mm: gup: add __get_user_pages_unlocked to customize gup_flags

Some callers (like KVM) may want to set the gup_flags like FOLL_HWPOSION
to get a proper -EHWPOSION retval instead of -EFAULT to take a more
appropriate action if get_user_pages runs into a memory failure.

Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Andres Lagar-Cavilla <andreslc@google.com>
Cc: Peter Feiner <pfeiner@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 49 insertions, 15 deletions

diff --git a/include/linux/mm.h b/include/linux/mm.h
index fc499e675475..3696b3bd1d7e 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1265,6 +1265,10 @@ 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);
+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 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);
diff --git a/mm/gup.c b/mm/gup.c
index 71a37738a326..dad5875fb766 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -582,9 +582,9 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
 						int write, int force,
 						struct page **pages,
 						struct vm_area_struct **vmas,
-						int *locked, bool notify_drop)
+						int *locked, bool notify_drop,
+						unsigned int flags)
 {
-	int flags = FOLL_TOUCH;
 	long ret, pages_done;
 	bool lock_dropped;
 
@@ -698,11 +698,37 @@ long get_user_pages_locked(struct task_struct *tsk, struct mm_struct *mm,
 			   int *locked)
 {
 	return __get_user_pages_locked(tsk, mm, start, nr_pages, write, force,
-				       pages, NULL, locked, true);
+				       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);
@@ -723,14 +749,8 @@ 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)
 {
-	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);
-	if (locked)
-		up_read(&mm->mmap_sem);
-	return ret;
+	return __get_user_pages_unlocked(tsk, mm, start, nr_pages, write,
+					 force, pages, FOLL_TOUCH);
 }
 EXPORT_SYMBOL(get_user_pages_unlocked);
 
@@ -794,7 +814,7 @@ long get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 		int force, struct page **pages, struct vm_area_struct **vmas)
 {
 	return __get_user_pages_locked(tsk, mm, start, nr_pages, write, force,
-				       pages, vmas, NULL, false);
+				       pages, vmas, NULL, false, FOLL_TOUCH);
 }
 EXPORT_SYMBOL(get_user_pages);
 
diff --git a/mm/nommu.c b/mm/nommu.c
index bfb690b0f986..4d1b8a199867 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -224,9 +224,10 @@ long get_user_pages_locked(struct task_struct *tsk, struct mm_struct *mm,
 }
 EXPORT_SYMBOL(get_user_pages_locked);
 
-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)
+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;
 	down_read(&mm->mmap_sem);
@@ -235,6 +236,15 @@ long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm,
 	up_read(&mm->mmap_sem);
 	return ret;
 }
+EXPORT_SYMBOL(__get_user_pages_unlocked);
+
+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, 0);
+}
 EXPORT_SYMBOL(get_user_pages_unlocked);
 
 /**