diff options
Diffstat (limited to 'samples/bpf')
-rw-r--r-- | samples/bpf/Makefile | 17 | ||||
-rw-r--r-- | samples/bpf/bpf_helpers.h | 26 | ||||
-rw-r--r-- | samples/bpf/bpf_load.c | 26 | ||||
-rw-r--r-- | samples/bpf/map_perf_test_user.c | 1 | ||||
-rw-r--r-- | samples/bpf/offwaketime_kern.c | 26 | ||||
-rw-r--r-- | samples/bpf/spintest_kern.c | 2 | ||||
-rw-r--r-- | samples/bpf/test_overhead_kprobe_kern.c | 41 | ||||
-rw-r--r-- | samples/bpf/test_overhead_tp_kern.c | 36 | ||||
-rw-r--r-- | samples/bpf/test_overhead_user.c | 162 | ||||
-rw-r--r-- | samples/bpf/tracex2_kern.c | 4 | ||||
-rw-r--r-- | samples/bpf/tracex4_kern.c | 2 |
11 files changed, 321 insertions, 22 deletions
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index 502c9fc8db85..744dd7a16144 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -19,6 +19,7 @@ hostprogs-y += lathist hostprogs-y += offwaketime hostprogs-y += spintest hostprogs-y += map_perf_test +hostprogs-y += test_overhead test_verifier-objs := test_verifier.o libbpf.o test_maps-objs := test_maps.o libbpf.o @@ -38,6 +39,7 @@ lathist-objs := bpf_load.o libbpf.o lathist_user.o offwaketime-objs := bpf_load.o libbpf.o offwaketime_user.o spintest-objs := bpf_load.o libbpf.o spintest_user.o map_perf_test-objs := bpf_load.o libbpf.o map_perf_test_user.o +test_overhead-objs := bpf_load.o libbpf.o test_overhead_user.o # Tell kbuild to always build the programs always := $(hostprogs-y) @@ -56,6 +58,8 @@ always += lathist_kern.o always += offwaketime_kern.o always += spintest_kern.o always += map_perf_test_kern.o +always += test_overhead_tp_kern.o +always += test_overhead_kprobe_kern.o HOSTCFLAGS += -I$(objtree)/usr/include @@ -75,17 +79,12 @@ HOSTLOADLIBES_lathist += -lelf HOSTLOADLIBES_offwaketime += -lelf HOSTLOADLIBES_spintest += -lelf HOSTLOADLIBES_map_perf_test += -lelf -lrt +HOSTLOADLIBES_test_overhead += -lelf -lrt -# point this to your LLVM backend with bpf support -LLC=$(srctree)/tools/bpf/llvm/bld/Debug+Asserts/bin/llc - -# asm/sysreg.h inline assmbly used by it is incompatible with llvm. -# But, ehere is not easy way to fix it, so just exclude it since it is +# asm/sysreg.h - inline assembly used by it is incompatible with llvm. +# But, there is no easy way to fix it, so just exclude it since it is # useless for BPF samples. $(obj)/%.o: $(src)/%.c clang $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) \ -D__KERNEL__ -D__ASM_SYSREG_H -Wno-unused-value -Wno-pointer-sign \ - -O2 -emit-llvm -c $< -o -| $(LLC) -march=bpf -filetype=obj -o $@ - clang $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) \ - -D__KERNEL__ -D__ASM_SYSREG_H -Wno-unused-value -Wno-pointer-sign \ - -O2 -emit-llvm -c $< -o -| $(LLC) -march=bpf -filetype=asm -o $@.s + -O2 -emit-llvm -c $< -o -| llc -march=bpf -filetype=obj -o $@ diff --git a/samples/bpf/bpf_helpers.h b/samples/bpf/bpf_helpers.h index 9363500131a7..7904a2a493de 100644 --- a/samples/bpf/bpf_helpers.h +++ b/samples/bpf/bpf_helpers.h @@ -82,6 +82,7 @@ static int (*bpf_l4_csum_replace)(void *ctx, int off, int