From: Lee Schermerhorn Here's a cut at fixing up uses of the online node map in generic code. mm/shmem.c:shmem_parse_mpol() Ensure nodelist is subset of nodes with memory. Use node_states[N_HIGH_MEMORY] as default for missing nodelist for interleave policy. mm/shmem.c:shmem_fill_super() initialize policy_nodes to node_states[N_HIGH_MEMORY] mm/page-writeback.c:highmem_dirtyable_memory() sum over nodes with memory mm/page_alloc.c:zlc_setup() allowednodes - use nodes with memory. mm/page_alloc.c:default_zonelist_order() average over nodes with memory. mm/page_alloc.c:find_next_best_node() skip nodes w/o memory. N_HIGH_MEMORY state mask may not be initialized at this time, unless we want to depend on early_calculate_totalpages() [see below]. Will ZONE_MOVABLE ever be configurable? mm/page_alloc.c:find_zone_movable_pfns_for_nodes() spread kernelcore over nodes with memory. This required calling early_calculate_totalpages() unconditionally, and populating N_HIGH_MEMORY node state therein from nodes in the early_node_map[]. If we can depend on this, we can eliminate the population of N_HIGH_MEMORY mask from __build_all_zonelists() and use the N_HIGH_MEMORY mask in find_next_best_node(). mm/mempolicy.c:mpol_check_policy() Ensure nodes specified for policy are subset of nodes with memory. Signed-off-by: Lee Schermerhorn Acked-by: Christoph Lameter Signed-off-by: Andrew Morton --- mm/mempolicy.c | 2 +- mm/page-writeback.c | 2 +- mm/page_alloc.c | 38 ++++++++++++++++++++++++++++---------- mm/shmem.c | 13 ++++++++----- 4 files changed, 38 insertions(+), 17 deletions(-) diff -puN mm/mempolicy.c~memoryless-nodes-fixup-uses-of-node_online_map-in-generic-code mm/mempolicy.c --- a/mm/mempolicy.c~memoryless-nodes-fixup-uses-of-node_online_map-in-generic-code +++ a/mm/mempolicy.c @@ -126,7 +126,7 @@ static int mpol_check_policy(int mode, n return -EINVAL; break; } - return nodes_subset(*nodes, node_online_map) ? 0 : -EINVAL; + return nodes_subset(*nodes, node_states[N_HIGH_MEMORY]) ? 0 : -EINVAL; } /* Generate a custom zonelist for the BIND policy. */ diff -puN mm/page-writeback.c~memoryless-nodes-fixup-uses-of-node_online_map-in-generic-code mm/page-writeback.c --- a/mm/page-writeback.c~memoryless-nodes-fixup-uses-of-node_online_map-in-generic-code +++ a/mm/page-writeback.c @@ -126,7 +126,7 @@ static unsigned long highmem_dirtyable_m int node; unsigned long x = 0; - for_each_online_node(node) { + for_each_node_state(node, N_HIGH_MEMORY) { struct zone *z = &NODE_DATA(node)->node_zones[ZONE_HIGHMEM]; diff -puN mm/page_alloc.c~memoryless-nodes-fixup-uses-of-node_online_map-in-generic-code mm/page_alloc.c --- a/mm/page_alloc.c~memoryless-nodes-fixup-uses-of-node_online_map-in-generic-code +++ a/mm/page_alloc.c @@ -1052,7 +1052,7 @@ int zone_watermark_ok(struct zone *z, in * * If the zonelist cache is present in the passed in zonelist, then * returns a pointer to the allowed node mask (either the current - * tasks mems_allowed, or node_online_map.) + * tasks mems_allowed, or node_states[N_HIGH_MEMORY].) * * If the zonelist cache is not available for this zonelist, does * nothing and returns NULL. @@ -1081,7 +1081,7 @@ static nodemask_t *zlc_setup(struct zone allowednodes = !in_interrupt() && (alloc_flags & ALLOC_CPUSET) ? &cpuset_current_mems_allowed : - &node_online_map; + &node_states[N_HIGH_MEMORY]; return allowednodes; } @@ -1815,8 +1815,17 @@ static int find_next_best_node(int node, } for_each_online_node(n) { + pg_data_t *pgdat = NODE_DATA(n); cpumask_t tmp; + /* + * skip nodes w/o memory. + * Note: N_HIGH_MEMORY state not guaranteed to be + * populated yet. + */ + if (pgdat->node_present_pages) + continue; + /* Don't want a node to appear more than once */ if (node_isset(n, *used_node_mask)) continue; @@ -1951,7 +1960,8 @@ static int default_zonelist_order(void) * If there is a node whose DMA/DMA32 memory is very big area on * local memory, NODE_ORDER may be suitable. */ - average_size = total_size / (num_online_nodes() + 1); + average_size = total_size / + (nodes_weight(node_states[N_HIGH_MEMORY]) + 1); for_each_online_node(nid) { low_kmem_size = 0; total_size = 0; @@ -3294,16 +3304,24 @@ unsigned long __init find_max_pfn_with_a return max_pfn; } +/* + * early_calculate_totalpages() + * Sum pages in active regions for movable zone. + * Populate N_HIGH_MEMORY for calculating usable_nodes. + */ unsigned long __init early_calculate_totalpages(void) { int i; unsigned long totalpages = 0; - for (i = 0; i < nr_nodemap_entries; i++) - totalpages += early_node_map[i].end_pfn - + for (i = 0; i < nr_nodemap_entries; i++) { + unsigned long pages = early_node_map[i].end_pfn - early_node_map[i].start_pfn; - - return totalpages; + totalpages += pages; + if (pages) + node_set_state(early_node_map[i].nid, N_HIGH_MEMORY); + } + return totalpages; } /* @@ -3317,7 +3335,8 @@ void __init find_zone_movable_pfns_for_n int i, nid; unsigned long usable_startpfn; unsigned long kernelcore_node, kernelcore_remaining; - int usable_nodes = num_online_nodes(); + unsigned long totalpages = early_calculate_totalpages(); + int usable_nodes = nodes_weight(node_states[N_HIGH_MEMORY]); /* * If movablecore was specified, calculate what size of @@ -3328,7 +3347,6 @@ void __init find_zone_movable_pfns_for_n * what movablecore would have allowed. */ if (required_movablecore) { - unsigned long totalpages = early_calculate_totalpages(); unsigned long corepages; /* @@ -3353,7 +3371,7 @@ void __init find_zone_movable_pfns_for_n restart: /* Spread kernelcore memory as evenly as possible throughout nodes */ kernelcore_node = required_kernelcore / usable_nodes; - for_each_online_node(nid) { + for_each_node_state(nid, N_HIGH_MEMORY) { /* * Recalculate kernelcore_node if the division per node * now exceeds what is necessary to satisfy the requested diff -puN mm/shmem.c~memoryless-nodes-fixup-uses-of-node_online_map-in-generic-code mm/shmem.c --- a/mm/shmem.c~memoryless-nodes-fixup-uses-of-node_online_map-in-generic-code +++ a/mm/shmem.c @@ -971,7 +971,7 @@ static inline int shmem_parse_mpol(char *nodelist++ = '\0'; if (nodelist_parse(nodelist, *policy_nodes)) goto out; - if (!nodes_subset(*policy_nodes, node_online_map)) + if (!nodes_subset(*policy_nodes, node_states[N_HIGH_MEMORY])) goto out; } if (!strcmp(value, "default")) { @@ -996,9 +996,11 @@ static inline int shmem_parse_mpol(char err = 0; } else if (!strcmp(value, "interleave")) { *policy = MPOL_INTERLEAVE; - /* Default to nodes online if no nodelist */ + /* + * Default to online nodes with memory if no nodelist + */ if (!nodelist) - *policy_nodes = node_online_map; + *policy_nodes = node_states[N_HIGH_MEMORY]; err = 0; } out: @@ -1060,7 +1062,8 @@ shmem_alloc_page(gfp_t gfp, struct shmem return page; } #else -static inline int shmem_parse_mpol(char *value, int *policy, nodemask_t *policy_nodes) +static inline int shmem_parse_mpol(char *value, int *policy, + nodemask_t *policy_nodes) { return 1; } @@ -2239,7 +2242,7 @@ static int shmem_fill_super(struct super unsigned long blocks = 0; unsigned long inodes = 0; int policy = MPOL_DEFAULT; - nodemask_t policy_nodes = node_online_map; + nodemask_t policy_nodes = node_states[N_HIGH_MEMORY]; #ifdef CONFIG_TMPFS /* _