From bfe63d3beabfac93521c8b7ccd40befd7a90148e Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Thu, 6 Jul 2017 15:37:42 -0700 Subject: mm: drop page_initialized check from get_nid_for_pfn Commit c04fc586c1a4 ("mm: show node to memory section relationship with symlinks in sysfs") has added means to export memblock<->node association into the sysfs. It has also introduced get_nid_for_pfn which is a rather confusing counterpart of pfn_to_nid which checks also whether the pfn page is already initialized (page_initialized). This is done by checking page::lru != NULL which doesn't make any sense at all. Nothing in this path really relies on the lru list being used or initialized. Just remove it because this will become a problem with later patches. Thanks to Reza Arbab for testing which revealed this to be a problem (http://lkml.kernel.org/r/20170403202337.GA12482@dhcp22.suse.cz) Link: http://lkml.kernel.org/r/20170515085827.16474-4-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Vlastimil Babka Cc: Reza Arbab Cc: Andi Kleen Cc: Andrea Arcangeli Cc: Balbir Singh Cc: Dan Williams Cc: Daniel Kiper Cc: David Rientjes Cc: Heiko Carstens Cc: Igor Mammedov Cc: Jerome Glisse Cc: Joonsoo Kim Cc: Martin Schwidefsky Cc: Mel Gorman Cc: Tobias Regnery Cc: Toshi Kani Cc: Vitaly Kuznetsov Cc: Xishi Qiu Cc: Yasuaki Ishimatsu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/node.c | 7 ------- 1 file changed, 7 deletions(-) (limited to 'drivers/base/node.c') diff --git a/drivers/base/node.c b/drivers/base/node.c index 0440d95c9b5b..db769d3148b7 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -368,21 +368,14 @@ int unregister_cpu_under_node(unsigned int cpu, unsigned int nid) } #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE -#define page_initialized(page) (page->lru.next) - static int __ref get_nid_for_pfn(unsigned long pfn) { - struct page *page; - if (!pfn_valid_within(pfn)) return -1; #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT if (system_state < SYSTEM_RUNNING) return early_pfn_to_nid(pfn); #endif - page = pfn_to_page(pfn); - if (!page_initialized(page)) - return -1; return pfn_to_nid(pfn); } -- cgit v1.3-18-gd494 From 9037a9934349b0e180896fc8cacaf1819418ba03 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Thu, 6 Jul 2017 15:37:49 -0700 Subject: mm, memory_hotplug: split up register_one_node() Memory hotplug (add_memory_resource) has to reinitialize node infrastructure if the node is offline (one which went through the complete add_memory(); remove_memory() cycle). That involves node registration to the kobj infrastructure (register_node), the proper association with cpus (register_cpu_under_node) and finally creation of node<->memblock symlinks (link_mem_sections). The last part requires to know node_start_pfn and node_spanned_pages which we currently have but a leter patch will postpone this initialization to the onlining phase which happens later. In fact we do not need to rely on the early pgdat initialization even now because the currently hot added pfn range is currently known. Split register_one_node into core which does all the common work for the boot time NUMA initialization and the hotplug (__register_one_node). register_one_node keeps the full initialization while hotplug calls __register_one_node and manually calls link_mem_sections for the proper range. This shouldn't introduce any functional change. Link: http://lkml.kernel.org/r/20170515085827.16474-6-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Vlastimil Babka Cc: Andi Kleen Cc: Andrea Arcangeli Cc: Balbir Singh Cc: Dan Williams Cc: Daniel Kiper Cc: David Rientjes Cc: Heiko Carstens Cc: Igor Mammedov Cc: Jerome Glisse Cc: Joonsoo Kim Cc: Martin Schwidefsky Cc: Mel Gorman Cc: Reza Arbab Cc: Tobias Regnery Cc: Toshi Kani Cc: Vitaly Kuznetsov Cc: Xishi Qiu Cc: Yasuaki