2923b27e54
* memory_failure() gets confused by dev_pagemap backed mappings. The recovery code has specific enabling for several possible page states that needs new enabling to handle poison in dax mappings. Teach memory_failure() about ZONE_DEVICE pages. -----BEGIN PGP SIGNATURE----- iQIzBAABCAAdFiEE5DAy15EJMCV1R6v9YGjFFmlTOEoFAlt9ui8ACgkQYGjFFmlT OEpNRw//XGj9s7sezfJFeol4psJlRUd935yii/gmJRgi/yPf2VxxQG9qyM6SMBUc 75jASfOL6FSsfxHz0kplyWzMDNdrTkNNAD+9rv80FmY7GqWgcas9DaJX7jZ994vI 5SRO7pfvNZcXlo7IhqZippDw3yxkIU9Ufi0YQKaEUm7GFieptvCZ0p9x3VYfdvwM BExrxQe0X1XUF4xErp5P78+WUbKxP47DLcucRDig8Q7dmHELUdyNzo3E1SVoc7m+ 3CmvyTj6XuFQgOZw7ZKun1BJYfx/eD5ZlRJLZbx6wJHRtTXv/Uea8mZ8mJ31ykN9 F7QVd0Pmlyxys8lcXfK+nvpL09QBE0/PhwWKjmZBoU8AdgP/ZvBXLDL/D6YuMTg6 T4wwtPNJorfV4lVD06OliFkVI4qbKbmNsfRq43Ns7PCaLueu4U/eMaSwSH99UMaZ MGbO140XW2RZsHiU9yTRUmZq73AplePEjxtzR8oHmnjo45nPDPy8mucWPlkT9kXA oUFMhgiviK7dOo19H4eaPJGqLmHM93+x5tpYxGqTr0dUOXUadKWxMsTnkID+8Yi7 /kzQWCFvySz3VhiEHGuWkW08GZT6aCcpkREDomnRh4MEnETlZI8bblcuXYOCLs6c nNf1SIMtLdlsl7U1fEX89PNeQQ2y237vEDhFQZftaalPeu/JJV0= =Ftop -----END PGP SIGNATURE----- Merge tag 'libnvdimm-for-4.19_dax-memory-failure' of gitolite.kernel.org:pub/scm/linux/kernel/git/nvdimm/nvdimm Pull libnvdimm memory-failure update from Dave Jiang: "As it stands, memory_failure() gets thoroughly confused by dev_pagemap backed mappings. The recovery code has specific enabling for several possible page states and needs new enabling to handle poison in dax mappings. In order to support reliable reverse mapping of user space addresses: 1/ Add new locking in the memory_failure() rmap path to prevent races that would typically be handled by the page lock. 2/ Since dev_pagemap pages are hidden from the page allocator and the "compound page" accounting machinery, add a mechanism to determine the size of the mapping that encompasses a given poisoned pfn. 3/ Given pmem errors can be repaired, change the speculatively accessed poison protection, mce_unmap_kpfn(), to be reversible and otherwise allow ongoing access from the kernel. A side effect of this enabling is that MADV_HWPOISON becomes usable for dax mappings, however the primary motivation is to allow the system to survive userspace consumption of hardware-poison via dax. Specifically the current behavior is: mce: Uncorrected hardware memory error in user-access at af34214200 {1}[Hardware Error]: It has been corrected by h/w and requires no further action mce: [Hardware Error]: Machine check events logged {1}[Hardware Error]: event severity: corrected Memory failure: 0xaf34214: reserved kernel page still referenced by 1 users [..] Memory failure: 0xaf34214: recovery action for reserved kernel page: Failed mce: Memory error not recovered <reboot> ...and with these changes: Injecting memory failure for pfn 0x20cb00 at process virtual address 0x7f763dd00000 Memory failure: 0x20cb00: Killing dax-pmd:5421 due to hardware memory corruption Memory failure: 0x20cb00: recovery action for dax page: Recovered Given all the cross dependencies I propose taking this through nvdimm.git with acks from Naoya, x86/core, x86/RAS, and of course dax folks" * tag 'libnvdimm-for-4.19_dax-memory-failure' of gitolite.kernel.org:pub/scm/linux/kernel/git/nvdimm/nvdimm: libnvdimm, pmem: Restore page attributes when clearing errors x86/memory_failure: Introduce {set, clear}_mce_nospec() x86/mm/pat: Prepare {reserve, free}_memtype() for "decoy" addresses mm, memory_failure: Teach memory_failure() about dev_pagemap pages filesystem-dax: Introduce dax_lock_mapping_entry() mm, memory_failure: Collect mapping size in collect_procs() mm, madvise_inject_error: Let memory_failure() optionally take a page reference mm, dev_pagemap: Do not clear ->mapping on final put mm, madvise_inject_error: Disable MADV_SOFT_OFFLINE for ZONE_DEVICE pages filesystem-dax: Set page->index device-dax: Set page->index device-dax: Enable page_mapping() device-dax: Convert to vmf_insert_mixed and vm_fault_t
