diff options
Diffstat (limited to 'samples')
32 files changed, 2003 insertions, 52 deletions
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index edd638b5825f..0bf2478cb7df 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -16,6 +16,10 @@ hostprogs-y += tracex5 hostprogs-y += tracex6 hostprogs-y += trace_output 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 @@ -32,6 +36,10 @@ tracex5-objs := bpf_load.o libbpf.o tracex5_user.o tracex6-objs := bpf_load.o libbpf.o tracex6_user.o trace_output-objs := bpf_load.o libbpf.o trace_output_user.o 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 := $(hostprogs-y) @@ -47,6 +55,12 @@ always += tracex6_kern.o always += trace_output_kern.o always += tcbpf1_kern.o always += lathist_kern.o +always += offwaketime_kern.o +always += spintest_kern.o +always += map_perf_test_kern.o +always += test_overhead_tp_kern.o +always += test_overhead_kprobe_kern.o +always += parse_varlen.o parse_simple.o parse_ldabs.o HOSTCFLAGS += -I$(objtree)/usr/include @@ -63,17 +77,49 @@ HOSTLOADLIBES_tracex5 += -lelf HOSTLOADLIBES_tracex6 += -lelf HOSTLOADLIBES_trace_output += -lelf -lrt 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 +# Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline: +# make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang +LLC ?= llc +CLANG ?= clang -# 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 +# Trick to allow make to be run from this directory +all: + $(MAKE) -C ../../ $$PWD/ + +clean: + $(MAKE) -C ../../ M=$$PWD clean + @rm -f *~ + +# Verify LLVM compiler tools are available and bpf target is supported by llc +.PHONY: verify_cmds verify_target_bpf $(CLANG) $(LLC) + +verify_cmds: $(CLANG) $(LLC) + @for TOOL in $^ ; do \ + if ! (which -- "$${TOOL}" > /dev/null 2>&1); then \ + echo "*** ERROR: Cannot find LLVM tool $${TOOL}" ;\ + exit 1; \ + else true; fi; \ + done + +verify_target_bpf: verify_cmds + @if ! (${LLC} -march=bpf -mattr=help > /dev/null 2>&1); then \ + echo "*** ERROR: LLVM (${LLC}) does not support 'bpf' target" ;\ + echo " NOTICE: LLVM version >= 3.7.1 required" ;\ + exit 2; \ + else true; fi + +$(src)/*.c: verify_target_bpf + +# 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) \ + $(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) \ -D__KERNEL__ -D__ASM_SYSREG_H -Wno-unused-value -Wno-pointer-sign \ + -Wno-compare-distinct-pointer-types \ -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 diff --git a/samples/bpf/README.rst b/samples/bpf/README.rst new file mode 100644 index 000000000000..a43eae3f0551 --- /dev/null +++ b/samples/bpf/README.rst @@ -0,0 +1,66 @@ +eBPF sample programs +==================== + +This directory contains a mini eBPF library, test stubs, verifier +test-suite and examples for using eBPF. + +Build dependencies +================== + +Compiling requires having installed: + * clang >= version 3.4.0 + * llvm >= version 3.7.1 + +Note that LLVM's tool 'llc' must support target 'bpf', list version +and supported targets with command: ``llc --version`` + +Kernel headers +-------------- + +There are usually dependencies to header files of the current kernel. +To avoid installing devel kernel headers system wide, as a normal +user, simply call:: + + make headers_install + +This will creates a local "usr/include" directory in the git/build top +level directory, that the make system automatically pickup first. + +Compiling +========= + +For building the BPF samples, issue the below command from the kernel +top level directory:: + + make samples/bpf/ + +Do notice the "/" slash after the directory name. + +It is also possible to call make from this directory. This will just +hide the the invocation of make as above with the appended "/". + +Manually compiling LLVM with 'bpf' support +------------------------------------------ + +Since version 3.7.0, LLVM adds a proper LLVM backend target for the +BPF bytecode architecture. + +By default llvm will build all non-experimental backends including bpf. +To generate a smaller llc binary one can use:: + + -DLLVM_TARGETS_TO_BUILD="BPF" + +Quick sniplet for manually compiling LLVM and clang +(build dependencies are cmake and gcc-c++):: + + $ git clone http://llvm.org/git/llvm.git + $ cd llvm/tools + $ git clone --depth 1 http://llvm.org/git/clang.git + $ cd ..; mkdir build; cd build + $ cmake .. -DLLVM_TARGETS_TO_BUILD="BPF;X86" + $ make -j $(getconf _NPROCESSORS_ONLN) + +It is also possible to point make to the newly compiled 'llc' or +'clang' command via redefining LLC or CLANG on the make command line:: + + make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang diff --git a/samples/bpf/bpf_helpers.h b/samples/bpf/bpf_helpers.h index 7ad19e1dbaf4..7904a2a493de 100644 --- a/samples/bpf/bpf_helpers.h +++ b/samples/bpf/bpf_helpers.h @@ -39,6 +39,8 @@ static int (*bpf_redirect)(int ifindex, int flags) = (void *) BPF_FUNC_redirect; static int (*bpf_perf_event_output)(void *ctx, void *map, int index, void *data, int size) = (void *) BPF_FUNC_perf_event_output; +static int (*bpf_get_stackid)(void *ctx, void *map, int flags) = + (void *) BPF_FUNC_get_stackid; /* llvm builtin functions that eBPF C program may use to * emit BPF_LD_ABS and BPF_LD_IND instructions @@ -59,6 +61,7 @@ struct bpf_map_def { unsigned int key_size; unsigned int value_size; unsigned int max_entries; + unsigned int map_flags; }; static int (*bpf_skb_store_bytes)(void *ctx, int off, void *from, int len, int flags) = @@ -79,6 +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__) @@ -91,6 +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__) @@ -103,6 +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 da86a8e0a95a..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) { @@ -157,9 +171,13 @@ static int load_maps(struct bpf_map_def *maps, int len) 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) + maps[i].max_entries, + maps[i].map_flags); + if (map_fd[i] < 0) { + printf("failed to create a map: %d %s\n", + errno, strerror(errno)); return 1; + } if (maps[i].type == BPF_MAP_TYPE_PROG_ARRAY) prog_array_fd = map_fd[i]; @@ -300,6 +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); } @@ -316,6 +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); } @@ -343,3 +363,65 @@ void read_trace_pipe(void) } } } + +#define MAX_SYMS 300000 +static struct ksym syms[MAX_SYMS]; +static int sym_cnt; + +static int ksym_cmp(const void *p1, const void *p2) +{ + return ((struct ksym *)p1)->addr - ((struct ksym *)p2)->addr; +} + +int load_kallsyms(void) +{ + FILE *f = fopen("/proc/kallsyms", "r"); + char func[256], buf[256]; + char symbol; + void *addr; + int i = 0; + + if (!f) + return -ENOENT; + + while (!feof(f)) { + if (!fgets(buf, sizeof(buf), f)) + break; + if (sscanf(buf, "%p %c %s", &addr, &symbol, func) != 3) + break; + if (!addr) + continue; + syms[i].addr = (long) addr; + syms[i].name = strdup(func); + i++; + } + sym_cnt = i; + qsort(syms, sym_cnt, sizeof(struct