Ishimatsu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/node.c | 51 ++++++++++++++++++++------------------------------- include/linux/node.h | 35 ++++++++++++++++++++++++++++++++++- mm/memory_hotplug.c | 17 ++++++++++++++++- 3 files changed, 70 insertions(+), 33 deletions(-) (limited to 'drivers/base/node.c') diff --git a/drivers/base/node.c b/drivers/base/node.c index db769d3148b7..1da0005341a1 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -461,10 +461,9 @@ int unregister_mem_sect_under_nodes(struct memory_block *mem_blk, return 0; } -static int link_mem_sections(int nid) +int link_mem_sections(int nid, unsigned long start_pfn, unsigned long nr_pages) { - unsigned long start_pfn = NODE_DATA(nid)->node_start_pfn; - unsigned long end_pfn = start_pfn + NODE_DATA(nid)->node_spanned_pages; + unsigned long end_pfn = start_pfn + nr_pages; unsigned long pfn; struct memory_block *mem_blk = NULL; int err = 0; @@ -552,10 +551,7 @@ static int node_memory_callback(struct notifier_block *self, return NOTIFY_OK; } #endif /* CONFIG_HUGETLBFS */ -#else /* !CONFIG_MEMORY_HOTPLUG_SPARSE */ - -static int link_mem_sections(int nid) { return 0; } -#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */ +#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */ #if !defined(CONFIG_MEMORY_HOTPLUG_SPARSE) || \ !defined(CONFIG_HUGETLBFS) @@ -569,39 +565,32 @@ static void init_node_hugetlb_work(int nid) { } #endif -int register_one_node(int nid) +int __register_one_node(int nid) { - int error = 0; + int p_node = parent_node(nid); + struct node *parent = NULL; + int error; int cpu; - if (node_online(nid)) { - int p_node = parent_node(nid); - struct node *parent = NULL; - - if (p_node != nid) - parent = node_devices[p_node]; - - node_devices[nid] = kzalloc(sizeof(struct node), GFP_KERNEL); - if (!node_devices[nid]) - return -ENOMEM; - - error = register_node(node_devices[nid], nid, parent); + if (p_node != nid) + parent = node_devices[p_node]; - /* link cpu under this node */ - for_each_present_cpu(cpu) { - if (cpu_to_node(cpu) == nid) - register_cpu_under_node(cpu, nid); - } + node_devices[nid] = kzalloc(sizeof(struct node), GFP_KERNEL); + if (!node_devices[nid]) + return -ENOMEM; - /* link memory sections under this node */ - error = link_mem_sections(nid); + error = register_node(node_devices[nid], nid, parent); - /* initialize work queue for memory hot plug */ - init_node_hugetlb_work(nid); + /* link cpu under this node */ + for_each_present_cpu(cpu) { + if (cpu_to_node(cpu) == nid) + register_cpu_under_node(cpu, nid); } - return error; + /* initialize work queue for memory hot plug */ + init_node_hugetlb_work(nid); + return error; } void unregister_one_node(int nid) diff --git a/include/linux/node.h b/include/linux/node.h index 2115ad5d6f19..d1751beb462c 100644 --- a/include/linux/node.h +++ b/include/linux/node.h @@ -30,9 +30,38 @@ struct memory_block; extern struct node *node_devices[]; typedef void (*node_registration_func_t)(struct node *); +#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_NUMA) +extern int link_mem_sections(int nid, unsigned long start_pfn, unsigned long nr_pages); +#else +static inline int link_mem_sections(int nid, unsigned long start_pfn, unsigned long nr_pages) +{ + return 0; +} +#endif + extern void unregister_node(struct node *node); #ifdef CONFIG_NUMA -extern int register_one_node(int nid); +/* Core of the node registration - only memory hotplug should use this */ +extern int __register_one_node(int nid); + +/* Registers an online node */ +static inline int register_one_node(int nid) +{ + int error = 0; + + if (node_online(nid)) { + struct pglist_data *pgdat = NODE_DATA(nid); + + error = __register_one_node(nid); + if (error) + return error; + /* link memory sections under this node */ + error = link_mem_sections(nid, pgdat->node_start_pfn, pgdat->node_spanned_pages); + } + + return