From d9eb1417c77df7ce19abd2e41619e9dceccbdf2a Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 13 May 2019 17:21:33 -0700 Subject: mm/memory_hotplug: release memory resource after arch_remove_memory() Patch series "mm/memory_hotplug: Better error handling when removing memory", v1. Error handling when removing memory is somewhat messed up right now. Some errors result in warnings, others are completely ignored. Memory unplug code can essentially not deal with errors properly as of now. remove_memory() will never fail. We have basically two choices: 1. Allow arch_remov_memory() and friends to fail, propagating errors via remove_memory(). Might be problematic (e.g. DIMMs consisting of multiple pieces added/removed separately). 2. Don't allow the functions to fail, handling errors in a nicer way. It seems like most errors that can theoretically happen are really corner cases and mostly theoretical (e.g. "section not valid"). However e.g. aborting removal of sections while all callers simply continue in case of errors is not nice. If we can gurantee that removal of memory always works (and WARN/skip in case of theoretical errors so we can figure out what is going on), we can go ahead and implement better error handling when adding memory. E.g. via add_memory(): arch_add_memory() ret = do_stuff() if (ret) { arch_remove_memory(); goto error; } Handling here that arch_remove_memory() might fail is basically impossible. So I suggest, let's avoid reporting errors while removing memory, warning on theoretical errors instead and continuing instead of aborting. This patch (of 4): __add_pages() doesn't add the memory resource, so __remove_pages() shouldn't remove it. Let's factor it out. Especially as it is a special case for memory used as system memory, added via add_memory() and friends. We now remove the resource after removing the sections instead of doing it the other way around. I don't think this change is problematic. add_memory() register memory resource arch_add_memory() remove_memory arch_remove_memory() release memory resource While at it, explain why we ignore errors and that it only happeny if we remove memory in a different granularity as we added it. [david@redhat.com: fix printk warning] Link: http://lkml.kernel.org/r/20190417120204.6997-1-david@redhat.com Link: http://lkml.kernel.org/r/20190409100148.24703-2-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Oscar Salvador Cc: Michal Hocko Cc: David Hildenbrand Cc: Pavel Tatashin Cc: Wei Yang Cc: Qian Cai Cc: Arun KS Cc: Mathieu Malaterre Cc: Andrew Banman Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Christophe Leroy Cc: Dave Hansen Cc: Fenghua Yu Cc: Geert Uytterhoeven Cc: Greg Kroah-Hartman Cc: Heiko Carstens Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Ingo Molnar Cc: Joonsoo Kim Cc: "Kirill A. Shutemov" Cc: Martin Schwidefsky Cc: Masahiro Yamada Cc: Michael Ellerman Cc: Mike Rapoport Cc: Mike Travis Cc: Nicholas Piggin Cc: Oscar Salvador Cc: Paul Mackerras Cc: Peter Zijlstra Cc: "Rafael J. Wysocki" Cc: Rich Felker Cc: Rob Herring Cc: Stefan Agner Cc: Thomas Gleixner Cc: Tony Luck Cc: Vasily Gorbik Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 35 +++++++++++++++++++++-------------- 1 file changed, 21 insertions(+), 14 deletions(-) (limited to 'mm') diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 339d5a62d5d5..65f166ec2e4c 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -561,20 +561,6 @@ int __remove_pages(struct zone *zone, unsigned long phys_start_pfn, if (is_dev_zone(zone)) { if (altmap) map_offset = vmem_altmap_offset(altmap); - } else { - resource_size_t start, size; - - start = phys_start_pfn << PAGE_SHIFT; - size = nr_pages * PAGE_SIZE; - - ret = release_mem_region_adjustable(&iomem_resource, start, - size); - if (ret) { - resource_size_t endres = start + size - 1; - - pr_warn("Unable to release resource <%pa-%pa> (%d)\n", - &start, &endres, ret); - } } clear_zone_contiguous(zone); @@ -1818,6 +1804,26 @@ void try_offline_node(int nid) } EXPORT_SYMBOL(try_offline_node); +static void __release_memory_resource(resource_size_t start, + resource_size_t size) +{ + int ret; + + /* + * When removing memory in the same granularity as it was added, + * this function never fails. It might only fail if resources + * have to be adjusted or split. We'll ignore the error, as + * removing of memory cannot fail. + */ + ret = release_mem_region_adjustable(&iomem_resource, start, size); + if (ret) { + resource_size_t endres = start + size - 1; + + pr_warn("Unable to release resource <%pa-%pa> (%d)\n", + &start, &endres, ret); + } +} + /** * remove_memory * @nid: the node ID @@ -1852,6 +1858,7 @@ void __ref __remove_memory(int nid, u64 start, u64 size) memblock_remove(start, size); arch_remove_memory(nid, start, size, NULL); + __release_memory_resource(start, size); try_offline_node(nid); -- cgit v1.2.3-58-ga151