libbpf.h"
static __u64 ptr_to_u64(void *ptr)
{
return (__u64) (unsigned long) ptr;
}
int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size,
int max_entries, int map_flags)
{
union bpf_attr attr = {
.map_type = map_type,
.key_size = key_size,
.value_size = value_size,
.max_entries = max_entries,
.map_flags = map_flags,
};
return syscall(__NR_bpf, BPF_MAP_CREATE, &attr, sizeof(attr));
}
int bpf_update_elem(int fd, void *key, void *value, unsigned long long flags)
{
union bpf_attr attr = {
.map_fd = fd,
.key = ptr_to_u64(key),
.value = ptr_to_u64(value),
.flags = flags,
};
return syscall(__NR_bpf, BPF_MAP_UPDATE_ELEM, &attr, sizeof(attr));
}
int bpf_lookup_elem(int fd, void *key, void *value)
{
union bpf_attr attr = {
.map_fd = fd,
.key = ptr_to_u64(key),
.value = ptr_to_u64(value),
};
return syscall(__NR_bpf, BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr));
}
int bpf_delete_elem(int fd, void *key)
{
union bpf_attr attr = {
.map_fd = fd,
.key = ptr_to_u64(key),
};
return syscall(__NR_bpf, BPF_MAP_DELETE_ELEM, &attr, sizeof(attr));
}
int bpf_get_next_key(int fd, void *key, void *next_key)
{
union bpf_attr attr = {
.map_fd = fd,
.key = ptr_to_u64(key),
.next_key = ptr_to_u64(next_key),
};
return syscall(__NR_bpf, BPF_MAP_GET_NEXT_KEY, &attr, sizeof(attr));
}
#define ROUND_UP(x, n) (((x) + (n) - 1u) & ~((n) - 1u))
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,
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>
2015-03-25 22:49:23 +03:00
const char *license, int kern_version)
{
union bpf_attr attr = {
.prog_type = prog_type,
.insns = ptr_to_u64((void *) insns),
.insn_cnt = prog_len / sizeof(struct bpf_insn),
.license = ptr_to_u64((void *) license),
.log_buf = ptr_to_u64(bpf_log_buf),
.log_size = LOG_BUF_SIZE,
.log_level = 1,
};
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>
2015-03-25 22:49:23 +03:00
/* 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));
}
bpf: add sample usages for persistent maps/progs This patch adds a couple of stand-alone examples on how BPF_OBJ_PIN and BPF_OBJ_GET commands can be used. Example with maps: # ./fds_example -F /sys/fs/bpf/m -P -m -k 1 -v 42 bpf: map fd:3 (Success) bpf: pin ret:(0,Success) bpf: fd:3 u->(1:42) ret:(0,Success) # ./fds_example -F /sys/fs/bpf/m -G -m -k 1 bpf: get fd:3 (Success) bpf: fd:3 l->(1):42 ret:(0,Success) # ./fds_example -F /sys/fs/bpf/m -G -m -k 1 -v 24 bpf: get fd:3 (Success) bpf: fd:3 u->(1:24) ret:(0,Success) # ./fds_example -F /sys/fs/bpf/m -G -m -k 1 bpf: get fd:3 (Success) bpf: fd:3 l->(1):24 ret:(0,Success) # ./fds_example -F /sys/fs/bpf/m2 -P -m bpf: map fd:3 (Success) bpf: pin ret:(0,Success) # ./fds_example -F /sys/fs/bpf/m2 -G -m -k 1 bpf: get fd:3 (Success) bpf: fd:3 l->(1):0 ret:(0,Success) # ./fds_example -F /sys/fs/bpf/m2 -G -m bpf: get fd:3 (Success) Example with progs: # ./fds_example -F /sys/fs/bpf/p -P -p bpf: prog fd:3 (Success) bpf: pin ret:(0,Success) bpf sock:4 <- fd:3 attached ret:(0,Success) # ./fds_example -F /sys/fs/bpf/p -G -p bpf: get fd:3 (Success) bpf: sock:4 <- fd:3 attached ret:(0,Success) # ./fds_example -F /sys/fs/bpf/p2 -P -p -o ./sockex1_kern.o bpf: prog fd:5 (Success) bpf: pin ret:(0,Success) bpf: sock:3 <- fd:5 attached ret:(0,Success) # ./fds_example -F /sys/fs/bpf/p2 -G -p bpf: get fd:3 (Success) bpf: sock:4 <- fd:3 attached ret:(0,Success) Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-29 16:58:10 +03:00
int bpf_obj_pin(int fd, const char *pathname)
{
union bpf_attr attr = {
.pathname = ptr_to_u64((void *)pathname),
.bpf_fd = fd,
};
return syscall(__NR_bpf, BPF_OBJ_PIN, &attr, sizeof(attr));
}
int bpf_obj_get(const char *pathname)
{
union bpf_attr attr = {
.pathname = ptr_to_u64((void *)pathname),
};
return syscall(__NR_bpf, BPF_OBJ_GET, &attr, sizeof(attr));
}
int open_raw_sock(const char *name)
{
struct sockaddr_ll sll;
int sock;
sock = socket(PF_PACKET, SOCK_RAW | SOCK_NONBLOCK | SOCK_CLOEXEC, htons(ETH_P_ALL));
if (sock < 0) {
printf("cannot create raw socket\n");
return -1;
}
memset(&sll, 0, sizeof(sll));
sll.sll_family = AF_PACKET;
sll.sll_ifindex = if_nametoindex(name);
sll.sll_protocol = htons(ETH_P_ALL);
if (bind(sock, (struct sockaddr *)&sll, sizeof(sll)) < 0) {
printf("bind to %s: %s\n", name, strerror(errno));
close(sock);
return -1;
}
return sock;
}
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>
2015-03-25 22:49:23 +03:00
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);
}