aboutsummaryrefslogtreecommitdiff
path: root/kernel/trace
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/trace')
-rw-r--r--kernel/trace/Kconfig1
-rw-r--r--kernel/trace/bpf_trace.c105
-rw-r--r--kernel/trace/ftrace.c22
-rw-r--r--kernel/trace/trace.c10
-rw-r--r--kernel/trace/trace.h19
-rw-r--r--kernel/trace/trace_events_filter.c8
-rw-r--r--kernel/trace/trace_events_hist.c13
-rw-r--r--kernel/trace/trace_kdb.c6
-rw-r--r--kernel/trace/trace_output.c2
-rw-r--r--kernel/trace/trace_uprobe.c15
10 files changed, 154 insertions, 47 deletions
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 5d965cef6c77..564e5fdb025f 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
#
# Architectures that offer an FUNCTION_TRACER implementation should
# select HAVE_FUNCTION_TRACER:
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index b496ffdf5f36..1c9a4745e596 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -410,8 +410,6 @@ 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)
@@ -442,24 +440,50 @@ __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map,
return perf_event_output(event, sd, regs);
}
+/*
+ * 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 = {
@@ -822,16 +846,48 @@ 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 = {
@@ -848,12 +904,18 @@ 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 = {
@@ -868,11 +930,17 @@ 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 = {
@@ -1297,7 +1365,8 @@ int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id,
}
#ifdef CONFIG_MODULES
-int bpf_event_notify(struct notifier_block *nb, unsigned long op, void *module)
+static int bpf_event_notify(struct notifier_block *nb, unsigned long op,
+ void *module)
{
struct bpf_trace_module *btm, *tmp;
struct module *mod = module;
@@ -1336,7 +1405,7 @@ static struct notifier_block bpf_module_nb = {
.notifier_call = bpf_event_notify,
};
-int __init bpf_event_init(void)
+static int __init bpf_event_init(void)
{
register_module_notifier(&bpf_module_nb);
return 0;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index a12aff849c04..38277af44f5c 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -34,6 +34,7 @@
#include <linux/hash.h>
#include <linux/rcupdate.h>
#include <linux/kprobes.h>
+#include <linux/memory.h>
#include <trace/events/sched.h>
@@ -2610,10 +2611,12 @@ static void ftrace_run_update_code(int command)
{
int ret;
+ mutex_lock(&text_mutex);
+
ret = ftrace_arch_code_modify_prepare();
FTRACE_WARN_ON(ret);
if (ret)
- return;
+ goto out_unlock;
/*
* By default we use stop_machine() to modify the code.
@@ -2625,6 +2628,9 @@ static void ftrace_run_update_code(int command)
ret = ftrace_arch_code_modify_post_process();
FTRACE_WARN_ON(ret);
+
+out_unlock:
+ mutex_unlock(&text_mutex);
}
static void ftrace_run_modify_code(struct ftrace_ops *ops, int command,
@@ -2935,14 +2941,13 @@ 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++;
}
@@ -4221,10 +4226,13 @@ 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) {
@@ -5776,6 +5784,7 @@ void ftrace_module_enable(struct module *mod)
struct ftrace_page *pg;
mutex_lock(&ftrace_lock);
+ mutex_lock(&text_mutex);
if (ftrace_disabled)
goto out_unlock;
@@ -5837,6 +5846,7 @@ void ftrace_module_enable(struct module *mod)
ftrace_arch_code_modify_post_process();
out_unlock:
+ mutex_unlock(&text_mutex);
mutex_unlock(&ftrace_lock);
process_cached_mods(mod->name);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 2c92b3d9ea30..83e08b78dbee 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -6923,7 +6923,7 @@ struct tracing_log_err {
static DEFINE_MUTEX(tracing_err_log_lock);
-struct tracing_log_err *get_tracing_log_err(struct trace_array *tr)
+static struct tracing_log_err *get_tracing_log_err(struct trace_array *tr)
{
struct tracing_log_err *err;
@@ -8192,7 +8192,7 @@ static const struct file_operations buffer_percent_fops = {
.llseek = default_llseek,
};
-struct dentry *trace_instance_dir;
+static struct dentry *trace_instance_dir;
static void
init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer);
@@ -8910,12 +8910,8 @@ 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 1974ce818ddb..005f08629b8b 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -15,7 +15,6 @@
