Re: [PATCH 2/4] x86: get rid of KERNEL_STACK_OFFSET

[Ingo Molnar <mingo@kernel.org>]

* Denys Vlasenko <dvlasenk@redhat.com> wrote:

> > The decision on how exactly we should fix 
> > KERNEL_STACK_OFFSET (set it to SIZEOF_PTREGS or to 
> > zero) depends on whether we switch to using PUSHes, or 
> > not. What do you think?

Yes.

> A data point. I implemented push-based creation of 
> pt_regs and benchmarked it. The patch is on top of all my 
> latest patches sent to ML.
> 
> On SandyBridge CPU, it does not get slower: seems to be 1 
> cycle faster per syscall.
> 
> We lose a number of large insns there:
> 
>     text           data     bss     dec     hex filename
> -   9863              0       0    9863    2687 entry_64.o
> +   9671              0       0    9671    25c7 entry_64.o

That's a nice reduction in I$ footprint ...

> +	/* Construct struct pt_regs on stack */
> +	pushq	$__USER_DS		/* pt_regs->ss */
> +	pushq	PER_CPU_VAR(old_rsp)	/* pt_regs->sp */
> +	pushq	%r11			/* pt_regs->flags */

Btw., this could also construct all the dwarf annotations 
in a natural, maintainable fashion - pushq_cfi and friends?

> +	pushq	$__USER_CS		/* pt_regs->cs */
> +	pushq	%rcx			/* pt_regs->ip */
> +	pushq	%rax			/* pt_regs->orig_ax */
> +	pushq	%rdi			/* pt_regs->di */
> +	pushq	%rsi			/* pt_regs->si */
> +	pushq	%rdx			/* pt_regs->dx */
> +	pushq	%rcx			/* pt_regs->cx */
> +	pushq	$-ENOSYS		/* pt_regs->ax */
> +	pushq	%r8			/* pt_regs->r8 */
> +	pushq	%r9			/* pt_regs->r9 */
> +	pushq	%r10			/* pt_regs->r10 */
> +	sub	$(7*8),%rsp /* pt_regs->r11,bp,bx,r12-15 */

So the 'SUB' there is a bit sad, but push sequences are 
generally easier to read, so I like it altogether.

Then we could indeed get rid of KERNEL_STACK_OFFSET.

Thanks,

	Ingo