Re: [patch 2/2]: introduce fast_gup

[Peter Zijlstra <peterz-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org>]

On Fri, 2008-03-28 at 04:00 +0100, Nick Piggin wrote:

> +static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
> +		unsigned long end, int write, struct page **pages, int *nr)
> +{
> +	unsigned long mask, result;
> +	pte_t *ptep;
> +
> +	result = _PAGE_PRESENT|_PAGE_USER;
> +	if (write)
> +		result |= _PAGE_RW;
> +	mask = result | _PAGE_SPECIAL;
> +
> +	ptep = pte_offset_map(&pmd, addr);
> +	do {
> +		/*
> +		 * XXX: careful. On 3-level 32-bit, the pte is 64 bits, and
> +		 * we need to make sure we load the low word first, then the
> +		 * high. This means _PAGE_PRESENT should be clear if the high
> +		 * word was not valid. Currently, the C compiler can issue
> +		 * the loads in any order, and I don't know of a wrapper
> +		 * function that will do this properly, so it is broken on
> +		 * 32-bit 3-level for the moment.
> +		 */
> +		pte_t pte = *ptep;
> +		struct page *page;
> +
> +		if ((pte_val(pte) & mask) != result)
> +			return 0;

This return path fails to unmap the pmd.

> +		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
> +		page = pte_page(pte);
> +		get_page(page);
> +		pages[*nr] = page;
> +		(*nr)++;
> +
> +	} while (ptep++, addr += PAGE_SIZE, addr != end);
> +	pte_unmap(ptep - 1);
> +
> +	return 1;
> +}