* Use new node_to_cpumask_ptr. This creates a pointer to the cpumask for a given node. This definition is in mm patch: asm-generic-add-node_to_cpumask_ptr-macro.patch * Use new set_cpus_allowed_ptr function. Depends on: [mm-patch]: asm-generic-add-node_to_cpumask_ptr-macro.patch [sched-devel]: sched: add new set_cpus_allowed_ptr function [x86/latest]: x86: add cpus_scnprintf function Based on: git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6.git + x86/latest .../x86/linux-2.6-x86.git + sched-devel/latest .../mingo/linux-2.6-sched-devel.git # pci Cc: Greg Kroah-Hartman # sunrpc Cc: Greg Banks # x86 Cc: Thomas Gleixner Cc: Ingo Molnar Cc: H. Peter Anvin Signed-off-by: Mike Travis --- One checkpatch error that I don't think can be fixed (was already in source): ERROR: Macros with complex values should be enclosed in parenthesis #230: FILE: include/linux/topology.h:49: #define for_each_node_with_cpus(node) \ for_each_online_node(node) \ if (nr_cpus_node(node)) --- drivers/base/node.c | 7 ++++--- kernel/sched.c | 29 ++++++++++++++--------------- mm/page_alloc.c | 6 +++--- mm/slab.c | 5 ++--- mm/vmscan.c | 18 ++++++++---------- net/sunrpc/svc.c | 16 +++++++++++----- 6 files changed, 42 insertions(+), 39 deletions(-) --- linux-2.6.x86.orig/drivers/base/node.c +++ linux-2.6.x86/drivers/base/node.c @@ -22,14 +22,15 @@ static struct sysdev_class node_class = static ssize_t node_read_cpumap(struct sys_device * dev, char * buf) { struct node *node_dev = to_node(dev); - cpumask_t mask = node_to_cpumask(node_dev->sysdev.id); + node_to_cpumask_ptr(mask, node_dev->sysdev.id); int len; /* 2004/06/03: buf currently PAGE_SIZE, need > 1 char per 4 bits. */ BUILD_BUG_ON(MAX_NUMNODES/4 > PAGE_SIZE/2); - len = cpumask_scnprintf(buf, PAGE_SIZE-1, mask); - len += sprintf(buf + len, "\n"); + len = cpumask_scnprintf(buf, PAGE_SIZE-2, *mask); + buf[len++] = '\n'; + buf[len] = '\0'; return len; } --- linux-2.6.x86.orig/kernel/sched.c +++ linux-2.6.x86/kernel/sched.c @@ -6484,7 +6484,7 @@ init_sched_build_groups(cpumask_t span, * * Should use nodemask_t. */ -static int find_next_best_node(int node, unsigned long *used_nodes) +static int find_next_best_node(int node, nodemask_t *used_nodes) { int i, n, val, min_val, best_node = 0; @@ -6498,7 +6498,7 @@ static int find_next_best_node(int node, continue; /* Skip already used nodes */ - if (test_bit(n, used_nodes)) + if (node_isset(n, *used_nodes)) continue; /* Simple min distance search */ @@ -6510,14 +6510,13 @@ static int find_next_best_node(int node, } } - set_bit(best_node, used_nodes); + node_set(best_node, *used_nodes); return best_node; } /** * sched_domain_node_span - get a cpumask for a node's sched_domain * @node: node whose cpumask we're constructing - * @size: number of nodes to include in this span * * Given a node, construct a good cpumask for its sched_domain to span. It * should be one that prevents unnecessary balancing, but also spreads tasks @@ -6525,22 +6524,22 @@ static int find_next_best_node(int node, */ static cpumask_t sched_domain_node_span(int node) { - DECLARE_BITMAP(used_nodes, MAX_NUMNODES); - cpumask_t span, nodemask; + nodemask_t used_nodes; + cpumask_t span; + node_to_cpumask_ptr(nodemask, node); int i; cpus_clear(span); - bitmap_zero(used_nodes, MAX_NUMNODES); + nodes_clear(used_nodes); - nodemask = node_to_cpumask(node); - cpus_or(span, span, nodemask); - set_bit(node, used_nodes); + cpus_or(span, span, *nodemask); + node_set(node, used_nodes); for (i = 1; i < SD_NODES_PER_DOMAIN; i++) { - int next_node = find_next_best_node(node, used_nodes); + int next_node = find_next_best_node(node, &used_nodes); - nodemask = node_to_cpumask(next_node); - cpus_or(span, span, nodemask); + node_to_cpumask_ptr_next(nodemask, next_node); + cpus_or(span, span, *nodemask); } return span; @@ -6937,6 +6936,7 @@ static int build_sched_domains(const cpu for (j = 0; j < MAX_NUMNODES; j++) { cpumask_t tmp, notcovered; int n = (i + j) % MAX_NUMNODES; + node_to_cpumask_ptr(pnodemask, n); cpus_complement(notcovered, covered); cpus_and(tmp, notcovered, *cpu_map); @@ -6944,8 +6944,7 @@ static int build_sched_domains(const cpu if (cpus_empty(tmp)) break; - nodemask = node_to_cpumask(n); - cpus_and(tmp, tmp, nodemask); + cpus_and(tmp, tmp, *pnodemask); if (cpus_empty(tmp)) continue; --- linux-2.6.x86.orig/mm/page_alloc.c +++ linux-2.6.x86/mm/page_alloc.c @@ -2029,6 +2029,7 @@ static int find_next_best_node(int node, int n, val; int min_val = INT_MAX; int best_node = -1; + node_to_cpumask_ptr(tmp, 0); /* Use the local node if we haven't already */ if (!node_isset(node, *used_node_mask)) { @@ -2037,7 +2038,6 @@ static int find_next_best_node(int node, } for_each_node_state(n, N_HIGH_MEMORY) { - cpumask_t tmp; /* Don't want a node to appear more than once */ if (node_isset(n, *used_node_mask)) @@ -2050,8 +2050,8 @@ static int find_next_best_node(int node, val += (n < node); /* Give preference to headless and unused nodes */ - tmp = node_to_cpumask(n); - if (!cpus_empty(tmp)) + node_to_cpumask_ptr_next(tmp, n); + if (!cpus_empty(*tmp)) val += PENALTY_FOR_NODE_WITH_CPUS; /* Slight preference for less loaded node */ --- linux-2.6.x86.orig/mm/slab.c +++ linux-2.6.x86/mm/slab.c @@ -1160,14 +1160,13 @@ static void __cpuinit cpuup_canceled(lon struct kmem_cache *cachep; struct kmem_list3 *l3 = NULL; int node = cpu_to_node(cpu); + node_to_cpumask_ptr(mask, node); list_for_each_entry(cachep, &cache_chain, next) { struct array_cache *nc; struct array_cache *shared; struct array_cache **alien; - cpumask_t mask; - mask = node_to_cpumask(node); /* cpu is dead; no one can alloc from it. */ nc = cachep->array[cpu]; cachep->array[cpu] = NULL; @@ -1183,7 +1182,7 @@ static void __cpuinit cpuup_canceled(lon if (nc) free_block(cachep, nc->entry, nc->avail, node); - if (!cpus_empty(mask)) { + if (!cpus_empty(*mask)) { spin_unlock_irq(&l3->list_lock); goto free_array_cache; } --- linux-2.6.x86.orig/mm/vmscan.c +++ linux-2.6.x86/mm/vmscan.c @@ -1647,11 +1647,10 @@ static int kswapd(void *p) struct reclaim_state reclaim_state = { .reclaimed_slab = 0, }; - cpumask_t cpumask; + node_to_cpumask_ptr(cpumask, pgdat->node_id); - cpumask = node_to_cpumask(pgdat->node_id); - if (!cpus_empty(cpumask)) - set_cpus_allowed(tsk, cpumask); + if (!cpus_empty(*cpumask)) + set_cpus_allowed_ptr(tsk, cpumask); current->reclaim_state = &reclaim_state; /* @@ -1880,17 +1879,16 @@ out: static int __devinit cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { - pg_data_t *pgdat; - cpumask_t mask; int nid; if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN) { for_each_node_state(nid, N_HIGH_MEMORY) { - pgdat = NODE_DATA(nid); - mask = node_to_cpumask(pgdat->node_id); - if (any_online_cpu(mask) != NR_CPUS) + pg_data_t *pgdat = NODE_DATA(nid); + node_to_cpumask_ptr(mask, pgdat->node_id); + + if (any_online_cpu(*mask) < nr_cpu_ids) /* One of our CPUs online: restore mask */ - set_cpus_allowed(pgdat->kswapd, mask); + set_cpus_allowed_ptr(pgdat->kswapd, mask); } } return NOTIFY_OK; --- linux-2.6.x86.orig/net/sunrpc/svc.c +++ linux-2.6.x86/net/sunrpc/svc.c @@ -301,7 +301,6 @@ static inline int svc_pool_map_set_cpumask(unsigned int pidx, cpumask_t *oldmask) { struct svc_pool_map *m = &svc_pool_map; - unsigned int node; /* or cpu */ /* * The caller checks for sv_nrpools > 1, which @@ -314,16 +313,23 @@ svc_pool_map_set_cpumask(unsigned int pi default: return 0; case SVC_POOL_PERCPU: - node = m->pool_to[pidx]; + { + unsigned int cpu = m->pool_to[pidx]; + *oldmask = current->cpus_allowed; - set_cpus_allowed(current, cpumask_of_cpu(node)); + set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu)); return 1; + } case SVC_POOL_PERNODE: - node = m->pool_to[pidx]; + { + unsigned int node = m->pool_to[pidx]; + node_to_cpumask_ptr(nodecpumask, node); + *oldmask = current->cpus_allowed; - set_cpus_allowed(current, node_to_cpumask(node)); + set_cpus_allowed_ptr(current, nodecpumask); return 1; } + } } /* -- -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/