the logic of the example is similar to tracex2, but syscall 'write' statistics is capturead from kprobe placed at sys_write function instead of through syscall instrumentation. Also tracex4_kern.c has a different way of doing log2 in C. Note, unlike tracepoint and syscall programs, kprobe programs receive 'struct pt_regs' as an input. It's responsibility of the program author or higher level dynamic tracing tool to match registers to function arguments. Since pt_regs are architecture dependent, programs are also arch dependent, unlike tracepoint/syscalls programs which are universal. Usage: $ sudo tracex4 writing bpf-6 -> /sys/kernel/debug/tracing/events/kprobes/sys_write/filter 2216443+0 records in 2216442+0 records out 1134818304 bytes (1.1 GB) copied, 2.00746 s, 565 MB/s kprobe sys_write() stats byte_size : count distribution 1 -> 1 : 0 | | 2 -> 3 : 0 | | 4 -> 7 : 0 | | 8 -> 15 : 0 | | 16 -> 31 : 0 | | 32 -> 63 : 0 | | 64 -> 127 : 1 | | 128 -> 255 : 0 | | 256 -> 511 : 0 | | 512 -> 1023 : 2214734 |************************************* | Signed-off-by: Alexei Starovoitov <ast@xxxxxxxxxxxx> --- samples/bpf/Makefile | 4 +++ samples/bpf/bpf_load.c | 3 ++ samples/bpf/tracex4_kern.c | 36 +++++++++++++++++++ samples/bpf/tracex4_user.c | 83 ++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 126 insertions(+) create mode 100644 samples/bpf/tracex4_kern.c create mode 100644 samples/bpf/tracex4_user.c diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index da0efd8032ab..22c7a38f3f95 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -10,6 +10,7 @@ hostprogs-y += dropmon hostprogs-y += tracex1 hostprogs-y += tracex2 hostprogs-y += tracex3 +hostprogs-y += tracex4 dropmon-objs := dropmon.o libbpf.o test_verifier-objs := test_verifier.o libbpf.o @@ -20,6 +21,7 @@ sockex2-objs := bpf_load.o libbpf.o sockex2_user.o tracex1-objs := bpf_load.o libbpf.o tracex1_user.o tracex2-objs := bpf_load.o libbpf.o tracex2_user.o tracex3-objs := bpf_load.o libbpf.o tracex3_user.o +tracex4-objs := bpf_load.o libbpf.o tracex4_user.o # Tell kbuild to always build the programs always := $(hostprogs-y) @@ -28,6 +30,7 @@ always += sockex2_kern.o always += tracex1_kern.o always += tracex2_kern.o always += tracex3_kern.o +always += tracex4_kern.o HOSTCFLAGS += -I$(objtree)/usr/include @@ -37,6 +40,7 @@ HOSTLOADLIBES_sockex2 += -lelf HOSTLOADLIBES_tracex1 += -lelf HOSTLOADLIBES_tracex2 += -lelf HOSTLOADLIBES_tracex3 += -lelf +HOSTLOADLIBES_tracex4 += -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_load.c b/samples/bpf/bpf_load.c index 788ac51c1024..d8c5176f0564 100644 --- a/samples/bpf/bpf_load.c +++ b/samples/bpf/bpf_load.c @@ -25,6 +25,7 @@ int prog_cnt; 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, "events/kprobes/", 15) == 0; enum bpf_prog_type prog_type; char path[256] = DEBUGFS; char fmt[32]; @@ -32,6 +33,8 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size) if (is_socket) prog_type = BPF_PROG_TYPE_SOCKET_FILTER; + else if (is_kprobe) + prog_type = BPF_PROG_TYPE_KPROBE_FILTER; else prog_type = BPF_PROG_TYPE_TRACING_FILTER; diff --git a/samples/bpf/tracex4_kern.c b/samples/bpf/tracex4_kern.c new file mode 100644 index 000000000000..9646f9e43417 --- /dev/null +++ b/samples/bpf/tracex4_kern.c @@ -0,0 +1,36 @@ +#include <linux/skbuff.h> +#include <linux/netdevice.h> +#include <uapi/linux/bpf.h> +#include <trace/bpf_trace.h> +#include "bpf_helpers.h" + +static unsigned int log2l(unsigned long long n) +{ +#define S(k) if (n >= (1ull << k)) { i += k; n >>= k; } + int i = -(n == 0); + S(32); S(16); S(8); S(4); S(2); S(1); + return i; +#undef S +} + +struct bpf_map_def SEC("maps") my_hist_map = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(u32), + .value_size = sizeof(long), + .max_entries = 64, +}; + +SEC("events/kprobes/sys_write") +int bpf_prog4(struct pt_regs *regs) +{ + long write_size = regs->dx; /* $rdx contains 3rd argument to a function */ + long init_val = 1; + void *value; + u32 index = log2l(write_size); + + value = bpf_map_lookup_elem(&my_hist_map, &index); + if (value) + __sync_fetch_and_add((long *)value, 1); + return 0; +} +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/tracex4_user.c b/samples/bpf/tracex4_user.c new file mode 100644 index 000000000000..47dde2791f9e --- /dev/null +++ b/samples/bpf/tracex4_user.c @@ -0,0 +1,83 @@ +#include <stdio.h> +#include <unistd.h> +#include <stdlib.h> +#include <signal.h> +#include <linux/bpf.h> +#include "libbpf.h" +#include "bpf_load.h" + +#define MAX_INDEX 64 +#define MAX_STARS 38 + +static void stars(char *str, long val, long max, int width) +{ + int i; + + for (i = 0; i < (width * val / max) - 1 && i < width - 1; i++) + str[i] = '*'; + if (val > max) + str[i - 1] = '+'; + str[i] = '\0'; +} + +static void print_hist(int fd) +{ + int key; + long value; + long data[MAX_INDEX] = {}; + char starstr[MAX_STARS]; + int i; + int max_ind = -1; + long max_value = 0; + + for (key = 0; key < MAX_INDEX; key++) { + bpf_lookup_elem(fd, &key, &value); + data[key] = value; + if (value && key > max_ind) + max_ind = key; + if (value > max_value) + max_value = value; + } + + printf("\n kprobe sys_write() stats\n"); + printf(" byte_size : count distribution\n"); + for (i = 1; i <= max_ind + 1; i++) { + stars(starstr, data[i - 1], max_value, MAX_STARS); + printf("%8ld -> %-8ld : %-8ld |%-*s|\n", + (1l << i) >> 1, (1l << i) - 1, data[i - 1], + MAX_STARS, starstr); + } +} +static void int_exit(int sig) +{ + print_hist(map_fd[0]); + exit(0); +} + +int main(int ac, char **argv) +{ + char filename[256]; + FILE *f; + int i; + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + + signal(SIGINT, int_exit); + + i = system("echo 'p:sys_write sys_write' > /sys/kernel/debug/tracing/kprobe_events"); + (void) i; + + /* start 'dd' in the background to have plenty of 'write' syscalls */ + f = popen("dd if=/dev/zero of=/dev/null", "r"); + (void) f; + + if (load_bpf_file(filename)) { + printf("%s", bpf_log_buf); + return 1; + } + + sleep(2); + kill(0, SIGINT); /* send Ctrl-C to self and to 'dd' */ + + return 0; +} -- 1.7.9.5 -- To unsubscribe from this list: send the line "unsubscribe linux-api" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html