mirror of
https://github.com/edk2-porting/linux-next.git
synced 2024-12-27 22:53:55 +08:00
2a1e274acf
The following 8 patches against 2.6.20-mm2 create a zone called ZONE_MOVABLE that is only usable by allocations that specify both __GFP_HIGHMEM and __GFP_MOVABLE. This has the effect of keeping all non-movable pages within a single memory partition while allowing movable allocations to be satisfied from either partition. The patches may be applied with the list-based anti-fragmentation patches that groups pages together based on mobility. The size of the zone is determined by a kernelcore= parameter specified at boot-time. This specifies how much memory is usable by non-movable allocations and the remainder is used for ZONE_MOVABLE. Any range of pages within ZONE_MOVABLE can be released by migrating the pages or by reclaiming. When selecting a zone to take pages from for ZONE_MOVABLE, there are two things to consider. First, only memory from the highest populated zone is used for ZONE_MOVABLE. On the x86, this is probably going to be ZONE_HIGHMEM but it would be ZONE_DMA on ppc64 or possibly ZONE_DMA32 on x86_64. Second, the amount of memory usable by the kernel will be spread evenly throughout NUMA nodes where possible. If the nodes are not of equal size, the amount of memory usable by the kernel on some nodes may be greater than others. By default, the zone is not as useful for hugetlb allocations because they are pinned and non-migratable (currently at least). A sysctl is provided that allows huge pages to be allocated from that zone. This means that the huge page pool can be resized to the size of ZONE_MOVABLE during the lifetime of the system assuming that pages are not mlocked. Despite huge pages being non-movable, we do not introduce additional external fragmentation of note as huge pages are always the largest contiguous block we care about. Credit goes to Andy Whitcroft for catching a large variety of problems during review of the patches. This patch creates an additional zone, ZONE_MOVABLE. This zone is only usable by allocations which specify both __GFP_HIGHMEM and __GFP_MOVABLE. Hot-added memory continues to be placed in their existing destination as there is no mechanism to redirect them to a specific zone. [y-goto@jp.fujitsu.com: Fix section mismatch of memory hotplug related code] [akpm@linux-foundation.org: various fixes] Signed-off-by: Mel Gorman <mel@csn.ul.ie> Cc: Andy Whitcroft <apw@shadowen.org> Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com> Cc: William Lee Irwin III <wli@holomorphy.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
265 lines
6.6 KiB
C
265 lines
6.6 KiB
C
#ifndef _LINUX_VMSTAT_H
|
|
#define _LINUX_VMSTAT_H
|
|
|
|
#include <linux/types.h>
|
|
#include <linux/percpu.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/mmzone.h>
|
|
#include <asm/atomic.h>
|
|
|
|
#ifdef CONFIG_ZONE_DMA
|
|
#define DMA_ZONE(xx) xx##_DMA,
|
|
#else
|
|
#define DMA_ZONE(xx)
|
|
#endif
|
|
|
|
#ifdef CONFIG_ZONE_DMA32
|
|
#define DMA32_ZONE(xx) xx##_DMA32,
|
|
#else
|
|
#define DMA32_ZONE(xx)
|
|
#endif
|
|
|
|
#ifdef CONFIG_HIGHMEM
|
|
#define HIGHMEM_ZONE(xx) , xx##_HIGH
|
|
#else
|
|
#define HIGHMEM_ZONE(xx)
|
|
#endif
|
|
|
|
#define FOR_ALL_ZONES(xx) DMA_ZONE(xx) DMA32_ZONE(xx) xx##_NORMAL HIGHMEM_ZONE(xx) , xx##_MOVABLE
|
|
|
|
enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
|
|
FOR_ALL_ZONES(PGALLOC),
|
|
PGFREE, PGACTIVATE, PGDEACTIVATE,
|
|
PGFAULT, PGMAJFAULT,
|
|
FOR_ALL_ZONES(PGREFILL),
|
|
FOR_ALL_ZONES(PGSTEAL),
|
|
FOR_ALL_ZONES(PGSCAN_KSWAPD),
|
|
FOR_ALL_ZONES(PGSCAN_DIRECT),
|
|
PGINODESTEAL, SLABS_SCANNED, KSWAPD_STEAL, KSWAPD_INODESTEAL,
|
|
PAGEOUTRUN, ALLOCSTALL, PGROTATED,
|
|
NR_VM_EVENT_ITEMS
|
|
};
|
|
|
|
#ifdef CONFIG_VM_EVENT_COUNTERS
|
|
/*
|
|
* Light weight per cpu counter implementation.
