diff options
Diffstat (limited to 'kernel/trace')
-rw-r--r-- | kernel/trace/bpf_trace.c | 100 | ||||
-rw-r--r-- | kernel/trace/ftrace.c | 12 | ||||
-rw-r--r-- | kernel/trace/trace.c | 16 | ||||
-rw-r--r-- | kernel/trace/trace.h | 18 | ||||
-rw-r--r-- | kernel/trace/trace_branch.c | 4 | ||||
-rw-r--r-- | kernel/trace/trace_events_hist.c | 3 | ||||
-rw-r--r-- | kernel/trace/trace_kdb.c | 6 |
7 files changed, 120 insertions, 39 deletions
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 6c28d519447d..83c4e76f513a 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -365,8 +365,6 @@ static const struct bpf_func_proto bpf_perf_event_read_value_proto = { .arg4_type = ARG_CONST_SIZE, }; -static DEFINE_PER_CPU(struct perf_sample_data, bpf_trace_sd); - static __always_inline u64 __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map, u64 flags, struct perf_sample_data *sd) @@ -398,24 +396,50 @@ __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map, return 0; } +/* + * Support executing tracepoints in normal, irq, and nmi context that each call + * bpf_perf_event_output + */ +struct bpf_trace_sample_data { + struct perf_sample_data sds[3]; +}; + +static DEFINE_PER_CPU(struct bpf_trace_sample_data, bpf_trace_sds); +static DEFINE_PER_CPU(int, bpf_trace_nest_level); BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map, u64, flags, void *, data, u64, size) { - struct perf_sample_data *sd = this_cpu_ptr(&bpf_trace_sd); + struct bpf_trace_sample_data *sds = this_cpu_ptr(&bpf_trace_sds); + int nest_level = this_cpu_inc_return(bpf_trace_nest_level); struct perf_raw_record raw = { .frag = { .size = size, .data = data, }, }; + struct perf_sample_data *sd; + int err; - if (unlikely(flags & ~(BPF_F_INDEX_MASK))) - return -EINVAL; + if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(sds->sds))) { + err = -EBUSY; + goto out; + } + + sd = &sds->sds[nest_level - 1]; + + if (unlikely(flags & ~(BPF_F_INDEX_MASK))) { + err = -EINVAL; + goto out; + } perf_sample_data_init(sd, 0, 0); sd->raw = &raw; - return __bpf_perf_event_output(regs, map, flags, sd); + err = __bpf_perf_event_output(regs, map, flags, sd); + +out: + this_cpu_dec(bpf_trace_nest_level); + return err; } static const struct bpf_func_proto bpf_perf_event_output_proto = { @@ -772,16 +796,48 @@ pe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) /* * bpf_raw_tp_regs are separate from bpf_pt_regs used from skb/xdp * to avoid potential recursive reuse issue when/if tracepoints are added - * inside bpf_*_event_output, bpf_get_stackid and/or bpf_get_stack + * inside bpf_*_event_output, bpf_get_stackid and/or bpf_get_stack. + * + * Since raw tracepoints run despite bpf_prog_active, support concurrent usage + * in normal, irq, and nmi context. */ -static DEFINE_PER_CPU(struct pt_regs, bpf_raw_tp_regs); +struct bpf_raw_tp_regs { + struct pt_regs regs[3]; +}; +static DEFINE_PER_CPU(struct bpf_raw_tp_regs, bpf_raw_tp_regs); +static DEFINE_PER_CPU(int, bpf_raw_tp_nest_level); +static struct pt_regs *get_bpf_raw_tp_regs(void) +{ + struct bpf_raw_tp_regs *tp_regs = this_cpu_ptr(&bpf_raw_tp_regs); + int nest_level = this_cpu_inc_return(bpf_raw_tp_nest_level); + + if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(tp_regs->regs))) { + this_cpu_dec(bpf_raw_tp_nest_level); + return ERR_PTR(-EBUSY); + } + + return &tp_regs->regs[nest_level - 1]; +} + +static void put_bpf_raw_tp_regs(void) +{ + this_cpu_dec(bpf_raw_tp_nest_level); +} + BPF_CALL_5(bpf_perf_event_output_raw_tp, struct bpf_raw_tracepoint_args *, args, struct bpf_map *, map, u64, flags, void *, data, u64, size) { - struct pt_regs *regs = this_cpu_ptr(&bpf_raw_tp_regs); + struct pt_regs *regs = get_bpf_raw_tp_regs(); + int ret; + + if (IS_ERR(regs)) + return PTR_ERR(regs); perf_fetch_caller_regs(regs); - return ____bpf_perf_event_output(regs, map, flags, data, size); + ret = ____bpf_perf_event_output(regs, map, flags, data, size); + + put_bpf_raw_tp_regs(); + return ret; } static const struct bpf_func_proto bpf_perf_event_output_proto_raw_tp = { @@ -798,12 +854,18 @@ static const struct bpf_func_proto bpf_perf_event_output_proto_raw_tp = { BPF_CALL_3(bpf_get_stackid_raw_tp, struct bpf_raw_tracepoint_args *, args, struct bpf_map *, map, u64, flags) { - struct pt_regs *regs = this_cpu_ptr(&bpf_raw_tp_regs); + struct pt_regs *regs = get_bpf_raw_tp_regs(); + int ret; + + if (IS_ERR(regs)) + return PTR_ERR(regs); perf_fetch_caller_regs(regs); /* similar to bpf_perf_event_output_tp, but pt_regs fetched differently */ - return bpf_get_stackid((unsigned long) regs, (unsigned long) map, - flags, 0, 0); + ret = bpf_get_stackid((unsigned long) regs, (unsigned long) map, + flags, 0, 0); + put_bpf_raw_tp_regs(); + return ret; } static const struct bpf_func_proto bpf_get_stackid_proto_raw_tp = { @@ -818,11 +880,17 @@ static const struct bpf_func_proto bpf_get_stackid_proto_raw_tp = { BPF_CALL_4(bpf_get_stack_raw_tp, struct bpf_raw_tracepoint_args *, args, void *, buf, u32, size, u64, flags) { - struct pt_regs *regs = this_cpu_ptr(&bpf_raw_tp_regs); + struct pt_regs *regs = get_bpf_raw_tp_regs(); + int ret; + + if (IS_ERR(regs)) + return PTR_ERR(regs); perf_fetch_caller_regs(regs); - return bpf_get_stack((unsigned long) regs, (unsigned long) buf, - (unsigned long) size, flags, 0); + ret = bpf_get_stack((unsigned long) regs, (unsigned long) buf, + (unsigned long) size, flags, 0); + put_bpf_raw_tp_regs(); + return ret; } static const struct bpf_func_proto bpf_get_stack_proto_raw_tp = { diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 1688782f3dfb..118ecce14386 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -2952,14 +2952,13 @@ static int ftrace_update_code(struct module *mod, struct ftrace_page *new_pgs) p = &pg->records[i]; p->flags = rec_flags; -#ifndef CC_USING_NOP_MCOUNT /* * Do the initial record conversion from mcount jump * to the NOP instructions. */ - if (!ftrace_code_disable(mod, p)) + if (!__is_defined(CC_USING_NOP_MCOUNT) && + !ftrace_code_disable(mod, p)) break; -#endif update_cnt++; } @@ -4208,10 +4207,13 @@ void free_ftrace_func_mapper(struct ftrace_func_mapper *mapper, struct ftrace_func_entry *entry; struct ftrace_func_map *map; struct hlist_head *hhd; - int size = 1 << mapper->hash.size_bits; - int i; + int size, i; + + if (!mapper) + return; if (free_func && mapper->hash.count) { + size = 1 << mapper->hash.size_bits; for (i = 0; i < size; i++) { hhd = &mapper->hash.buckets[i]; hlist_for_each_entry(entry, hhd, hlist) { diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 2ce8428d0f45..f82da65109eb 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -6480,11 +6480,13 