LKML Archive on lore.kernel.org
 help / color / Atom feed
From: Michal Hocko <mhocko@kernel.org>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: <linux-mm@kvack.org>, Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>,
	Mike Kravetz <mike.kravetz@oracle.com>,
	Mel Gorman <mgorman@suse.de>, Vlastimil Babka <vbabka@suse.cz>,
	LKML <linux-kernel@vger.kernel.org>,
	Michal Hocko <mhocko@suse.com>
Subject: [PATCH 2/3] hugetlb: add support for preferred node to alloc_huge_page_nodemask
Date: Thu, 22 Jun 2017 21:30:33 +0200
Message-ID: <20170622193034.28972-3-mhocko@kernel.org> (raw)
In-Reply-To: <20170622193034.28972-1-mhocko@kernel.org>

From: Michal Hocko <mhocko@suse.com>

alloc_huge_page_nodemask tries to allocate from any numa node in the
allowed node mask starting from lower numa nodes. This might lead to
filling up those low NUMA nodes while others are not used. We can reduce
this risk by introducing a concept of the preferred node similar to what
we have in the regular page allocator. We will start allocating from the
preferred nid and then iterate over all allowed nodes in the zonelist
order until we try them all.

This is mimicking the page allocator logic except it operates on
per-node mempools. dequeue_huge_page_vma already does this so distill
the zonelist logic into a more generic dequeue_huge_page_nodemask
and use it in alloc_huge_page_nodemask.

This will allow us to use proper per numa distance fallback also for
alloc_huge_page_node which can use alloc_huge_page_nodemask now and we
can get rid of alloc_huge_page_node helper which doesn't have any user
anymore.

Changes since v1
- get rid of dequeue_huge_page_node because it is not really needed
- simplify dequeue_huge_page_nodemask and alloc_huge_page_nodemask a bit
  as per Vlastimil

Acked-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Michal Hocko <mhocko@suse.com>
---
 include/linux/hugetlb.h |  5 +--
 include/linux/migrate.h |  2 +-
 mm/hugetlb.c            | 88 ++++++++++++++++++++++++-------------------------
 3 files changed, 48 insertions(+), 47 deletions(-)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 66b621469f52..8d9fe131a240 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -349,7 +349,8 @@ struct page *alloc_huge_page(struct vm_area_struct *vma,
 struct page *alloc_huge_page_node(struct hstate *h, int nid);
 struct page *alloc_huge_page_noerr(struct vm_area_struct *vma,
 				unsigned long addr, int avoid_reserve);
-struct page *alloc_huge_page_nodemask(struct hstate *h, nodemask_t *nmask);
+struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
+				nodemask_t *nmask);
 int huge_add_to_page_cache(struct page *page, struct address_space *mapping,
 			pgoff_t idx);
 
@@ -525,7 +526,7 @@ static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr
 struct hstate {};
 #define alloc_huge_page(v, a, r) NULL
 #define alloc_huge_page_node(h, nid) NULL
-#define alloc_huge_page_nodemask(h, nmask) NULL
+#define alloc_huge_page_nodemask(h, preferred_nid, nmask) NULL
 #define alloc_huge_page_noerr(v, a, r) NULL
 #define alloc_bootmem_huge_page(h) NULL
 #define hstate_file(f) NULL
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index f80c9882403a..af3ccf93efaa 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -38,7 +38,7 @@ static inline struct page *new_page_nodemask(struct page *page, int preferred_ni
 
 	if (PageHuge(page))
 		return alloc_huge_page_nodemask(page_hstate(compound_head(page)),
-				nodemask);
+				preferred_nid, nodemask);
 
 	if (PageHighMem(page)
 	    || (zone_idx(page_zone(page)) == ZONE_MOVABLE))
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index fd6e0c50f949..1e516520433d 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -887,19 +887,39 @@ static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid)
 	return page;
 }
 
-static struct page *dequeue_huge_page_node(struct hstate *h, int nid)
+static struct page *dequeue_huge_page_nodemask(struct hstate *h, gfp_t gfp_mask, int nid,
+		nodemask_t *nmask)
 {
-	struct page *page;
-	int node;
+	unsigned int cpuset_mems_cookie;
+	struct zonelist *zonelist;
+	struct zone *zone;
+	struct zoneref *z;
+	int node = -1;
 
-	if (nid != NUMA_NO_NODE)
-		return dequeue_huge_page_node_exact(h, nid);
+	zonelist = node_zonelist(nid, gfp_mask);
+
+retry_cpuset:
+	cpuset_mems_cookie = read_mems_allowed_begin();
+	for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(gfp_mask), nmask) {
+		struct page *page;
+
+		if (!cpuset_zone_allowed(zone, gfp_mask))
+			continue;
+		/*
+		 * no need to ask again on the same node. Pool is node rather than
+		 * zone aware
+		 */
+		if (zone_to_nid(zone) == node)
+			continue;
+		node = zone_to_nid(zone);
 
-	for_each_online_node(node) {
 		page = dequeue_huge_page_node_exact(h, node);
 		if (page)
 			return page;
 	}
+	if (unlikely(read_mems_allowed_retry(cpuset_mems_cookie)))
+		goto retry_cpuset;
+
 	return NULL;
 }
 
