diff options
Diffstat (limited to 'include/linux/memory.h')
| -rw-r--r-- | include/linux/memory.h | 217 |
1 files changed, 132 insertions, 85 deletions
diff --git a/include/linux/memory.h b/include/linux/memory.h index 85c31a8e2904..faeaa921e55b 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * include/linux/memory.h - generic memory definition * @@ -18,74 +19,111 @@ #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_group - a logical group of memory blocks + * @nid: The node id for all memory blocks inside the memory group. + * @memory_blocks: List of all memory blocks belonging to this memory group. + * @present_kernel_pages: Present (online) memory outside ZONE_MOVABLE of this + * memory group. + * @present_movable_pages: Present (online) memory in ZONE_MOVABLE of this + * memory group. + * @is_dynamic: The memory group type: static vs. dynamic + * @s.max_pages: Valid with &memory_group.is_dynamic == false. The maximum + * number of pages we'll have in this static memory group. + * @d.unit_pages: Valid with &memory_group.is_dynamic == true. Unit in pages + * in which memory is added/removed in this dynamic memory group. + * This granularity defines the alignment of a unit in physical + * address space; it has to be at least as big as a single + * memory block. + * + * A memory group logically groups memory blocks; each memory block + * belongs to at most one memory group. A memory group corresponds to + * a memory device, such as a DIMM or a NUMA node, which spans multiple + * memory blocks and might even span multiple non-contiguous physical memory + * ranges. + * + * Modification of members after registration is serialized by memory + * hot(un)plug code. + */ +struct memory_group { + int nid; + struct list_head memory_blocks; + unsigned long present_kernel_pages; + unsigned long present_movable_pages; + bool is_dynamic; + union { + struct { + unsigned long max_pages; + } s; + struct { + unsigned long unit_pages; + } d; + }; +}; + +enum memory_block_state { + /* These states are exposed to userspace as text strings in sysfs */ + MEM_ONLINE, /* exposed to userspace */ + MEM_GOING_OFFLINE, /* exposed to userspace */ + MEM_OFFLINE, /* exposed to userspace */ + MEM_GOING_ONLINE, + MEM_CANCEL_ONLINE, + MEM_CANCEL_OFFLINE, +}; + struct memory_block { unsigned long start_section_nr; - unsigned long end_section_nr; - unsigned long state; - int section_count; - + enum memory_block_state state; /* serialized by the dev->lock */ + int online_type; /* for passing data to online routine */ + int nid; /* NID for this memory block */ /* - * This serializes all state change requests. It isn't - * held during creation because the control files are - * created long after the critical areas during - * initialization. + * The single zone of this memory block if all PFNs of this memory block + * that are System RAM (not a memory hole, not ZONE_DEVICE ranges) are + * managed by a single zone. NULL if multiple zones (including nodes) + * apply. */ - struct mutex state_mutex; - int phys_device; /* to which fru does this belong? */ - void *hw; /* optional pointer to fw/hw data */ - int (*phys_callback)(struct memory_block *); + struct zone *zone; struct device dev; + struct vmem_altmap *altmap; + struct memory_group *group; /* group (if any) for this block */ + struct list_head group_next; /* next block inside memory group */ +#if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG) + atomic_long_t nr_hwpoison; +#endif }; int arch_get_memory_phys_device(unsigned long start_pfn); - -/* 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) +unsigned long memory_block_size_bytes(void); +int set_memory_block_size_order(unsigned int order); 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; -}; - -/* - * 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) + * Priorities for the hotplug memory callback routines. Invoked from + * high to low. Higher priorities correspond to higher