linux_dsm_epyc7002/include/linux/memory_hotplug.h
David Rientjes 30467e0b3b mm, hotplug: fix concurrent memory hot-add deadlock
There's a deadlock when concurrently hot-adding memory through the probe
interface and switching a memory block from offline to online.

When hot-adding memory via the probe interface, add_memory() first takes
mem_hotplug_begin() and then device_lock() is later taken when registering
the newly initialized memory block.  This creates a lock dependency of (1)
mem_hotplug.lock (2) dev->mutex.

When switching a memory block from offline to online, dev->mutex is first
grabbed in device_online() when the write(2) transitions an existing
memory block from offline to online, and then online_pages() will take
mem_hotplug_begin().

This creates a lock inversion between mem_hotplug.lock and dev->mutex.
Vitaly reports that this deadlock can happen when kworker handling a probe
event races with systemd-udevd switching a memory block's state.

This patch requires the state transition to take mem_hotplug_begin()
before dev->mutex.  Hot-adding memory via the probe interface creates a
memory block while holding mem_hotplug_begin(), there is no way to take
dev->mutex first in this case.

online_pages() and offline_pages() are only called when transitioning
memory block state.  We now require that mem_hotplug_begin() is taken
before calling them -- this requires exporting the mem_hotplug_begin() and
mem_hotplug_done() to generic code.  In all hot-add and hot-remove cases,
mem_hotplug_begin() is done prior to device_online().  This is all that is
needed to avoid the deadlock.

Signed-off-by: David Rientjes <rientjes@google.com>
Reported-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Tested-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: Tang Chen <tangchen@cn.fujitsu.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Zhang Zhen <zhenzhang.zhang@huawei.com>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Cc: Wang Nan <wangnan0@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-14 16:49:00 -07:00

280 lines
8.2 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 and offlined memory */
enum {
MMOP_OFFLINE = -1,
MMOP_ONLINE_KEEP,
MMOP_ONLINE_KERNEL,
MMOP_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 int test_pages_in_a_zone(unsigned long, unsigned long);
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);
void mem_hotplug_begin(void);
void mem_hotplug_done(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) {}
static inline void mem_hotplug_begin(void) {}
static inline void mem_hotplug_done(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 zone_for_memory(int nid, u64 start, u64 size, int zone_default);
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 */