linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: js1304@gmail.com
To: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org,
	kernel-team@lge.com, Vlastimil Babka <vbabka@suse.cz>,
	Christoph Hellwig <hch@infradead.org>,
	Roman Gushchin <guro@fb.com>,
	Mike Kravetz <mike.kravetz@oracle.com>,
	Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>,
	Michal Hocko <mhocko@suse.com>,
	Joonsoo Kim <iamjoonsoo.kim@lge.com>
Subject: [PATCH v3 4/8] mm/hugetlb: make hugetlb migration callback CMA aware
Date: Tue, 23 Jun 2020 15:13:44 +0900	[thread overview]
Message-ID: <1592892828-1934-5-git-send-email-iamjoonsoo.kim@lge.com> (raw)
In-Reply-To: <1592892828-1934-1-git-send-email-iamjoonsoo.kim@lge.com>

From: Joonsoo Kim <iamjoonsoo.kim@lge.com>

new_non_cma_page() in gup.c which try to allocate migration target page
requires to allocate the new page that is not on the CMA area.
new_non_cma_page() implements it by removing __GFP_MOVABLE flag. This way
works well for THP page or normal page but not for hugetlb page.

hugetlb page allocation process consists of two steps. First is dequeing
from the pool. Second is, if there is no available page on the queue,
allocating from the page allocator.

new_non_cma_page() can control allocation from the page allocator by
specifying correct gfp flag. However, dequeing cannot be controlled until
now, so, new_non_cma_page() skips dequeing completely. It is a suboptimal
since new_non_cma_page() cannot utilize hugetlb pages on the queue so
this patch tries to fix this situation.

This patch makes the deque function on hugetlb CMA aware and skip CMA
pages if newly added skip_cma argument is passed as true.

Acked-by: Mike Kravetz <mike.kravetz@oracle.com>
Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
---
 include/linux/hugetlb.h |  6 ++----
 mm/gup.c                |  3 ++-
 mm/hugetlb.c            | 31 ++++++++++++++++++++++---------
 mm/mempolicy.c          |  2 +-
 mm/migrate.c            |  2 +-
 5 files changed, 28 insertions(+), 16 deletions(-)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 8a8b755..858522e 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -505,11 +505,9 @@ struct huge_bootmem_page {
 struct page *alloc_huge_page(struct vm_area_struct *vma,
 				unsigned long addr, int avoid_reserve);
 struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
-				nodemask_t *nmask, gfp_t gfp_mask);
+				nodemask_t *nmask, gfp_t gfp_mask, bool skip_cma);
 struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma,
 				unsigned long address);
-struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask,
-				     int nid, nodemask_t *nmask);
 int huge_add_to_page_cache(struct page *page, struct address_space *mapping,
 			pgoff_t idx);
 
@@ -760,7 +758,7 @@ static inline struct page *alloc_huge_page(struct vm_area_struct *vma,
 
 static inline struct page *
 alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
-			nodemask_t *nmask, gfp_t gfp_mask)
+			nodemask_t *nmask, gfp_t gfp_mask, bool skip_cma)
 {
 	return NULL;
 }
diff --git a/mm/gup.c b/mm/gup.c
index 6f47697..15be281 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1630,11 +1630,12 @@ static struct page *new_non_cma_page(struct page *page, unsigned long private)
 #ifdef CONFIG_HUGETLB_PAGE
 	if (PageHuge(page)) {
 		struct hstate *h = page_hstate(page);
+
 		/*
 		 * We don't want to dequeue from the pool because pool pages will
 		 * mostly be from the CMA region.
 		 */
-		return alloc_migrate_huge_page(h, gfp_mask, nid, NULL);
+		return alloc_huge_page_nodemask(h, nid, NULL, gfp_mask, true);
 	}
 #endif
 	if (PageTransHuge(page)) {
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index bd408f2..1410e62 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1033,13 +1033,18 @@ static void enqueue_huge_page(struct hstate *h, struct page *page)
 	h->free_huge_pages_node[nid]++;
 }
 
-static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid)
+static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid, bool skip_cma)
 {
 	struct page *page;
 
