linux_dsm_epyc7002/include/linux/memory.h

149 lines
4.6 KiB
C
Raw Normal View History

/*
* include/linux/memory.h - generic memory definition
*
* This is mainly for topological representation. We define the
* basic "struct memory_block" here, which can be embedded in per-arch
* definitions or NUMA information.
*
* Basic handling of the devices is done in drivers/base/memory.c
* and system devices are handled in drivers/base/sys.c.
*
* Memory block are exported via sysfs in the class/memory/devices/
* directory.
*
*/
#ifndef _LINUX_MEMORY_H_
#define _LINUX_MEMORY_H_
#include <linux/node.h>
#include <linux/compiler.h>
#include <linux/mutex.h>
#include <linux/notifier.h>
#define MIN_MEMORY_BLOCK_SIZE (1UL << SECTION_SIZE_BITS)
struct memory_block {
unsigned long start_section_nr;
unsigned long end_section_nr;
unsigned long state; /* serialized by the dev->lock */
int section_count; /* serialized by mem_sysfs_mutex */
int online_type; /* for passing data to online routine */
int phys_device; /* to which fru does this belong? */
void *hw; /* optional pointer to fw/hw data */
int (*phys_callback)(struct memory_block *);
struct device dev;
};
int arch_get_memory_phys_device(unsigned long start_pfn);
unsigned long memory_block_size_bytes(void);
/* These states are exposed to userspace as text strings in sysfs */
#define MEM_ONLINE (1<<0) /* exposed to userspace */
#define MEM_GOING_OFFLINE (1<<1) /* exposed to userspace */
#define MEM_OFFLINE (1<<2) /* exposed to userspace */
#define MEM_GOING_ONLINE (1<<3)
#define MEM_CANCEL_ONLINE (1<<4)
#define MEM_CANCEL_OFFLINE (1<<5)
struct memory_notify {
unsigned long start_pfn;
unsigned long nr_pages;
memory_hotplug: fix possible incorrect node_states[N_NORMAL_MEMORY] Currently memory_hotplug only manages the node_states[N_HIGH_MEMORY], it forgets to manage node_states[N_NORMAL_MEMORY]. This may cause node_states[N_NORMAL_MEMORY] to become incorrect. Example, if a node is empty before online, and we online a memory which is in ZONE_NORMAL. And after online, node_states[N_HIGH_MEMORY] is correct, but node_states[N_NORMAL_MEMORY] is incorrect, the online code doesn't set the new online node to node_states[N_NORMAL_MEMORY]. The same thing will happen when offlining (the offline code doesn't clear the node from node_states[N_NORMAL_MEMORY] when needed). Some memory managment code depends node_states[N_NORMAL_MEMORY], so we have to fix up the node_states[N_NORMAL_MEMORY]. We add node_states_check_changes_online() and node_states_check_changes_offline() to detect whether node_states[N_HIGH_MEMORY] and node_states[N_NORMAL_MEMORY] are changed while hotpluging. Also add @status_change_nid_normal to struct memory_notify, thus the memory hotplug callbacks know whether the node_states[N_NORMAL_MEMORY] are changed. (We can add a @flags and reuse @status_change_nid instead of introducing @status_change_nid_normal, but it will add much more complexity in memory hotplug callback in every subsystem. So introducing @status_change_nid_normal is better and it doesn't change the sematics of @status_change_nid) Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: David Rientjes <rientjes@google.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Rob Landley <rob@landley.net> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Kay Sievers <kay.sievers@vrfy.org> Cc: Greg Kroah-Hartman <gregkh@suse.de> Cc: Mel Gorman <mgorman@suse.de> Cc: Wen Congyang <wency@cn.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-12-12 07:01:03 +07:00
int status_change_nid_normal;
int status_change_nid_high;
int status_change_nid;
};
/*
* During pageblock isolation, count the number of pages within the
* range [start_pfn, start_pfn + nr_pages) which are owned by code
* in the notifier chain.
