Unverified Commit 70e304bd authored by openeuler-ci-bot's avatar openeuler-ci-bot Committed by Gitee
Browse files

!11569 support poison recover from migrate folio 

Merge Pull Request from: @ci-robot 
 
PR sync from: Tong Tiangen <tongtiangen@huawei.com>
https://mailweb.openeuler.org/hyperkitty/list/kernel@openeuler.org/message/ITJWBUI6R7RF44YE7RKZ4FUR5G4634CN/ 
The folio migration is widely used in kernel, memory compaction, memory
hotplug, soft offline page, numa balance, memory demote/promotion, etc,
but once access a poisoned source folio when migrating, the kernel will
panic.

There is a mechanism in the kernel to recover from uncorrectable memory
errors, ARCH_HAS_COPY_MC(eg, Machine Check Safe Memory Copy on x86), which
is already used in NVDIMM or core-mm paths(eg, CoW, khugepaged, coredump,
ksm copy), see copy_mc_to_{user,kernel}, copy_mc_{user_}highpage callers.

This series of patches provide the recovery mechanism from folio copy for
the widely used folio migration. Please note, because folio migration is
no guarantee of success, so we could chose to make folio migration tolerant
of memory failures, adding folio_mc_copy() which is a #MC versions of
folio_copy(), once accessing a poisoned source folio, we could return error
and make the folio migration fail, and this could avoid the similar panic
shown below.

   CPU: 1 PID: 88343 Comm: test_softofflin Kdump: loaded Not tainted 6.6.0
   pc : copy_page+0x10/0xc0
   lr : copy_highpage+0x38/0x50
   ...
   Call trace:
    copy_page+0x10/0xc0
    folio_copy+0x78/0x90
    migrate_folio_extra+0x54/0xa0
    move_to_new_folio+0xd8/0x1f0
    migrate_folio_move+0xb8/0x300
    migrate_pages_batch+0x528/0x788
    migrate_pages_sync+0x8c/0x258
    migrate_pages+0x440/0x528
    soft_offline_in_use_page+0x2ec/0x3c0
    soft_offline_page+0x238/0x310
    soft_offline_page_store+0x6c/0xc0
    dev_attr_store+0x20/0x40
    sysfs_kf_write+0x4c/0x68
    kernfs_fop_write_iter+0x130/0x1c8
    new_sync_write+0xa4/0x138
    vfs_write+0x238/0x2d8
    ksys_write+0x74/0x110

Kefeng Wang (8):
  mm: migrate: simplify __buffer_migrate_folio()
  mm: migrate_device: unify migrate folio for MIGRATE_SYNC_NO_COPY
  mm: migrate: remove migrate_folio_extra()
  mm: move memory_failure_queue() into copy_mc_[user]_highpage()
  mm: add folio_mc_copy()
  mm: migrate: split folio_migrate_mapping()
  mm: migrate: support poisoned recover from migrate folio
  fs: hugetlbfs: support poisoned recover from hugetlbfs_migrate_folio()


-- 
2.25.1
 
https://gitee.com/openeuler/kernel/issues/IAROKE 
 
Link:https://gitee.com/openeuler/kernel/pulls/11569

 

Reviewed-by: default avatarKefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: default avatarZhang Peng <zhangpeng362@huawei.com>
parents 7dff1425 374fe8ea

fs/hugetlbfs/inode.c

+1 −4
Original line number Diff line number Diff line
@@ -1156,9 +1156,6 @@ static int hugetlbfs_migrate_folio(struct address_space *mapping, 
		hugetlb_set_folio_subpool(src, NULL);

	}



	if (mode != MIGRATE_SYNC_NO_COPY)

		folio_migrate_copy(dst, src);

	else

	folio_migrate_flags(dst, src);



	return MIGRATEPAGE_SUCCESS;

include/linux/highmem.h

+6 −0
Original line number Diff line number Diff line
@@ -353,6 +353,9 @@ static inline int copy_mc_user_highpage(struct page *to, struct page *from, 
	kunmap_local(vto);

	kunmap_local(vfrom);



	if (ret)

		memory_failure_queue(page_to_pfn(from), 0);



	return ret ? -EFAULT : 0;

}

#endif
@@ -371,6 +374,9 @@ static inline int copy_mc_highpage(struct page *to, struct page *from) 
	kunmap_local(vto);

	kunmap_local(vfrom);



	if (ret)

		memory_failure_queue(page_to_pfn(from), 0);



	return ret ? -EFAULT : 0;

}

#endif

include/linux/migrate.h

+0 −2
Original line number Diff line number Diff line
@@ -63,8 +63,6 @@ extern const char *migrate_reason_names[MR_TYPES]; 
#ifdef CONFIG_MIGRATION



void putback_movable_pages(struct list_head *l);

int migrate_folio_extra(struct address_space *mapping, struct folio *dst,

		struct folio *src, enum migrate_mode mode, int extra_count);

int migrate_folio(struct address_space *mapping, struct folio *dst,

		struct folio *src, enum migrate_mode mode);

int migrate_pages(struct list_head *l, new_folio_t new, free_folio_t free,

include/linux/mm.h

+1 −0
Original line number Diff line number Diff line
@@ -1318,6 +1318,7 @@ void put_pages_list(struct list_head *pages); 


void split_page(struct page *page, unsigned int order);

void folio_copy(struct folio *dst, struct folio *src);

int folio_mc_copy(struct folio *dst, struct folio *src);



unsigned long nr_free_buffer_pages(void);

mm/ksm.c

+0 −1
Original line number Diff line number Diff line
@@ -2827,7 +2827,6 @@ struct folio *ksm_might_need_to_copy(struct folio *folio, 
		if (copy_mc_user_highpage(folio_page(new_folio, 0), page,

								addr, vma)) {

			folio_put(new_folio);

			memory_failure_queue(folio_pfn(folio), 0);

			return ERR_PTR(-EHWPOISON);

		}

		folio_set_dirty(new_folio);