linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: "Kirill A. Shutemov" <kirill@shutemov.name>
To: Matthew Wilcox <willy@infradead.org>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>,
	"Theodore Ts'o" <tytso@mit.edu>,
	Andreas Dilger <adilger.kernel@dilger.ca>,
	Jan Kara <jack@suse.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Alexander Viro <viro@zeniv.linux.org.uk>,
	Hugh Dickins <hughd@google.com>,
	Andrea Arcangeli <aarcange@redhat.com>,
	Dave Hansen <dave.hansen@intel.com>,
	Vlastimil Babka <vbabka@suse.cz>,
	Ross Zwisler <ross.zwisler@linux.intel.com>,
	linux-ext4@vger.kernel.org, linux-fsdevel@vger.kernel.org,
	linux-kernel@vger.kernel.org, linux-mm@kvack.org,
	linux-block@vger.kernel.org
Subject: Re: [PATCHv6 01/37] mm, shmem: swich huge tmpfs to multi-order radix-tree entries
Date: Mon, 13 Feb 2017 16:43:45 +0300	[thread overview]
Message-ID: <20170213134345.GA20394@node.shutemov.name> (raw)
In-Reply-To: <20170209165820.GA12768@node.shutemov.name>

On Thu, Feb 09, 2017 at 07:58:20PM +0300, Kirill A. Shutemov wrote:
> I'll look into it.

I ended up with this (I'll test it more later):

void filemap_map_pages(struct vm_fault *vmf,
		pgoff_t start_pgoff, pgoff_t end_pgoff)
{
	struct radix_tree_iter iter;
	void **slot;
	struct file *file = vmf->vma->vm_file;
	struct address_space *mapping = file->f_mapping;
	pgoff_t last_pgoff = start_pgoff;
	loff_t size;
	struct page *page;
	bool mapped;

	rcu_read_lock();
	radix_tree_for_each_slot(slot, &mapping->page_tree, &iter,
			start_pgoff) {
		unsigned long index = iter.index;
		if (index < start_pgoff)
			index = start_pgoff;
		if (index > end_pgoff)
			break;
repeat:
		page = radix_tree_deref_slot(slot);
		if (unlikely(!page))
			continue;
		if (radix_tree_exception(page)) {
			if (radix_tree_deref_retry(page))
				slot = radix_tree_iter_retry(&iter);
			continue;
		}

		if (!page_cache_get_speculative(page))
			goto repeat;

		/* Has the page moved? */
		if (unlikely(page != *slot)) {
			put_page(page);
			goto repeat;
		}

		/* For multi-order entries, find relevant subpage */
		page = find_subpage(page, index);

		if (!PageUptodate(page) || PageReadahead(page))
			goto skip;
		if (!trylock_page(page))
			goto skip;

		if (page_mapping(page) != mapping || !PageUptodate(page))
			goto skip_unlock;

		size = round_up(i_size_read(mapping->host), PAGE_SIZE);
		if (compound_head(page)->index >= size >> PAGE_SHIFT)
			goto skip_unlock;

		if (file->f_ra.mmap_miss > 0)
			file->f_ra.mmap_miss--;
map_next_subpage:
		if (PageHWPoison(page))
			goto next;

		vmf->address += (index - last_pgoff) << PAGE_SHIFT;
		if (vmf->pte)
			vmf->pte += index - last_pgoff;
		last_pgoff = index;
		mapped = !alloc_set_pte(vmf, NULL, page);

		/* Huge page is mapped or last index? No need to proceed. */
		if (pmd_trans_huge(*vmf->pmd) ||
				index == end_pgoff) {
			unlock_page(page);
			break;
		}
next:
		if (page && PageCompound(page)) {
			/* Last subpage handled? */
			if ((index & (compound_nr_pages(page) - 1)) ==
					compound_nr_pages(page) - 1)
				goto skip_unlock;
			index++;
			page++;

			/*
			 * One page reference goes to page table mapping.
			 * Need additional reference, if last alloc_set_pte()
			 * succeed.
			 */
			if (mapped)
				get_page(page);
			goto map_next_subpage;
		}
skip_unlock:
		unlock_page(page);
skip:
		iter.index = compound_head(page)->index +
			compound_nr_pages(page) - 1;
		/* Only give up reference if alloc_set_pte() failed. */
		if (!mapped)
			put_page(page);
	}
	rcu_read_unlock();
}

