Linux-mm 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, Mike Kravetz <mike.kravetz@oracle.com>,
	Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>,
	LKML <linux-kernel@vger.kernel.org>,
	Michal Hocko <mhocko@suse.com>
Subject: [PATCH 1/6] mm, hugetlb: unify core page allocation accounting and initialization
Date: Wed,  3 Jan 2018 10:32:08 +0100
Message-ID: <20180103093213.26329-2-mhocko@kernel.org> (raw)
In-Reply-To: <20180103093213.26329-1-mhocko@kernel.org>

From: Michal Hocko <mhocko@suse.com>

hugetlb allocator has two entry points to the page allocator
- alloc_fresh_huge_page_node
- __hugetlb_alloc_buddy_huge_page

The two differ very subtly in two aspects. The first one doesn't care
about HTLB_BUDDY_* stats and it doesn't initialize the huge page.
prep_new_huge_page is not used because it not only initializes hugetlb
specific stuff but because it also put_page and releases the page to
the hugetlb pool which is not what is required in some contexts. This
makes things more complicated than necessary.

Simplify things by a) removing the page allocator entry point duplicity
and only keep __hugetlb_alloc_buddy_huge_page and b) make
prep_new_huge_page more reusable by removing the put_page which moves
the page to the allocator pool. All current callers are updated to call
put_page explicitly. Later patches will add new callers which won't
need it.

This patch shouldn't introduce any functional change.

Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Signed-off-by: Michal Hocko <mhocko@suse.com>
---
 mm/hugetlb.c | 61 +++++++++++++++++++++++++++++-------------------------------
 1 file changed, 29 insertions(+), 32 deletions(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 4137fb67cd79..a8959667f539 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1157,6 +1157,7 @@ static struct page *alloc_fresh_gigantic_page_node(struct hstate *h, int nid)
 	if (page) {
 		prep_compound_gigantic_page(page, huge_page_order(h));
 		prep_new_huge_page(h, page, nid);
+		put_page(page); /* free it into the hugepage allocator */
 	}
 
 	return page;
@@ -1304,7 +1305,6 @@ static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
 	h->nr_huge_pages++;
 	h->nr_huge_pages_node[nid]++;
 	spin_unlock(&hugetlb_lock);
-	put_page(page); /* free it into the hugepage allocator */
 }
 
 static void prep_compound_gigantic_page(struct page *page, unsigned int order)
@@ -1381,41 +1381,49 @@ pgoff_t __basepage_index(struct page *page)
 	return (index << compound_order(page_head)) + compound_idx;
 }
 
-static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
+static struct page *__hugetlb_alloc_buddy_huge_page(struct hstate *h,
+		gfp_t gfp_mask, int nid, nodemask_t *nmask)
 {
+	int order = huge_page_order(h);
 	struct page *page;
 
-	page = __alloc_pages_node(nid,
-		htlb_alloc_mask(h)|__GFP_COMP|__GFP_THISNODE|
-						__GFP_RETRY_MAYFAIL|__GFP_NOWARN,
-		huge_page_order(h));
-	if (page) {
-		prep_new_huge_page(h, page, nid);
-	}
+	gfp_mask |= __GFP_COMP|__GFP_RETRY_MAYFAIL|__GFP_NOWARN;
+	if (nid == NUMA_NO_NODE)
+		nid = numa_mem_id();
+	page = __alloc_pages_nodemask(gfp_mask, order, nid, nmask);
+	if (page)
+		__count_vm_event(HTLB_BUDDY_PGALLOC);
+	else
+		__count_vm_event(HTLB_BUDDY_PGALLOC_FAIL);
 
 	return page;
 }
 
+/*
+ * Allocates a fresh page to the hugetlb allocator pool in the node interleaved
+ * manner.
+ */
 static int alloc_fresh_huge_page(struct hstate *h, nodemask_t *nodes_allowed)
 {
 	struct page *page;
 	int nr_nodes, node;
-	int ret = 0;
+	gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE;
 
 	for_each_node_mask_to_alloc(h, nr_nodes, node, nodes_allowed) {
-		page = alloc_fresh_huge_page_node(h, node);
-		if (page) {
-			ret = 1;
+		page = __hugetlb_alloc_buddy_huge_page(h, gfp_mask,
+				node, nodes_allowed);
+		if (page)
 			break;
-		}
+
 	}
 
