From 35dca71c1fad13616d9ea336c05730071793b63a Mon Sep 17 00:00:00 2001 From: Yasuaki Ishimatsu Date: Wed, 29 Oct 2014 14:50:40 -0700 Subject: memory-hotplug: clear pgdat which is allocated by bootmem in try_offline_node() When hot adding the same memory after hot removal, the following messages are shown: WARNING: CPU: 20 PID: 6 at mm/page_alloc.c:4968 free_area_init_node+0x3fe/0x426() ... Call Trace: dump_stack+0x46/0x58 warn_slowpath_common+0x81/0xa0 warn_slowpath_null+0x1a/0x20 free_area_init_node+0x3fe/0x426 hotadd_new_pgdat+0x90/0x110 add_memory+0xd4/0x200 acpi_memory_device_add+0x1aa/0x289 acpi_bus_attach+0xfd/0x204 acpi_bus_attach+0x178/0x204 acpi_bus_scan+0x6a/0x90 acpi_device_hotplug+0xe8/0x418 acpi_hotplug_work_fn+0x1f/0x2b process_one_work+0x14e/0x3f0 worker_thread+0x11b/0x510 kthread+0xe1/0x100 ret_from_fork+0x7c/0xb0 The detaled explanation is as follows: When hot removing memory, pgdat is set to 0 in try_offline_node(). But if the pgdat is allocated by bootmem allocator, the clearing step is skipped. And when hot adding the same memory, the uninitialized pgdat is reused. But free_area_init_node() checks wether pgdat is set to zero. As a result, free_area_init_node() hits WARN_ON(). This patch clears pgdat which is allocated by bootmem allocator in try_offline_node(). Signed-off-by: Yasuaki Ishimatsu Cc: Zhang Zhen Cc: Wang Nan Cc: Tang Chen Reviewed-by: Toshi Kani Cc: Dave Hansen Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 5 ----- 1 file changed, 5 deletions(-) (limited to 'mm/memory_hotplug.c') diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 29d8693d0c61..252e1dbbed86 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1912,7 +1912,6 @@ void try_offline_node(int nid) unsigned long start_pfn = pgdat->node_start_pfn; unsigned long end_pfn = start_pfn + pgdat->node_spanned_pages; unsigned long pfn; - struct page *pgdat_page = virt_to_page(pgdat); int i; for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) { @@ -1941,10 +1940,6 @@ void try_offline_node(int nid) node_set_offline(nid); unregister_one_node(nid); - if (!PageSlab(pgdat_page) && !PageCompound(pgdat_page)) - /* node data is allocated from boot memory */ - return; - /* free waittable in each zone */ for (i = 0; i < MAX_NR_ZONES; i++) { struct zone *zone = pgdat->node_zones + i; -- cgit v1.2.3 From f784a3f19613901ca4539a5b0eed3bdc700e6ee7 Mon Sep 17 00:00:00 2001 From: Tang Chen Date: Thu, 13 Nov 2014 15:19:39 -0800 Subject: mem-hotplug: reset node managed pages when hot-adding a new pgdat In free_area_init_core(), zone->managed_pages is set to an approximate value for lowmem, and will be adjusted when the bootmem allocator frees pages into the buddy system. But free_area_init_core() is also called by hotadd_new_pgdat() when hot-adding memory. As a result, zone->managed_pages of the newly added node's pgdat is set to an approximate value in the very beginning. Even if the memory on that node has node been onlined, /sys/device/system/node/nodeXXX/meminfo has wrong value: hot-add node2 (memory not onlined) cat /sys/device/system/node/node2/meminfo Node 2 MemTotal: 33554432 kB Node 2 MemFree: 0 kB Node 2 MemUsed: 33554432 kB Node 2 Active: 0 kB This patch fixes this problem by reset node managed pages to 0 after hot-adding a new node. 1. Move reset_managed_pages_done from reset_node_managed_pages() to reset_all_zones_managed_pages() 2. Make reset_node_managed_pages() non-static 3. Call reset_node_managed_pages() in hotadd_new_pgdat() after pgdat is initialized Signed-off-by: Tang Chen Signed-off-by: Yasuaki Ishimatsu Cc: [3.16+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 1 + mm/bootmem.c | 9 +++++---- mm/memory_hotplug.c | 9 +++++++++ mm/nobootmem.c | 8 +++++--- 4 files changed, 20 insertions(+), 7 deletions(-) (limited to 'mm/memory_hotplug.c') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 4e2bd4c95b66..0995c2de8162 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -46,6 +46,7 @@ extern unsigned long init_bootmem_node(pg_data_t *pgdat, extern unsigned long init_bootmem(unsigned