All of lore.kernel.org
 help / color / mirror / Atom feed
From: Joao Martins <joao.m.martins@oracle.com>
To: linux-mm@kvack.org
Cc: linux-nvdimm@lists.01.org, Matthew Wilcox <willy@infradead.org>,
	Jason Gunthorpe <jgg@ziepe.ca>,
	Muchun Song <songmuchun@bytedance.com>,
	Mike Kravetz <mike.kravetz@oracle.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Joao Martins <joao.m.martins@oracle.com>
Subject: [PATCH RFC 6/9] mm/gup: Grab head page refcount once for group of subpages
Date: Tue,  8 Dec 2020 17:28:58 +0000	[thread overview]
Message-ID: <20201208172901.17384-8-joao.m.martins@oracle.com> (raw)
In-Reply-To: <20201208172901.17384-1-joao.m.martins@oracle.com>

Much like hugetlbfs or THPs, we treat device pagemaps with
compound pages like the rest of GUP handling of compound pages.

Rather than incrementing the refcount every 4K, we record
all sub pages and increment by @refs amount *once*.

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

 $ gup_benchmark -f /dev/dax0.2 -m 16384 -r 10 -S [-u,-a] -n 512 -w

(get_user_pages_fast 2M pages) ~75k us -> ~3.6k us
(pin_user_pages_fast 2M pages) ~125k us -> ~3.8k us

Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
---
 mm/gup.c | 67 ++++++++++++++++++++++++++++++++++++++++++--------------
 1 file changed, 51 insertions(+), 16 deletions(-)

diff --git a/mm/gup.c b/mm/gup.c
index 98eb8e6d2609..194e6981eb03 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -2250,22 +2250,68 @@ 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)
+static int __gup_device_compound_huge(struct dev_pagemap *pgmap,
+				      struct page *head, unsigned long sz,
+				      unsigned long addr, unsigned long end,
+				      unsigned int flags, struct page **pages)
+{
+	struct page *page;
+	int refs;
+
+	if (!(pgmap->flags & PGMAP_COMPOUND))
+		return -1;
+
+	page = head + ((addr & (sz-1)) >> PAGE_SHIFT);
+	refs = record_subpages(page, addr, end, pages);
+
+	SetPageReferenced(page);
+	head = try_grab_compound_head(head, refs, flags);
+	if (!head) {
+		ClearPageReferenced(page);
+		return 0;
+	}
+
+	return refs;
+}
+
+static int __gup_device_huge(unsigned long pfn, unsigned long sz,
+			     unsigned long addr, unsigned long end,
+			     unsigned int flags, struct page **pages, int *nr)
 {
 	int nr_start = *nr;
 	struct dev_pagemap *pgmap = NULL;
 
 	do {
 		struct page *page = pfn_to_page(pfn);
+		int refs;
 
 		pgmap = get_dev_pagemap(pfn, pgmap);
 		if (unlikely(!pgmap)) {
 			undo_dev_pagemap(nr, nr_start, flags, pages);
 			return 0;
 		}
+
+		refs = __gup_device_compound_huge(pgmap, page, sz, addr, end,
+						  flags, pages + *nr);
+		if (refs >= 0) {
+			*nr += refs;
+			put_dev_pagemap(pgmap);
+			return refs ? 1 : 0;
+		}
+
 		SetPageReferenced(page);
 		pages[*nr] = page;
 		if (unlikely(!try_grab_page(page, flags))) {
@@ -2289,7 +2335,7 @@ static int __gup_device_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 	int nr_start = *nr;
 
 	fault_pfn = pmd_pfn(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
-	if (!__gup_device_huge(fault_pfn, addr, end, flags, pages, nr))
+	if (!__gup_device_huge(fault_pfn, PMD_SHIFT, addr, end, flags, pages, nr))
 		return 0;
 
 	if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) {
@@ -2307,7 +2353,7 @@ static int __gup_device_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
 	int nr_start = *nr;
 
 	fault_pfn = pud_pfn(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
-	if (!__gup_device_huge(fault_pfn, addr, end, flags, pages, nr))
+	if (!__gup_device_huge(fault_pfn, PUD_SHIFT, addr, end, flags, pages, nr))
 		return 0;
 
 	if (unlikely(pud_val(orig) != pud_val(*pudp))) {
@@ -2334,17 +2380,6 @@ 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
_______________________________________________
Linux-nvdimm mailing list -- linux-nvdimm@lists.01.org
To unsubscribe send an email to linux-nvdimm-leave@lists.01.org

