dvb-usb: reading before start of array
Subsystems (2)
This is a static checker fix. In the ttusb_process_muxpack() we do:
cc = (muxpack[len - 4] << 8) | muxpack[len - 3];
That means if we pass a number less than 4 then we will either trigger a checksum error message or read before the start of the array.
---
I can't test this.
This patch doesn't introduce any bugs, but I'm not positive this is the right thing to do. Perhaps it's better to print an error message?
drivers/media/usb/ttusb-budget/dvb-ttusb-budget.c +1 -1
@@ -709,7 +709,7 @@ static void ttusb_process_frame(struct ttusb *ttusb, u8 * data, int len)* if length is valid and we reached the end: * goto next muxpack */ -if ((ttusb->muxpack_ptr >=2 ) && +if ((ttusb->muxpack_ptr >=4 ) && (ttusb->muxpack_ptr = ttusb->muxpack_len)) { ttusb_process_muxpack(ttusb,
Em Wed, 9 Jan 2013 10:36:32 +0300
Dan Carpenter <[email protected]> escreveu:
Quoted 7 lines
This is a static checker fix. In the
ttusb_process_muxpack()we do:cc = (muxpack[len - 4] << 8) | muxpack[len - 3];That means if we pass a number less than 4 then we will either trigger a checksum error message or read before the start of the array.
Quoted 6 lines
Signed-off-by Dan Carpenter <[email protected]>---
I can't test this.This patch doesn't introduce any bugs, but I'm not positive this is the right thing to do. Perhaps it's better to print an error message?
I don't have any ttusb device either, but i suspect that printing an error message inside ttusb_process_muxpack() would be better.
From what I understood, this code gets the URB data and groups it into one TS packet (188 bytes, typically). Then, it calls ttusb_process_muxpack() in order to handle it.
So, the normal condition would be to always receive 188 bytes here (usual TS packet size), except if there's something wrong with the URB transfer.
It seems, however, that there are other issues at the logic at ttusb_process_muxpack().
For example, from this code snippet:
for (i = 0; i < len; i += 2)
csum ^= le16_to_cpup((__le16 *) (muxpack + i));an odd value for len also seems to cause troubles at this logic.
so, IMHO, the better would be to print a warning if the value is odd or smaller than 4, and discard it.
Quoted 18 lines
drivers/media/usb/ttusb-budget/dvb-ttusb-budget.c +1
-2@@ -709,7 +709,7 @@ static void ttusb_process_frame(struct ttusb *ttusb, u8 * data, int len)* if length is valid and we reached the end: * goto next muxpack */ -if ((ttusb->muxpack_ptr >=2 ) && +if ((ttusb->muxpack_ptr >=4 ) && (ttusb->muxpack_ptr = ttusb->muxpack_len)) { ttusb_process_muxpack(ttusb, --To unsubscribe from this list: send the line "unsubscribe linux-media" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Signature · 2 lines
Cheers, Mauro
PATCH v2 1/1 dvb-usb: check for invalid length in ttusb_process_muxpack()
This patch is driven by a static checker warning.
The ttusb_process_muxpack() function is only called from ttusb_process_frame(). Before calling, it verifies that len >= 2. The problem is that len = 2 is not valid and would lead to an array underflow.
Odd number values for len are also invalid and would lead to reading past the end of the array.
---
v2: Moved the check from the caller into the function. Added a check for odd values. Added an error message. Increment the numinvalid counter.
drivers/media/usb/ttusb-budget/dvb-ttusb-budget.c +7 -0
@@ -561,6 +561,13 @@ static void ttusb_process_muxpack(struct ttusb *ttusb, const u8 * muxpack, {u16 csum =0 , cc;int i; + +if (len <4 || len &0x1 ) { +pr_warn ("%s: muxpack has invalid len %d\n" , __func__, len); + numinvalid++; +return ; + } +for (i =0 ; i < len; i +=2 ) csum ^=le16_to_cpup ((__le16 *) (muxpack + i));if (csum) {