Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Zheng Yejian <zhengyejian1@huawei.com>
To:     <rostedt@goodmis.org>, <mhiramat@kernel.org>, <zanussi@kernel.org>
CC:     <linux-kernel@vger.kernel.org>,
        <linux-trace-kernel@vger.kernel.org>, <zhengyejian1@huawei.com>
Subject: [PATCH] tracing/hist: Fix out-of-bound write on 'action_data.var_ref_idx'
Date:   Wed, 7 Dec 2022 11:51:43 +0800
Message-ID: <20221207035143.2278781-1-zhengyejian1@huawei.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 7BIT
Content-Type:   text/plain; charset=US-ASCII
Precedence: bulk

When generate a synthetic event with many params and then create a trace
action for it [1], kernel panic happened [2].

It is because that in trace_action_create() 'data->n_params' is up to
SYNTH_FIELDS_MAX (current value is 64), and array 'data->var_ref_idx'
keeps indices into array 'hist_data->var_refs' for each synthetic event
param, but the length of 'data->var_ref_idx' is TRACING_MAP_VARS_MAX
(current value is 16), so out-of-bound write happened when 'data->n_params'
more than 16. In this case, 'data->match_data.event' is overwritten and
eventually cause the panic.

To solve the issue, adjust the length of 'data->var_ref_idx' to be
SYNTH_FIELDS_MAX and add sanity checks to avoid out-of-bound write.

[1]
 # cd /sys/kernel/tracing/
 # echo "my_synth_event int v1; int v2; int v3; int v4; int v5; int v6;\
int v7; int v8; int v9; int v10; int v11; int v12; int v13; int v14;\
int v15; int v16; int v17; int v18; int v19; int v20; int v21; int v22;\
int v23; int v24; int v25; int v26; int v27; int v28; int v29; int v30;\
int v31; int v32; int v33; int v34; int v35; int v36; int v37; int v38;\
int v39; int v40; int v41; int v42; int v43; int v44; int v45; int v46;\
int v47; int v48; int v49; int v50; int v51; int v52; int v53; int v54;\
int v55; int v56; int v57; int v58; int v59; int v60; int v61; int v62;\
int v63" >> synthetic_events
 # echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="bash"' >> \
events/sched/sched_waking/trigger
 # echo "hist:keys=next_pid:onmatch(sched.sched_waking).my_synth_event(\
pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,\
pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,\
pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,\
pid,pid,pid,pid,pid,pid,pid,pid,pid)" >> events/sched/sched_switch/trigger

