Within show_valid_zones() the function test_pages_in_a_zone() should be called for online memory blocks only. Otherwise it might lead to the VM_BUG_ON due to uninitialized struct pages (when CONFIG_DEBUG_VM_PGFLAGS kernel option is set): page dumped because: VM_BUG_ON_PAGE(PagePoisoned(p)) ------------[ cut here ]------------ Call Trace: ([<000000000038f91e>] test_pages_in_a_zone+0xe6/0x168) [<0000000000923472>] show_valid_zones+0x5a/0x1a8 [<0000000000900284>] dev_attr_show+0x3c/0x78 [<000000000046f6f0>] sysfs_kf_seq_show+0xd0/0x150 [<00000000003ef662>] seq_read+0x212/0x4b8 [<00000000003bf202>] __vfs_read+0x3a/0x178 [<00000000003bf3ca>] vfs_read+0x8a/0x148 [<00000000003bfa3a>] ksys_read+0x62/0xb8 [<0000000000bc2220>] system_call+0xdc/0x2d8 That VM_BUG_ON was triggered by the page poisoning introduced in mm/sparse.c with the git commit d0dc12e86b31 ("mm/memory_hotplug: optimize memory hotplug"). With the same commit the new 'nid' field has been added to the struct memory_block in order to store and later on derive the node id for offline pages (instead of accessing struct page which might be uninitialized). But one reference to nid in show_valid_zones() function has been overlooked. Fixed with current commit. Also, nr_pages will not be used any more after test_pages_in_a_zone() call, do not update it.
Unified · Split
| @@ -416,26 +416,24 @@ static ssize_t show_valid_zones(struct device *dev, · 415 unmodified lines | ||
| 416 | 416 | struct zone *default_zone; |
| 417 | 417 | int nid; |
| 418 | 418 | |
| 419 | − /* | |
| 420 | − * The block contains more than one zone can not be offlined. | |
| 421 | − * This can happen e.g. for ZONE_DMA and ZONE_DMA32 | |
| 422 | − */ | |
| 423 | − if (!test_pages_in_a_zone(start_pfn, start_pfn + nr_pages, &valid_start_pfn, &valid_end_pfn)) | |
| 424 | − return sprintf(buf, "none\n"); | |
| 425 | − | |
| 426 | − start_pfn = valid_start_pfn; | |
| 427 | − nr_pages = valid_end_pfn - start_pfn; | |
| 428 | − | |
| 429 | 419 | /* |
| 430 | 420 | * Check the existing zone. Make sure that we do that only on the |
| 431 | 421 | * online nodes otherwise the page_zone is not reliable |
| 432 | 422 | */ |
| 433 | 423 | if (mem->state == MEM_ONLINE) { |
| 424 | + /* | |
| 425 | + * The block contains more than one zone can not be offlined. | |
| 426 | + * This can happen e.g. for ZONE_DMA and ZONE_DMA32 | |
| 427 | + */ | |
| 428 | + if (!test_pages_in_a_zone(start_pfn, start_pfn + nr_pages, | |
| 429 | + &valid_start_pfn, &valid_end_pfn)) | |
| 430 | + return sprintf(buf, "none\n"); | |
| 431 | + start_pfn = valid_start_pfn; | |
| 434 | 432 | strcat(buf, page_zone(pfn_to_page(start_pfn))->name); |
| 435 | 433 | goto out; |
| 436 | 434 | } |
| 437 | 435 | |
| 438 | − nid = pfn_to_nid(start_pfn); | |
| 436 | + nid = mem->nid; | |
| 439 | 437 | default_zone = zone_for_pfn_range(MMOP_ONLINE_KEEP, nid, start_pfn, nr_pages); |
| 440 | 438 | strcat(buf, default_zone->name); |
| 441 | 439 | |