1 files changed, 154 insertions, 137 deletions

diff --git a/mm/gup.c b/mm/gup.c
index ca0f5cedce9b..f1d6bc06eb52 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -76,7 +76,7 @@ retry:
 	folio = page_folio(page);
 	if (WARN_ON_ONCE(folio_ref_count(folio) < 0))
 		return NULL;
-	if (unlikely(!folio_ref_try_add_rcu(folio, refs)))
+	if (unlikely(!folio_ref_try_add(folio, refs)))
 		return NULL;
 
 	/*
@@ -97,95 +97,6 @@ retry:
 	return folio;
 }
 
-/**
- * try_grab_folio() - Attempt to get or pin a folio.
- * @page:  pointer to page to be grabbed
- * @refs:  the value to (effectively) add to the folio's refcount
- * @flags: gup flags: these are the FOLL_* flag values.
- *
- * "grab" names in this file mean, "look at flags to decide whether to use
- * FOLL_PIN or FOLL_GET behavior, when incrementing the folio's refcount.
- *
- * Either FOLL_PIN or FOLL_GET (or neither) must be set, but not both at the
- * same time. (That's true throughout the get_user_pages*() and
- * pin_user_pages*() APIs.) Cases:
- *
- *    FOLL_GET: folio's refcount will be incremented by @refs.
- *
- *    FOLL_PIN on large folios: folio's refcount will be incremented by
- *    @refs, and its pincount will be incremented by @refs.
- *
- *    FOLL_PIN on single-page folios: folio's refcount will be incremented by
- *    @refs * GUP_PIN_COUNTING_BIAS.
- *
- * Return: The folio containing @page (with refcount appropriately
- * incremented) for success, or NULL upon failure. If neither FOLL_GET
- * nor FOLL_PIN was set, that's considered failure, and furthermore,
- * a likely bug in the caller, so a warning is also emitted.
- */
-struct folio *try_grab_folio(struct page *page, int refs, unsigned int flags)
-{
-	struct folio *folio;
-
-	if (WARN_ON_ONCE((flags & (FOLL_GET | FOLL_PIN)) == 0))
-		return NULL;
-
-	if (unlikely(!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(page)))
-		return NULL;
-
-	if (flags & FOLL_GET)
-		return try_get_folio(page, refs);
-
-	/* FOLL_PIN is set */
-
-	/*
-	 * Don't take a pin on the zero page - it's not going anywhere
-	 * and it is used in a *lot* of places.
-	 */
-	if (is_zero_page(page))
-		return page_folio(page);
-
-	folio = try_get_folio(page, refs);
-	if (!folio)
-		return NULL;
-
-	/*
-	 * Can't do FOLL_LONGTERM + FOLL_PIN gup fast path if not in a
-	 * right zone, so fail and let the caller fall back to the slow
-	 * path.
-	 */
-	if (unlikely((flags & FOLL_LONGTERM) &&
-		     !folio_is_longterm_pinnable(folio))) {
-		if (!put_devmap_managed_folio_refs(folio, refs))
-			folio_put_refs(folio, refs);
-		return NULL;
-	}
-
-	/*
-	 * When pinning a large folio, use an exact count to track it.
-	 *
-	 * However, be sure to *also* increment the normal folio
-	 * refcount field at least once, so that the folio really
-	 * is pinned.  That's why the refcount from the earlier
-	 * try_get_folio() is left intact.
-	 */
-	if (folio_test_large(folio))
-		atomic_add(refs, &folio->_pincount);
-	else
-		folio_ref_add(folio,
-				refs * (GUP_PIN_COUNTING_BIAS - 1));
-	/*
-	 * Adjust the pincount before re-checking the PTE for changes.
-	 * This is essentially a smp_mb() and is paired with a memory
-	 * barrier in folio_try_share_anon_rmap_*().
-	 */
-	smp_mb__after_atomic();
-
-	node_stat_mod_folio(folio, NR_FOLL_PIN_ACQUIRED, refs);
-
-	return folio;
-}
-
 static void gup_put_folio(struct folio *folio, int refs, unsigned int flags)
 {
 	if (flags & FOLL_PIN) {
@@ -203,58 +114,59 @@ static void gup_put_folio(struct folio *folio, int refs, unsigned int flags)
 }
 
