1 files changed, 57 insertions, 188 deletions

diff --git a/mm/gup.c b/mm/gup.c
index 3c39cbbeebef..adffe663594d 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -64,11 +64,11 @@ static inline void sanity_check_pinned_pages(struct page **pages,
 		    !folio_test_anon(folio))
 			continue;
 		if (!folio_test_large(folio) || folio_test_hugetlb(folio))
-			VM_BUG_ON_PAGE(!PageAnonExclusive(&folio->page), page);
+			VM_WARN_ON_ONCE_FOLIO(!PageAnonExclusive(&folio->page), folio);
 		else
 			/* Either a PTE-mapped or a PMD-mapped THP. */
-			VM_BUG_ON_PAGE(!PageAnonExclusive(&folio->page) &&
-				       !PageAnonExclusive(page), page);
+			VM_WARN_ON_ONCE_PAGE(!PageAnonExclusive(&folio->page) &&
+					     !PageAnonExclusive(page), page);
 	}
 }
 
@@ -679,31 +679,9 @@ static struct page *follow_huge_pud(struct vm_area_struct *vma,
 		return NULL;
 
 	pfn += (addr & ~PUD_MASK) >> PAGE_SHIFT;
-
-	if (IS_ENABLED(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) &&
-	    pud_devmap(pud)) {
-		/*
-		 * device mapped pages can only be returned if the caller
-		 * will manage the page reference count.
-		 *
-		 * At least one of FOLL_GET | FOLL_PIN must be set, so
-		 * assert that here:
-		 */
-		if (!(flags & (FOLL_GET | FOLL_PIN)))
-			return ERR_PTR(-EEXIST);
-
-		if (flags & FOLL_TOUCH)
-			touch_pud(vma, addr, pudp, flags & FOLL_WRITE);
-
-		ctx->pgmap = get_dev_pagemap(pfn, ctx->pgmap);
-		if (!ctx->pgmap)
-			return ERR_PTR(-EFAULT);
-	}
-
 	page = pfn_to_page(pfn);
 
-	if (!pud_devmap(pud) && !pud_write(pud) &&
-	    gup_must_unshare(vma, flags, page))
+	if (!pud_write(pud) && gup_must_unshare(vma, flags, page))
 		return ERR_PTR(-EMLINK);
 
 	ret = try_grab_folio(page_folio(page), 1, flags);
@@ -760,8 +738,8 @@ static struct page *follow_huge_pmd(struct vm_area_struct *vma,
 	if (!pmd_write(pmdval) && gup_must_unshare(vma, flags, page))
 		return ERR_PTR(-EMLINK);
 
-	VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) &&
-			!PageAnonExclusive(page), page);
+	VM_WARN_ON_ONCE_PAGE((flags & FOLL_PIN) && PageAnon(page) &&
+			     !PageAnonExclusive(page), page);
 
 	ret = try_grab_folio(page_folio(page), 1, flags);
 	if (ret)
@@ -857,8 +835,7 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
 	page = vm_normal_page(vma, address, pte);
 
 	/*
-	 * We only care about anon pages in can_follow_write_pte() and don't
-	 * have to worry about pte_devmap() because they are never anon.
+	 * We only care about anon pages in can_follow_write_pte().
 	 */
 	if ((flags & FOLL_WRITE) &&
 	    !can_follow_write_pte(pte, page, vma, flags)) {
@@ -866,18 +843,7 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
 		goto out;
 	}
 
-	if (!page && pte_devmap(pte) && (flags & (FOLL_GET | FOLL_PIN))) {
-		/*
-		 * Only return device mapping pages in the FOLL_GET or FOLL_PIN
-		 * case since they are only valid while holding the pgmap
-		 * reference.
-		 */
-		*pgmap = get_dev_pagemap(pte_pfn(pte), *pgmap);
-		if (*pgmap)
-			page = pte_page(pte);
-		else
-			goto no_page;
-	} else if (unlikely(!page)) {
+	if (unlikely(!page)) {
 		if (flags & FOLL_DUMP) {
 			/* Avoid special (like zero) pages in core dumps */
 			page = ERR_PTR(-EFAULT);
@@ -899,8 +865,8 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
 		goto out;
 	}
 
