Re: [PATCH 13/43] x86/asm/64: Use a percpu trampoline stack for IDT entries

[Borislav Petkov]

On Fri, Nov 24, 2017 at 06:23:41PM +0100, Ingo Molnar wrote:
> From: Andy Lutomirski <luto@xxxxxxxxxx>
> 
> Historically, IDT entries from usermode have always gone directly
> to the running task's kernel stack.  Rearrange it so that we enter on
> a percpu trampoline stack and then manually switch to the task's stack.
> This touches a couple of extra cachelines, but it gives us a chance
> to run some code before we touch the kernel stack.
> 
> The asm isn't exactly beautiful, but I think that fully refactoring
> it can wait.
> 
> Signed-off-by: Andy Lutomirski <luto@xxxxxxxxxx>
> Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>

I think you mean Reviewed-by: here. The following patches have it too.

> Cc: Borislav Petkov <bpetkov@xxxxxxx>
> Cc: Brian Gerst <brgerst@xxxxxxxxx>
> Cc: Dave Hansen <dave.hansen@xxxxxxxxx>
> Cc: Josh Poimboeuf <jpoimboe@xxxxxxxxxx>
> Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
> Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
> Link: https://lkml.kernel.org/r/fa3958723a1a85baeaf309c735b775841205800e.1511497875.git.luto@xxxxxxxxxx
> Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
> ---
>  arch/x86/entry/entry_64.S        | 67 ++++++++++++++++++++++++++++++----------
>  arch/x86/entry/entry_64_compat.S |  5 ++-
>  arch/x86/include/asm/switch_to.h |  2 +-
>  arch/x86/include/asm/traps.h     |  1 -
>  arch/x86/kernel/cpu/common.c     |  6 ++--
>  arch/x86/kernel/traps.c          | 18 +++++------
>  6 files changed, 68 insertions(+), 31 deletions(-)

...

> diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
> index 8c6bd6863db9..a6796ac8d311 100644
> --- a/arch/x86/include/asm/switch_to.h
> +++ b/arch/x86/include/asm/switch_to.h
> @@ -93,7 +93,7 @@ static inline void update_sp0(struct task_struct *task)
>  #ifdef CONFIG_X86_32
>  	load_sp0(task->thread.sp0);
>  #else
> -	load_sp0(task_top_of_stack(task));
> +	/* On x86_64, sp0 always points to the entry trampoline stack. */
>  #endif

You can put this comment to the one ontop and remove the #else.
ifdeffery is always ugly and the less, the better.

...

> -asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs)
> +asmlinkage __visible notrace
> +struct pt_regs *sync_regs(struct pt_regs *eregs)
>  {
> -	struct pt_regs *regs = task_pt_regs(current);
> +	struct pt_regs *regs = (struct pt_regs *)this_cpu_read(cpu_current_top_of_stack) - 1;
>  	*regs = *eregs;
>  	return regs;
>  }
> @@ -630,13 +630,13 @@ struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s)
>  	/*
>  	 * This is called from entry_64.S early in handling a fault
>  	 * caused by a bad iret to user mode.  To handle the fault
> -	 * correctly, we want move our stack frame to task_pt_regs
> -	 * and we want to pretend that the exception came from the
> -	 * iret target.
> +	 * correctly, we want move our stack frame to where it would

" ... we want to move... "

> +	 * be had we entered directly on the entry stack (rather than
> +	 * just below the IRET frame) and we want to pretend that the
> +	 * exception came from the iret target.

s/iret/IRET/

>  	 */
>  	struct bad_iret_stack *new_stack =
> -		container_of(task_pt_regs(current),
> -			     struct bad_iret_stack, regs);
> +		(struct bad_iret_stack *)this_cpu_read(cpu_tss.x86_tss.sp0) - 1;
>  
>  	/* Copy the IRET target to the new stack. */
>  	memmove(&new_stack->regs.ip, (void *)s->regs.sp, 5*8);
> -- 

with that:

Reviewed-by: Borislav Petkov <bp@xxxxxxx>

-- 
Regards/Gruss,
    Boris.

Good mailing practices for 400: avoid top-posting and trim the reply.