ksym), ksym_cmp); + return 0; +} + +struct ksym *ksym_search(long key) +{ + int start = 0, end = sym_cnt; + int result; + + while (start < end) { + size_t mid = start + (end - start) / 2; + + result = key - syms[mid].addr; + if (result < 0) + end = mid; + else if (result > 0) + start = mid + 1; + else + return &syms[mid]; + } + + if (start >= 1 && syms[start - 1].addr < key && + key < syms[start].addr) + /* valid ksym */ + return &syms[start - 1]; + + /* out of range. return _stext */ + return &syms[0]; +} diff --git a/samples/bpf/bpf_load.h b/samples/bpf/bpf_load.h index cbd7c2b532b9..dfa57fe65c8e 100644 --- a/samples/bpf/bpf_load.h +++ b/samples/bpf/bpf_load.h @@ -23,5 +23,11 @@ extern int event_fd[MAX_PROGS]; int load_bpf_file(char *path); void read_trace_pipe(void); +struct ksym { + long addr; + char *name; +}; +int load_kallsyms(void); +struct ksym *ksym_search(long key); #endif diff --git a/samples/bpf/fds_example.c b/samples/bpf/fds_example.c index e2fd16c3d0f0..625e797be6ef 100644 --- a/samples/bpf/fds_example.c +++ b/samples/bpf/fds_example.c @@ -44,7 +44,7 @@ static void usage(void) static int bpf_map_create(void) { return bpf_create_map(BPF_MAP_TYPE_ARRAY, sizeof(uint32_t), - sizeof(uint32_t), 1024); + sizeof(uint32_t), 1024, 0); } static int bpf_prog_create(const char *object) diff --git a/samples/bpf/libbpf.c b/samples/bpf/libbpf.c index 65a8d48d2799..9969e35550c3 100644 --- a/samples/bpf/libbpf.c +++ b/samples/bpf/libbpf.c @@ -19,13 +19,14 @@ static __u64 ptr_to_u64(void *ptr) } int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size, - int max_entries) + 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 + .max_entries = max_entries, + .map_flags = map_flags, }; return syscall(__NR_bpf, BPF_MAP_CREATE, &attr, sizeof(attr)); diff --git a/samples/bpf/libbpf.h b/samples/bpf/libbpf.h index 014aacf916e4..364582b77888 100644 --- a/samples/bpf/libbpf.h +++ b/samples/bpf/libbpf.h @@ -5,7 +5,7 @@ struct bpf_insn; int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size, - int max_entries); + int max_entries, int map_flags); int bpf_update_elem(int fd, void *key, void *value, unsigned long long flags); int bpf_lookup_elem(int fd, void *key, void *value); int bpf_delete_elem(int fd, void *key); diff --git a/samples/bpf/map_perf_test_kern.c b/samples/bpf/map_perf_test_kern.c new file mode 100644 index 000000000000..311538e5a701 --- /dev/null +++ b/samples/bpf/map_perf_test_kern.c @@ -0,0 +1,100 @@ +/* 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/skbuff.h> +#include <linux/netdevice.h> +#include <linux/version.h> +#include <uapi/linux/bpf.h> +#include "bpf_helpers.h" + +#define MAX_ENTRIES 1000 + +struct bpf_map_def SEC("maps") hash_map = { + .type = BPF_MAP_TYPE_HASH, + .key_size = sizeof(u32), + .value_size = sizeof(long), + .max_entries = MAX_ENTRIES, +}; + +struct bpf_map_def SEC("maps") percpu_hash_map = { + .type = BPF_MAP_TYPE_PERCPU_HASH, + .key_size = sizeof(u32), + .value_size = sizeof(long), + .max_entries = MAX_ENTRIES, +}; + +struct bpf_map_def SEC("maps") hash_map_alloc = { + .type = BPF_MAP_TYPE_HASH, + .key_size = sizeof(u32), + .value_size = sizeof(long), + .max_entries = MAX_ENTRIES, + .map_flags = BPF_F_NO_PREALLOC, +}; + +struct bpf_map_def SEC("maps") percpu_hash_map_alloc = { + .type = BPF_MAP_TYPE_PERCPU_HASH, + .key_size = sizeof(u32), + .value_size = sizeof(long), + .max_entries = MAX_ENTRIES, + .map_flags = BPF_F_NO_PREALLOC, +}; + +SEC("kprobe/sys_getuid") +int stress_hmap(struct pt_regs *ctx) +{ + u32 key = bpf_get_current_pid_tgid(); + long init_val = 1; + long *value; + + bpf_map_update_elem(&hash_map, &key, &init_val, BPF_ANY); + value = bpf_map_lookup_elem(&hash_map, &key); + if (value) + bpf_map_delete_elem(&hash_map, &key); + return 0; +} + +SEC("kprobe/sys_geteuid") +int stress_percpu_hmap(struct pt_regs *ctx) +{ + u32 key = bpf_get_current_pid_tgid(); + long init_val = 1; + long *value; + + bpf_map_update_elem(&percpu_hash_map, &key, &init_val, BPF_ANY); + value = bpf_map_lookup_elem(&percpu_hash_map, &key); + if (value) + bpf_map_delete_elem(&percpu_hash_map, &key); + return 0; +} +SEC("kprobe/sys_getgid") +int stress_hmap_alloc(struct pt_regs *ctx) +{ + u32 key = bpf_get_current_pid_tgid(); + long init_val = 1; + long *value; + + bpf_map_update_elem(&hash_map_alloc, &key, &init_val, BPF_ANY); + value = bpf_map_lookup_elem(&hash_map_alloc, &key); + if (value) + bpf_map_delete_elem(&hash_map_alloc, &key); + return 0; +} + +SEC("kprobe/sys_getegid") +int stress_percpu_hmap_alloc(struct pt_regs *ctx) +{ + u32 key = bpf_get_current_pid_tgid(); + long init_val = 1; + long *value; + + bpf_map_update_elem(&percpu_hash_map_alloc, &key, &init_val, BPF_ANY); + value = bpf_map_lookup_elem(&percpu_hash_map_alloc, &key); + if (value) + bpf_map_delete_elem(&percpu_hash_map_alloc, &key); + return 0; +} +char _license[] SEC("license") = "GPL"; +u32 _version SEC("version") = LINUX_VERSION_CODE; diff --git a/samples/bpf/map_perf_test_user.c b/samples/bpf/map_perf_test_user.c new file mode 100644 index 000000000000..3147377e8fd3 --- /dev/null +++ b/samples/bpf/map_perf_test_user.c @@ -0,0 +1,156 @@ +/* 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 <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; +} + +#define HASH_PREALLOC (1 << 0) +#define PERCPU_HASH_PREALLOC (1 << 1) +#define HASH_KMALLOC (1 << 2) +#define PERCPU_HASH_KMALLOC (1 << 3) + +static int test_flags = ~0; + +static void test_hash_prealloc(int cpu) +{ + __u64 start_time; + int i; + + start_time = time_get_ns(); + for (i = 0; i < MAX_CNT; i++) + syscall(__NR_getuid); + printf("%d:hash_map_perf pre-alloc %lld events per sec\n", + cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time)); +} + +static void test_percpu_hash_prealloc(int cpu) +{ + __u64 start_time; + int i; + + start_time = time_get_ns(); + for (i = 0; i < MAX_CNT; i++) + syscall(__NR_geteuid); + printf("%d:percpu_hash_map_perf pre-alloc %lld events per sec\n", + cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time)); +} + +static void test_hash_kmalloc(int cpu) +{ + __u64 start_time; + int i; + + start_time = time_get_ns(); + for (i = 0; i < MAX_CNT; i++) + syscall(__NR_getgid); + printf("%d:hash_map_perf kmalloc %lld events per sec\n", + cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time)); +} + +static void test_percpu_hash_kmalloc(int cpu) +{ + __u64 start_time; + int i; + + start_time = time_get_ns(); + for (i = 0; i < MAX_CNT; i++) + syscall(__NR_getegid); + printf("%d:percpu_hash_map_perf kmalloc %lld events per sec\n", + cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time)); +} + +static void loop(int cpu) +{ + cpu_set_t cpuset; + + CPU_ZERO(&cpuset); + CPU_SET(cpu, &cpuset); + sched_setaffinity(0, sizeof(cpuset), &cpuset); + + if (test_flags & HASH_PREALLOC) + test_hash_prealloc(cpu); + + if (test_flags & PERCPU_HASH_PREALLOC) + test_percpu_hash_prealloc(cpu); + + if (test_flags & HASH_KMALLOC) + test_hash_kmalloc(cpu); + + if (test_flags & PERCPU_HASH_KMALLOC) + test_percpu_hash_kmalloc(cpu); +} + +static void run_perf_test(int tasks) +{ + pid_t pid[tasks]; + int i; + + for (i = 0; i < tasks; i++) { + pid[i] = fork(); + if (pid[i] == 0) { + loop(i); + 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); + } +} + +int main(int argc, char **argv) +{ + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + char filename[256]; + int num_cpu = 8; + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[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 (load_bpf_file(filename)) { + printf("%s", bpf_log_buf); + return 1; + } + + run_perf_test(num_cpu); + + return 0; +} diff --git a/samples/bpf/offwaketime_kern.c b/samples/bpf/offwaketime_kern.c new file mode 100644 index 000000000000..e7d9a0a3d45b --- /dev/null +++ b/samples/bpf/offwaketime_kern.c @@ -0,0 +1,151 @@ +/* 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" +#include <uapi/linux/ptrace.h> +#include <uapi/linux/perf_event.h> +#include <linux/version.h> +#include <linux/sched.h> + +#define _(P) ({typeof(P) val; bpf_probe_read(&val, sizeof(val), &P); val;}) + +#define MINBLOCK_US 1 + +struct key_t { + char waker[TASK_COMM_LEN]; + char target[TASK_COMM_LEN]; + u32 wret; + u32 tret; +}; + +struct bpf_map_def SEC("maps") counts = { + .type = BPF_MAP_TYPE_HASH, + .key_size = sizeof(struct key_t), + .value_size = sizeof(u64), + .max_entries = 10000, +}; + +struct bpf_map_def SEC("maps") start = { + .type = BPF_MAP_TYPE_HASH, + .key_size = sizeof(u32), + .value_size = sizeof(u64), + .max_entries = 10000, +}; + +struct wokeby_t { + char name[TASK_COMM_LEN]; + u32 ret; +}; + +struct bpf_map_def SEC("maps") wokeby = { + .type = BPF_MAP_TYPE_HASH, + .key_size = sizeof(u32), + .value_size = sizeof(struct wokeby_t), + .max_entries = 10000, +}; + +struct bpf_map_def SEC("maps") stackmap = { + .type = BPF_MAP_TYPE_STACK_TRACE, + .key_size = sizeof(u32), + .value_size = PERF_MAX_STACK_DEPTH * sizeof(u64), + .max_entries = 10000, +}; + +#define STACKID_FLAGS (0 | BPF_F_FAST_STACK_CMP) + +SEC("kprobe/try_to_wake_up") +int waker(struct pt_regs *ctx) +{ + struct task_struct *p = (void *) PT_REGS_PARM1(ctx); + struct wokeby_t woke; + u32 pid; + + pid = _(p->pid); + + bpf_get_current_comm(&woke.name, sizeof(woke.name)); + woke.ret = bpf_get_stackid(ctx, &stackmap, STACKID_FLAGS); + + bpf_map_update_elem(&wokeby, &pid, &woke, BPF_ANY); + return 0; +} + +static inline int update_counts(void *ctx, u32 pid, u64 delta) +{ + struct wokeby_t *woke; + u64 zero = 0, *val; + struct key_t key; + + __builtin_memset(&key.waker, 0, sizeof(key.waker)); + bpf_get_current_comm(&key.target, sizeof(key.target)); + key.tret = bpf_get_stackid(ctx, &stackmap, STACKID_FLAGS); + key.wret = 0; + + woke = bpf_map_lookup_elem(&wokeby, &pid); + if (woke) { + key.wret = woke->ret; + __builtin_memcpy(&key.waker, woke->name, sizeof(key.waker)); + bpf_map_delete_elem(&wokeby, &pid); + } + + val = bpf_map_lookup_elem(&counts, &key); + if (!val) { + bpf_map_update_elem(&counts, &key, &zero, BPF_NOEXIST); + val = bpf_map_lookup_elem(&counts, &key); + if (!val) + return 0; + } + (*val) += 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; + + ts = bpf_ktime_get_ns(); + bpf_map_update_elem(&start, &pid, &ts, BPF_ANY); + + /* calculate current thread's delta time */ + pid = bpf_get_current_pid_tgid(); + tsp = bpf_map_lookup_elem(&start, &pid); + if (!tsp) + /* missed start or filtered */ + return 0; + + delta = bpf_ktime_get_ns() - *tsp; + bpf_map_delete_elem(&start, &pid); + delta = delta / 1000; + if (delta < MINBLOCK_US) + return 0; + + return update_counts(ctx, pid, delta); +} +char _license[] SEC("license") = "GPL"; +u32 _version SEC("version") = LINUX_VERSION_CODE; diff --git a/samples/bpf/offwaketime_user.c b/samples/bpf/offwaketime_user.c new file mode 100644 index 000000000000..6f002a9c24fa --- /dev/null +++ b/samples/bpf/offwaketime_user.c @@ -0,0 +1,120 @@ +/* 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 <stdio.h> +#include <unistd.h> +#include <stdlib.h> +#include <signal.h> +#include <linux/bpf.h> +#include <string.h> +#include <linux/perf_event.h> +#include <errno.h> +#include <assert.h> +#include <stdbool.h> +#include <sys/resource.h> +#include "libbpf.h" +#include "bpf_load.h" + +#define PRINT_RAW_ADDR 0 + +static void print_ksym(__u64 addr) +{ + struct ksym *sym; + + if (!addr) + return; + sym = ksym_search(addr); + if (PRINT_RAW_ADDR) + printf("%s/%llx;", sym->name, addr); + else + printf("%s;", sym->name); +} + +#define TASK_COMM_LEN 16 + +struct key_t { + char waker[TASK_COMM_LEN]; + char target[TASK_COMM_LEN]; + __u32 wret; + __u32 tret; +}; + +static void print_stack(struct key_t *key, __u64 count) +{ + __u64 ip[PERF_MAX_STACK_DEPTH] = {}; + static bool warned; + int i; + + printf("%s;", key->target); + if (bpf_lookup_elem(map_fd[3], &key->tret, ip) != 0) { + printf("---;"); + } else { + for (i = PERF_MAX_STACK_DEPTH - 1; i >= 0; i--) + print_ksym(ip[i]); + } + printf("-;"); + if (bpf_lookup_elem(map_fd[3], &key->wret, ip) != 0) { + printf("---;"); + } else { + for (i = 0; i < PERF_MAX_STACK_DEPTH; i++) + print_ksym(ip[i]); + } + printf(";%s %lld\n", key->waker, count); + + if ((key->tret == -EEXIST || key->wret == -EEXIST) && !warned) { + printf("stackmap collisions seen. Consider increasing size\n"); + warned = true; + } else if (((int)(key->tret) < 0 || (int)(key->wret) < 0)) { + printf("err stackid %d %d\n", key->tret, key->wret); + } +} + +static void print_stacks(int fd) +{ + struct key_t key = {}, next_key; + __u64 value; + + while (bpf_get_next_key(fd, &key, &next_key) == 0) { + bpf_lookup_elem(fd, &next_key, &value); + print_stack(&next_key, value); + key = next_key; + } +} + +static void int_exit(int sig) +{ + print_stacks(map_fd[0]); + exit(0); +} + +int main(int argc, char **argv) +{ + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + char filename[256]; + int delay = 1; + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + setrlimit(RLIMIT_MEMLOCK, &r); + + signal(SIGINT, int_exit); + + if (load_kallsyms()) { + printf("failed to process /proc/kallsyms\n"); + return 2; + } + + if (load_bpf_file(filename)) { + printf("%s", bpf_log_buf); + return 1; + } + + if (argc > 1) + delay = atoi(argv[1]); + sleep(delay); + print_stacks(map_fd[0]); + + return 0; +} diff --git a/samples/bpf/parse_ldabs.c b/samples/bpf/parse_ldabs.c new file mode 100644 index 000000000000..d17550198d06 --- /dev/null +++ b/samples/bpf/parse_ldabs.