 /**
- * try_grab_page() - elevate a page's refcount by a flag-dependent amount
- * @page:    pointer to page to be grabbed
- * @flags:   gup flags: these are the FOLL_* flag values.
+ * try_grab_folio() - add a folio's refcount by a flag-dependent amount
+ * @folio:    pointer to folio to be grabbed
+ * @refs:     the value to (effectively) add to the folio's refcount
+ * @flags:    gup flags: these are the FOLL_* flag values
  *
  * This might not do anything at all, depending on the flags argument.
  *
  * "grab" names in this file mean, "look at flags to decide whether to use
- * FOLL_PIN or FOLL_GET behavior, when incrementing the page's refcount.
+ * FOLL_PIN or FOLL_GET behavior, when incrementing the folio's refcount.
  *
  * Either FOLL_PIN or FOLL_GET (or neither) may be set, but not both at the same
- * time. Cases: please see the try_grab_folio() documentation, with
- * "refs=1".
+ * time.
  *
  * Return: 0 for success, or if no action was required (if neither FOLL_PIN
  * nor FOLL_GET was set, nothing is done). A negative error code for failure:
  *
- *   -ENOMEM		FOLL_GET or FOLL_PIN was set, but the page could not
+ *   -ENOMEM		FOLL_GET or FOLL_PIN was set, but the folio could not
  *			be grabbed.
+ *
+ * It is called when we have a stable reference for the folio, typically in
+ * GUP slow path.
  */
-int __must_check try_grab_page(struct page *page, unsigned int flags)
+int __must_check try_grab_folio(struct folio *folio, int refs,
+				unsigned int flags)
 {
-	struct folio *folio = page_folio(page);
-
 	if (WARN_ON_ONCE(folio_ref_count(folio) <= 0))
 		return -ENOMEM;
 
-	if (unlikely(!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(page)))
+	if (unlikely(!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(&folio->page)))
 		return -EREMOTEIO;
 
 	if (flags & FOLL_GET)
-		folio_ref_inc(folio);
+		folio_ref_add(folio, refs);
 	else if (flags & FOLL_PIN) {
 		/*
 		 * Don't take a pin on the zero page - it's not going anywhere
 		 * and it is used in a *lot* of places.
 		 */
-		if (is_zero_page(page))
+		if (is_zero_folio(folio))
 			return 0;
 
 		/*
-		 * Similar to try_grab_folio(): be sure to *also*
-		 * increment the normal page refcount field at least once,
+		 * Increment the normal page refcount field at least once,
 		 * so that the page really is pinned.
 		 */
 		if (folio_test_large(folio)) {
-			folio_ref_add(folio, 1);
-			atomic_add(1, &folio->_pincount);
+			folio_ref_add(folio, refs);
+			atomic_add(refs, &folio->_pincount);
 		} else {
-			folio_ref_add(folio, GUP_PIN_COUNTING_BIAS);
+			folio_ref_add(folio, refs * GUP_PIN_COUNTING_BIAS);
 		}
 
-		node_stat_mod_folio(folio, NR_FOLL_PIN_ACQUIRED, 1);
+		node_stat_mod_folio(folio, NR_FOLL_PIN_ACQUIRED, refs);
 	}
 
 	return 0;
@@ -515,6 +427,102 @@ static int record_subpages(struct page *page, unsigned long sz,
 
