Web lists-archives.com

[tip:x86/mm] mm/gup: Provide callback to check if __GUP_fast() is allowed for the range




Commit-ID:  73e10a61817dfc97fe7418bfad1f608e562d7348
Gitweb:     http://git.kernel.org/tip/73e10a61817dfc97fe7418bfad1f608e562d7348
Author:     Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
AuthorDate: Thu, 16 Mar 2017 18:26:54 +0300
Committer:  Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Sat, 18 Mar 2017 09:48:03 +0100

mm/gup: Provide callback to check if __GUP_fast() is allowed for the range

This is a preparation patch for the transition of x86 to the generic GUP_fast()
implementation.

On x86, get_user_pages_fast() does a couple of sanity checks to see if we can
call __get_user_pages_fast() for the range.

This kind of wrapping protection should be useful for the generic code too.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Aneesh Kumar K . V <aneesh.kumar@xxxxxxxxxxxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: Catalin Marinas <catalin.marinas@xxxxxxx>
Cc: Dann Frazier <dann.frazier@xxxxxxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxx>
Cc: H. Peter Anvin <hpa@xxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: Steve Capper <steve.capper@xxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: linux-arch@xxxxxxxxxxxxxxx
Cc: linux-mm@xxxxxxxxx
Link: http://lkml.kernel.org/r/20170316152655.37789-7-kirill.shutemov@xxxxxxxxxxxxxxx
[ Small readability edits. ]
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
 mm/gup.c | 24 +++++++++++++++++++++---
 1 file changed, 21 insertions(+), 3 deletions(-)

diff --git a/mm/gup.c b/mm/gup.c
index e3d1e80..527ec2c 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1614,6 +1614,21 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
 	return nr;
 }
 
+#ifndef gup_fast_permitted
+/*
+ * Check if it's allowed to use __get_user_pages_fast() for the range, or
+ * we need to fall back to the slow version:
+ */
+bool gup_fast_permitted(unsigned long start, int nr_pages, int write)
+{
+	unsigned long len, end;
+
+	len = (unsigned long) nr_pages << PAGE_SHIFT;
+	end = start + len;
+	return end >= start;
+}
+#endif
+
 /**
  * get_user_pages_fast() - pin user pages in memory
  * @start:	starting user address
@@ -1633,11 +1648,14 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
 int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 			struct page **pages)
 {
-	int nr, ret;
+	int nr = 0, ret = 0;
 
 	start &= PAGE_MASK;
-	nr = __get_user_pages_fast(start, nr_pages, write, pages);
-	ret = nr;
+
+	if (gup_fast_permitted(start, nr_pages, write)) {
+		nr = __get_user_pages_fast(start, nr_pages, write, pages);
+		ret = nr;
+	}
 
 	if (nr < nr_pages) {
 		/* Try to get the remaining pages with get_user_pages */