from, int to, int flag #define PT_REGS_FP(x) ((x)->bp) #define PT_REGS_RC(x) ((x)->ax) #define PT_REGS_SP(x) ((x)->sp) +#define PT_REGS_IP(x) ((x)->ip) #elif defined(__s390x__) @@ -94,6 +95,7 @@ static int (*bpf_l4_csum_replace)(void *ctx, int off, int from, int to, int flag #define PT_REGS_FP(x) ((x)->gprs[11]) /* Works only with CONFIG_FRAME_POINTER */ #define PT_REGS_RC(x) ((x)->gprs[2]) #define PT_REGS_SP(x) ((x)->gprs[15]) +#define PT_REGS_IP(x) ((x)->ip) #elif defined(__aarch64__) @@ -106,6 +108,30 @@ static int (*bpf_l4_csum_replace)(void *ctx, int off, int from, int to, int flag #define PT_REGS_FP(x) ((x)->regs[29]) /* Works only with CONFIG_FRAME_POINTER */ #define PT_REGS_RC(x) ((x)->regs[0]) #define PT_REGS_SP(x) ((x)->sp) +#define PT_REGS_IP(x) ((x)->pc) + +#elif defined(__powerpc__) + +#define PT_REGS_PARM1(x) ((x)->gpr[3]) +#define PT_REGS_PARM2(x) ((x)->gpr[4]) +#define PT_REGS_PARM3(x) ((x)->gpr[5]) +#define PT_REGS_PARM4(x) ((x)->gpr[6]) +#define PT_REGS_PARM5(x) ((x)->gpr[7]) +#define PT_REGS_RC(x) ((x)->gpr[3]) +#define PT_REGS_SP(x) ((x)->sp) +#define PT_REGS_IP(x) ((x)->nip) #endif + +#ifdef __powerpc__ +#define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ (ip) = (ctx)->link; }) +#define BPF_KRETPROBE_READ_RET_IP BPF_KPROBE_READ_RET_IP +#else +#define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ \ + bpf_probe_read(&(ip), sizeof(ip), (void *)PT_REGS_RET(ctx)); }) +#define BPF_KRETPROBE_READ_RET_IP(ip, ctx) ({ \ + bpf_probe_read(&(ip), sizeof(ip), \ + (void *)(PT_REGS_FP(ctx) + sizeof(ip))); }) +#endif + #endif diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c index 58f86bd11b3d..022af71c2bb5 100644 --- a/samples/bpf/bpf_load.c +++ b/samples/bpf/bpf_load.c @@ -49,6 +49,7 @@ 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, "kprobe/", 7) == 0; bool is_kretprobe = strncmp(event, "kretprobe/", 10) == 0; + bool is_tracepoint = strncmp(event, "tracepoint/", 11) == 0; enum bpf_prog_type prog_type; char buf[256]; int fd, efd, err, id; @@ -63,6 +64,8 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size) prog_type = BPF_PROG_TYPE_SOCKET_FILTER; } else if (is_kprobe || is_kretprobe) { prog_type = BPF_PROG_TYPE_KPROBE; + } else if (is_tracepoint) { + prog_type = BPF_PROG_TYPE_TRACEPOINT; } else { printf("Unknown event '%s'\n", event); return -1; @@ -111,12 +114,23 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size) event, strerror(errno)); return -1; } - } - strcpy(buf, DEBUGFS); - strcat(buf, "events/kprobes/"); - strcat(buf, event); - strcat(buf, "/id"); + strcpy(buf, DEBUGFS); + strcat(buf, "events/kprobes/"); + strcat(buf, event); + strcat(buf, "/id"); + } else if (is_tracepoint) { + event += 11; + + if (*event == 0) { + printf("event name cannot be empty\n"); + return -1; + } + strcpy(buf, DEBUGFS); + strcat(buf, "events/"); + strcat(buf, event); + strcat(buf, "/id"); + } efd = open(buf, O_RDONLY, 0); if (efd < 0) { @@ -304,6 +318,7 @@ int load_bpf_file(char *path) if (memcmp(shname_prog, "kprobe/", 7) == 0 || memcmp(shname_prog, "kretprobe/", 