ae07562909
Patch series "Fix CONT-PTE/PMD size hugetlb issue when unmapping or migrating", v4. 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@oracle.com/ [2] https://lore.kernel.org/all/cover.1651998586.git.baolin.wang@linux.alibaba.com/ [3] https://lore.kernel.org/linux-mm/20220503120343.6264e126@thinkpad/ This patch (of 3): 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. [baolin.wang@linux.alibaba.com: fix build in several more architectures] Link: https://lkml.kernel.org/r/0009a4cd-2826-e8be-e671-f050d4f18d5d@linux.alibaba.com [sfr@canb.auug.org.au: fixup] Link: https://lkml.kernel.org/r/20220511181531.7f27a5c1@canb.auug.org.au Link: https://lkml.kernel.org/r/cover.1652270205.git.baolin.wang@linux.alibaba.com Link: https://lkml.kernel.org/r/20f77ddab90baa249bd24504c413189b82acde69.1652270205.git.baolin.wang@linux.alibaba.com Link: https://lkml.kernel.org/r/cover.1652147571.git.baolin.wang@linux.alibaba.com Link: https://lkml.kernel.org/r/dcf065868cce35bceaf138613ad27f17bb7c0c19.1652147571.git.baolin.wang@linux.alibaba.com Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Acked-by: Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by: Muchun Song <songmuchun@bytedance.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will@kernel.org> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Helge Deller <deller@gmx.de> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Heiko Carstens <hca@linux.ibm.com> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Alexander Gordeev <agordeev@linux.ibm.com> Cc: Christian Borntraeger <borntraeger@linux.ibm.com> Cc: Sven Schnelle <svens@linux.ibm.com> Cc: Yoshinori Sato <ysato@users.osdn.me> Cc: Rich Felker <dalias@libc.org> Cc: David S. Miller <davem@davemloft.net> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
90 lines
2.1 KiB
C
90 lines
2.1 KiB
C
/*
|
|
* This file is subject to the terms and conditions of the GNU General Public
|
|
* License. See the file "COPYING" in the main directory of this archive
|
|
* for more details.
|
|
*
|
|
* Copyright (C) 2008, 2009 Cavium Networks, Inc.
|
|
*/
|
|
|
|
#ifndef __ASM_HUGETLB_H
|
|
#define __ASM_HUGETLB_H
|
|
|
|
#include <asm/page.h>
|
|
|
|
#define __HAVE_ARCH_PREPARE_HUGEPAGE_RANGE
|
|
static inline int prepare_hugepage_range(struct file *file,
|
|
unsigned long addr,
|
|
unsigned long len)
|
|
{
|
|
unsigned long task_size = STACK_TOP;
|
|
struct hstate *h = hstate_file(file);
|
|
|
|
if (len & ~huge_page_mask(h))
|
|
return -EINVAL;
|
|
if (addr & ~huge_page_mask(h))
|
|
return -EINVAL;
|
|
if (len > task_size)
|
|
return -ENOMEM;
|
|
if (task_size - len < addr)
|
|
return -EINVAL;
|
|
return 0;
|
|
}
|
|
|
|
#define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
|
|
static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
|
|
unsigned long addr, pte_t *ptep)
|
|
{
|
|
pte_t clear;
|
|
pte_t pte = *ptep;
|
|
|
|
pte_val(clear) = (unsigned long)invalid_pte_table;
|
|
set_pte_at(mm, addr, ptep, clear);
|
|
return pte;
|
|
}
|
|
|
|
#define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
|
|
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
|
|
*/
|
|
pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
|
|
flush_tlb_page(vma, addr);
|
|
return pte;
|
|
}
|
|
|
|
#define __HAVE_ARCH_HUGE_PTE_NONE
|
|
static inline int huge_pte_none(pte_t pte)
|
|
{
|
|
unsigned long val = pte_val(pte) & ~_PAGE_GLOBAL;
|
|
return !val || (val == (unsigned long)invalid_pte_table);
|
|
}
|
|
|
|
#define __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS
|
|
static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
|
|
unsigned long addr,
|
|
pte_t *ptep, pte_t pte,
|
|
int dirty)
|
|
{
|
|
int changed = !pte_same(*ptep, pte);
|
|
|
|
if (changed) {
|
|
set_pte_at(vma->vm_mm, addr, ptep, pte);
|
|
/*
|
|
* There could be some standard sized pages in there,
|
|
* get them all.
|
|
*/
|
|
flush_tlb_range(vma, addr, addr + HPAGE_SIZE);
|
|
}
|
|
return changed;
|
|
}
|
|
|
|
#include <asm-generic/hugetlb.h>
|
|
|
|
#endif /* __ASM_HUGETLB_H */
|