ath9k: fix OOB read ar9300_eeprom_restore_internal

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

diff --git a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c
index b4885a7..b0a4ca3 100644 (file)
--- a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c
+++ b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c
@@ -3351,7 +3351,8 @@ found:
                        "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;