On 11/10/2014 05:14 PM, Rob Herring 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...
It's actually OK to tag the patch for stable (not really send to stable), so that that list gets automatically notified when the comment lands in the mainline. Unless the maintainer doesn't have his own rules about stable patches (like e.g. DaveM). Do you have alike rules?
Rob
WBR, Sergei
