[for-linus][PATCH 15/20] tracing: Fix memory corruption from the histogram stacktrace modifier

[Steven Rostedt]

From: Donggeun Yoo <donggeunyoo.kernel@xxxxxxxxx>

parse_field() sets HIST_FIELD_FL_STACKTRACE from the ".stacktrace"
modifier before it looks the field name up, and nothing afterwards
checks that the name resolved to a field which holds a stacktrace.
create_hist_field() picks HIST_FIELD_FN_STACK on the strength of the
field pointer alone, which reads a __data_loc word from the record and
follows its low 16 bits as an offset into the same record.
event_hist_trigger() takes the first word there as an entry count and
copies that many longs into a 31 entry array:

	n_entries = *stack;
	memcpy(entries, ++stack, n_entries * sizeof(unsigned long));

Neither end of that copy is bounded, and the count is whatever the event
holds at the offset, so any field will do:

  # cd /sys/kernel/tracing/events/sched/sched_process_fork
  # echo 'hist:keys=parent_pid.stacktrace' > trigger
  # (true)

  BUG: kernel NULL pointer dereference, address: 0000000000000008
  RIP: 0010:rb_insert_color+0x18/0x130
   timerqueue_linked_add+0x7e/0xd0
   enqueue_hrtimer+0x39/0xb0
   __hrtimer_run_queues+0x10f/0x1f0
   </IRQ>
  RIP: 0010:memcpy+0xc/0x30
   event_hist_trigger+0x165/0x690

The timer interrupt landed on the rbtree the copy had already run over.
No debug options are needed for this; KASAN reports the same write as an
out-of-bounds read of 13835058055416381440 bytes.

Documentation/trace/histogram.rst already states the rule, "must be a
long[] type", so enforce it once the name has been resolved. Names which
resolve to no field at all, "hitcount.stacktrace" and the common_*
pseudo-fields, are refused for the same reason: they hold no stacktrace
to read.

Cc: stable@xxxxxxxxxxxxxxx
Fixes: cc5fc8bfc961 ("tracing/histogram: Add stacktrace type")
Link: https://patch.msgid.link/20260907155045.692664-2-donggeunyoo.kernel@xxxxxxxxx
Signed-off-by: Donggeun Yoo <donggeunyoo.kernel@xxxxxxxxx>
Signed-off-by: Steven Rostedt <rostedt@xxxxxxxxxxx>
---
 kernel/trace/trace_events_hist.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 53100287466f..9bc829c1e876 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -2317,6 +2317,7 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file,
 	struct ftrace_event_field *field = NULL;
 	char *field_name, *modifier, *str;
 	struct trace_array *tr = file->tr;
+	bool stack_modifier = false;
 
 	modifier = str = kstrdup(field_str, GFP_KERNEL);
 	if (!modifier)
@@ -2339,9 +2340,10 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file,
 			*flags |= HIST_FIELD_FL_EXECNAME;
 		else if (strcmp(modifier, "syscall") == 0)
 			*flags |= HIST_FIELD_FL_SYSCALL;
-		else if (strcmp(modifier, "stacktrace") == 0)
+		else if (strcmp(modifier, "stacktrace") == 0) {
 			*flags |= HIST_FIELD_FL_STACKTRACE;
-		else if (strcmp(modifier, "log2") == 0)
+			stack_modifier = true;
+		} else if (strcmp(modifier, "log2") == 0)
 			*flags |= HIST_FIELD_FL_LOG2;
 		else if (strcmp(modifier, "usecs") == 0)
 			*flags |= HIST_FIELD_FL_TIMESTAMP_USECS;
@@ -2412,6 +2414,12 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file,
 			}
 		}
 	}
+
+	if (stack_modifier &&
+	    (!field || field->filter_type != FILTER_STACKTRACE)) {
+		hist_err(tr, HIST_ERR_BAD_FIELD_MODIFIER, errpos(field_str));
+		field = ERR_PTR(-EINVAL);
+	}
  out:
 	kfree(str);
 
-- 
2.53.0