On Fri, Sep 21, 2018 at 08:05:48AM -0700, Yu-cheng Yu wrote:
> The indirect branch tracking legacy bitmap takes a large address
> space. This causes may_expand_vm() failure on the address limit
> check. For a IBT-enabled task, add the bitmap size to the
> address limit.
>
> Signed-off-by: Yu-cheng Yu <yu-cheng.yu@xxxxxxxxx>
> ---
> arch/x86/include/uapi/asm/resource.h | 5 +++++
> include/uapi/asm-generic/resource.h | 3 +++
> mm/mmap.c | 12 +++++++++++-
> 3 files changed, 19 insertions(+), 1 deletion(-)
>
> diff --git a/arch/x86/include/uapi/asm/resource.h b/arch/x86/include/uapi/asm/resource.h
> index 04bc4db8921b..0741b2a6101a 100644
> --- a/arch/x86/include/uapi/asm/resource.h
> +++ b/arch/x86/include/uapi/asm/resource.h
> @@ -1 +1,6 @@
> +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
> +#ifdef CONFIG_X86_INTEL_CET
> +#define rlimit_as_extra() current->thread.cet.ibt_bitmap_size
> +#endif
Does this really belong to UAPI?
> +
> #include <asm-generic/resource.h>
> diff --git a/include/uapi/asm-generic/resource.h b/include/uapi/asm-generic/resource.h
> index f12db7a0da64..8a7608a09700 100644
> --- a/include/uapi/asm-generic/resource.h
> +++ b/include/uapi/asm-generic/resource.h
> @@ -58,5 +58,8 @@
> # define RLIM_INFINITY (~0UL)
> #endif
>
> +#ifndef rlimit_as_extra
> +#define rlimit_as_extra() 0
> +#endif
And this?
> #endif /* _UAPI_ASM_GENERIC_RESOURCE_H */
> diff --git a/mm/mmap.c b/mm/mmap.c
> index fa581ced3f56..397b8cb0b0af 100644
> --- a/mm/mmap.c
> +++ b/mm/mmap.c
> @@ -3237,7 +3237,17 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
> */
> bool may_expand_vm(struct mm_struct *mm, vm_flags_t flags, unsigned long npages)
> {
> - if (mm->total_vm + npages > rlimit(RLIMIT_AS) >> PAGE_SHIFT)
> + unsigned long as_limit = rlimit(RLIMIT_AS);
> + unsigned long as_limit_plus = as_limit + rlimit_as_extra();
> +
> + /* as_limit_plus overflowed */
> + if (as_limit_plus < as_limit)
> + as_limit_plus = RLIM_INFINITY;
> +
> + if (as_limit_plus > as_limit)
> + as_limit = as_limit_plus;
> +
> + if (mm->total_vm + npages > as_limit >> PAGE_SHIFT)
I wonder, how realistic a scenario where a userspace application enables IBT,
configures a huge prefetchable IO memory region (that just ignores bits
of offset beyond 16, for example), and start repeatedly loading a legacy
library there at different linear addresses.
> return false;
>
> if (is_data_mapping(flags) &&
> --
> 2.17.1
>
