+ huge_memory-add-vmf_insert_folio_pud.patch added to mm-unstable branch

[Andrew Morton <akpm@linux-foundation.org>]

The patch titled
     Subject: huge_memory: add vmf_insert_folio_pud()
has been added to the -mm mm-unstable branch.  Its filename is
     huge_memory-add-vmf_insert_folio_pud.patch

This patch will shortly appear at
     https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/huge_memory-add-vmf_insert_folio_pud.patch

This patch will later appear in the mm-unstable branch at
    git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Before you just go and hit "reply", please:
   a) Consider who else should be cc'ed
   b) Prefer to cc a suitable mailing list as well
   c) Ideally: find the original patch on the mailing list and do a
      reply-to-all to that, adding suitable additional cc's

*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***

The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days

------------------------------------------------------
From: Alistair Popple <apopple@nvidia.com>
Subject: huge_memory: add vmf_insert_folio_pud()
Date: Wed, 5 Feb 2025 09:48:12 +1100

Currently DAX folio/page reference counts are managed differently to
normal pages.  To allow these to be managed the same as normal pages
introduce vmf_insert_folio_pud.  This will map the entire PUD-sized folio
and take references as it would for a normally mapped page.

This is distinct from the current mechanism, vmf_insert_pfn_pud, which
simply inserts a special devmap PUD entry into the page table without
holding a reference to the page for the mapping.

Link: https://lkml.kernel.org/r/ef0f8d6a6fd340531613c351c99c98fd6f94ad93.1738709036.git-series.apopple@nvidia.com
Signed-off-by: Alistair Popple <apopple@nvidia.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Tested-by: Alison Schofield <alison.schofield@intel.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Asahi Lina <lina@asahilina.net>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Chunyan Zhang <zhang.lyra@gmail.com>
Cc: "Darrick J. Wong" <djwong@kernel.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: linmiaohe <linmiaohe@huawei.com>
Cc: Logan Gunthorpe <logang@deltatee.com>
Cc: Mattew Wilcox <willy@infradead.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Ted Ts'o <tytso@mit.edu>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: WANG Xuerui <kernel@xen0n.name>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 include/linux/huge_mm.h |    1 
 mm/huge_memory.c        |   96 +++++++++++++++++++++++++++++++++-----
 2 files changed, 85 insertions(+), 12 deletions(-)

--- a/include/linux/huge_mm.h~huge_memory-add-vmf_insert_folio_pud
+++ a/include/linux/huge_mm.h
@@ -39,6 +39,7 @@ int change_huge_pmd(struct mmu_gather *t
 
 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);
+vm_fault_t vmf_insert_folio_pud(struct vm_fault *vmf, struct folio *folio, bool write);
 
 enum transparent_hugepage_flag {
 	TRANSPARENT_HUGEPAGE_UNSUPPORTED,
--- a/mm/huge_memory.c~huge_memory-add-vmf_insert_folio_pud
+++ a/mm/huge_memory.c
@@ -1482,19 +1482,17 @@ static void insert_pfn_pud(struct vm_are
 	struct mm_struct *mm = vma->vm_mm;
 	pgprot_t prot = vma->vm_page_prot;
 	pud_t entry;
-	spinlock_t *ptl;
 
-	ptl = pud_lock(mm, pud);
 	if (!pud_none(*pud)) {
 		if (write) {
 			if (WARN_ON_ONCE(pud_pfn(*pud) != pfn_t_to_pfn(pfn)))
-				goto out_unlock;
+				return;
 			entry = pud_mkyoung(*pud);
 			entry = maybe_pud_mkwrite(pud_mkdirty(entry), vma);
 			if (pudp_set_access_flags(vma, addr, pud, entry, 1))
 				update_mmu_cache_pud(vma, addr, pud);
 		}
-		goto out_unlock;
+		return;
 	}
 
 	entry = pud_mkhuge(pfn_t_pud(pfn, prot));
@@ -1508,9 +1506,6 @@ static void insert_pfn_pud(struct vm_are
 	}
 	set_pud_at(mm, addr, pud, entry);
 	update_mmu_cache_pud(vma, addr, pud);
-
-out_unlock:
-	spin_unlock(ptl);
 }
 
