Re: arm64: fp-stress: BUG: KFENCE: memory corruption in fpsimd_release_task

[Mark Brown]

On Mon, May 22, 2023 at 06:40:59PM +0300, Dan Carpenter wrote:
> On Thu, May 18, 2023 at 10:52:31AM +0900, Mark Brown wrote:

> > > When we call sme_alloc() it will say the buffer is already allocated
> > > and just zero out what we need for "vl", but the existing buffer is too
> > > small.

> > If we are setting the SVE vector length we do not need to reallocate the
> > SME state since the size of the data stored in the sme_state buffer is
> > influenced only by the SME vector length, not the SVE vector length.  We
> > unconditionally free the SVE state (causing it to be reallocated when
> > needed) since the size needed for it depends on both vector lengths.

> arch/arm64/kernel/fpsimd.c
>    909          /*
>    910           * Force reallocation of task SVE and SME state to the correct
>    911           * size on next use:
>    912           */
>    913          sve_free(task);

> Sure, this forces a reallocation.  But what prevents it from happening
> before we reach the task_set_vl() line?

Reallocation is either triggered by a trap from userspace or via ptrace,
as is a vector length configuration.  The two cases should already be
prevented from running simultaneously, and can't simultaneously perform
two actions.

Attachment: signature.asc
Description: PGP signature