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/ip.h> +#include <linux/ipv6.h> +#include <linux/in.h> +#include <linux/tcp.h> +#include <linux/udp.h> +#include <uapi/linux/bpf.h> +#include "bpf_helpers.h" + +#define DEFAULT_PKTGEN_UDP_PORT 9 +#define IP_MF 0x2000 +#define IP_OFFSET 0x1FFF + +static inline int ip_is_fragment(struct __sk_buff *ctx, __u64 nhoff) +{ + return load_half(ctx, nhoff + offsetof(struct iphdr, frag_off)) + & (IP_MF | IP_OFFSET); +} + +SEC("ldabs") +int handle_ingress(struct __sk_buff *skb) +{ + __u64 troff = ETH_HLEN + sizeof(struct iphdr); + + if (load_half(skb, offsetof(struct ethhdr, h_proto)) != ETH_P_IP) + return 0; + if (load_byte(skb, ETH_HLEN + offsetof(struct iphdr, protocol)) != IPPROTO_UDP || + load_byte(skb, ETH_HLEN) != 0x45) + return 0; + if (ip_is_fragment(skb, ETH_HLEN)) + return 0; + if (load_half(skb, troff + offsetof(struct udphdr, dest)) == DEFAULT_PKTGEN_UDP_PORT) + return TC_ACT_SHOT; + return 0; +} +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/parse_simple.c b/samples/bpf/parse_simple.c new file mode 100644 index 000000000000..cf2511c33905 --- /dev/null +++ b/samples/bpf/parse_simple.c @@ -0,0 +1,48 @@ +/* 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/ip.h> +#include <linux/ipv6.h> +#include <linux/in.h> +#include <linux/tcp.h> +#include <linux/udp.h> +#include <uapi/linux/bpf.h> +#include <net/ip.h> +#include "bpf_helpers.h" + +#define DEFAULT_PKTGEN_UDP_PORT 9 + +/* copy of 'struct ethhdr' without __packed */ +struct eth_hdr { + unsigned char h_dest[ETH_ALEN]; + unsigned char h_source[ETH_ALEN]; + unsigned short h_proto; +}; + +SEC("simple") +int handle_ingress(struct __sk_buff *skb) +{ + void *data = (void *)(long)skb->data; + struct eth_hdr *eth = data; + struct iphdr *iph = data + sizeof(*eth); + struct udphdr *udp = data + sizeof(*eth) + sizeof(*iph); + void *data_end = (void *)(long)skb->data_end; + + /* single length check */ + if (data + sizeof(*eth) + sizeof(*iph) + sizeof(*udp) > data_end) + return 0; + + if (eth->h_proto != htons(ETH_P_IP)) + return 0; + if (iph->protocol != IPPROTO_UDP || iph->ihl != 5) + return 0; + if (ip_is_fragment(iph)) + return 0; + if (udp->dest == htons(DEFAULT_PKTGEN_UDP_PORT)) + return TC_ACT_SHOT; + return 0; +} +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/parse_varlen.c b/samples/bpf/parse_varlen.c new file mode 100644 index 000000000000..edab34dce79b --- /dev/null +++ b/samples/bpf/parse_varlen.c @@ -0,0 +1,153 @@ +/* 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/if_ether.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/in.h> +#include <linux/tcp.h> +#include <linux/udp.h> +#include <uapi/linux/bpf.h> +#include <net/ip.h> +#include "bpf_helpers.h" + +#define DEFAULT_PKTGEN_UDP_PORT 9 +#define DEBUG 0 + +static int tcp(void *data, uint64_t tp_off, void *data_end) +{ + struct tcphdr *tcp = data + tp_off; + + if (tcp + 1 > data_end) + return 0; + if (tcp->dest == htons(80) || tcp->source == htons(80)) + return TC_ACT_SHOT; + return 0; +} + +static int udp(void *data, uint64_t tp_off, void *data_end) +{ + struct udphdr *udp = data + tp_off; + + if (udp + 1 > data_end) + return 0; + if (udp->dest == htons(DEFAULT_PKTGEN_UDP_PORT) || + udp->source == htons(DEFAULT_PKTGEN_UDP_PORT)) { + if (DEBUG) { + char fmt[] = "udp port 9 indeed\n"; + + bpf_trace_printk(fmt, sizeof(fmt)); + } + return TC_ACT_SHOT; + } + return 0; +} + +static int parse_ipv4(void *data, uint64_t nh_off, void *data_end) +{ + struct iphdr *iph; + uint64_t ihl_len; + + iph = data + nh_off; + if (iph + 1 > data_end) + return 0; + + if (ip_is_fragment(iph)) + return 0; + ihl_len = iph->ihl * 4; + + if (iph->protocol == IPPROTO_IPIP) { + iph = data + nh_off + ihl_len; + if (iph + 1 > data_end) + return 0; + ihl_len += iph->ihl * 4; + } + + if (iph->protocol == IPPROTO_TCP) + return tcp(data, nh_off + ihl_len, data_end); + else if (iph->protocol == IPPROTO_UDP) + return udp(data, nh_off + ihl_len, data_end); + return 0; +} + +static int parse_ipv6(void *data, uint64_t nh_off, void *data_end) +{ + struct ipv6hdr *ip6h; + struct iphdr *iph; + uint64_t ihl_len = sizeof(struct ipv6hdr); + uint64_t nexthdr; + + ip6h = data + nh_off; + if (ip6h + 1 > data_end) + return 0; + + nexthdr = ip6h->nexthdr; + + if (nexthdr == IPPROTO_IPIP) { + iph = data + nh_off + ihl_len; + if (iph + 1 > data_end) + return 0; + ihl_len += iph->ihl * 4; + nexthdr = iph->protocol; + } else if (nexthdr == IPPROTO_IPV6) { + ip6h = data + nh_off + ihl_len; + if (ip6h + 1 > data_end) + return 0; + ihl_len += sizeof(struct ipv6hdr); + nexthdr = ip6h->nexthdr; + } + + if (nexthdr == IPPROTO_TCP) + return tcp(data, nh_off + ihl_len, data_end); + else if (nexthdr == IPPROTO_UDP) + return udp(data, nh_off + ihl_len, data_end); + return 0; +} + +struct vlan_hdr { + uint16_t h_vlan_TCI; + uint16_t h_vlan_encapsulated_proto; +}; + +SEC("varlen") +int handle_ingress(struct __sk_buff *skb) +{ + void *data = (void *)(long)skb->data; + struct ethhdr *eth = data; + void *data_end = (void *)(long)skb->data_end; + uint64_t h_proto, nh_off; + + nh_off = sizeof(*eth); + if (data + nh_off > data_end) + return 0; + + h_proto = eth->h_proto; + + if (h_proto == ETH_P_8021Q || h_proto == ETH_P_8021AD) { + struct vlan_hdr *vhdr; + + vhdr = data + nh_off; + nh_off += sizeof(struct vlan_hdr); + if (data + nh_off > data_end) + return 0; + h_proto = vhdr->h_vlan_encapsulated_proto; + } + if (h_proto == ETH_P_8021Q || h_proto == ETH_P_8021AD) { + struct vlan_hdr *vhdr; + + vhdr = data + nh_off; + nh_off += sizeof(struct vlan_hdr); + if (data + nh_off > data_end) + return 0; + h_proto = vhdr->h_vlan_encapsulated_proto; + } + if (h_proto == htons(ETH_P_IP)) + return parse_ipv4(data, nh_off, data_end); + else if (h_proto == htons(ETH_P_IPV6)) + return parse_ipv6(data, nh_off, data_end); + return 0; +} +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/sock_example.c b/samples/bpf/sock_example.c index a0ce251c5390..28b60baa9fa8 100644 --- a/samples/bpf/sock_example.c +++ b/samples/bpf/sock_example.c @@ -34,7 +34,7 @@ static int test_sock(void) long long value = 0, tcp_cnt, udp_cnt, icmp_cnt; map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, sizeof(key), sizeof(value), - 256); + 256, 0); if (map_fd < 0) { printf("failed to create map '%s'\n", strerror(errno)); goto cleanup; diff --git a/samples/bpf/spintest_kern.c b/samples/bpf/spintest_kern.c new file mode 100644 index 000000000000..ce0167d09cdc --- /dev/null +++ b/samples/bpf/spintest_kern.c @@ -0,0 +1,68 @@ +/* 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/skbuff.h> +#include <linux/netdevice.h> +#include <linux/version.h> +#include <uapi/linux/bpf.h> +#include <uapi/linux/perf_event.h> +#include "bpf_helpers.h" + +struct bpf_map_def SEC("maps") my_map = { + .type = BPF_MAP_TYPE_HASH, + .key_size = sizeof(long), + .value_size = sizeof(long), + .max_entries = 1024, +}; +struct bpf_map_def SEC("maps") my_map2 = { + .type = BPF_MAP_TYPE_PERCPU_HASH, + .key_size = sizeof(long), + .value_size = sizeof(long), + .max_entries = 1024, +}; + +struct bpf_map_def SEC("maps") stackmap = { + .type = BPF_MAP_TYPE_STACK_TRACE, + .key_size = sizeof(u32), + .value_size = PERF_MAX_STACK_DEPTH * sizeof(u64), + .max_entries = 10000, +}; + +#define PROG(foo) \ +int foo(struct pt_regs *ctx) \ +{ \ + 