[PATCH v1 1/6] mm/hwpoison: mf_mutex for soft offline and unpoison

[Naoya Horiguchi]

From: Naoya Horiguchi <naoya.horiguchi@xxxxxxx>

Originally mf_mutex is introduced to serialize multiple MCE events, but
it's also helpful to exclude races among  soft_offline_page() and
unpoison_memory().  So apply mf_mutex to them.

Signed-off-by: Naoya Horiguchi <naoya.horiguchi@xxxxxxx>
---
 mm/memory-failure.c | 26 ++++++++++++++++++--------
 1 file changed, 18 insertions(+), 8 deletions(-)

diff --git v5.13-rc5/mm/memory-failure.c v5.13-rc5_patched/mm/memory-failure.c
index ae30fd6d575a..280eb6d6dd15 100644
--- v5.13-rc5/mm/memory-failure.c
+++ v5.13-rc5_patched/mm/memory-failure.c
@@ -1583,6 +1583,8 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags,
 	return rc;
 }
 
+static DEFINE_MUTEX(mf_mutex);
+
 /**
  * memory_failure - Handle memory failure of a page.
  * @pfn: Page Number of the corrupted page
@@ -1609,7 +1611,6 @@ int memory_failure(unsigned long pfn, int flags)
 	int res = 0;
 	unsigned long page_flags;
 	bool retry = true;
-	static DEFINE_MUTEX(mf_mutex);
 
 	if (!sysctl_memory_failure_recovery)
 		panic("Memory failure on page %lx", pfn);
@@ -1918,6 +1919,7 @@ int unpoison_memory(unsigned long pfn)
 	struct page *page;
 	struct page *p;
 	int freeit = 0;
+	int ret = 0;
 	unsigned long flags = 0;
 	static DEFINE_RATELIMIT_STATE(unpoison_rs, DEFAULT_RATELIMIT_INTERVAL,
 					DEFAULT_RATELIMIT_BURST);
@@ -1928,28 +1930,30 @@ int unpoison_memory(unsigned long pfn)
 	p = pfn_to_page(pfn);
 	page = compound_head(p);
 
+	mutex_lock(&mf_mutex);
+
 	if (!PageHWPoison(p)) {
 		unpoison_pr_info("Unpoison: Page was already unpoisoned %#lx\n",
 				 pfn, &unpoison_rs);
-		return 0;
+		goto unlock_mutex;
 	}
 
 	if (page_count(page) > 1) {
 		unpoison_pr_info("Unpoison: Someone grabs the hwpoison page %#lx\n",
 				 pfn, &unpoison_rs);
-		return 0;
+		goto unlock_mutex;
 	}
 
 	if (page_mapped(page)) {
 		unpoison_pr_info("Unpoison: Someone maps the hwpoison page %#lx\n",
 				 pfn, &unpoison_rs);
-		return 0;
+		goto unlock_mutex;
 	}
 
 	if (page_mapping(page)) {
 		unpoison_pr_info("Unpoison: the hwpoison page has non-NULL mapping %#lx\n",
 				 pfn, &unpoison_rs);
-		return 0;
+		goto unlock_mutex;
 	}
 
 	/*
@@ -1960,7 +1964,7 @@ int unpoison_memory(unsigned long pfn)
 	if (!PageHuge(page) && PageTransHuge(page)) {
 		unpoison_pr_info("Unpoison: Memory failure is now running on %#lx\n",
 				 pfn, &unpoison_rs);
-		return 0;
+		goto unlock_mutex;
 	}
 
 	if (!get_hwpoison_page(p, flags)) {
@@ -1968,7 +1972,7 @@ int unpoison_memory(unsigned long pfn)
 			num_poisoned_pages_dec();
 		unpoison_pr_info("Unpoison: Software-unpoisoned free page %#lx\n",
 				 pfn, &unpoison_rs);
-		return 0;
+		goto unlock_mutex;
 	}
 
 	lock_page(page);
@@ -1990,7 +1994,9 @@ int unpoison_memory(unsigned long pfn)
 	if (freeit && !(pfn == my_zero_pfn(0) && page_count(p) == 1))
 		put_page(page);
 
-	return 0;
+unlock_mutex:
+	mutex_unlock(&mf_mutex);
+	return ret;
 }
 EXPORT_SYMBOL(unpoison_memory);
 
@@ -2171,6 +2177,8 @@ int soft_offline_page(unsigned long pfn, int flags)
 		return -EIO;
 	}
 
+	mutex_lock(&mf_mutex);
+
 	if (PageHWPoison(page)) {
 		pr_info("%s: %#lx page already poisoned\n", __func__, pfn);
 		put_ref_page(ref_page);
@@ -2194,5 +2202,7 @@ int soft_offline_page(unsigned long pfn, int flags)
 			 __func__, pfn, page->flags, &page->flags);
 	}
 
+	mutex_unlock(&mf_mutex);
+
 	return ret;
 }
-- 
2.25.1