A kernel that inherits a record of hardware-poisoned frames from an
earlier kernel needs a way to apply it. memory_failure() does not fit: it
takes mf_mutex, prints a line per frame, and a 2M unit is 512 of them.

Add hwpoison_boot_pfn(). A frame that is free takes the same route
memory_failure() takes for a free page: take_page_off_buddy(), the flag,
the refcount and the counter. A frame the kernel is already sitting on is
only flagged, since it cannot be taken away from whoever reserved it.
free_pages_prepare() drops such a frame if it is ever handed back, so it
does not reach the allocator either way.

The accounting cannot go through num_poisoned_pages_inc(). Its per memory
block half divides by sections_per_block, which memory_dev_init() only
sets up from driver_init(), so where this runs it is still zero and the
boot dies on a divide by zero. Bump the global counter directly; the block
counters stay short by these frames.

Signed-off-by: Breno Leitao <leitao@debian.org>
---
 include/linux/mm.h  |  1 +
 mm/memory-failure.c | 24 ++++++++++++++++++++++++
 2 files changed, 25 insertions(+)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 32bb723ffbb92..52a00a0e090c7 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -5104,6 +5104,7 @@ extern const struct attribute_group memory_failure_attr_group;
 extern void memory_failure_queue(unsigned long pfn, int flags);
 void num_poisoned_pages_inc(unsigned long pfn);
 void num_poisoned_pages_sub(unsigned long pfn, long i);
+bool __init hwpoison_boot_pfn(unsigned long pfn);
 #else
 static inline void memory_failure_queue(unsigned long pfn, int flags)
 {
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 357a72ffda625..713fb2f8e0332 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -97,6 +97,30 @@ void num_poisoned_pages_sub(unsigned long pfn, long i)
 		memblk_nr_poison_sub(pfn, i);
 }
 
+static void update_per_node_mf_stats(unsigned long pfn, enum mf_result result);
+
+bool __init hwpoison_boot_pfn(unsigned long pfn)
+{
+	struct page *page = pfn_to_online_page(pfn);
+
+	if (!page || PageHWPoison(page))
+		return false;
+
+	if (is_free_buddy_page(page)) {
+		if (!take_page_off_buddy(page))
+			return false;
+		page_ref_inc(page);
+	} else if (!PageReserved(page)) {
+		return false;
+	}
+
+	SetPageHWPoison(page);
+	update_per_node_mf_stats(pfn, MF_RECOVERED);
+	atomic_long_inc(&num_poisoned_pages);
+
+	return true;
+}
+
 /**
  * MF_ATTR_RO - Create sysfs entry for each memory failure statistics.
  * @_name: name of the file in the per NUMA sysfs directory.

-- 
2.53.0-Meta