Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1403655

Re: [PATCHv9 0/2] mremap vDSO for 32-bit

Show all headers | View raw

On 05/17/2016 03:13 PM, Dmitry Safonov wrote:
> The first patch adds support of mremapping 32-bit vDSO.
> One could move vDSO vma before this patch, but fast syscalls
> on moved vDSO hasn't been working. It's because of code that
> relies on mm->context.vdso pointer.
> So all this code is just fixup for that pointer on moving.
> (Also adds preventing for splitting vDSO vma).
> As Andy notted, 64-bit vDSO mremap also has worked only by a chance
> before this patches.
> The second patch adds a test for the new functionality.
>
> I need possibility to move vDSO in CRIU - on restore we need
> to choose vma's position:
> - if vDSO blob of restoring application is the same as the kernel has,
>   we need to move it on the same place;
> - if it differs, we need to choose place that wasn't tooken by other
>   vma of restoring application and than add jump trampolines to it
>   from the place of vDSO in restoring application.
>
> CRIU code now relies on possibility on x86_64 to mremap vDSO.
> Without this patch that may be broken in future.
> And as I work on C/R of compatible 32-bit applications on x86_64,
> I need mremap to work also for 32-bit vDSO. Which does not work,
> because of context.vdso pointer mentioned above.
>
> Changes:
> v9: Added cover-letter with changelog and reasons for patches
> v8: Add WARN_ON_ONCE on current->mm != new_vma->vm_mm;
>     run test for x86_64 too;
>     removed fixed VDSO_SIZE - check EINVAL mremap return for partial remapping
> v7: Build fix
> v6: Moved vdso_image_32 check and fixup code into vdso_fix_landing function
>     with ifdefs around
> v5: As Andy suggested, add a check that new_vma->vm_mm and current->mm are
>     the same, also check not only in_ia32_syscall() but image == &vdso_image_32;
>     added test for mremapping vDSO
> v4: Drop __maybe_unused & use image from mm->context instead vdso_image_32
> v3: As Andy suggested, return EINVAL in case of splitting vdso blob on mremap;
>     used is_ia32_task instead of ifdefs
> v2: Added __maybe_unused for pt_regs in vdso_mremap

Ping?

Back to linux.kernel | Previous | Next — Previous in thread | Find similar | Unroll thread

Thread

[PATCHv9 0/2] mremap vDSO for 32-bit Dmitry Safonov <dsafonov@virtuozzo.com> - 2016-05-17 14:40 +0200
  [PATCHv9 1/2] x86/vdso: add mremap hook to vm_special_mapping Dmitry Safonov <dsafonov@virtuozzo.com> - 2016-05-17 14:50 +0200
  Re: [PATCHv9 0/2] mremap vDSO for 32-bit Dmitry Safonov <dsafonov@virtuozzo.com> - 2016-05-19 13:30 +0200

csiph-web