1 files changed, 53 insertions, 73 deletions

diff --git a/mm/gup.c b/mm/gup.c
index 0bc4d140fc07..a8ba5112e4d0 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -28,11 +28,6 @@
 #include "internal.h"
 #include "swap.h"
 
-struct follow_page_context {
-	struct dev_pagemap *pgmap;
-	unsigned int page_mask;
-};
-
 static inline void sanity_check_pinned_pages(struct page **pages,
 					     unsigned long npages)
 {
@@ -148,7 +143,7 @@ int __must_check try_grab_folio(struct folio *folio, int refs,
 	if (WARN_ON_ONCE(folio_ref_count(folio) <= 0))
 		return -ENOMEM;
 
-	if (unlikely(!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(&folio->page)))
+	if (unlikely(!(flags & FOLL_PCI_P2PDMA) && folio_is_pci_p2pdma(folio)))
 		return -EREMOTEIO;
 
 	if (flags & FOLL_GET)
@@ -237,7 +232,7 @@ void folio_add_pin(struct folio *folio)
 static inline struct folio *gup_folio_range_next(struct page *start,
 		unsigned long npages, unsigned long i, unsigned int *ntails)
 {
-	struct page *next = nth_page(start, i);
+	struct page *next = start + i;
 	struct folio *folio = page_folio(next);
 	unsigned int nr = 1;
 
@@ -342,6 +337,10 @@ EXPORT_SYMBOL(unpin_user_pages_dirty_lock);
  * "gup-pinned page range" refers to a range of pages that has had one of the
  * pin_user_pages() variants called on that page.
  *
+ * The page range must be truly physically contiguous: the page range
+ * corresponds to a contiguous PFN range and all pages can be iterated
+ * naturally.
+ *
  * For the page ranges defined by [page .. page+npages], make that range (or
  * its head pages, if a compound page) dirty, if @make_dirty is true, and if the
  * page range was previously listed as clean.
@@ -359,6 +358,8 @@ void unpin_user_page_range_dirty_lock(struct page *page, unsigned long npages,
 	struct folio *folio;
 	unsigned int nr;
 
+	VM_WARN_ON_ONCE(!page_range_contiguous(page, npages));
+
 	for (i = 0; i < npages; i += nr) {
 		folio = gup_folio_range_next(page, npages, i, &nr);
 		if (make_dirty && !folio_test_dirty(folio)) {
@@ -475,29 +476,15 @@ EXPORT_SYMBOL_GPL(unpin_folios);
  * lifecycle.  Avoid setting the bit unless necessary, or it might cause write
  * cache bouncing on large SMP machines for concurrent pinned gups.
  */
-static inline void mm_set_has_pinned_flag(unsigned long *mm_flags)
+static inline void mm_set_has_pinned_flag(struct mm_struct *mm)
 {
-	if (!test_bit(MMF_HAS_PINNED, mm_flags))
-		set_bit(MMF_HAS_PINNED, mm_flags);
+	if (!mm_flags_test(MMF_HAS_PINNED, mm))
+		mm_flags_set(MMF_HAS_PINNED, mm);
 }
 
 #ifdef CONFIG_MMU
 
 #ifdef CONFIG_HAVE_GUP_FAST
-static int record_subpages(struct page *page, unsigned long sz,
-			   unsigned long addr, unsigned long end,
-			   struct page **pages)
-{
-	struct page *start_page;
-	int nr;
-
-	start_page = nth_page(page, (addr & (sz - 1)) >> PAGE_SHIFT);
-	for (nr = 0; addr != end; nr++, addr += PAGE_SIZE)
-		pages[nr] = nth_page(start_page, nr);
-
-	return nr;
-}
-
 /**
  * try_grab_folio_fast() - Attempt to get or pin a folio in fast path.
  * @page:  pointer to page to be grabbed
@@ -661,7 +648,7 @@ static inline bool can_follow_write_pud(pud_t pud, struct page *page,
 
 static struct page *follow_huge_pud(struct vm_area_struct *vma,
 				    unsigned long addr, pud_t *pudp,
-				    int flags, struct follow_page_context *ctx)
+				    int flags, unsigned long *page_mask)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	struct page *page;
@@ -688,7 +675,7 @@ static struct page *follow_huge_pud(struct vm_area_struct *vma,
 	if (ret)
 		page = ERR_PTR(ret);
 	else
-		ctx->page_mask = HPAGE_PUD_NR - 1;
+		*page_mask = HPAGE_PUD_NR - 1;
 