@@ -917,15 +937,11 @@ static struct page *dequeue_huge_page_vma(struct hstate *h,
 				unsigned long address, int avoid_reserve,
 				long chg)
 {
-	struct page *page = NULL;
+	struct page *page;
 	struct mempolicy *mpol;
-	nodemask_t *nodemask;
 	gfp_t gfp_mask;
+	nodemask_t *nodemask;
 	int nid;
-	struct zonelist *zonelist;
-	struct zone *zone;
-	struct zoneref *z;
-	unsigned int cpuset_mems_cookie;
 
 	/*
 	 * A child process with MAP_PRIVATE mappings created by their parent
@@ -940,32 +956,15 @@ static struct page *dequeue_huge_page_vma(struct hstate *h,
 	if (avoid_reserve && h->free_huge_pages - h->resv_huge_pages == 0)
 		goto err;
 
-retry_cpuset:
-	cpuset_mems_cookie = read_mems_allowed_begin();
 	gfp_mask = htlb_alloc_mask(h);
 	nid = huge_node(vma, address, gfp_mask, &mpol, &nodemask);
-	zonelist = node_zonelist(nid, gfp_mask);
-
-	for_each_zone_zonelist_nodemask(zone, z, zonelist,
-						MAX_NR_ZONES - 1, nodemask) {
-		if (cpuset_zone_allowed(zone, gfp_mask)) {
-			page = dequeue_huge_page_node(h, zone_to_nid(zone));
-			if (page) {
-				if (avoid_reserve)
-					break;
-				if (!vma_has_reserves(vma, chg))
-					break;
-
-				SetPagePrivate(page);
-				h->resv_huge_pages--;
-				break;
-			}
-		}
+	page = dequeue_huge_page_nodemask(h, gfp_mask, nid, nodemask);
+	if (page && !avoid_reserve && vma_has_reserves(vma, chg)) {
+		SetPagePrivate(page);
+		h->resv_huge_pages--;
 	}
 
 	mpol_cond_put(mpol);
-	if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
-		goto retry_cpuset;
 	return page;
 
 err:
@@ -1633,7 +1632,7 @@ struct page *alloc_huge_page_node(struct hstate *h, int nid)
 
 	spin_lock(&hugetlb_lock);
 	if (h->free_huge_pages - h->resv_huge_pages > 0)
-		page = dequeue_huge_page_node(h, nid);
+		page = dequeue_huge_page_nodemask(h, gfp_mask, nid, NULL);
 	spin_unlock(&hugetlb_lock);
 
 	if (!page)
@@ -1642,26 +1641,27 @@ struct page *alloc_huge_page_node(struct hstate *h, int nid)
 	return page;
 }
 
-struct page *alloc_huge_page_nodemask(struct hstate *h, nodemask_t *nmask)
+
+struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
+		nodemask_t *nmask)
 {
 	gfp_t gfp_mask = htlb_alloc_mask(h);
-	struct page *page = NULL;
-	int node;
 
 	spin_lock(&hugetlb_lock);
 	if (h->free_huge_pages - h->resv_huge_pages > 0) {
-		for_each_node_mask(node, *nmask) {
-			page = dequeue_huge_page_node_exact(h, node);
-			if (page)
-				break;
+		struct page *page;
+
+		page = dequeue_huge_page_nodemask(h, gfp_mask, preferred_nid, nmask);
+		if (page) {
+			spin_unlock(&hugetlb_lock);
+			return page;
 		}
 	}
 	spin_unlock(&hugetlb_lock);
-	if (page)
-		return page;
 
 	/* No reservations, try to overcommit */
-	return __alloc_buddy_huge_page(h, gfp_mask, NUMA_NO_NODE, nmask);
+
+	return __alloc_buddy_huge_page(h, gfp_mask, preferred_nid, nmask);
 }
 
 /*
-- 
2.11.0

  parent reply index

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-06-22 19:30 [PATCH 0/3] mm, hugetlb: allow proper node fallback dequeue Michal Hocko
2017-06-22 19:30 ` [PATCH 1/3] mm, hugetlb: unclutter hugetlb allocation layers Michal Hocko
2017-06-26 18:30   ` Mike Kravetz
2017-06-22 19:30 ` Michal Hocko [this message]
2017-06-26 18:31   ` [PATCH 2/3] hugetlb: add support for preferred node to alloc_huge_page_nodemask Mike Kravetz
2017-06-22 19:30 ` [PATCH 3/3] mm, hugetlb, soft_offline: use new_page_nodemask for soft offline migration Michal Hocko
2017-06-26 18:32   ` Mike Kravetz

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=20170622193034.28972-3-mhocko@kernel.org \
    --to=mhocko@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mgorman@suse.de \
    --cc=mhocko@suse.com \
    --cc=mike.kravetz@oracle.com \
    --cc=n-horiguchi@ah.jp.nec.com \
    --cc=vbabka@suse.cz \
    /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

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.git
	git clone --mirror https://lore.kernel.org/lkml/8 lkml/git/8.git
	git clone --mirror https://lore.kernel.org/lkml/9 lkml/git/9.git
	git clone --mirror https://lore.kernel.org/lkml/10 lkml/git/10.git

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

Example config snippet for mirrors

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


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