Received-SPF: pass (google.com: domain of linux-kernel+bounces-162359-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:4601:e00::3 as permitted sender) client-ip=2604:1380:4601:e00::3;
From: Lance Yang <ioworker0@gmail.com>
To: akpm@linux-foundation.org
Cc: willy@infradead.org,
	maskray@google.com,
	ziy@nvidia.com,
	ryan.roberts@arm.com,
	david@redhat.com,
	21cnbao@gmail.com,
	mhocko@suse.com,
	fengwei.yin@intel.com,
	zokeefe@google.com,
	shy828301@gmail.com,
	xiehuan09@gmail.com,
	libang.li@antgroup.com,
	wangkefeng.wang@huawei.com,
	songmuchun@bytedance.com,
	peterx@redhat.com,
	minchan@kernel.org,
	linux-mm@kvack.org,
	linux-kernel@vger.kernel.org,
	Lance Yang <ioworker0@gmail.com>
Subject: [PATCH v3 2/3] mm/rmap: integrate PMD-mapped folio splitting into pagewalk loop
Date: Mon, 29 Apr 2024 21:23:07 +0800
Message-Id: <20240429132308.38794-3-ioworker0@gmail.com>
In-Reply-To: <20240429132308.38794-1-ioworker0@gmail.com>
References: <20240429132308.38794-1-ioworker0@gmail.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

In preparation for supporting try_to_unmap_one() to unmap PMD-mapped
folios, start the pagewalk first, then call split_huge_pmd_address()
to split the folio.

Suggested-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Lance Yang <ioworker0@gmail.com>
---
 include/linux/huge_mm.h |  2 ++
 mm/huge_memory.c        | 42 +++++++++++++++++++++--------------------
 mm/rmap.c               | 26 +++++++++++++++++++------
 3 files changed, 44 insertions(+), 26 deletions(-)

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index c8d3ec116e29..2daadfcc6776 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -36,6 +36,8 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
 int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		    pmd_t *pmd, unsigned long addr, pgprot_t newprot,
 		    unsigned long cp_flags);
+void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address,
+			   pmd_t *pmd, bool freeze, struct folio *folio);
 
 vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write);
 vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 8261b5669397..145505a1dd05 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2584,6 +2584,27 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 	pmd_populate(mm, pmd, pgtable);
 }
 
+void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address,
+			   pmd_t *pmd, bool freeze, struct folio *folio)
+{
+	VM_WARN_ON_ONCE(folio && !folio_test_pmd_mappable(folio));
+	VM_WARN_ON_ONCE(!IS_ALIGNED(address, HPAGE_PMD_SIZE));
+	VM_WARN_ON_ONCE(folio && !folio_test_locked(folio));
+	VM_BUG_ON(freeze && !folio);
+
+	/*
+	 * When the caller requests to set up a migration entry, we
+	 * require a folio to check the PMD against. Otherwise, there
+	 * is a risk of replacing the wrong folio.
+	 */
+	if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd) ||
+	    is_pmd_migration_entry(*pmd)) {
+		if (folio && folio != pmd_folio(*pmd))
+			return;
+		__split_huge_pmd_locked(vma, pmd, address, freeze);
+	}
+}
+
 void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 		unsigned long address, bool freeze, struct folio *folio)
 {
@@ -2595,26 +2616,7 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 				(address & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE);
 	mmu_notifier_invalidate_range_start(&range);
 	ptl = pmd_lock(vma->vm_mm, pmd);
-
-	/*
-	 * If caller asks to setup a migration entry, we need a folio to check
-	 * pmd against. Otherwise we can end up replacing wrong folio.
-	 */
-	VM_BUG_ON(freeze && !folio);
-	VM_WARN_ON_ONCE(folio && !folio_test_locked(folio));
-
-	if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd) ||
-	    is_pmd_migration_entry(*pmd)) {
-		/*
-		 * It's safe to call pmd_page when folio is set because it's
-		 * guaranteed that pmd is present.
-		 */
-		if (folio && folio != pmd_folio(*pmd))
-			goto out;
-		__split_huge_pmd_locked(vma, pmd, range.start, freeze);
-	}
-
-out:
+	split_huge_pmd_locked(vma, range.start, pmd, freeze, folio);
 	spin_unlock(ptl);
 	mmu_notifier_invalidate_range_end(&range);
 }
diff --git a/mm/rmap.c b/mm/rmap.c
index 7e2575d669a9..e42f436c7ff3 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1636,9 +1636,6 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
 	if (flags & TTU_SYNC)
 		pvmw.flags = PVMW_SYNC;
 
-	if (flags & TTU_SPLIT_HUGE_PMD)
-		split_huge_pmd_address(vma, address, false, folio);
-
 	/*
 	 * For THP, we have to assume the worse case ie pmd for invalidation.
 	 * For hugetlb, it could be much worse if we need to do pud
@@ -1650,6 +1647,10 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
 	range.end = vma_address_end(&pvmw);
 	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm,
 				address, range.end);
+	if (flags & TTU_SPLIT_HUGE_PMD) {
+		range.start = address & HPAGE_PMD_MASK;
+		range.end = (address & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE;
+	}
 	if (folio_test_hugetlb(folio)) {
 		/*
 		 * If sharing is possible, start and end will be adjusted
@@ -1664,9 +1665,6 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
 	mmu_notifier_invalidate_range_start(&range);
 
 	while (page_vma_mapped_walk(&pvmw)) {
-		/* Unexpected PMD-mapped THP? */
-		VM_BUG_ON_FOLIO(!pvmw.pte, folio);
-
 		/*
 		 * If the folio is in an mlock()d vma, we must not swap it out.
 		 */
@@ -1678,6 +1676,22 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
 			goto walk_done_err;
 		}
 
+		if (!pvmw.pte && (flags & TTU_SPLIT_HUGE_PMD)) {
+			/*
+			 * We temporarily have to drop the PTL and start once
+			 * again from that now-PTE-mapped page table.
+			 */
+			split_huge_pmd_locked(vma, range.start, pvmw.pmd, false,
+					      folio);
+			pvmw.pmd = NULL;
+			spin_unlock(pvmw.ptl);
+			flags &= ~TTU_SPLIT_HUGE_PMD;
+			continue;
+		}
+
+		/* Unexpected PMD-mapped THP? */
+		VM_BUG_ON_FOLIO(!pvmw.pte, folio);
+
 		pfn = pte_pfn(ptep_get(pvmw.pte));
 		subpage = folio_page(folio, pfn - folio_pfn(folio));
 		address = pvmw.address;
-- 
2.33.1