From: Zekun Shen <bruceshenzk@xxxxxxxxx> [ Upstream commit 23151b9ae79e3bc4f6a0c4cd3a7f355f68dad128 ] Bad header can have large length field which can cause OOB. cptr is the last bytes for read, and the eeprom is parsed from high to low address. The OOB, triggered by the condition length > cptr could cause memory error with a read on negative index. There are some sanity check around length, but it is not compared with cptr (the remaining bytes). Here, the corrupted/bad EEPROM can cause panic. I was able to reproduce the crash, but I cannot find the log and the reproducer now. After I applied the patch, the bug is no longer reproducible. Signed-off-by: Zekun Shen <bruceshenzk@xxxxxxxxx> Signed-off-by: Kalle Valo <kvalo@xxxxxxxxxxxxxx> Link: https://lore.kernel.org/r/YM3xKsQJ0Hw2hjrc@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx> --- drivers/net/wireless/ath/ath9k/ar9003_eeprom.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c index b4885a700296..b0a4ca3559fd 100644 --- a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c +++ b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c @@ -3351,7 +3351,8 @@ static int ar9300_eeprom_restore_internal(struct ath_hw *ah, "Found block at %x: code=%d ref=%d length=%d major=%d minor=%d\n", cptr, code, reference, length, major, minor); if ((!AR_SREV_9485(ah) && length >= 1024) || - (AR_SREV_9485(ah) && length > EEPROM_DATA_LEN_9485)) { + (AR_SREV_9485(ah) && length > EEPROM_DATA_LEN_9485) || + (length > cptr)) { ath_dbg(common, EEPROM, "Skipping bad header\n"); cptr -= COMP_HDR_LEN; continue; -- 2.30.2
