From mboxrd@z Thu Jan  1 00:00:00 1970
From: "Kirill A. Shutemov" <kirill-oKw7cIdHH8eLwutG50LtGA@public.gmane.org>
Subject: Re: [PATCH v3 01/17] mm: support madvise(MADV_FREE)
Date: Thu, 12 Nov 2015 13:26:20 +0200
Message-ID: <20151112112620.GB22481@node.shutemov.name>
References: <1447302793-5376-1-git-send-email-minchan@kernel.org>
 <1447302793-5376-2-git-send-email-minchan@kernel.org>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Return-path: <linux-api-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>
Content-Disposition: inline
In-Reply-To: <1447302793-5376-2-git-send-email-minchan-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>
Sender: linux-api-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
To: Minchan Kim <minchan-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>
Cc: Andrew Morton <akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org>, linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org, Michael Kerrisk <mtk.manpages-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>, linux-api-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, Hugh Dickins <hughd-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>, Johannes Weiner <hannes-druUgvl0LCNAfugRpC6u6w@public.gmane.org>, Rik van Riel <riel-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>, Mel Gorman <mgorman-l3A5Bk7waGM@public.gmane.org>, KOSAKI Motohiro <kosaki.motohiro-+CUm20s59erQFUHtdCDX3A@public.gmane.org>, Jason Evans <je-b10kYP2dOMg@public.gmane.org>, Daniel Micay <danielmicay-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>, Shaohua Li <shli-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>, Michal Hocko <mhocko-AlSwsSmVLrQ@public.gmane.org>, yalin.wang2010-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org
List-Id: linux-api@vger.kernel.org

On Thu, Nov 12, 2015 at 01:32:57PM +0900, Minchan Kim wrote:
> @@ -256,6 +260,125 @@ static long madvise_willneed(struct vm_area_struct *vma,
>  	return 0;
>  }
>  
> +static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
> +				unsigned long end, struct mm_walk *walk)
> +
> +{
> +	struct mmu_gather *tlb = walk->private;
> +	struct mm_struct *mm = tlb->mm;
> +	struct vm_area_struct *vma = walk->vma;
> +	spinlock_t *ptl;
> +	pte_t *pte, ptent;
> +	struct page *page;
> +
> +	split_huge_page_pmd(vma, addr, pmd);
> +	if (pmd_trans_unstable(pmd))
> +		return 0;
> +
> +	pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
> +	arch_enter_lazy_mmu_mode();
> +	for (; addr != end; pte++, addr += PAGE_SIZE) {
> +		ptent = *pte;
> +
> +		if (!pte_present(ptent))
> +			continue;
> +
> +		page = vm_normal_page(vma, addr, ptent);
> +		if (!page)
> +			continue;
> +
> +		if (PageSwapCache(page)) {

Could you put VM_BUG_ON_PAGE(PageTransCompound(page), page) here?
Just in case.

> +			if (!trylock_page(page))
> +				continue;
> +
> +			if (!try_to_free_swap(page)) {
> +				unlock_page(page);
> +				continue;
> +			}
> +
> +			ClearPageDirty(page);
> +			unlock_page(page);

Hm. Do we handle pages shared over fork() here?
Souldn't we ignore pages with mapcount > 0?

> +		}
> +
> +		if (pte_young(ptent) || pte_dirty(ptent)) {
> +			/*
> +			 * Some of architecture(ex, PPC) don't update TLB
> +			 * with set_pte_at and tlb_remove_tlb_entry so for
> +			 * the portability, remap the pte with old|clean
> +			 * after pte clearing.
> +			 */
> +			ptent = ptep_get_and_clear_full(mm, addr, pte,
> +							tlb->fullmm);
> +
> +			ptent = pte_mkold(ptent);
> +			ptent = pte_mkclean(ptent);
> +			set_pte_at(mm, addr, pte, ptent);
> +			tlb_remove_tlb_entry(tlb, pte, addr);
> +		}
> +	}
> +
> +	arch_leave_lazy_mmu_mode();
> +	pte_unmap_unlock(pte - 1, ptl);
> +	cond_resched();
> +	return 0;
> +}
> 

-- 
 Kirill A. Shutemov