mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-10-30 08:02:30 +00:00
e9a2e48e87
No need to store the value for each and every memory block, as we can easily query the value at runtime. Reshuffle the members to optimize the memory layout. Also, let's clarify what the interface once was used for and why it's legacy nowadays. "phys_device" was used on s390x in older versions of lsmem[2]/chmem[3], back when they were still part of s390x-tools. They were later replaced by the variants in linux-utils. For example, RHEL6 and RHEL7 contain lsmem/chmem from s390-utils. RHEL8 switched to versions from util-linux on s390x [4]. "phys_device" was added with sysfs support for memory hotplug in commit3947be1969
("[PATCH] memory hotplug: sysfs and add/remove functions") in 2005. It always returned 0. s390x started returning something != 0 on some setups (if sclp.rzm is set by HW) in 2010 via commit57b552ba0b
("memory hotplug/s390: set phys_device"). For s390x, it allowed for identifying which memory block devices belong to the same storage increment (RZM). Only if all memory block devices comprising a single storage increment were offline, the memory could actually be removed in the hypervisor. Since commite5d709bb5f
("s390/memory hotplug: provide memory_block_size_bytes() function") in 2013 a memory block device spans at least one storage increment - which is why the interface isn't really helpful/used anymore (except by old lsmem/chmem tools). There were once RFC patches to make use of "phys_device" in ACPI context; however, the underlying problem could be solved using different interfaces [1]. [1] https://patchwork.kernel.org/patch/2163871/ [2] https://github.com/ibm-s390-tools/s390-tools/blob/v2.1.0/zconf/lsmem [3] https://github.com/ibm-s390-tools/s390-tools/blob/v2.1.0/zconf/chmem [4] https://bugzilla.redhat.com/show_bug.cgi?id=1504134 Link: https://lkml.kernel.org/r/20210201181347.13262-2-david@redhat.com Signed-off-by: David Hildenbrand <david@redhat.com> Acked-by: Michal Hocko <mhocko@suse.com> Reviewed-by: Oscar Salvador <osalvador@suse.de> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: "Rafael J. Wysocki" <rafael@kernel.org> Cc: Mauro Carvalho Chehab <mchehab+huawei@kernel.org> Cc: Ilya Dryomov <idryomov@gmail.com> Cc: Vaibhav Jain <vaibhav@linux.ibm.com> Cc: Tom Rix <trix@redhat.com> Cc: Geert Uytterhoeven <geert+renesas@glider.be> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
116 lines
3.7 KiB
C
116 lines
3.7 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/*
|
|
* 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 state; /* serialized by the dev->lock */
|
|
int online_type; /* for passing data to online routine */
|
|
int nid; /* NID for this memory block */
|
|
struct device dev;
|
|
};
|
|
|
|
int arch_get_memory_phys_device(unsigned long start_pfn);
|
|
unsigned long memory_block_size_bytes(void);
|
|
int set_memory_block_size_order(unsigned int order);
|
|
|
|
/* 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;
|
|
int status_change_nid_normal;
|
|
int status_change_nid_high;
|
|
int status_change_nid;
|
|
};
|
|
|
|
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 void memory_dev_init(void)
|
|
{
|
|
return;
|
|
}
|
|
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;
|
|
}
|
|
#else
|
|
extern int register_memory_notifier(struct notifier_block *nb);
|
|
extern void unregister_memory_notifier(struct notifier_block *nb);
|
|
int create_memory_block_devices(unsigned long start, unsigned long size);
|
|
void remove_memory_block_devices(unsigned long start, unsigned long size);
|
|
extern void memory_dev_init(void);
|
|
extern int memory_notify(unsigned long val, void *v);
|
|
extern struct memory_block *find_memory_block(struct mem_section *);
|
|
typedef int (*walk_memory_blocks_func_t)(struct memory_block *, void *);
|
|
extern int walk_memory_blocks(unsigned long start, unsigned long size,
|
|
void *arg, walk_memory_blocks_func_t func);
|
|
extern int for_each_memory_block(void *arg, walk_memory_blocks_func_t func);
|
|
#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_ */
|