1 files changed, 202 insertions, 38 deletions

diff --git a/mm/gup.c b/mm/gup.c
index 12bc2bc33da7..a6e24e246f86 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -64,7 +64,7 @@ retry:
 		migration_entry_wait(mm, pmd, address);
 		goto retry;
 	}
-	if ((flags & FOLL_NUMA) && pte_numa(pte))
+	if ((flags & FOLL_NUMA) && pte_protnone(pte))
 		goto no_page;
 	if ((flags & FOLL_WRITE) && !pte_write(pte)) {
 		pte_unmap_unlock(ptep, ptl);
@@ -167,10 +167,10 @@ struct page *follow_page_mask(struct vm_area_struct *vma,
 	if (pud_none(*pud))
 		return no_page_table(vma, flags);
 	if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) {
-		if (flags & FOLL_GET)
-			return NULL;
-		page = follow_huge_pud(mm, address, pud, flags & FOLL_WRITE);
-		return page;
+		page = follow_huge_pud(mm, address, pud, flags);
+		if (page)
+			return page;
+		return no_page_table(vma, flags);
 	}
 	if (unlikely(pud_bad(*pud)))
 		return no_page_table(vma, flags);
@@ -179,21 +179,12 @@ struct page *follow_page_mask(struct vm_area_struct *vma,
 	if (pmd_none(*pmd))
 		return no_page_table(vma, flags);
 	if (pmd_huge(*pmd) && vma->vm_flags & VM_HUGETLB) {
-		page = follow_huge_pmd(mm, address, pmd, flags & FOLL_WRITE);
-		if (flags & FOLL_GET) {
-			/*
-			 * Refcount on tail pages are not well-defined and
-			 * shouldn't be taken. The caller should handle a NULL
-			 * return when trying to follow tail pages.
-			 */
-			if (PageHead(page))
-				get_page(page);
-			else
-				page = NULL;
-		}
-		return page;
+		page = follow_huge_pmd(mm, address, pmd, flags);
+		if (page)
+			return page;
+		return no_page_table(vma, flags);
 	}
-	if ((flags & FOLL_NUMA) && pmd_numa(*pmd))
+	if ((flags & FOLL_NUMA) && pmd_protnone(*pmd))
 		return no_page_table(vma, flags);
 	if (pmd_trans_huge(*pmd)) {
 		if (flags & FOLL_SPLIT) {
@@ -584,6 +575,185 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
 	return 0;
 }
 
