02a0e53d82
Elaborate the API for calling cpuset_zone_allowed(), so that users have to explicitly choose between the two variants: cpuset_zone_allowed_hardwall() cpuset_zone_allowed_softwall() Until now, whether or not you got the hardwall flavor depended solely on whether or not you or'd in the __GFP_HARDWALL gfp flag to the gfp_mask argument. If you didn't specify __GFP_HARDWALL, you implicitly got the softwall version. Unfortunately, this meant that users would end up with the softwall version without thinking about it. Since only the softwall version might sleep, this led to bugs with possible sleeping in interrupt context on more than one occassion. The hardwall version requires that the current tasks mems_allowed allows the node of the specified zone (or that you're in interrupt or that __GFP_THISNODE is set or that you're on a one cpuset system.) The softwall version, depending on the gfp_mask, might allow a node if it was allowed in the nearest enclusing cpuset marked mem_exclusive (which requires taking the cpuset lock 'callback_mutex' to evaluate.) This patch removes the cpuset_zone_allowed() call, and forces the caller to explicitly choose between the hardwall and the softwall case. If the caller wants the gfp_mask to determine this choice, they should (1) be sure they can sleep or that __GFP_HARDWALL is set, and (2) invoke the cpuset_zone_allowed_softwall() routine. This adds another 100 or 200 bytes to the kernel text space, due to the few lines of nearly duplicate code at the top of both cpuset_zone_allowed_* routines. It should save a few instructions executed for the calls that turned into calls of cpuset_zone_allowed_hardwall, thanks to not having to set (before the call) then check (within the call) the __GFP_HARDWALL flag. For the most critical call, from get_page_from_freelist(), the same instructions are executed as before -- the old cpuset_zone_allowed() routine it used to call is the same code as the cpuset_zone_allowed_softwall() routine that it calls now. Not a perfect win, but seems worth it, to reduce this chance of hitting a sleeping with irq off complaint again. Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
152 lines
3.8 KiB
C
152 lines
3.8 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);
|
|
#define cpuset_current_mems_allowed (current->mems_allowed)
|
|
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_softwall(struct zone *z, gfp_t gfp_mask);
|
|
extern int __cpuset_zone_allowed_hardwall(struct zone *z, gfp_t gfp_mask);
|
|
|
|
static int inline cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask)
|
|
{
|
|
return number_of_cpusets <= 1 ||
|
|
__cpuset_zone_allowed_softwall(z, gfp_mask);
|
|
}
|
|
|
|
static int inline cpuset_zone_allowed_hardwall(struct zone *z, gfp_t gfp_mask)
|
|
{
|
|
return number_of_cpusets <= 1 ||
|
|
__cpuset_zone_allowed_hardwall(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 const 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;
|
|
}
|
|
|
|
#define cpuset_current_mems_allowed (node_online_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_softwall(struct zone *z, gfp_t gfp_mask)
|
|
{
|
|
return 1;
|
|
}
|
|
|
|
static inline int cpuset_zone_allowed_hardwall(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 */
|