-	list_for_each_entry(page, &h->hugepage_freelists[nid], lru)
+	list_for_each_entry(page, &h->hugepage_freelists[nid], lru) {
+		if (skip_cma && is_migrate_cma_page(page))
+			continue;
+
 		if (!PageHWPoison(page))
 			break;
+	}
+
 	/*
 	 * if 'non-isolated free hugepage' not found on the list,
 	 * the allocation fails.
@@ -1054,7 +1059,7 @@ static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid)
 }
 
 static struct page *dequeue_huge_page_nodemask(struct hstate *h, gfp_t gfp_mask, int nid,
-		nodemask_t *nmask)
+		nodemask_t *nmask, bool skip_cma)
 {
 	unsigned int cpuset_mems_cookie;
 	struct zonelist *zonelist;
@@ -1079,7 +1084,7 @@ static struct page *dequeue_huge_page_nodemask(struct hstate *h, gfp_t gfp_mask,
 			continue;
 		node = zone_to_nid(zone);
 
-		page = dequeue_huge_page_node_exact(h, node);
+		page = dequeue_huge_page_node_exact(h, node, skip_cma);
 		if (page)
 			return page;
 	}
@@ -1124,7 +1129,7 @@ static struct page *dequeue_huge_page_vma(struct hstate *h,
 
 	gfp_mask = htlb_alloc_mask(h);
 	nid = huge_node(vma, address, gfp_mask, &mpol, &nodemask);
-	page = dequeue_huge_page_nodemask(h, gfp_mask, nid, nodemask);
+	page = dequeue_huge_page_nodemask(h, gfp_mask, nid, nodemask, false);
 	if (page && !avoid_reserve && vma_has_reserves(vma, chg)) {
 		SetPagePrivate(page);
 		h->resv_huge_pages--;
@@ -1937,7 +1942,7 @@ static struct page *alloc_surplus_huge_page(struct hstate *h, gfp_t gfp_mask,
 	return page;
 }
 
-struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask,
+static struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask,
 				     int nid, nodemask_t *nmask)
 {
 	struct page *page;
@@ -1980,7 +1985,7 @@ struct page *alloc_buddy_huge_page_with_mpol(struct hstate *h,
 
 /* page migration callback function */
 struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
-		nodemask_t *nmask, gfp_t gfp_mask)
+		nodemask_t *nmask, gfp_t gfp_mask, bool skip_cma)
 {
 	gfp_mask |= htlb_alloc_mask(h);
 
@@ -1988,7 +1993,8 @@ struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
 	if (h->free_huge_pages - h->resv_huge_pages > 0) {
 		struct page *page;
 
-		page = dequeue_huge_page_nodemask(h, gfp_mask, preferred_nid, nmask);
+		page = dequeue_huge_page_nodemask(h, gfp_mask,
+					preferred_nid, nmask, skip_cma);
 		if (page) {
 			spin_unlock(&hugetlb_lock);
 			return page;
@@ -1996,6 +2002,13 @@ struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
 	}
 	spin_unlock(&hugetlb_lock);
 
+	/*
+	 * To skip the memory on CMA area, we need to clear __GFP_MOVABLE.
+	 * Clearing __GFP_MOVABLE at the top of this function would also skip
+	 * the proper allocation candidates for dequeue so clearing it here.
+	 */
+	if (skip_cma)
+		gfp_mask &= ~__GFP_MOVABLE;
 	return alloc_migrate_huge_page(h, gfp_mask, preferred_nid, nmask);
 }
 
@@ -2011,7 +2024,7 @@ struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma,
 
 	gfp_mask = htlb_alloc_mask(h);
 	node = huge_node(vma, address, gfp_mask, &mpol, &nodemask);
-	page = alloc_huge_page_nodemask(h, node, nodemask, 0);
+	page = alloc_huge_page_nodemask(h, node, nodemask, 0, false);
 	mpol_cond_put(mpol);
 
 	return page;
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index f21cff5..a3abf64 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1071,7 +1071,7 @@ struct page *alloc_new_node_page(struct page *page, unsigned long node)
 	if (PageHuge(page)) {
 		return alloc_huge_page_nodemask(
 			page_hstate(compound_head(page)), node,
-			NULL, __GFP_THISNODE);
+			NULL, __GFP_THISNODE, false);
 	} else if (PageTransHuge(page)) {
 		struct page *thp;
 
