mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-12 23:56:42 +07:00
ad2c814441
Anton noticed (http://www.spinics.net/lists/linux-mm/msg67489.html) that
on ppc LPARs with memoryless nodes, a large amount of memory was consumed
by slabs and was marked unreclaimable. He tracked it down to slab
deactivations in the SLUB core when we allocate remotely, leading to poor
efficiency always when memoryless nodes are present.
After much discussion, Joonsoo provided a few patches that help
significantly. They don't resolve the problem altogether:
- memory hotplug still needs testing, that is when a memoryless node
becomes memory-ful, we want to dtrt
- there are other reasons for going off-node than memoryless nodes,
e.g., fully exhausted local nodes
Neither case is resolved with this series, but I don't think that should
block their acceptance, as they can be explored/resolved with follow-on
patches.
The series consists of:
[1/3] topology: add support for node_to_mem_node() to determine the
fallback node
[2/3] slub: fallback to node_to_mem_node() node if allocating on
memoryless node
- Joonsoo's patches to cache the nearest node with memory for each
NUMA node
[3/3] Partial revert of 81c98869fa (""kthread: ensure locality of
task_struct allocations")
- At Tejun's request, keep the knowledge of memoryless node fallback
to the allocator core.
This patch (of 3):
We need to determine the fallback node in slub allocator if the allocation
target node is memoryless node. Without it, the SLUB wrongly select the
node which has no memory and can't use a partial slab, because of node
mismatch. Introduced function, node_to_mem_node(X), will return a node Y
with memory that has the nearest distance. If X is memoryless node, it
will return nearest distance node, but, if X is normal node, it will
return itself.
We will use this function in following patch to determine the fallback
node.
Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Nishanth Aravamudan <nacc@linux.vnet.ibm.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Han Pingtian <hanpt@linux.vnet.ibm.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Anton Blanchard <anton@samba.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
215 lines
4.9 KiB
C
215 lines
4.9 KiB
C
/*
|
|
* 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
|
|
|
|
#include <linux/cpumask.h>
|
|
#include <linux/bitops.h>
|
|
#include <linux/mmzone.h>
|
|
#include <linux/smp.h>
|
|
#include <linux/percpu.h>
|
|
#include <asm/topology.h>
|
|
|
|
#ifndef node_has_online_mem
|
|
#define node_has_online_mem(nid) (1)
|
|
#endif
|
|
|
|
#ifndef nr_cpus_node
|
|
#define nr_cpus_node(node) cpumask_weight(cpumask_of_node(node))
|
|
#endif
|
|
|
|
#define for_each_node_with_cpus(node) \
|
|
for_each_online_node(node) \
|
|
if (nr_cpus_node(node))
|
|
|
|
int arch_update_cpu_topology(void);
|
|
|
|
/* Conform to ACPI 2.0 SLIT distance definitions */
|
|
#define LOCAL_DISTANCE 10
|
|
#define REMOTE_DISTANCE 20
|
|
#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 zone_reclaim_mode is enabled then the VM will only call zone_reclaim()
|
|
* on nodes within this distance.
