linux_dsm_epyc7002/include/linux/cpuset.h
Paul Jackson 38837fc75a [PATCH] cpuset: top_cpuset tracks hotplug changes to node_online_map
Change the list of memory nodes allowed to tasks in the top (root) nodeset
to dynamically track what cpus are online, using a call to a cpuset hook
from the memory hotplug code.  Make this top cpus file read-only.

On systems that have cpusets configured in their kernel, but that aren't
actively using cpusets (for some distros, this covers the majority of
systems) all tasks end up in the top cpuset.

If that system does support memory hotplug, then these tasks cannot make
use of memory nodes that are added after system boot, because the memory
nodes are not allowed in the top cpuset.  This is a surprising regression
over earlier kernels that didn't have cpusets enabled.

One key motivation for this change is to remain consistent with the
behaviour for the top_cpuset's 'cpus', which is also read-only, and which
automatically tracks the cpu_online_map.

This change also has the minor benefit that it fixes a long standing,
little noticed, minor bug in cpusets.  The cpuset performance tweak to
short circuit the cpuset_zone_allowed() check on systems with just a single
cpuset (see 'number_of_cpusets', in linux/cpuset.h) meant that simply
changing the 'mems' of the top_cpuset had no affect, even though the change
(the write system call) appeared to succeed.  With the following change,
that write to the 'mems' file fails -EACCES, and the 'mems' file stubbornly
refuses to be changed via user space writes.  Thus no one should be mislead
into thinking they've changed the top_cpusets's 'mems' when in affect they
haven't.

In order to keep the behaviour of cpusets consistent between systems
actively making use of them and systems not using them, this patch changes
the behaviour of the 'mems' file in the top (root) cpuset, making it read
only, and making it automatically track the value of node_online_map.  Thus
tasks in the top cpuset will have automatic use of hot plugged memory nodes
allowed by their cpuset.

[akpm@osdl.org: build fix]
[bunk@stusta.de: build fix]
Signed-off-by: Paul Jackson <pj@sgi.com>
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-29 09:18:21 -07:00

136 lines
3.3 KiB
C

#ifndef _LINUX_CPUSET_H
#define _LINUX_CPUSET_H
/*
* cpuset interface
*
* Copyright (C) 2003 BULL SA
* Copyright (C) 2004-2006 Silicon Graphics, Inc.
*
*/
#include <linux/sched.h>
#include <linux/cpumask.h>
#include <linux/nodemask.h>
#ifdef CONFIG_CPUSETS
extern int number_of_cpusets; /* How many cpusets are defined in system? */
extern int cpuset_init_early(void);
extern int cpuset_init(void);
extern void cpuset_init_smp(void);
extern void cpuset_fork(struct task_struct *p);
extern void cpuset_exit(struct task_struct *p);
extern cpumask_t cpuset_cpus_allowed(struct task_struct *p);
extern nodemask_t cpuset_mems_allowed(struct task_struct *p);
void cpuset_init_current_mems_allowed(void);
void cpuset_update_task_memory_state(void);
#define cpuset_nodes_subset_current_mems_allowed(nodes) \
nodes_subset((nodes), current->mems_allowed)
int cpuset_zonelist_valid_mems_allowed(struct zonelist *zl);
extern int __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask);
static int inline cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask)
{
return number_of_cpusets <= 1 || __cpuset_zone_allowed(z, gfp_mask);
}
extern int cpuset_excl_nodes_overlap(const struct task_struct *p);
#define cpuset_memory_pressure_bump() \
do { \
if (cpuset_memory_pressure_enabled) \
__cpuset_memory_pressure_bump(); \
} while (0)
extern int cpuset_memory_pressure_enabled;
extern void __cpuset_memory_pressure_bump(void);
extern struct file_operations proc_cpuset_operations;
extern char *cpuset_task_status_allowed(struct task_struct *task, char *buffer);
extern void cpuset_lock(void);
extern void cpuset_unlock(void);
extern int cpuset_mem_spread_node(void);
static inline int cpuset_do_page_mem_spread(void)
{
return current->flags & PF_SPREAD_PAGE;
}
static inline int cpuset_do_slab_mem_spread(void)
{
return current->flags & PF_SPREAD_SLAB;
}
extern void cpuset_track_online_nodes(void);
#else /* !CONFIG_CPUSETS */
static inline int cpuset_init_early(void) { return 0; }
static inline int cpuset_init(void) { return 0; }
static inline void cpuset_init_smp(void) {}
static inline void cpuset_fork(struct task_struct *p) {}
static inline void cpuset_exit(struct task_struct *p) {}
static inline cpumask_t cpuset_cpus_allowed(struct task_struct *p)
{
return cpu_possible_map;
}
static inline nodemask_t cpuset_mems_allowed(struct task_struct *p)
{
return node_possible_map;
}
static inline void cpuset_init_current_mems_allowed(void) {}
static inline void cpuset_update_task_memory_state(void) {}
#define cpuset_nodes_subset_current_mems_allowed(nodes) (1)
static inline int cpuset_zonelist_valid_mems_allowed(struct zonelist *zl)
{
return 1;
}
static inline int cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask)
{
return 1;
}
static inline int cpuset_excl_nodes_overlap(const struct task_struct *p)
{
return 1;
}
static inline void cpuset_memory_pressure_bump(void) {}
static inline char *cpuset_task_status_allowed(struct task_struct *task,
char *buffer)
{
return buffer;
}
static inline void cpuset_lock(void) {}
static inline void cpuset_unlock(void) {}
static inline int cpuset_mem_spread_node(void)
{
return 0;
}
static inline int cpuset_do_page_mem_spread(void)
{
return 0;
}
static inline int cpuset_do_slab_mem_spread(void)
{
return 0;
}
static inline void cpuset_track_online_nodes(void) {}
#endif /* !CONFIG_CPUSETS */
#endif /* _LINUX_CPUSET_H */