Patch series "mm, hwpoison: improve handling workload related to hugetlb
and memory_hotplug", v7.
This patchset tries to solve the issue among memory_hotplug, hugetlb and hwpoison.
In this patchset, memory hotplug handles hwpoison pages like below:
- hwpoison pages should not prevent memory hotremove,
- memory block with hwpoison pages should not be onlined.
This patch (of 4):
HWPoisoned page is not supposed to be accessed once marked, but currently
such accesses can happen during memory hotremove because
do_migrate_range() can be called before dissolve_free_huge_pages() is
called.
Clear HPageMigratable for hwpoisoned hugepages to prevent them from being
migrated. This should be done in hugetlb_lock to avoid race against
isolate_hugetlb().
get_hwpoison_huge_page() needs to have a flag to show it's called from
unpoison to take refcount of hwpoisoned hugepages, so add it.
[naoya.horiguchi@linux.dev: remove TestClearHPageMigratable and reduce to test and clear separately]
Link: https://lkml.kernel.org/r/20221025053559.GA2104800@ik1-406-35019.vs.sakura.ne.jp
Link: https://lkml.kernel.org/r/20221024062012.1520887-1-naoya.horiguchi@linux.dev
Link: https://lkml.kernel.org/r/20221024062012.1520887-2-naoya.horiguchi@linux.dev
Signed-off-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Reported-by: Miaohe Lin <linmiaohe@huawei.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
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: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
long hugetlb_unreserve_pages(struct inode *inode, long start, long end,
long freed);
int isolate_hugetlb(struct page *page, struct list_head *list);
-int get_hwpoison_huge_page(struct page *page, bool *hugetlb);
-int get_huge_page_for_hwpoison(unsigned long pfn, int flags);
+int get_hwpoison_huge_page(struct page *page, bool *hugetlb, bool unpoison);
+int get_huge_page_for_hwpoison(unsigned long pfn, int flags,
+ bool *migratable_cleared);
void putback_active_hugepage(struct page *page);
void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason);
void free_huge_page(struct page *page);
return -EBUSY;
}
-static inline int get_hwpoison_huge_page(struct page *page, bool *hugetlb)
+static inline int get_hwpoison_huge_page(struct page *page, bool *hugetlb, bool unpoison)
{
return 0;
}
-static inline int get_huge_page_for_hwpoison(unsigned long pfn, int flags)
+static inline int get_huge_page_for_hwpoison(unsigned long pfn, int flags,
+ bool *migratable_cleared)
{
return 0;
}
extern atomic_long_t num_poisoned_pages __read_mostly;
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);
+extern int __get_huge_page_for_hwpoison(unsigned long pfn, int flags,
+ bool *migratable_cleared);
#else
-static inline int __get_huge_page_for_hwpoison(unsigned long pfn, int flags)
+static inline int __get_huge_page_for_hwpoison(unsigned long pfn, int flags,
+ bool *migratable_cleared)
{
return 0;
}
return ret;
}
-int get_hwpoison_huge_page(struct page *page, bool *hugetlb)
+int get_hwpoison_huge_page(struct page *page, bool *hugetlb, bool unpoison)
{
int ret = 0;
*hugetlb = true;
if (HPageFreed(page))
ret = 0;
- else if (HPageMigratable(page))
+ else if (HPageMigratable(page) || unpoison)
ret = get_page_unless_zero(page);
else
ret = -EBUSY;
return ret;
}
-int get_huge_page_for_hwpoison(unsigned long pfn, int flags)
+int get_huge_page_for_hwpoison(unsigned long pfn, int flags,
+ bool *migratable_cleared)
{
int ret;
spin_lock_irq(&hugetlb_lock);
- ret = __get_huge_page_for_hwpoison(pfn, flags);
+ ret = __get_huge_page_for_hwpoison(pfn, flags, migratable_cleared);
spin_unlock_irq(&hugetlb_lock);
return ret;
}
int ret = 0;
bool hugetlb = false;
- ret = get_hwpoison_huge_page(head, &hugetlb);
+ ret = get_hwpoison_huge_page(head, &hugetlb, false);
if (hugetlb)
return ret;
int ret = 0;
bool hugetlb = false;
- ret = get_hwpoison_huge_page(head, &hugetlb);
+ ret = get_hwpoison_huge_page(head, &hugetlb, true);
if (hugetlb)
return ret;
* -EBUSY - the hugepage is busy (try to retry)
* -EHWPOISON - the hugepage is already hwpoisoned
*/
-int __get_huge_page_for_hwpoison(unsigned long pfn, int flags)
+int __get_huge_page_for_hwpoison(unsigned long pfn, int flags,
+ bool *migratable_cleared)
{
struct page *page = pfn_to_page(pfn);
struct page *head = compound_head(page);
goto out;
}
+ /*
+ * Clearing HPageMigratable for hwpoisoned hugepages to prevent them
+ * from being migrated by memory hotremove.
+ */
+ if (count_increased && HPageMigratable(head)) {
+ ClearHPageMigratable(head);
+ *migratable_cleared = true;
+ }
+
return ret;
out:
if (count_increased)
struct page *p = pfn_to_page(pfn);
struct page *head;
unsigned long page_flags;
+ bool migratable_cleared = false;
*hugetlb = 1;
retry:
- res = get_huge_page_for_hwpoison(pfn, flags);
+ res = get_huge_page_for_hwpoison(pfn, flags, &migratable_cleared);
if (res == 2) { /* fallback to normal page handling */
*hugetlb = 0;
return 0;
if (hwpoison_filter(p)) {
hugetlb_clear_page_hwpoison(head);
+ if (migratable_cleared)
+ SetHPageMigratable(head);
unlock_page(head);
if (res == 1)
put_page(head);