mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-25 23:25:37 +07:00
bfc8c90139
kmem_cache_{create,destroy,shrink} need to get a stable value of cpu/node online mask, because they init/destroy/access per-cpu/node kmem_cache parts, which can be allocated or destroyed on cpu/mem hotplug. To protect against cpu hotplug, these functions use {get,put}_online_cpus. However, they do nothing to synchronize with memory hotplug - taking the slab_mutex does not eliminate the possibility of race as described in patch 2. What we need there is something like get_online_cpus, but for memory. We already have lock_memory_hotplug, which serves for the purpose, but it's a bit of a hammer right now, because it's backed by a mutex. As a result, it imposes some limitations to locking order, which are not desirable, and can't be used just like get_online_cpus. That's why in patch 1 I substitute it with get/put_online_mems, which work exactly like get/put_online_cpus except they block not cpu, but memory hotplug. [ v1 can be found at https://lkml.org/lkml/2014/4/6/68. I NAK'ed it by myself, because it used an rw semaphore for get/put_online_mems, making them dead lock prune. ] This patch (of 2): {un}lock_memory_hotplug, which is used to synchronize against memory hotplug, is currently backed by a mutex, which makes it a bit of a hammer - threads that only want to get a stable value of online nodes mask won't be able to proceed concurrently. Also, it imposes some strong locking ordering rules on it, which narrows down the set of its usage scenarios. This patch introduces get/put_online_mems, which are the same as get/put_online_cpus, but for memory hotplug, i.e. executing a code inside a get/put_online_mems section will guarantee a stable value of online nodes, present pages, etc. lock_memory_hotplug()/unlock_memory_hotplug() are removed altogether. Signed-off-by: Vladimir Davydov <vdavydov@parallels.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: Tang Chen <tangchen@cn.fujitsu.com> Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Xishi Qiu <qiuxishi@huawei.com> Cc: Jiang Liu <liuj97@gmail.com> Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Cc: David Rientjes <rientjes@google.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
271 lines
7.8 KiB
C
271 lines
7.8 KiB
C
#ifndef __LINUX_MEMORY_HOTPLUG_H
|
|
#define __LINUX_MEMORY_HOTPLUG_H
|
|
|
|
#include <linux/mmzone.h>
|
|
#include <linux/spinlock.h>
|
|
#include <linux/notifier.h>
|
|
#include <linux/bug.h>
|
|
|
|
struct page;
|
|
struct zone;
|
|
struct pglist_data;
|
|
struct mem_section;
|
|
struct memory_block;
|
|
|
|
#ifdef CONFIG_MEMORY_HOTPLUG
|
|
|
|
/*
|
|
* Types for free bootmem stored in page->lru.next. These have to be in
|
|
* some random range in unsigned long space for debugging purposes.
|
|
*/
|
|
enum {
|
|
MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE = 12,
|
|
SECTION_INFO = MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE,
|
|
MIX_SECTION_INFO,
|
|
NODE_INFO,
|
|
MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE = NODE_INFO,
|
|
};
|
|
|
|
/* Types for control the zone type of onlined memory */
|
|
enum {
|
|
ONLINE_KEEP,
|
|
ONLINE_KERNEL,
|
|
ONLINE_MOVABLE,
|
|
};
|
|
|
|
/*
|
|
* pgdat resizing functions
|
|
*/
|
|
static inline
|
|
void pgdat_resize_lock(struct pglist_data *pgdat, unsigned long *flags)
|
|
{
|
|
spin_lock_irqsave(&pgdat->node_size_lock, *flags);
|
|
}
|
|
static inline
|
|
void pgdat_resize_unlock(struct pglist_data *pgdat, unsigned long *flags)
|
|
{
|
|
spin_unlock_irqrestore(&pgdat->node_size_lock, *flags);
|
|
}
|
|
static inline
|
|
void pgdat_resize_init(struct pglist_data *pgdat)
|
|
{
|
|
spin_lock_init(&pgdat->node_size_lock);
|
|
}
|
|
/*
|
|
* Zone resizing functions
|
|
*
|
|
* Note: any attempt to resize a zone should has pgdat_resize_lock()
|
|
* zone_span_writelock() both held. This ensure the size of a zone
|
|
* can't be changed while pgdat_resize_lock() held.