 /**
@@ -1528,6 +1523,7 @@ vm_fault_t vmf_insert_pfn_pud(struct vm_
 	unsigned long addr = vmf->address & PUD_MASK;
 	struct vm_area_struct *vma = vmf->vma;
 	pgprot_t pgprot = vma->vm_page_prot;
+	spinlock_t *ptl;
 
 	/*
 	 * If we had pud_special, we could avoid all these restrictions,
@@ -1545,10 +1541,55 @@ vm_fault_t vmf_insert_pfn_pud(struct vm_
 
 	track_pfn_insert(vma, &pgprot, pfn);
 
+	ptl = pud_lock(vma->vm_mm, vmf->pud);
 	insert_pfn_pud(vma, addr, vmf->pud, pfn, write);
+	spin_unlock(ptl);
+
 	return VM_FAULT_NOPAGE;
 }
 EXPORT_SYMBOL_GPL(vmf_insert_pfn_pud);
+
+/**
+ * vmf_insert_folio_pud - insert a pud size folio mapped by a pud entry
+ * @vmf: Structure describing the fault
+ * @folio: folio to insert
+ * @write: whether it's a write fault
+ *
+ * Return: vm_fault_t value.
+ */
+vm_fault_t vmf_insert_folio_pud(struct vm_fault *vmf, struct folio *folio, bool write)
+{
+	struct vm_area_struct *vma = vmf->vma;
+	unsigned long addr = vmf->address & PUD_MASK;
+	pud_t *pud = vmf->pud;
+	struct mm_struct *mm = vma->vm_mm;
+	spinlock_t *ptl;
+
+	if (addr < vma->vm_start || addr >= vma->vm_end)
+		return VM_FAULT_SIGBUS;
+
+	if (WARN_ON_ONCE(folio_order(folio) != PUD_ORDER))
+		return VM_FAULT_SIGBUS;
+
+	ptl = pud_lock(mm, pud);
+
+	/*
+	 * If there is already an entry present we assume the folio is
+	 * already mapped, hence no need to take another reference. We
+	 * still call insert_pfn_pud() though in case the mapping needs
+	 * upgrading to writeable.
+	 */
+	if (pud_none(*vmf->pud)) {
+		folio_get(folio);
+		folio_add_file_rmap_pud(folio, &folio->page, vma);
+		add_mm_counter(mm, mm_counter_file(folio), HPAGE_PUD_NR);
+	}
+	insert_pfn_pud(vma, addr, vmf->pud, pfn_to_pfn_t(folio_pfn(folio)), write);
+	spin_unlock(ptl);
+
+	return VM_FAULT_NOPAGE;
+}
+EXPORT_SYMBOL_GPL(vmf_insert_folio_pud);
 #endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
 
