/* * include/linux/topology.h * * Written by: Matthew Dobson, IBM Corporation * * Copyright (C) 2002, IBM Corp. * * All rights reserved. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. * * This program is distributed in the hope that it will be useful, but * WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or * NON INFRINGEMENT. See the GNU General Public License for more * details. * * You should have received a copy of the GNU General Public License * along with this program; if not, write to the Free Software * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. * * Send feedback to <colpatch@us.ibm.com>
*/ #ifndef _LINUX_TOPOLOGY_H #define _LINUX_TOPOLOGY_H
/* Conform to ACPI 2.0 SLIT distance definitions */ #define LOCAL_DISTANCE 10 #define REMOTE_DISTANCE 20 #define DISTANCE_BITS 8 #ifndef node_distance #define node_distance(from,to) ((from) == (to) ? LOCAL_DISTANCE : REMOTE_DISTANCE) #endif #ifndef RECLAIM_DISTANCE /* * If the distance between nodes in a system is larger than RECLAIM_DISTANCE * (in whatever arch specific measurement units returned by node_distance()) * and node_reclaim_mode is enabled then the VM will only call node_reclaim() * on nodes within this distance.
*/ #define RECLAIM_DISTANCE 30 #endif
/* * The following tunable allows platforms to override the default node * reclaim distance (RECLAIM_DISTANCE) if remote memory accesses are * sufficiently fast that the default value actually hurts * performance. * * AMD EPYC machines use this because even though the 2-hop distance * is 32 (3.2x slower than a local memory access) performance actually * *improves* if allowed to reclaim memory and load balance tasks * between NUMA nodes 2-hops apart.
*/ externint __read_mostly node_reclaim_distance;
/* Returns the number of the current Node. */ #ifndef numa_node_id staticinlineint numa_node_id(void)
{ return cpu_to_node(raw_smp_processor_id());
} #endif
#endif/* [!]CONFIG_USE_PERCPU_NUMA_NODE_ID */
#ifdef CONFIG_HAVE_MEMORYLESS_NODES
/* * N.B., Do NOT reference the '_numa_mem_' per cpu variable directly. * It will not be defined when CONFIG_HAVE_MEMORYLESS_NODES is not defined. * Use the accessor functions set_numa_mem(), numa_mem_id() and cpu_to_mem().
*/
DECLARE_PER_CPU(int, _numa_mem_);
#ifndef numa_mem_id /* Returns the number of the nearest Node with memory */ staticinlineint numa_mem_id(void)
{ return raw_cpu_read(_numa_mem_);
} #endif
staticinlinebool topology_is_primary_thread(unsignedint cpu)
{ /* * When disabling SMT, the primary thread of the SMT will remain * enabled/active. Architectures that have a special primary thread * (e.g. x86) need to override this function. Otherwise the first * thread in the SMT can be made the primary thread. * * The sibling cpumask of an offline CPU always contains the CPU * itself on architectures using the implementation of * CONFIG_GENERIC_ARCH_TOPOLOGY for building their topology. * Other architectures not using CONFIG_GENERIC_ARCH_TOPOLOGY for * building their topology have to check whether to use this default * implementation or to override it.
*/ return cpu == cpumask_first(topology_sibling_cpumask(cpu));
} #define topology_is_primary_thread topology_is_primary_thread
/** * for_each_node_numadist() - iterate over nodes in increasing distance * order, starting from a given node * @node: the iteration variable and the starting node. * @unvisited: a nodemask to keep track of the unvisited nodes. * * This macro iterates over NUMA node IDs in increasing distance from the * starting @node and yields MAX_NUMNODES when all the nodes have been * visited. * * Note that by the time the loop completes, the @unvisited nodemask will * be fully cleared, unless the loop exits early. * * The difference between for_each_node() and for_each_node_numadist() is * that the former allows to iterate over nodes in numerical order, whereas * the latter iterates over nodes in increasing order of distance. * * This complexity of this iterator is O(N^2), where N represents the * number of nodes, as each iteration involves scanning all nodes to * find the one with the shortest distance. * * Requires rcu_lock to be held.
*/ #define for_each_node_numadist(node, unvisited) \ for (int __start = (node), \
(node) = nearest_node_nodemask((__start), &(unvisited)); \
(node) < MAX_NUMNODES; \
node_clear((node), (unvisited)), \
(node) = nearest_node_nodemask((__start), &(unvisited)))
/** * for_each_numa_hop_mask - iterate over cpumasks of increasing NUMA distance * from a given node. * @mask: the iteration variable. * @node: the NUMA node to start the search from. * * Requires rcu_lock to be held. * * Yields cpu_online_mask for @node == NUMA_NO_NODE.
*/ #define for_each_numa_hop_mask(mask, node) \ for (unsignedint __hops = 0; \
mask = (node != NUMA_NO_NODE || __hops) ? \
sched_numa_hop_mask(node, __hops) : \
cpu_online_mask, \
!IS_ERR_OR_NULL(mask); \
__hops++)
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.