On Wed, Aug 24, 2022 at 10:01:00AM +0200, Heiko Carstens wrote: > 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! Applied, Thank you!
