2021-04-21 10:34:59

by Dan Carpenter

Subject: [PATCH 1/2] ataflop: potential out of bounds in do_format()

The function uses "type" as an array index:

q = unit[drive].disk[type]->queue;

Unfortunately the bounds check on "type" isn't done until later in the
function. Fix this by moving the bounds check to the start.

Fixes: bf9c0538e485 ("ataflop: use a separate gendisk for each media format")
Reported-by: kernel test robot <[email protected]>
Signed-off-by: Dan Carpenter <[email protected]>
---
drivers/block/ataflop.c | 11 +++++------
1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c
index 104b713f4055..aed2c2a4f4ea 100644
--- a/drivers/block/ataflop.c
+++ b/drivers/block/ataflop.c
@@ -729,8 +729,12 @@ static int do_format(int drive, int type, struct atari_format_descr *desc)
unsigned long flags;
int ret;

- if (type)
+ if (type) {
type--;
+ if (type >= NUM_DISK_MINORS ||
+ minor2disktype[type].drive_types > DriveType)
+ return -EINVAL;
+ }

q = unit[drive].disk[type]->queue;
blk_mq_freeze_queue(q);
@@ -742,11 +746,6 @@ static int do_format(int drive, int type, struct atari_format_descr *desc)
local_irq_restore(flags);

if (type) {
- if (type >= NUM_DISK_MINORS ||
- minor2disktype[type].drive_types > DriveType) {
- ret = -EINVAL;
- goto out;
- }
type = minor2disktype[type].index;
UDT = &atari_disk_type[type];
}
--
2.30.2

2021-04-21 10:35:13

by Dan Carpenter

Subject: [PATCH 2/2] ataflop: fix off by one in ataflop_probe()

Smatch complains that the "type > NUM_DISK_MINORS" should be >=
instead of >. We also need to subtract one from "type" at the start.

Fixes: bf9c0538e485 ("ataflop: use a separate gendisk for each media format")
Reported-by: kernel test robot <[email protected]>
Signed-off-by: Dan Carpenter <[email protected]>
---
drivers/block/ataflop.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c
index aed2c2a4f4ea..d601e49f80e0 100644
--- a/drivers/block/ataflop.c
+++ b/drivers/block/ataflop.c
@@ -2001,7 +2001,10 @@ static void ataflop_probe(dev_t dev)
int drive = MINOR(dev) & 3;
int type = MINOR(dev) >> 2;

- if (drive >= FD_MAX_UNITS || type > NUM_DISK_MINORS)
+ if (type)
+ type--;
+
+ if (drive >= FD_MAX_UNITS || type >= NUM_DISK_MINORS)
return;
mutex_lock(&ataflop_probe_lock);
if (!unit[drive].disk[type]) {
--
2.30.2

2021-04-21 19:45:07

by Christoph Hellwig

Subject: Re: [PATCH 1/2] ataflop: potential out of bounds in do_format()

Looks good,

Reviewed-by: Christoph Hellwig <[email protected]>

2021-04-21 19:46:27

by Christoph Hellwig

Subject: Re: [PATCH 2/2] ataflop: fix off by one in ataflop_probe()

On Wed, Apr 21, 2021 at 01:19:45PM +0300, Dan Carpenter wrote:
> Smatch complains that the "type > NUM_DISK_MINORS" should be >=
> instead of >. We also need to subtract one from "type" at the start.
>
> Fixes: bf9c0538e485 ("ataflop: use a separate gendisk for each media format")
> Reported-by: kernel test robot <[email protected]>
> Signed-off-by: Dan Carpenter <[email protected]>

Looks good,

Reviewed-by: Christoph Hellwig <[email protected]>

2021-04-21 22:53:01

by Jens Axboe

Subject: Re: [PATCH 1/2] ataflop: potential out of bounds in do_format()

On 4/21/21 4:18 AM, Dan Carpenter wrote:
> The function uses "type" as an array index:
>
> q = unit[drive].disk[type]->queue;
>
> Unfortunately the bounds check on "type" isn't done until later in the
> function. Fix this by moving the bounds check to the start.

Applied this and 2/2, thanks Dan.

--
Jens Axboe