The patch titled
Subject: mm: change huge_ptep_clear_flush() to return the original pte
has been added to the -mm mm-unstable branch. Its filename is
mm-change-huge_ptep_clear_flush-to-return-the-original-pte.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-change-huge_ptep_clear_flush-to-return-the-original-pte.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Baolin Wang <baolin.wang@xxxxxxxxxxxxxxxxx>
Subject: mm: change huge_ptep_clear_flush() to return the original pte
Patch series "Fix CONT-PTE/PMD size hugetlb issue when unmapping or migrating", v3.
presently, migrating a hugetlb page or unmapping a poisoned hugetlb page,
we'll use ptep_clear_flush() and set_pte_at() to nuke the page table entry
and remap it, and this is incorrect for CONT-PTE or CONT-PMD size hugetlb
page, which will cause potential data consistent issue. This patch set
will change to use hugetlb related APIs to fix this issue.
Note: Mike pointed out the huge_ptep_get() will only return the one
specific value, and it would not take into account the dirty or young bits
of CONT-PTE/PMDs like the huge_ptep_get_and_clear() [1]. This
inconsistent issue is not introduced by this patch set, and this issue
will be addressed in another thread [2]. Meanwhile the uffd for hugetlb
case [3] pointed out by Gerald also needs another patch to address.
[1] https://lore.kernel.org/linux-mm/85bd80b4-b4fd-0d3f-a2e5-149559f2f387@xxxxxxxxxx/
[2] https://lore.kernel.org/all/cover.1651998586.git.baolin.wang@xxxxxxxxxxxxxxxxx/
[3] https://lore.kernel.org/linux-mm/20220503120343.6264e126@thinkpad/
It is incorrect to use ptep_clear_flush() to nuke a hugetlb page table
when unmapping or migrating a hugetlb page, and will change to use
huge_ptep_clear_flush() instead in the following patches.
So this is a preparation patch, which changes the huge_ptep_clear_flush()
to return the original pte to help to nuke a hugetlb page table.
Link: https://lkml.kernel.org/r/cover.1652147571.git.baolin.wang@xxxxxxxxxxxxxxxxx
Link: https://lkml.kernel.org/r/dcf065868cce35bceaf138613ad27f17bb7c0c19.1652147571.git.baolin.wang@xxxxxxxxxxxxxxxxx
Signed-off-by: Baolin Wang <baolin.wang@xxxxxxxxxxxxxxxxx>
Acked-by: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Reviewed-by: Muchun Song <songmuchun@xxxxxxxxxxxxx>
Cc: Catalin Marinas <catalin.marinas@xxxxxxx>
Cc: Will Deacon <will@xxxxxxxxxx>
Cc: Thomas Bogendoerfer <tsbogend@xxxxxxxxxxxxxxxx>
Cc: James Bottomley <James.Bottomley@xxxxxxxxxxxxxxxxxxxxx>
Cc: Helge Deller <deller@xxxxxx>
Cc: Michael Ellerman <mpe@xxxxxxxxxxxxxx>
Cc: Benjamin Herrenschmidt <benh@xxxxxxxxxxxxxxxxxxx>
Cc: Paul Mackerras <paulus@xxxxxxxxx>
Cc: Heiko Carstens <hca@xxxxxxxxxxxxx>
Cc: Vasily Gorbik <gor@xxxxxxxxxxxxx>
Cc: Alexander Gordeev <agordeev@xxxxxxxxxxxxx>
Cc: Christian Borntraeger <borntraeger@xxxxxxxxxxxxx>
Cc: Sven Schnelle <svens@xxxxxxxxxxxxx>
Cc: Yoshinori Sato <ysato@xxxxxxxxxxxxx>
Cc: Rich Felker <dalias@xxxxxxxx>
Cc: David S. Miller <davem@xxxxxxxxxxxxx>
Cc: Arnd Bergmann <arnd@xxxxxxxx>
Cc: Gerald Schaefer <gerald.schaefer@xxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
arch/arm64/include/asm/hugetlb.h | 4 ++--
arch/arm64/mm/hugetlbpage.c | 12 +++++-------
arch/ia64/include/asm/hugetlb.h | 4 ++--
arch/mips/include/asm/hugetlb.h | 9 ++++++---
arch/parisc/include/asm/hugetlb.h | 4 ++--
arch/powerpc/include/asm/hugetlb.h | 9 ++++++---
arch/s390/include/asm/hugetlb.h | 6 +++---
arch/sh/include/asm/hugetlb.h | 4 ++--
arch/sparc/include/asm/hugetlb.h | 4 ++--
include/asm-generic/hugetlb.h | 4 ++--
10 files changed, 32 insertions(+), 28 deletions(-)
--- a/arch/arm64/include/asm/hugetlb.h~mm-change-huge_ptep_clear_flush-to-return-the-original-pte
+++ a/arch/arm64/include/asm/hugetlb.h
@@ -39,8 +39,8 @@ extern pte_t huge_ptep_get_and_clear(str
extern void huge_ptep_set_wrprotect(struct mm_struct *mm,
unsigned long addr, pte_t *ptep);
#define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
-extern void huge_ptep_clear_flush(struct vm_area_struct *vma,
- unsigned long addr, pte_t *ptep);
+extern pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep);
#define __HAVE_ARCH_HUGE_PTE_CLEAR
extern void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, unsigned long sz);
--- a/arch/arm64/mm/hugetlbpage.c~mm-change-huge_ptep_clear_flush-to-return-the-original-pte
+++ a/arch/arm64/mm/hugetlbpage.c
@@ -486,19 +486,17 @@ void huge_ptep_set_wrprotect(struct mm_s
set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot));
}
-void huge_ptep_clear_flush(struct vm_area_struct *vma,
- unsigned long addr, pte_t *ptep)
+pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep)
{
size_t pgsize;
int ncontig;
- if (!pte_cont(READ_ONCE(*ptep))) {
- ptep_clear_flush(vma, addr, ptep);
- return;
- }
+ if (!pte_cont(READ_ONCE(*ptep)))
+ return ptep_clear_flush(vma, addr, ptep);
