From ba72b4c8cf60e452cf6f0258ed9ee697957b7dfd Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 18 Jul 2019 15:58:26 -0700 Subject: mm/sparsemem: support sub-section hotplug The libnvdimm sub-system has suffered a series of hacks and broken workarounds for the memory-hotplug implementation's awkward section-aligned (128MB) granularity. For example the following backtrace is emitted when attempting arch_add_memory() with physical address ranges that intersect 'System RAM' (RAM) with 'Persistent Memory' (PMEM) within a given section: # cat /proc/iomem | grep -A1 -B1 Persistent\ Memory 100000000-1ffffffff : System RAM 200000000-303ffffff : Persistent Memory (legacy) 304000000-43fffffff : System RAM 440000000-23ffffffff : Persistent Memory 2400000000-43bfffffff : Persistent Memory 2400000000-43bfffffff : namespace2.0 WARNING: CPU: 38 PID: 928 at arch/x86/mm/init_64.c:850 add_pages+0x5c/0x60 [..] RIP: 0010:add_pages+0x5c/0x60 [..] Call Trace: devm_memremap_pages+0x460/0x6e0 pmem_attach_disk+0x29e/0x680 [nd_pmem] ? nd_dax_probe+0xfc/0x120 [libnvdimm] nvdimm_bus_probe+0x66/0x160 [libnvdimm] It was discovered that the problem goes beyond RAM vs PMEM collisions as some platform produce PMEM vs PMEM collisions within a given section. The libnvdimm workaround for that case revealed that the libnvdimm section-alignment-padding implementation has been broken for a long while. A fix for that long-standing breakage introduces as many problems as it solves as it would require a backward-incompatible change to the namespace metadata interpretation. Instead of that dubious route [1], address the root problem in the memory-hotplug implementation. Note that EEXIST is no longer treated as success as that is how sparse_add_section() reports subsection collisions, it was also obviated by recent changes to perform the request_region() for 'System RAM' before arch_add_memory() in the add_memory() sequence. [1] https://lore.kernel.org/r/155000671719.348031.2347363160141119237.stgit@dwillia2-desk3.amr.corp.intel.com [osalvador@suse.de: fix deactivate_section for early sections] Link: http://lkml.kernel.org/r/20190715081549.32577-2-osalvador@suse.de Link: http://lkml.kernel.org/r/156092354368.979959.6232443923440952359.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams Signed-off-by: Oscar Salvador Tested-by: Aneesh Kumar K.V [ppc64] Reviewed-by: Oscar Salvador Cc: Michal Hocko Cc: Vlastimil Babka Cc: Logan Gunthorpe Cc: Pavel Tatashin Cc: David Hildenbrand Cc: Jane Chu Cc: Jeff Moyer Cc: Jérôme Glisse Cc: Jonathan Corbet Cc: Mike Rapoport Cc: Toshi Kani Cc: Wei Yang Cc: Jason Gunthorpe Cc: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 27 ++++----------------------- 1 file changed, 4 insertions(+), 23 deletions(-) (limited to 'mm/memory_hotplug.c') diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 3fbb2cfab126..aafb71594ee3 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -252,18 +252,6 @@ void __init register_page_bootmem_info_node(struct pglist_data *pgdat) } #endif /* CONFIG_HAVE_BOOTMEM_INFO_NODE */ -static int __meminit __add_section(int nid, unsigned long pfn, - unsigned long nr_pages, struct vmem_altmap *altmap) -{ - int ret; - - if (pfn_valid(pfn)) - return -EEXIST; - - ret = sparse_add_section(nid, pfn, nr_pages, altmap); - return ret < 0 ? ret : 0; -} - static int check_pfn_span(unsigned long pfn, unsigned long nr_pages, const char *reason) { @@ -327,18 +315,11 @@ int __ref __add_pages(int nid, unsigned long pfn, unsigned long nr_pages, pfns = min(nr_pages, PAGES_PER_SECTION - (pfn & ~PAGE_SECTION_MASK)); - err = __add_section(nid, pfn, pfns, altmap); + err = sparse_add_section(nid, pfn, pfns, altmap); + if (err) + break; pfn += pfns; nr_pages -= pfns; - - /* - * EEXIST is finally dealt with by ioresource collision - * check. see add_memory() => register_memory_resource() - * Warning will be printed if there is collision. - */ - if (err && (err != -EEXIST)) - break; - err = 0; cond_resched(); } vmemmap_populate_print_last(); @@ -541,7 +522,7 @@ static void __remove_section(struct zone *zone, unsigned long pfn, return; __remove_zone(zone, pfn, nr_pages); - sparse_remove_one_section(ms, pfn, nr_pages, map_offset, altmap); + sparse_remove_section(ms, pfn, nr_pages, map_offset, altmap); } /** -- cgit v1.2.3-55-g7522