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); \ + bpf_map_update_elem(&my_map2, &v, &v, BPF_ANY); \ + bpf_map_delete_elem(&my_map2, &v); \ + bpf_get_stackid(ctx, &stackmap, BPF_F_REUSE_STACKID); \ + return 0; \ +} + +/* add kprobes to all possible *spin* functions */ +SEC("kprobe/spin_unlock")PROG(p1) +SEC("kprobe/spin_lock")PROG(p2) +SEC("kprobe/mutex_spin_on_owner")PROG(p3) +SEC("kprobe/rwsem_spin_on_owner")PROG(p4) +SEC("kprobe/spin_unlock_irqrestore")PROG(p5) +SEC("kprobe/_raw_spin_unlock_irqrestore")PROG(p6) +SEC("kprobe/_raw_spin_unlock_bh")PROG(p7) +SEC("kprobe/_raw_spin_unlock")PROG(p8) +SEC("kprobe/_raw_spin_lock_irqsave")PROG(p9) +SEC("kprobe/_raw_spin_trylock_bh")PROG(p10) +SEC("kprobe/_raw_spin_lock_irq")PROG(p11) +SEC("kprobe/_raw_spin_trylock")PROG(p12) +SEC("kprobe/_raw_spin_lock")PROG(p13) +SEC("kprobe/_raw_spin_lock_bh")PROG(p14) +/* and to inner bpf helpers */ +SEC("kprobe/htab_map_update_elem")PROG(p15) +SEC("kprobe/__htab_percpu_map_update_elem")PROG(p16) +SEC("kprobe/htab_map_alloc")PROG(p17) + +char _license[] SEC("license") = "GPL"; +u32 _version SEC("version") = LINUX_VERSION_CODE; diff --git a/samples/bpf/spintest_user.c b/samples/bpf/spintest_user.c new file mode 100644 index 000000000000..311ede532230 --- /dev/null +++ b/samples/bpf/spintest_user.c @@ -0,0 +1,50 @@ +#include <stdio.h> +#include <unistd.h> +#include <linux/bpf.h> +#include <string.h> +#include <assert.h> +#include <sys/resource.h> +#include "libbpf.h" +#include "bpf_load.h" + +int main(int ac, char **argv) +{ + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + long key, next_key, value; + char filename[256]; + struct ksym *sym; + int i; + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + setrlimit(RLIMIT_MEMLOCK, &r); + + if (load_kallsyms()) { + printf("failed to process /proc/kallsyms\n"); + return 2; + } + + if (load_bpf_file(filename)) { + printf("%s", bpf_log_buf); + return 1; + } + + for (i = 0; i < 5; i++) { + key = 0; + printf("kprobing funcs:"); + while (bpf_get_next_key(map_fd[0], &key, &next_key) == 0) { + bpf_lookup_elem(map_fd[0], &next_key, &value); + assert(next_key == value); + sym = ksym_search(value); + printf(" %s", sym->name); + key = next_key; + } + if (key) + printf("\n"); + key = 0; + while (bpf_get_next_key(map_fd[0], &key, &next_key) == 0) + bpf_delete_elem(map_fd[0], &next_key); + sleep(1); + } + + return 0; +} diff --git a/samples/bpf/test_cls_bpf.sh b/samples/bpf/test_cls_bpf.sh new file mode 100755 index 000000000000..0365d5ee512c --- /dev/null +++ b/samples/bpf/test_cls_bpf.sh @@ -0,0 +1,37 @@ +#!/bin/bash + +function pktgen { + ../pktgen/pktgen_bench_xmit_mode_netif_receive.sh -i $IFC -s 64 \ + -m 90:e2:ba:ff:ff:ff -d 192.168.0.1 -t 4 + local dropped=`tc -s qdisc show dev $IFC | tail -3 | awk '/drop/{print $7}'` + if [ "$dropped" == "0," ]; then + echo "FAIL" + else + echo "Successfully filtered " $dropped " packets" + fi +} + +function test { + echo -n "Loading bpf program '$2'... " + tc qdisc add dev $IFC clsact + tc filter add dev $IFC ingress bpf da obj $1 sec $2 + local status=$? + if [ $status -ne 0 ]; then + echo "FAIL" + else + echo "ok" + pktgen + fi + tc qdisc del dev $IFC clsact +} + +IFC=test_veth + +ip link add name $IFC type veth peer name pair_$IFC +ip link set $IFC up +ip link set pair_$IFC up + +test ./parse_simple.o simple +test ./parse_varlen.o varlen +test ./parse_ldabs.o ldabs +ip link del dev $IFC diff --git a/samples/bpf/test_maps.c b/samples/bpf/test_maps.c index 6299ee95cd11..47bf0858f9e4 100644 --- a/samples/bpf/test_maps.c +++ b/samples/bpf/test_maps.c @@ -2,6 +2,7 @@ * Testsuite for eBPF maps * * Copyright (c) 2014 PLUMgrid, http://plumgrid.com + * 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 @@ -17,13 +18,16 @@ #include <stdlib.h> #include "libbpf.h" +static int map_flags; + /* sanity tests for map API */ static void test_hashmap_sanity(int i, void *data) { long long key, next_key, value; int map_fd; - map_fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value), 2); + map_fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value), + 2, map_flags); if (map_fd < 0) { printf("failed to create hashmap '%s'\n", strerror(errno)); exit(1); @@ -89,12 +93,107 @@ static void test_hashmap_sanity(int i, void *data) close(map_fd); } +/* sanity tests for percpu map API */ +static void test_percpu_hashmap_sanity(int task, void *data) +{ + long long key, next_key; + int expected_key_mask = 0; + unsigned int nr_cpus = sysconf(_SC_NPROCESSORS_CONF); + long long value[nr_cpus]; + int map_fd, i; + + map_fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_HASH, sizeof(key), + sizeof(value[0]), 2, map_flags); + if (map_fd < 0) { + printf("failed to create hashmap '%s'\n", strerror(errno)); + exit(1); + } + + for (i = 0; i < nr_cpus; i++) + value[i] = i + 100; + key = 1; + /* insert key=1 element */ + assert(!(expected_key_mask & key)); + assert(bpf_update_elem(map_fd, &key, value, BPF_ANY) == 0); + expected_key_mask |= key; + + /* BPF_NOEXIST means: add new element if it doesn't exist */ + assert(bpf_update_elem(map_fd, &key, value, BPF_NOEXIST) == -1 && + /* key=1 already exists */ + errno == EEXIST); + + /* -1 is an invalid flag */ + assert(bpf_update_elem(map_fd, &key, value, -1) == -1 && + errno == EINVAL); + + /* check that key=1 can be found. value could be 0 if the lookup + * was run from a different cpu. + */ + value[0] = 1; + assert(bpf_lookup_elem(map_fd, &key, value) == 0 && value[0] == 100); + + key = 2; + /* check that key=2 is not found */ + assert(bpf_lookup_elem(map_fd, &key, value) == -1 && errno == ENOENT); + + /* BPF_EXIST means: update existing element */ + assert(bpf_update_elem(map_fd, &key, value, BPF_EXIST) == -1 && + /* key=2 is not there */ + errno == ENOENT); + + /* insert key=2 element */ + assert(!(expected_key_mask & key)); + assert(bpf_update_elem(map_fd, &key, value, BPF_NOEXIST) == 0); + expected_key_mask |= key; + + /* key=1 and key=2 were inserted, check that key=0 cannot be inserted + * due to max_entries limit + */ + key = 0; + assert(bpf_update_elem(map_fd, &key, value, BPF_NOEXIST) == -1 && + errno == E2BIG); + + /* check that key = 0 doesn't exist */ + assert(bpf_delete_elem(map_fd, &key) == -1 && errno == ENOENT); + + /* iterate over two elements */ + while (!bpf_get_next_key(map_fd, &key, &next_key)) { + assert((expected_key_mask & next_key) == next_key); + expected_key_mask &= ~next_key; + + assert(bpf_lookup_elem(map_fd, &next_key, value) == 0); + for (i = 0; i < nr_cpus; i++) + assert(value[i] == i + 100); + + key = next_key; + } + assert(errno == ENOENT); + + /* Update with BPF_EXIST */ + key = 1; + assert(bpf_update_elem(map_fd, &key, value, BPF_EXIST) == 0); + + /* delete both elements */ + key = 1; + assert(bpf_delete_elem(map_fd, &key) == 0); + key = 2; + assert(bpf_delete_elem(map_fd, &key) == 0); + assert(bpf_delete_elem(map_fd, &key) == -1 && errno == ENOENT); + + key = 