diff options
| -rw-r--r-- | mm/migrate.c | 164 |
1 files changed, 129 insertions, 35 deletions
diff --git a/mm/migrate.c b/mm/migrate.c index 6f04aa2a3bd4..9d2642a34018 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -50,6 +50,7 @@ #include <linux/ptrace.h> #include <linux/oom.h> #include <linux/memory.h> +#include <linux/random.h> #include <asm/tlbflush.h> @@ -1118,12 +1119,25 @@ out: * * This is represented in the node_demotion[] like this: * - * { 1, // Node 0 migrates to 1 - * 2, // Node 1 migrates to 2 - * -1, // Node 2 does not migrate - * 4, // Node 3 migrates to 4 - * 5, // Node 4 migrates to 5 - * -1} // Node 5 does not migrate + * { nr=1, nodes[0]=1 }, // Node 0 migrates to 1 + * { nr=1, nodes[0]=2 }, // Node 1 migrates to 2 + * { nr=0, nodes[0]=-1 }, // Node 2 does not migrate + * { nr=1, nodes[0]=4 }, // Node 3 migrates to 4 + * { nr=1, nodes[0]=5 }, // Node 4 migrates to 5 + * { nr=0, nodes[0]=-1 }, // Node 5 does not migrate + * + * Moreover some systems may have multiple slow memory nodes. + * Suppose a system has one socket with 3 memory nodes, node 0 + * is fast memory type, and node 1/2 both are slow memory + * type, and the distance between fast memory node and slow + * memory node is same. So the migration path should be: + * + * 0 -> 1/2 -> stop + * + * This is represented in the node_demotion[] like this: + * { nr=2, {nodes[0]=1, nodes[1]=2} }, // Node 0 migrates to node 1 and node 2 + * { nr=0, nodes[0]=-1, }, // Node 1 dose not migrate + * { nr=0, nodes[0]=-1, }, // Node 2 does not migrate */ /* @@ -1134,8 +1148,20 @@ out: * must be held over all reads to ensure that no cycles are * observed. */ -static int node_demotion[MAX_NUMNODES] __read_mostly = - {[0 ... MAX_NUMNODES - 1] = NUMA_NO_NODE}; +#define DEFAULT_DEMOTION_TARGET_NODES 15 + +#if MAX_NUMNODES < DEFAULT_DEMOTION_TARGET_NODES +#define DEMOTION_TARGET_NODES (MAX_NUMNODES - 1) +#else +#define DEMOTION_TARGET_NODES DEFAULT_DEMOTION_TARGET_NODES +#endif + +struct demotion_nodes { + unsigned short nr; + short nodes[DEMOTION_TARGET_NODES]; +}; + +static struct demotion_nodes *node_demotion __read_mostly; /** * next_demotion_node() - Get the next node in the demotion path @@ -1148,8 +1174,15 @@ static int node_demotion[MAX_NUMNODES] __read_mostly = */ int next_demotion_node(int node) { + struct demotion_nodes *nd; + unsigned short target_nr, index; int target; + if (!node_demotion) + return NUMA_NO_NODE; + + nd = &node_demotion[node]; + /* * node_demotion[] is updated without excluding this * function from running. RCU doesn't provide any @@ -1160,9 +1193,28 @@ int next_demotion_node(int node) * node_demotion[] reads need to be consistent. */ rcu_read_lock(); - target = READ_ONCE(node_demotion[node]); - rcu_read_unlock(); + target_nr = READ_ONCE(nd->nr); + switch (target_nr) { + case 0: + target = NUMA_NO_NODE; + goto out; + case 1: + index = 0; + break; + default: + /* + * If there are multiple target nodes, just select one + * target node randomly. + */ + index = get_random_int() % target_nr; + break; + } + + target = READ_ONCE(nd->nodes[index]); + +out: + rcu_read_unlock(); return target; } @@ -3003,10 +3055,16 @@ EXPORT_SYMBOL(migrate_vma_finalize); /* Disable reclaim-based migration. */ static void __disable_all_migrate_targets(void) { - int node; + int node, i; - for_each_online_node(node) - node_demotion[node] = NUMA_NO_NODE; + if (!node_demotion) + return; + + for_each_online_node(node) { + node_demotion[node].nr = 0; + for (i = 0; i < DEMOTION_TARGET_NODES; i++) + node_demotion[node].nodes[i] = NUMA_NO_NODE; + } } static void disable_all_migrate_targets(void) @@ -3033,26 +3091,40 @@ static void disable_all_migrate_targets(void) * Failing here is OK. It