diff mbox series

[2/2] wifi: mac80211: fix UBSAN noise in ieee80211_prep_hw_scan()

Message ID 20240517153332.18271-2-dmantipov@yandex.ru
State New
Headers show
Series [1/2] wifi: cfg80211: use __counted_by where appropriate | expand

Commit Message

Dmitry Antipov May 17, 2024, 3:33 p.m. UTC
When testing the previous patch with CONFIG_UBSAN_BOUNDS, I've
noticed the following:

UBSAN: array-index-out-of-bounds in net/mac80211/scan.c:372:4
index 0 is out of range for type 'struct ieee80211_channel *[]'
CPU: 0 PID: 1435 Comm: wpa_supplicant Not tainted 6.9.0+ #1
Hardware name: LENOVO 20UN005QRT/20UN005QRT <...BIOS details...>
Call Trace:
 <TASK>
 dump_stack_lvl+0x2d/0x90
 __ubsan_handle_out_of_bounds+0xe7/0x140
 ? timerqueue_add+0x98/0xb0
 ieee80211_prep_hw_scan+0x2db/0x480 [mac80211]
 ? __kmalloc+0xe1/0x470
 __ieee80211_start_scan+0x541/0x760 [mac80211]
 rdev_scan+0x1f/0xe0 [cfg80211]
 nl80211_trigger_scan+0x9b6/0xae0 [cfg80211]
 ...<the rest is not too useful...>

Since '__ieee80211_start_scan()' leaves 'hw_scan_req->req.n_channels'
uninitialized, actual boundaries of 'hw_scan_req->req.channels' can't
be checked in 'ieee80211_prep_hw_scan()'. Although an initialization
of 'hw_scan_req->req.n_channels' introduces some confusion around
allocated vs. used VLA members, this shouldn't be a problem since
everything is correctly adjusted soon in 'ieee80211_prep_hw_scan()'.

Cleanup 'kmalloc()' math in '__ieee80211_start_scan()' by using the
convenient 'struct_size()' as well.

Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
---
 net/mac80211/scan.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)
diff mbox series

Patch

diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index 3da1c5c45035..ab2a11a02673 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -745,14 +745,19 @@  static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata,
 		}
 
 		local->hw_scan_req = kmalloc(
-				sizeof(*local->hw_scan_req) +
-				req->n_channels * sizeof(req->channels[0]) +
-				local->hw_scan_ies_bufsize, GFP_KERNEL);
+			(struct_size(local->hw_scan_req,
+				     req.channels, req->n_channels)
+			 + local->hw_scan_ies_bufsize), GFP_KERNEL);
 		if (!local->hw_scan_req)
 			return -ENOMEM;
 
 		local->hw_scan_req->req.ssids = req->ssids;
 		local->hw_scan_req->req.n_ssids = req->n_ssids;
+		/* None of the channels are actually set
+		 * up but let UBSAN know the boundaries.
+		 */
+		local->hw_scan_req->req.n_channels = req->n_channels;
+
 		ies = (u8 *)local->hw_scan_req +
 			sizeof(*local->hw_scan_req) +
 			req->n_channels * sizeof(req->channels[0]);