[tip:x86/mm] x86/mm/gup: Add 5-level paging support

[tip-bot for Kirill A. Shutemov]

Commit-ID:  0318e5abe1c0933b8bf6763a1a0d3caec4f0826d
Gitweb:     http://git.kernel.org/tip/0318e5abe1c0933b8bf6763a1a0d3caec4f0826d
Author:     Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
AuthorDate: Mon, 13 Mar 2017 17:33:06 +0300
Committer:  Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Tue, 14 Mar 2017 08:45:08 +0100

x86/mm/gup: Add 5-level paging support

Extend get_user_pages_fast() to handle an additional page table level.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: Arnd Bergmann <arnd@xxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: Brian Gerst <brgerst@xxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxx>
Cc: Denys Vlasenko <dvlasenk@xxxxxxxxxx>
Cc: H. Peter Anvin <hpa@xxxxxxxxx>
Cc: Josh Poimboeuf <jpoimboe@xxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: linux-arch@xxxxxxxxxxxxxxx
Cc: linux-mm@xxxxxxxxx
Link: http://lkml.kernel.org/r/20170313143309.16020-4-kirill.shutemov@xxxxxxxxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
 arch/x86/mm/gup.c | 33 +++++++++++++++++++++++++++------
 1 file changed, 27 insertions(+), 6 deletions(-)

diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index 1f3b6ef..456dfdf 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -76,9 +76,9 @@ static void undo_dev_pagemap(int *nr, int nr_start, struct page **pages)
 }
 
 /*
- * 'pteval' can come from a pte, pmd or pud.  We only check
+ * 'pteval' can come from a pte, pmd, pud or p4d.  We only check
  * _PAGE_PRESENT, _PAGE_USER, and _PAGE_RW in here which are the
- * same value on all 3 types.
+ * same value on all 4 types.
  */
 static inline int pte_allows_gup(unsigned long pteval, int write)
 {
@@ -295,13 +295,13 @@ static noinline int gup_huge_pud(pud_t pud, unsigned long addr,
 	return 1;
 }
 
-static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
+static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end,
 			int write, struct page **pages, int *nr)
 {
 	unsigned long next;
 	pud_t *pudp;
 
-	pudp = pud_offset(&pgd, addr);
+	pudp = pud_offset(&p4d, addr);
 	do {
 		pud_t pud = *pudp;
 
@@ -320,6 +320,27 @@ static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
 	return 1;
 }
 
+static int gup_p4d_range(pgd_t pgd, unsigned long addr, unsigned long end,
+			int write, struct page **pages, int *nr)
+{
+	unsigned long next;
+	p4d_t *p4dp;
+
+	p4dp = p4d_offset(&pgd, addr);
+	do {
+		p4d_t p4d = *p4dp;
+
+		next = p4d_addr_end(addr, end);
+		if (p4d_none(p4d))
+			return 0;
+		BUILD_BUG_ON(p4d_large(p4d));
+		if (!gup_pud_range(p4d, addr, next, write, pages, nr))
+			return 0;
+	} while (p4dp++, addr = next, addr != end);
+
+	return 1;
+}
+
 /*
  * Like get_user_pages_fast() except its IRQ-safe in that it won't fall
  * back to the regular GUP.
@@ -368,7 +389,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
 		next = pgd_addr_end(addr, end);
 		if (pgd_none(pgd))
 			break;
-		if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
+		if (!gup_p4d_range(pgd, addr, next, write, pages, &nr))
 			break;
 	} while (pgdp++, addr = next, addr != end);
 	local_irq_restore(flags);
@@ -440,7 +461,7 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 		next = pgd_addr_end(addr, end);
 		if (pgd_none(pgd))
 			goto slow;
-		if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
+		if (!gup_p4d_range(pgd, addr, next, write, pages, &nr))
 			goto slow;
 	} while (pgdp++, addr = next, addr != end);
 	local_irq_enable();