On Sun, Nov 9, 2014 at 2:55 AM, Kevin Cernekee <cernekee@xxxxxxxxx> wrote:
> __earlycon_of_table_sentinel.compatible is a char[128], not a pointer, so
> it will never be NULL. Checking it against NULL causes the match loop to
> run past the end of the array, and eventually match a bogus entry, under
> the following conditions:
>
> - Kernel command line specifies "earlycon" with no parameters
> - DT has a stdout-path pointing to a UART node
> - The UART driver doesn't use OF_EARLYCON_DECLARE (or maybe the console
> driver is compiled out)
>
> Fix this by checking to see if match->compatible is a non-empty string.
>
> Signed-off-by: Kevin Cernekee <cernekee@xxxxxxxxx>
> Cc: <stable@xxxxxxxxxxxxxxx> # 3.16+
Thanks. I'll queue this up.
BTW, you should not add stable CC when submitting for review, but
rather add a note for the maintainer to apply to stable. Only if a
commit is in mainline already and not flagged for stable, then you
send the patch with the stable tag to get the commit added to stable.
It's a bit confusing...
Rob
> ---
> drivers/of/fdt.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
> index d1ffca8..30e97bc 100644
> --- a/drivers/of/fdt.c
> +++ b/drivers/of/fdt.c
> @@ -773,7 +773,7 @@ int __init early_init_dt_scan_chosen_serial(void)
> if (offset < 0)
> return -ENODEV;
>
> - while (match->compatible) {
> + while (match->compatible[0]) {
> unsigned long addr;
> if (fdt_node_check_compatible(fdt, offset, match->compatible)) {
> match++;
> --
> 2.1.1
>
