1 files changed, 263 insertions, 19 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index f9ecc2aeadfc..71e3dede95b4 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -757,6 +757,60 @@ int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
 }
 EXPORT_SYMBOL_GPL(vmf_insert_pfn_pmd);
 
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+static pud_t maybe_pud_mkwrite(pud_t pud, struct vm_area_struct *vma)
+{
+	if (likely(vma->vm_flags & VM_WRITE))
+		pud = pud_mkwrite(pud);
+	return pud;
+}
+
+static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
+		pud_t *pud, pfn_t pfn, pgprot_t prot, bool write)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	pud_t entry;
+	spinlock_t *ptl;
+
+	ptl = pud_lock(mm, pud);
+	entry = pud_mkhuge(pfn_t_pud(pfn, prot));
+	if (pfn_t_devmap(pfn))
+		entry = pud_mkdevmap(entry);
+	if (write) {
+		entry = pud_mkyoung(pud_mkdirty(entry));
+		entry = maybe_pud_mkwrite(entry, vma);
+	}
+	set_pud_at(mm, addr, pud, entry);
+	update_mmu_cache_pud(vma, addr, pud);
+	spin_unlock(ptl);
+}
+
+int vmf_insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
+			pud_t *pud, pfn_t pfn, bool write)
+{
+	pgprot_t pgprot = vma->vm_page_prot;
+	/*
+	 * If we had pud_special, we could avoid all these restrictions,
+	 * but we need to be consistent with PTEs and architectures that
+	 * can't support a 'special' bit.
+	 */
+	BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)));
+	BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) ==
+						(VM_PFNMAP|VM_MIXEDMAP));
+	BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags));
+	BUG_ON(!pfn_t_devmap(pfn));
+
+	if (addr < vma->vm_start || addr >= vma->vm_end)
+		return VM_FAULT_SIGBUS;
+
+	track_pfn_insert(vma, &pgprot, pfn);
+
+	insert_pfn_pud(vma, addr, pud, pfn, pgprot, write);
+	return VM_FAULT_NOPAGE;
+}
+EXPORT_SYMBOL_GPL(vmf_insert_pfn_pud);
+#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+
 static void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
 		pmd_t *pmd)
 {
@@ -887,6 +941,123 @@ out:
 	return ret;
 }
 