 	return nr;
 }
+
+/**
+ * try_grab_folio_fast() - Attempt to get or pin a folio in fast path.
+ * @page:  pointer to page to be grabbed
+ * @refs:  the value to (effectively) add to the folio's refcount
+ * @flags: gup flags: these are the FOLL_* flag values.
+ *
+ * "grab" names in this file mean, "look at flags to decide whether to use
+ * FOLL_PIN or FOLL_GET behavior, when incrementing the folio's refcount.
+ *
+ * Either FOLL_PIN or FOLL_GET (or neither) must be set, but not both at the
+ * same time. (That's true throughout the get_user_pages*() and
+ * pin_user_pages*() APIs.) Cases:
+ *
+ *    FOLL_GET: folio's refcount will be incremented by @refs.
+ *
+ *    FOLL_PIN on large folios: folio's refcount will be incremented by
+ *    @refs, and its pincount will be incremented by @refs.
+ *
+ *    FOLL_PIN on single-page folios: folio's refcount will be incremented by
+ *    @refs * GUP_PIN_COUNTING_BIAS.
+ *
+ * Return: The folio containing @page (with refcount appropriately
+ * incremented) for success, or NULL upon failure. If neither FOLL_GET
+ * nor FOLL_PIN was set, that's considered failure, and furthermore,
+ * a likely bug in the caller, so a warning is also emitted.
+ *
+ * It uses add ref unless zero to elevate the folio refcount and must be called
+ * in fast path only.
+ */
+static struct folio *try_grab_folio_fast(struct page *page, int refs,
+					 unsigned int flags)
+{
+	struct folio *folio;
+
+	/* Raise warn if it is not called in fast GUP */
+	VM_WARN_ON_ONCE(!irqs_disabled());
+
+	if (WARN_ON_ONCE((flags & (FOLL_GET | FOLL_PIN)) == 0))
+		return NULL;
+
+	if (unlikely(!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(page)))
+		return NULL;
+
+	if (flags & FOLL_GET)
+		return try_get_folio(page, refs);
+
+	/* FOLL_PIN is set */
+
+	/*
+	 * Don't take a pin on the zero page - it's not going anywhere
+	 * and it is used in a *lot* of places.
+	 */
+	if (is_zero_page(page))
+		return page_folio(page);
+
+	folio = try_get_folio(page, refs);
+	if (!folio)
+		return NULL;
+
+	/*
+	 * Can't do FOLL_LONGTERM + FOLL_PIN gup fast path if not in a
+	 * right zone, so fail and let the caller fall back to the slow
+	 * path.
+	 */
+	if (unlikely((flags & FOLL_LONGTERM) &&
+		     !folio_is_longterm_pinnable(folio))) {
+		if (!put_devmap_managed_folio_refs(folio, refs))
+			folio_put_refs(folio, refs);
+		return NULL;
+	}
+
+	/*
+	 * When pinning a large folio, use an exact count to track it.
+	 *
+	 * However, be sure to *also* increment the normal folio
+	 * refcount field at least once, so that the folio really
+	 * is pinned.  That's why the refcount from the earlier
+	 * try_get_folio() is left intact.
+	 */
+	if (folio_test_large(folio))
+		atomic_add(refs, &folio->_pincount);
+	else
+		folio_ref_add(folio,
+				refs * (GUP_PIN_COUNTING_BIAS - 1));
+	/*
+	 * Adjust the pincount before re-checking the PTE for changes.
+	 * This is essentially a smp_mb() and is paired with a memory
+	 * barrier in folio_try_share_anon_rmap_*().
+	 */
+	smp_mb__after_atomic();
+
+	node_stat_mod_folio(folio, NR_FOLL_PIN_ACQUIRED, refs);
+
+	return folio;
+}
 #endif	/* CONFIG_ARCH_HAS_HUGEPD || CONFIG_HAVE_GUP_FAST */
 
 #ifdef CONFIG_ARCH_HAS_HUGEPD
@@ -535,7 +543,7 @@ static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end,
  */
 static int gup_hugepte(struct vm_area_struct *vma, pte_t *ptep, unsigned long sz,
 		       unsigned long addr, unsigned long end, unsigned int flags,
-		       struct page **pages, int *nr)
+		       struct page **pages, int *nr, bool fast)
 {
 	unsigned long pte_end;
 	struct page *page;
@@ -558,9 +566,15 @@ static int gup_hugepte(struct vm_area_struct *vma, pte_t *ptep, unsigned long sz
 	page = pte_page(pte);
 	refs = record_subpages(page, sz, addr, end, pages + *nr);
 
-	folio = try_grab_folio(page, refs, flags);
-	if (!folio)
-		return 0;
+	if (fast) {
+		folio = try_grab_folio_fast(page, refs, flags);
+		if (!folio)
+			return 0;
+	} else {
+		folio = page_folio(page);
+		if (try_grab_folio(folio, refs, flags))
+			return 0;
+	}
 