-- 
 Kirill A. Shutemov

  reply	other threads:[~2017-02-13 13:43 UTC|newest]

Thread overview: 67+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-01-26 11:57 [PATCHv6 00/37] ext4: support of huge pages Kirill A. Shutemov
2017-01-26 11:57 ` [PATCHv6 01/37] mm, shmem: swich huge tmpfs to multi-order radix-tree entries Kirill A. Shutemov
2017-02-09  3:57   ` Matthew Wilcox
2017-02-09 16:58     ` Kirill A. Shutemov
2017-02-13 13:43       ` Kirill A. Shutemov [this message]
2017-01-26 11:57 ` [PATCHv6 02/37] Revert "radix-tree: implement radix_tree_maybe_preload_order()" Kirill A. Shutemov
2017-01-26 15:38   ` Matthew Wilcox
2017-01-26 11:57 ` [PATCHv6 03/37] page-flags: relax page flag policy for few flags Kirill A. Shutemov
2017-02-09  4:01   ` Matthew Wilcox
2017-02-13 13:59     ` Kirill A. Shutemov
2017-01-26 11:57 ` [PATCHv6 04/37] mm, rmap: account file thp pages Kirill A. Shutemov
2017-02-09 20:17   ` Matthew Wilcox
2017-01-26 11:57 ` [PATCHv6 05/37] thp: try to free page's buffers before attempt split Kirill A. Shutemov
2017-02-09 20:14   ` Matthew Wilcox
2017-02-13 14:32     ` Kirill A. Shutemov
2017-01-26 11:57 ` [PATCHv6 06/37] thp: handle write-protection faults for file THP Kirill A. Shutemov
2017-01-26 15:44   ` Matthew Wilcox
2017-01-26 15:57     ` Kirill A. Shutemov
2017-02-09 20:19   ` Matthew Wilcox
2017-01-26 11:57 ` [PATCHv6 07/37] filemap: allocate huge page in page_cache_read(), if allowed Kirill A. Shutemov
2017-02-09 21:18   ` Matthew Wilcox
2017-02-13 15:17     ` Kirill A. Shutemov
2017-01-26 11:57 ` [PATCHv6 08/37] filemap: handle huge pages in do_generic_file_read() Kirill A. Shutemov
2017-02-09 21:55   ` Matthew Wilcox
2017-02-13 15:33     ` Kirill A. Shutemov
2017-02-13 16:01       ` Matthew Wilcox
2017-02-13 16:09         ` Matthew Wilcox
2017-02-13 16:28   ` Matthew Wilcox
2017-01-26 11:57 ` [PATCHv6 09/37] filemap: allocate huge page in pagecache_get_page(), if allowed Kirill A. Shutemov
2017-02-09 21:59   ` Matthew Wilcox
2017-01-26 11:57 ` [PATCHv6 10/37] filemap: handle huge pages in filemap_fdatawait_range() Kirill A. Shutemov
2017-02-09 23:03   ` Matthew Wilcox
2017-01-26 11:57 ` [PATCHv6 11/37] HACK: readahead: alloc huge pages, if allowed Kirill A. Shutemov
2017-02-09 23:34   ` Matthew Wilcox
2017-02-10  0:23     ` Andreas Dilger
2017-02-10 14:51       ` Matthew Wilcox
2017-01-26 11:57 ` [PATCHv6 12/37] brd: make it handle huge pages Kirill A. Shutemov
2017-02-10 17:24   ` Matthew Wilcox
2017-01-26 11:57 ` [PATCHv6 13/37] mm: make write_cache_pages() work on " Kirill A. Shutemov
2017-02-10 17:46   ` Matthew Wilcox
2017-01-26 11:57 ` [PATCHv6 14/37] thp: introduce hpage_size() and hpage_mask() Kirill A. Shutemov
2017-01-26 11:57 ` [PATCHv6 15/37] thp: do not threat slab pages as huge in hpage_{nr_pages,size,mask} Kirill A. Shutemov
2017-02-10 22:13   ` Matthew Wilcox
2017-01-26 11:57 ` [PATCHv6 16/37] thp: make thp_get_unmapped_area() respect S_HUGE_MODE Kirill A. Shutemov
