All of lore.kernel.org
 help / color / mirror / Atom feed
From: Joao Martins <joao.m.martins@oracle.com>
To: linux-mm@kvack.org
Cc: Dan Williams <dan.j.williams@intel.com>,
	Vishal Verma <vishal.l.verma@intel.com>,
	Dave Jiang <dave.jiang@intel.com>,
	Naoya Horiguchi <naoya.horiguchi@nec.com>,
	Matthew Wilcox <willy@infradead.org>,
	Jason Gunthorpe <jgg@ziepe.ca>,
	John Hubbard <jhubbard@nvidia.com>,
	Jane Chu <jane.chu@oracle.com>,
	Muchun Song <songmuchun@bytedance.com>,
	Mike Kravetz <mike.kravetz@oracle.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Jonathan Corbet <corbet@lwn.net>, Christoph Hellwig <hch@lst.de>,
	nvdimm@lists.linux.dev, linux-doc@vger.kernel.org,
	Joao Martins <joao.m.martins@oracle.com>
Subject: [PATCH v4 08/14] mm/gup: grab head page refcount once for group of subpages
Date: Fri, 27 Aug 2021 15:58:13 +0100	[thread overview]
Message-ID: <20210827145819.16471-9-joao.m.martins@oracle.com> (raw)
In-Reply-To: <20210827145819.16471-1-joao.m.martins@oracle.com>

Use try_grab_compound_head() for device-dax GUP when configured with a
compound devmap.

Rather than incrementing the refcount for each page, do one atomic
addition for all the pages to be pinned.

Performance measured by gup_benchmark improves considerably
get_user_pages_fast() and pin_user_pages_fast() with NVDIMMs:

 $ gup_test -f /dev/dax1.0 -m 16384 -r 10 -S [-u,-a] -n 512 -w
(get_user_pages_fast 2M pages) ~59 ms -> ~6.1 ms
(pin_user_pages_fast 2M pages) ~87 ms -> ~6.2 ms
[altmap]
(get_user_pages_fast 2M pages) ~494 ms -> ~9 ms
(pin_user_pages_fast 2M pages) ~494 ms -> ~10 ms

 $ gup_test -f /dev/dax1.0 -m 129022 -r 10 -S [-u,-a] -n 512 -w
(get_user_pages_fast 2M pages) ~492 ms -> ~49 ms
(pin_user_pages_fast 2M pages) ~493 ms -> ~50 ms
[altmap with -m 127004]
(get_user_pages_fast 2M pages) ~3.91 sec -> ~70 ms
(pin_user_pages_fast 2M pages) ~3.97 sec -> ~74 ms

Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
---
 mm/gup.c | 51 +++++++++++++++++++++++++++++++--------------------
 1 file changed, 31 insertions(+), 20 deletions(-)

diff --git a/mm/gup.c b/mm/gup.c
index 7a406d79bd2e..0741d2c0ba5e 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -2234,17 +2234,30 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 }
 #endif /* CONFIG_ARCH_HAS_PTE_SPECIAL */
 
+
+static int record_subpages(struct page *page, unsigned long addr,
+			   unsigned long end, struct page **pages)
+{
+	int nr;
+
+	for (nr = 0; addr != end; addr += PAGE_SIZE)
+		pages[nr++] = page++;
+
+	return nr;
+}
+
 #if defined(CONFIG_ARCH_HAS_PTE_DEVMAP) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
 static int __gup_device_huge(unsigned long pfn, unsigned long addr,
 			     unsigned long end, unsigned int flags,
 			     struct page **pages, int *nr)
 {
-	int nr_start = *nr;
+	int refs, nr_start = *nr;
 	struct dev_pagemap *pgmap = NULL;
 	int ret = 1;
 
 	do {
-		struct page *page = pfn_to_page(pfn);
+		struct page *head, *page = pfn_to_page(pfn);
+		unsigned long next = addr + PAGE_SIZE;
 
 		pgmap = get_dev_pagemap(pfn, pgmap);
 		if (unlikely(!pgmap)) {
@@ -2252,16 +2265,25 @@ static int __gup_device_huge(unsigned long pfn, unsigned long addr,
 			ret = 0;
 			break;
 		}
-		SetPageReferenced(page);
-		pages[*nr] = page;
-		if (unlikely(!try_grab_page(page, flags))) {
-			undo_dev_pagemap(nr, nr_start, flags, pages);
+
+		head = compound_head(page);
+		/* @end is assumed to be limited at most one compound page */
+		if (PageHead(head))
+			next = end;
+		refs = record_subpages(page, addr, next, pages + *nr);
+
+		SetPageReferenced(head);
+		if (unlikely(!try_grab_compound_head(head, refs, flags))) {
+			if (PageHead(head))
+				ClearPageReferenced(head);
+			else
+				undo_dev_pagemap(nr, nr_start, flags, pages);
 			ret = 0;
 			break;
 		}
-		(*nr)++;
-		pfn++;
-	} while (addr += PAGE_SIZE, addr != end);
+		*nr += refs;
+		pfn += refs;
+	} while (addr += (refs << PAGE_SHIFT), addr != end);
 
 	put_dev_pagemap(pgmap);
 	return ret;
@@ -2320,17 +2342,6 @@ static int __gup_device_huge_pud(pud_t pud, pud_t *pudp, unsigned long addr,
 }
 #endif
 