0; + /* check that map is empty */ + assert(bpf_get_next_key(map_fd, &key, &next_key) == -1 && + errno == ENOENT); + close(map_fd); +} + static void test_arraymap_sanity(int i, void *data) { int key, next_key, map_fd; long long value; - map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, sizeof(key), sizeof(value), 2); + map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, sizeof(key), sizeof(value), + 2, 0); if (map_fd < 0) { printf("failed to create arraymap '%s'\n", strerror(errno)); exit(1); @@ -142,6 +241,94 @@ static void test_arraymap_sanity(int i, void *data) close(map_fd); } +static void test_percpu_arraymap_many_keys(void) +{ + unsigned nr_cpus = sysconf(_SC_NPROCESSORS_CONF); + unsigned nr_keys = 20000; + long values[nr_cpus]; + int key, map_fd, i; + + map_fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_ARRAY, sizeof(key), + sizeof(values[0]), nr_keys, 0); + if (map_fd < 0) { + printf("failed to create per-cpu arraymap '%s'\n", + strerror(errno)); + exit(1); + } + + for (i = 0; i < nr_cpus; i++) + values[i] = i + 10; + + for (key = 0; key < nr_keys; key++) + assert(bpf_update_elem(map_fd, &key, values, BPF_ANY) == 0); + + for (key = 0; key < nr_keys; key++) { + for (i = 0; i < nr_cpus; i++) + values[i] = 0; + assert(bpf_lookup_elem(map_fd, &key, values) == 0); + for (i = 0; i < nr_cpus; i++) + assert(values[i] == i + 10); + } + + close(map_fd); +} + +static void test_percpu_arraymap_sanity(int i, void *data) +{ + unsigned nr_cpus = sysconf(_SC_NPROCESSORS_CONF); + long values[nr_cpus]; + int key, next_key, map_fd; + + map_fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_ARRAY, sizeof(key), + sizeof(values[0]), 2, 0); + if (map_fd < 0) { + printf("failed to create arraymap '%s'\n", strerror(errno)); + exit(1); + } + + for (i = 0; i < nr_cpus; i++) + values[i] = i + 100; + + key = 1; + /* insert key=1 element */ + assert(bpf_update_elem(map_fd, &key, values, BPF_ANY) == 0); + + values[0] = 0; + assert(bpf_update_elem(map_fd, &key, values, BPF_NOEXIST) == -1 && + errno == EEXIST); + + /* check that key=1 can be found */ + assert(bpf_lookup_elem(map_fd, &key, values) == 0 && values[0] == 100); + + key = 0; + /* check that key=0 is also found and zero initialized */ + assert(bpf_lookup_elem(map_fd, &key, values) == 0 && + values[0] == 0 && values[nr_cpus - 1] == 0); + + + /* check that key=2 cannot be inserted due to max_entries limit */ + key = 2; + assert(bpf_update_elem(map_fd, &key, values, BPF_EXIST) == -1 && + errno == E2BIG); + + /* check that key = 2 doesn't exist */ + assert(bpf_lookup_elem(map_fd, &key, values) == -1 && errno == ENOENT); + + /* iterate over two elements */ + assert(bpf_get_next_key(map_fd, &key, &next_key) == 0 && + next_key == 0); + assert(bpf_get_next_key(map_fd, &next_key, &next_key) == 0 && + next_key == 1); + assert(bpf_get_next_key(map_fd, &next_key, &next_key) == -1 && + errno == ENOENT); + + /* delete shouldn't succeed */ + key = 1; + assert(bpf_delete_elem(map_fd, &key) == -1 && errno == EINVAL); + + close(map_fd); +} + #define MAP_SIZE (32 * 1024) static void test_map_large(void) { @@ -154,7 +341,7 @@ static void test_map_large(void) /* allocate 4Mbyte of memory */ map_fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value), - MAP_SIZE); + MAP_SIZE, map_flags); if (map_fd < 0) { printf("failed to create large map '%s'\n", strerror(errno)); exit(1); @@ -209,7 +396,9 @@ static void run_parallel(int tasks, void (*fn)(int i, void *data), void *data) static void test_map_stress(void) { run_parallel(100, test_hashmap_sanity, NULL); + run_parallel(100, test_percpu_hashmap_sanity, NULL); run_parallel(100, test_arraymap_sanity, NULL); + run_parallel(100, test_percpu_arraymap_sanity, NULL); } #define TASKS 1024 @@ -237,7 +426,7 @@ static void test_map_parallel(void) int data[2]; map_fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value), - MAP_SIZE); + MAP_SIZE, map_flags); if (map_fd < 0) { printf("failed to create map for parallel test '%s'\n", strerror(errno)); @@ -279,13 +468,25 @@ static void test_map_parallel(void) assert(bpf_get_next_key(map_fd, &key, &key) == -1 && errno == ENOENT); } -int main(void) +static void run_all_tests(void) { test_hashmap_sanity(0, NULL); + test_percpu_hashmap_sanity(0, NULL); test_arraymap_sanity(0, NULL); + test_percpu_arraymap_sanity(0, NULL); + test_percpu_arraymap_many_keys(); + test_map_large(); test_map_parallel(); test_map_stress(); +} + +int main(void) +{ + map_flags = 0; + run_all_tests(); + map_flags = BPF_F_NO_PREALLOC; + run_all_tests(); printf("test_maps: OK\n"); return 0; } 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/test_verifier.c b/samples/bpf/test_verifier.c index 563c507c0a09..fe2fcec98c1f 100644 --- a/samples/bpf/test_verifier.c +++ b/samples/bpf/test_verifier.c @@ -309,6 +309,19 @@ static struct bpf_test tests[] = { .result_unpriv = REJECT, }, { + "check valid spill/fill, skb mark", + .insns = { + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_1), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_6, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, + offsetof(struct __sk_buff, mark)), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .result_unpriv = ACCEPT, + }, + { "check corrupted spill/fill", .insns = { /* spill R1(ctx) into stack */ @@ -1180,6 +1193,341 @@ static struct bpf_test tests[] = { .result_unpriv = REJECT, .result = ACCEPT, }, + { + "raw_stack: no skb_load_bytes", + .insns = { + BPF_MOV64_IMM(BPF_REG_2, 4), + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_4, 8), + /* Call to skb_load_bytes() omitted. */ + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid read from stack off -8+0 size 8", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "raw_stack: skb_load_bytes, no init", + .insns = { + BPF_MOV64_IMM(BPF_REG_2, 4), + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_4, 8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_skb_load_bytes), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "raw_stack: skb_load_bytes, init", + .insns = { + BPF_MOV64_IMM(BPF_REG_2, 4), + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_6, 0, 0xcafe), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_4, 8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_skb_load_bytes), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "raw_stack: skb_load_bytes, spilled regs around bounds", + .insns = { + BPF_MOV64_IMM(BPF_REG_2, 4), + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -16), + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, -8), /* spill ctx from R1 */ + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 8), /* spill ctx from R1 */ + BPF_MOV64_REG(BPF_REG_3, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_4, 8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_skb_load_bytes), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, -8), /* fill ctx into R0 */ + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_6, 