[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20170316152655.37789-7-kirill.shutemov@linux.intel.com>
Date: Thu, 16 Mar 2017 18:26:54 +0300
From: "Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>
To: Linus Torvalds <torvalds@...ux-foundation.org>,
Andrew Morton <akpm@...ux-foundation.org>, x86@...nel.org,
Thomas Gleixner <tglx@...utronix.de>,
Ingo Molnar <mingo@...hat.com>,
"H. Peter Anvin" <hpa@...or.com>
Cc: Dave Hansen <dave.hansen@...el.com>,
"Aneesh Kumar K . V" <aneesh.kumar@...ux.vnet.ibm.com>,
Steve Capper <steve.capper@...aro.org>,
Dann Frazier <dann.frazier@...onical.com>,
Catalin Marinas <catalin.marinas@....com>,
linux-arch@...r.kernel.org, linux-mm@...ck.org,
linux-kernel@...r.kernel.org,
"Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>
Subject: [PATCH 6/7] mm/gup: Provide hook to check if __GUP_fast() is allowed for the range
This is preparation patch for transition of x86 to generic GUP_fast()
implementation.
On x86, get_user_pages_fast() does few sanity checks to see if we can
call __get_user_pages_fast() for the range.
Wrapping protection should be useful for generic code too.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@...ux.intel.com>
---
mm/gup.c | 24 +++++++++++++++++++++---
1 file changed, 21 insertions(+), 3 deletions(-)
diff --git a/mm/gup.c b/mm/gup.c
index e04f76594eb9..a6e21380c8b0 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1600,6 +1600,21 @@ 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
+ * need to fallback to non-fast 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
@@ -1619,11 +1634,14 @@ 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 */
--
2.11.0
Powered by blists - more mailing lists