WARNING: multiple messages have this Message-ID
From: Joao Martins <joao.m.martins@oracle.com>
To: linux-mm@kvack.org
Cc: Dan Williams <dan.j.williams@intel.com>,
	Ira Weiny <ira.weiny@intel.com>,
	linux-nvdimm@lists.01.org, Matthew Wilcox <willy@infradead.org>,
	Jason Gunthorpe <jgg@ziepe.ca>, Jane Chu <jane.chu@oracle.com>,
	Muchun Song <songmuchun@bytedance.com>,
	Mike Kravetz <mike.kravetz@oracle.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Joao Martins <joao.m.martins@oracle.com>
Subject: [PATCH RFC 6/9] mm/gup: Grab head page refcount once for group of subpages
Date: Tue,  8 Dec 2020 17:28:58 +0000	[thread overview]
Message-ID: <20201208172901.17384-8-joao.m.martins@oracle.com> (raw)
In-Reply-To: <20201208172901.17384-1-joao.m.martins@oracle.com>

Much like hugetlbfs or THPs, we treat device pagemaps with
compound pages like the rest of GUP handling of compound pages.

Rather than incrementing the refcount every 4K, we record
all sub pages and increment by @refs amount *once*.

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

 $ gup_benchmark -f /dev/dax0.2 -m 16384 -r 10 -S [-u,-a] -n 512 -w

(get_user_pages_fast 2M pages) ~75k us -> ~3.6k us
(pin_user_pages_fast 2M pages) ~125k us -> ~3.8k us

Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
---
 mm/gup.c | 67 ++++++++++++++++++++++++++++++++++++++++++--------------
 1 file changed, 51 insertions(+), 16 deletions(-)

diff --git a/mm/gup.c b/mm/gup.c
index 98eb8e6d2609..194e6981eb03 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -2250,22 +2250,68 @@ 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)
+static int __gup_device_compound_huge(struct dev_pagemap *pgmap,
+				      struct page *head, unsigned long sz,
+				      unsigned long addr, unsigned long end,
+				      unsigned int flags, struct page **pages)
+{
+	struct page *page;
+	int refs;
+
+	if (!(pgmap->flags & PGMAP_COMPOUND))
+		return -1;
+
+	page = head + ((addr & (sz-1)) >> PAGE_SHIFT);
+	refs = record_subpages(page, addr, end, pages);
+
+	SetPageReferenced(page);
+	head = try_grab_compound_head(head, refs, flags);
+	if (!head) {
+		ClearPageReferenced(page);
+		return 0;
+	}
+
+	return refs;
+}
+
+static int __gup_device_huge(unsigned long pfn, unsigned long sz,
+			     unsigned long addr, unsigned long end,
+			     unsigned int flags, struct page **pages, int *nr)
 {
 	int nr_start = *nr;
 	struct dev_pagemap *pgmap = NULL;
 
 	do {
 		struct page *page = pfn_to_page(pfn);
+		int refs;
 
 		pgmap = get_dev_pagemap(pfn, pgmap);
 		if (unlikely(!pgmap)) {
 			undo_dev_pagemap(nr, nr_start, flags, pages);
 			return 0;
 		}
+
+		refs = __gup_device_compound_huge(pgmap, page, sz, addr, end,
+						  flags, pages + *nr);
+		if (refs >= 0) {
+			*nr += refs;
+			put_dev_pagemap(pgmap);
+			return refs ? 1 : 0;
+		}
+
 		SetPageReferenced(page);
 		pages[*nr] = page;
 		if (unlikely(!try_grab_page(page, flags))) {
@@ -2289,7 +2335,7 @@ static int __gup_device_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 	int nr_start = *nr;
 
 	fault_pfn = pmd_pfn(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
-	if (!__gup_device_huge(fault_pfn, addr, end, flags, pages, nr))
+	if (!__gup_device_huge(fault_pfn, PMD_SHIFT, addr, end, flags, pages, nr))
 		return 0;
 
 	if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) {
@@ -2307,7 +2353,7 @@ static int __gup_device_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
 	int nr_start = *nr;
 
 	fault_pfn = pud_pfn(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
-	if (!__gup_device_huge(fault_pfn, addr, end, flags, pages, nr))
+	if (!__gup_device_huge(fault_pfn, PUD_SHIFT, addr, end, flags, pages, nr))
 		return 0;
 
 	if (unlikely(pud_val(orig) != pud_val(*pudp))) {
@@ -2334,17 +2380,6 @@ 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:[~2020-12-08 17:30 UTC|newest]