*/
#define MEM_ISOLATE_COUNT (1<<0)
struct memory_isolate_notify {
unsigned long start_pfn; /* Start of range to check */
unsigned int nr_pages; /* # pages in range to check */
unsigned int pages_found; /* # pages owned found by callbacks */
};
struct notifier_block;
struct mem_section;
/*
* Priorities for the hotplug memory callback routines (stored in decreasing
* order in the callback chain)
*/
#define SLAB_CALLBACK_PRI 1
#define IPC_CALLBACK_PRI 10
#ifndef CONFIG_MEMORY_HOTPLUG_SPARSE
static inline int memory_dev_init(void)
{
return 0;
}
static inline int register_memory_notifier(struct notifier_block *nb)
{
return 0;
}
static inline void unregister_memory_notifier(struct notifier_block *nb)
{
}
static inline int memory_notify(unsigned long val, void *v)
{
return 0;
}
static inline int register_memory_isolate_notifier(struct notifier_block *nb)
{
return 0;
}
static inline void unregister_memory_isolate_notifier(struct notifier_block *nb)
{
}
static inline int memory_isolate_notify(unsigned long val, void *v)
{
return 0;
}
#else
extern int register_memory_notifier(struct notifier_block *nb);
extern void unregister_memory_notifier(struct notifier_block *nb);
extern int register_memory_isolate_notifier(struct notifier_block *nb);
extern void unregister_memory_isolate_notifier(struct notifier_block *nb);
mm: show node to memory section relationship with symlinks in sysfs Show node to memory section relationship with symlinks in sysfs Add /sys/devices/system/node/nodeX/memoryY symlinks for all the memory sections located on nodeX. For example: /sys/devices/system/node/node1/memory135 -> ../../memory/memory135 indicates that memory section 135 resides on node1. Also revises documentation to cover this change as well as updating Documentation/ABI/testing/sysfs-devices-memory to include descriptions of memory hotremove files 'phys_device', 'phys_index', and 'state' that were previously not described there. In addition to it always being a good policy to provide users with the maximum possible amount of physical location information for resources that can be hot-added and/or hot-removed, the following are some (but likely not all) of the user benefits provided by this change. Immediate: - Provides information needed to determine the specific node on which a defective DIMM is located. This will reduce system downtime when the node or defective DIMM is swapped out. - Prevents unintended onlining of a memory section that was previously offlined due to a defective DIMM. This could happen during node hot-add when the user or node hot-add assist script onlines _all_ offlined sections due to user or script inability to identify the specific memory sections located on the hot-added node. The consequences of reintroducing the defective memory could be ugly. - Provides information needed to vary the amount and distribution of memory on specific nodes for testing or debugging purposes. Future: - Will provide information needed to identify the memory sections that need to be offlined prior to physical removal of a specific node. Symlink creation during boot was tested on 2-node x86_64, 2-node ppc64, and 2-node ia64 systems. Symlink creation during physical memory hot-add tested on a 2-node x86_64 system. Signed-off-by: Gary Hade <garyhade@us.ibm.com> Signed-off-by: Badari Pulavarty <pbadari@us.ibm.com> Acked-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-07 05:39:14 +07:00
extern int register_new_memory(int, struct mem_section *);
memory-hotplug: add automatic onlining policy for the newly added memory Currently, all newly added memory blocks remain in 'offline' state unless someone onlines them, some linux distributions carry special udev rules like: SUBSYSTEM=="memory", ACTION=="add", ATTR{state}=="offline", ATTR{state}="online" to make this happen automatically. This is not a great solution for virtual machines where memory hotplug is being used to address high memory pressure situations as such onlining is slow and a userspace process doing this (udev) has a chance of being killed by the OOM killer as it will probably require to allocate some memory. Introduce default policy for the newly added memory blocks in /sys/devices/system/memory/auto_online_blocks file with two possible values: "offline" which preserves the current behavior and "online" which causes all newly added memory blocks to go online as soon as they're added. The default is "offline". Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com> Reviewed-by: Daniel Kiper <daniel.kiper@oracle.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Daniel Kiper <daniel.kiper@oracle.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Tang Chen <tangchen@cn.fujitsu.com> Cc: David Vrabel <david.vrabel@citrix.com> Acked-by: David Rientjes <rientjes@google.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Xishi Qiu <qiuxishi@huawei.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: "K. Y. Srinivasan" <kys@microsoft.com> Cc: Igor Mammedov <imammedo@redhat.com> Cc: Kay Sievers <kay@vrfy.org> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-16 04:56:48 +07:00
extern int memory_block_change_state(struct memory_block *mem,
unsigned long to_state,
unsigned long from_state_req);
#ifdef CONFIG_MEMORY_HOTREMOVE
extern int unregister_memory_section(struct mem_section *);
#endif
extern int memory_dev_init(void);
extern int memory_notify(unsigned long val, void *v);
extern int memory_isolate_notify(unsigned long val, void *v);
extern struct memory_block *find_memory_block_hinted(struct mem_section *,
struct memory_block *);
mm: show node to memory section relationship with symlinks in sysfs Show node to memory section relationship with symlinks in sysfs Add /sys/devices/system/node/nodeX/memoryY symlinks for all the memory sections located on nodeX. For example: /sys/devices/system/node/node1/memory135 -> ../../memory/memory135 indicates that memory section 135 resides on node1. Also revises documentation to cover this change as well as updating Documentation/ABI/testing/sysfs-devices-memory to include descriptions of memory hotremove files 'phys_device', 'phys_index', and 'state' that were previously not described there. In addition to it always being a good policy to provide users with the maximum possible amount of physical location information for resources that can be hot-added and/or hot-removed, the following are some (but likely not all) of the user benefits provided by this change. Immediate: - Provides information needed to determine the specific node on which a defective DIMM is located. This will reduce system downtime when the node or defective DIMM is swapped out. - Prevents unintended onlining of a memory section that was previously offlined due to a defective DIMM. This could happen during node hot-add when the user or node hot-add assist script onlines _all_ offlined sections due to user or script inability to identify the specific memory sections located on the hot-added node. The consequences of reintroducing the defective memory could be ugly. - Provides information needed to vary the amount and distribution of memory on specific nodes for testing or debugging purposes. Future: - Will provide information needed to identify the memory sections that need to be offlined prior to physical removal of a specific node. Symlink creation during boot was tested on 2-node x86_64, 2-node ppc64, and 2-node ia64 systems. Symlink creation during physical memory hot-add tested on a 2-node x86_64 system. Signed-off-by: Gary Hade <garyhade@us.ibm.com> Signed-off-by: Badari Pulavarty <pbadari@us.ibm.com> Acked-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-07 05:39:14 +07:00
extern struct memory_block *find_memory_block(struct mem_section *);
#define CONFIG_MEM_BLOCK_SIZE (PAGES_PER_SECTION<<PAGE_SHIFT)
#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */
#ifdef CONFIG_MEMORY_HOTPLUG
#define hotplug_memory_notifier(fn, pri) ({ \
static __meminitdata struct notifier_block fn##_mem_nb =\
{ .notifier_call = fn, .priority = pri };\
register_memory_notifier(&fn##_mem_nb); \
})
#define register_hotmemory_notifier(nb) register_memory_notifier(nb)
#define unregister_hotmemory_notifier(nb) unregister_memory_notifier(nb)
#else
#define hotplug_memory_notifier(fn, pri) ({ 0; })
/* These aren't inline functions due to a GCC bug. */
#define register_hotmemory_notifier(nb) ({ (void)(nb); 0; })
#define unregister_hotmemory_notifier(nb) ({ (void)(nb); })
#endif
/*
* Kernel text modification mutex, used for code patching. Users of this lock
* can sleep.
*/
extern struct mutex text_mutex;
#endif /* _LINUX_MEMORY_H_ */