 	if (unlikely(pte_val(pte) != pte_val(ptep_get(ptep)))) {
 		gup_put_folio(folio, refs, flags);
@@ -588,7 +602,7 @@ static int gup_hugepte(struct vm_area_struct *vma, pte_t *ptep, unsigned long sz
 static int gup_hugepd(struct vm_area_struct *vma, hugepd_t hugepd,
 		      unsigned long addr, unsigned int pdshift,
 		      unsigned long end, unsigned int flags,
-		      struct page **pages, int *nr)
+		      struct page **pages, int *nr, bool fast)
 {
 	pte_t *ptep;
 	unsigned long sz = 1UL << hugepd_shift(hugepd);
@@ -598,7 +612,8 @@ static int gup_hugepd(struct vm_area_struct *vma, hugepd_t hugepd,
 	ptep = hugepte_offset(hugepd, addr, pdshift);
 	do {
 		next = hugepte_addr_end(addr, end, sz);
-		ret = gup_hugepte(vma, ptep, sz, addr, end, flags, pages, nr);
+		ret = gup_hugepte(vma, ptep, sz, addr, end, flags, pages, nr,
+				  fast);
 		if (ret != 1)
 			return ret;
 	} while (ptep++, addr = next, addr != end);
@@ -625,7 +640,7 @@ static struct page *follow_hugepd(struct vm_area_struct *vma, hugepd_t hugepd,
 	ptep = hugepte_offset(hugepd, addr, pdshift);
 	ptl = huge_pte_lock(h, vma->vm_mm, ptep);
 	ret = gup_hugepd(vma, hugepd, addr, pdshift, addr + PAGE_SIZE,
-			 flags, &page, &nr);
+			 flags, &page, &nr, false);
 	spin_unlock(ptl);
 
 	if (ret == 1) {
@@ -642,7 +657,7 @@ static struct page *follow_hugepd(struct vm_area_struct *vma, hugepd_t hugepd,
 static inline int gup_hugepd(struct vm_area_struct *vma, hugepd_t hugepd,
 			     unsigned long addr, unsigned int pdshift,
 			     unsigned long end, unsigned int flags,
-			     struct page **pages, int *nr)
+			     struct page **pages, int *nr, bool fast)
 {
 	return 0;
 }
@@ -729,7 +744,7 @@ static struct page *follow_huge_pud(struct vm_area_struct *vma,
 	    gup_must_unshare(vma, flags, page))
 		return ERR_PTR(-EMLINK);
 
-	ret = try_grab_page(page, flags);
+	ret = try_grab_folio(page_folio(page), 1, flags);
 	if (ret)
 		page = ERR_PTR(ret);
 	else
@@ -806,7 +821,7 @@ static struct page *follow_huge_pmd(struct vm_area_struct *vma,
 	VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) &&
 			!PageAnonExclusive(page), page);
 
-	ret = try_grab_page(page, flags);
+	ret = try_grab_folio(page_folio(page), 1, flags);
 	if (ret)
 		return ERR_PTR(ret);
 
@@ -968,8 +983,8 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
 	VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) &&
 		       !PageAnonExclusive(page), page);
 
-	/* try_grab_page() does nothing unless FOLL_GET or FOLL_PIN is set. */
-	ret = try_grab_page(page, flags);
+	/* try_grab_folio() does nothing unless FOLL_GET or FOLL_PIN is set. */
+	ret = try_grab_folio(page_folio(page), 1, flags);
 	if (unlikely(ret)) {
 		page = ERR_PTR(ret);
 		goto out;
@@ -1233,7 +1248,7 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address,
 			goto unmap;
 		*page = pte_page(entry);
 	}
-	ret = try_grab_page(*page, gup_flags);
+	ret = try_grab_folio(page_folio(*page), 1, gup_flags);
 	if (unlikely(ret))
 		goto unmap;
 out:
@@ -1636,20 +1651,19 @@ next_page:
 			 * pages.
 			 */
 			if (page_increm > 1) {
-				struct folio *folio;
+				struct folio *folio = page_folio(page);
 
 				/*
 				 * Since we already hold refcount on the
 				 * large folio, this should never fail.
 				 */
-				folio = try_grab_folio(page, page_increm - 1,
-						       foll_flags);
-				if (WARN_ON_ONCE(!folio)) {
+				if (try_grab_folio(folio, page_increm - 1,
+						   foll_flags)) {
 					/*
 					 * Release the 1st page ref if the
 					 * folio is problematic, fail hard.
 					 */
-					gup_put_folio(page_folio(page), 1,
+					gup_put_folio(folio, 1,
 						      foll_flags);
 					ret = -EFAULT;
 					goto out;
@@ -2797,7 +2811,6 @@ EXPORT_SYMBOL(get_user_pages_unlocked);
  * This code is based heavily on the PowerPC implementation by Nick Piggin.
  */
 #ifdef CONFIG_HAVE_GUP_FAST
-
 /*
  * Used in the GUP-fast path to determine whether GUP is permitted to work on
  * a specific folio.
@@ -2962,7 +2975,7 @@ static int gup_fast_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr,
 		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
 		page = pte_page(pte);
 