diff --git a/mm/migrate.c b/mm/migrate.c
index 6ca9f0c..634f1ea 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1546,7 +1546,7 @@ struct page *new_page_nodemask(struct page *page,
 	if (PageHuge(page)) {
 		return alloc_huge_page_nodemask(
 				page_hstate(compound_head(page)),
-				preferred_nid, nodemask, 0);
+				preferred_nid, nodemask, 0, false);
 	}
 
 	if (PageTransHuge(page)) {
-- 
2.7.4



  parent reply	other threads:[~2020-06-23  6:14 UTC|newest]

Thread overview: 46+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-06-23  6:13 [PATCH v3 0/8] clean-up the migration target allocation functions js1304
2020-06-23  6:13 ` [PATCH v3 1/8] mm/page_isolation: prefer the node of the source page js1304
2020-06-23  6:13 ` [PATCH v3 2/8] mm/migrate: move migration helper from .h to .c js1304
2020-06-23  6:13 ` [PATCH v3 3/8] mm/hugetlb: unify migration callbacks js1304
2020-06-24 21:18   ` Mike Kravetz
2020-06-25 11:26   ` Michal Hocko
2020-06-26  4:02     ` Joonsoo Kim
2020-07-02 16:13       ` Vlastimil Babka
2020-07-03  0:55         ` Joonsoo Kim
2020-06-23  6:13 ` js1304 [this message]
2020-06-25 11:54   ` [PATCH v3 4/8] mm/hugetlb: make hugetlb migration callback CMA aware Michal Hocko
2020-06-26  4:49     ` Joonsoo Kim
2020-06-26  7:23       ` Michal Hocko
2020-06-29  6:27         ` Joonsoo Kim
2020-06-29  7:55           ` Michal Hocko
2020-06-30  6:30             ` Joonsoo Kim
2020-06-30  6:42               ` Michal Hocko
2020-06-30  7:22                 ` Joonsoo Kim
2020-06-30 16:37                   ` Mike Kravetz
2020-06-23  6:13 ` [PATCH v3 5/8] mm/migrate: make a standard migration target allocation function js1304
2020-06-25 12:05   ` Michal Hocko
2020-06-26  5:02     ` Joonsoo Kim
2020-06-26  7:33       ` Michal Hocko
2020-06-29  6:41         ` Joonsoo Kim
2020-06-29  8:03           ` Michal Hocko
2020-06-30  7:19             ` Joonsoo Kim
2020-07-03 15:25   ` Vlastimil Babka
2020-06-23  6:13 ` [PATCH v3 6/8] mm/gup: use a standard migration target allocation callback js1304
2020-06-25 12:08   ` Michal Hocko
2020-06-26  5:03     ` Joonsoo Kim
2020-07-03 15:56   ` Vlastimil Babka
2020-07-06  8:34     ` Joonsoo Kim
2020-06-23  6:13 ` [PATCH v3 7/8] mm/mempolicy: " js1304
2020-06-25 12:09   ` Michal Hocko
2020-07-03 15:59   ` Vlastimil Babka
     [not found]   ` <20200708012044.GC992@lca.pw>
2020-07-08  6:45     ` Michal Hocko
2020-10-08  3:21     ` Hugh Dickins
2020-10-08 17:29       ` Mike Kravetz
2020-10-09  5:50         ` Hugh Dickins
2020-10-09 17:42           ` Mike Kravetz
2020-10-09 22:23             ` Hugh Dickins
2020-10-10  0:25               ` Mike Kravetz
2020-06-23  6:13 ` [PATCH v3 8/8] mm/page_alloc: remove a wrapper for alloc_migration_target() js1304
2020-06-25 12:10   ` Michal Hocko
2020-07-03 16:18   ` Vlastimil Babka
2020-07-06  8:44     ` Joonsoo Kim

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=1592892828-1934-5-git-send-email-iamjoonsoo.kim@lge.com \
    --to=js1304@gmail.com \
    --cc=akpm@linux-foundation.org \
    --cc=guro@fb.com \
    --cc=hch@infradead.org \
    --cc=iamjoonsoo.kim@lge.com \
    --cc=kernel-team@lge.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --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
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).