 void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
@@ -2146,7 +2187,8 @@ int zap_huge_pmd(struct mmu_gather *tlb,
 			zap_deposited_table(tlb->mm, pmd);
 		spin_unlock(ptl);
 	} else if (is_huge_zero_pmd(orig_pmd)) {
-		zap_deposited_table(tlb->mm, pmd);
+		if (!vma_is_dax(vma) || arch_needs_pgtable_deposit())
+			zap_deposited_table(tlb->mm, pmd);
 		spin_unlock(ptl);
 	} else {
 		struct folio *folio = NULL;
@@ -2646,12 +2688,23 @@ int zap_huge_pud(struct mmu_gather *tlb,
 	orig_pud = pudp_huge_get_and_clear_full(vma, addr, pud, tlb->fullmm);
 	arch_check_zapped_pud(vma, orig_pud);
 	tlb_remove_pud_tlb_entry(tlb, pud, addr);
-	if (vma_is_special_huge(vma)) {
+	if (!vma_is_dax(vma) && vma_is_special_huge(vma)) {
 		spin_unlock(ptl);
 		/* No zero page support yet */
 	} else {
-		/* No support for anonymous PUD pages yet */
-		BUG();
+		struct page *page = NULL;
+		struct folio *folio;
+
+		/* No support for anonymous PUD pages or migration yet */
+		VM_WARN_ON_ONCE(vma_is_anonymous(vma) || !pud_present(orig_pud));
+
+		page = pud_page(orig_pud);
+		folio = page_folio(page);
+		folio_remove_rmap_pud(folio, page, vma);
+		add_mm_counter(tlb->mm, mm_counter_file(folio), -HPAGE_PUD_NR);
+
+		spin_unlock(ptl);
+		tlb_remove_page_size(tlb, page, HPAGE_PUD_SIZE);
 	}
 	return 1;
 }
@@ -2659,6 +2712,10 @@ int zap_huge_pud(struct mmu_gather *tlb,
 static void __split_huge_pud_locked(struct vm_area_struct *vma, pud_t *pud,
 		unsigned long haddr)
 {
+	struct folio *folio;
+	struct page *page;
+	pud_t old_pud;
+
 	VM_BUG_ON(haddr & ~HPAGE_PUD_MASK);
 	VM_BUG_ON_VMA(vma->vm_start > haddr, vma);
 	VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PUD_SIZE, vma);
@@ -2666,7 +2723,22 @@ static void __split_huge_pud_locked(stru
 
 	count_vm_event(THP_SPLIT_PUD);
 
-	pudp_huge_clear_flush(vma, haddr, pud);
+	old_pud = pudp_huge_clear_flush(vma, haddr, pud);
+
+	if (!vma_is_dax(vma))
+		return;
+
+	page = pud_page(old_pud);
+	folio = page_folio(page);
+
+	if (!folio_test_dirty(folio) && pud_dirty(old_pud))
+		folio_mark_dirty(folio);
+	if (!folio_test_referenced(folio) && pud_young(old_pud))
+		folio_set_referenced(folio);
+	folio_remove_rmap_pud(folio, page, vma);
+	folio_put(folio);
+	add_mm_counter(vma->vm_mm, mm_counter_file(folio),
+		-HPAGE_PUD_NR);
 }
 
 void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud,
_

Patches currently in -mm which might be from apopple@nvidia.com are

fuse-fix-dax-truncate-punch_hole-fault-path.patch
fs-dax-return-unmapped-busy-pages-from-dax_layout_busy_page_range.patch
fs-dax-dont-skip-locked-entries-when-scanning-entries.patch
fs-dax-refactor-wait-for-dax-idle-page.patch
fs-dax-create-a-common-implementation-to-break-dax-layouts.patch
fs-dax-always-remove-dax-page-cache-entries-when-breaking-layouts.patch
fs-dax-ensure-all-pages-are-idle-prior-to-filesystem-unmount.patch
fs-dax-remove-page_mapping_dax_shared-mapping-flag.patch
mm-gup-remove-redundant-check-for-pci-p2pdma-page.patch
mm-mm_init-move-p2pdma-page-refcount-initialisation-to-p2pdma.patch
mm-allow-compound-zone-device-pages.patch
mm-memory-enhance-insert_page_into_pte_locked-to-create-writable-mappings.patch
mm-memory-add-vmf_insert_page_mkwrite.patch
rmap-add-support-for-pud-sized-mappings-to-rmap.patch
huge_memory-add-vmf_insert_folio_pud.patch
huge_memory-add-vmf_insert_folio_pmd.patch
mm-gup-dont-allow-foll_longterm-pinning-of-fs-dax-pages.patch
fs-dax-properly-refcount-fs-dax-pages.patch
device-dax-properly-refcount-device-dax-pages-when-mapping.patch