 	return page;
 }
@@ -714,7 +701,7 @@ static inline bool can_follow_write_pmd(pmd_t pmd, struct page *page,
 static struct page *follow_huge_pmd(struct vm_area_struct *vma,
 				    unsigned long addr, pmd_t *pmd,
 				    unsigned int flags,
-				    struct follow_page_context *ctx)
+				    unsigned long *page_mask)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	pmd_t pmdval = *pmd;
@@ -751,7 +738,7 @@ static struct page *follow_huge_pmd(struct vm_area_struct *vma,
 #endif	/* CONFIG_TRANSPARENT_HUGEPAGE */
 
 	page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT;
-	ctx->page_mask = HPAGE_PMD_NR - 1;
+	*page_mask = HPAGE_PMD_NR - 1;
 
 	return page;
 }
@@ -759,7 +746,7 @@ static struct page *follow_huge_pmd(struct vm_area_struct *vma,
 #else  /* CONFIG_PGTABLE_HAS_HUGE_LEAVES */
 static struct page *follow_huge_pud(struct vm_area_struct *vma,
 				    unsigned long addr, pud_t *pudp,
-				    int flags, struct follow_page_context *ctx)
+				    int flags, unsigned long *page_mask)
 {
 	return NULL;
 }
@@ -767,7 +754,7 @@ static struct page *follow_huge_pud(struct vm_area_struct *vma,
 static struct page *follow_huge_pmd(struct vm_area_struct *vma,
 				    unsigned long addr, pmd_t *pmd,
 				    unsigned int flags,
-				    struct follow_page_context *ctx)
+				    unsigned long *page_mask)
 {
 	return NULL;
 }
@@ -813,8 +800,7 @@ static inline bool can_follow_write_pte(pte_t pte, struct page *page,
 }
 
 static struct page *follow_page_pte(struct vm_area_struct *vma,
-		unsigned long address, pmd_t *pmd, unsigned int flags,
-		struct dev_pagemap **pgmap)
+		unsigned long address, pmd_t *pmd, unsigned int flags)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	struct folio *folio;
@@ -912,7 +898,7 @@ no_page:
 static struct page *follow_pmd_mask(struct vm_area_struct *vma,
 				    unsigned long address, pud_t *pudp,
 				    unsigned int flags,
-				    struct follow_page_context *ctx)
+				    unsigned long *page_mask)
 {
 	pmd_t *pmd, pmdval;
 	spinlock_t *ptl;
@@ -926,7 +912,7 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma,
 	if (!pmd_present(pmdval))
 		return no_page_table(vma, flags, address);
 	if (likely(!pmd_leaf(pmdval)))
-		return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);
+		return follow_page_pte(vma, address, pmd, flags);
 
 	if (pmd_protnone(pmdval) && !gup_can_follow_protnone(vma, flags))
 		return no_page_table(vma, flags, address);
@@ -939,16 +925,16 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma,
 	}
 	if (unlikely(!pmd_leaf(pmdval))) {
 		spin_unlock(ptl);
-		return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);
+		return follow_page_pte(vma, address, pmd, flags);
 	}
 	if (pmd_trans_huge(pmdval) && (flags & FOLL_SPLIT_PMD)) {
 		spin_unlock(ptl);
 		split_huge_pmd(vma, pmd, address);
 		/* If pmd was left empty, stuff a page table in there quickly */
 		return pte_alloc(mm, pmd) ? ERR_PTR(-ENOMEM) :
-			follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);
+			follow_page_pte(vma, address, pmd, flags);
 	}
-	page = follow_huge_pmd(vma, address, pmd, flags, ctx);
+	page = follow_huge_pmd(vma, address, pmd, flags, page_mask);
 	spin_unlock(ptl);
 	return page;
 }
@@ -956,7 +942,7 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma,
 static struct page *follow_pud_mask(struct vm_area_struct *vma,
 				    unsigned long address, p4d_t *p4dp,
 				    unsigned int flags,
-				    struct follow_page_context *ctx)
+				    unsigned long *page_mask)
 {
 	pud_t *pudp, pud;
 	spinlock_t *ptl;
@@ -969,7 +955,7 @@ static struct page *follow_pud_mask(struct vm_area_struct *vma,
 		return no_page_table(vma, flags, address);
 	if (pud_leaf(pud)) {
 		ptl = pud_lock(mm, pudp);
-		page = follow_huge_pud(vma, address, pudp, flags, ctx);
+		page = follow_huge_pud(vma, address, pudp, flags, page_mask);
 		spin_unlock(ptl);
 		if (page)
 			return page;
@@ -978,13 +964,13 @@ static struct page *follow_pud_mask(struct vm_area_struct *vma,
 	if (unlikely(pud_bad(pud)))
 		return no_page_table(vma, flags, address);
 