numbers. */ -#define SLAB_CALLBACK_PRI 1 -#define IPC_CALLBACK_PRI 10 - -#ifndef CONFIG_MEMORY_HOTPLUG_SPARSE -static inline int memory_dev_init(void) +#define DEFAULT_CALLBACK_PRI 0 +#define SLAB_CALLBACK_PRI 1 +#define CXL_CALLBACK_PRI 5 +#define HMAT_CALLBACK_PRI 6 +#define MM_COMPUTE_BATCH_PRI 10 +#define CPUSET_CALLBACK_PRI 10 +#define MEMTIER_HOTPLUG_PRI 100 +#define KSM_CALLBACK_PRI 100 + +#ifndef CONFIG_MEMORY_HOTPLUG +static inline void memory_dev_init(void) { - return 0; + return; } static inline int register_memory_notifier(struct notifier_block *nb) { @@ -94,65 +132,74 @@ static inline int register_memory_notifier(struct notifier_block *nb) static inline void unregister_memory_notifier(struct notifier_block *nb) { } -static inline int memory_notify(unsigned long val, void *v) +static inline int memory_notify(enum memory_block_state state, void *v) { return 0; } -static inline int register_memory_isolate_notifier(struct notifier_block *nb) +static inline int hotplug_memory_notifier(notifier_fn_t fn, int pri) { return 0; } -static inline void unregister_memory_isolate_notifier(struct notifier_block *nb) +static inline int memory_block_advise_max_size(unsigned long size) { + return -ENODEV; } -static inline int memory_isolate_notify(unsigned long val, void *v) +static inline unsigned long memory_block_advised_max_size(void) { return 0; } -#else +#else /* CONFIG_MEMORY_HOTPLUG */ 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); -extern int register_new_memory(int, struct mem_section *); -#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 *); -extern struct memory_block *find_memory_block(struct mem_section *); -#define CONFIG_MEM_BLOCK_SIZE (PAGES_PER_SECTION<<PAGE_SHIFT) -enum mem_add_context { BOOT, HOTPLUG }; -#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */ - -#ifdef CONFIG_MEMORY_HOTPLUG +int create_memory_block_devices(unsigned long start, unsigned long size, + int nid, struct vmem_altmap *altmap, + struct memory_group *group); +void remove_memory_block_devices(unsigned long start, unsigned long size); +extern void memory_dev_init(void); +extern int memory_notify(enum memory_block_state state, void *v); +extern struct memory_block *find_memory_block(unsigned long section_nr); +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); + +extern int memory_group_register_static(int nid, unsigned long max_pages); +extern int memory_group_register_dynamic(int nid, unsigned long unit_pages); +extern int memory_group_unregister(int mgid); +struct memory_group *memory_group_find_by_id(int mgid); +typedef int (*walk_memory_groups_func_t)(struct memory_group *, void *); +int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func, + struct memory_group *excluded, void *arg); +struct memory_block *find_memory_block_by_id(unsigned long block_id); #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 -/* - * 'struct memory_accessor' is a generic interface to provide - * in-kernel access to persistent memory such as i2c or SPI EEPROMs - */ -struct memory_accessor { - ssize_t (*read)(struct memory_accessor *, char *buf, off_t offset, - size_t count); - ssize_t (*write)(struct memory_accessor *, const char *buf, - off_t offset, size_t count); -}; +extern int sections_per_block; + +static inline unsigned long memory_block_id(unsigned long section_nr) +{ + return section_nr / sections_per_block; +} + +static inline unsigned long pfn_to_block_id(unsigned long pfn) +{ + return memory_block_id(pfn_to_section_nr(pfn)); +} + +static inline unsigned long phys_to_block_id(unsigned long phys) +{ + return pfn_to_block_id(PFN_DOWN(phys)); +} + +#ifdef CONFIG_NUMA +void memory_block_add_nid_early(struct memory_block *mem, int nid); +#endif /* CONFIG_NUMA */ +int memory_block_advise_max_size(unsigned long size); +unsigned long memory_block_advised_max_size(void); +#endif /* CONFIG_MEMORY_HOTPLUG */ /* * Kernel text modification mutex, used for code patching. Users of this lock |