Message-ID: <dd86249dee026991b1a996a8ab551b1b1fdd32a4.1732239628.git-series.apopple@nvidia.com>
Date: Fri, 22 Nov 2024 12:40:35 +1100
From: Alistair Popple <apopple@...dia.com>
To: dan.j.williams@...el.com,
	linux-mm@...ck.org
Cc: Alistair Popple <apopple@...dia.com>,
	lina@...hilina.net,
	zhang.lyra@...il.com,
	gerald.schaefer@...ux.ibm.com,
	vishal.l.verma@...el.com,
	dave.jiang@...el.com,
	logang@...tatee.com,
	bhelgaas@...gle.com,
	jack@...e.cz,
	jgg@...pe.ca,
	catalin.marinas@....com,
	will@...nel.org,
	mpe@...erman.id.au,
	npiggin@...il.com,
	dave.hansen@...ux.intel.com,
	ira.weiny@...el.com,
	willy@...radead.org,
	djwong@...nel.org,
	tytso@....edu,
	linmiaohe@...wei.com,
	david@...hat.com,
	peterx@...hat.com,
	linux-doc@...r.kernel.org,
	linux-kernel@...r.kernel.org,
	linux-arm-kernel@...ts.infradead.org,
	linuxppc-dev@...ts.ozlabs.org,
	nvdimm@...ts.linux.dev,
	linux-cxl@...r.kernel.org,
	linux-fsdevel@...r.kernel.org,
	linux-ext4@...r.kernel.org,
	linux-xfs@...r.kernel.org,
	jhubbard@...dia.com,
	hch@....de,
	david@...morbit.com
Subject: [PATCH v3 14/25] huge_memory: Allow mappings of PUD sized pages

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.

Signed-off-by: Alistair Popple <apopple@...dia.com>
---
 include/linux/huge_mm.h | 11 +++++-
 include/linux/rmap.h    | 15 +++++++-
 mm/huge_memory.c        | 96 ++++++++++++++++++++++++++++++++++++------
 mm/rmap.c               | 49 +++++++++++++++++++++-
 4 files changed, 159 insertions(+), 12 deletions(-)

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index ef5b80e..e804e41 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -40,6 +40,7 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 
 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,
@@ -468,6 +469,11 @@ static inline bool is_huge_zero_pmd(pmd_t pmd)
 	return pmd_present(pmd) && READ_ONCE(huge_zero_pfn) == pmd_pfn(pmd);
 }
 
+static inline bool is_huge_zero_pud(pud_t pud)
+{
+	return false;
+}
+
 struct folio *mm_get_huge_zero_folio(struct mm_struct *mm);
 void mm_put_huge_zero_folio(struct mm_struct *mm);
 
@@ -614,6 +620,11 @@ static inline bool is_huge_zero_pmd(pmd_t pmd)
 	return false;
 }
 
+static inline bool is_huge_zero_pud(pud_t pud)
+{
+	return false;
+}
+
 static inline void mm_put_huge_zero_folio(struct mm_struct *mm)
 {
 	return;
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index d5e93e4..4a811c5 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -192,6 +192,7 @@ typedef int __bitwise rmap_t;
 enum rmap_level {
 	RMAP_LEVEL_PTE = 0,
 	RMAP_LEVEL_PMD,
+	RMAP_LEVEL_PUD,
 };
 
