From 381eab4a6ee81266f8dddc62e57376c7e584e5b8 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 30 Oct 2018 15:10:29 -0700 Subject: mm/memory_hotplug: fix online/offline_pages called w.o. mem_hotplug_lock There seem to be some problems as result of 30467e0b3be ("mm, hotplug: fix concurrent memory hot-add deadlock"), which tried to fix a possible lock inversion reported and discussed in [1] due to the two locks a) device_lock() b) mem_hotplug_lock While add_memory() first takes b), followed by a) during bus_probe_device(), onlining of memory from user space first took a), followed by b), exposing a possible deadlock. In [1], and it was decided to not make use of device_hotplug_lock, but rather to enforce a locking order. The problems I spotted related to this: 1. Memory block device attributes: While .state first calls mem_hotplug_begin() and the calls device_online() - which takes device_lock() - .online does no longer call mem_hotplug_begin(), so effectively calls online_pages() without mem_hotplug_lock. 2. device_online() should be called under device_hotplug_lock, however onlining memory during add_memory() does not take care of that. In addition, I think there is also something wrong about the locking in 3. arch/powerpc/platforms/powernv/memtrace.c calls offline_pages() without locks. This was introduced after 30467e0b3be. And skimming over the code, I assume it could need some more care in regards to locking (e.g. device_online() called without device_hotplug_lock. This will be addressed in the following patches. Now that we hold the device_hotplug_lock when - adding memory (e.g. via add_memory()/add_memory_resource()) - removing memory (e.g. via remove_memory()) - device_online()/device_offline() We can move mem_hotplug_lock usage back into online_pages()/offline_pages(). Why is mem_hotplug_lock still needed? Essentially to make get_online_mems()/put_online_mems() be very fast (relying on device_hotplug_lock would be very slow), and to serialize against addition of memory that does not create memory block devices (hmm). [1] http://driverdev.linuxdriverproject.org/pipermail/ driverdev-devel/ 2015-February/065324.html This patch is partly based on a patch by Vitaly Kuznetsov. Link: http://lkml.kernel.org/r/20180925091457.28651-4-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Pavel Tatashin Reviewed-by: Rashmica Gupta Reviewed-by: Oscar Salvador Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: "Rafael J. Wysocki" Cc: Len Brown Cc: Greg Kroah-Hartman Cc: "K. Y. Srinivasan" Cc: Haiyang Zhang Cc: Stephen Hemminger Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: Boris Ostrovsky Cc: Juergen Gross Cc: Rashmica Gupta Cc: Michael Neuling Cc: Balbir Singh Cc: Kate Stewart Cc: Thomas Gleixner Cc: Philippe Ombredanne Cc: Pavel Tatashin Cc: Vlastimil Babka Cc: Dan Williams Cc: Oscar Salvador Cc: YASUAKI ISHIMATSU Cc: Mathieu Malaterre Cc: John Allen Cc: Jonathan Corbet Cc: Joonsoo Kim Cc: Nathan Fontenot Cc: Rafael J. Wysocki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 28 ++++++++++++++++++++-------- 1 file changed, 20 insertions(+), 8 deletions(-) (limited to 'mm') diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 39cc887bbdcc..61972da38d93 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -838,7 +838,6 @@ static struct zone * __meminit move_pfn_range(int online_type, int nid, return zone; } -/* Must be protected by mem_hotplug_begin() or a device_lock */ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_type) { unsigned long flags; @@ -850,6 +849,8 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ struct memory_notify arg; struct memory_block *mem; + mem_hotplug_begin(); + /* * We can't use pfn_to_nid() because nid might be stored in struct page * which is not yet initialized. Instead, we find nid from memory block. @@ -914,6 +915,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ if (onlined_pages) memory_notify(MEM_ONLINE, &arg); + mem_hotplug_done(); return 0; failed_addition: @@ -921,6 +923,7 @@ failed_addition: (unsigned long long) pfn << PAGE_SHIFT, (((unsigned long long) pfn + nr_pages) << PAGE_SHIFT) - 1); memory_notify(MEM_CANCEL_ONLINE, &arg); + mem_hotplug_done(); return ret; } #endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */ @@ -1125,20 +1128,20 @@ int __ref add_memory_resource(int nid, struct resource *res, bool online) /* create new memmap entry */ firmware_map_add_hotplug(start, start + size, "System RAM"); + /* device_online() will take the lock when calling online_pages() */ + mem_hotplug_done(); + /* online pages if requested */ if (online) walk_memory_range(PFN_DOWN(start), PFN_UP(start + size - 1), NULL, online_memory_block); - goto out; - + return ret; error: /* rollback pgdat allocation and others */ if (new_node) rollback_node_hotadd(nid); memblock_remove(start, size); - -out: mem_hotplug_done(); return ret; } @@ -1555,10 +1558,16 @@ static int __ref __offline_pages(unsigned long start_pfn, return -EINVAL; if (!IS_ALIGNED(end_pfn, pageblock_nr_pages)) return -EINVAL; + + mem_hotplug_begin(); + /* 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)) + if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start, + &valid_end)) { + mem_hotplug_done(); return -EINVAL; + } zone = page_zone(pfn_to_page(valid_start)); node = zone_to_nid(zone); @@ -1567,8 +1576,10 @@ static int __ref __offline_pages(unsigned long start_pfn, /* set above range as isolated */ ret = start_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE, true); - if (ret) + if (ret) { + mem_hotplug_done(); return ret; + } arg.start_pfn = start_pfn; arg.nr_pages = nr_pages; @@ -1639,6 +1650,7 @@ repeat: writeback_set_ratelimit(); memory_notify(MEM_OFFLINE, &arg); + mem_hotplug_done(); return 0; failed_removal: @@ -1648,10 +1660,10 @@ failed_removal: 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; } -/* Must be protected by mem_hotplug_begin() or a device_lock */ int offline_pages(unsigned long start_pfn, unsigned long nr_pages) { return __offline_pages(start_pfn, start_pfn + nr_pages); -- cgit