10) == 0 || + memcmp(shname_prog, "tracepoint/", 11) == 0 || memcmp(shname_prog, "socket", 6) == 0) load_and_attach(shname_prog, insns, data_prog->d_size); } @@ -320,6 +335,7 @@ int load_bpf_file(char *path) if (memcmp(shname, "kprobe/", 7) == 0 || memcmp(shname, "kretprobe/", 10) == 0 || + memcmp(shname, "tracepoint/", 11) == 0 || memcmp(shname, "socket", 6) == 0) load_and_attach(shname, data->d_buf, data->d_size); } diff --git a/samples/bpf/map_perf_test_user.c b/samples/bpf/map_perf_test_user.c index 95af56ec5739..3147377e8fd3 100644 --- a/samples/bpf/map_perf_test_user.c +++ b/samples/bpf/map_perf_test_user.c @@ -17,6 +17,7 @@ #include <linux/bpf.h> #include <string.h> #include <time.h> +#include <sys/resource.h> #include "libbpf.h" #include "bpf_load.h" diff --git a/samples/bpf/offwaketime_kern.c b/samples/bpf/offwaketime_kern.c index c0aa5a9b9c48..983629a31c79 100644 --- a/samples/bpf/offwaketime_kern.c +++ b/samples/bpf/offwaketime_kern.c @@ -73,7 +73,7 @@ int waker(struct pt_regs *ctx) return 0; } -static inline int update_counts(struct pt_regs *ctx, u32 pid, u64 delta) +static inline int update_counts(void *ctx, u32 pid, u64 delta) { struct key_t key = {}; struct wokeby_t *woke; @@ -100,15 +100,33 @@ static inline int update_counts(struct pt_regs *ctx, u32 pid, u64 delta) return 0; } +#if 1 +/* taken from /sys/kernel/debug/tracing/events/sched/sched_switch/format */ +struct sched_switch_args { + unsigned long long pad; + char prev_comm[16]; + int prev_pid; + int prev_prio; + long long prev_state; + char next_comm[16]; + int next_pid; + int next_prio; +}; +SEC("tracepoint/sched/sched_switch") +int oncpu(struct sched_switch_args *ctx) +{ + /* record previous thread sleep time */ + u32 pid = ctx->prev_pid; +#else SEC("kprobe/finish_task_switch") int oncpu(struct pt_regs *ctx) { struct task_struct *p = (void *) PT_REGS_PARM1(ctx); + /* record previous thread sleep time */ + u32 pid = _(p->pid); +#endif u64 delta, ts, *tsp; - u32 pid; - /* record previous thread sleep time */ - pid = _(p->pid); ts = bpf_ktime_get_ns(); bpf_map_update_elem(&start, &pid, &ts, BPF_ANY); diff --git a/samples/bpf/spintest_kern.c b/samples/bpf/spintest_kern.c index 4b27619d91a4..ce0167d09cdc 100644 --- a/samples/bpf/spintest_kern.c +++ b/samples/bpf/spintest_kern.c @@ -34,7 +34,7 @@ struct bpf_map_def SEC("maps") stackmap = { #define PROG(foo) \ int foo(struct pt_regs *ctx) \ { \ - long v = ctx->ip, *val; \ + long v = PT_REGS_IP(ctx), *val; \ \ val = bpf_map_lookup_elem(&my_map, &v); \ bpf_map_update_elem(&my_map, &v, &v, BPF_ANY); \ diff --git a/samples/bpf/test_overhead_kprobe_kern.c b/samples/bpf/test_overhead_kprobe_kern.c new file mode 100644 index 000000000000..468a66a92ef9 --- /dev/null +++ b/samples/bpf/test_overhead_kprobe_kern.c @@ -0,0 +1,41 @@ +/* Copyright (c) 2016 Facebook + * + * 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/version.h> +#include <linux/ptrace.h> +#include <uapi/linux/bpf.h> +#include "bpf_helpers.h" + +#define _(P) ({typeof(P) val = 