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+static void touch_pud(struct vm_area_struct *vma, unsigned long addr,
+		pud_t *pud)
+{
+	pud_t _pud;
+
+	/*
+	 * We should set the dirty bit only for FOLL_WRITE but for now
+	 * the dirty bit in the pud is meaningless.  And if the dirty
+	 * bit will become meaningful and we'll only set it with
+	 * FOLL_WRITE, an atomic set_bit will be required on the pud to
+	 * set the young bit, instead of the current set_pud_at.
+	 */
+	_pud = pud_mkyoung(pud_mkdirty(*pud));
+	if (pudp_set_access_flags(vma, addr & HPAGE_PUD_MASK,
+				pud, _pud,  1))
+		update_mmu_cache_pud(vma, addr, pud);
+}
+
+struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr,
+		pud_t *pud, int flags)
+{
+	unsigned long pfn = pud_pfn(*pud);
+	struct mm_struct *mm = vma->vm_mm;
+	struct dev_pagemap *pgmap;
+	struct page *page;
+
+	assert_spin_locked(pud_lockptr(mm, pud));
+
+	if (flags & FOLL_WRITE && !pud_write(*pud))
+		return NULL;
+
+	if (pud_present(*pud) && pud_devmap(*pud))
+		/* pass */;
+	else
+		return NULL;
+
+	if (flags & FOLL_TOUCH)
+		touch_pud(vma, addr, pud);
+
+	/*
+	 * device mapped pages can only be returned if the
+	 * caller will manage the page reference count.
+	 */
+	if (!(flags & FOLL_GET))
+		return ERR_PTR(-EEXIST);
+
+	pfn += (addr & ~PUD_MASK) >> PAGE_SHIFT;
+	pgmap = get_dev_pagemap(pfn, NULL);
+	if (!pgmap)
+		return ERR_PTR(-EFAULT);
+	page = pfn_to_page(pfn);
+	get_page(page);
+	put_dev_pagemap(pgmap);
+
+	return page;
+}
+
+int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm,
+		  pud_t *dst_pud, pud_t *src_pud, unsigned long addr,
+		  struct vm_area_struct *vma)
+{
+	spinlock_t *dst_ptl, *src_ptl;
+	pud_t pud;
+	int ret;
+
+	dst_ptl = pud_lock(dst_mm, dst_pud);
+	src_ptl = pud_lockptr(src_mm, src_pud);
+	spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
+
+	ret = -EAGAIN;
+	pud = *src_pud;
+	if (unlikely(!pud_trans_huge(pud) && !pud_devmap(pud)))
+		goto out_unlock;
+
+	/*
+	 * When page table lock is held, the huge zero pud should not be
+	 * under splitting since we don't split the page itself, only pud to
+	 * a page table.
+	 */
+	if (is_huge_zero_pud(pud)) {
+		/* No huge zero pud yet */
+	}
+
+	pudp_set_wrprotect(src_mm, addr, src_pud);
+	pud = pud_mkold(pud_wrprotect(pud));
+	set_pud_at(dst_mm, addr, dst_pud, pud);
+
+	ret = 0;
+out_unlock:
+	spin_unlock(src_ptl);
+	spin_unlock(dst_ptl);
+	return ret;
+}
+
+void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud)
+{
+	pud_t entry;
+	unsigned long haddr;
+	bool write = vmf->flags & FAULT_FLAG_WRITE;
+
+	vmf->ptl = pud_lock(vmf->vma->vm_mm, vmf->pud);
+	if (unlikely(!pud_same(*vmf->pud, orig_pud)))
+		goto unlock;
+
+	entry = pud_mkyoung(orig_pud);
+	if (write)
+		entry = pud_mkdirty(entry);
+	haddr = vmf->address & HPAGE_PUD_MASK;
+	if (pudp_set_access_flags(vmf->vma, haddr, vmf->pud, entry, write))
+		update_mmu_cache_pud(vmf->vma, vmf->address, vmf->pud);
+
+unlock:
+	spin_unlock(vmf->ptl);
+}
+#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+
 void huge_pmd_set_accessed(struct vm_fault *vmf, pmd_t orig_pmd)
 {
 	pmd_t entry;
@@ -1255,7 +1426,7 @@ int do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd)
 	}
 
 	/* See similar comment in do_numa_page for explanation */
-	if (!pmd_write(pmd))
+	if (!pmd_savedwrite(pmd))
 		flags |= TNF_NO_GROUP;
 
 	/*
@@ -1318,7 +1489,7 @@ int do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd)
 	goto out;
 clear_pmdnuma:
 	BUG_ON(!PageLocked(page));
-	was_writable = pmd_write(pmd);
+	was_writable = pmd_savedwrite(pmd);
 	pmd = pmd_modify(pmd, vma->vm_page_prot);
 	pmd = pmd_mkyoung(pmd);
 	if (was_writable)
@@ -1335,7 +1506,7 @@ out:
 
 	if (page_nid != -1)
 		task_numa_fault(last_cpupid, page_nid, HPAGE_PMD_NR,
-				vmf->flags);
+				flags);
 
 	return 0;
 }
@@ -1573,7 +1744,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 			entry = pmdp_huge_get_and_clear_notify(mm, addr, pmd);
 			entry = pmd_modify(entry, newprot);
 			if (preserve_write)
-				entry = pmd_mkwrite(entry);
+				entry = pmd_mk_savedwrite(entry);
 			ret = HPAGE_PMD_NR;
 			set_pmd_at(mm, addr, pmd, entry);
 			BUG_ON(vma_is_anonymous(vma) && !preserve_write &&
@@ -1601,6 +1772,84 @@ spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma)
 	return NULL;
 }
 