#include <linux/trace_seq.h>
#include <linux/trace_events.h>
#include <linux/compiler.h>
-#include <linux/trace_seq.h>
#include <linux/glob.h>
#ifdef CONFIG_FTRACE_SYSCALLS
@@ -1967,4 +1966,22 @@ 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_events_filter.c b/kernel/trace/trace_events_filter.c
index d3e59312ef40..5079d1db3754 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -428,7 +428,7 @@ predicate_parse(const char *str, int nr_parens, int nr_preds,
op_stack = kmalloc_array(nr_parens, sizeof(*op_stack), GFP_KERNEL);
if (!op_stack)
return ERR_PTR(-ENOMEM);
- prog_stack = kmalloc_array(nr_preds, sizeof(*prog_stack), GFP_KERNEL);
+ prog_stack = kcalloc(nr_preds, sizeof(*prog_stack), GFP_KERNEL);
if (!prog_stack) {
parse_error(pe, -ENOMEM, 0);
goto out_free;
@@ -579,7 +579,11 @@ predicate_parse(const char *str, int nr_parens, int nr_preds,
out_free:
kfree(op_stack);
kfree(inverts);
- kfree(prog_stack);
+ if (prog_stack) {
+ for (i = 0; prog_stack[i].pred; i++)
+ kfree(prog_stack[i].pred);
+ kfree(prog_stack);
+ }
return ERR_PTR(ret);
}
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 7fca3457c705..ca6b0dff60c5 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -59,7 +59,7 @@
C(NO_CLOSING_PAREN, "No closing paren found"), \
C(SUBSYS_NOT_FOUND, "Missing subsystem"), \
C(INVALID_SUBSYS_EVENT, "Invalid subsystem or event name"), \
- C(INVALID_REF_KEY, "Using variable references as keys not supported"), \
+ C(INVALID_REF_KEY, "Using variable references in keys not supported"), \
C(VAR_NOT_FOUND, "Couldn't find variable"), \
C(FIELD_NOT_FOUND, "Couldn't find field"),
@@ -1854,6 +1854,9 @@ 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];
@@ -3582,14 +3585,20 @@ static bool cond_snapshot_update(struct trace_array *tr, void *cond_data)
struct track_data *track_data = tr->cond_snapshot->cond_data;
struct hist_elt_data *elt_data, *track_elt_data;
struct snapshot_context *context = cond_data;
+ struct action_data *action;
u64 track_val;
if (!track_data)
return false;
+ action = track_data->action_data;
+
track_val = get_track_val(track_data->hist_data, context->elt,
track_data->action_data);
+ if (!action->track_data.check_val(track_data->track_val, track_val))
+ return false;
+
track_data->track_val = track_val;
memcpy(track_data->key, context->key, track_data->key_len);
@@ -4503,7 +4512,7 @@ static int create_key_field(struct hist_trigger_data *hist_data,
goto out;
}
- if (hist_field->flags & HIST_FIELD_FL_VAR_REF) {
+ if (field_has_hist_vars(hist_field, 0)) {
hist_err(tr, HIST_ERR_INVALID_REF_KEY, errpos(field_str));
destroy_hist_field(hist_field, 0);
ret = -EINVAL;
diff --git a/kernel/trace/trace_kdb.c b/kernel/trace/trace_kdb.c
index 6c1ae6b752d1..cca65044c14c 100644
--- a/kernel/trace/trace_kdb.c
+++ b/kernel/trace/trace_kdb.c
@@ -37,12 +37,8 @@ static void ftrace_dump_buf(int skip_entries, long cpu_file)
if (skip_entries)
kdb_printf("(skipping %d entries)\n", skip_entries);
- /* 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) {
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 54373d93e251..ba751f993c3b 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -1057,7 +1057,7 @@ static enum print_line_t trace_stack_print(struct trace_iterator *iter,
trace_seq_puts(s, "<stack trace>\n");
- for (p = field->caller; p && *p != ULONG_MAX && p < end; p++) {
+ for (p = field->caller; p && p < end && *p != ULONG_MAX; p++) {
if (trace_seq_has_overflowed(s))
break;
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index eb7e06b54741..b55906c77ce0 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -426,8 +426,6 @@ end:
/*
* Argument syntax:
* - Add uprobe: p|r[:[GRP/]EVENT] PATH:OFFSET [FETCHARGS]
- *
- * - Remove uprobe: -:[GRP/]EVENT
*/
static int trace_uprobe_create(int argc, const char **argv)
{
@@ -443,10 +441,17 @@ static int trace_uprobe_create(int argc, const char **argv)
ret = 0;
ref_ctr_offset = 0;
- /* argc must be >= 1 */
- if (argv[0][0] == 'r')
+ switch (argv[0][0]) {
+ case 'r':
is_return = true;
- else if (argv[0][0] != 'p' || argc < 2)
+ break;
+ case 'p':
+ break;
+ default:
+ return -ECANCELED;
+ }
+
+ if (argc < 2)
return -ECANCELED;
if (argv[0][1] == ':')
Powered by cgit, Gruvboxed by Blaster4385.