Re: [PATCH v8 29/46] x86, mm: only call early_ioremap_page_table_range_init() once

[Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>]

On Fri, Nov 16, 2012 at 07:39:06PM -0800, Yinghai Lu wrote:
> On 32bit, before patcheset that only set page table for ram, we only
> call that one time.

Um.. Which patchset? x86, mm: Only direct map addresses that are marked as E820_RAM?

> 
> Now, we are calling that during every init_memory_mapping if we have holes
> under max_low_pfn.
> 
> We should only call it one time after all ranges under max_low_page get
> mapped just like we did before.
> 
> Also that could avoid the risk to run out of pgt_buf in BRK.
                                ^^- 'of running out of pgt_buf in BRK.'

> 
> Need to update page_table_range_init() to count the pages for kmap page table
> at first, and use new added alloc_low_pages() to get pages in sequence.
> That will conform to the requirement that pages need to be in low to high order.
> 
> Signed-off-by: Yinghai Lu <yinghai@kernel.org>
> ---
>  arch/x86/mm/init.c    |   13 +++++--------
>  arch/x86/mm/init_32.c |   47 +++++++++++++++++++++++++++++++++++++++++------
>  2 files changed, 46 insertions(+), 14 deletions(-)
> 
> diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
> index cb4f8ba..bed4888 100644
> --- a/arch/x86/mm/init.c
> +++ b/arch/x86/mm/init.c
> @@ -343,14 +343,6 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
>  		ret = kernel_physical_mapping_init(mr[i].start, mr[i].end,
>  						   mr[i].page_size_mask);
>  
> -#ifdef CONFIG_X86_32
> -	early_ioremap_page_table_range_init();
> -
> -	load_cr3(swapper_pg_dir);
> -#endif
> -
> -	__flush_tlb_all();
> -
>  	add_pfn_range_mapped(start >> PAGE_SHIFT, ret >> PAGE_SHIFT);
>  
>  	return ret >> PAGE_SHIFT;
> @@ -447,7 +439,12 @@ void __init init_mem_mapping(void)
>  		/* can we preseve max_low_pfn ?*/
>  		max_low_pfn = max_pfn;
>  	}
> +#else
> +	early_ioremap_page_table_range_init();
> +	load_cr3(swapper_pg_dir);
> +	__flush_tlb_all();
>  #endif
> +
>  	early_memtest(0, max_pfn_mapped << PAGE_SHIFT);
>  }
>  
> diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
> index a7f2df1..0ae1ba8 100644
> --- a/arch/x86/mm/init_32.c
> +++ b/arch/x86/mm/init_32.c
> @@ -135,8 +135,39 @@ pte_t * __init populate_extra_pte(unsigned long vaddr)
>  	return one_page_table_init(pmd) + pte_idx;
>  }
>  
> +static unsigned long __init
> +page_table_range_init_count(unsigned long start, unsigned long end)
> +{
> +	unsigned long count = 0;
> +#ifdef CONFIG_HIGHMEM
> +	int pmd_idx_kmap_begin = fix_to_virt(FIX_KMAP_END) >> PMD_SHIFT;
> +	int pmd_idx_kmap_end = fix_to_virt(FIX_KMAP_BEGIN) >> PMD_SHIFT;
> +	int pgd_idx, pmd_idx;
> +	unsigned long vaddr;
> +
> +	if (pmd_idx_kmap_begin == pmd_idx_kmap_end)
> +		return 0;
> +
> +	vaddr = start;
> +	pgd_idx = pgd_index(vaddr);
> +
> +	for ( ; (pgd_idx < PTRS_PER_PGD) && (vaddr != end); pgd_idx++) {
> +		for (; (pmd_idx < PTRS_PER_PMD) && (vaddr != end);
> +							pmd_idx++) {
> +			if ((vaddr >> PMD_SHIFT) >= pmd_idx_kmap_begin &&
> +			    (vaddr >> PMD_SHIFT) <= pmd_idx_kmap_end)
> +				count++;
> +			vaddr += PMD_SIZE;
> +		}
> +		pmd_idx = 0;
> +	}
> +#endif
> +	return count;
> +}
> +
>  static pte_t *__init page_table_kmap_check(pte_t *pte, pmd_t *pmd,
> -					   unsigned long vaddr, pte_t *lastpte)
> +					   unsigned long vaddr, pte_t *lastpte,
> +					   void **adr)
>  {
>  #ifdef CONFIG_HIGHMEM
>  	/*
> @@ -150,16 +181,15 @@ static pte_t *__init page_table_kmap_check(pte_t *pte, pmd_t *pmd,
>  
>  	if (pmd_idx_kmap_begin != pmd_idx_kmap_end
>  	    && (vaddr >> PMD_SHIFT) >= pmd_idx_kmap_begin
> -	    && (vaddr >> PMD_SHIFT) <= pmd_idx_kmap_end
> -	    && ((__pa(pte) >> PAGE_SHIFT) < pgt_buf_start
> -		|| (__pa(pte) >> PAGE_SHIFT) >= pgt_buf_end)) {
> +	    && (vaddr >> PMD_SHIFT) <= pmd_idx_kmap_end) {
>  		pte_t *newpte;
>  		int i;
>  
>  		BUG_ON(after_bootmem);
> -		newpte = alloc_low_page();
> +		newpte = *adr;
>  		for (i = 0; i < PTRS_PER_PTE; i++)
>  			set_pte(newpte + i, pte[i]);
> +		*adr = (void *)(((unsigned long)(*adr)) + PAGE_SIZE);
>  
>  		paravirt_alloc_pte(&init_mm, __pa(newpte) >> PAGE_SHIFT);
>  		set_pmd(pmd, __pmd(__pa(newpte)|_PAGE_TABLE));
> @@ -193,6 +223,11 @@ page_table_range_init(unsigned long start, unsigned long end, pgd_t *pgd_base)
>  	pgd_t *pgd;
>  	pmd_t *pmd;
>  	pte_t *pte = NULL;
> +	unsigned long count = page_table_range_init_count(start, end);
> +	void *adr = NULL;
> +
> +	if (count)
> +		adr = alloc_low_pages(count);
>  
>  	vaddr = start;
>  	pgd_idx = pgd_index(vaddr);
> @@ -205,7 +240,7 @@ page_table_range_init(unsigned long start, unsigned long end, pgd_t *pgd_base)
>  		for (; (pmd_idx < PTRS_PER_PMD) && (vaddr != end);
>  							pmd++, pmd_idx++) {
>  			pte = page_table_kmap_check(one_page_table_init(pmd),
> -			                            pmd, vaddr, pte);
> +						    pmd, vaddr, pte, &adr);
>  
>  			vaddr += PMD_SIZE;
>  		}
> -- 
> 1.7.7