+static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
+						struct mm_struct *mm,
+						unsigned long start,
+						unsigned long nr_pages,
+						int write, int force,
+						struct page **pages,
+						struct vm_area_struct **vmas,
+						int *locked, bool notify_drop,
+						unsigned int flags)
+{
+	long ret, pages_done;
+	bool lock_dropped;
+
+	if (locked) {
+		/* if VM_FAULT_RETRY can be returned, vmas become invalid */
+		BUG_ON(vmas);
+		/* check caller initialized locked */
+		BUG_ON(*locked != 1);
+	}
+
+	if (pages)
+		flags |= FOLL_GET;
+	if (write)
+		flags |= FOLL_WRITE;
+	if (force)
+		flags |= FOLL_FORCE;
+
+	pages_done = 0;
+	lock_dropped = false;
+	for (;;) {
+		ret = __get_user_pages(tsk, mm, start, nr_pages, flags, pages,
+				       vmas, locked);
+		if (!locked)
+			/* VM_FAULT_RETRY couldn't trigger, bypass */
+			return ret;
+
+		/* VM_FAULT_RETRY cannot return errors */
+		if (!*locked) {
+			BUG_ON(ret < 0);
+			BUG_ON(ret >= nr_pages);
+		}
+
+		if (!pages)
+			/* If it's a prefault don't insist harder */
+			return ret;
+
+		if (ret > 0) {
+			nr_pages -= ret;
+			pages_done += ret;
+			if (!nr_pages)
+				break;
+		}
+		if (*locked) {
+			/* VM_FAULT_RETRY didn't trigger */
+			if (!pages_done)
+				pages_done = ret;
+			break;
+		}
+		/* VM_FAULT_RETRY triggered, so seek to the faulting offset */
+		pages += ret;
+		start += ret << PAGE_SHIFT;
+
+		/*
+		 * Repeat on the address that fired VM_FAULT_RETRY
+		 * without FAULT_FLAG_ALLOW_RETRY but with
+		 * FAULT_FLAG_TRIED.
+		 */
+		*locked = 1;
+		lock_dropped = true;
+		down_read(&mm->mmap_sem);
+		ret = __get_user_pages(tsk, mm, start, 1, flags | FOLL_TRIED,
+				       pages, NULL, NULL);
+		if (ret != 1) {
+			BUG_ON(ret > 1);
+			if (!pages_done)
+				pages_done = ret;
+			break;
+		}
+		nr_pages--;
+		pages_done++;
+		if (!nr_pages)
+			break;
+		pages++;
+		start += PAGE_SIZE;
+	}
+	if (notify_drop && lock_dropped && *locked) {
+		/*
+		 * We must let the caller know we temporarily dropped the lock
+		 * and so the critical section protected by it was lost.
+		 */
+		up_read(&mm->mmap_sem);
+		*locked = 0;
+	}
+	return pages_done;
+}
+
+/*
+ * We can leverage the VM_FAULT_RETRY functionality in the page fault
+ * paths better by using either get_user_pages_locked() or
+ * get_user_pages_unlocked().
+ *
+ * get_user_pages_locked() is suitable to replace the form:
+ *
+ *      down_read(&mm->mmap_sem);
+ *      do_something()
+ *      get_user_pages(tsk, mm, ..., pages, NULL);
+ *      up_read(&mm->mmap_sem);
+ *
+ *  to:
+ *
+ *      int locked = 1;
+ *      down_read(&mm->mmap_sem);
+ *      do_something()
+ *      get_user_pages_locked(tsk, mm, ..., pages, &locked);
+ *      if (locked)
+ *          up_read(&mm->mmap_sem);
+ */
+long get_user_pages_locked(struct task_struct *tsk, struct mm_struct *mm,
+			   unsigned long start, unsigned long nr_pages,
+			   int write, int force, struct page **pages,
+			   int *locked)
+{
+	return __get_user_pages_locked(tsk, mm, start, nr_pages, write, force,
+				       pages, NULL, locked, true, FOLL_TOUCH);
+}
+EXPORT_SYMBOL(get_user_pages_locked);
+
+/*
+ * Same as get_user_pages_unlocked(...., FOLL_TOUCH) but it allows to
+ * pass additional gup_flags as last parameter (like FOLL_HWPOISON).
+ *
+ * NOTE: here FOLL_TOUCH is not set implicitly and must be set by the
+ * caller if required (just like with __get_user_pages). "FOLL_GET",
+ * "FOLL_WRITE" and "FOLL_FORCE" are set implicitly as needed
+ * according to the parameters "pages", "write", "force"
+ * respectively.
+ */
+__always_inline long __get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm,
+					       unsigned long start, unsigned long nr_pages,
+					       int write, int force, struct page **pages,
+					       unsigned int gup_flags)
+{
+	long ret;
+	int locked = 1;
+	down_read(&mm->mmap_sem);
+	ret = __get_user_pages_locked(tsk, mm, start, nr_pages, write, force,
+				      pages, NULL, &locked, false, gup_flags);
+	if (locked)
+		up_read(&mm->mmap_sem);
+	return ret;
+}
+EXPORT_SYMBOL(__get_user_pages_unlocked);
+
+/*
+ * get_user_pages_unlocked() is suitable to replace the form:
+ *
+ *      down_read(&mm->mmap_sem);
+ *      get_user_pages(tsk, mm, ..., pages, NULL);
+ *      up_read(&mm->mmap_sem);
+ *
+ *  with:
+ *
+ *      get_user_pages_unlocked(tsk, mm, ..., pages);
+ *
+ * It is functionally equivalent to get_user_pages_fast so
+ * get_user_pages_fast should be used instead, if the two parameters
+ * "tsk" and "mm" are respectively equal to current and current->mm,
+ * or if "force" shall be set to 1 (get_user_pages_fast misses the
+ * "force" parameter).
+ */
+long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm,
+			     unsigned long start, unsigned long nr_pages,
+			     int write, int force, struct page **pages)
+{
+	return __get_user_pages_unlocked(tsk, mm, start, nr_pages, write,
+					 force, pages, FOLL_TOUCH);
+}
+EXPORT_SYMBOL(get_user_pages_unlocked);
+
 /*
  * get_user_pages() - pin user pages in memory
  * @tsk:	the task_struct to use for page fault accounting, or
@@ -633,22 +803,18 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
  * use the correct cache flushing APIs.
  *
  * See also get_user_pages_fast, for performance critical applications.
+ *
+ * get_user_pages should be phased out in favor of
+ * get_user_pages_locked|unlocked or get_user_pages_fast. Nothing
+ * should use get_user_pages because it cannot pass
+ * FAULT_FLAG_ALLOW_RETRY to handle_mm_fault.
  */
 long get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 		unsigned long start, unsigned long nr_pages, int write,
 		int force, struct page **pages, struct vm_area_struct **vmas)
 {
-	int flags = FOLL_TOUCH;
-
-	if (pages)
-		flags |= FOLL_GET;
-	if (write)
-		flags |= FOLL_WRITE;
-	if (force)
-		flags |= FOLL_FORCE;
-
-	return __get_user_pages(tsk, mm, start, nr_pages, flags, pages, vmas,
-				NULL);
+	return __get_user_pages_locked(tsk, mm, start, nr_pages, write, force,
+				       pages, vmas, NULL, false, FOLL_TOUCH);
 }
 EXPORT_SYMBOL(get_user_pages);
 
@@ -740,10 +906,10 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 
 		/*
 		 * Similar to the PMD case below, NUMA hinting must take slow
-		 * path
+		 * path using the pte_protnone check.
 		 */
 		if (!pte_present(pte) || pte_special(pte) ||
-			pte_numa(pte) || (write && !pte_write(pte)))
+			pte_protnone(pte) || (write && !pte_write(pte)))
 			goto pte_unmap;
 
 		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
@@ -926,7 +1092,7 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
 
 	pmdp = pmd_offset(&pud, addr);
 	do {
-		pmd_t pmd = ACCESS_ONCE(*pmdp);
+		pmd_t pmd = READ_ONCE(*pmdp);
 
 		next = pmd_addr_end(addr, end);
 		if (pmd_none(pmd) || pmd_trans_splitting(pmd))
@@ -938,7 +1104,7 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
 			 * slowpath for accounting purposes and so that they
 			 * can be serialised against THP migration.
 			 */
-			if (pmd_numa(pmd))
+			if (pmd_protnone(pmd))
 				return 0;
 
 			if (!gup_huge_pmd(pmd, pmdp, addr, next, write,
@@ -1077,10 +1243,8 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 		start += nr << PAGE_SHIFT;
 		pages += nr;
 
-		down_read(&mm->mmap_sem);
-		ret = get_user_pages(current, mm, start,
-				     nr_pages - nr, write, 0, pages, NULL);
-		up_read(&mm->mmap_sem);
+		ret = get_user_pages_unlocked(current, mm, start,
+					      nr_pages - nr, write, 0, pages);
 
 		/* Have to be a bit careful with return values */
 		if (nr > 0) {