8), /* fill ctx into R2 */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, + offsetof(struct __sk_buff, mark)), + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_2, + offsetof(struct __sk_buff, priority)), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_2), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "raw_stack: skb_load_bytes, spilled regs corruption", + .insns = { + BPF_MOV64_IMM(BPF_REG_2, 4), + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0), /* spill ctx from R1 */ + BPF_MOV64_REG(BPF_REG_3, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_4, 8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_skb_load_bytes), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0), /* fill ctx into R0 */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, + offsetof(struct __sk_buff, mark)), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "R0 invalid mem access 'inv'", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "raw_stack: skb_load_bytes, spilled regs corruption 2", + .insns = { + BPF_MOV64_IMM(BPF_REG_2, 4), + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -16), + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, -8), /* spill ctx from R1 */ + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0), /* spill ctx from R1 */ + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 8), /* spill ctx from R1 */ + BPF_MOV64_REG(BPF_REG_3, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_4, 8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_skb_load_bytes), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, -8), /* fill ctx into R0 */ + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_6, 8), /* fill ctx into R2 */ + BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_6, 0), /* fill ctx into R3 */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, + offsetof(struct __sk_buff, mark)), + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_2, + offsetof(struct __sk_buff, priority)), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_2), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_3, + offsetof(struct __sk_buff, pkt_type)), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_3), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "R3 invalid mem access 'inv'", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "raw_stack: skb_load_bytes, spilled regs + data", + .insns = { + BPF_MOV64_IMM(BPF_REG_2, 4), + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -16), + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, -8), /* spill ctx from R1 */ + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0), /* spill ctx from R1 */ + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 8), /* spill ctx from R1 */ + BPF_MOV64_REG(BPF_REG_3, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_4, 8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_skb_load_bytes), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, -8), /* fill ctx into R0 */ + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_6, 8), /* fill ctx into R2 */ + BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_6, 0), /* fill data into R3 */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, + offsetof(struct __sk_buff, mark)), + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_2, + offsetof(struct __sk_buff, priority)), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_3), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "raw_stack: skb_load_bytes, invalid access 1", + .insns = { + BPF_MOV64_IMM(BPF_REG_2, 4), + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -513), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_4, 8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_skb_load_bytes), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid stack type R3 off=-513 access_size=8", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "raw_stack: skb_load_bytes, invalid access 2", + .insns = { + BPF_MOV64_IMM(BPF_REG_2, 4), + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -1), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_4, 8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_skb_load_bytes), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid stack type R3 off=-1 access_size=8", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "raw_stack: skb_load_bytes, invalid access 3", + .insns = { + BPF_MOV64_IMM(BPF_REG_2, 4), + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 0xffffffff), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_4, 0xffffffff), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_skb_load_bytes), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid stack type R3 off=-1 access_size=-1", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "raw_stack: skb_load_bytes, invalid access 4", + .insns = { + BPF_MOV64_IMM(BPF_REG_2, 4), + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -1), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_4, 0x7fffffff), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_skb_load_bytes), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid stack type R3 off=-1 access_size=2147483647", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "raw_stack: skb_load_bytes, invalid access 5", + .insns = { + BPF_MOV64_IMM(BPF_REG_2, 4), + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -512), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_4, 0x7fffffff), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_skb_load_bytes), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid stack type R3 off=-512 access_size=2147483647", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "raw_stack: skb_load_bytes, invalid access 6", + .insns = { + BPF_MOV64_IMM(BPF_REG_2, 4), + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -512), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_skb_load_bytes), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid stack type R3 off=-512 access_size=0", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "raw_stack: skb_load_bytes, large access", + .insns = { + BPF_MOV64_IMM(BPF_REG_2, 4), + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -512), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_4, 512), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_skb_load_bytes), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "pkt: test1", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "pkt: test2", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_MOV64_REG(BPF_REG_5, BPF_REG_3), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 14), + BPF_JMP_REG(BPF_JGT, BPF_REG_5, BPF_REG_4, 15), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_3, 7), + BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_3, 12), + BPF_ALU64_IMM(BPF_MUL, BPF_REG_4, 14), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_ALU64_REG(BPF_ADD, BPF_REG_3, BPF_REG_4), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_1), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_2, 