Files
linux/include/linux/memory.h
Linus Torvalds 7203ca412f Merge tag 'mm-stable-2025-12-03-21-26' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Pull MM updates from Andrew Morton:

  "__vmalloc()/kvmalloc() and no-block support" (Uladzislau Rezki)
     Rework the vmalloc() code to support non-blocking allocations
     (GFP_ATOIC, GFP_NOWAIT)

  "ksm: fix exec/fork inheritance" (xu xin)
     Fix a rare case where the KSM MMF_VM_MERGE_ANY prctl state is not
     inherited across fork/exec

  "mm/zswap: misc cleanup of code and documentations" (SeongJae Park)
     Some light maintenance work on the zswap code

  "mm/page_owner: add debugfs files 'show_handles' and 'show_stacks_handles'" (Mauricio Faria de Oliveira)
     Enhance the /sys/kernel/debug/page_owner debug feature by adding
     unique identifiers to differentiate the various stack traces so
     that userspace monitoring tools can better match stack traces over
     time

  "mm/page_alloc: pcp->batch cleanups" (Joshua Hahn)
     Minor alterations to the page allocator's per-cpu-pages feature

  "Improve UFFDIO_MOVE scalability by removing anon_vma lock" (Lokesh Gidra)
     Address a scalability issue in userfaultfd's UFFDIO_MOVE operation

  "kasan: cleanups for kasan_enabled() checks" (Sabyrzhan Tasbolatov)

  "drivers/base/node: fold node register and unregister functions" (Donet Tom)
     Clean up the NUMA node handling code a little

  "mm: some optimizations for prot numa" (Kefeng Wang)
     Cleanups and small optimizations to the NUMA allocation hinting
     code

  "mm/page_alloc: Batch callers of free_pcppages_bulk" (Joshua Hahn)
     Address long lock hold times at boot on large machines. These were
     causing (harmless) softlockup warnings

  "optimize the logic for handling dirty file folios during reclaim" (Baolin Wang)
     Remove some now-unnecessary work from page reclaim

  "mm/damon: allow DAMOS auto-tuned for per-memcg per-node memory usage" (SeongJae Park)
     Enhance the DAMOS auto-tuning feature

  "mm/damon: fixes for address alignment issues in DAMON_LRU_SORT and DAMON_RECLAIM" (Quanmin Yan)
     Fix DAMON_LRU_SORT and DAMON_RECLAIM with certain userspace
     configuration

  "expand mmap_prepare functionality, port more users" (Lorenzo Stoakes)
     Enhance the new(ish) file_operations.mmap_prepare() method and port
     additional callsites from the old ->mmap() over to ->mmap_prepare()

  "Fix stale IOTLB entries for kernel address space" (Lu Baolu)
     Fix a bug (and possible security issue on non-x86) in the IOMMU
     code. In some situations the IOMMU could be left hanging onto a
     stale kernel pagetable entry

  "mm/huge_memory: cleanup __split_unmapped_folio()" (Wei Yang)
     Clean up and optimize the folio splitting code

  "mm, swap: misc cleanup and bugfix" (Kairui Song)
     Some cleanups and a minor fix in the swap discard code

  "mm/damon: misc documentation fixups" (SeongJae Park)

  "mm/damon: support pin-point targets removal" (SeongJae Park)
     Permit userspace to remove a specific monitoring target in the
     middle of the current targets list

  "mm: MISC follow-up patches for linux/pgalloc.h" (Harry Yoo)
     A couple of cleanups related to mm header file inclusion

  "mm/swapfile.c: select swap devices of default priority round robin" (Baoquan He)
     improve the selection of swap devices for NUMA machines

  "mm: Convert memory block states (MEM_*) macros to enums" (Israel Batista)
     Change the memory block labels from macros to enums so they will
     appear in kernel debug info

  "ksm: perform a range-walk to jump over holes in break_ksm" (Pedro Demarchi Gomes)
     Address an inefficiency when KSM unmerges an address range

  "mm/damon/tests: fix memory bugs in kunit tests" (SeongJae Park)
     Fix leaks and unhandled malloc() failures in DAMON userspace unit
     tests

  "some cleanups for pageout()" (Baolin Wang)
     Clean up a couple of minor things in the page scanner's
     writeback-for-eviction code