error; +} + extern void unregister_one_node(int nid); extern int register_cpu_under_node(unsigned int cpu, unsigned int nid); extern int unregister_cpu_under_node(unsigned int cpu, unsigned int nid); @@ -46,6 +75,10 @@ extern void register_hugetlbfs_with_node(node_registration_func_t doregister, node_registration_func_t unregister); #endif #else +static inline int __register_one_node(int nid) +{ + return 0; +} static inline int register_one_node(int nid) { return 0; diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index c0147d3024eb..caa58338d121 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1388,7 +1388,22 @@ int __ref add_memory_resource(int nid, struct resource *res, bool online) node_set_online(nid); if (new_node) { - ret = register_one_node(nid); + unsigned long start_pfn = start >> PAGE_SHIFT; + unsigned long nr_pages = size >> PAGE_SHIFT; + + ret = __register_one_node(nid); + if (ret) + goto register_fail; + + /* + * link memory sections under this node. This is already + * done when creatig memory section in register_new_memory + * but that depends to have the node registered so offline + * nodes have to go through register_node. + * TODO clean up this mess. + */ + ret = link_mem_sections(nid, start_pfn, nr_pages); +register_fail: /* * If sysfs file of new node can't create, cpu on the node * can't be hot-added. There is no rollback way now. -- cgit v1.3-18-gd494 From 385386cff4c6f047907655e05791d88198c4c523 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 6 Jul 2017 15:40:43 -0700 Subject: mm: vmstat: move slab statistics from zone to node counters Patch series "mm: per-lruvec slab stats" Josef is working on a new approach to balancing slab caches and the page cache. For this to work, he needs slab cache statistics on the lruvec level. These patches implement that by adding infrastructure that allows updating and reading generic VM stat items per lruvec, then switches some existing VM accounting sites, including the slab accounting ones, to this new cgroup-aware API. I'll follow up with more patches on this, because there is actually substantial simplification that can be done to the memory controller when we replace private memcg accounting with making the existing VM accounting sites cgroup-aware. But this is enough for Josef to base his slab reclaim work on, so here goes. This patch (of 5): To re-implement slab cache vs. page cache balancing, we'll need the slab counters at the lruvec level, which, ever since lru reclaim was moved from the zone to the node, is the intersection of the node, not the zone, and the memcg. We could retain the per-zone counters for when the page allocator dumps its memory information on failures, and have counters on both levels - which on all but NUMA node 0 is usually redundant. But let's keep it simple for now and just move them. If anybody complains we can restore the per-zone counters. [hannes@cmpxchg.org: fix oops] Link: http://lkml.kernel.org/r/20170605183511.GA8915@cmpxchg.org Link: http://lkml.kernel.org/r/20170530181724.27197-3-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Cc: Josef Bacik Cc: Michal Hocko Cc: Vladimir Davydov Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/node.c | 10 +++++----- include/linux/mmzone.h | 4 ++-- mm/page_alloc.c | 7 +++---- mm/slab.c | 8 ++++---- mm/slub.c | 4 ++-- mm/vmscan.c | 2 +- mm/vmstat.c | 4 ++-- 7 files changed, 19 insertions(+), 20 deletions(-) (limited to 'drivers/base/node.c') diff --git a/drivers/base/node.c b/drivers/base/node.c index 1da0005341a1..6b1ee371ee97 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -129,11 +129,11 @@ static ssize_t node_read_meminfo(struct device *dev, nid, K(node_page_state(pgdat, NR_UNSTABLE_NFS)), nid, K(sum_zone_node_page_state(nid, NR_BOUNCE)), nid, K(node_page_state(pgdat, NR_WRITEBACK_TEMP)), - nid, K(sum_zone_node_page_state(nid, NR_SLAB_RECLAIMABLE) + - sum_zone_node_page_state(nid, NR_SLAB_UNRECLAIMABLE)), - nid, K(sum_zone_node_page_state(nid, NR_SLAB_RECLAIMABLE)), + nid, K(node_page_state(pgdat, NR_SLAB_RECLAIMABLE) + + node_page_state(pgdat, NR_SLAB_UNRECLAIMABLE)), + nid, K(node_page_state(pgdat, NR_SLAB_RECLAIMABLE)), #ifdef CONFIG_TRANSPARENT_HUGEPAGE - nid, K(sum_zone_node_page_state(nid, NR_SLAB_UNRECLAIMABLE)), + nid, K(node_page_state(pgdat, NR_SLAB_UNRECLAIMABLE)), nid, K(node_page_state(pgdat, NR_ANON_THPS) * HPAGE_PMD_NR), nid, K(node_page_state(pgdat, NR_SHMEM_THPS) * @@ -141,7 +141,7 @@ static ssize_t node_read_meminfo(struct device *dev, nid, K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED) * HPAGE_PMD_NR)); #else - nid, K(sum_zone_node_page_state(nid, NR_SLAB_UNRECLAIMABLE))); + nid, K(node_page_state(pgdat, NR_SLAB_UNRECLAIMABLE))); #endif n += hugetlb_report_node_meminfo(nid, buf + n); return n; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index abc1641011f2..7e8f100cb56d 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -125,8 +125,6 @@ enum zone_stat_item { NR_ZONE_UNEVICTABLE, NR_ZONE_WRITE_PENDING, /* Count of dirty, writeback and unstable pages */ NR_MLOCK, /* mlock()ed pages found and moved off LRU */ - NR_SLAB_RECLAIMABLE, - NR_SLAB_UNRECLAIMABLE, NR_PAGETABLE, /* used for pagetables */ NR_KERNEL_STACK_KB, /* measured in KiB */ /* Second 128 byte cacheline */ @@ -152,6 +150,8 @@ enum node_stat_item { NR_INACTIVE_FILE, /* " " " " " */ NR_ACTIVE_FILE, /* " " " " " */ NR_UNEVICTABLE, /* " " " " " */ + NR_SLAB_RECLAIMABLE, + NR_SLAB_UNRECLAIMABLE, NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */ NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ WORKINGSET_REFAULT, diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 8aa860017d66..a35add8d7c0b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4643,8 +4643,6 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) " present:%lukB" " managed:%lukB" " mlocked:%lukB" - " slab_reclaimable:%lukB" - " slab_unreclaimable:%lukB" " kernel_stack:%lukB" " pagetables:%lukB" " bounce:%lukB" @@ -4666,8 +4664,6 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) K(zone->present_pages), K(zone->managed_pages), K(zone_page_state(zone, NR_MLOCK)), - K(zone_page_state(zone, NR_SLAB_RECLAIMABLE)), - K(zone_page_state(zone, NR_SLAB_UNRECLAIMABLE)), zone_page_state(zone, NR_KERNEL_STACK_KB), K(zone_page_state(zone, NR_PAGETABLE)), K(zone_page_state(zone, NR_BOUNCE)), @@ -5153,6 +5149,7 @@ static void build_zonelists(pg_data_t *pgdat) */ static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch); static DEFINE_PER_CPU(struct per_cpu_pageset, boot_pageset); +static DEFINE_PER_CPU(struct per_cpu_nodestat, boot_nodestats); static void setup_zone_pageset(struct zone *zone); /* @@ -6053,6 +6050,8 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat) spin_lock_init(&pgdat->lru_lock); lruvec_init(node_lruvec(pgdat)); + pgdat->per_cpu_nodestats = &boot_nodestats; + for (j = 0; j < MAX_NR_ZONES; j++) { struct zone *zone = pgdat->node_zones + j; unsigned long size, realsize, freesize, memmap_pages; diff --git a/mm/slab.c b/mm/slab.c index 503317188926..a38634ed478e 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -1425,10 +1425,10 @@ static struct page *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, nr_pages = (1 << cachep->gfporder); if (cachep->flags & SLAB_RECLAIM_ACCOUNT) - add_zone_page_state(page_zone(page), + add_node_page_state(page_pgdat(page), NR_SLAB_RECLAIMABLE, nr_pages); else - add_zone_page_state(page_zone(page), + add_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE, nr_pages); __SetPageSlab(page); @@ -1459,10 +1459,10 @@ static void kmem_freepages(struct kmem_cache *cachep, struct page *page) kmemcheck_free_shadow(page, order); if (cachep->flags & SLAB_RECLAIM_ACCOUNT) - sub_zone_page_state(page_zone(page), + sub_node_page_state(page_pgdat(page), NR_SLAB_RECLAIMABLE, nr_freed); else - sub_zone_page_state(page_zone(page), + sub_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE, nr_freed); BUG_ON(!PageSlab(page)); diff --git a/mm/slub.c b/mm/slub.c index 388f66d1da5e..aa5aa6bfb35e 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1615,7 +1615,7 @@ out: if (!page) return NULL; - mod_zone_page_state(page_zone(page), + mod_node_page_state(page_pgdat(page), (s->flags & SLAB_RECLAIM_ACCOUNT) ? NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE, 1 << oo_order(oo)); @@ -1655,7 +1655,7 @@ static void __free_slab(struct kmem_cache *s, struct page *page) kmemcheck_free_shadow(page, compound_order(page)); - mod_zone_page_state(page_zone(page), + mod_node_page_state(page_pgdat(page), (s->flags & SLAB_RECLAIM_ACCOUNT) ? NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE, -pages); diff --git a/mm/vmscan.c b/mm/vmscan.c index 7d3c6c59897c..9e95fafc026b 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -3874,7 +3874,7 @@ int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order) * unmapped file backed pages. */ if (node_pagecache_reclaimable(pgdat) <= pgdat->min_unmapped_pages && - sum_zone_node_page_state(pgdat->node_id, NR_SLAB_RECLAIMABLE) <= pgdat->min_slab_pages) + node_page_state(pgdat, NR_SLAB_RECLAIMABLE) <= pgdat->min_slab_pages) return NODE_RECLAIM_FULL; /* diff --git a/mm/vmstat.c b/mm/vmstat.c index 46281825c710..744ceaeb42a0 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -928,8 +928,6 @@ const char * const vmstat_text[] = { "nr_zone_unevictable", "nr_zone_write_pending", "nr_mlock", - "nr_slab_reclaimable", - "nr_slab_unreclaimable", "nr_page_table_pages", "nr_kernel_stack", "nr_bounce", @@ -952,6 +950,8 @@ const char * const vmstat_text[] = { "nr_inactive_file", "nr_active_file", "nr_unevictable", + "nr_slab_reclaimable", + "nr_slab_unreclaimable", "nr_isolated_anon", "nr_isolated_file", "workingset_refault", -- cgit v1.3-18-gd494 From f70029bbaacbfa8f082d2b4988717cba4e269f17 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Thu, 6 Jul 2017 15:41:02 -0700 Subject: mm, memory_hotplug: drop CONFIG_MOVABLE_NODE Commit 20b2f52b73fe ("numa: add CONFIG_MOVABLE_NODE for movable-dedicated node") has introduced CONFIG_MOVABLE_NODE without a good explanation on why it is actually useful. It makes a lot of sense to make movable node semantic opt in but we already have that because the feature has to be explicitly enabled on the kernel command line. A config option on top only makes the configuration space larger without a good reason. It also adds an additional ifdefery that pollutes the code. Just drop the config option and make it de-facto always enabled. This shouldn't introduce any change to the semantic. Link: http://lkml.kernel.org/r/20170529114141.536-3-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Reza Arbab Acked-by: Vlastimil Babka Cc: Mel Gorman Cc: Andrea Arcangeli Cc: Jerome Glisse Cc: Yasuaki Ishimatsu Cc: Xishi Qiu Cc: Kani Toshimitsu Cc: Chen Yucong Cc: Joonsoo Kim Cc: Andi Kleen Cc: David Rientjes Cc: Daniel Kiper Cc: Igor Mammedov Cc: Vitaly Kuznetsov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/kernel-parameters.txt | 7 +++++-- drivers/base/node.c | 4 ---- include/linux/memblock.h | 18 ----------------- include/linux/nodemask.h | 4 ---- mm/Kconfig | 26 ------------------------- mm/memblock.c | 2 -- mm/memory_hotplug.c | 4 ---- mm/page_alloc.c | 2 -- 8 files changed, 5 insertions(+), 62 deletions(-) (limited to 'drivers/base/node.c') diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 34ae9663aefd..dd7abbea8188 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2303,8 +2303,11 @@ that the amount of memory usable for all allocations is not