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

Groups > linux.kernel > #1186205

Re: [RFC][PATCH] x86, fpu: dynamically allocate 'struct fpu'

Show all headers | View raw

On Thu, Jul 16, 2015 at 12:14 PM, Dave Hansen <dave@sr71.net> wrote:
>
> The FPU rewrite removed the dynamic allocations of 'struct fpu'.
> But, this potentially wastes massive amounts of memory (2k per
> task on systems that do not have AVX-512 for instance).
>
> Instead of having a separate slab, this patch just appends the
> space that we need to the 'task_struct' which we dynamically
> allocate already.  This saves from doing an extra slab allocation
> at fork().  The only real downside here is that we have to stick
> everything and the end of the task_struct.  But, I think the
> BUILD_BUG_ON()s I stuck in there should keep that from being too
> fragile.
>
> This survives a quick build and boot in a VM.  Does anyone see any
> real downsides to this?

Looks generally sensible.  Minor nitpicking below.

> +#define CHECK_MEMBER_AT_END_OF(TYPE, MEMBER)   \
> +       BUILD_BUG_ON((sizeof(TYPE) -                    \
> +                       offsetof(TYPE, MEMBER) -        \
> +                       sizeof(((TYPE *)0)->MEMBER)) >  \
> +                       0)                              \
> +

You could save a bit of typing by using offsetofend here.  Something
along the lines of BUILD_BUG_ON(sizeof(TYPE) != offsetofend(TYPE,
MEMBER));

>  #endif /* _ASM_X86_FPU_H */
> diff -puN arch/x86/kernel/process.c~dynamically-allocate-struct-fpu arch/x86/kernel/process.c
> --- a/arch/x86/kernel/process.c~dynamically-allocate-struct-fpu 2015-07-16 10:50:42.360571875 -0700
> +++ b/arch/x86/kernel/process.c 2015-07-16 12:00:59.204808551 -0700
> @@ -81,7 +81,7 @@ EXPORT_SYMBOL_GPL(idle_notifier_unregist
>   */
>  int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
>  {
> -       *dst = *src;
> +       memcpy(dst, src, arch_task_struct_size());

This is actually vaguely performance-critical, which makes me thing
that using some kind of inline or other real way (config macro, ifdef,
etc) to detect whether there's an arch override would be better than a
weak function.

--Andy
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

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

Thread

[RFC][PATCH] x86, fpu: dynamically allocate 'struct fpu' Dave Hansen <dave@sr71.net> - 2015-07-16 21:20 +0200
  Re: [RFC][PATCH] x86, fpu: dynamically allocate 'struct fpu' Andy Lutomirski <luto@amacapital.net> - 2015-07-16 21:30 +0200
    Re: [RFC][PATCH] x86, fpu: dynamically allocate 'struct fpu' Dave Hansen <dave@sr71.net> - 2015-07-16 23:30 +0200
      Re: [RFC][PATCH] x86, fpu: dynamically allocate 'struct fpu' Ingo Molnar <mingo@kernel.org> - 2015-07-17 10:50 +0200
        [PATCH] x86/fpu, sched: Introduce  CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT and use it on x86 Ingo Molnar <mingo@kernel.org> - 2015-07-17 11:40 +0200
  Re: [RFC][PATCH] x86, fpu: dynamically allocate 'struct fpu' Peter Zijlstra <peterz@infradead.org> - 2015-07-17 00:40 +0200
    [PATCH] x86/fpu, bug.h: Move CHECK_MEMBER_AT_END_OF() to a generic  header and use it in generic code Ingo Molnar <mingo@kernel.org> - 2015-07-17 10:50 +0200
    Re: [RFC][PATCH] x86, fpu: dynamically allocate 'struct fpu' Ingo Molnar <mingo@kernel.org> - 2015-07-17 10:50 +0200
  Re: [RFC][PATCH] x86, fpu: dynamically allocate 'struct fpu' "H. Peter Anvin" <hpa@zytor.com> - 2015-07-17 00:50 +0200
    Re: [RFC][PATCH] x86, fpu: dynamically allocate 'struct fpu' Andy Lutomirski <luto@amacapital.net> - 2015-07-17 01:00 +0200
  Re: [RFC][PATCH] x86, fpu: dynamically allocate 'struct fpu' Ingo Molnar <mingo@kernel.org> - 2015-07-17 10:30 +0200

csiph-web