 static inline void __folio_rmap_sanity_checks(struct folio *folio,
@@ -228,6 +229,14 @@ static inline void __folio_rmap_sanity_checks(struct folio *folio,
 		VM_WARN_ON_FOLIO(folio_nr_pages(folio) != HPAGE_PMD_NR, folio);
 		VM_WARN_ON_FOLIO(nr_pages != HPAGE_PMD_NR, folio);
 		break;
+	case RMAP_LEVEL_PUD:
+		/*
+		 * Asume that we are creating * a single "entire" mapping of the
+		 * folio.
+		 */
+		VM_WARN_ON_FOLIO(folio_nr_pages(folio) != HPAGE_PUD_NR, folio);
+		VM_WARN_ON_FOLIO(nr_pages != HPAGE_PUD_NR, folio);
+		break;
 	default:
 		VM_WARN_ON_ONCE(true);
 	}
@@ -251,12 +260,16 @@ void folio_add_file_rmap_ptes(struct folio *, struct page *, int nr_pages,
 	folio_add_file_rmap_ptes(folio, page, 1, vma)
 void folio_add_file_rmap_pmd(struct folio *, struct page *,
 		struct vm_area_struct *);
+void folio_add_file_rmap_pud(struct folio *, struct page *,
+		struct vm_area_struct *);
 void folio_remove_rmap_ptes(struct folio *, struct page *, int nr_pages,
 		struct vm_area_struct *);
 #define folio_remove_rmap_pte(folio, page, vma) \
 	folio_remove_rmap_ptes(folio, page, 1, vma)
 void folio_remove_rmap_pmd(struct folio *, struct page *,
 		struct vm_area_struct *);
+void folio_remove_rmap_pud(struct folio *, struct page *,
+		struct vm_area_struct *);
 
 void hugetlb_add_anon_rmap(struct folio *, struct vm_area_struct *,
 		unsigned long address, rmap_t flags);
@@ -341,6 +354,7 @@ static __always_inline void __folio_dup_file_rmap(struct folio *folio,
 		atomic_add(orig_nr_pages, &folio->_large_mapcount);
 		break;
 	case RMAP_LEVEL_PMD:
+	case RMAP_LEVEL_PUD:
 		atomic_inc(&folio->_entire_mapcount);
 		atomic_inc(&folio->_large_mapcount);
 		break;
@@ -437,6 +451,7 @@ static __always_inline int __folio_try_dup_anon_rmap(struct folio *folio,
 		atomic_add(orig_nr_pages, &folio->_large_mapcount);
 		break;
 	case RMAP_LEVEL_PMD:
+	case RMAP_LEVEL_PUD:
 		if (PageAnonExclusive(page)) {
 			if (unlikely(maybe_pinned))
 				return -EBUSY;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 2fb3288..c51ef3e 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1441,19 +1441,17 @@ static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
 	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));
@@ -1467,9 +1465,6 @@ static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
 	}
 	set_pud_at(mm, addr, pud, entry);
 	update_mmu_cache_pud(vma, addr, pud);
-
-out_unlock:
-	spin_unlock(ptl);
 }
 
 /**
@@ -1487,6 +1482,7 @@ vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write)
 	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,
@@ -1504,10 +1500,55 @@ vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write)
 
 	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
+ * @pfn: pfn of the page 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;
+	pfn_t pfn = pfn_to_pfn_t(folio_pfn(folio));
+	pud_t *pud = vmf->pud;
+	pgprot_t prot = vma->vm_page_prot;
+	struct mm_struct *mm = vma->vm_mm;
+	spinlock_t *ptl;
+	struct page *page;
+
+	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;
+
+	track_pfn_insert(vma, &prot, pfn);
+
+	ptl = pud_lock(mm, pud);
+	if (pud_none(*vmf->pud)) {
+		page = pfn_t_to_page(pfn);
+		folio = page_folio(page);
+		folio_get(folio);
+		folio_add_file_rmap_pud(folio, page, vma);
+		add_mm_counter(mm, mm_counter_file(folio), HPAGE_PUD_NR);
+	}
+	insert_pfn_pud(vma, addr, vmf->pud, pfn, 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,
@@ -2066,7 +2107,8 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 			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;
@@ -2554,12 +2596,24 @@ int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	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 */
+		BUG_ON(vma_is_anonymous(vma) || !pud_present(orig_pud));
+
+		page = pud_page(orig_pud);
+		folio = page_folio(page);
+		folio_remove_rmap_pud(folio, page, vma);
+		VM_BUG_ON_PAGE(!PageHead(page), page);
+		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;
 }
@@ -2567,6 +2621,8 @@ int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma,
 static void __split_huge_pud_locked(struct vm_area_struct *vma, pud_t *pud,
 		unsigned long haddr)
 {
+	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);
@@ -2574,7 +2630,23 @@ static void __split_huge_pud_locked(struct vm_area_struct *vma, pud_t *pud,
 
 	count_vm_event(THP_SPLIT_PUD);
 