|
|
*
|
|
* Counters should only be incremented and no critical kernel component
|
|
* should rely on the counter values.
|
|
*
|
|
* Counters are handled completely inline. On many platforms the code
|
|
* generated will simply be the increment of a global address.
|
|
*/
|
|
|
|
struct vm_event_state {
|
|
unsigned long event[NR_VM_EVENT_ITEMS];
|
|
};
|
|
|
|
DECLARE_PER_CPU(struct vm_event_state, vm_event_states);
|
|
|
|
static inline void __count_vm_event(enum vm_event_item item)
|
|
{
|
|
__get_cpu_var(vm_event_states).event[item]++;
|
|
}
|
|
|
|
static inline void count_vm_event(enum vm_event_item item)
|
|
{
|
|
get_cpu_var(vm_event_states).event[item]++;
|
|
put_cpu();
|
|
}
|
|
|
|
static inline void __count_vm_events(enum vm_event_item item, long delta)
|
|
{
|
|
__get_cpu_var(vm_event_states).event[item] += delta;
|
|
}
|
|
|
|
static inline void count_vm_events(enum vm_event_item item, long delta)
|
|
{
|
|
get_cpu_var(vm_event_states).event[item] += delta;
|
|
put_cpu();
|
|
}
|
|
|
|
extern void all_vm_events(unsigned long *);
|
|
#ifdef CONFIG_HOTPLUG
|
|
extern void vm_events_fold_cpu(int cpu);
|
|
#else
|
|
static inline void vm_events_fold_cpu(int cpu)
|
|
{
|
|
}
|
|
#endif
|
|
|
|
#else
|
|
|
|
/* Disable counters */
|
|
static inline void count_vm_event(enum vm_event_item item)
|
|
{
|
|
}
|
|
static inline void count_vm_events(enum vm_event_item item, long delta)
|
|
{
|
|
}
|
|
static inline void __count_vm_event(enum vm_event_item item)
|
|
{
|
|
}
|
|
static inline void __count_vm_events(enum vm_event_item item, long delta)
|
|
{
|
|
}
|
|
static inline void all_vm_events(unsigned long *ret)
|
|
{
|
|
}
|
|
static inline void vm_events_fold_cpu(int cpu)
|
|
{
|
|
}
|
|
|
|
#endif /* CONFIG_VM_EVENT_COUNTERS */
|
|
|
|
#define __count_zone_vm_events(item, zone, delta) \
|
|
__count_vm_events(item##_NORMAL - ZONE_NORMAL + \
|
|
zone_idx(zone), delta)
|
|
|
|
/*
|
|
* Zone based page accounting with per cpu differentials.
|
|
*/
|
|
extern atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS];
|
|
|
|
static inline void zone_page_state_add(long x, struct zone *zone,
|
|
enum zone_stat_item item)
|
|
{
|
|
atomic_long_add(x, &zone->vm_stat[item]);
|
|
atomic_long_add(x, &vm_stat[item]);
|
|
}
|
|
|
|
static inline unsigned long global_page_state(enum zone_stat_item item)
|
|
{
|
|
long x = atomic_long_read(&vm_stat[item]);
|
|
#ifdef CONFIG_SMP
|
|
if (x < 0)
|
|
x = 0;
|
|
#endif
|
|
return x;
|
|
}
|
|
|
|
static inline unsigned long zone_page_state(struct zone *zone,
|
|
enum zone_stat_item item)
|
|
{
|
|
long x = atomic_long_read(&zone->vm_stat[item]);
|
|
#ifdef CONFIG_SMP
|
|
if (x < 0)
|
|
x = 0;
|
|
#endif
|
|
return x;
|
|
}
|
|
|
|
#ifdef CONFIG_NUMA
|
|
/*
|
|
* Determine the per node value of a stat item. This function
|
|
* is called frequently in a NUMA machine, so try to be as
|
|
* frugal as possible.