-	if (ret)
-		count_vm_event(HTLB_BUDDY_PGALLOC);
-	else
-		count_vm_event(HTLB_BUDDY_PGALLOC_FAIL);
+	if (!page)
+		return 0;
 
-	return ret;
+	prep_new_huge_page(h, page, page_to_nid(page));
+	put_page(page); /* free it into the hugepage allocator */
+
+	return 1;
 }
 
 /*
@@ -1523,17 +1531,6 @@ int dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn)
 	return rc;
 }
 
-static struct page *__hugetlb_alloc_buddy_huge_page(struct hstate *h,
-		gfp_t gfp_mask, int nid, nodemask_t *nmask)
-{
-	int order = huge_page_order(h);
-
-	gfp_mask |= __GFP_COMP|__GFP_RETRY_MAYFAIL|__GFP_NOWARN;
-	if (nid == NUMA_NO_NODE)
-		nid = numa_mem_id();
-	return __alloc_pages_nodemask(gfp_mask, order, nid, nmask);
-}
-
 static struct page *__alloc_buddy_huge_page(struct hstate *h, gfp_t gfp_mask,
 		int nid, nodemask_t *nmask)
 {
@@ -1589,11 +1586,9 @@ static struct page *__alloc_buddy_huge_page(struct hstate *h, gfp_t gfp_mask,
 		 */
 		h->nr_huge_pages_node[r_nid]++;
 		h->surplus_huge_pages_node[r_nid]++;
-		__count_vm_event(HTLB_BUDDY_PGALLOC);
 	} else {
 		h->nr_huge_pages--;
 		h->surplus_huge_pages--;
-		__count_vm_event(HTLB_BUDDY_PGALLOC_FAIL);
 	}
 	spin_unlock(&hugetlb_lock);
 
@@ -2148,6 +2143,8 @@ static void __init gather_bootmem_prealloc(void)
 		prep_compound_huge_page(page, h->order);
 		WARN_ON(PageReserved(page));
 		prep_new_huge_page(h, page, page_to_nid(page));
+		put_page(page); /* free it into the hugepage allocator */
+
 		/*
 		 * If we had gigantic hugepages allocated at boot time, we need
 		 * to restore the 'stolen' pages to totalram_pages in order to
-- 
2.15.1

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  reply index

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-01-03  9:32 [PATCH 0/6] mm, hugetlb: allocation API and migration improvements Michal Hocko
2018-01-03  9:32 ` Michal Hocko [this message]
2018-01-03  9:32 ` [PATCH 2/6] mm, hugetlb: integrate giga hugetlb more naturally to the allocation path Michal Hocko
2018-01-03  9:32 ` [PATCH 3/6] mm, hugetlb: do not rely on overcommit limit during migration Michal Hocko
2018-01-03  9:32 ` [PATCH 4/6] mm, hugetlb: get rid of surplus page accounting tricks Michal Hocko
2018-01-03  9:32 ` [PATCH 5/6] mm, hugetlb: further simplify hugetlb allocation API Michal Hocko
2018-02-21  4:24   ` Dan Rue
2018-02-21  9:55     ` Michal Hocko
2018-02-21 10:01       ` Michal Hocko
2018-02-21 16:19         ` Dan Rue
2018-02-21 18:52           ` Michal Hocko
2018-02-21 19:05             ` Dan Rue
2018-02-21 17:59         ` Mike Kravetz
2018-02-21 18:54           ` Michal Hocko
2018-02-21 19:14     ` [PATCH] hugetlb: fix surplus pages accounting Michal Hocko
2018-01-03  9:32 ` [PATCH 6/6] hugetlb, mempolicy: fix the mbind hugetlb migration Michal Hocko
2018-01-04  0:05 ` [PATCH 0/6] mm, hugetlb: allocation API and migration improvements Andrew Morton
2018-01-04  7:32   ` Michal Hocko

Reply instructions:

You may reply publically 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=20180103093213.26329-2-mhocko@kernel.org \
    --to=mhocko@kernel.org \
    --cc=akpm@linux-foundation.org \
    --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 \
    /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

Linux-mm Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-mm/0 linux-mm/git/0.git

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

Example config snippet for mirrors

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


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