Re: [PATCH 2/2] s390/tlb: convert to generic mmu_gather

[Peter Zijlstra]

On Tue, Sep 18, 2018 at 02:51:51PM +0200, Martin Schwidefsky wrote:
> +#define pte_free_tlb pte_free_tlb
> +#define pmd_free_tlb pmd_free_tlb
> +#define p4d_free_tlb p4d_free_tlb
> +#define pud_free_tlb pud_free_tlb

> @@ -121,9 +62,18 @@ static inline void tlb_remove_page_size(struct mmu_gather *tlb,
>   * page table from the tlb.
>   */
>  static inline void pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
> +                                unsigned long address)
>  {
> +	__tlb_adjust_range(tlb, address, PAGE_SIZE);
> +	tlb->mm->context.flush_mm = 1;
> +	tlb->freed_tables = 1;
> +	tlb->cleared_ptes = 1;
> +	/*
> +	 * page_table_free_rcu takes care of the allocation bit masks
> +	 * of the 2K table fragments in the 4K page table page,
> +	 * then calls tlb_remove_table.
> +	 */
> +        page_table_free_rcu(tlb, (unsigned long *) pte, address);

(whitespace damage, fixed)

Also, could you perhaps explain the need for that
page_table_alloc/page_table_free code? That is, I get the comment about
using 2K page-table fragments out of 4k physical page, but why this
custom allocator instead of kmem_cache? It feels like there's a little
extra complication, but it's not immediately obvious what.

>  }

We _could_ use __pte_free_tlb() here I suppose, but...

>  /*
> @@ -139,6 +89,10 @@ static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
>  	if (tlb->mm->context.asce_limit <= _REGION3_SIZE)
>  		return;
>  	pgtable_pmd_page_dtor(virt_to_page(pmd));
> +	__tlb_adjust_range(tlb, address, PAGE_SIZE);
> +	tlb->mm->context.flush_mm = 1;
> +	tlb->freed_tables = 1;
> +	tlb->cleared_puds = 1;
>  	tlb_remove_table(tlb, pmd);
>  }
>  
> @@ -154,6 +108,10 @@ static inline void p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d,
>  {
>  	if (tlb->mm->context.asce_limit <= _REGION1_SIZE)
>  		return;
> +	__tlb_adjust_range(tlb, address, PAGE_SIZE);
> +	tlb->mm->context.flush_mm = 1;
> +	tlb->freed_tables = 1;
> +	tlb->cleared_p4ds = 1;
>  	tlb_remove_table(tlb, p4d);
>  }
>  
> @@ -169,19 +127,11 @@ static inline void pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
>  {
>  	if (tlb->mm->context.asce_limit <= _REGION2_SIZE)
>  		return;
> +	tlb->mm->context.flush_mm = 1;
> +	tlb->freed_tables = 1;
> +	tlb->cleared_puds = 1;
>  	tlb_remove_table(tlb, pud);
>  }

It's that ASCE limit that makes it impossible to use the generic
helpers, right?