[PATCH v3 2/2] arm64: Mark kernel page ranges contiguous

[will.deacon@arm.com (Will Deacon)]

On Fri, Feb 19, 2016 at 11:46:23AM -0600, Jeremy Linton wrote:
> With 64k pages, the next larger segment size is 512M. The linux
> kernel also uses different protection flags to cover its code and data.
> Because of these requirements, the vast majority of the kernel code and
> data structures end up being mapped with 64k pages instead of the larger
> pages common with a 4k page kernel.
> 
> Recent ARM processors support a contiguous bit in the
> page tables which allows a TLB to cover a range larger than a
> single PTE if that range is mapped into physically contiguous
> RAM.
> 
> So, for the kernel its a good idea to set this flag. Some basic
> micro benchmarks show it can significantly reduce the number of
> L1 dTLB refills.
> 
> Signed-off-by: Jeremy Linton <jeremy.linton@arm.com>
> ---
>  arch/arm64/mm/mmu.c | 64 ++++++++++++++++++++++++++++++++++++++++++++++++-----
>  1 file changed, 58 insertions(+), 6 deletions(-)
> 
> diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
> index 7711554..ab69a99 100644
> --- a/arch/arm64/mm/mmu.c
> +++ b/arch/arm64/mm/mmu.c
> @@ -1,3 +1,4 @@
> +
>  /*
>   * Based on arch/arm/mm/mmu.c
>   *
> @@ -103,17 +104,49 @@ static void split_pmd(pmd_t *pmd, pte_t *pte)
>  		 * Need to have the least restrictive permissions available
>  		 * permissions will be fixed up later
>  		 */
> -		set_pte(pte, pfn_pte(pfn, PAGE_KERNEL_EXEC));
> +		set_pte(pte, pfn_pte(pfn, PAGE_KERNEL_EXEC_CONT));
>  		pfn++;
>  	} while (pte++, i++, i < PTRS_PER_PTE);
>  }
>  
> +static void clear_cont_pte_range(pte_t *pte, unsigned long addr)
> +{
> +	int i;
> +
> +	pte -= CONT_RANGE_OFFSET(addr);
> +	for (i = 0; i < CONT_PTES; i++) {
> +		if (pte_cont(*pte))
> +			set_pte(pte, pte_mknoncont(*pte));
> +		pte++;
> +	}
> +	flush_tlb_all();

Do you still need this invalidation? I thought the table weren't even
live at this point?

> +}
> +
> +/*
> + * Given a range of PTEs set the pfn and provided page protection flags
> + */
> +static void __populate_init_pte(pte_t *pte, unsigned long addr,
> +			       unsigned long end, phys_addr_t phys,
> +			       pgprot_t prot)
> +{
> +	unsigned long pfn = __phys_to_pfn(phys);
> +
> +	do {
> +		/* clear all the bits except the pfn, then apply the prot */
> +		set_pte(pte, pfn_pte(pfn, prot));
> +		pte++;
> +		pfn++;
> +		addr += PAGE_SIZE;
> +	} while (addr != end);
> +}
> +
>  static void alloc_init_pte(pmd_t *pmd, unsigned long addr,
> -				  unsigned long end, unsigned long pfn,
> +				  unsigned long end, phys_addr_t phys,
>  				  pgprot_t prot,
>  				  phys_addr_t (*pgtable_alloc)(void))
>  {
>  	pte_t *pte;
> +	unsigned long next;
>  
>  	if (pmd_none(*pmd) || pmd_sect(*pmd)) {
>  		phys_addr_t pte_phys = pgtable_alloc();
> @@ -127,10 +160,29 @@ static void alloc_init_pte(pmd_t *pmd, unsigned long addr,
>  	BUG_ON(pmd_bad(*pmd));
>  
>  	pte = pte_set_fixmap_offset(pmd, addr);
> +
>  	do {
> -		set_pte(pte, pfn_pte(pfn, prot));
> -		pfn++;
> -	} while (pte++, addr += PAGE_SIZE, addr != end);
> +		next = min(end, (addr + CONT_SIZE) & CONT_MASK);
> +		if (((addr | next | phys) & ~CONT_MASK) == 0) {
> +			/* a block of CONT_PTES	 */
> +			__populate_init_pte(pte, addr, next, phys,
> +					    prot | __pgprot(PTE_CONT));
> +		} else {
> +			/*
> +			 * If the range being split is already inside of a
> +			 * contiguous range but this PTE isn't going to be
> +			 * contiguous, then we want to unmark the adjacent
> +			 * ranges, then update the portion of the range we
> +			 * are interrested in.
> +			 */
> +			clear_cont_pte_range(pte, addr);
> +			__populate_init_pte(pte, addr, next, phys, prot);

I don't understand the comment or the code here... the splitting is now
done seperately, and I can't think of a scenario where you need to clear
the cont hint explicitly for adjacent ptes.

What am I missing?

Will