too small. - movable_node [KNL] Boot-time switch to enable the effects - of CONFIG_MOVABLE_NODE=y. See mm/Kconfig for details. + movable_node [KNL] Boot-time switch to make hotplugable memory + NUMA nodes to be movable. This means that the memory + of such nodes will be usable only for movable + allocations which rules out almost all kernel + allocations. Use with caution! MTD_Partition= [MTD] Format: ,,, diff --git a/drivers/base/node.c b/drivers/base/node.c index 6b1ee371ee97..73d39bc58c42 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -639,9 +639,7 @@ static struct node_attr node_state_attr[] = { #ifdef CONFIG_HIGHMEM [N_HIGH_MEMORY] = _NODE_ATTR(has_high_memory, N_HIGH_MEMORY), #endif -#ifdef CONFIG_MOVABLE_NODE [N_MEMORY] = _NODE_ATTR(has_memory, N_MEMORY), -#endif [N_CPU] = _NODE_ATTR(has_cpu, N_CPU), }; @@ -652,9 +650,7 @@ static struct attribute *node_state_attrs[] = { #ifdef CONFIG_HIGHMEM &node_state_attr[N_HIGH_MEMORY].attr.attr, #endif -#ifdef CONFIG_MOVABLE_NODE &node_state_attr[N_MEMORY].attr.attr, -#endif &node_state_attr[N_CPU].attr.attr, NULL }; diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 8098695e5d8d..1199e605d676 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -57,10 +57,8 @@ struct memblock { extern struct memblock memblock; extern int memblock_debug; -#ifdef CONFIG_MOVABLE_NODE /* If movable_node boot option specified */ extern bool movable_node_enabled; -#endif /* CONFIG_MOVABLE_NODE */ #ifdef CONFIG_ARCH_DISCARD_MEMBLOCK #define __init_memblock __meminit @@ -169,7 +167,6 @@ void __next_reserved_mem_region(u64 *idx, phys_addr_t *out_start, i != (u64)ULLONG_MAX; \ __next_reserved_mem_region(&i, p_start, p_end)) -#ifdef CONFIG_MOVABLE_NODE static inline bool memblock_is_hotpluggable(struct memblock_region *m) { return m->flags & MEMBLOCK_HOTPLUG; @@ -179,16 +176,6 @@ static inline bool __init_memblock movable_node_is_enabled(void) { return movable_node_enabled; } -#else -static inline bool memblock_is_hotpluggable(struct memblock_region *m) -{ - return false; -} -static inline bool movable_node_is_enabled(void) -{ - return false; -} -#endif static inline bool memblock_is_mirror(struct memblock_region *m) { @@ -296,7 +283,6 @@ phys_addr_t memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid) phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align); -#ifdef CONFIG_MOVABLE_NODE /* * Set the allocation direction to bottom-up or top-down. */ @@ -314,10 +300,6 @@ static inline bool memblock_bottom_up(void) { return memblock.bottom_up; } -#else -static inline void __init memblock_set_bottom_up(bool enable) {} -static inline bool memblock_bottom_up(void) { return false; } -#endif /* Flags for memblock_alloc_base() amd __memblock_alloc_base() */ #define MEMBLOCK_ALLOC_ANYWHERE (~(phys_addr_t)0) diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index f746e44d4046..cf0b91c3ec12 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -387,11 +387,7 @@ enum node_states { #else N_HIGH_MEMORY = N_NORMAL_MEMORY, #endif -#ifdef CONFIG_MOVABLE_NODE N_MEMORY, /* The node has memory(regular, high, movable) */ -#else - N_MEMORY = N_HIGH_MEMORY, -#endif N_CPU, /* The node has one or more cpus */ NR_NODE_STATES }; diff --git a/mm/Kconfig b/mm/Kconfig index 9870baafb096..857f6ef368d4 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -149,32 +149,6 @@ config NO_BOOTMEM config MEMORY_ISOLATION bool -config MOVABLE_NODE - bool "Enable to assign a node which has only movable memory" - depends on HAVE_MEMBLOCK - depends on NO_BOOTMEM - depends on X86_64 || OF_EARLY_FLATTREE || MEMORY_HOTPLUG - depends on NUMA - default n - help - Allow a node to have only movable memory. Pages used by the kernel, - such as direct mapping pages cannot be migrated. So the corresponding - memory device cannot be hotplugged. This option allows the following - two