|
|
*/
|
|
static inline unsigned zone_span_seqbegin(struct zone *zone)
|
|
{
|
|
return read_seqbegin(&zone->span_seqlock);
|
|
}
|
|
static inline int zone_span_seqretry(struct zone *zone, unsigned iv)
|
|
{
|
|
return read_seqretry(&zone->span_seqlock, iv);
|
|
}
|
|
static inline void zone_span_writelock(struct zone *zone)
|
|
{
|
|
write_seqlock(&zone->span_seqlock);
|
|
}
|
|
static inline void zone_span_writeunlock(struct zone *zone)
|
|
{
|
|
write_sequnlock(&zone->span_seqlock);
|
|
}
|
|
static inline void zone_seqlock_init(struct zone *zone)
|
|
{
|
|
seqlock_init(&zone->span_seqlock);
|
|
}
|
|
extern int zone_grow_free_lists(struct zone *zone, unsigned long new_nr_pages);
|
|
extern int zone_grow_waitqueues(struct zone *zone, unsigned long nr_pages);
|
|
extern int add_one_highpage(struct page *page, int pfn, int bad_ppro);
|
|
/* VM interface that may be used by firmware interface */
|
|
extern int online_pages(unsigned long, unsigned long, int);
|
|
extern void __offline_isolated_pages(unsigned long, unsigned long);
|
|
|
|
typedef void (*online_page_callback_t)(struct page *page);
|
|
|
|
extern int set_online_page_callback(online_page_callback_t callback);
|
|
extern int restore_online_page_callback(online_page_callback_t callback);
|
|
|
|
extern void __online_page_set_limits(struct page *page);
|
|
extern void __online_page_increment_counters(struct page *page);
|
|
extern void __online_page_free(struct page *page);
|
|
|
|
extern int try_online_node(int nid);
|
|
|
|
#ifdef CONFIG_MEMORY_HOTREMOVE
|
|
extern bool is_pageblock_removable_nolock(struct page *page);
|
|
extern int arch_remove_memory(u64 start, u64 size);
|
|
extern int __remove_pages(struct zone *zone, unsigned long start_pfn,
|
|
unsigned long nr_pages);
|
|
#endif /* CONFIG_MEMORY_HOTREMOVE */
|
|
|
|
/* reasonably generic interface to expand the physical pages in a zone */
|
|
extern int __add_pages(int nid, struct zone *zone, unsigned long start_pfn,
|
|
unsigned long nr_pages);
|
|
|
|
#ifdef CONFIG_NUMA
|
|
extern int memory_add_physaddr_to_nid(u64 start);
|
|
#else
|
|
static inline int memory_add_physaddr_to_nid(u64 start)
|
|
{
|
|
return 0;
|
|
}
|
|
#endif
|
|
|
|
#ifdef CONFIG_HAVE_ARCH_NODEDATA_EXTENSION
|
|
/*
|
|
* For supporting node-hotadd, we have to allocate a new pgdat.
|
|
*
|
|
* If an arch has generic style NODE_DATA(),
|
|
* node_data[nid] = kzalloc() works well. But it depends on the architecture.
|
|
*
|
|
* In general, generic_alloc_nodedata() is used.
|
|
* Now, arch_free_nodedata() is just defined for error path of node_hot_add.
|
|
*
|
|
*/
|
|
extern pg_data_t *arch_alloc_nodedata(int nid);
|
|
extern void arch_free_nodedata(pg_data_t *pgdat);
|
|
extern void arch_refresh_nodedata(int nid, pg_data_t *pgdat);
|
|
|
|
#else /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */
|
|
|
|
#define arch_alloc_nodedata(nid) generic_alloc_nodedata(nid)
|
|
#define arch_free_nodedata(pgdat) generic_free_nodedata(pgdat)
|
|
|
|
#ifdef CONFIG_NUMA
|
|
/*
|
|
* If ARCH_HAS_NODEDATA_EXTENSION=n, this func is used to allocate pgdat.
|
|
* XXX: kmalloc_node() can't work well to get new node's memory at this time.
|
|
* Because, pgdat for the new node is not allocated/initialized yet itself.
|
|
* To use new node's memory, more consideration will be necessary.
|
|
*/
|
|
#define generic_alloc_nodedata(nid) \
|
|
({ \
|
|
kzalloc(sizeof(pg_data_t), GFP_KERNEL); \
|
|
})
|
|
/*
|
|
* This definition is just for error path in node hotadd.
