On Tue, Aug 16, 2022 at 11:54:07AM -0400, Brian Foster wrote: > The pointers for guarded storage and runtime instrumentation control > blocks are stored in the thread_struct of the associated task. These > pointers are initially copied on fork() via arch_dup_task_struct() > and then cleared via copy_thread() before fork() returns. If fork() > happens to fail after the initial task dup and before copy_thread(), > the newly allocated task and associated thread_struct memory are > freed via free_task() -> arch_release_task_struct(). This results in > a double free of the guarded storage and runtime info structs > because the fields in the failed task still refer to memory > associated with the source task. > > This problem can manifest as a BUG_ON() in set_freepointer() (with > CONFIG_SLAB_FREELIST_HARDENED enabled) or KASAN splat (if enabled) > when running trinity syscall fuzz tests on s390x. To avoid this > problem, clear the associated pointer fields in > arch_dup_task_struct() immediately after the new task is copied. > Note that the RI flag is still cleared in copy_thread() because it > resides in thread stack memory and that is where stack info is > copied. > > Signed-off-by: Brian Foster <bfoster@xxxxxxxxxx> > --- > arch/s390/kernel/process.c | 22 ++++++++++++++++------ > 1 file changed, 16 insertions(+), 6 deletions(-) Reviewed-by: Heiko Carstens <hca@xxxxxxxxxxxxx> Thanks for debugging and fixing this! Vasily, could you pick this one up, and also add the Fixes: and Cc: stable tags as proposed by Gerald? Thanks!
