linux-ext4 - Re: [PATCHv3 29/41] ext4: make ext4_mpage

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <56332284-449B-4998-AA99-245361CEE6D9@dilger.ca>
Date:   Thu, 15 Sep 2016 06:27:10 -0600
From:   Andreas Dilger <adilger@...ger.ca>
To:     "Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>
Cc:     Theodore Ts'o <tytso@....edu>, Jan Kara <jack@...e.com>,
        Andrew Morton <akpm@...ux-foundation.org>,
        Alexander Viro <viro@...iv.linux.org.uk>,
        Hugh Dickins <hughd@...gle.com>,
        Andrea Arcangeli <aarcange@...hat.com>,
        Dave Hansen <dave.hansen@...el.com>,
        Vlastimil Babka <vbabka@...e.cz>,
        Matthew Wilcox <willy@...radead.org>,
        Ross Zwisler <ross.zwisler@...ux.intel.com>,
        linux-ext4 <linux-ext4@...r.kernel.org>,
        linux-fsdevel <linux-fsdevel@...r.kernel.org>,
        LKML <linux-kernel@...r.kernel.org>,
        Linux MM <linux-mm@...ck.org>, linux-block@...r.kernel.org
Subject: Re: [PATCHv3 29/41] ext4: make ext4_mpage_readpages() hugepage-aware

On Sep 15, 2016, at 5:55 AM, Kirill A. Shutemov <kirill.shutemov@...ux.intel.com> wrote:
> 
> This patch modifies ext4_mpage_readpages() to deal with huge pages.
> 
> We read out 2M at once, so we have to alloc (HPAGE_PMD_NR *
> blocks_per_page) sector_t for that. I'm not entirely happy with kmalloc
> in this codepath, but don't see any other option.

If you're reading 2MB from disk (possibly from disjoint blocks with seeks
in between) I don't think that the kmalloc() is going to be the limiting
performance factor.  If you are concerned about the size of the kmalloc()
causing failures when pages are fragmented (it can be 16KB for 1KB blocks
with 4KB pages), then using ext4_kvmalloc() to fall back to vmalloc() in
case kmalloc() fails.  It shouldn't fail often for 16KB allocations,
but it could in theory.

I also notice that ext4_kvmalloc() should probably use unlikely() for
the failure case, so that the uncommon vmalloc() fallback is out-of-line
in this more important codepath.  The only other callers are during mount,
so a branch misprediction is not critical.

Cheers, Andreas

> 
> Signed-off-by: Kirill A. Shutemov <kirill.shutemov@...ux.intel.com>
> ---
> fs/ext4/readpage.c | 38 ++++++++++++++++++++++++++++++++------
> 1 file changed, 32 insertions(+), 6 deletions(-)
> 
> diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c
> index a81b829d56de..6d7cbddceeb2 100644
> --- a/fs/ext4/readpage.c
> +++ b/fs/ext4/readpage.c
> @@ -104,12 +104,12 @@ int ext4_mpage_readpages(struct address_space *mapping,
> 
> 	struct inode *inode = mapping->host;
> 	const unsigned blkbits = inode->i_blkbits;
> -	const unsigned blocks_per_page = PAGE_SIZE >> blkbits;
> 	const unsigned blocksize = 1 << blkbits;
> 	sector_t block_in_file;
> 	sector_t last_block;
> 	sector_t last_block_in_file;
> -	sector_t blocks[MAX_BUF_PER_PAGE];
> +	sector_t blocks_on_stack[MAX_BUF_PER_PAGE];
> +	sector_t *blocks = blocks_on_stack;
> 	unsigned page_block;
> 	struct block_device *bdev = inode->i_sb->s_bdev;
> 	int length;
> @@ -122,8 +122,9 @@ int ext4_mpage_readpages(struct address_space *mapping,
> 	map.m_flags = 0;
> 
> 	for (; nr_pages; nr_pages--) {
> -		int fully_mapped = 1;
> -		unsigned first_hole = blocks_per_page;
> +		int fully_mapped = 1, nr = nr_pages;
> +		unsigned blocks_per_page = PAGE_SIZE >> blkbits;
> +		unsigned first_hole;
> 
> 		prefetchw(&page->flags);
> 		if (pages) {
> @@ -138,10 +139,31 @@ int ext4_mpage_readpages(struct address_space *mapping,
> 			goto confused;
> 
> 		block_in_file = (sector_t)page->index << (PAGE_SHIFT - blkbits);
> -		last_block = block_in_file + nr_pages * blocks_per_page;
> +
> +		if (PageTransHuge(page)) {
> +			BUILD_BUG_ON(BIO_MAX_PAGES < HPAGE_PMD_NR);
> +			nr = HPAGE_PMD_NR * blocks_per_page;
> +			/* XXX: need a better solution ? */
> +			blocks = kmalloc(sizeof(sector_t) * nr, GFP_NOFS);
> +			if (!blocks) {
> +				if (pages) {
> +					delete_from_page_cache(page);
> +					goto next_page;
> +				}
> +				return -ENOMEM;
> +			}
> +
> +			blocks_per_page *= HPAGE_PMD_NR;
> +			last_block = block_in_file + blocks_per_page;
> +		} else {
> +			blocks = blocks_on_stack;
> +			last_block = block_in_file + nr * blocks_per_page;
> +		}
> +
> 		last_block_in_file = (i_size_read(inode) + blocksize - 1) >> blkbits;
> 		if (last_block > last_block_in_file)
> 			last_block = last_block_in_file;
> +		first_hole = blocks_per_page;
> 		page_block = 0;
> 
> 		/*
> @@ -213,6 +235,8 @@ int ext4_mpage_readpages(struct address_space *mapping,
> 			}
> 		}
> 		if (first_hole != blocks_per_page) {
> +			if (PageTransHuge(page))
> +				goto confused;
> 			zero_user_segment(page, first_hole << blkbits,
> 					  PAGE_SIZE);
> 			if (first_hole == 0) {
> @@ -248,7 +272,7 @@ int ext4_mpage_readpages(struct address_space *mapping,
> 					goto set_error_page;
> 			}
> 			bio = bio_alloc(GFP_KERNEL,
> -				min_t(int, nr_pages, BIO_MAX_PAGES));
> +				min_t(int, nr, BIO_MAX_PAGES));
> 			if (!bio) {
> 				if (ctx)
> 					fscrypt_release_ctx(ctx);
> @@ -289,5 +313,7 @@ int ext4_mpage_readpages(struct address_space *mapping,
> 	BUG_ON(pages && !list_empty(pages));
> 	if (bio)
> 		submit_bio(bio);
> +	if (blocks != blocks_on_stack)
> +		kfree(blocks);
> 	return 0;
> }
> --
> 2.9.3
> 


Cheers, Andreas






Download attachment "signature.asc" of type "application/pgp-signature" (834 bytes)