48), + BPF_ALU64_IMM(BPF_RSH, BPF_REG_2, 48), + BPF_ALU64_REG(BPF_ADD, BPF_REG_3, BPF_REG_2), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_3), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 8), + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_JMP_REG(BPF_JGT, BPF_REG_2, BPF_REG_1, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_3, 4), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "pkt: test3", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access off=76", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SOCKET_FILTER, + }, + { + "pkt: test4", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), + BPF_STX_MEM(BPF_B, BPF_REG_2, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "cannot write", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, }; static int probe_filter_length(struct bpf_insn *fp) @@ -1198,7 +1546,7 @@ static int create_map(void) int map_fd; map_fd = bpf_create_map(BPF_MAP_TYPE_HASH, - sizeof(long long), sizeof(long long), 1024); + sizeof(long long), sizeof(long long), 1024, 0); if (map_fd < 0) printf("failed to create map '%s'\n", strerror(errno)); @@ -1210,7 +1558,7 @@ static int create_prog_array(void) int map_fd; map_fd = bpf_create_map(BPF_MAP_TYPE_PROG_ARRAY, - sizeof(int), sizeof(int), 4); + sizeof(int), sizeof(int), 4, 0); if (map_fd < 0) printf("failed to create prog_array '%s'\n", strerror(errno)); diff --git a/samples/bpf/trace_output_kern.c b/samples/bpf/trace_output_kern.c index 8d8d1ec429eb..9b96f4fb8cea 100644 --- a/samples/bpf/trace_output_kern.c +++ b/samples/bpf/trace_output_kern.c @@ -18,7 +18,6 @@ int bpf_prog1(struct pt_regs *ctx) u64 cookie; } data; - memset(&data, 0, sizeof(data)); data.pid = bpf_get_current_pid_tgid(); data.cookie = 0x12345678; diff --git a/samples/bpf/tracex1_kern.c b/samples/bpf/tracex1_kern.c index 3f450a8fa1f3..107da148820f 100644 --- a/samples/bpf/tracex1_kern.c +++ b/samples/bpf/tracex1_kern.c @@ -23,16 +23,14 @@ 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] = {}; + 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 *) PT_REGS_PARM1(ctx); - dev = _(skb->dev); - len = _(skb->len); bpf_probe_read(devname, sizeof(devname), dev->name); diff --git a/samples/bpf/tracex2_kern.c b/samples/bpf/tracex2_kern.c index b32367cfbff4..5e11c20ce5ec 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) @@ -66,11 +66,11 @@ struct hist_key { char comm[16]; u64 pid_tgid; u64 uid_gid; - u32 index; + u64 index; }; struct bpf_map_def SEC("maps") my_hist_map = { - .type = BPF_MAP_TYPE_HASH, + .type = BPF_MAP_TYPE_PERCPU_HASH, .key_size = sizeof(struct hist_key), .value_size = sizeof(long), .max_entries = 1024, @@ -82,7 +82,7 @@ int bpf_prog3(struct pt_regs *ctx) long write_size = PT_REGS_PARM3(ctx); long init_val = 1; long *value; - struct hist_key key = {}; + struct hist_key key; key.index = log2l(write_size); key.pid_tgid = bpf_get_current_pid_tgid(); diff --git a/samples/bpf/tracex2_user.c b/samples/bpf/tracex2_user.c index cd0241c1447a..ab5b19e68acf 100644 --- a/samples/bpf/tracex2_user.c +++ b/samples/bpf/tracex2_user.c @@ -37,6 +37,8 @@ struct hist_key { static void print_hist_for_pid(int fd, void *task) { struct hist_key key = {}, next_key; + unsigned int nr_cpus = sysconf(_SC_NPROCESSORS_CONF); + long values[nr_cpus]; char starstr[MAX_STARS]; long value; long data[MAX_INDEX] = {}; @@ -49,7 +51,10 @@ static void print_hist_for_pid(int fd, void *task) key = next_key; continue; } - bpf_lookup_elem(fd, &next_key, &value); + bpf_lookup_elem(fd, &next_key, values); + value = 0; + for (i = 0; i < nr_cpus; i++) + value += values[i]; ind = next_key.index; data[ind] = value; if (value && ind > max_ind) diff --git a/samples/bpf/tracex3_kern.c b/samples/bpf/tracex3_kern.c index bf337fbb0947..9974c3d7c18b 100644 --- a/samples/bpf/tracex3_kern.c +++ b/samples/bpf/tracex3_kern.c @@ -20,7 +20,7 @@ struct bpf_map_def SEC("maps") my_map = { /* kprobe is NOT a stable ABI. If kernel internals change this bpf+kprobe * example will no longer be meaningful */ -SEC("kprobe/blk_mq_start_request") +SEC("kprobe/blk_start_request") int bpf_prog1(struct pt_regs *ctx) { long rq = PT_REGS_PARM1(ctx); @@ -42,13 +42,13 @@ static unsigned int log2l(unsigned long long n) #define SLOTS 100 struct bpf_map_def SEC("maps") lat_map = { - .type = BPF_MAP_TYPE_ARRAY, + .type = BPF_MAP_TYPE_PERCPU_ARRAY, .key_size = sizeof(u32), .value_size = sizeof(u64), .max_entries = SLOTS, }; -SEC("kprobe/blk_update_request") +SEC("kprobe/blk_account_io_completion") int bpf_prog2(struct pt_regs *ctx) { long rq = PT_REGS_PARM1(ctx); @@ -81,7 +81,7 @@ int bpf_prog2(struct pt_regs *ctx) value = bpf_map_lookup_elem(&lat_map, &index); if (value) - __sync_fetch_and_add((long *)value, 1); + *value += 1; return 0; } diff --git a/samples/bpf/tracex3_user.c b/samples/bpf/tracex3_user.c index 0aaa933ab938..48716f7f0d8b 100644 --- a/samples/bpf/tracex3_user.c +++ b/samples/bpf/tracex3_user.c @@ -20,11 +20,13 @@ static void clear_stats(int fd) { + unsigned int nr_cpus = sysconf(_SC_NPROCESSORS_CONF); + __u64 values[nr_cpus]; __u32 key; - __u64 value = 0; + memset(values, 0, sizeof(values)); for (key = 0; key < SLOTS; key++) - bpf_update_elem(fd, &key, &value, BPF_ANY); + bpf_update_elem(fd, &key, values, BPF_ANY); } const char *color[] = { @@ -75,15 +77,20 @@ static void print_banner(void) static void print_hist(int fd) { - __u32 key; - __u64 value; - __u64 cnt[SLOTS]; - __u64 max_cnt = 0; + unsigned int nr_cpus = sysconf(_SC_NPROCESSORS_CONF); __u64 total_events = 0; + long values[nr_cpus]; + __u64 max_cnt = 0; + __u64 cnt[SLOTS]; + __u64 value; + __u32 key; + int i; for (key = 0; key < SLOTS; key++) { + bpf_lookup_elem(fd, &key, values); value = 0; - bpf_lookup_elem(fd, &key, &value); + for (i = 0; i < nr_cpus; i++) + value += values[i]; cnt[key] = value; total_events += value; if (value > max_cnt) 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(), diff --git a/samples/bpf/tracex5_kern.c b/samples/bpf/tracex5_kern.c index b3f4295bf288..f95f232cbab9 100644 --- a/samples/bpf/tracex5_kern.c +++ b/samples/bpf/tracex5_kern.c @@ -22,7 +22,7 @@ struct bpf_map_def SEC("maps") progs = { SEC("kprobe/seccomp_phase1") int bpf_prog1(struct pt_regs *ctx) { - struct seccomp_data sd = {}; + struct seccomp_data sd; bpf_probe_read(&sd, sizeof(sd), (void *)PT_REGS_PARM1(ctx)); @@ -40,7 +40,7 @@ int bpf_prog1(struct pt_regs *ctx) /* we jump here when syscall number == __NR_write */ PROG(__NR_write)(struct pt_regs *ctx) { - struct seccomp_data sd = {}; + struct seccomp_data sd; bpf_probe_read(&sd, sizeof(sd), (void *)PT_REGS_PARM1(ctx)); if (sd.args[2] == 512) { @@ -53,7 +53,7 @@ PROG(__NR_write)(struct pt_regs *ctx) PROG(__NR_read)(struct pt_regs *ctx) { - struct seccomp_data sd = {}; + struct seccomp_data sd; bpf_probe_read(&sd, sizeof(sd), (void *)PT_REGS_PARM1(ctx)); if (sd.args[2] > 128 && sd.args[2] <= 1024) { |