mm/hwpoison: avoid the impact of hwpoison_filter() return value on mce handler

When the hwpoison page meets the filter conditions, it should not be
regarded as successful memory_failure() processing for mce handler, but
should return a distinct value, otherwise mce handler regards the error
page has been identified and isolated, which may lead to calling
set_mce_nospec() to change page attribute, etc.

Here memory_failure() return -EOPNOTSUPP to indicate that the error
event is filtered, mce handler should not take any action for this
situation and hwpoison injector should treat as correct.

Link: https://lkml.kernel.org/r/20220223082135.2769649-1-luofei@unicloud.com
Signed-off-by: luofei <luofei@unicloud.com>
Acked-by: Borislav Petkov <bp@suse.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tony Luck <tony.luck@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

arch/x86/kernel/cpu/mce/core.c

@@ -1304,10 +1304,12 @@ static void kill_me_maybe(struct callback_head *cb)
 
 	/*
 	 * -EHWPOISON from memory_failure() means that it already sent SIGBUS
-	 * to the current process with the proper error info, so no need to
-	 * send SIGBUS here again.
+	 * to the current process with the proper error info,
+	 * -EOPNOTSUPP means hwpoison_filter() filtered the error event,
+	 *
+	 * In both cases, no further processing is required.
 	 */
-	if (ret == -EHWPOISON)
+	if (ret == -EHWPOISON || ret == -EOPNOTSUPP)
 		return;
 
 	pr_err("Memory error not recovered");

drivers/base/memory.c

@@ -555,6 +555,8 @@ static ssize_t hard_offline_page_store(struct device *dev,
 		return -EINVAL;
 	pfn >>= PAGE_SHIFT;
 	ret = memory_failure(pfn, 0);
+	if (ret == -EOPNOTSUPP)
+		ret = 0;
 	return ret ? ret : count;
 }
 

mm/hwpoison-inject.c

@@ -48,7 +48,8 @@ static int hwpoison_inject(void *data, u64 val)
 
 inject:
 	pr_info("Injecting memory failure at pfn %#lx\n", pfn);
-	return memory_failure(pfn, 0);
+	err = memory_failure(pfn, 0);
+	return (err == -EOPNOTSUPP) ? 0 : err;
 }
 
 static int hwpoison_unpoison(void *data, u64 val)

mm/madvise.c

@@ -1067,6 +1067,8 @@ static int madvise_inject_error(int behavior,
 			pr_info("Injecting memory failure for pfn %#lx at process virtual address %#lx\n",
 				 pfn, start);
 			ret = memory_failure(pfn, MF_COUNT_INCREASED);
+			if (ret == -EOPNOTSUPP)
+				ret = 0;
 		}
 
 		if (ret)

mm/memory-failure.c

@@ -1515,7 +1515,7 @@ static int memory_failure_hugetlb(unsigned long pfn, int flags)
 				if (TestClearPageHWPoison(head))
 					num_poisoned_pages_dec();
 				unlock_page(head);
-				return 0;
+				return -EOPNOTSUPP;
 			}
 			unlock_page(head);
 			res = MF_FAILED;
@@ -1602,7 +1602,7 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags,
 		goto out;
 
 	if (hwpoison_filter(page)) {
-		rc = 0;
+		rc = -EOPNOTSUPP;
 		goto unlock;
 	}
 
@@ -1671,6 +1671,10 @@ static DEFINE_MUTEX(mf_mutex);
  *
  * Must run in process context (e.g. a work queue) with interrupts
  * enabled and no spinlocks hold.
+ *
+ * Return: 0 for successfully handled the memory error,
+ *         -EOPNOTSUPP for memory_filter() filtered the error event,
+ *         < 0(except -EOPNOTSUPP) on failure.
  */
 int memory_failure(unsigned long pfn, int flags)
 {
@@ -1836,6 +1840,7 @@ int memory_failure(unsigned long pfn, int flags)
 			num_poisoned_pages_dec();
 		unlock_page(p);
 		put_page(p);
+		res = -EOPNOTSUPP;
 		goto unlock_mutex;
 	}