From 7960509329c24a2bf0bc4929636614a1b7bb4443 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 28 Dec 2018 00:33:49 -0800 Subject: [PATCH] mm, memory_hotplug: print reason for the offlining failure 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@linux-foundation.org: tweak messages a bit] Link: http://lkml.kernel.org/r/20181107101830.17405-5-mhocko@kernel.org Signed-off-by: Michal Hocko Reviewed-by: Andrew Morton Reviewed-by: Oscar Salvador Reviewed-by: Anshuman Khandual Cc: Baoquan He Cc: Oscar Salvador Cc: William Kucharski Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 34 +++++++++++++++++++++++----------- 1 file changed, 23 insertions(+), 11 deletions(-) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index a92b1b8f6218..88d50e74e3fe 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1553,6 +1553,7 @@ static int __ref __offline_pages(unsigned long start_pfn, unsigned long valid_start, valid_end; struct zone *zone; struct memory_notify arg; + char *reason; mem_hotplug_begin(); @@ -1561,7 +1562,9 @@ static int __ref __offline_pages(unsigned long start_pfn, if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start, &valid_end)) { mem_hotplug_done(); - return -EINVAL; + ret = -EINVAL; + reason = "multizone range"; + goto failed_removal; } zone = page_zone(pfn_to_page(valid_start)); @@ -1573,7 +1576,8 @@ static int __ref __offline_pages(unsigned long start_pfn, MIGRATE_MOVABLE, true); if (ret) { mem_hotplug_done(); - return ret; + reason = "failure to isolate range"; + goto failed_removal; } arg.start_pfn = start_pfn; @@ -1582,15 +1586,19 @@ static int __ref __offline_pages(unsigned long start_pfn, 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; + } cond_resched(); lru_add_drain_all(); @@ -1607,8 +1615,10 @@ 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) @@ -1648,13 +1658,15 @@ repeat: mem_hotplug_done(); 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); mem_hotplug_done(); return ret; }