364 lines
10 KiB
C
364 lines
10 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _LINUX_HUGE_MM_H
|
|
#define _LINUX_HUGE_MM_H
|
|
|
|
#include <linux/sched/coredump.h>
|
|
#include <linux/mm_types.h>
|
|
|
|
#include <linux/fs.h> /* only for vma_is_dax() */
|
|
|
|
extern vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf);
|
|
extern int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
|
|
pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
|
|
struct vm_area_struct *vma);
|
|
extern void huge_pmd_set_accessed(struct vm_fault *vmf, pmd_t orig_pmd);
|
|
extern int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm,
|
|
pud_t *dst_pud, pud_t *src_pud, unsigned long addr,
|
|
struct vm_area_struct *vma);
|
|
|
|
#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
|
|
extern void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud);
|
|
#else
|
|
static inline void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud)
|
|
{
|
|
}
|
|
#endif
|
|
|
|
extern vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd);
|
|
extern struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
|
|
unsigned long addr,
|
|
pmd_t *pmd,
|
|
unsigned int flags);
|
|
extern bool madvise_free_huge_pmd(struct mmu_gather *tlb,
|
|
struct vm_area_struct *vma,
|
|
pmd_t *pmd, unsigned long addr, unsigned long next);
|
|
extern int zap_huge_pmd(struct mmu_gather *tlb,
|
|
struct vm_area_struct *vma,
|
|
pmd_t *pmd, unsigned long addr);
|
|
extern int zap_huge_pud(struct mmu_gather *tlb,
|
|
struct vm_area_struct *vma,
|
|
pud_t *pud, unsigned long addr);
|
|
extern int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
|
|
unsigned long addr, unsigned long end,
|
|
unsigned char *vec);
|
|
extern bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
|
|
unsigned long new_addr, unsigned long old_end,
|
|
pmd_t *old_pmd, pmd_t *new_pmd, bool *need_flush);
|
|
extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
|
|
unsigned long addr, pgprot_t newprot,
|
|
int prot_numa);
|
|
vm_fault_t vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
|
|
pmd_t *pmd, pfn_t pfn, bool write);
|
|
vm_fault_t vmf_insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
|
|
pud_t *pud, pfn_t pfn, bool write);
|
|
enum transparent_hugepage_flag {
|
|
TRANSPARENT_HUGEPAGE_FLAG,
|
|
TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
|
|
TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG,
|
|
TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG,
|
|
TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG,
|
|
TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG,
|
|
TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG,
|
|
TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG,
|
|
#ifdef CONFIG_DEBUG_VM
|
|
TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG,
|
|
#endif
|
|
};
|
|
|
|
struct kobject;
|
|
struct kobj_attribute;
|
|
|
|
extern ssize_t single_hugepage_flag_store(struct kobject *kobj,
|
|
struct kobj_attribute *attr,
|
|
const char *buf, size_t count,
|
|
enum transparent_hugepage_flag flag);
|
|
extern ssize_t single_hugepage_flag_show(struct kobject *kobj,
|
|
struct kobj_attribute *attr, char *buf,
|
|
enum transparent_hugepage_flag flag);
|
|
extern struct kobj_attribute shmem_enabled_attr;
|
|
|
|
#define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT)
|
|
#define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER)
|
|
|
|
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
|
|
#define HPAGE_PMD_SHIFT PMD_SHIFT
|
|
#define HPAGE_PMD_SIZE ((1UL) << HPAGE_PMD_SHIFT)
|
|
#define HPAGE_PMD_MASK (~(HPAGE_PMD_SIZE - 1))
|
|
|
|
#define HPAGE_PUD_SHIFT PUD_SHIFT
|
|
#define HPAGE_PUD_SIZE ((1UL) << HPAGE_PUD_SHIFT)
|
|
#define HPAGE_PUD_MASK (~(HPAGE_PUD_SIZE - 1))
|
|
|
|
extern bool is_vma_temporary_stack(struct vm_area_struct *vma);
|
|
|
|
extern unsigned long transparent_hugepage_flags;
|
|
|
|
static inline bool transparent_hugepage_enabled(struct vm_area_struct *vma)