might just indicate * being at the end of a chain. */ -static int establish_migrate_target(int node, nodemask_t *used) +static int establish_migrate_target(int node, nodemask_t *used, + int best_distance) { - int migration_target; + int migration_target, index, val; + struct demotion_nodes *nd; - /* - * Can not set a migration target on a - * node with it already set. - * - * No need for READ_ONCE() here since this - * in the write path for node_demotion[]. - * This should be the only thread writing. - */ - if (node_demotion[node] != NUMA_NO_NODE) + if (!node_demotion) return NUMA_NO_NODE; + nd = &node_demotion[node]; + migration_target = find_next_best_node(node, used); if (migration_target == NUMA_NO_NODE) return NUMA_NO_NODE; - node_demotion[node] = migration_target; + /* + * If the node has been set a migration target node before, + * which means it's the best distance between them. Still + * check if this node can be demoted to other target nodes + * if they have a same best distance. + */ + if (best_distance != -1) { + val = node_distance(node, migration_target); + if (val > best_distance) + return NUMA_NO_NODE; + } + + index = nd->nr; + if (WARN_ONCE(index >= DEMOTION_TARGET_NODES, + "Exceeds maximum demotion target nodes\n")) + return NUMA_NO_NODE; + + nd->nodes[index] = migration_target; + nd->nr++; return migration_target; } @@ -3068,7 +3140,9 @@ static int establish_migrate_target(int node, nodemask_t *used) * * The difference here is that cycles must be avoided. If * node0 migrates to node1, then neither node1, nor anything - * node1 migrates to can migrate to node0. + * node1 migrates to can migrate to node0. Also one node can + * be migrated to multiple nodes if the target nodes all have + * a same best-distance against the source node. * * This function can run simultaneously with readers of * node_demotion[]. However, it can not run simultaneously @@ -3080,7 +3154,7 @@ static void __set_migration_target_nodes(void) nodemask_t next_pass = NODE_MASK_NONE; nodemask_t this_pass = NODE_MASK_NONE; nodemask_t used_targets = NODE_MASK_NONE; - int node; + int node, best_distance; /* * Avoid any oddities like cycles that could occur @@ -3109,18 +3183,33 @@ again: * multiple source nodes to share a destination. */ nodes_or(used_targets, used_targets, this_pass); - for_each_node_mask(node, this_pass) { - int target_node = establish_migrate_target(node, &used_targets); - if (target_node == NUMA_NO_NODE) - continue; + for_each_node_mask(node, this_pass) { + best_distance = -1; /* - * Visit targets from this pass in the next pass. - * Eventually, every node will have been part of - * a pass, and will become set in 'used_targets'. + * Try to set up the migration path for the node, and the target + * migration nodes can be multiple, so doing a loop to find all + * the target nodes if they all have a best node distance. */ - node_set(target_node, next_pass); + do { + int target_node = + establish_migrate_target(node, &used_targets, + best_distance); + + if (target_node == NUMA_NO_NODE) + break; + + if (best_distance == -1) + best_distance = node_distance(node, target_node); + + /* + * Visit targets from this pass in the next pass. + * Eventually, every node will have been part of + * a pass, and will become set in 'used_targets'. + */ + node_set(target_node, next_pass); + } while (1); } /* * 'next_pass' contains nodes which became migration @@ -3221,6 +3310,11 @@ static int __init migrate_on_reclaim_init(void) { int ret; + node_demotion = kmalloc_array(nr_node_ids, + sizeof(struct demotion_nodes), + GFP_KERNEL); + WARN_ON(!node_demotion); + ret = cpuhp_setup_state_nocalls(CPUHP_MM_DEMOTION_DEAD, "mm/demotion:offline", NULL, migration_offline_cpu); /* |