|
|
*/
|
|
static inline unsigned long node_page_state(int node,
|
|
enum zone_stat_item item)
|
|
{
|
|
struct zone *zones = NODE_DATA(node)->node_zones;
|
|
|
|
return
|
|
#ifdef CONFIG_ZONE_DMA
|
|
zone_page_state(&zones[ZONE_DMA], item) +
|
|
#endif
|
|
#ifdef CONFIG_ZONE_DMA32
|
|
zone_page_state(&zones[ZONE_DMA32], item) +
|
|
#endif
|
|
#ifdef CONFIG_HIGHMEM
|
|
zone_page_state(&zones[ZONE_HIGHMEM], item) +
|
|
#endif
|
|
zone_page_state(&zones[ZONE_NORMAL], item) +
|
|
zone_page_state(&zones[ZONE_MOVABLE], item);
|
|
}
|
|
|
|
extern void zone_statistics(struct zonelist *, struct zone *);
|
|
|
|
#else
|
|
|
|
#define node_page_state(node, item) global_page_state(item)
|
|
#define zone_statistics(_zl,_z) do { } while (0)
|
|
|
|
#endif /* CONFIG_NUMA */
|
|
|
|
#define __add_zone_page_state(__z, __i, __d) \
|
|
__mod_zone_page_state(__z, __i, __d)
|
|
#define __sub_zone_page_state(__z, __i, __d) \
|
|
__mod_zone_page_state(__z, __i,-(__d))
|
|
|
|
#define add_zone_page_state(__z, __i, __d) mod_zone_page_state(__z, __i, __d)
|
|
#define sub_zone_page_state(__z, __i, __d) mod_zone_page_state(__z, __i, -(__d))
|
|
|
|
static inline void zap_zone_vm_stats(struct zone *zone)
|
|
{
|
|
memset(zone->vm_stat, 0, sizeof(zone->vm_stat));
|
|
}
|
|
|
|
extern void inc_zone_state(struct zone *, enum zone_stat_item);
|
|
|
|
#ifdef CONFIG_SMP
|
|
void __mod_zone_page_state(struct zone *, enum zone_stat_item item, int);
|
|
void __inc_zone_page_state(struct page *, enum zone_stat_item);
|
|
void __dec_zone_page_state(struct page *, enum zone_stat_item);
|
|
|
|
void mod_zone_page_state(struct zone *, enum zone_stat_item, int);
|
|
void inc_zone_page_state(struct page *, enum zone_stat_item);
|
|
void dec_zone_page_state(struct page *, enum zone_stat_item);
|
|
|
|
extern void inc_zone_state(struct zone *, enum zone_stat_item);
|
|
extern void __inc_zone_state(struct zone *, enum zone_stat_item);
|
|
extern void dec_zone_state(struct zone *, enum zone_stat_item);
|
|
extern void __dec_zone_state(struct zone *, enum zone_stat_item);
|
|
|
|
void refresh_cpu_vm_stats(int);
|
|
#else /* CONFIG_SMP */
|
|
|
|
/*
|
|
* We do not maintain differentials in a single processor configuration.
|
|
* The functions directly modify the zone and global counters.
|
|
*/
|
|
static inline void __mod_zone_page_state(struct zone *zone,
|
|
enum zone_stat_item item, int delta)
|
|
{
|
|
zone_page_state_add(delta, zone, item);
|
|
}
|
|
|
|
static inline void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
|
|
{
|
|
atomic_long_inc(&zone->vm_stat[item]);
|
|
atomic_long_inc(&vm_stat[item]);
|
|
}
|
|
|
|
static inline void __inc_zone_page_state(struct page *page,
|
|
enum zone_stat_item item)
|
|
{
|
|
__inc_zone_state(page_zone(page), item);
|
|
}
|
|
|
|
static inline void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
|
|
{
|
|
atomic_long_dec(&zone->vm_stat[item]);
|
|
atomic_long_dec(&vm_stat[item]);
|
|
}
|
|
|
|
static inline void __dec_zone_page_state(struct page *page,
|
|
enum zone_stat_item item)
|
|
{
|
|
atomic_long_dec(&page_zone(page)->vm_stat[item]);
|
|
atomic_long_dec(&vm_stat[item]);
|
|
}
|
|
|
|
/*
|
|
* We only use atomic operations to update counters. So there is no need to
|
|
* disable interrupts.
|
|
*/
|
|
#define inc_zone_page_state __inc_zone_page_state
|
|
#define dec_zone_page_state __dec_zone_page_state
|
|
#define mod_zone_page_state __mod_zone_page_state
|
|
|
|
static inline void refresh_cpu_vm_stats(int cpu) { }
|
|
#endif
|
|
|
|
#endif /* _LINUX_VMSTAT_H */
|