diff options
Diffstat (limited to 'kernel/trace')
-rw-r--r-- | kernel/trace/Kconfig | 2 | ||||
-rw-r--r-- | kernel/trace/blktrace.c | 10 | ||||
-rw-r--r-- | kernel/trace/bpf_trace.c | 63 | ||||
-rw-r--r-- | kernel/trace/trace_kprobe.c | 20 | ||||
-rw-r--r-- | kernel/trace/trace_sched_switch.c | 2 | ||||
-rw-r--r-- | kernel/trace/trace_sched_wakeup.c | 2 | ||||
-rw-r--r-- | kernel/trace/trace_uprobe.c | 22 |
7 files changed, 92 insertions, 29 deletions
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 3b9a48ae153a..1153c43428f3 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -434,7 +434,7 @@ config UPROBE_EVENT config BPF_EVENTS depends on BPF_SYSCALL - depends on KPROBE_EVENT + depends on KPROBE_EVENT || UPROBE_EVENT bool default y help diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index b3e6b39b6cf9..90e72a0c3047 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -778,9 +778,6 @@ static void blk_add_trace_bio(struct request_queue *q, struct bio *bio, if (likely(!bt)) return; - if (!error && !bio_flagged(bio, BIO_UPTODATE)) - error = EIO; - __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, bio->bi_rw, what, error, 0, NULL); } @@ -887,8 +884,7 @@ static void blk_add_trace_split(void *ignore, __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, bio->bi_rw, BLK_TA_SPLIT, - !bio_flagged(bio, BIO_UPTODATE), - sizeof(rpdu), &rpdu); + bio->bi_error, sizeof(rpdu), &rpdu); } } @@ -920,8 +916,8 @@ static void blk_add_trace_bio_remap(void *ignore, r.sector_from = cpu_to_be64(from); __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, - bio->bi_rw, BLK_TA_REMAP, - !bio_flagged(bio, BIO_UPTODATE), sizeof(r), &r); + bio->bi_rw, BLK_TA_REMAP, bio->bi_error, + sizeof(r), &r); } /** diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 88a041adee90..0fe96c7c8803 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 b7d0cdd9906c..c9956440d0e6 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)); diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c index 419ca37e72c9..f270088e9929 100644 --- a/kernel/trace/trace_sched_switch.c +++ b/kernel/trace/trace_sched_switch.c @@ -26,7 +26,7 @@ probe_sched_switch(void *ignore, struct task_struct *prev, struct task_struct *n } static void -probe_sched_wakeup(void *ignore, struct task_struct *wakee, int success) +probe_sched_wakeup(void *ignore, struct task_struct *wakee) { if (unlikely(!sched_ref)) return; diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 9b33dd117f3f..12cbe77b4136 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -514,7 +514,7 @@ static void wakeup_reset(struct trace_array *tr) } static void -probe_wakeup(void *ignore, struct task_struct *p, int success) +probe_wakeup(void *ignore, struct task_struct *p) { struct trace_array_cpu *data; int cpu = smp_processor_id(); diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index aa1ea7b36fa8..d2f6d0be3503 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -601,7 +601,22 @@ static int probes_seq_show(struct seq_file *m, void *v) seq_printf(m, "%c:%s/%s", c, tu->tp.call.class->system, trace_event_name(&tu->tp.call)); - seq_printf(m, " %s:0x%p", tu->filename, (void *)tu->offset); + seq_printf(m, " %s:", tu->filename); + + /* Don't print "0x (null)" when offset is 0 */ + if (tu->offset) { + seq_printf(m, "0x%p", (void *)tu->offset); + } else { + switch (sizeof(void *)) { + case 4: + seq_printf(m, "0x00000000"); + break; + case 8: + default: + seq_printf(m, "0x0000000000000000"); + break; + } + } for (i = 0; i < tu->tp.nr_args; i++) seq_printf(m, " %s=%s", tu->tp.args[i].name, tu->tp.args[i].comm); @@ -1095,11 +1110,15 @@ static void __uprobe_perf_func(struct trace_uprobe *tu, { struct trace_event_call *call = &tu->tp.call; struct uprobe_trace_entry_head *entry; + struct bpf_prog *prog = call->prog; struct hlist_head *head; void *data; int size, esize; int rctx; + if (prog && !trace_call_bpf(prog, regs)) + return; + esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); size = esize + tu->tp.size + dsize; @@ -1289,6 +1308,7 @@ static int register_uprobe_event(struct trace_uprobe *tu) return -ENODEV; } + call->flags = TRACE_EVENT_FL_UPROBE; call->class->reg = trace_uprobe_register; call->data = tu; ret = trace_add_event_call(call); |