Thread overview: 147+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-12-08 17:28 [PATCH RFC 0/9] mm, sparse-vmemmap: Introduce compound pagemaps Joao Martins
2020-12-08 17:28 ` Joao Martins
2020-12-08 17:28 ` [PATCH RFC 1/9] memremap: add ZONE_DEVICE support for compound pages Joao Martins
2020-12-08 17:28   ` Joao Martins
2020-12-09  5:59   ` John Hubbard
2020-12-09  5:59     ` John Hubbard
2020-12-09  6:33     ` Matthew Wilcox
2020-12-09  6:33       ` Matthew Wilcox
2020-12-09 13:12       ` Joao Martins
2020-12-09 13:12         ` Joao Martins
2021-02-20  1:43     ` Dan Williams
2021-02-20  1:43       ` Dan Williams
2021-02-22 11:24       ` Joao Martins
2021-02-22 11:24         ` Joao Martins
2021-02-22 20:37         ` Dan Williams
2021-02-22 20:37           ` Dan Williams
2021-02-23 15:46           ` Joao Martins
2021-02-23 15:46             ` Joao Martins
2021-02-23 16:50             ` Dan Williams
2021-02-23 16:50               ` Dan Williams
2021-02-23 17:18               ` Joao Martins
2021-02-23 17:18                 ` Joao Martins
2021-02-23 18:18                 ` Dan Williams
2021-02-23 18:18                   ` Dan Williams
2021-03-10 18:12           ` Joao Martins
2021-03-10 18:12             ` Joao Martins
2021-03-12  5:54             ` Dan Williams
2021-03-12  5:54               ` Dan Williams
2021-02-20  1:24   ` Dan Williams
2021-02-20  1:24     ` Dan Williams
2021-02-22 11:09     ` Joao Martins
2021-02-22 11:09       ` Joao Martins
2020-12-08 17:28 ` [PATCH RFC 2/9] sparse-vmemmap: Consolidate arguments in vmemmap section populate Joao Martins
2020-12-08 17:28   ` Joao Martins
2020-12-09  6:16   ` John Hubbard
2020-12-09  6:16     ` John Hubbard
2020-12-09 13:51     ` Joao Martins
2020-12-09 13:51       ` Joao Martins
2021-02-20  1:49   ` Dan Williams
2021-02-20  1:49     ` Dan Williams
2021-02-22 11:26     ` Joao Martins
2021-02-22 11:26       ` Joao Martins
2020-12-08 17:28 ` [PATCH RFC 3/9] sparse-vmemmap: Reuse vmemmap areas for a given mhp_params::align Joao Martins
2020-12-08 17:28   ` Joao Martins
2020-12-08 17:38   ` Joao Martins
2020-12-08 17:38     ` Joao Martins
2020-12-08 17:28 ` [PATCH RFC 3/9] sparse-vmemmap: Reuse vmemmap areas for a given page size Joao Martins
2020-12-08 17:28   ` Joao Martins
2021-02-20  3:34   ` Dan Williams
2021-02-20  3:34     ` Dan Williams
2021-02-22 11:42     ` Joao Martins
2021-02-22 11:42       ` Joao Martins
2021-02-22 22:40       ` Dan Williams
2021-02-22 22:40         ` Dan Williams
2021-02-23 15:46         ` Joao Martins
2021-02-23 15:46           ` Joao Martins
2020-12-08 17:28 ` [PATCH RFC 4/9] mm/page_alloc: Reuse tail struct pages for compound pagemaps Joao Martins
2020-12-08 17:28   ` Joao Martins
2021-02-20  6:17   ` Dan Williams
2021-02-20  6:17     ` Dan Williams
2021-02-22 12:01     ` Joao Martins
2021-02-22 12:01       ` Joao Martins
2020-12-08 17:28 ` [PATCH RFC 5/9] device-dax: Compound pagemap support Joao Martins
2020-12-08 17:28   ` Joao Martins
2020-12-08 17:28 ` Joao Martins [this message]
2020-12-08 17:28   ` [PATCH RFC 6/9] mm/gup: Grab head page refcount once for group of subpages Joao Martins
2020-12-08 19:49   ` Jason Gunthorpe
2020-12-09 11:05     ` Joao Martins
2020-12-09 11:05       ` Joao Martins
2020-12-09 15:15       ` Jason Gunthorpe
2020-12-09 16:02         ` Joao Martins
2020-12-09 16:02           ` Joao Martins
2020-12-09 16:24           ` Jason Gunthorpe
2020-12-09 17:27             ` Joao Martins
2020-12-09 17:27               ` Joao Martins
2020-12-09 18:14             ` Matthew Wilcox