+/*
+ * Returns true if a given pud maps a thp, false otherwise.
+ *
+ * Note that if it returns true, this routine returns without unlocking page
+ * table lock. So callers must unlock it.
+ */
+spinlock_t *__pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma)
+{
+	spinlock_t *ptl;
+
+	ptl = pud_lock(vma->vm_mm, pud);
+	if (likely(pud_trans_huge(*pud) || pud_devmap(*pud)))
+		return ptl;
+	spin_unlock(ptl);
+	return NULL;
+}
+
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma,
+		 pud_t *pud, unsigned long addr)
+{
+	pud_t orig_pud;
+	spinlock_t *ptl;
+
+	ptl = __pud_trans_huge_lock(pud, vma);
+	if (!ptl)
+		return 0;
+	/*
+	 * For architectures like ppc64 we look at deposited pgtable
+	 * when calling pudp_huge_get_and_clear. So do the
+	 * pgtable_trans_huge_withdraw after finishing pudp related
+	 * operations.
+	 */
+	orig_pud = pudp_huge_get_and_clear_full(tlb->mm, addr, pud,
+			tlb->fullmm);
+	tlb_remove_pud_tlb_entry(tlb, pud, addr);
+	if (vma_is_dax(vma)) {
+		spin_unlock(ptl);
+		/* No zero page support yet */
+	} else {
+		/* No support for anonymous PUD pages yet */
+		BUG();
+	}
+	return 1;
+}
+
+static void __split_huge_pud_locked(struct vm_area_struct *vma, pud_t *pud,
+		unsigned long haddr)
+{
+	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);
+	VM_BUG_ON(!pud_trans_huge(*pud) && !pud_devmap(*pud));
+
+	count_vm_event(THP_SPLIT_PMD);
+
+	pudp_huge_clear_flush_notify(vma, haddr, pud);
+}
+
+void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud,
+		unsigned long address)
+{
+	spinlock_t *ptl;
+	struct mm_struct *mm = vma->vm_mm;
+	unsigned long haddr = address & HPAGE_PUD_MASK;
+
+	mmu_notifier_invalidate_range_start(mm, haddr, haddr + HPAGE_PUD_SIZE);
+	ptl = pud_lock(mm, pud);
+	if (unlikely(!pud_trans_huge(*pud) && !pud_devmap(*pud)))
+		goto out;
+	__split_huge_pud_locked(vma, pud, haddr);
+
+out:
+	spin_unlock(ptl);
+	mmu_notifier_invalidate_range_end(mm, haddr, haddr + HPAGE_PUD_SIZE);
+}
+#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+
 static void __split_huge_zero_page_pmd(struct vm_area_struct *vma,
 		unsigned long haddr, pmd_t *pmd)
 {
@@ -1857,32 +2106,27 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma,
 static void freeze_page(struct page *page)
 {
 	enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS |
-		TTU_RMAP_LOCKED;
-	int i, ret;
+		TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD;
+	int ret;
 
 	VM_BUG_ON_PAGE(!PageHead(page), page);
 
 	if (PageAnon(page))
 		ttu_flags |= TTU_MIGRATION;
 
-	/* We only need TTU_SPLIT_HUGE_PMD once */
-	ret = try_to_unmap(page, ttu_flags | TTU_SPLIT_HUGE_PMD);
-	for (i = 1; !ret && i < HPAGE_PMD_NR; i++) {
-		/* Cut short if the page is unmapped */
-		if (page_count(page) == 1)
-			return;
-
-		ret = try_to_unmap(page + i, ttu_flags);
-	}
-	VM_BUG_ON_PAGE(ret, page + i - 1);
+	ret = try_to_unmap(page, ttu_flags);
+	VM_BUG_ON_PAGE(ret, page);
 }
 
 static void unfreeze_page(struct page *page)
 {
 	int i;
-
-	for (i = 0; i < HPAGE_PMD_NR; i++)
-		remove_migration_ptes(page + i, page + i, true);
+	if (PageTransHuge(page)) {
+		remove_migration_ptes(page, page, true);
+	} else {
+		for (i = 0; i < HPAGE_PMD_NR; i++)
+			remove_migration_ptes(page + i, page + i, true);
+	}
 }
 
 static void __split_huge_page_tail(struct page *head, int tail,