Linux-Fsdevel Archive on lore.kernel.org
 help / color / Atom feed
From: Matthew Wilcox <willy@infradead.org>
To: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: linux-fsdevel@vger.kernel.org, linux-mm@kvack.org,
	linux-kernel@vger.kernel.org
Subject: Re: [PATCH v2 13/25] fs: Add zero_user_large
Date: Fri, 14 Feb 2020 08:03:42 -0800
Message-ID: <20200214160342.GA7778@bombadil.infradead.org> (raw)
In-Reply-To: <20200214135248.zqcqx3erb4pnlvmu@box>

On Fri, Feb 14, 2020 at 04:52:48PM +0300, Kirill A. Shutemov wrote:
> On Tue, Feb 11, 2020 at 08:18:33PM -0800, Matthew Wilcox wrote:
> > From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
> > 
> > We can't kmap() a THP, so add a wrapper around zero_user() for large
> > pages.
> 
> I would rather address it closer to the root: make zero_user_segments()
> handle compound pages.

Hah.  I ended up doing that, but hadn't sent it out.  I don't like
how ugly it is:

@@ -219,18 +219,57 @@ static inline void zero_user_segments(struct page *page,
        unsigned start1, unsigned end1,
        unsigned start2, unsigned end2)
 {
-       void *kaddr = kmap_atomic(page);
-
-       BUG_ON(end1 > PAGE_SIZE || end2 > PAGE_SIZE);
-
-       if (end1 > start1)
-               memset(kaddr + start1, 0, end1 - start1);
-
-       if (end2 > start2)
-               memset(kaddr + start2, 0, end2 - start2);
-
-       kunmap_atomic(kaddr);
-       flush_dcache_page(page);
+       unsigned int i;
+
+       BUG_ON(end1 > thp_size(page) || end2 > thp_size(page));
+
+       for (i = 0; i < hpage_nr_pages(page); i++) {
+               void *kaddr;
+               unsigned this_end;
+
+               if (end1 == 0 && start2 >= PAGE_SIZE) {
+                       start2 -= PAGE_SIZE;
+                       end2 -= PAGE_SIZE;
+                       continue;
+               }
+
+               if (start1 >= PAGE_SIZE) {
+                       start1 -= PAGE_SIZE;
+                       end1 -= PAGE_SIZE;
+                       if (start2) {
+                               start2 -= PAGE_SIZE;
+                               end2 -= PAGE_SIZE;
+                       }
+                       continue;
+               }
+
+               kaddr = kmap_atomic(page + i);
+
+               this_end = min_t(unsigned, end1, PAGE_SIZE);
+               if (end1 > start1)
+                       memset(kaddr + start1, 0, this_end - start1);
+               end1 -= this_end;
+               start1 = 0;
+
+               if (start2 >= PAGE_SIZE) {
+                       start2 -= PAGE_SIZE;
+                       end2 -= PAGE_SIZE;
+               } else {
+                       this_end = min_t(unsigned, end2, PAGE_SIZE);
+                       if (end2 > start2)
+                               memset(kaddr + start2, 0, this_end - start2);
+                       end2 -= this_end;
+                       start2 = 0;
+               }
+
+               kunmap_atomic(kaddr);
+               flush_dcache_page(page + i);
+
+               if (!end1 && !end2)
+                       break;
+       }
+
+       BUG_ON((start1 | start2 | end1 | end2) != 0);
 }

I think at this point it has to move out-of-line too.

> > +static inline void zero_user_large(struct page *page,
> > +		unsigned start, unsigned size)
> > +{
> > +	unsigned int i;
> > +
> > +	for (i = 0; i < thp_order(page); i++) {
> > +		if (start > PAGE_SIZE) {
> 
> Off-by-one? >= ?

Good catch; I'd also noticed that when I came to redo the zero_user_segments().