-static int record_subpages(struct page *page, unsigned long addr,
-			   unsigned long end, struct page **pages)
-{
-	int nr;
-
-	for (nr = 0; addr != end; addr += PAGE_SIZE)
-		pages[nr++] = page++;
-
-	return nr;
-}
-
 #ifdef CONFIG_ARCH_HAS_HUGEPD
 static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end,
 				      unsigned long sz)
-- 
2.17.1


  parent reply	other threads:[~2021-08-27 14:59 UTC|newest]

Thread overview: 48+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-08-27 14:58 [PATCH v4 00/14] mm, sparse-vmemmap: Introduce compound devmaps for device-dax Joao Martins
2021-08-27 14:58 ` [PATCH v4 01/14] memory-failure: fetch compound_head after pgmap_pfn_valid() Joao Martins
2021-08-27 14:58 ` [PATCH v4 02/14] mm/page_alloc: split prep_compound_page into head and tail subparts Joao Martins
2021-08-27 14:58 ` [PATCH v4 03/14] mm/page_alloc: refactor memmap_init_zone_device() page init Joao Martins
2021-08-27 14:58 ` [PATCH v4 04/14] mm/memremap: add ZONE_DEVICE support for compound pages Joao Martins
2021-08-27 15:33   ` Christoph Hellwig
2021-08-27 16:00     ` Joao Martins
2021-09-01  9:44       ` Christoph Hellwig
2021-09-09  9:38         ` Joao Martins
2021-08-27 14:58 ` [PATCH v4 05/14] device-dax: use ALIGN() for determining pgoff Joao Martins
2021-08-27 14:58 ` [PATCH v4 06/14] device-dax: ensure dev_dax->pgmap is valid for dynamic devices Joao Martins
2021-11-05  0:31   ` Dan Williams
2021-11-05 12:09     ` Joao Martins
2021-11-05 16:14       ` Joao Martins
2021-11-05 16:46       ` Dan Williams
2021-11-05 18:11         ` Joao Martins
2021-08-27 14:58 ` [PATCH v4 07/14] device-dax: compound devmap support Joao Martins
2021-11-05  0:38   ` Dan Williams
2021-11-05 14:10     ` Joao Martins
2021-11-05 16:41       ` Dan Williams
2021-08-27 14:58 ` Joao Martins [this message]
2021-08-27 16:25   ` [PATCH v4 08/14] mm/gup: grab head page refcount once for group of subpages Jason Gunthorpe
2021-08-27 18:34     ` Joao Martins
2021-08-30 13:07       ` Jason Gunthorpe
2021-08-31 12:34         ` Joao Martins
2021-08-31 17:05           ` Jason Gunthorpe
2021-09-23 16:51             ` Joao Martins
2021-09-28 18:01               ` Jason Gunthorpe
2021-09-29 11:50                 ` Joao Martins
2021-09-29 19:34                   ` Jason Gunthorpe
2021-09-30  3:01                     ` Alistair Popple
2021-09-30 17:54                       ` Joao Martins
2021-09-30 21:55                         ` Jason Gunthorpe
2021-10-18 18:36                       ` Jason Gunthorpe
2021-10-18 18:37                   ` Jason Gunthorpe
2021-10-08 11:54   ` Jason Gunthorpe
2021-10-11 15:53     ` Joao Martins
2021-10-13 17:41       ` Jason Gunthorpe
2021-10-13 19:18         ` Joao Martins
2021-10-13 19:43           ` Jason Gunthorpe
2021-10-14 17:56             ` Joao Martins
2021-10-14 18:06               ` Jason Gunthorpe
2021-08-27 14:58 ` [PATCH v4 09/14] mm/sparse-vmemmap: add a pgmap argument to section activation Joao Martins
2021-08-27 14:58 ` [PATCH v4 10/14] mm/sparse-vmemmap: refactor core of vmemmap_populate_basepages() to helper Joao Martins
2021-08-27 14:58 ` [PATCH v4 11/14] mm/hugetlb_vmemmap: move comment block to Documentation/vm Joao Martins
2021-08-27 14:58 ` [PATCH v4 12/14] mm/sparse-vmemmap: populate compound devmaps Joao Martins
2021-08-27 14:58 ` [PATCH v4 13/14] mm/page_alloc: reuse tail struct pages for " Joao Martins
2021-08-27 14:58 ` [PATCH v4 14/14] mm/sparse-vmemmap: improve memory savings for compound pud geometry Joao Martins

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=20210827145819.16471-9-joao.m.martins@oracle.com \
    --to=joao.m.martins@oracle.com \
    --cc=akpm@linux-foundation.org \
    --cc=corbet@lwn.net \
    --cc=dan.j.williams@intel.com \
    --cc=dave.jiang@intel.com \
    --cc=hch@lst.de \
    --cc=jane.chu@oracle.com \
    --cc=jgg@ziepe.ca \
    --cc=jhubbard@nvidia.com \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mike.kravetz@oracle.com \
    --cc=naoya.horiguchi@nec.com \
    --cc=nvdimm@lists.linux.dev \
    --cc=songmuchun@bytedance.com \
    --cc=vishal.l.verma@intel.com \
    --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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.