0; bpf_probe_read(&val, sizeof(val), &P); val;}) + +SEC("kprobe/__set_task_comm") +int prog(struct pt_regs *ctx) +{ + struct signal_struct *signal; + struct task_struct *tsk; + char oldcomm[16] = {}; + char newcomm[16] = {}; + u16 oom_score_adj; + u32 pid; + + tsk = (void *)PT_REGS_PARM1(ctx); + + pid = _(tsk->pid); + bpf_probe_read(oldcomm, sizeof(oldcomm), &tsk->comm); + bpf_probe_read(newcomm, sizeof(newcomm), (void *)PT_REGS_PARM2(ctx)); + signal = _(tsk->signal); + oom_score_adj = _(signal->oom_score_adj); + return 0; +} + +SEC("kprobe/urandom_read") +int prog2(struct pt_regs *ctx) +{ + return 0; +} + +char _license[] SEC("license") = "GPL"; +u32 _version SEC("version") = LINUX_VERSION_CODE; diff --git a/samples/bpf/test_overhead_tp_kern.c b/samples/bpf/test_overhead_tp_kern.c new file mode 100644 index 000000000000..38f5c0b9da9f --- /dev/null +++ b/samples/bpf/test_overhead_tp_kern.c @@ -0,0 +1,36 @@ +/* Copyright (c) 2016 Facebook + * + * 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 <uapi/linux/bpf.h> +#include "bpf_helpers.h" + +/* from /sys/kernel/debug/tracing/events/task/task_rename/format */ +struct task_rename { + __u64 pad; + __u32 pid; + char oldcomm[16]; + char newcomm[16]; + __u16 oom_score_adj; +}; +SEC("tracepoint/task/task_rename") +int prog(struct task_rename *ctx) +{ + return 0; +} + +/* from /sys/kernel/debug/tracing/events/random/urandom_read/format */ +struct urandom_read { + __u64 pad; + int got_bits; + int pool_left; + int input_left; +}; +SEC("tracepoint/random/urandom_read") +int prog2(struct urandom_read *ctx) +{ + return 0; +} +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/test_overhead_user.c b/samples/bpf/test_overhead_user.c new file mode 100644 index 000000000000..d291167fd3c7 --- /dev/null +++ b/samples/bpf/test_overhead_user.c @@ -0,0 +1,162 @@ +/* Copyright (c) 2016 Facebook + * + * 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. + */ +#define _GNU_SOURCE +#include <sched.h> +#include <stdio.h> +#include <sys/types.h> +#include <asm/unistd.h> +#include <fcntl.h> +#include <unistd.h> +#include <assert.h> +#include <sys/wait.h> +#include <stdlib.h> +#include <signal.h> +#include <linux/bpf.h> +#include <string.h> +#include <time.h> +#include <sys/resource.h> +#include "libbpf.h" +#include "bpf_load.h" + +#define MAX_CNT 1000000 + +static __u64 time_get_ns(void) +{ + struct timespec ts; + + clock_gettime(CLOCK_MONOTONIC, &ts); + return ts.tv_sec * 1000000000ull + ts.tv_nsec; +} + +static void test_task_rename(int cpu) +{ + __u64 start_time; + char buf[] = "test\n"; + int i, fd; + + fd = open("/proc/self/comm", O_WRONLY|O_TRUNC); + if (fd < 0) { + printf("couldn't open /proc\n"); + exit(1); + } + start_time = time_get_ns(); + for (i = 0; i < MAX_CNT; i++) + write(fd, buf, sizeof(buf)); + printf("task_rename:%d: %lld events per sec\n", + cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time)); + close(fd); +} + +static void test_urandom_read(int cpu) +{ + __u64 start_time; + char buf[4]; + int i, fd; + + fd = open("/dev/urandom", O_RDONLY); + if (fd < 0) { + printf("couldn't open /dev/urandom\n"); + exit(1); + } + start_time = time_get_ns(); + for (i = 0; i < MAX_CNT; i++) + read(fd, buf, sizeof(buf)); + printf("urandom_read:%d: %lld events per sec\n", + cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time)); + close(fd); +} + +static void loop(int cpu, int flags) +{ + cpu_set_t cpuset; + + CPU_ZERO(&cpuset); + CPU_SET(cpu, &cpuset); + sched_setaffinity(0, sizeof(cpuset), &cpuset); + + if (flags & 1) + test_task_rename(cpu); + if (flags & 2) + test_urandom_read(cpu); +} + +static void run_perf_test(int tasks, int flags) +{ + pid_t pid[tasks]; + int i; + + for (i = 0; i < tasks; i++) { + pid[i] = fork(); + if (pid[i] == 0) { + loop(i, flags); + exit(0); + } else if (pid[i] == -1) { + printf("couldn't spawn #%d process\n", i); + exit(1); + } + } + for (i = 0; i < tasks; i++) { + int status; + + assert(waitpid(pid[i], &status, 0) == pid[i]); + assert(status == 0); + } +} + +static void unload_progs(void) +{ + close(prog_fd[0]); + close(prog_fd[1]); + close(event_fd[0]); + close(event_fd[1]); +} + +int main(int argc, char **argv) +{ + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + char filename[256]; + int num_cpu = 8; + int test_flags = ~0; + + setrlimit(RLIMIT_MEMLOCK, &r); + + if (argc > 1) + test_flags = atoi(argv[1]) ? : test_flags; + if (argc > 2) + num_cpu = atoi(argv[2]) ? : num_cpu; + + if (test_flags & 0x3) { + printf("BASE\n"); + run_perf_test(num_cpu, test_flags); + } + + if (test_flags & 0xC) { + snprintf(filename, sizeof(filename), + "%s_kprobe_kern.o", argv[0]); + if (load_bpf_file(filename)) { + printf("%s", bpf_log_buf); + return 1; + } + printf("w/KPROBE\n"); + run_perf_test(num_cpu, test_flags >> 2); + unload_progs(); + } + + if (test_flags & 0x30) { + snprintf(filename, sizeof(filename), + "%s_tp_kern.o", argv[0]); + if (load_bpf_file(filename)) { + printf("%s", bpf_log_buf); + return 1; + } + printf("w/TRACEPOINT\n"); + run_perf_test(num_cpu, test_flags >> 4); + unload_progs(); + } + + return 0; +} diff --git a/samples/bpf/tracex2_kern.c b/samples/bpf/tracex2_kern.c index 09c1adc27d42..6d6eefd0d465 100644 --- a/samples/bpf/tracex2_kern.c +++ b/samples/bpf/tracex2_kern.c @@ -27,10 +27,10 @@ int bpf_prog2(struct pt_regs *ctx) long init_val = 1; long *value; - /* x64/s390x specific: read ip of kfree_skb caller. + /* read ip of kfree_skb caller. * non-portable version of __builtin_return_address(0) */ - bpf_probe_read(&loc, sizeof(loc), (void *)PT_REGS_RET(ctx)); + BPF_KPROBE_READ_RET_IP(loc, ctx); value = bpf_map_lookup_elem(&my_map, &loc); if (value) diff --git a/samples/bpf/tracex4_kern.c b/samples/bpf/tracex4_kern.c index ac4671420cf1..6dd8e384de96 100644 --- a/samples/bpf/tracex4_kern.c +++ b/samples/bpf/tracex4_kern.c @@ -40,7 +40,7 @@ int bpf_prog2(struct pt_regs *ctx) long ip = 0; /* get ip address of kmem_cache_alloc_node() caller */ - bpf_probe_read(&ip, sizeof(ip), (void *)(PT_REGS_FP(ctx) + sizeof(ip))); + BPF_KRETPROBE_READ_RET_IP(ip, ctx); struct pair v = { .val = bpf_ktime_get_ns(), |