|
|
{
|
|
if (vma->vm_flags & VM_NOHUGEPAGE)
|
|
return false;
|
|
|
|
if (is_vma_temporary_stack(vma))
|
|
return false;
|
|
|
|
if (test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags))
|
|
return false;
|
|
|
|
if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_FLAG))
|
|
return true;
|
|
|
|
if (vma_is_dax(vma))
|
|
return true;
|
|
|
|
if (transparent_hugepage_flags &
|
|
(1 << TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG))
|
|
return !!(vma->vm_flags & VM_HUGEPAGE);
|
|
|
|
return false;
|
|
}
|
|
|
|
#define transparent_hugepage_use_zero_page() \
|
|
(transparent_hugepage_flags & \
|
|
(1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG))
|
|
#ifdef CONFIG_DEBUG_VM
|
|
#define transparent_hugepage_debug_cow() \
|
|
(transparent_hugepage_flags & \
|
|
(1<<TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG))
|
|
#else /* CONFIG_DEBUG_VM */
|
|
#define transparent_hugepage_debug_cow() 0
|
|
#endif /* CONFIG_DEBUG_VM */
|
|
|
|
extern unsigned long thp_get_unmapped_area(struct file *filp,
|
|
unsigned long addr, unsigned long len, unsigned long pgoff,
|
|
unsigned long flags);
|
|
|
|
extern void prep_transhuge_page(struct page *page);
|
|
extern void free_transhuge_page(struct page *page);
|
|
|
|
bool can_split_huge_page(struct page *page, int *pextra_pins);
|
|
int split_huge_page_to_list(struct page *page, struct list_head *list);
|
|
static inline int split_huge_page(struct page *page)
|
|
{
|
|
return split_huge_page_to_list(page, NULL);
|
|
}
|
|
void deferred_split_huge_page(struct page *page);
|
|
|
|
void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
|
|
unsigned long address, bool freeze, struct page *page);
|
|
|
|
#define split_huge_pmd(__vma, __pmd, __address) \
|
|
do { \
|
|
pmd_t *____pmd = (__pmd); \
|
|
if (is_swap_pmd(*____pmd) || pmd_trans_huge(*____pmd) \
|
|
|| pmd_devmap(*____pmd)) \
|
|
__split_huge_pmd(__vma, __pmd, __address, \
|
|
false, NULL); \
|
|
} while (0)
|
|
|
|
|
|
void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address,
|
|
bool freeze, struct page *page);
|
|
|
|
void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud,
|
|
unsigned long address);
|
|
|
|
#define split_huge_pud(__vma, __pud, __address) \
|
|
do { \
|
|
pud_t *____pud = (__pud); \
|
|
if (pud_trans_huge(*____pud) \
|
|
|| pud_devmap(*____pud)) \
|
|
__split_huge_pud(__vma, __pud, __address); \
|
|
} while (0)
|
|
|
|
extern int hugepage_madvise(struct vm_area_struct *vma,
|
|
unsigned long *vm_flags, int advice);
|
|
extern void vma_adjust_trans_huge(struct vm_area_struct *vma,
|
|
unsigned long start,
|
|
unsigned long end,
|
|
long adjust_next);
|
|
extern spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd,
|
|
struct vm_area_struct *vma);
|
|
extern spinlock_t *__pud_trans_huge_lock(pud_t *pud,
|
|
struct vm_area_struct *vma);
|
|
|
|
static inline int is_swap_pmd(pmd_t pmd)
|
|
{
|
|
return !pmd_none(pmd) && !pmd_present(pmd);
|
|
}
|
|
|
|
/* mmap_sem must be held on entry */
|
|
static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd,
|
|
struct vm_area_struct *vma)
|
|
{
|
|
VM_BUG_ON_VMA(!rwsem_is_locked(&vma->vm_mm->mmap_sem), vma);
|
|
if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd))
|
|
return __pmd_trans_huge_lock(pmd, vma);
|
|
else
|
|
return NULL;
|
|
}
|
|
static inline spinlock_t *pud_trans_huge_lock(pud_t *pud,
|
|
struct vm_area_struct *vma)
|
|
{
|
|
VM_BUG_ON_VMA(!rwsem_is_locked(&vma->vm_mm->mmap_sem), vma);
|
|
if (pud_trans_huge(*pud) || pud_devmap(*pud))
|
|
return __pud_trans_huge_lock(pud, vma);
|
|
else
|
|
return NULL;
|
|
}
|
|
static inline int hpage_nr_pages(struct page *page)
|
|
{
|
|
if (unlikely(PageTransHuge(page)))
|
|
return HPAGE_PMD_NR;
|
|
return 1;
|
|
}
|
|
|
|
struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
|
|
pmd_t *pmd, int flags);
|
|
struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr,
|
|