2017-02-10 17:50   ` Matthew Wilcox
2017-01-26 11:57 ` [PATCHv6 17/37] fs: make block_read_full_page() be able to read huge page Kirill A. Shutemov
2017-02-10 17:58   ` Matthew Wilcox
2017-01-26 11:58 ` [PATCHv6 18/37] fs: make block_write_{begin,end}() be able to handle huge pages Kirill A. Shutemov
2017-01-26 11:58 ` [PATCHv6 19/37] fs: make block_page_mkwrite() aware about " Kirill A. Shutemov
2017-01-26 11:58 ` [PATCHv6 20/37] truncate: make truncate_inode_pages_range() " Kirill A. Shutemov
2017-01-26 11:58 ` [PATCHv6 21/37] truncate: make invalidate_inode_pages2_range() " Kirill A. Shutemov
2017-01-26 11:58 ` [PATCHv6 22/37] mm, hugetlb: switch hugetlbfs to multi-order radix-tree entries Kirill A. Shutemov
2017-01-26 11:58 ` [PATCHv6 23/37] mm: account huge pages to dirty, writaback, reclaimable, etc Kirill A. Shutemov
2017-01-26 11:58 ` [PATCHv6 24/37] ext4: make ext4_mpage_readpages() hugepage-aware Kirill A. Shutemov
2017-01-26 11:58 ` [PATCHv6 25/37] ext4: make ext4_writepage() work on huge pages Kirill A. Shutemov
2017-01-26 11:58 ` [PATCHv6 26/37] ext4: handle huge pages in ext4_page_mkwrite() Kirill A. Shutemov
2017-01-26 11:58 ` [PATCHv6 27/37] ext4: handle huge pages in __ext4_block_zero_page_range() Kirill A. Shutemov
2017-01-26 11:58 ` [PATCHv6 28/37] ext4: make ext4_block_write_begin() aware about huge pages Kirill A. Shutemov
2017-01-26 11:58 ` [PATCHv6 29/37] ext4: handle huge pages in ext4_da_write_end() Kirill A. Shutemov
2017-01-26 11:58 ` [PATCHv6 30/37] ext4: make ext4_da_page_release_reservation() aware about huge pages Kirill A. Shutemov
2017-01-26 11:58 ` [PATCHv6 31/37] ext4: handle writeback with " Kirill A. Shutemov
2017-01-26 11:58 ` [PATCHv6 32/37] ext4: make EXT4_IOC_MOVE_EXT work " Kirill A. Shutemov
2017-01-26 11:58 ` [PATCHv6 33/37] ext4: fix SEEK_DATA/SEEK_HOLE for " Kirill A. Shutemov
2017-01-26 11:58 ` [PATCHv6 34/37] ext4: make fallocate() operations work with " Kirill A. Shutemov
2017-01-26 11:58 ` [PATCHv6 35/37] ext4: reserve larger jounral transaction for " Kirill A. Shutemov
2017-01-26 11:58 ` [PATCHv6 36/37] mm, fs, ext4: expand use of page_mapping() and page_to_pgoff() Kirill A. Shutemov
2017-01-26 11:58 ` [PATCHv6 37/37] ext4, vfs: add huge= mount option Kirill A. Shutemov

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20170213134345.GA20394@node.shutemov.name \
    --to=kirill@shutemov.name \
    --cc=aarcange@redhat.com \
    --cc=adilger.kernel@dilger.ca \
    --cc=akpm@linux-foundation.org \
    --cc=dave.hansen@intel.com \
    --cc=hughd@google.com \
    --cc=jack@suse.com \
    --cc=kirill.shutemov@linux.intel.com \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-ext4@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=ross.zwisler@linux.intel.com \
    --cc=tytso@mit.edu \
    --cc=vbabka@suse.cz \
    --cc=viro@zeniv.linux.org.uk \
    --cc=willy@infradead.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).