1 files changed, 53 insertions, 63 deletions
diff --git a/mm/gup.c b/mm/gup.c
index 3b75e631f369..855ab860f88b 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -596,6 +596,33 @@ static struct folio *try_grab_folio_fast(struct page *page, int refs,
 }
 #endif	/* CONFIG_HAVE_GUP_FAST */
 
+/* Common code for can_follow_write_* */
+static inline bool can_follow_write_common(struct page *page,
+		struct vm_area_struct *vma, unsigned int flags)
+{
+	/* Maybe FOLL_FORCE is set to override it? */
+	if (!(flags & FOLL_FORCE))
+		return false;
+
+	/* But FOLL_FORCE has no effect on shared mappings */
+	if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED))
+		return false;
+
+	/* ... or read-only private ones */
+	if (!(vma->vm_flags & VM_MAYWRITE))
+		return false;
+
+	/* ... or already writable ones that just need to take a write fault */
+	if (vma->vm_flags & VM_WRITE)
+		return false;
+
+	/*
+	 * See can_change_pte_writable(): we broke COW and could map the page
+	 * writable if we have an exclusive anonymous page ...
+	 */
+	return page && PageAnon(page) && PageAnonExclusive(page);
+}
+
 static struct page *no_page_table(struct vm_area_struct *vma,
 				  unsigned int flags, unsigned long address)
 {
@@ -622,6 +649,18 @@ static struct page *no_page_table(struct vm_area_struct *vma,
 }
 
 #ifdef CONFIG_PGTABLE_HAS_HUGE_LEAVES
+/* FOLL_FORCE can write to even unwritable PUDs in COW mappings. */
+static inline bool can_follow_write_pud(pud_t pud, struct page *page,
+					struct vm_area_struct *vma,
+					unsigned int flags)
+{
+	/* If the pud is writable, we can write to the page. */
+	if (pud_write(pud))
+		return true;
+
+	return can_follow_write_common(page, vma, flags);
+}
+
 static struct page *follow_huge_pud(struct vm_area_struct *vma,
 				    unsigned long addr, pud_t *pudp,
 				    int flags, struct follow_page_context *ctx)
@@ -634,10 +673,11 @@ static struct page *follow_huge_pud(struct vm_area_struct *vma,
 
 	assert_spin_locked(pud_lockptr(mm, pudp));
 
-	if ((flags & FOLL_WRITE) && !pud_write(pud))
+	if (!pud_present(pud))
 		return NULL;
 
-	if (!pud_present(pud))
+	if ((flags & FOLL_WRITE) &&
+	    !can_follow_write_pud(pud, pfn_to_page(pfn), vma, flags))
 		return NULL;
 
 	pfn += (addr & ~PUD_MASK) >> PAGE_SHIFT;
@@ -686,27 +726,7 @@ static inline bool can_follow_write_pmd(pmd_t pmd, struct page *page,
 	if (pmd_write(pmd))
 		return true;
 
-	/* Maybe FOLL_FORCE is set to override it? */
-	if (!(flags & FOLL_FORCE))
-		return false;
-
-	/* But FOLL_FORCE has no effect on shared mappings */
-	if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED))
-		return false;
-
-	/* ... or read-only private ones */
-	if (!(vma->vm_flags & VM_MAYWRITE))
-		return false;
-
-	/* ... or already writable ones that just need to take a write fault */
-	if (vma->vm_flags & VM_WRITE)
-		return false;
-
-	/*
-	 * See can_change_pte_writable(): we broke COW and could map the page
-	 * writable if we have an exclusive anonymous page ...
-	 */
-	if (!page || !PageAnon(page) || !PageAnonExclusive(page))
+	if (!can_follow_write_common(page, vma, flags))
 		return false;
 
 	/* ... and a write-fault isn't required for other reasons. */
@@ -807,27 +827,7 @@ static inline bool can_follow_write_pte(pte_t pte, struct page *page,
 	if (pte_write(pte))
 		return true;
 