-	VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) &&
-		       !PageAnonExclusive(page), page);
+	VM_WARN_ON_ONCE_PAGE((flags & FOLL_PIN) && PageAnon(page) &&
+			     !PageAnonExclusive(page), page);
 
 	/* try_grab_folio() does nothing unless FOLL_GET or FOLL_PIN is set. */
 	ret = try_grab_folio(folio, 1, flags);
@@ -959,14 +925,6 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma,
 		return no_page_table(vma, flags, address);
 	if (!pmd_present(pmdval))
 		return no_page_table(vma, flags, address);
-	if (pmd_devmap(pmdval)) {
-		ptl = pmd_lock(mm, pmd);
-		page = follow_devmap_pmd(vma, address, pmd, flags, &ctx->pgmap);
-		spin_unlock(ptl);
-		if (page)
-			return page;
-		return no_page_table(vma, flags, address);
-	}
 	if (likely(!pmd_leaf(pmdval)))
 		return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);
 
@@ -1180,7 +1138,7 @@ static int faultin_page(struct vm_area_struct *vma,
 	if (unshare) {
 		fault_flags |= FAULT_FLAG_UNSHARE;
 		/* FAULT_FLAG_WRITE and FAULT_FLAG_UNSHARE are incompatible */
-		VM_BUG_ON(fault_flags & FAULT_FLAG_WRITE);
+		VM_WARN_ON_ONCE(fault_flags & FAULT_FLAG_WRITE);
 	}
 
 	ret = handle_mm_fault(vma, address, fault_flags, NULL);
@@ -1760,10 +1718,7 @@ static __always_inline long __get_user_pages_locked(struct mm_struct *mm,
 		}
 
 		/* VM_FAULT_RETRY or VM_FAULT_COMPLETED cannot return errors */
-		if (!*locked) {
-			BUG_ON(ret < 0);
-			BUG_ON(ret >= nr_pages);
-		}
+		VM_WARN_ON_ONCE(!*locked && (ret < 0 || ret >= nr_pages));
 
 		if (ret > 0) {
 			nr_pages -= ret;
@@ -1808,7 +1763,6 @@ retry:
 
 		ret = mmap_read_lock_killable(mm);
 		if (ret) {
-			BUG_ON(ret > 0);
 			if (!pages_done)
 				pages_done = ret;
 			break;
@@ -1819,11 +1773,11 @@ retry:
 				       pages, locked);
 		if (!*locked) {
 			/* Continue to retry until we succeeded */
-			BUG_ON(ret != 0);
+			VM_WARN_ON_ONCE(ret != 0);
 			goto retry;
 		}
 		if (ret != 1) {
-			BUG_ON(ret > 1);
+			VM_WARN_ON_ONCE(ret > 1);
 			if (!pages_done)
 				pages_done = ret;
 			break;
@@ -1885,10 +1839,10 @@ long populate_vma_page_range(struct vm_area_struct *vma,
 	int gup_flags;
 	long ret;
 
-	VM_BUG_ON(!PAGE_ALIGNED(start));
-	VM_BUG_ON(!PAGE_ALIGNED(end));
-	VM_BUG_ON_VMA(start < vma->vm_start, vma);
-	VM_BUG_ON_VMA(end   > vma->vm_end, vma);
+	VM_WARN_ON_ONCE(!PAGE_ALIGNED(start));
+	VM_WARN_ON_ONCE(!PAGE_ALIGNED(end));
+	VM_WARN_ON_ONCE_VMA(start < vma->vm_start, vma);
+	VM_WARN_ON_ONCE_VMA(end   > vma->vm_end, vma);
 	mmap_assert_locked(mm);
 
 	/*
@@ -1957,8 +1911,8 @@ long faultin_page_range(struct mm_struct *mm, unsigned long start,
 	int gup_flags;
 	long ret;
 
-	VM_BUG_ON(!PAGE_ALIGNED(start));
-	VM_BUG_ON(!PAGE_ALIGNED(end));
+	VM_WARN_ON_ONCE(!PAGE_ALIGNED(start));
+	VM_WARN_ON_ONCE(!PAGE_ALIGNED(end));
 	mmap_assert_locked(mm);
 