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, break; } #endif - if (!tr->allocated_snapshot) { + if (tr->allocated_snapshot) + ret = resize_buffer_duplicate_size(&tr->max_buffer, + &tr->trace_buffer, iter->cpu_file); + else ret = tracing_alloc_snapshot_instance(tr); - if (ret < 0) - break; - } + if (ret < 0) + break; local_irq_disable(); /* Now, we're going to swap */ if (iter->cpu_file == RING_BUFFER_ALL_CPUS) @@ -8360,12 +8362,8 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) cnt++; - /* reset all but tr, trace, and overruns */ - memset(&iter.seq, 0, - sizeof(struct trace_iterator) - - offsetof(struct trace_iterator, seq)); + trace_iterator_reset(&iter); iter.iter_flags |= TRACE_FILE_LAT_FMT; - iter.pos = -1; if (trace_find_next_entry_inc(&iter) != NULL) { int ret; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 65afd0c04622..6eba8c96f4bc 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1897,4 +1897,22 @@ static inline void tracer_hardirqs_off(unsigned long a0, unsigned long a1) { } extern struct trace_iterator *tracepoint_print_iter; +/* + * Reset the state of the trace_iterator so that it can read consumed data. + * Normally, the trace_iterator is used for reading the data when it is not + * consumed, and must retain state. + */ +static __always_inline void trace_iterator_reset(struct trace_iterator *iter) +{ + const size_t offset = offsetof(struct trace_iterator, seq); + + /* + * Keep gcc from complaining about overwriting more than just one + * member in the structure. + */ + memset((char *)iter + offset, 0, sizeof(struct trace_iterator) - offset); + + iter->pos = -1; +} + #endif /* _LINUX_KERNEL_TRACE_H */ diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c index 3ea65cdff30d..4ad967453b6f 100644 --- a/kernel/trace/trace_branch.c +++ b/kernel/trace/trace_branch.c @@ -205,8 +205,6 @@ void trace_likely_condition(struct ftrace_likely_data *f, int val, int expect) void ftrace_likely_update(struct ftrace_likely_data *f, int val, int expect, int is_constant) { - unsigned long flags = user_access_save(); - /* A constant is always correct */ if (is_constant) { f->constant++; @@ -225,8 +223,6 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, f->data.correct++; else f->data.incorrect++; - - user_access_restore(flags); } EXPORT_SYMBOL(ftrace_likely_update); diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 11853e90b649..3f34cfb66a85 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -1632,6 +1632,9 @@ static u64 hist_field_var_ref(struct hist_field *hist_field, struct hist_elt_data *elt_data; u64 var_val = 0; + if (WARN_ON_ONCE(!elt)) + return var_val; + elt_data = elt->private_data; var_val = elt_data->var_ref_vals[hist_field->var_ref_idx]; diff --git a/kernel/trace/trace_kdb.c b/kernel/trace/trace_kdb.c index 810d78a8d14c..2905a3dd94c1 100644 --- a/kernel/trace/trace_kdb.c +++ b/kernel/trace/trace_kdb.c @@ -41,12 +41,8 @@ static void ftrace_dump_buf(int skip_lines, long cpu_file) kdb_printf("Dumping ftrace buffer:\n"); - /* reset all but tr, trace, and overruns */ - memset(&iter.seq, 0, - sizeof(struct trace_iterator) - - offsetof(struct trace_iterator, seq)); + trace_iterator_reset(&iter); iter.iter_flags |= TRACE_FILE_LAT_FMT; - iter.pos = -1; if (cpu_file == RING_BUFFER_ALL_CPUS) { for_each_tracing_cpu(cpu) { |