Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:2 as permitted sender) client-ip=2620:137:e000::3:2;
From:   David Hildenbrand <david@redhat.com>
To:     linux-kernel@vger.kernel.org
Cc:     linux-mm@kvack.org, David Hildenbrand <david@redhat.com>,
        Andrew Morton <akpm@linux-foundation.org>,
        Linus Torvalds <torvalds@linux-foundation.org>,
        Ryan Roberts <ryan.roberts@arm.com>,
        Matthew Wilcox <willy@infradead.org>,
        Hugh Dickins <hughd@google.com>,
        Yin Fengwei <fengwei.yin@intel.com>,
        Yang Shi <shy828301@gmail.com>,
        Ying Huang <ying.huang@intel.com>, Zi Yan <ziy@nvidia.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Ingo Molnar <mingo@redhat.com>, Will Deacon <will@kernel.org>,
        Waiman Long <longman@redhat.com>,
        "Paul E. McKenney" <paulmck@kernel.org>
Subject: [PATCH WIP v1 13/20] mm/huge_memory: batch rmap operations in __split_huge_pmd_locked()
Date:   Fri, 24 Nov 2023 14:26:18 +0100
Message-ID: <20231124132626.235350-14-david@redhat.com>
In-Reply-To: <20231124132626.235350-1-david@redhat.com>
References: <20231124132626.235350-1-david@redhat.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Let's batch the rmap operations, as a preparation to making individual
page_add_anon_rmap() calls more expensive.

While at it, use more folio operations (but only in the code branch we're
touching), use VM_WARN_ON_FOLIO(), and pass RMAP_COMPOUND instead of
manually setting PageAnonExclusive.

We should never see non-anon pages on that branch: otherwise, the
existing page_add_anon_rmap() call would have been flawed already.

Signed-off-by: David Hildenbrand <david@redhat.com>
---
 mm/huge_memory.c | 23 +++++++++++++++--------
 1 file changed, 15 insertions(+), 8 deletions(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index fd7251923557..f47971d1afbf 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2100,6 +2100,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 		unsigned long haddr, bool freeze)
 {
 	struct mm_struct *mm = vma->vm_mm;
+	struct folio *folio;
 	struct page *page;
 	pgtable_t pgtable;
 	pmd_t old_pmd, _pmd;
@@ -2195,16 +2196,18 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 		uffd_wp = pmd_swp_uffd_wp(old_pmd);
 	} else {
 		page = pmd_page(old_pmd);
+		folio = page_folio(page);
 		if (pmd_dirty(old_pmd)) {
 			dirty = true;
-			SetPageDirty(page);
+			folio_set_dirty(folio);
 		}
 		write = pmd_write(old_pmd);
 		young = pmd_young(old_pmd);
 		soft_dirty = pmd_soft_dirty(old_pmd);
 		uffd_wp = pmd_uffd_wp(old_pmd);
 
-		VM_BUG_ON_PAGE(!page_count(page), page);
+		VM_WARN_ON_FOLIO(!folio_ref_count(folio), folio);
+		VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio);
 
 		/*
 		 * Without "freeze", we'll simply split the PMD, propagating the
@@ -2221,11 +2224,18 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 		 *
 		 * See page_try_share_anon_rmap(): invalidate PMD first.
 		 */
-		anon_exclusive = PageAnon(page) && PageAnonExclusive(page);
+		anon_exclusive = PageAnonExclusive(page);
 		if (freeze && anon_exclusive && page_try_share_anon_rmap(page))
 			freeze = false;
-		if (!freeze)
-			page_ref_add(page, HPAGE_PMD_NR - 1);
+		if (!freeze) {
+			rmap_t rmap_flags = RMAP_NONE;
+
+			folio_ref_add(folio, HPAGE_PMD_NR - 1);
+			if (anon_exclusive)
+				rmap_flags = RMAP_EXCLUSIVE;
+			folio_add_anon_rmap_range(folio, page, HPAGE_PMD_NR,
+						  vma, haddr, rmap_flags);
+		}
 	}
 
 	/*
@@ -2268,8 +2278,6 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 			entry = mk_pte(page + i, READ_ONCE(vma->vm_page_prot));
 			if (write)
 				entry = pte_mkwrite(entry, vma);
-			if (anon_exclusive)
-				SetPageAnonExclusive(page + i);
 			if (!young)
 				entry = pte_mkold(entry);
 			/* NOTE: this may set soft-dirty too on some archs */
@@ -2279,7 +2287,6 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 				entry = pte_mksoft_dirty(entry);
 			if (uffd_wp)
 				entry = pte_mkuffd_wp(entry);
-			page_add_anon_rmap(page + i, vma, addr, RMAP_NONE);
 		}
 		VM_BUG_ON(!pte_none(ptep_get(pte)));
 		set_pte_at(mm, addr, pte, entry);
-- 
2.41.0