  reply index

Thread overview: 68+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-02-12  4:18 [PATCH v2 00/25] Large pages in the page cache Matthew Wilcox
2020-02-12  4:18 ` [PATCH v2 01/25] mm: Use vm_fault error code directly Matthew Wilcox
2020-02-12  7:34   ` Christoph Hellwig
2020-02-12  4:18 ` [PATCH v2 02/25] mm: Optimise find_subpage for !THP Matthew Wilcox
2020-02-12  7:41   ` Christoph Hellwig
2020-02-12 13:02     ` Matthew Wilcox
2020-02-12 17:52       ` Christoph Hellwig
2020-02-13 13:50       ` Kirill A. Shutemov
2020-02-12  4:18 ` [PATCH v2 03/25] mm: Use VM_BUG_ON_PAGE in clear_page_dirty_for_io Matthew Wilcox
2020-02-12  7:38   ` Christoph Hellwig
2020-02-13 13:50   ` Kirill A. Shutemov
2020-02-12  4:18 ` [PATCH v2 04/25] mm: Unexport find_get_entry Matthew Wilcox
2020-02-12  7:37   ` Christoph Hellwig
2020-02-13 13:51   ` Kirill A. Shutemov
2020-02-12  4:18 ` [PATCH v2 05/25] mm: Fix documentation of FGP flags Matthew Wilcox
2020-02-12  7:42   ` Christoph Hellwig
2020-02-12 19:11     ` Matthew Wilcox
2020-02-13 14:00       ` Kirill A. Shutemov
2020-02-13 13:59   ` Kirill A. Shutemov
2020-02-13 14:34     ` Matthew Wilcox
2020-02-12  4:18 ` [PATCH v2 06/25] mm: Allow hpages to be arbitrary order Matthew Wilcox
2020-02-13 14:11   ` Kirill A. Shutemov
2020-02-13 14:30     ` Matthew Wilcox
2020-02-12  4:18 ` [PATCH v2 07/25] mm: Introduce thp_size Matthew Wilcox
2020-02-13 14:19   ` Kirill A. Shutemov
2020-02-12  4:18 ` [PATCH v2 08/25] mm: Introduce thp_order Matthew Wilcox
2020-02-13 14:20   ` Kirill A. Shutemov
2020-02-12  4:18 ` [PATCH v2 09/25] fs: Add a filesystem flag for large pages Matthew Wilcox
2020-02-12  7:43   ` Christoph Hellwig
2020-02-12 14:59     ` Matthew Wilcox
2020-02-12  4:18 ` [PATCH v2 10/25] fs: Introduce i_blocks_per_page Matthew Wilcox
2020-02-12  7:44   ` Christoph Hellwig
2020-02-12 15:05     ` Matthew Wilcox
2020-02-12 17:54       ` Christoph Hellwig
2020-02-13 15:40   ` Kirill A. Shutemov
2020-02-13 16:07     ` Matthew Wilcox
2020-02-12  4:18 ` [PATCH v2 11/25] fs: Make page_mkwrite_check_truncate thp-aware Matthew Wilcox
2020-02-13 15:44   ` Kirill A. Shutemov
2020-02-13 16:26     ` Matthew Wilcox
2020-02-12  4:18 ` [PATCH v2 12/25] mm: Add file_offset_of_ helpers Matthew Wilcox
2020-02-12  7:46   ` Christoph Hellwig
2020-02-12  4:18 ` [PATCH v2 13/25] fs: Add zero_user_large Matthew Wilcox
2020-02-14 13:52   ` Kirill A. Shutemov
2020-02-14 16:03     ` Matthew Wilcox [this message]
2020-02-18 14:16       ` Kirill A. Shutemov
2020-02-18 16:13         ` Matthew Wilcox
2020-02-18 17:10           ` Kirill A. Shutemov
2020-02-18 18:07             ` Matthew Wilcox
2020-02-21 12:42               ` Kirill A. Shutemov
2020-02-12  4:18 ` [PATCH v2 14/25] iomap: Support arbitrarily many blocks per page Matthew Wilcox
2020-02-12  8:05   ` Christoph Hellwig
2020-02-12  4:18 ` [PATCH v2 15/25] iomap: Support large pages in iomap_adjust_read_range Matthew Wilcox
2020-02-12  8:11   ` Christoph Hellwig
2020-02-12  4:18 ` [PATCH v2 16/25] iomap: Support large pages in read paths Matthew Wilcox
2020-02-12  8:13   ` Christoph Hellwig
2020-02-12 17:45     ` Matthew Wilcox
2020-02-12  4:18 ` [PATCH v2 17/25] iomap: Support large pages in write paths Matthew Wilcox
2020-02-12  8:17   ` Christoph Hellwig
2020-02-12  4:18 ` [PATCH v2 18/25] iomap: Inline data shouldn't see large pages Matthew Wilcox
2020-02-12  8:05   ` Christoph Hellwig
2020-02-12  4:18 ` [PATCH v2 19/25] xfs: Support " Matthew Wilcox
2020-02-12  4:18 ` [PATCH v2 20/25] mm: Make prep_transhuge_page return its argument Matthew Wilcox
2020-02-12  4:18 ` [PATCH v2 21/25] mm: Add __page_cache_alloc_order Matthew Wilcox
2020-02-12  4:18 ` [PATCH v2 22/25] mm: Allow large pages to be added to the page cache Matthew Wilcox
2020-02-12  4:18 ` [PATCH v2 23/25] mm: Allow large pages to be removed from " Matthew Wilcox
2020-02-12  4:18 ` [PATCH v2 24/25] mm: Add large page readahead Matthew Wilcox
2020-02-12  4:18 ` [PATCH v2 25/25] mm: Align THP mappings for non-DAX Matthew Wilcox
2020-02-12  7:50   ` Christoph Hellwig

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=20200214160342.GA7778@bombadil.infradead.org \
    --to=willy@infradead.org \
    --cc=kirill@shutemov.name \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.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

Linux-Fsdevel Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-fsdevel/0 linux-fsdevel/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-fsdevel linux-fsdevel/ https://lore.kernel.org/linux-fsdevel \
		linux-fsdevel@vger.kernel.org
	public-inbox-index linux-fsdevel

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-fsdevel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git