-	return follow_pmd_mask(vma, address, pudp, flags, ctx);
+	return follow_pmd_mask(vma, address, pudp, flags, page_mask);
 }
 
 static struct page *follow_p4d_mask(struct vm_area_struct *vma,
 				    unsigned long address, pgd_t *pgdp,
 				    unsigned int flags,
-				    struct follow_page_context *ctx)
+				    unsigned long *page_mask)
 {
 	p4d_t *p4dp, p4d;
 
@@ -995,7 +981,7 @@ static struct page *follow_p4d_mask(struct vm_area_struct *vma,
 	if (!p4d_present(p4d) || p4d_bad(p4d))
 		return no_page_table(vma, flags, address);
 
-	return follow_pud_mask(vma, address, p4dp, flags, ctx);
+	return follow_pud_mask(vma, address, p4dp, flags, page_mask);
 }
 
 /**
@@ -1003,20 +989,16 @@ static struct page *follow_p4d_mask(struct vm_area_struct *vma,
  * @vma: vm_area_struct mapping @address
  * @address: virtual address to look up
  * @flags: flags modifying lookup behaviour
- * @ctx: contains dev_pagemap for %ZONE_DEVICE memory pinning and a
- *       pointer to output page_mask
+ * @page_mask: a pointer to output page_mask
  *
  * @flags can have FOLL_ flags set, defined in <linux/mm.h>
  *
- * When getting pages from ZONE_DEVICE memory, the @ctx->pgmap caches
- * the device's dev_pagemap metadata to avoid repeating expensive lookups.
- *
  * When getting an anonymous page and the caller has to trigger unsharing
  * of a shared anonymous page first, -EMLINK is returned. The caller should
  * trigger a fault with FAULT_FLAG_UNSHARE set. Note that unsharing is only
  * relevant with FOLL_PIN and !FOLL_WRITE.
  *
- * On output, the @ctx->page_mask is set according to the size of the page.
+ * On output, @page_mask is set according to the size of the page.
  *
  * Return: the mapped (struct page *), %NULL if no mapping exists, or
  * an error pointer if there is a mapping to something not represented
@@ -1024,7 +1006,7 @@ static struct page *follow_p4d_mask(struct vm_area_struct *vma,
  */
 static struct page *follow_page_mask(struct vm_area_struct *vma,
 			      unsigned long address, unsigned int flags,
-			      struct follow_page_context *ctx)
+			      unsigned long *page_mask)
 {
 	pgd_t *pgd;
 	struct mm_struct *mm = vma->vm_mm;
@@ -1032,13 +1014,13 @@ static struct page *follow_page_mask(struct vm_area_struct *vma,
 
 	vma_pgtable_walk_begin(vma);
 
-	ctx->page_mask = 0;
+	*page_mask = 0;
 	pgd = pgd_offset(mm, address);
 
 	if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
 		page = no_page_table(vma, flags, address);
 	else
-		page = follow_p4d_mask(vma, address, pgd, flags, ctx);
+		page = follow_p4d_mask(vma, address, pgd, flags, page_mask);
 
 	vma_pgtable_walk_end(vma);
 
@@ -1376,7 +1358,7 @@ static long __get_user_pages(struct mm_struct *mm,
 {
 	long ret = 0, i = 0;
 	struct vm_area_struct *vma = NULL;
-	struct follow_page_context ctx = { NULL };
+	unsigned long page_mask = 0;
 
 	if (!nr_pages)
 		return 0;
@@ -1418,7 +1400,7 @@ static long __get_user_pages(struct mm_struct *mm,
 						pages ? &page : NULL);
 				if (ret)
 					goto out;
-				ctx.page_mask = 0;
+				page_mask = 0;
 				goto next_page;
 			}
 
@@ -1441,7 +1423,7 @@ retry:
 		}
 		cond_resched();
 
-		page = follow_page_mask(vma, start, gup_flags, &ctx);
+		page = follow_page_mask(vma, start, gup_flags, &page_mask);
 		if (!page || PTR_ERR(page) == -EMLINK) {
 			ret = faultin_page(vma, start, gup_flags,
 					   PTR_ERR(page) == -EMLINK, locked);
@@ -1474,7 +1456,7 @@ retry:
 			goto out;
 		}
 next_page:
-		page_increm = 1 + (~(start >> PAGE_SHIFT) & ctx.page_mask);
+		page_increm = 1 + (~(start >> PAGE_SHIFT) & page_mask);
 		if (page_increm > nr_pages)
 			page_increm = nr_pages;
 