pud_t *pud, int flags);
|
|
|
|
extern vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd);
|
|
|
|
extern struct page *huge_zero_page;
|
|
|
|
static inline bool is_huge_zero_page(struct page *page)
|
|
{
|
|
return READ_ONCE(huge_zero_page) == page;
|
|
}
|
|
|
|
static inline bool is_huge_zero_pmd(pmd_t pmd)
|
|
{
|
|
return is_huge_zero_page(pmd_page(pmd));
|
|
}
|
|
|
|
static inline bool is_huge_zero_pud(pud_t pud)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
struct page *mm_get_huge_zero_page(struct mm_struct *mm);
|
|
void mm_put_huge_zero_page(struct mm_struct *mm);
|
|
|
|
#define mk_huge_pmd(page, prot) pmd_mkhuge(mk_pmd(page, prot))
|
|
|
|
static inline bool thp_migration_supported(void)
|
|
{
|
|
return IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION);
|
|
}
|
|
|
|
#else /* CONFIG_TRANSPARENT_HUGEPAGE */
|
|
#define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; })
|
|
#define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; })
|
|
#define HPAGE_PMD_SIZE ({ BUILD_BUG(); 0; })
|
|
|
|
#define HPAGE_PUD_SHIFT ({ BUILD_BUG(); 0; })
|
|
#define HPAGE_PUD_MASK ({ BUILD_BUG(); 0; })
|
|
#define HPAGE_PUD_SIZE ({ BUILD_BUG(); 0; })
|
|
|
|
#define hpage_nr_pages(x) 1
|
|
|
|
static inline bool transparent_hugepage_enabled(struct vm_area_struct *vma)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
static inline void prep_transhuge_page(struct page *page) {}
|
|
|
|
#define transparent_hugepage_flags 0UL
|
|
|
|
#define thp_get_unmapped_area NULL
|
|
|
|
static inline bool
|
|
can_split_huge_page(struct page *page, int *pextra_pins)
|
|
{
|
|
BUILD_BUG();
|
|
return false;
|
|
}
|
|
static inline int
|
|
split_huge_page_to_list(struct page *page, struct list_head *list)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline int split_huge_page(struct page *page)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline void deferred_split_huge_page(struct page *page) {}
|
|
#define split_huge_pmd(__vma, __pmd, __address) \
|
|
do { } while (0)
|
|
|
|
static inline void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
|
|
unsigned long address, bool freeze, struct page *page) {}
|
|
static inline void split_huge_pmd_address(struct vm_area_struct *vma,
|
|
unsigned long address, bool freeze, struct page *page) {}
|
|
|
|
#define split_huge_pud(__vma, __pmd, __address) \
|
|
do { } while (0)
|
|
|
|
static inline int hugepage_madvise(struct vm_area_struct *vma,
|
|
unsigned long *vm_flags, int advice)
|
|
{
|
|
BUG();
|
|
return 0;
|
|
}
|
|
static inline void vma_adjust_trans_huge(struct vm_area_struct *vma,
|
|
unsigned long start,
|
|
unsigned long end,
|
|
long adjust_next)
|
|
{
|
|
}
|
|
static inline int is_swap_pmd(pmd_t pmd)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd,
|
|
struct vm_area_struct *vma)
|
|
{
|
|
return NULL;
|
|
}
|
|
static inline spinlock_t *pud_trans_huge_lock(pud_t *pud,
|
|
struct vm_area_struct *vma)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static inline vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf,
|
|
pmd_t orig_pmd)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline bool is_huge_zero_page(struct page *page)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
static inline bool is_huge_zero_pud(pud_t pud)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
static inline void mm_put_huge_zero_page(struct mm_struct *mm)
|
|
{
|
|
return;
|
|
}
|
|
|
|
static inline struct page *follow_devmap_pmd(struct vm_area_struct *vma,
|
|
unsigned long addr, pmd_t *pmd, int flags)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static inline struct page *follow_devmap_pud(struct vm_area_struct *vma,
|
|
unsigned long addr, pud_t *pud, int flags)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static inline bool thp_migration_supported(void)
|
|
{
|
|
return false;
|
|
}
|
|
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
|
|
|
|
#endif /* _LINUX_HUGE_MM_H */
|