diff options
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/bpf/arraymap.c | 137 | ||||
-rw-r--r-- | kernel/bpf/core.c | 9 | ||||
-rw-r--r-- | kernel/bpf/syscall.c | 2 | ||||
-rw-r--r-- | kernel/bpf/verifier.c | 54 | ||||
-rw-r--r-- | kernel/events/core.c | 78 | ||||
-rw-r--r-- | kernel/trace/bpf_trace.c | 63 | ||||
-rw-r--r-- | kernel/trace/trace_kprobe.c | 20 |
7 files changed, 295 insertions, 68 deletions
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index cb31229..29ace10 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -150,15 +150,15 @@ static int __init register_array_map(void) } late_initcall(register_array_map); -static struct bpf_map *prog_array_map_alloc(union bpf_attr *attr) +static struct bpf_map *fd_array_map_alloc(union bpf_attr *attr) { - /* only bpf_prog file descriptors can be stored in prog_array map */ + /* only file descriptors can be stored in this type of map */ if (attr->value_size != sizeof(u32)) return ERR_PTR(-EINVAL); return array_map_alloc(attr); } -static void prog_array_map_free(struct bpf_map *map) +static void fd_array_map_free(struct bpf_map *map) { struct bpf_array *array = container_of(map, struct bpf_array, map); int i; @@ -167,21 +167,21 @@ static void prog_array_map_free(struct bpf_map *map) /* make sure it's empty */ for (i = 0; i < array->map.max_entries; i++) - BUG_ON(array->prog[i] != NULL); + BUG_ON(array->ptrs[i] != NULL); kvfree(array); } -static void *prog_array_map_lookup_elem(struct bpf_map *map, void *key) +static void *fd_array_map_lookup_elem(struct bpf_map *map, void *key) { return NULL; } /* only called from syscall */ -static int prog_array_map_update_elem(struct bpf_map *map, void *key, - void *value, u64 map_flags) +static int fd_array_map_update_elem(struct bpf_map *map, void *key, + void *value, u64 map_flags) { struct bpf_array *array = container_of(map, struct bpf_array, map); - struct bpf_prog *prog, *old_prog; + void *new_ptr, *old_ptr; u32 index = *(u32 *)key, ufd; if (map_flags != BPF_ANY) @@ -191,57 +191,75 @@ static int prog_array_map_update_elem(struct bpf_map *map, void *key, return -E2BIG; ufd = *(u32 *)value; - prog = bpf_prog_get(ufd); - if (IS_ERR(prog)) - return PTR_ERR(prog); - - if (!bpf_prog_array_compatible(array, prog)) { - bpf_prog_put(prog); - return -EINVAL; - } + new_ptr = map->ops->map_fd_get_ptr(map, ufd); + if (IS_ERR(new_ptr)) + return PTR_ERR(new_ptr); - old_prog = xchg(array->prog + index, prog); - if (old_prog) - bpf_prog_put_rcu(old_prog); + old_ptr = xchg(array->ptrs + index, new_ptr); + if (old_ptr) + map->ops->map_fd_put_ptr(old_ptr); return 0; } -static int prog_array_map_delete_elem(struct bpf_map *map, void *key) +static int fd_array_map_delete_elem(struct bpf_map *map, void *key) { struct bpf_array *array = container_of(map, struct bpf_array, map); - struct bpf_prog *old_prog; + void *old_ptr; u32 index = *(u32 *)key; if (index >= array->map.max_entries) return -E2BIG; - old_prog = xchg(array->prog + index, NULL); - if (old_prog) { - bpf_prog_put_rcu(old_prog); + old_ptr = xchg(array->ptrs + index, NULL); + if (old_ptr) { + map->ops->map_fd_put_ptr(old_ptr); return 0; } else { return -ENOENT; } } +static void *prog_fd_array_get_ptr(struct bpf_map *map, int fd) +{ + struct bpf_array *array = container_of(map, struct bpf_array, map); + struct bpf_prog *prog = bpf_prog_get(fd); + if (IS_ERR(prog)) + return prog; + + if (!bpf_prog_array_compatible(array, prog)) { + bpf_prog_put(prog); + return ERR_PTR(-EINVAL); + } + return prog; +} + +static void prog_fd_array_put_ptr(void *ptr) +{ + struct bpf_prog *prog = ptr; + + bpf_prog_put_rcu(prog); +} + /* decrement refcnt of all bpf_progs that are stored in this map */ -void bpf_prog_array_map_clear(struct bpf_map *map) +void bpf_fd_array_map_clear(struct bpf_map *map) { struct bpf_array *array = container_of(map, struct bpf_array, map); int i; for (i = 0; i < array->map.max_entries; i++) - prog_array_map_delete_elem(map, &i); + fd_array_map_delete_elem(map, &i); } static const struct bpf_map_ops prog_array_ops = { - .map_alloc = prog_array_map_alloc, - .map_free = prog_array_map_free, + .map_alloc = fd_array_map_alloc, + .map_free = fd_array_map_free, .map_get_next_key = array_map_get_next_key, - .map_lookup_elem = prog_array_map_lookup_elem, - .map_update_elem = prog_array_map_update_elem, - .map_delete_elem = prog_array_map_delete_elem, + .map_lookup_elem = fd_array_map_lookup_elem, + .map_update_elem = fd_array_map_update_elem, + .map_delete_elem = fd_array_map_delete_elem, + .map_fd_get_ptr = prog_fd_array_get_ptr, + .map_fd_put_ptr = prog_fd_array_put_ptr, }; static struct bpf_map_type_list prog_array_type __read_mostly = { @@ -255,3 +273,60 @@ static int __init register_prog_array_map(void) return 0; } late_initcall(register_prog_array_map); + +static void perf_event_array_map_free(struct bpf_map *map) +{ + bpf_fd_array_map_clear(map); + fd_array_map_free(map); +} + +static void *perf_event_fd_array_get_ptr(struct bpf_map *map, int fd) +{ + struct perf_event *event; + const struct perf_event_attr *attr; + + event = perf_event_get(fd); + if (IS_ERR(event)) + return event; + + attr = perf_event_attrs(event); + if (IS_ERR(attr)) + return (void *)attr; + + if (attr->type != PERF_TYPE_RAW && + attr->type != PERF_TYPE_HARDWARE) { + perf_event_release_kernel(event); + return ERR_PTR(-EINVAL); + } + return event; +} + +static void perf_event_fd_array_put_ptr(void *ptr) +{ + struct perf_event *event = ptr; + + perf_event_release_kernel(event); +} + +static const struct bpf_map_ops perf_event_array_ops = { + .map_alloc = fd_array_map_alloc, + .map_free = perf_event_array_map_free, + .map_get_next_key = array_map_get_next_key, + .map_lookup_elem = fd_array_map_lookup_elem, + .map_update_elem = fd_array_map_update_elem, + .map_delete_elem = fd_array_map_delete_elem, + .map_fd_get_ptr = perf_event_fd_array_get_ptr, + .map_fd_put_ptr = perf_event_fd_array_put_ptr, +}; + +static struct bpf_map_type_list perf_event_array_type __read_mostly = { + .ops = &perf_event_array_ops, + .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, +}; + +static int __init register_perf_event_array_map(void) +{ + bpf_register_map_type(&perf_event_array_type); + return 0; +} +late_initcall(register_perf_event_array_map); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index c5bedc8..67c380c 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -177,6 +177,7 @@ noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) { return 0; } +EXPORT_SYMBOL_GPL(__bpf_call_base); /** * __bpf_prog_run - run eBPF program on a given context @@ -449,11 +450,15 @@ select_insn: tail_call_cnt++; - prog = READ_ONCE(array->prog[index]); + prog = READ_ONCE(array->ptrs[index]); if (unlikely(!prog)) goto out; - ARG1 = BPF_R1; + /* ARG1 at this point is guaranteed to point to CTX from + * the verifier side due to the fact that the tail call is + * handeled like a helper, that is, bpf_tail_call_proto, + * where arg1_type is ARG_PTR_TO_CTX. + */ insn = prog->insnsi; goto select_insn; out: diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index a1b14d1..dc9b464 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -72,7 +72,7 @@ static int bpf_map_release(struct inode *inode, struct file *filp) /* prog_array stores refcnt-ed bpf_prog pointers * release them all when user space closes prog_array_fd */ - bpf_prog_array_map_clear(map); + bpf_fd_array_map_clear(map); bpf_map_put(map); return 0; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 039d866..ed12e38 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -238,6 +238,14 @@ static const char * const reg_type_str[] = { [CONST_IMM] = "imm", }; +static const struct { + int map_type; + int func_id; +} func_limit[] = { + {BPF_MAP_TYPE_PROG_ARRAY, BPF_FUNC_tail_call}, + {BPF_MAP_TYPE_PERF_EVENT_ARRAY, BPF_FUNC_perf_event_read}, +}; + static void print_verifier_state(struct verifier_env *env) { enum bpf_reg_type t; @@ -648,6 +656,9 @@ static int check_mem_access(struct verifier_env *env, u32 regno, int off, struct verifier_state *state = &env->cur_state; int size, err = 0; + if (state->regs[regno].type == PTR_TO_STACK) + off += state->regs[regno].imm; + size = bpf_size_to_bytes(bpf_size); if (size < 0) return size; @@ -667,7 +678,8 @@ static int check_mem_access(struct verifier_env *env, u32 regno, int off, if (!err && t == BPF_READ && value_regno >= 0) mark_reg_unknown_value(state->regs, value_regno); - } else if (state->regs[regno].type == FRAME_PTR) { + } else if (state->regs[regno].type == FRAME_PTR || + state->regs[regno].type == PTR_TO_STACK) { if (off >= 0 || off < -MAX_BPF_STACK) { verbose("invalid stack off=%d size=%d\n", off, size); return -EACCES; @@ -833,6 +845,28 @@ static int check_func_arg(struct verifier_env *env, u32 regno, return err; } +static int check_map_func_compatibility(struct bpf_map *map, int func_id) +{ + bool bool_map, bool_func; + int i; + + if (!map) + return 0; + + for (i = 0; i < ARRAY_SIZE(func_limit); i++) { + bool_map = (map->map_type == func_limit[i].map_type); + bool_func = (func_id == func_limit[i].func_id); + /* only when map & func pair match it can continue. + * don't allow any other map type to be passed into + * the special func; + */ + if (bool_map != bool_func) + return -EINVAL; + } + + return 0; +} + static int check_call(struct verifier_env *env, int func_id) { struct verifier_state *state = &env->cur_state; @@ -908,21 +942,9 @@ static int check_call(struct verifier_env *env, int func_id) return -EINVAL; } - if (map && map->map_type == BPF_MAP_TYPE_PROG_ARRAY && - func_id != BPF_FUNC_tail_call) - /* prog_array map type needs extra care: - * only allow to pass it into bpf_tail_call() for now. - * bpf_map_delete_elem() can be allowed in the future, - * while bpf_map_update_elem() must only be done via syscall - */ - return -EINVAL; - - if (func_id == BPF_FUNC_tail_call && - map->map_type != BPF_MAP_TYPE_PROG_ARRAY) - /* don't allow any other map type to be passed into - * bpf_tail_call() - */ - return -EINVAL; + err = check_map_func_compatibility(map, func_id); + if (err) + return err; return 0; } diff --git a/kernel/events/core.c b/kernel/events/core.c index ae16867..e818389 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3222,6 +3222,59 @@ static inline u64 perf_event_count(struct perf_event *event) return __perf_event_count(event); } +/* + * NMI-safe method to read a local event, that is an event that + * is: + * - either for the current task, or for this CPU + * - does not have inherit set, for inherited task events + * will not be local and we cannot read them atomically + * - must not have a pmu::count method + */ +u64 perf_event_read_local(struct perf_event *event) +{ + unsigned long flags; + u64 val; + + /* + * Disabling interrupts avoids all counter scheduling (context + * switches, timer based rotation and IPIs). + */ + local_irq_save(flags); + + /* If this is a per-task event, it must be for current */ + WARN_ON_ONCE((event->attach_state & PERF_ATTACH_TASK) && + event->hw.target != current); + + /* If this is a per-CPU event, it must be for this CPU */ + WARN_ON_ONCE(!(event->attach_state & PERF_ATTACH_TASK) && + event->cpu != smp_processor_id()); + + /* + * It must not be an event with inherit set, we cannot read + * all child counters from atomic context. + */ + WARN_ON_ONCE(event->attr.inherit); + + /* + * It must not have a pmu::count method, those are not + * NMI safe. + */ + WARN_ON_ONCE(event->pmu->count); + + /* + * If the event is currently on this CPU, its either a per-task event, + * or local to this CPU. Furthermore it means its ACTIVE (otherwise + * oncpu == -1). + */ + if (event->oncpu == smp_processor_id()) + event->pmu->read(event); + + val = local64_read(&event->count); + local_irq_restore(flags); + + return val; +} + static u64 perf_event_read(struct perf_event *event) { /* @@ -8718,6 +8771,31 @@ void perf_event_delayed_put(struct task_struct *task) WARN_ON_ONCE(task->perf_event_ctxp[ctxn]); } +struct perf_event *perf_event_get(unsigned int fd) +{ + int err; + struct fd f; + struct perf_event *event; + + err = perf_fget_light(fd, &f); + if (err) + return ERR_PTR(err); + + event = f.file->private_data; + atomic_long_inc(&event->refcount); + fdput(f); + + return