-		folio = try_grab_folio(page, 1, flags);
+		folio = try_grab_folio_fast(page, 1, flags);
 		if (!folio)
 			goto pte_unmap;
 
@@ -3049,7 +3062,7 @@ static int gup_fast_devmap_leaf(unsigned long pfn, unsigned long addr,
 			break;
 		}
 
-		folio = try_grab_folio(page, 1, flags);
+		folio = try_grab_folio_fast(page, 1, flags);
 		if (!folio) {
 			gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages);
 			break;
@@ -3138,7 +3151,7 @@ static int gup_fast_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 	page = pmd_page(orig);
 	refs = record_subpages(page, PMD_SIZE, addr, end, pages + *nr);
 
-	folio = try_grab_folio(page, refs, flags);
+	folio = try_grab_folio_fast(page, refs, flags);
 	if (!folio)
 		return 0;
 
@@ -3182,7 +3195,7 @@ static int gup_fast_pud_leaf(pud_t orig, pud_t *pudp, unsigned long addr,
 	page = pud_page(orig);
 	refs = record_subpages(page, PUD_SIZE, addr, end, pages + *nr);
 
-	folio = try_grab_folio(page, refs, flags);
+	folio = try_grab_folio_fast(page, refs, flags);
 	if (!folio)
 		return 0;
 
@@ -3222,7 +3235,7 @@ static int gup_fast_pgd_leaf(pgd_t orig, pgd_t *pgdp, unsigned long addr,
 	page = pgd_page(orig);
 	refs = record_subpages(page, PGDIR_SIZE, addr, end, pages + *nr);
 
-	folio = try_grab_folio(page, refs, flags);
+	folio = try_grab_folio_fast(page, refs, flags);
 	if (!folio)
 		return 0;
 
@@ -3276,7 +3289,8 @@ static int gup_fast_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr,
 			 * pmd format and THP pmd format
 			 */
 			if (gup_hugepd(NULL, __hugepd(pmd_val(pmd)), addr,
-				       PMD_SHIFT, next, flags, pages, nr) != 1)
+				       PMD_SHIFT, next, flags, pages, nr,
+				       true) != 1)
 				return 0;
 		} else if (!gup_fast_pte_range(pmd, pmdp, addr, next, flags,
 					       pages, nr))
@@ -3306,7 +3320,8 @@ static int gup_fast_pud_range(p4d_t *p4dp, p4d_t p4d, unsigned long addr,
 				return 0;
 		} else if (unlikely(is_hugepd(__hugepd(pud_val(pud))))) {
 			if (gup_hugepd(NULL, __hugepd(pud_val(pud)), addr,
-				       PUD_SHIFT, next, flags, pages, nr) != 1)
+				       PUD_SHIFT, next, flags, pages, nr,
+				       true) != 1)
 				return 0;
 		} else if (!gup_fast_pmd_range(pudp, pud, addr, next, flags,
 					       pages, nr))
@@ -3333,7 +3348,8 @@ static int gup_fast_p4d_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr,
 		BUILD_BUG_ON(p4d_leaf(p4d));
 		if (unlikely(is_hugepd(__hugepd(p4d_val(p4d))))) {
 			if (gup_hugepd(NULL, __hugepd(p4d_val(p4d)), addr,
-				       P4D_SHIFT, next, flags, pages, nr) != 1)
+				       P4D_SHIFT, next, flags, pages, nr,
+				       true) != 1)
 				return 0;
 		} else if (!gup_fast_pud_range(p4dp, p4d, addr, next, flags,
 					       pages, nr))
@@ -3362,7 +3378,8 @@ static void gup_fast_pgd_range(unsigned long addr, unsigned long end,
 				return;
 		} else if (unlikely(is_hugepd(__hugepd(pgd_val(pgd))))) {
 			if (gup_hugepd(NULL, __hugepd(pgd_val(pgd)), addr,
-				       PGDIR_SHIFT, next, flags, pages, nr) != 1)
+				       PGDIR_SHIFT, next, flags, pages, nr,
+				       true) != 1)
 				return;
 		} else if (!gup_fast_p4d_range(pgdp, pgd, addr, next, flags,
 					       pages, nr))