LKML Archive on lore.kernel.org
 help / color / Atom feed
From: Mina Almasry <almasrymina@google.com>
To: mike.kravetz@oracle.com
Cc: shuah@kernel.org, almasrymina@google.com, rientjes@google.com,
	shakeelb@google.com, gthelen@google.com,
	akpm@linux-foundation.org, khalid.aziz@oracle.com,
	linux-kernel@vger.kernel.org, linux-mm@kvack.org,
	linux-kselftest@vger.kernel.org, cgroups@vger.kernel.org,
	aneesh.kumar@linux.vnet.ibm.com, mkoutny@suse.com
Subject: [PATCH v6 7/9] hugetlb_cgroup: support noreserve mappings
Date: Sat, 12 Oct 2019 17:30:22 -0700
Message-ID: <20191013003024.215429-7-almasrymina@google.com> (raw)
In-Reply-To: <20191013003024.215429-1-almasrymina@google.com>

Support MAP_NORESERVE accounting as part of the new counter.

For each hugepage allocation, at allocation time we check if there is
a reservation for this allocation or not. If there is a reservation for
this allocation, then this allocation was charged at reservation time,
and we don't re-account it. If there is no reserevation for this
allocation, we charge the appropriate hugetlb_cgroup.

The hugetlb_cgroup to uncharge for this allocation is stored in
page[3].private. We use new APIs added in an earlier patch to set this
pointer.

---
 mm/hugetlb.c | 25 ++++++++++++++++++++++++-
 1 file changed, 24 insertions(+), 1 deletion(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index af336bf227fb6..79b99878ce6f9 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1217,6 +1217,7 @@ static void update_and_free_page(struct hstate *h, struct page *page)
 				1 << PG_writeback);
 	}
 	VM_BUG_ON_PAGE(hugetlb_cgroup_from_page(page, false), page);
+	VM_BUG_ON_PAGE(hugetlb_cgroup_from_page(page, true), page);
 	set_compound_page_dtor(page, NULL_COMPOUND_DTOR);
 	set_page_refcounted(page);
 	if (hstate_is_gigantic(h)) {
@@ -1328,6 +1329,9 @@ void free_huge_page(struct page *page)
 	clear_page_huge_active(page);
 	hugetlb_cgroup_uncharge_page(hstate_index(h), pages_per_huge_page(h),
 				     page, false);
+	hugetlb_cgroup_uncharge_page(hstate_index(h), pages_per_huge_page(h),
+				     page, true);
+
 	if (restore_reserve)
 		h->resv_huge_pages++;

@@ -1354,6 +1358,7 @@ static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
 	set_compound_page_dtor(page, HUGETLB_PAGE_DTOR);
 	spin_lock(&hugetlb_lock);
 	set_hugetlb_cgroup(page, NULL, false);
+	set_hugetlb_cgroup(page, NULL, true);
 	h->nr_huge_pages++;
 	h->nr_huge_pages_node[nid]++;
 	spin_unlock(&hugetlb_lock);
@@ -2155,10 +2160,19 @@ struct page *alloc_huge_page(struct vm_area_struct *vma,
 			gbl_chg = 1;
 	}

+	/* If this allocation is not consuming a reservation, charge it now.
+	 */
+	if (map_chg || avoid_reserve || !vma_resv_map(vma)) {
+		ret = hugetlb_cgroup_charge_cgroup(idx, pages_per_huge_page(h),
+						   &h_cg, true);
+		if (ret)
+			goto out_subpool_put;
+	}
+
 	ret = hugetlb_cgroup_charge_cgroup(idx, pages_per_huge_page(h), &h_cg,
 					   false);
 	if (ret)
-		goto out_subpool_put;
+		goto out_uncharge_cgroup_reservation;

 	spin_lock(&hugetlb_lock);
 	/*
@@ -2182,6 +2196,11 @@ struct page *alloc_huge_page(struct vm_area_struct *vma,
 	}
 	hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), h_cg, page,
 				     false);
+	if (!vma_resv_map(vma) || map_chg || avoid_reserve) {
+		hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), h_cg,
+					     page, true);
+	}
+
 	spin_unlock(&hugetlb_lock);

 	set_page_private(page, (unsigned long)spool);
@@ -2207,6 +2226,10 @@ struct page *alloc_huge_page(struct vm_area_struct *vma,
 out_uncharge_cgroup:
 	hugetlb_cgroup_uncharge_cgroup(idx, pages_per_huge_page(h), h_cg,
 				       false);
+out_uncharge_cgroup_reservation:
+	if (map_chg || avoid_reserve || !vma_resv_map(vma))
+		hugetlb_cgroup_uncharge_cgroup(idx, pages_per_huge_page(h),
+					       h_cg, true);
 out_subpool_put:
 	if (map_chg || avoid_reserve)
 		hugepage_subpool_put_pages(spool, 1);
--
2.23.0.700.g56cf767bdb-goog

  parent reply index

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-10-13  0:30 [PATCH v6 1/9] hugetlb_cgroup: Add hugetlb_cgroup reservation counter Mina Almasry
2019-10-13  0:30 ` [PATCH v6 2/9] hugetlb_cgroup: add interface for charge/uncharge hugetlb reservations Mina Almasry
2019-10-13  0:30 ` [PATCH v6 3/9] hugetlb_cgroup: add cgroup-v2 support Mina Almasry
2019-10-13  0:30 ` [PATCH v6 4/9] hugetlb_cgroup: add reservation accounting for private mappings Mina Almasry
2019-10-13  0:30 ` [PATCH v6 5/9] hugetlb: disable region_add file_region coalescing Mina Almasry
2019-10-13  0:30 ` [PATCH v6 6/9] hugetlb_cgroup: add accounting for shared mappings Mina Almasry
2019-10-13  0:30 ` Mina Almasry [this message]
2019-10-13  0:30 ` [PATCH v6 8/9] hugetlb_cgroup: Add hugetlb_cgroup reservation tests Mina Almasry
2019-10-13  0:30 ` [PATCH v6 9/9] hugetlb_cgroup: Add hugetlb_cgroup reservation docs Mina Almasry

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=20191013003024.215429-7-almasrymina@google.com \
    --to=almasrymina@google.com \
    --cc=akpm@linux-foundation.org \
    --cc=aneesh.kumar@linux.vnet.ibm.com \
    --cc=cgroups@vger.kernel.org \
    --cc=gthelen@google.com \
    --cc=khalid.aziz@oracle.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mike.kravetz@oracle.com \
    --cc=mkoutny@suse.com \
    --cc=rientjes@google.com \
    --cc=shakeelb@google.com \
    --cc=shuah@kernel.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

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

	# 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 linux-kernel@archiver.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