2020-12-09 18:14               ` Matthew Wilcox
2020-12-09 19:08               ` Jason Gunthorpe
2020-12-10 15:43               ` Joao Martins
2020-12-10 15:43                 ` Joao Martins
2020-12-09  4:40   ` John Hubbard
2020-12-09  4:40     ` John Hubbard
2020-12-09 13:44     ` Joao Martins
2020-12-09 13:44       ` Joao Martins
2020-12-08 17:28 ` [PATCH RFC 7/9] mm/gup: Decrement head page " Joao Martins
2020-12-08 17:28   ` Joao Martins
2020-12-08 19:34   ` Jason Gunthorpe
2020-12-09  5:06     ` John Hubbard
2020-12-09  5:06       ` John Hubbard
2020-12-09 13:43       ` Jason Gunthorpe
2020-12-09 12:17     ` Joao Martins
2020-12-09 12:17       ` Joao Martins
2020-12-17 19:05     ` Joao Martins
2020-12-17 19:05       ` Joao Martins
2020-12-17 20:05       ` Jason Gunthorpe
2020-12-17 22:34         ` Joao Martins
2020-12-17 22:34           ` Joao Martins
2020-12-18 14:25           ` Jason Gunthorpe
2020-12-19  2:06         ` John Hubbard
2020-12-19  2:06           ` John Hubbard
2020-12-19 13:10           ` Joao Martins
2020-12-19 13:10             ` Joao Martins
2020-12-08 17:29 ` [PATCH RFC 8/9] RDMA/umem: batch page unpin in __ib_mem_release() Joao Martins
2020-12-08 17:29   ` Joao Martins
2020-12-08 19:29   ` Jason Gunthorpe
2020-12-09 10:59     ` Joao Martins
2020-12-09 10:59       ` Joao Martins
2020-12-19 13:15       ` Joao Martins
2020-12-19 13:15         ` Joao Martins
2020-12-09  5:18   ` John Hubbard
2020-12-09  5:18     ` John Hubbard
2020-12-08 17:29 ` [PATCH RFC 9/9] mm: Add follow_devmap_page() for devdax vmas Joao Martins
2020-12-08 17:29   ` Joao Martins
2020-12-08 19:57   ` Jason Gunthorpe
2020-12-09  8:05     ` Christoph Hellwig
2020-12-09  8:05       ` Christoph Hellwig
2020-12-09 11:19     ` Joao Martins
2020-12-09 11:19       ` Joao Martins
2020-12-09  5:23   ` John Hubbard
2020-12-09  5:23     ` John Hubbard
2020-12-09  9:38 ` [PATCH RFC 0/9] mm, sparse-vmemmap: Introduce compound pagemaps David Hildenbrand
2020-12-09  9:38   ` David Hildenbrand
2020-12-09  9:52 ` [External] " Muchun Song
2020-12-09  9:52   ` Muchun Song
2021-02-20  1:18 ` Dan Williams
2021-02-20  1:18   ` Dan Williams
2021-02-22 11:06   ` Joao Martins
2021-02-22 11:06     ` Joao Martins
2021-02-22 14:32     ` Joao Martins
2021-02-22 14:32       ` Joao Martins
2021-02-23 16:28   ` Joao Martins
2021-02-23 16:28     ` Joao Martins
2021-02-23 16:44     ` Dan Williams
2021-02-23 16:44       ` Dan Williams
2021-02-23 17:15       ` Joao Martins
2021-02-23 17:15         ` Joao Martins
2021-02-23 18:15         ` Dan Williams
2021-02-23 18:15           ` Dan Williams
2021-02-23 18:54       ` Jason Gunthorpe
2021-02-23 22:48         ` Dan Williams
2021-02-23 22:48           ` Dan Williams
2021-02-23 23:07           ` Jason Gunthorpe
2021-02-24  0:14             ` Dan Williams
2021-02-24  0:14               ` Dan Williams
2021-02-24  1:00               ` Jason Gunthorpe
2021-02-24  1:32                 ` Dan Williams
2021-02-24  1:32                   ` Dan Williams

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=20201208172901.17384-8-joao.m.martins@oracle.com \
    --to=joao.m.martins@oracle.com \
    --cc=akpm@linux-foundation.org \
    --cc=jgg@ziepe.ca \
    --cc=linux-mm@kvack.org \
    --cc=linux-nvdimm@lists.01.org \
    --cc=mike.kravetz@oracle.com \
    --cc=songmuchun@bytedance.com \
    --cc=willy@infradead.org \
    --subject='Re: [PATCH RFC 6/9] mm/gup: Grab head page refcount once for group of subpages' \
    /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

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.