things: - - When the system is booting, node full of hotpluggable memory can - be arranged to have only movable memory so that the whole node can - be hot-removed. (need movable_node boot option specified). - - After the system is up, the option allows users to online all the - memory of a node as movable memory so that the whole node can be - hot-removed. - - Users who don't use the memory hotplug feature are fine with this - option on since they don't specify movable_node boot option or they - don't online memory as movable. - - Say Y here if you want to hotplug a whole node. - Say N here if you want kernel to use memory on all nodes evenly. - # # Only be set on architectures that have completely implemented memory hotplug # feature. If you are not sure, don't touch it. diff --git a/mm/memblock.c b/mm/memblock.c index 7b8a5db76a2f..41eaeebb03dc 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -54,9 +54,7 @@ struct memblock memblock __initdata_memblock = { }; int memblock_debug __initdata_memblock; -#ifdef CONFIG_MOVABLE_NODE bool movable_node_enabled __initdata_memblock = false; -#endif static bool system_has_some_mirror __initdata_memblock = false; static int memblock_can_resize __initdata_memblock; static int memblock_memory_in_slab __initdata_memblock = 0; diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 937319899e61..0dc8cf0a59d7 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1572,11 +1572,7 @@ check_pages_isolated(unsigned long start_pfn, unsigned long end_pfn) static int __init cmdline_parse_movable_node(char *p) { -#ifdef CONFIG_MOVABLE_NODE movable_node_enabled = true; -#else - pr_warn("movable_node option not supported\n"); -#endif return 0; } early_param("movable_node", cmdline_parse_movable_node); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index a35add8d7c0b..bd65b60939b6 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -113,9 +113,7 @@ nodemask_t node_states[NR_NODE_STATES] __read_mostly = { #ifdef CONFIG_HIGHMEM [N_HIGH_MEMORY] = { { [0] = 1UL } }, #endif -#ifdef CONFIG_MOVABLE_NODE [N_MEMORY] = { { [0] = 1UL } }, -#endif [N_CPU] = { { [0] = 1UL } }, #endif /* NUMA */ }; -- cgit v1.3-18-gd494 From a7be6e5a7f8da433065b23f98ff68f445113080a Mon Sep 17 00:00:00 2001 From: Dou Liyang Date: Mon, 10 Jul 2017 15:49:20 -0700 Subject: mm: drop useless local parameters of __register_one_node() __register_one_node() initializes local parameters "p_node" & "parent" for register_node(). But, register_node() does not use them. Remove the related code of "parent" node, cleanup __register_one_node() and register_node(). Link: http://lkml.kernel.org/r/1498013846-20149-1-git-send-email-douly.fnst@cn.fujitsu.com Signed-off-by: Dou Liyang Acked-by: David Rientjes Acked-by: Michal Hocko Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/node.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) (limited to 'drivers/base/node.c') diff --git a/drivers/base/node.c b/drivers/base/node.c index 73d39bc58c42..d8dc83017d8d 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -288,7 +288,7 @@ static void node_device_release(struct device *dev) * * Initialize and register the node device. */ -static int register_node(struct node *node, int num, struct node *parent) +static int register_node(struct node *node, int num) { int error; @@ -567,19 +567,14 @@ static void init_node_hugetlb_work(int nid) { } int __register_one_node(int nid) { - int p_node = parent_node(nid); - struct node *parent = NULL; int error; int cpu; - if (p_node != nid) - parent = node_devices[p_node]; - node_devices[nid] = kzalloc(sizeof(struct node), GFP_KERNEL); if (!node_devices[nid]) return -ENOMEM; - error = register_node(node_devices[nid], nid, parent); + error = register_node(node_devices[nid], nid); /* link cpu under this node */ for_each_present_cpu(cpu) { -- cgit v1.3-18-gd494