event; +} + +const struct perf_event_attr *perf_event_attrs(struct perf_event *event) +{ + if (!event) + return ERR_PTR(-EINVAL); + + return &event->attr; +} + /* * inherit a event from parent task to child task: */ diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 88a041a..0fe96c7 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -81,13 +81,16 @@ static const struct bpf_func_proto bpf_probe_read_proto = { /* * limited trace_printk() - * only %d %u %x %ld %lu %lx %lld %llu %llx %p conversion specifiers allowed + * only %d %u %x %ld %lu %lx %lld %llu %llx %p %s conversion specifiers allowed */ static u64 bpf_trace_printk(u64 r1, u64 fmt_size, u64 r3, u64 r4, u64 r5) { char *fmt = (char *) (long) r1; + bool str_seen = false; int mod[3] = {}; int fmt_cnt = 0; + u64 unsafe_addr; + char buf[64]; int i; /* @@ -114,12 +117,37 @@ static u64 bpf_trace_printk(u64 r1, u64 fmt_size, u64 r3, u64 r4, u64 r5) if (fmt[i] == 'l') { mod[fmt_cnt]++; i++; - } else if (fmt[i] == 'p') { + } else if (fmt[i] == 'p' || fmt[i] == 's') { mod[fmt_cnt]++; i++; if (!isspace(fmt[i]) && !ispunct(fmt[i]) && fmt[i] != 0) return -EINVAL; fmt_cnt++; + if (fmt[i - 1] == 's') { + if (str_seen) + /* allow only one '%s' per fmt string */ + return -EINVAL; + str_seen = true; + + switch (fmt_cnt) { + case 1: + unsafe_addr = r3; + r3 = (long) buf; + break; + case 2: + unsafe_addr = r4; + r4 = (long) buf; + break; + case 3: + unsafe_addr = r5; + r5 = (long) buf; + break; + } + buf[0] = 0; + strncpy_from_unsafe(buf, + (void *) (long) unsafe_addr, + sizeof(buf)); + } continue; } @@ -158,6 +186,35 @@ const struct bpf_func_proto *bpf_get_trace_printk_proto(void) return &bpf_trace_printk_proto; } +static u64 bpf_perf_event_read(u64 r1, u64 index, u64 r3, u64 r4, u64 r5) +{ + struct bpf_map *map = (struct bpf_map *) (unsigned long) r1; + struct bpf_array *array = container_of(map, struct bpf_array, map); + struct perf_event *event; + + if (unlikely(index >= array->map.max_entries)) + return -E2BIG; + + event = (struct perf_event *)array->ptrs[index]; + if (!event) + return -ENOENT; + + /* + * we don't know if the function is run successfully by the + * return value. It can be judged in other places, such as + * eBPF programs. + */ + return perf_event_read_local(event); +} + +const struct bpf_func_proto bpf_perf_event_read_proto = { + .func = bpf_perf_event_read, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_ANYTHING, +}; + static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func_id) { switch (func_id) { @@ -183,6 +240,8 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func return bpf_get_trace_printk_proto(); case BPF_FUNC_get_smp_processor_id: return &bpf_get_smp_processor_id_proto; + case BPF_FUNC_perf_event_read: + return &bpf_perf_event_read_proto; default: return NULL; } diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index b7d0cdd..c995644 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -165,11 +165,9 @@ DEFINE_BASIC_FETCH_FUNCS(memory) static void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs, void *addr, void *dest) { - long ret; int maxlen = get_rloc_len(*(u32 *)dest); u8 *dst = get_rloc_data(dest); - u8 *src = addr; - mm_segment_t old_fs = get_fs(); + long ret; if (!maxlen) return; @@ -178,23 +176,13 @@ static void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs, * Try to get string again, since the string can be changed while * probing. */ - set_fs(KERNEL_DS); - pagefault_disable(); - - do - ret = __copy_from_user_inatomic(dst++, src++, 1); - while (dst[-1] && ret == 0 && src - (u8 *)addr < maxlen); - - dst[-1] = '\0'; - pagefault_enable(); - set_fs(old_fs); + ret = strncpy_from_unsafe(dst, addr, maxlen); if (ret < 0) { /* Failed to fetch string */ - ((u8 *)get_rloc_data(dest))[0] = '\0'; + dst[0] = '\0'; *(u32 *)dest = make_data_rloc(0, get_rloc_offs(*(u32 *)dest)); } else { - *(u32 *)dest = make_data_rloc(src - (u8 *)addr, - get_rloc_offs(*(u32 *)dest)); + *(u32 *)dest = make_data_rloc(ret, get_rloc_offs(*(u32 *)dest)); } } NOKPROBE_SYMBOL(FETCH_FUNC_NAME(memory, string)); |