 	/*
@@ -2048,7 +2002,7 @@ static long __get_user_pages_locked(struct mm_struct *mm, unsigned long start,
 {
 	struct vm_area_struct *vma;
 	bool must_unlock = false;
-	unsigned long vm_flags;
+	vm_flags_t vm_flags;
 	long i;
 
 	if (!nr_pages)
@@ -2300,6 +2254,31 @@ static void pofs_unpin(struct pages_or_folios *pofs)
 		unpin_user_pages(pofs->pages, pofs->nr_entries);
 }
 
+static struct folio *pofs_next_folio(struct folio *folio,
+		struct pages_or_folios *pofs, long *index_ptr)
+{
+	long i = *index_ptr + 1;
+
+	if (!pofs->has_folios && folio_test_large(folio)) {
+		const unsigned long start_pfn = folio_pfn(folio);
+		const unsigned long end_pfn = start_pfn + folio_nr_pages(folio);
+
+		for (; i < pofs->nr_entries; i++) {
+			unsigned long pfn = page_to_pfn(pofs->pages[i]);
+
+			/* Is this page part of this folio? */
+			if (pfn < start_pfn || pfn >= end_pfn)
+				break;
+		}
+	}
+
+	if (unlikely(i == pofs->nr_entries))
+		return NULL;
+	*index_ptr = i;
+
+	return pofs_get_folio(pofs, i);
+}
+
 /*
  * Returns the number of collected folios. Return value is always >= 0.
  */
@@ -2307,16 +2286,13 @@ static unsigned long collect_longterm_unpinnable_folios(
 		struct list_head *movable_folio_list,
 		struct pages_or_folios *pofs)
 {
-	unsigned long i, collected = 0;
-	struct folio *prev_folio = NULL;
+	unsigned long collected = 0;
 	bool drain_allow = true;
+	struct folio *folio;
+	long i = 0;
 
-	for (i = 0; i < pofs->nr_entries; i++) {
-		struct folio *folio = pofs_get_folio(pofs, i);
-
-		if (folio == prev_folio)
-			continue;
-		prev_folio = folio;
+	for (folio = pofs_get_folio(pofs, i); folio;
+	     folio = pofs_next_folio(folio, pofs, &i)) {
 
 		if (folio_is_longterm_pinnable(folio))
 			continue;
@@ -2828,9 +2804,9 @@ static bool gup_fast_folio_allowed(struct folio *folio, unsigned int flags)
 		return false;
 
 	/* Anonymous folios pose no problem. */
-	mapping_flags = (unsigned long)mapping & PAGE_MAPPING_FLAGS;
+	mapping_flags = (unsigned long)mapping & FOLIO_MAPPING_FLAGS;
 	if (mapping_flags)
-		return mapping_flags & PAGE_MAPPING_ANON;
+		return mapping_flags & FOLIO_MAPPING_ANON;
 
 	/*
 	 * At this point, we know the mapping is non-null and points to an
@@ -2878,7 +2854,7 @@ static int gup_fast_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr,
 		int *nr)
 {
 	struct dev_pagemap *pgmap = NULL;
-	int nr_start = *nr, ret = 0;
+	int ret = 0;
 	pte_t *ptep, *ptem;
 
 	ptem = ptep = pte_offset_map(&pmd, addr);
@@ -2902,19 +2878,11 @@ static int gup_fast_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr,
 		if (!pte_access_permitted(pte, flags & FOLL_WRITE))
 			goto pte_unmap;
 
-		if (pte_devmap(pte)) {
-			if (unlikely(flags & FOLL_LONGTERM))
-				goto pte_unmap;
-
-			pgmap = get_dev_pagemap(pte_pfn(pte), pgmap);
-			if (unlikely(!pgmap)) {
-				gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages);
-				goto pte_unmap;
-			}
-		} else if (pte_special(pte))
+		if (pte_special(pte))
 			goto pte_unmap;
 