|
|
* For node hotremove, we have to replace this.
|
|
*/
|
|
#define generic_free_nodedata(pgdat) kfree(pgdat)
|
|
|
|
extern pg_data_t *node_data[];
|
|
static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat)
|
|
{
|
|
node_data[nid] = pgdat;
|
|
}
|
|
|
|
#else /* !CONFIG_NUMA */
|
|
|
|
/* never called */
|
|
static inline pg_data_t *generic_alloc_nodedata(int nid)
|
|
{
|
|
BUG();
|
|
return NULL;
|
|
}
|
|
static inline void generic_free_nodedata(pg_data_t *pgdat)
|
|
{
|
|
}
|
|
static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat)
|
|
{
|
|
}
|
|
#endif /* CONFIG_NUMA */
|
|
#endif /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */
|
|
|
|
#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE
|
|
extern void register_page_bootmem_info_node(struct pglist_data *pgdat);
|
|
#else
|
|
static inline void register_page_bootmem_info_node(struct pglist_data *pgdat)
|
|
{
|
|
}
|
|
#endif
|
|
extern void put_page_bootmem(struct page *page);
|
|
extern void get_page_bootmem(unsigned long ingo, struct page *page,
|
|
unsigned long type);
|
|
|
|
void get_online_mems(void);
|
|
void put_online_mems(void);
|
|
|
|
#else /* ! CONFIG_MEMORY_HOTPLUG */
|
|
/*
|
|
* Stub functions for when hotplug is off
|
|
*/
|
|
static inline void pgdat_resize_lock(struct pglist_data *p, unsigned long *f) {}
|
|
static inline void pgdat_resize_unlock(struct pglist_data *p, unsigned long *f) {}
|
|
static inline void pgdat_resize_init(struct pglist_data *pgdat) {}
|
|
|
|
static inline unsigned zone_span_seqbegin(struct zone *zone)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline int zone_span_seqretry(struct zone *zone, unsigned iv)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline void zone_span_writelock(struct zone *zone) {}
|
|
static inline void zone_span_writeunlock(struct zone *zone) {}
|
|
static inline void zone_seqlock_init(struct zone *zone) {}
|
|
|
|
static inline int mhp_notimplemented(const char *func)
|
|
{
|
|
printk(KERN_WARNING "%s() called, with CONFIG_MEMORY_HOTPLUG disabled\n", func);
|
|
dump_stack();
|
|
return -ENOSYS;
|
|
}
|
|
|
|
static inline void register_page_bootmem_info_node(struct pglist_data *pgdat)
|
|
{
|
|
}
|
|
|
|
static inline int try_online_node(int nid)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void get_online_mems(void) {}
|
|
static inline void put_online_mems(void) {}
|
|
|
|
#endif /* ! CONFIG_MEMORY_HOTPLUG */
|
|
|
|
#ifdef CONFIG_MEMORY_HOTREMOVE
|
|
|
|
extern int is_mem_section_removable(unsigned long pfn, unsigned long nr_pages);
|
|
extern void try_offline_node(int nid);
|
|
extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages);
|
|
extern void remove_memory(int nid, u64 start, u64 size);
|
|
|
|
#else
|
|
static inline int is_mem_section_removable(unsigned long pfn,
|
|
unsigned long nr_pages)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void try_offline_node(int nid) {}
|
|
|
|
static inline int offline_pages(unsigned long start_pfn, unsigned long nr_pages)
|
|
{
|
|
return -EINVAL;
|
|
}
|
|
|
|
static inline void remove_memory(int nid, u64 start, u64 size) {}
|
|
#endif /* CONFIG_MEMORY_HOTREMOVE */
|
|
|
|
extern int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn,
|
|
void *arg, int (*func)(struct memory_block *, void *));
|
|
extern int add_memory(int nid, u64 start, u64 size);
|
|
extern int arch_add_memory(int nid, u64 start, u64 size);
|
|
extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages);
|
|
extern bool is_memblock_offlined(struct memory_block *mem);
|
|
extern void remove_memory(int nid, u64 start, u64 size);
|
|
extern int sparse_add_one_section(struct zone *zone, unsigned long start_pfn);
|
|
extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms);
|
|
extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map,
|
|
unsigned long pnum);
|
|
|
|
#endif /* __LINUX_MEMORY_HOTPLUG_H */
|