diff options
| author | Naoya Horiguchi <naoya.horiguchi@nec.com> | 2022-10-24 09:20:12 +0300 |
|---|---|---|
| committer | Andrew Morton <akpm@linux-foundation.org> | 2022-11-09 04:37:22 +0300 |
| commit | 5033091de814ab4b5623faed2755f3064e19e2d2 (patch) | |
| tree | 7edde57024f06ca1015a0cc59e0173d848d04ade /include | |
| parent | a46c9304b4bbf1b164154976cbb7e648980c7b5b (diff) | |
| download | linux-5033091de814ab4b5623faed2755f3064e19e2d2.tar.xz | |
mm/hwpoison: introduce per-memory_block hwpoison counter
Currently PageHWPoison flag does not behave well when experiencing memory
hotremove/hotplug. Any data field in struct page is unreliable when the
associated memory is offlined, and the current mechanism can't tell
whether a memory block is onlined because a new memory devices is
installed or because previous failed offline operations are undone.
Especially if there's a hwpoisoned memory, it's unclear what the best
option is.
So introduce a new mechanism to make struct memory_block remember that a
memory block has hwpoisoned memory inside it. And make any online event
fail if the onlining memory block contains hwpoison. struct memory_block
is freed and reallocated over ACPI-based hotremove/hotplug, but not over
sysfs-based hotremove/hotplug. So the new counter can distinguish these
cases.
Link: https://lkml.kernel.org/r/20221024062012.1520887-5-naoya.horiguchi@linux.dev
Signed-off-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Reported-by: kernel test robot <lkp@intel.com>
Reviewed-by: Miaohe Lin <linmiaohe@huawei.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Jane Chu <jane.chu@oracle.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Diffstat (limited to 'include')
| -rw-r--r-- | include/linux/memory.h | 3 | ||||
| -rw-r--r-- | include/linux/mm.h | 20 |
2 files changed, 22 insertions, 1 deletions
diff --git a/include/linux/memory.h b/include/linux/memory.h index 463662ef7614..31343566c221 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -84,6 +84,9 @@ struct memory_block { unsigned long nr_vmemmap_pages; struct memory_group *group; /* group (if any) for this block */ struct list_head group_next; /* next block inside memory group */ +#if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG) + atomic_long_t nr_hwpoison; +#endif }; int arch_get_memory_phys_device(unsigned long start_pfn); diff --git a/include/linux/mm.h b/include/linux/mm.h index 78ae2ee09a24..429ff89bfe06 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3279,7 +3279,8 @@ extern int soft_offline_page(unsigned long pfn, int flags); #ifdef CONFIG_MEMORY_FAILURE extern int __get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared); -extern void num_poisoned_pages_inc(unsigned long pfn); +void num_poisoned_pages_inc(unsigned long pfn); +void num_poisoned_pages_sub(unsigned long pfn, long i); #else static inline int __get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared) @@ -3290,6 +3291,23 @@ static inline int __get_huge_page_for_hwpoison(unsigned long pfn, int flags, static inline void num_poisoned_pages_inc(unsigned long pfn) { } + +static inline void num_poisoned_pages_sub(unsigned long pfn, long i) +{ +} +#endif + +#if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG) +extern void memblk_nr_poison_inc(unsigned long pfn); +extern void memblk_nr_poison_sub(unsigned long pfn, long i); +#else +static inline void memblk_nr_poison_inc(unsigned long pfn) +{ +} + +static inline void memblk_nr_poison_sub(unsigned long pfn, long i) +{ +} #endif #ifndef arch_memory_failure |