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>
return blocking_notifier_call_chain(&memory_chain, val, v);
}
+#if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG)
+static unsigned long memblk_nr_poison(struct memory_block *mem);
+#else
+static inline unsigned long memblk_nr_poison(struct memory_block *mem)
+{
+ return 0;
+}
+#endif
+
static int memory_block_online(struct memory_block *mem)
{
unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr);
struct zone *zone;
int ret;
+ if (memblk_nr_poison(mem))
+ return -EHWPOISON;
+
zone = zone_for_pfn_range(mem->online_type, mem->nid, mem->group,
start_pfn, nr_pages);
mem = find_memory_block_by_id(block_id);
if (WARN_ON_ONCE(!mem))
continue;
+ num_poisoned_pages_sub(-1UL, memblk_nr_poison(mem));
unregister_memory_block_under_nodes(mem);
remove_memory_block(mem);
}
}
return ret;
}
+
+#if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG)
+void memblk_nr_poison_inc(unsigned long pfn)
+{
+ const unsigned long block_id = pfn_to_block_id(pfn);
+ struct memory_block *mem = find_memory_block_by_id(block_id);
+
+ if (mem)
+ atomic_long_inc(&mem->nr_hwpoison);
+}
+
+void memblk_nr_poison_sub(unsigned long pfn, long i)
+{
+ const unsigned long block_id = pfn_to_block_id(pfn);
+ struct memory_block *mem = find_memory_block_by_id(block_id);
+
+ if (mem)
+ atomic_long_sub(i, &mem->nr_hwpoison);
+}
+
+static unsigned long memblk_nr_poison(struct memory_block *mem)
+{
+ return atomic_long_read(&mem->nr_hwpoison);
+}
+#endif
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);
#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)
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
extern u64 hwpoison_filter_memcg;
extern u32 hwpoison_filter_enable;
-#ifdef CONFIG_MEMORY_FAILURE
-void clear_hwpoisoned_pages(struct page *memmap, int nr_pages);
-#else
-static inline void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
-{
-}
-#endif
-
extern unsigned long __must_check vm_mmap_pgoff(struct file *, unsigned long,
unsigned long, unsigned long,
unsigned long, unsigned long);
inline void num_poisoned_pages_inc(unsigned long pfn)
{
atomic_long_inc(&num_poisoned_pages);
+ memblk_nr_poison_inc(pfn);
}
-static inline void num_poisoned_pages_sub(unsigned long pfn, long i)
+inline void num_poisoned_pages_sub(unsigned long pfn, long i)
{
atomic_long_sub(i, &num_poisoned_pages);
+ if (pfn != -1UL)
+ memblk_nr_poison_sub(pfn, i);
}
/*
if (move_flag)
SetPageHWPoison(p->page);
+ else
+ num_poisoned_pages_sub(page_to_pfn(p->page), 1);
kfree(p);
count++;
}
int ret = -EBUSY;
int freeit = 0;
unsigned long count = 1;
+ bool huge = false;
static DEFINE_RATELIMIT_STATE(unpoison_rs, DEFAULT_RATELIMIT_INTERVAL,
DEFAULT_RATELIMIT_BURST);
ret = get_hwpoison_page(p, MF_UNPOISON);
if (!ret) {
if (PageHuge(p)) {
+ huge = true;
count = free_raw_hwp_pages(page, false);
if (count == 0) {
ret = -EBUSY;
pfn, &unpoison_rs);
} else {
if (PageHuge(p)) {
+ huge = true;
count = free_raw_hwp_pages(page, false);
if (count == 0) {
ret = -EBUSY;
unlock_mutex:
mutex_unlock(&mf_mutex);
if (!ret || freeit) {
- num_poisoned_pages_sub(pfn, count);
+ if (!huge)
+ num_poisoned_pages_sub(pfn, 1);
unpoison_pr_info("Unpoison: Software-unpoisoned page %#lx\n",
page_to_pfn(p), &unpoison_rs);
}
return ret;
}
-
-void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
-{
- int i, total = 0;
-
- /*
- * A further optimization is to have per section refcounted
- * num_poisoned_pages. But that would need more space per memmap, so
- * for now just do a quick global check to speed up this routine in the
- * absence of bad pages.
- */
- if (atomic_long_read(&num_poisoned_pages) == 0)
- return;
-
- for (i = 0; i < nr_pages; i++) {
- if (PageHWPoison(&memmap[i])) {
- total++;
- ClearPageHWPoison(&memmap[i]);
- }
- }
- if (total)
- num_poisoned_pages_sub(0, total);
-}
unsigned long nr_pages, unsigned long map_offset,
struct vmem_altmap *altmap)
{
- clear_hwpoisoned_pages(pfn_to_page(pfn) + map_offset,
- nr_pages - map_offset);
section_deactivate(pfn, nr_pages, altmap);
}
#endif /* CONFIG_MEMORY_HOTPLUG */