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>

3 files changed, 11 insertions, 35 deletions

diff --git a/mm/internal.h b/mm/internal.h
index 68afdbe7106e..bcf75a8b032d 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -708,14 +708,6 @@ extern u64 hwpoison_filter_flags_value;
 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);
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 757a46e172de..9b82402ec242 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -77,11 +77,14 @@ static bool hw_memory_failure __read_mostly = false;
 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);
 }
 
 /*
@@ -1706,6 +1709,8 @@ static unsigned long __free_raw_hwp_pages(struct page *hpage, bool move_flag)
 
 		if (move_flag)
 			SetPageHWPoison(p->page);
+		else
+			num_poisoned_pages_sub(page_to_pfn(p->page), 1);
 		kfree(p);
 		count++;
 	}
@@ -2332,6 +2337,7 @@ int unpoison_memory(unsigned long pfn)
 	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);
 
@@ -2380,6 +2386,7 @@ int unpoison_memory(unsigned long pfn)
 	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;
@@ -2395,6 +2402,7 @@ int unpoison_memory(unsigned long pfn)
 					 pfn, &unpoison_rs);
 	} else {
 		if (PageHuge(p)) {
+			huge = true;
 			count = free_raw_hwp_pages(page, false);
 			if (count == 0) {
 				ret = -EBUSY;
@@ -2414,7 +2422,8 @@ int unpoison_memory(unsigned long pfn)
 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);
 	}
@@ -2609,26 +2618,3 @@ retry:
 
 	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);
-}
diff --git a/mm/sparse.c b/mm/sparse.c
index e5a8a3a0edd7..2779b419ef2a 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -926,8 +926,6 @@ void sparse_remove_section(struct mem_section *ms, unsigned long pfn,
 		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 */