long addr, unsigned long memend); extern unsigned long free_all_bootmem(void); +extern void reset_node_managed_pages(pg_data_t *pgdat); extern void reset_all_zones_managed_pages(void); extern void free_bootmem_node(pg_data_t *pgdat, diff --git a/mm/bootmem.c b/mm/bootmem.c index 8a000cebb0d7..477be696511d 100644 --- a/mm/bootmem.c +++ b/mm/bootmem.c @@ -243,13 +243,10 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata) static int reset_managed_pages_done __initdata; -static inline void __init reset_node_managed_pages(pg_data_t *pgdat) +void reset_node_managed_pages(pg_data_t *pgdat) { struct zone *z; - if (reset_managed_pages_done) - return; - for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++) z->managed_pages = 0; } @@ -258,8 +255,12 @@ void __init reset_all_zones_managed_pages(void) { struct pglist_data *pgdat; + if (reset_managed_pages_done) + return; + for_each_online_pgdat(pgdat) reset_node_managed_pages(pgdat); + reset_managed_pages_done = 1; } diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 252e1dbbed86..c5f7fe199a60 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -31,6 +31,7 @@ #include #include #include +#include #include @@ -1096,6 +1097,14 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start) build_all_zonelists(pgdat, NULL); mutex_unlock(&zonelists_mutex); + /* + * zone->managed_pages is set to an approximate value in + * free_area_init_core(), which will cause + * /sys/device/system/node/nodeX/meminfo has wrong data. + * So reset it to 0 before any memory is onlined. + */ + reset_node_managed_pages(pgdat); + return pgdat; } diff --git a/mm/nobootmem.c b/mm/nobootmem.c index 7c7ab32ee503..90b50468333e 100644 --- a/mm/nobootmem.c +++ b/mm/nobootmem.c @@ -145,12 +145,10 @@ static unsigned long __init free_low_memory_core_early(void) static int reset_managed_pages_done __initdata; -static inline void __init reset_node_managed_pages(pg_data_t *pgdat) +void reset_node_managed_pages(pg_data_t *pgdat) { struct zone *z; - if (reset_managed_pages_done) - return; for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++) z->managed_pages = 0; } @@ -159,8 +157,12 @@ void __init reset_all_zones_managed_pages(void) { struct pglist_data *pgdat; + if (reset_managed_pages_done) + return; + for_each_online_pgdat(pgdat) reset_node_managed_pages(pgdat); + reset_managed_pages_done = 1; } -- cgit v1.2.3 From 0bd854200873894a76f32603ff2c4c988ad6b5b5 Mon Sep 17 00:00:00 2001 From: Tang Chen Date: Thu, 13 Nov 2014 15:19:41 -0800 Subject: mem-hotplug: reset node present pages when hot-adding a new pgdat When memory is hot-added, all the memory is in offline state. So clear all zones' present_pages because they will be updated in online_pages() and offline_pages(). Otherwise, /proc/zoneinfo will corrupt: When the memory of node2 is offline: # cat /proc/zoneinfo ...... Node 2, zone Movable ...... spanned 8388608 present 8388608 managed 0 When we online memory on node2: # cat /proc/zoneinfo ...... Node 2, zone Movable ...... spanned 8388608 present 16777216 managed 8388608 Signed-off-by: Tang Chen Reviewed-by: Yasuaki Ishimatsu Cc: [3.16+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'mm/memory_hotplug.c') diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index c5f7fe199a60..1bf4807cb21e 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1067,6 +1067,16 @@ out: } #endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */ +static void reset_node_present_pages(pg_data_t *pgdat) +{ + struct zone *z; + + for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++) + z->present_pages = 0; + + pgdat->node_present_pages = 0; +} + /* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start) { @@ -1105,6 +1115,13 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start) */ reset_node_managed_pages(pgdat); + /* + * When memory is hot-added, all the memory is in offline state. So + * clear all zones' present_pages because they will be updated in + * online_pages() and offline_pages(). + */ + reset_node_present_pages(pgdat); + return pgdat; } -- cgit v1.2.3