-	pudp_huge_clear_flush(vma, haddr, pud);
+	old_pud = pudp_huge_clear_flush(vma, haddr, pud);
+	if (is_huge_zero_pud(old_pud))
+		return;
+
+	if (vma_is_dax(vma)) {
+		struct page *page = pud_page(old_pud);
+		struct folio *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,
diff --git a/mm/rmap.c b/mm/rmap.c
index a8797d1..84d7ab7 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1180,6 +1180,7 @@ static __always_inline unsigned int __folio_add_rmap(struct folio *folio,
 		atomic_add(orig_nr_pages, &folio->_large_mapcount);
 		break;
 	case RMAP_LEVEL_PMD:
+	case RMAP_LEVEL_PUD:
 		first = atomic_inc_and_test(&folio->_entire_mapcount);
 		if (first) {
 			nr = atomic_add_return_relaxed(ENTIRELY_MAPPED, mapped);
@@ -1330,6 +1331,13 @@ static __always_inline void __folio_add_anon_rmap(struct folio *folio,
 		case RMAP_LEVEL_PMD:
 			SetPageAnonExclusive(page);
 			break;
+		case RMAP_LEVEL_PUD:
+			/*
+			 * Keep the compiler happy, we don't support anonymous
+			 * PUD mappings.
+			 */
+			WARN_ON_ONCE(1);
+			break;
 		}
 	}
 	for (i = 0; i < nr_pages; i++) {
@@ -1523,6 +1531,26 @@ void folio_add_file_rmap_pmd(struct folio *folio, struct page *page,
 #endif
 }
 
+/**
+ * folio_add_file_rmap_pud - add a PUD mapping to a page range of a folio
+ * @folio:	The folio to add the mapping to
+ * @page:	The first page to add
+ * @vma:	The vm area in which the mapping is added
+ *
+ * The page range of the folio is defined by [page, page + HPAGE_PUD_NR)
+ *
+ * The caller needs to hold the page table lock.
+ */
+void folio_add_file_rmap_pud(struct folio *folio, struct page *page,
+		struct vm_area_struct *vma)
+{
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+	__folio_add_file_rmap(folio, page, HPAGE_PUD_NR, vma, RMAP_LEVEL_PUD);
+#else
+	WARN_ON_ONCE(true);
+#endif
+}
+
 static __always_inline void __folio_remove_rmap(struct folio *folio,
 		struct page *page, int nr_pages, struct vm_area_struct *vma,
 		enum rmap_level level)
@@ -1552,6 +1580,7 @@ static __always_inline void __folio_remove_rmap(struct folio *folio,
 		partially_mapped = nr && atomic_read(mapped);
 		break;
 	case RMAP_LEVEL_PMD:
+	case RMAP_LEVEL_PUD:
 		atomic_dec(&folio->_large_mapcount);
 		last = atomic_add_negative(-1, &folio->_entire_mapcount);
 		if (last) {
@@ -1632,6 +1661,26 @@ void folio_remove_rmap_pmd(struct folio *folio, struct page *page,
 #endif
 }
 
+/**
+ * folio_remove_rmap_pud - remove a PUD mapping from a page range of a folio
+ * @folio:	The folio to remove the mapping from
+ * @page:	The first page to remove
+ * @vma:	The vm area from which the mapping is removed
+ *
+ * The page range of the folio is defined by [page, page + HPAGE_PUD_NR)
+ *
+ * The caller needs to hold the page table lock.
+ */
+void folio_remove_rmap_pud(struct folio *folio, struct page *page,
+		struct vm_area_struct *vma)
+{
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+	__folio_remove_rmap(folio, page, HPAGE_PUD_NR, vma, RMAP_LEVEL_PUD);
+#else
+	WARN_ON_ONCE(true);
+#endif
+}
+
 /*
  * @arg: enum ttu_flags will be passed to this argument
  */
-- 
git-series 0.9.1

Powered by blists - more mailing lists