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>,
	nvdimm@lists.linux.dev, linux-doc@vger.kernel.org,
	Joao Martins <joao.m.martins@oracle.com>
Subject: [PATCH v2 04/14] mm/memremap: add ZONE_DEVICE support for compound pages
Date: Thu, 17 Jun 2021 19:44:57 +0100	[thread overview]
Message-ID: <20210617184507.3662-5-joao.m.martins@oracle.com> (raw)
In-Reply-To: <20210617184507.3662-1-joao.m.martins@oracle.com>

Add a new align property for struct dev_pagemap which specifies that a
pagemap is composed of a set of compound pages of size @align, instead of
base pages. When a compound page geometry is requested, all but the first
page are initialised as tail pages instead of order-0 pages.

For certain ZONE_DEVICE users like device-dax which have a fixed page size,
this creates an opportunity to optimize GUP and GUP-fast walkers, treating
it the same way as THP or hugetlb pages.

Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
---
 include/linux/memremap.h | 17 +++++++++++++++++
 mm/memremap.c            |  8 ++++++--
 mm/page_alloc.c          | 34 +++++++++++++++++++++++++++++++++-
 3 files changed, 56 insertions(+), 3 deletions(-)

diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index 119f130ef8f1..e5ab6d4525c1 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -99,6 +99,10 @@ struct dev_pagemap_ops {
  * @done: completion for @internal_ref
  * @type: memory type: see MEMORY_* in memory_hotplug.h
  * @flags: PGMAP_* flags to specify defailed behavior
+ * @geometry: structural definition of how the vmemmap metadata is populated.
+ *	A zero or PAGE_SIZE defaults to using base pages as the memmap metadata
+ *	representation. A bigger value but also multiple of PAGE_SIZE will set
+ *	up compound struct pages representative of the requested geometry size.
  * @ops: method table
  * @owner: an opaque pointer identifying the entity that manages this
  *	instance.  Used by various helpers to make sure that no
@@ -114,6 +118,7 @@ struct dev_pagemap {
 	struct completion done;
 	enum memory_type type;
 	unsigned int flags;
+	unsigned long geometry;
 	const struct dev_pagemap_ops *ops;
 	void *owner;
 	int nr_range;
@@ -130,6 +135,18 @@ static inline struct vmem_altmap *pgmap_altmap(struct dev_pagemap *pgmap)
 	return NULL;
 }
 
+static inline unsigned long pgmap_geometry(struct dev_pagemap *pgmap)
+{
+	if (!pgmap || !pgmap->geometry)
+		return PAGE_SIZE;
+	return pgmap->geometry;
+}
+
+static inline unsigned long pgmap_pfn_geometry(struct dev_pagemap *pgmap)
+{
+	return PHYS_PFN(pgmap_geometry(pgmap));
+}
+
 #ifdef CONFIG_ZONE_DEVICE
 bool pfn_zone_device_reserved(unsigned long pfn);
 void *memremap_pages(struct dev_pagemap *pgmap, int nid);
diff --git a/mm/memremap.c b/mm/memremap.c
index 805d761740c4..ffcb924eb6a5 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -318,8 +318,12 @@ static int pagemap_range(struct dev_pagemap *pgmap, struct mhp_params *params,
 	memmap_init_zone_device(&NODE_DATA(nid)->node_zones[ZONE_DEVICE],
 				PHYS_PFN(range->start),
 				PHYS_PFN(range_len(range)), pgmap);
-	percpu_ref_get_many(pgmap->ref, pfn_end(pgmap, range_id)
-			- pfn_first(pgmap, range_id));
+	if (pgmap_geometry(pgmap) > PAGE_SIZE)
+		percpu_ref_get_many(pgmap->ref, (pfn_end(pgmap, range_id)
+			- pfn_first(pgmap, range_id)) / pgmap_pfn_geometry(pgmap));
+	else
+		percpu_ref_get_many(pgmap->ref, pfn_end(pgmap, range_id)
+				- pfn_first(pgmap, range_id));
 	return 0;
 
 err_add_memory:
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 1264c025becb..42611c206d0a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6605,6 +6605,31 @@ static void __ref __init_zone_device_page(struct page *page, unsigned long pfn,
 	}
 }
 
