From 7677d2a21d685810d75817aa89c668a956e06507 Mon Sep 17 00:00:00 2001
From: Michal Hocko <mhocko@suse.com>
Date: Wed, 7 Nov 2018 10:51:09 +0100
Subject: [PATCH 4/5] mm, memory_hotplug: print reason for the offlining
 failure
Git-commit: 7960509329c24a2bf0bc4929636614a1b7bb4443
Patch-mainline: v5.0-rc1
References: generic hotplug debugability

The memory offlining failure reporting is inconsistent and insufficient.
Some error paths simply do not report the failure to the log at all.
When we do report there are no details about the reason of the failure
and there are several of them which makes memory offlining failures
hard to debug.

Make sure that the
	memory offlining [mem %#010llx-%#010llx] failed
message is printed for all failures and also provide a short textual
reason for the failure e.g.

[ 1984.506184] rac1 kernel: memory offlining [mem 0x82600000000-0x8267fffffff] failed due to signal backoff

this tells us that the offlining has failed because of a signal pending
aka user intervention.

[akpm: tweak messages a bit]
Signed-off-by: Michal Hocko <mhocko@suse.com>

---
 mm/memory_hotplug.c |   41 +++++++++++++++++++++++++++--------------
 1 file changed, 27 insertions(+), 14 deletions(-)

--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1746,11 +1746,15 @@ static int __ref __offline_pages(unsigne
 	unsigned long valid_start, valid_end;
 	struct zone *zone;
 	struct memory_notify arg;
+	char *reason;
 
 	/* This makes hotplug much easier...and readable.
 	   we assume this for now. .*/
-	if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start, &valid_end))
-		return -EINVAL;
+	if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start, &valid_end)) {
+		ret = -EINVAL;
+		reason = "multizone range";
+		goto failed_removal;
+	}
 
 	zone = page_zone(pfn_to_page(valid_start));
 	node = zone_to_nid(zone);
@@ -1762,8 +1766,10 @@ static int __ref __offline_pages(unsigne
 	/* set above range as isolated */
 	ret = start_isolate_page_range(start_pfn, end_pfn,
 				       MIGRATE_MOVABLE, true);
-	if (ret)
-		return ret;
+	if (ret) {
+		reason = "failure to isolate range";
+		goto failed_removal;
+	}
 
 	arg.start_pfn = start_pfn;
 	arg.nr_pages = nr_pages;
@@ -1771,15 +1777,19 @@ static int __ref __offline_pages(unsigne
 
 	ret = memory_notify(MEM_GOING_OFFLINE, &arg);
 	ret = notifier_to_errno(ret);
-	if (ret)
-		goto failed_removal;
+	if (ret) {
+		reason = "notifier failure";
+		goto failed_removal_isolated;
+	}
 
 	pfn = start_pfn;
 repeat:
 	/* start memory hot removal */
 	ret = -EINTR;
-	if (signal_pending(current))
-		goto failed_removal;
+	if (signal_pending(current)) {
+		reason = "signal backoff";
+		goto failed_removal_isolated;
+	}
 	ret = 0;
 
 	cond_resched();
@@ -1797,8 +1807,10 @@ repeat:
 	 * actually in order to make hugetlbfs's object counting consistent.
 	 */
 	ret = dissolve_free_huge_pages(start_pfn, end_pfn);
-	if (ret)
-		goto failed_removal;
+	if (ret) {
+		reason = "failure to dissolve huge pages";
+		goto failed_removal_isolated;
+	}
 	/* check again */
 	offlined_pages = check_pages_isolated(start_pfn, end_pfn);
 	if (offlined_pages < 0)
@@ -1839,13 +1851,14 @@ repeat:
 	memory_notify(MEM_OFFLINE, &arg);
 	return 0;
 
+failed_removal_isolated:
+	undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE);
 failed_removal:
-	pr_debug("memory offlining [mem %#010llx-%#010llx] failed\n",
+	pr_debug("memory offlining [mem %#010llx-%#010llx] failed due to %s\n",
 		 (unsigned long long) start_pfn << PAGE_SHIFT,
-		 ((unsigned long long) end_pfn << PAGE_SHIFT) - 1);
+		 ((unsigned long long) end_pfn << PAGE_SHIFT) - 1,
+		 reason);
 	memory_notify(MEM_CANCEL_OFFLINE, &arg);
-	/* pushback to free area */
-	undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE);
 	return ret;
 }