aboutsummaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
authorKirill A. Shutemov <kirill@shutemov.name>2020-01-30 22:13:57 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2020-01-31 10:30:38 -0800
commit3f1353552e256cb3bf0f23334c48f50476044673 (patch)
treebba5464134ecf526046af1dfbf3e539335fff6ea /mm
parentmm/early_ioremap.c: use %pa to print resource_size_t variables (diff)
downloadlinux-dev-3f1353552e256cb3bf0f23334c48f50476044673.tar.xz
linux-dev-3f1353552e256cb3bf0f23334c48f50476044673.zip
mm/page_alloc: skip non present sections on zone initialization
memmap_init_zone() can be called on the ranges with holes during the boot. It will skip any non-valid PFNs one-by-one. It works fine as long as holes are not too big. But huge holes in the memory map causes a problem. It takes over 20 seconds to walk 32TiB hole. x86-64 with 5-level paging allows for much larger holes in the memory map which would practically hang the system. Deferred struct page init doesn't help here. It only works on the present ranges. Skipping non-present sections would fix the issue. Link: http://lkml.kernel.org/r/20191230093828.24613-1-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Reviewed-by: Baoquan He <bhe@redhat.com> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Mel Gorman <mgorman@suse.de> Cc: "Jin, Zhi" <zhi.jin@intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Oscar Salvador <osalvador@suse.de> Cc: Pavel Tatashin <pasha.tatashin@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r--mm/page_alloc.c28
1 files changed, 27 insertions, 1 deletions
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d047bf7d8fd4..fe8a529f7fd8 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5848,6 +5848,30 @@ overlap_memmap_init(unsigned long zone, unsigned long *pfn)
return false;
}
+#ifdef CONFIG_SPARSEMEM
+/* Skip PFNs that belong to non-present sections */
+static inline __meminit unsigned long next_pfn(unsigned long pfn)
+{
+ unsigned long section_nr;
+
+ section_nr = pfn_to_section_nr(++pfn);
+ if (present_section_nr(section_nr))
+ return pfn;
+
+ while (++section_nr <= __highest_present_section_nr) {
+ if (present_section_nr(section_nr))
+ return section_nr_to_pfn(section_nr);
+ }
+
+ return -1;
+}
+#else
+static inline __meminit unsigned long next_pfn(unsigned long pfn)
+{
+ return pfn++;
+}
+#endif
+
/*
* Initially all pages are reserved - free ones are freed
* up by memblock_free_all() once the early boot process is
@@ -5887,8 +5911,10 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
* function. They do not exist on hotplugged memory.
*/
if (context == MEMMAP_EARLY) {
- if (!early_pfn_valid(pfn))
+ if (!early_pfn_valid(pfn)) {
+ pfn = next_pfn(pfn) - 1;
continue;
+ }
if (!early_pfn_in_nid(pfn, nid))
continue;
if (overlap_memmap_init(zone, &pfn))