[tip:x86/urgent] x86/mm: Fix regression with huge pages on PAE

From: tip-bot for Kirill A. Shutemov
Date: Fri Dec 04 2015 - 06:51:05 EST


Commit-ID: 70f1528747651b20c7769d3516ade369f9963237
Gitweb: http://git.kernel.org/tip/70f1528747651b20c7769d3516ade369f9963237
Author: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
AuthorDate: Mon, 30 Nov 2015 11:10:33 +0100
Committer: Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Fri, 4 Dec 2015 09:14:27 +0100

x86/mm: Fix regression with huge pages on PAE

Recent PAT patchset has caused issue on 32-bit PAE machines:

page:eea45000 count:0 mapcount:-128 mapping: (null) index:0x0 flags: 0x40000000()
page dumped because: VM_BUG_ON_PAGE(page_mapcount(page) < 0)
------------[ cut here ]------------
kernel BUG at /home/build/linux-boris/mm/huge_memory.c:1485!
invalid opcode: 0000 [#1] SMP
[...]
Call Trace:
unmap_single_vma
? __wake_up
unmap_vmas
unmap_region
do_munmap
vm_munmap
SyS_munmap
do_fast_syscall_32
? __do_page_fault
sysenter_past_esp
Code: ...
EIP: [<c11bde80>] zap_huge_pmd+0x240/0x260 SS:ESP 0068:f6459d98

The problem is in pmd_pfn_mask() and pmd_flags_mask(). These
helpers use PMD_PAGE_MASK to calculate resulting mask.
PMD_PAGE_MASK is 'unsigned long', not 'unsigned long long' as
phys_addr_t is on 32-bit PAE (ARCH_PHYS_ADDR_T_64BIT). As a
result, the upper bits of resulting mask get truncated.

pud_pfn_mask() and pud_flags_mask() aren't problematic since we
don't have PUD page table level on 32-bit systems, but it's
reasonable to keep them consistent with PMD counterpart.

Introduce PHYSICAL_PMD_PAGE_MASK and PHYSICAL_PUD_PAGE_MASK in
addition to existing PHYSICAL_PAGE_MASK and reworks helpers to
use them.

Reported-and-Tested-by: Boris Ostrovsky <boris.ostrovsky@xxxxxxxxxx>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
[ Fix -Woverflow warnings from the realmode code. ]
Signed-off-by: Borislav Petkov <bp@xxxxxxx>
Reviewed-by: Toshi Kani <toshi.kani@xxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: Brian Gerst <brgerst@xxxxxxxxx>
Cc: Denys Vlasenko <dvlasenk@xxxxxxxxxx>
Cc: H. Peter Anvin <hpa@xxxxxxxxx>
Cc: JÃrgen Gross <jgross@xxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: elliott@xxxxxxx
Cc: konrad.wilk@xxxxxxxxxx
Cc: linux-mm <linux-mm@xxxxxxxxx>
Fixes: f70abb0fc3da ("x86/asm: Fix pud/pmd interfaces to handle large PAT bit")
Link: http://lkml.kernel.org/r/1448878233-11390-2-git-send-email-bp@xxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>

Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
arch/x86/boot/boot.h | 1 -
arch/x86/boot/video-mode.c | 2 ++
arch/x86/boot/video.c | 2 ++
arch/x86/include/asm/page_types.h | 16 +++++++++-------
arch/x86/include/asm/pgtable_types.h | 14 ++++----------
arch/x86/include/asm/x86_init.h | 1 -
6 files changed, 17 insertions(+), 19 deletions(-)

diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h
index 0033e96..9011a88 100644
--- a/arch/x86/boot/boot.h
+++ b/arch/x86/boot/boot.h
@@ -23,7 +23,6 @@
#include <stdarg.h>
#include <linux/types.h>
#include <linux/edd.h>
-#include <asm/boot.h>
#include <asm/setup.h>
#include "bitops.h"
#include "ctype.h"
diff --git a/arch/x86/boot/video-mode.c b/arch/x86/boot/video-mode.c
index aa8a96b..95c7a81 100644
--- a/arch/x86/boot/video-mode.c
+++ b/arch/x86/boot/video-mode.c
@@ -19,6 +19,8 @@
#include "video.h"
#include "vesa.h"