-	/* Maybe FOLL_FORCE is set to override it? */
-	if (!(flags & FOLL_FORCE))
-		return false;
-
-	/* But FOLL_FORCE has no effect on shared mappings */
-	if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED))
-		return false;
-
-	/* ... or read-only private ones */
-	if (!(vma->vm_flags & VM_MAYWRITE))
-		return false;
-
-	/* ... or already writable ones that just need to take a write fault */
-	if (vma->vm_flags & VM_WRITE)
-		return false;
-
-	/*
-	 * See can_change_pte_writable(): we broke COW and could map the page
-	 * writable if we have an exclusive anonymous page ...
-	 */
-	if (!page || !PageAnon(page) || !PageAnonExclusive(page))
+	if (!can_follow_write_common(page, vma, flags))
 		return false;
 
 	/* ... and a write-fault isn't required for other reasons. */
@@ -1294,9 +1294,6 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
 		if (!(vm_flags & VM_WRITE) || (vm_flags & VM_SHADOW_STACK)) {
 			if (!(gup_flags & FOLL_FORCE))
 				return -EFAULT;
-			/* hugetlb does not support FOLL_FORCE|FOLL_WRITE. */
-			if (is_vm_hugetlb_page(vma))
-				return -EFAULT;
 			/*
 			 * We used to let the write,force case do COW in a
 			 * VM_MAYWRITE VM_SHARED !VM_WRITE vma, so ptrace could
@@ -2257,6 +2254,7 @@ EXPORT_SYMBOL(fault_in_readable);
 /**
  * get_dump_page() - pin user page in memory while writing it to core dump
  * @addr: user address
+ * @locked: a pointer to an int denoting whether the mmap sem is held
  *
  * Returns struct page pointer of user page pinned for dump,
  * to be freed afterwards by put_page().
@@ -2269,13 +2267,12 @@ EXPORT_SYMBOL(fault_in_readable);
  * Called without mmap_lock (takes and releases the mmap_lock by itself).
  */
 #ifdef CONFIG_ELF_CORE
-struct page *get_dump_page(unsigned long addr)
+struct page *get_dump_page(unsigned long addr, int *locked)
 {
 	struct page *page;
-	int locked = 0;
 	int ret;
 
-	ret = __get_user_pages_locked(current->mm, addr, 1, &page, &locked,
+	ret = __get_user_pages_locked(current->mm, addr, 1, &page, locked,
 				      FOLL_FORCE | FOLL_DUMP | FOLL_GET);
 	return (ret == 1) ? page : NULL;
 }
@@ -2323,13 +2320,13 @@ static void pofs_unpin(struct pages_or_folios *pofs)
 /*
  * Returns the number of collected folios. Return value is always >= 0.
  */
-static unsigned long collect_longterm_unpinnable_folios(
+static void 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;
 	bool drain_allow = true;
+	unsigned long i;
 
 	for (i = 0; i < pofs->nr_entries; i++) {
 		struct folio *folio = pofs_get_folio(pofs, i);
@@ -2341,13 +2338,11 @@ static unsigned long collect_longterm_unpinnable_folios(
 		if (folio_is_longterm_pinnable(folio))
 			continue;
 
-		collected++;
-
 		if (folio_is_device_coherent(folio))
 			continue;
 
 		if (folio_test_hugetlb(folio)) {
-			isolate_hugetlb(folio, movable_folio_list);
+			folio_isolate_hugetlb(folio, movable_folio_list);
 			continue;
 		}
 
@@ -2364,8 +2359,6 @@ static unsigned long collect_longterm_unpinnable_folios(
 				    NR_ISOLATED_ANON + folio_is_file_lru(folio),
 				    folio_nr_pages(folio));
 	}
-
-	return collected;
 }
 
 /*
@@ -2442,11 +2435,9 @@ static long
 check_and_migrate_movable_pages_or_folios(struct pages_or_folios *pofs)
 {
 	LIST_HEAD(movable_folio_list);
-	unsigned long collected;
 
-	collected = collect_longterm_unpinnable_folios(&movable_folio_list,
-						       pofs);
-	if (!collected)
+	collect_longterm_unpinnable_folios(&movable_folio_list, pofs);
+	if (list_empty(&movable_folio_list))
 		return 0;
 
 	return migrate_longterm_unpinnable_folios(&movable_folio_list, pofs);
@@ -3360,8 +3351,7 @@ static unsigned long gup_fast(unsigned long start, unsigned long end,
 		return 0;
 
 	if (gup_flags & FOLL_PIN) {
-		seq = raw_read_seqcount(&current->mm->write_protect_seq);
-		if (seq & 1)
+		if (!raw_seqcount_try_begin(&current->mm->write_protect_seq, seq))
 			return 0;
 	}