ncontig = find_num_contig(vma->vm_mm, addr, ptep, &pgsize);
- clear_flush(vma->vm_mm, addr, ptep, pgsize, ncontig);
+ return get_clear_flush(vma->vm_mm, addr, ptep, pgsize, ncontig);
}
static int __init hugetlbpage_init(void)
--- a/arch/ia64/include/asm/hugetlb.h~mm-change-huge_ptep_clear_flush-to-return-the-original-pte
+++ a/arch/ia64/include/asm/hugetlb.h
@@ -23,8 +23,8 @@ static inline int is_hugepage_only_range
#define is_hugepage_only_range is_hugepage_only_range
#define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
-static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
- unsigned long addr, pte_t *ptep)
+static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep)
{
}
--- a/arch/mips/include/asm/hugetlb.h~mm-change-huge_ptep_clear_flush-to-return-the-original-pte
+++ a/arch/mips/include/asm/hugetlb.h
@@ -43,16 +43,19 @@ static inline pte_t huge_ptep_get_and_cl
}
#define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
-static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
- unsigned long addr, pte_t *ptep)
+static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep)
{
+ pte_t pte;
+
/*
* clear the huge pte entry firstly, so that the other smp threads will
* not get old pte entry after finishing flush_tlb_page and before
* setting new huge pte entry
*/
- huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+ pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
flush_tlb_page(vma, addr);
+ return pte;
}
#define __HAVE_ARCH_HUGE_PTE_NONE
--- a/arch/parisc/include/asm/hugetlb.h~mm-change-huge_ptep_clear_flush-to-return-the-original-pte
+++ a/arch/parisc/include/asm/hugetlb.h
@@ -28,8 +28,8 @@ static inline int prepare_hugepage_range
}
#define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
-static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
- unsigned long addr, pte_t *ptep)
+static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep)
{
}
--- a/arch/powerpc/include/asm/hugetlb.h~mm-change-huge_ptep_clear_flush-to-return-the-original-pte
+++ a/arch/powerpc/include/asm/hugetlb.h
@@ -43,11 +43,14 @@ static inline pte_t huge_ptep_get_and_cl
}
#define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
-static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
- unsigned long addr, pte_t *ptep)
+static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep)
{
- huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+ pte_t pte;
+
+ pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
flush_hugetlb_page(vma, addr);
+ return pte;
}
#define __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS
--- a/arch/s390/include/asm/hugetlb.h~mm-change-huge_ptep_clear_flush-to-return-the-original-pte
+++ a/arch/s390/include/asm/hugetlb.h
@@ -50,10 +50,10 @@ static inline void huge_pte_clear(struct
set_pte(ptep, __pte(_SEGMENT_ENTRY_EMPTY));
}
-static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
- unsigned long address, pte_t *ptep)
+static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
+ unsigned long address, pte_t *ptep)
{
- huge_ptep_get_and_clear(vma->vm_mm, address, ptep);
+ return huge_ptep_get_and_clear(vma->vm_mm, address, ptep);
}
static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
--- a/arch/sh/include/asm/hugetlb.h~mm-change-huge_ptep_clear_flush-to-return-the-original-pte
+++ a/arch/sh/include/asm/hugetlb.h
@@ -21,8 +21,8 @@ static inline int prepare_hugepage_range
}
#define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
-static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
- unsigned long addr, pte_t *ptep)
+static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep)
{
}
--- a/arch/sparc/include/asm/hugetlb.h~mm-change-huge_ptep_clear_flush-to-return-the-original-pte
+++ a/arch/sparc/include/asm/hugetlb.h
@@ -21,8 +21,8 @@ pte_t huge_ptep_get_and_clear(struct mm_
pte_t *ptep);
#define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
-static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
- unsigned long addr, pte_t *ptep)
+static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep)
{
}
--- a/include/asm-generic/hugetlb.h~mm-change-huge_ptep_clear_flush-to-return-the-original-pte
+++ a/include/asm-generic/hugetlb.h
@@ -84,10 +84,10 @@ static inline pte_t huge_ptep_get_and_cl
#endif
#ifndef __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
-static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
+static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep)
{
- ptep_clear_flush(vma, addr, ptep);
+ return ptep_clear_flush(vma, addr, ptep);
}
#endif
_
Patches currently in -mm which might be from baolin.wang@xxxxxxxxxxxxxxxxx are
mm-change-huge_ptep_clear_flush-to-return-the-original-pte.patch
mm-rmap-fix-cont-pte-pmd-size-hugetlb-issue-when-migration.patch
mm-rmap-fix-cont-pte-pmd-size-hugetlb-issue-when-unmapping.patch
