ath9k: fix OOB read ar9300_eeprom_restore_internal

[ 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@gmail.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/YM3xKsQJ0Hw2hjrc@Zekuns-MBP-16.fios-router.home
Signed-off-by: Sasha Levin <sashal@kernel.org>

diff --git a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c
index 76385834a7def376feac4d3a7c29c32c81823fbd..694a58b1e99505ae1947058be2f68a8d17b324c1 100644 (file)
--- a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c
+++ b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c
@@ -3346,7 +3346,8 @@ 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;