[2]
BUG: unable to handle page fault for address: ffff91c900000000
PGD 61001067 P4D 61001067 PUD 0
Oops: 0000 [#1] PREEMPT SMP NOPTI
CPU: 2 PID: 322 Comm: bash Tainted: G        W          6.1.0-rc8+ #229
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS
rel-1.15.0-0-g2dd4b9b3f840-prebuilt.qemu.org 04/01/2014
RIP: 0010:strcmp+0xc/0x30
Code: 75 f7 31 d2 44 0f b6 04 16 44 88 04 11 48 83 c2 01 45 84 c0 75 ee
c3 cc cc cc cc 0f 1f 00 31 c0 eb 08 48 83 c0 01 84 d2 74 13 <0f> b6 14
07 3a 14 06 74 ef 19 c0 83 c8 01 c3 cc cc cc cc 31 c3
RSP: 0018:ffff9b3b00f53c48 EFLAGS: 00000246
RAX: 0000000000000000 RBX: ffffffffba958a68 RCX: 0000000000000000
RDX: 0000000000000010 RSI: ffff91c943d33a90 RDI: ffff91c900000000
RBP: ffff91c900000000 R08: 00000018d604b529 R09: 0000000000000000
R10: ffff91c9483eddb1 R11: ffff91ca483eddab R12: ffff91c946171580
R13: ffff91c9479f0538 R14: ffff91c9457c2848 R15: ffff91c9479f0538
FS:  00007f1d1cfbe740(0000) GS:ffff91c9bdc80000(0000)
knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: ffff91c900000000 CR3: 0000000006316000 CR4: 00000000000006e0
Call Trace:
 <TASK>
 __find_event_file+0x55/0x90
 action_create+0x76c/0x1060
 event_hist_trigger_parse+0x146d/0x2060
 ? event_trigger_write+0x31/0xd0
 trigger_process_regex+0xbb/0x110
 event_trigger_write+0x6b/0xd0
 vfs_write+0xc8/0x3e0
 ? alloc_fd+0xc0/0x160
 ? preempt_count_add+0x4d/0xa0
 ? preempt_count_add+0x70/0xa0
 ksys_write+0x5f/0xe0
 do_syscall_64+0x3b/0x90
 entry_SYSCALL_64_after_hwframe+0x63/0xcd
RIP: 0033:0x7f1d1d0cf077
Code: 64 89 02 48 c7 c0 ff ff ff ff eb bb 0f 1f 80 00 00 00 00 f3 0f 1e
fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 01 00 00 00 0f 05 <48> 3d 00
f0 ff ff 77 51 c3 48 83 ec 28 48 89 54 24 18 48 89 74
RSP: 002b:00007ffcebb0e568 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 0000000000000143 RCX: 00007f1d1d0cf077
RDX: 0000000000000143 RSI: 00005639265aa7e0 RDI: 0000000000000001
RBP: 00005639265aa7e0 R08: 000000000000000a R09: 0000000000000142
R10: 000056392639c017 R11: 0000000000000246 R12: 0000000000000143
R13: 00007f1d1d1ae6a0 R14: 00007f1d1d1aa4a0 R15: 00007f1d1d1a98a0
 </TASK>
Modules linked in:
CR2: ffff91c900000000
---[ end trace 0000000000000000 ]---
RIP: 0010:strcmp+0xc/0x30
Code: 75 f7 31 d2 44 0f b6 04 16 44 88 04 11 48 83 c2 01 45 84 c0 75 ee
c3 cc cc cc cc 0f 1f 00 31 c0 eb 08 48 83 c0 01 84 d2 74 13 <0f> b6 14
07 3a 14 06 74 ef 19 c0 83 c8 01 c3 cc cc cc cc 31 c3
RSP: 0018:ffff9b3b00f53c48 EFLAGS: 00000246
RAX: 0000000000000000 RBX: ffffffffba958a68 RCX: 0000000000000000
RDX: 0000000000000010 RSI: ffff91c943d33a90 RDI: ffff91c900000000
RBP: ffff91c900000000 R08: 00000018d604b529 R09: 0000000000000000
R10: ffff91c9483eddb1 R11: ffff91ca483eddab R12: ffff91c946171580
R13: ffff91c9479f0538 R14: ffff91c9457c2848 R15: ffff91c9479f0538
FS:  00007f1d1cfbe740(0000) GS:ffff91c9bdc80000(0000)
knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: ffff91c900000000 CR3: 0000000006316000 CR4: 00000000000006e0

Cc: stable@vger.kernel.org
Fixes: d380dcde9a07 ("tracing: Fix now invalid var_ref_vals assumption in trace action")
Signed-off-by: Zheng Yejian <zhengyejian1@huawei.com>
---
 kernel/trace/trace_events_hist.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 1c82478e8dff..0a11671af952 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -617,7 +617,7 @@ struct action_data {
 	 * event param, and is passed to the synthetic event
 	 * invocation.
 	 */
-	unsigned int		var_ref_idx[TRACING_MAP_VARS_MAX];
+	unsigned int		var_ref_idx[SYNTH_FIELDS_MAX];
 	struct synth_event	*synth_event;
 	bool			use_trace_keyword;
 	char			*synth_event_name;
@@ -2173,7 +2173,9 @@ static struct hist_field *create_var_ref(struct hist_trigger_data *hist_data,
 			return ref_field;
 		}
 	}
-
+	/* Sanity check to avoid out-of-bound write on 'hist_data->var_refs' */
+	if (hist_data->n_var_refs >= TRACING_MAP_VARS_MAX)
+		return NULL;
 	ref_field = create_hist_field(var_field->hist_data, NULL, flags, NULL);
 	if (ref_field) {
 		if (init_var_ref(ref_field, var_field, system, event_name)) {
@@ -3922,6 +3924,10 @@ static int trace_action_create(struct hist_trigger_data *hist_data,
 
 	lockdep_assert_held(&event_mutex);
 
+	/* Sanity check to avoid out-of-bound write on 'data->var_ref_idx' */
+	if (data->n_params > SYNTH_FIELDS_MAX)
+		return -EINVAL;
+
 	if (data->use_trace_keyword)
 		synth_event_name = data->synth_event_name;
 	else
-- 
2.25.1