+static void __ref memmap_init_compound(struct page *page, unsigned long pfn,
+					unsigned long zone_idx, int nid,
+					struct dev_pagemap *pgmap,
+					unsigned long nr_pages)
+{
+	unsigned int order_align = order_base_2(nr_pages);
+	unsigned long i;
+
+	__SetPageHead(page);
+
+	for (i = 1; i < nr_pages; i++) {
+		__init_zone_device_page(page + i, pfn + i, zone_idx,
+					nid, pgmap);
+		prep_compound_tail(page, i);
+
+		/*
+		 * The first and second tail pages need to
+		 * initialized first, hence the head page is
+		 * prepared last.
+		 */
+		if (i == 2)
+			prep_compound_head(page, order_align);
+	}
+}
+
 void __ref memmap_init_zone_device(struct zone *zone,
 				   unsigned long start_pfn,
 				   unsigned long nr_pages,
@@ -6613,6 +6638,7 @@ void __ref memmap_init_zone_device(struct zone *zone,
 	unsigned long pfn, end_pfn = start_pfn + nr_pages;
 	struct pglist_data *pgdat = zone->zone_pgdat;
 	struct vmem_altmap *altmap = pgmap_altmap(pgmap);
+	unsigned int pfns_per_compound = pgmap_pfn_geometry(pgmap);
 	unsigned long zone_idx = zone_idx(zone);
 	unsigned long start = jiffies;
 	int nid = pgdat->node_id;
@@ -6630,10 +6656,16 @@ void __ref memmap_init_zone_device(struct zone *zone,
 		nr_pages = end_pfn - start_pfn;
 	}
 
-	for (pfn = start_pfn; pfn < end_pfn; pfn++) {
+	for (pfn = start_pfn; pfn < end_pfn; pfn += pfns_per_compound) {
 		struct page *page = pfn_to_page(pfn);
 
 		__init_zone_device_page(page, pfn, zone_idx, nid, pgmap);
+
+		if (pfns_per_compound == 1)
+			continue;
+
+		memmap_init_compound(page, pfn, zone_idx, nid, pgmap,
+				     pfns_per_compound);
 	}
 
 	pr_info("%s initialised %lu pages in %ums\n", __func__,
-- 
2.17.1


  parent reply	other threads:[~2021-06-17 18:46 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-06-17 18:44 [PATCH v2 00/14] mm, sparse-vmemmap: Introduce compound pagemaps Joao Martins
2021-06-17 18:44 ` [PATCH v2 01/14] memory-failure: fetch compound_head after pgmap_pfn_valid() Joao Martins
2021-06-20 23:56   ` HORIGUCHI NAOYA(堀口 直也)
2021-06-21 13:50     ` Joao Martins
2021-06-17 18:44 ` [PATCH v2 02/14] mm/page_alloc: split prep_compound_page into head and tail subparts Joao Martins
2021-07-13  0:02   ` Mike Kravetz
2021-07-13  1:11     ` Joao Martins
2021-06-17 18:44 ` [PATCH v2 03/14] mm/page_alloc: refactor memmap_init_zone_device() page init Joao Martins
2021-06-17 18:44 ` Joao Martins [this message]
2021-06-17 18:44 ` [PATCH v2 05/14] mm/sparse-vmemmap: add a pgmap argument to section activation Joao Martins
2021-06-17 18:44 ` [PATCH v2 06/14] mm/sparse-vmemmap: refactor core of vmemmap_populate_basepages() to helper Joao Martins
2021-06-17 18:45 ` [PATCH v2 07/14] mm/hugetlb_vmemmap: move comment block to Documentation/vm Joao Martins
2021-06-21 13:12   ` [External] " Muchun Song
2021-06-21 13:12     ` Muchun Song
2021-06-21 13:42     ` Joao Martins
2021-07-13  0:14       ` Mike Kravetz
2021-07-13  1:11         ` Joao Martins
2021-06-17 18:45 ` [PATCH v2 08/14] mm/sparse-vmemmap: populate compound pagemaps Joao Martins
2021-06-17 18:45 ` [PATCH v2 09/14] mm/page_alloc: reuse tail struct pages for " Joao Martins
2021-06-17 18:45 ` [PATCH v2 10/14] device-dax: use ALIGN() for determining pgoff Joao Martins
2021-06-17 18:45 ` [PATCH v2 11/14] device-dax: ensure dev_dax->pgmap is valid for dynamic devices Joao Martins
2021-06-17 18:45 ` [PATCH v2 12/14] device-dax: compound pagemap support Joao Martins
2021-06-17 18:45 ` [PATCH v2 13/14] mm/gup: grab head page refcount once for group of subpages Joao Martins
2021-06-17 18:45 ` [PATCH v2 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=20210617184507.3662-5-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=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.