@@ -1512,7 +1494,7 @@ next_page:
 			}
 
 			for (j = 0; j < page_increm; j++) {
-				subpage = nth_page(page, j);
+				subpage = page + j;
 				pages[i + j] = subpage;
 				flush_anon_page(vma, subpage, start + j * PAGE_SIZE);
 				flush_dcache_page(subpage);
@@ -1524,8 +1506,6 @@ next_page:
 		nr_pages -= page_increm;
 	} while (nr_pages);
 out:
-	if (ctx.pgmap)
-		put_dev_pagemap(ctx.pgmap);
 	return i ? i : ret;
 }
 
@@ -1693,7 +1673,7 @@ static __always_inline long __get_user_pages_locked(struct mm_struct *mm,
 		mmap_assert_locked(mm);
 
 	if (flags & FOLL_PIN)
-		mm_set_has_pinned_flag(&mm->flags);
+		mm_set_has_pinned_flag(mm);
 
 	/*
 	 * FOLL_PIN and FOLL_GET are mutually exclusive. Traditional behavior
@@ -2861,7 +2841,6 @@ static int gup_fast_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr,
 		unsigned long end, unsigned int flags, struct page **pages,
 		int *nr)
 {
-	struct dev_pagemap *pgmap = NULL;
 	int ret = 0;
 	pte_t *ptep, *ptem;
 
@@ -2919,12 +2898,9 @@ static int gup_fast_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr,
 		 * see Documentation/core-api/pin_user_pages.rst for
 		 * details.
 		 */
-		if (flags & FOLL_PIN) {
-			ret = arch_make_folio_accessible(folio);
-			if (ret) {
-				gup_put_folio(folio, 1, flags);
-				goto pte_unmap;
-			}
+		if ((flags & FOLL_PIN) && arch_make_folio_accessible(folio)) {
+			gup_put_folio(folio, 1, flags);
+			goto pte_unmap;
 		}
 		folio_set_referenced(folio);
 		pages[*nr] = page;
@@ -2934,8 +2910,6 @@ static int gup_fast_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr,
 	ret = 1;
 
 pte_unmap:
-	if (pgmap)
-		put_dev_pagemap(pgmap);
 	pte_unmap(ptem);
 	return ret;
 }
@@ -2972,8 +2946,8 @@ static int gup_fast_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 	if (pmd_special(orig))
 		return 0;
 
-	page = pmd_page(orig);
-	refs = record_subpages(page, PMD_SIZE, addr, end, pages + *nr);
+	refs = (end - addr) >> PAGE_SHIFT;
+	page = pmd_page(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
 
 	folio = try_grab_folio_fast(page, refs, flags);
 	if (!folio)
@@ -2993,7 +2967,10 @@ static int gup_fast_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 		return 0;
 	}
 
+	pages += *nr;
 	*nr += refs;
+	for (; refs; refs--)
+		*(pages++) = page++;
 	folio_set_referenced(folio);
 	return 1;
 }
@@ -3012,8 +2989,8 @@ static int gup_fast_pud_leaf(pud_t orig, pud_t *pudp, unsigned long addr,
 	if (pud_special(orig))
 		return 0;
 
-	page = pud_page(orig);
-	refs = record_subpages(page, PUD_SIZE, addr, end, pages + *nr);
+	refs = (end - addr) >> PAGE_SHIFT;
+	page = pud_page(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
 
 	folio = try_grab_folio_fast(page, refs, flags);
 	if (!folio)
@@ -3034,7 +3011,10 @@ static int gup_fast_pud_leaf(pud_t orig, pud_t *pudp, unsigned long addr,
 		return 0;
 	}
 
+	pages += *nr;
 	*nr += refs;
+	for (; refs; refs--)
+		*(pages++) = page++;
 	folio_set_referenced(folio);
 	return 1;
 }
@@ -3218,7 +3198,7 @@ static int gup_fast_fallback(unsigned long start, unsigned long nr_pages,
 		return -EINVAL;
 
 	if (gup_flags & FOLL_PIN)
-		mm_set_has_pinned_flag(&current->mm->flags);
+		mm_set_has_pinned_flag(current->mm);
 
 	if (!(gup_flags & FOLL_FAST_ONLY))
 		might_lock_read(&current->mm->mmap_lock);