-		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
+		/* If it's not marked as special it must have a valid memmap. */
+		VM_WARN_ON_ONCE(!pfn_valid(pte_pfn(pte)));
 		page = pte_page(pte);
 
 		folio = try_grab_folio_fast(page, 1, flags);
@@ -2982,91 +2950,6 @@ static int gup_fast_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr,
 }
 #endif /* CONFIG_ARCH_HAS_PTE_SPECIAL */
 
-#if defined(CONFIG_ARCH_HAS_PTE_DEVMAP) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
-static int gup_fast_devmap_leaf(unsigned long pfn, unsigned long addr,
-	unsigned long end, unsigned int flags, struct page **pages, int *nr)
-{
-	int nr_start = *nr;
-	struct dev_pagemap *pgmap = NULL;
-
-	do {
-		struct folio *folio;
-		struct page *page = pfn_to_page(pfn);
-
-		pgmap = get_dev_pagemap(pfn, pgmap);
-		if (unlikely(!pgmap)) {
-			gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages);
-			break;
-		}
-
-		folio = try_grab_folio_fast(page, 1, flags);
-		if (!folio) {
-			gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages);
-			break;
-		}
-		folio_set_referenced(folio);
-		pages[*nr] = page;
-		(*nr)++;
-		pfn++;
-	} while (addr += PAGE_SIZE, addr != end);
-
-	put_dev_pagemap(pgmap);
-	return addr == end;
-}
-
-static int gup_fast_devmap_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr,
-		unsigned long end, unsigned int flags, struct page **pages,
-		int *nr)
-{
-	unsigned long fault_pfn;
-	int nr_start = *nr;
-
-	fault_pfn = pmd_pfn(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
-	if (!gup_fast_devmap_leaf(fault_pfn, addr, end, flags, pages, nr))
-		return 0;
-
-	if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) {
-		gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages);
-		return 0;
-	}
-	return 1;
-}
-
-static int gup_fast_devmap_pud_leaf(pud_t orig, pud_t *pudp, unsigned long addr,
-		unsigned long end, unsigned int flags, struct page **pages,
-		int *nr)
-{
-	unsigned long fault_pfn;
-	int nr_start = *nr;
-
-	fault_pfn = pud_pfn(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
-	if (!gup_fast_devmap_leaf(fault_pfn, addr, end, flags, pages, nr))
-		return 0;
-
-	if (unlikely(pud_val(orig) != pud_val(*pudp))) {
-		gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages);
-		return 0;
-	}
-	return 1;
-}
-#else
-static int gup_fast_devmap_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr,
-		unsigned long end, unsigned int flags, struct page **pages,
-		int *nr)
-{
-	BUILD_BUG();
-	return 0;
-}
-
-static int gup_fast_devmap_pud_leaf(pud_t pud, pud_t *pudp, unsigned long addr,
-		unsigned long end, unsigned int flags, struct page **pages,
-		int *nr)
-{
-	BUILD_BUG();
-	return 0;
-}
-#endif
-
 static int gup_fast_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 		unsigned long end, unsigned int flags, struct page **pages,
 		int *nr)
@@ -3081,13 +2964,6 @@ static int gup_fast_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 	if (pmd_special(orig))
 		return 0;
 
-	if (pmd_devmap(orig)) {
-		if (unlikely(flags & FOLL_LONGTERM))
-			return 0;
-		return gup_fast_devmap_pmd_leaf(orig, pmdp, addr, end, flags,
-					        pages, nr);
-	}
-
 	page = pmd_page(orig);
 	refs = record_subpages(page, PMD_SIZE, addr, end, pages + *nr);
 
@@ -3128,13 +3004,6 @@ static int gup_fast_pud_leaf(pud_t orig, pud_t *pudp, unsigned long addr,
 	if (pud_special(orig))
 		return 0;
 
-	if (pud_devmap(orig)) {
-		if (unlikely(flags & FOLL_LONGTERM))
-			return 0;
-		return gup_fast_devmap_pud_leaf(orig, pudp, addr, end, flags,
-					        pages, nr);
-	}
-
 	page = pud_page(orig);
 	refs = record_subpages(page, PUD_SIZE, addr, end, pages + *nr);