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>

1 files changed, 38 insertions, 0 deletions

diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 9aa0da991cfb..fe98fb8d94e5 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -175,6 +175,15 @@ int memory_notify(unsigned long val, void *v)
 	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);
@@ -183,6 +192,9 @@ static int memory_block_online(struct memory_block *mem)
 	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);
 
@@ -864,6 +876,7 @@ void remove_memory_block_devices(unsigned long start, unsigned long size)
 		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);
 	}
@@ -1164,3 +1177,28 @@ int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func,
 	}
 	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