|
|
*/
|
|
#define RECLAIM_DISTANCE 30
|
|
#endif
|
|
#ifndef PENALTY_FOR_NODE_WITH_CPUS
|
|
#define PENALTY_FOR_NODE_WITH_CPUS (1)
|
|
#endif
|
|
|
|
#ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID
|
|
DECLARE_PER_CPU(int, numa_node);
|
|
|
|
#ifndef numa_node_id
|
|
/* Returns the number of the current Node. */
|
|
static inline int numa_node_id(void)
|
|
{
|
|
return raw_cpu_read(numa_node);
|
|
}
|
|
#endif
|
|
|
|
#ifndef cpu_to_node
|
|
static inline int cpu_to_node(int cpu)
|
|
{
|
|
return per_cpu(numa_node, cpu);
|
|
}
|
|
#endif
|
|
|
|
#ifndef set_numa_node
|
|
static inline void set_numa_node(int node)
|
|
{
|
|
this_cpu_write(numa_node, node);
|
|
}
|
|
#endif
|
|
|
|
#ifndef set_cpu_numa_node
|
|
static inline void set_cpu_numa_node(int cpu, int node)
|
|
{
|
|
per_cpu(numa_node, cpu) = node;
|
|
}
|
|
#endif
|
|
|
|
#else /* !CONFIG_USE_PERCPU_NUMA_NODE_ID */
|
|
|
|
/* Returns the number of the current Node. */
|
|
#ifndef numa_node_id
|
|
static inline int 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_);
|
|
extern int _node_numa_mem_[MAX_NUMNODES];
|
|
|
|
#ifndef set_numa_mem
|
|
static inline void set_numa_mem(int node)
|
|
{
|
|
this_cpu_write(_numa_mem_, node);
|
|
_node_numa_mem_[numa_node_id()] = node;
|
|
}
|
|
#endif
|
|
|
|
#ifndef node_to_mem_node
|
|
static inline int node_to_mem_node(int node)
|
|
{
|
|
return _node_numa_mem_[node];
|
|
}
|
|
#endif
|
|
|
|
#ifndef numa_mem_id
|
|
/* Returns the number of the nearest Node with memory */
|
|
static inline int numa_mem_id(void)
|
|
{
|
|
return raw_cpu_read(_numa_mem_);
|
|
}
|
|
#endif
|
|
|
|
#ifndef cpu_to_mem
|
|
static inline int cpu_to_mem(int cpu)
|
|
{
|
|
return per_cpu(_numa_mem_, cpu);
|
|
}
|
|
#endif
|
|
|
|
#ifndef set_cpu_numa_mem
|
|
static inline void set_cpu_numa_mem(int cpu, int node)
|
|
{
|
|
per_cpu(_numa_mem_, cpu) = node;
|
|
_node_numa_mem_[cpu_to_node(cpu)] = node;
|
|
}
|
|
#endif
|
|
|
|
#else /* !CONFIG_HAVE_MEMORYLESS_NODES */
|
|
|
|
#ifndef numa_mem_id
|
|
/* Returns the number of the nearest Node with memory */
|
|
static inline int numa_mem_id(void)
|
|
{
|
|
return numa_node_id();
|
|
}
|
|
#endif
|
|
|
|
#ifndef node_to_mem_node
|
|
static inline int node_to_mem_node(int node)
|
|
{
|
|
return node;
|
|
}
|
|
#endif
|
|
|
|
#ifndef cpu_to_mem
|
|
static inline int cpu_to_mem(int cpu)
|
|
{
|
|
return cpu_to_node(cpu);
|
|
}
|
|
#endif
|
|
|
|
#endif /* [!]CONFIG_HAVE_MEMORYLESS_NODES */
|
|
|
|
#ifndef topology_physical_package_id
|
|
#define topology_physical_package_id(cpu) ((void)(cpu), -1)
|
|
#endif
|
|
#ifndef topology_core_id
|
|
#define topology_core_id(cpu) ((void)(cpu), 0)
|
|
#endif
|
|
#ifndef topology_thread_cpumask
|
|
#define topology_thread_cpumask(cpu) cpumask_of(cpu)
|
|
#endif
|
|
#ifndef topology_core_cpumask
|
|
#define topology_core_cpumask(cpu) cpumask_of(cpu)
|
|
#endif
|
|
|
|
#ifdef CONFIG_SCHED_SMT
|
|
static inline const struct cpumask *cpu_smt_mask(int cpu)
|
|
{
|
|
return topology_thread_cpumask(cpu);
|
|
}
|
|
#endif
|
|
|
|
static inline const struct cpumask *cpu_cpu_mask(int cpu)
|
|
{
|
|
return cpumask_of_node(cpu_to_node(cpu));
|
|
}
|
|
|
|
|
|
#endif /* _LINUX_TOPOLOGY_H */
|