+#include <uapi/asm/boot.h>
+
/*
* Common variables
*/
diff --git a/arch/x86/boot/video.c b/arch/x86/boot/video.c
index 05111bb..77780e3 100644
--- a/arch/x86/boot/video.c
+++ b/arch/x86/boot/video.c
@@ -13,6 +13,8 @@
* Select video mode
*/

+#include <uapi/asm/boot.h>
+
#include "boot.h"
#include "video.h"
#include "vesa.h"
diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index c5b7fb2..cc071c6 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -9,19 +9,21 @@
#define PAGE_SIZE (_AC(1,UL) << PAGE_SHIFT)
#define PAGE_MASK (~(PAGE_SIZE-1))

+#define PMD_PAGE_SIZE (_AC(1, UL) << PMD_SHIFT)
+#define PMD_PAGE_MASK (~(PMD_PAGE_SIZE-1))
+
+#define PUD_PAGE_SIZE (_AC(1, UL) << PUD_SHIFT)
+#define PUD_PAGE_MASK (~(PUD_PAGE_SIZE-1))
+
#define __PHYSICAL_MASK ((phys_addr_t)((1ULL << __PHYSICAL_MASK_SHIFT) - 1))
#define __VIRTUAL_MASK ((1UL << __VIRTUAL_MASK_SHIFT) - 1)

-/* Cast PAGE_MASK to a signed type so that it is sign-extended if
+/* Cast *PAGE_MASK to a signed type so that it is sign-extended if
virtual addresses are 32-bits but physical addresses are larger
(ie, 32-bit PAE). */
#define PHYSICAL_PAGE_MASK (((signed long)PAGE_MASK) & __PHYSICAL_MASK)
-
-#define PMD_PAGE_SIZE (_AC(1, UL) << PMD_SHIFT)
-#define PMD_PAGE_MASK (~(PMD_PAGE_SIZE-1))
-
-#define PUD_PAGE_SIZE (_AC(1, UL) << PUD_SHIFT)
-#define PUD_PAGE_MASK (~(PUD_PAGE_SIZE-1))
+#define PHYSICAL_PMD_PAGE_MASK (((signed long)PMD_PAGE_MASK) & __PHYSICAL_MASK)
+#define PHYSICAL_PUD_PAGE_MASK (((signed long)PUD_PAGE_MASK) & __PHYSICAL_MASK)

#define HPAGE_SHIFT PMD_SHIFT
#define HPAGE_SIZE (_AC(1,UL) << HPAGE_SHIFT)
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index dd5b0aa..a471cad 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -279,17 +279,14 @@ static inline pmdval_t native_pmd_val(pmd_t pmd)
static inline pudval_t pud_pfn_mask(pud_t pud)
{
if (native_pud_val(pud) & _PAGE_PSE)
- return PUD_PAGE_MASK & PHYSICAL_PAGE_MASK;
+ return PHYSICAL_PUD_PAGE_MASK;
else
return PTE_PFN_MASK;
}

static inline pudval_t pud_flags_mask(pud_t pud)
{
- if (native_pud_val(pud) & _PAGE_PSE)
- return ~(PUD_PAGE_MASK & (pudval_t)PHYSICAL_PAGE_MASK);
- else
- return ~PTE_PFN_MASK;
+ return ~pud_pfn_mask(pud);
}

static inline pudval_t pud_flags(pud_t pud)
@@ -300,17 +297,14 @@ static inline pudval_t pud_flags(pud_t pud)
static inline pmdval_t pmd_pfn_mask(pmd_t pmd)
{
if (native_pmd_val(pmd) & _PAGE_PSE)
- return PMD_PAGE_MASK & PHYSICAL_PAGE_MASK;
+ return PHYSICAL_PMD_PAGE_MASK;
else
return PTE_PFN_MASK;
}

static inline pmdval_t pmd_flags_mask(pmd_t pmd)
{
- if (native_pmd_val(pmd) & _PAGE_PSE)
- return ~(PMD_PAGE_MASK & (pmdval_t)PHYSICAL_PAGE_MASK);
- else
- return ~PTE_PFN_MASK;
+ return ~pmd_pfn_mask(pmd);
}

static inline pmdval_t pmd_flags(pmd_t pmd)
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 48d34d2..cd0fc0c 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -1,7 +1,6 @@
#ifndef _ASM_X86_PLATFORM_H
#define _ASM_X86_PLATFORM_H

-#include <asm/pgtable_types.h>
#include <asm/bootparam.h>

struct mpc_bus;
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/