  "mm/hugetlb: refactor sysfs/sysctl interfaces" (Hui Zhu)
     Move hugetlb's sysfs/sysctl handling code into a new file

  "introduce VM_MAYBE_GUARD and make it sticky" (Lorenzo Stoakes)
     Make the VMA guard regions available in /proc/pid/smaps and
     improves the mergeability of guarded VMAs

  "mm: perform guard region install/remove under VMA lock" (Lorenzo Stoakes)
     Reduce mmap lock contention for callers performing VMA guard region
     operations

  "vma_start_write_killable" (Matthew Wilcox)
     Start work on permitting applications to be killed when they are
     waiting on a read_lock on the VMA lock

  "mm/damon/tests: add more tests for online parameters commit" (SeongJae Park)
     Add additional userspace testing of DAMON's "commit" feature

  "mm/damon: misc cleanups" (SeongJae Park)

  "make VM_SOFTDIRTY a sticky VMA flag" (Lorenzo Stoakes)
     Address the possible loss of a VMA's VM_SOFTDIRTY flag when that
     VMA is merged with another

  "mm: support device-private THP" (Balbir Singh)
     Introduce support for Transparent Huge Page (THP) migration in zone
     device-private memory

  "Optimize folio split in memory failure" (Zi Yan)

  "mm/huge_memory: Define split_type and consolidate split support checks" (Wei Yang)
     Some more cleanups in the folio splitting code

  "mm: remove is_swap_[pte, pmd]() + non-swap entries, introduce leaf entries" (Lorenzo Stoakes)
     Clean up our handling of pagetable leaf entries by introducing the
     concept of 'software leaf entries', of type softleaf_t

  "reparent the THP split queue" (Muchun Song)
     Reparent the THP split queue to its parent memcg. This is in
     preparation for addressing the long-standing "dying memcg" problem,
     wherein dead memcg's linger for too long, consuming memory
     resources

  "unify PMD scan results and remove redundant cleanup" (Wei Yang)
     A little cleanup in the hugepage collapse code

  "zram: introduce writeback bio batching" (Sergey Senozhatsky)
     Improve zram writeback efficiency by introducing batched bio
     writeback support

  "memcg: cleanup the memcg stats interfaces" (Shakeel Butt)
     Clean up our handling of the interrupt safety of some memcg stats

  "make vmalloc gfp flags usage more apparent" (Vishal Moola)
     Clean up vmalloc's handling of incoming GFP flags

  "mm: Add soft-dirty and uffd-wp support for RISC-V" (Chunyan Zhang)
     Teach soft dirty and userfaultfd write protect tracking to use
     RISC-V's Svrsw60t59b extension

  "mm: swap: small fixes and comment cleanups" (Youngjun Park)
     Fix a small bug and clean up some of the swap code

  "initial work on making VMA flags a bitmap" (Lorenzo Stoakes)
     Start work on converting the vma struct's flags to a bitmap, so we
     stop running out of them, especially on 32-bit

  "mm/swapfile: fix and cleanup swap list iterations" (Youngjun Park)
     Address a possible bug in the swap discard code and clean things
     up a little

[ This merge also reverts commit ebb9aeb980 ("vfio/nvgrace-gpu:
  register device memory for poison handling") because it looks
  broken to me, I've asked for clarification   - Linus ]

* tag 'mm-stable-2025-12-03-21-26' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (321 commits)
  mm: fix vma_start_write_killable() signal handling
  mm/swapfile: use plist_for_each_entry in __folio_throttle_swaprate
  mm/swapfile: fix list iteration when next node is removed during discard
  fs/proc/task_mmu.c: fix make_uffd_wp_huge_pte() huge pte handling
  mm/kfence: add reboot notifier to disable KFENCE on shutdown
  memcg: remove inc/dec_lruvec_kmem_state helpers
  selftests/mm/uffd: initialize char variable to Null
  mm: fix DEBUG_RODATA_TEST indentation in Kconfig
  mm: introduce VMA flags bitmap type
  tools/testing/vma: eliminate dependency on vma->__vm_flags
  mm: simplify and rename mm flags function for clarity
  mm: declare VMA flags by bit
  zram: fix a spelling mistake
  mm/page_alloc: optimize lowmem_reserve max lookup using its semantic monotonicity
  mm/vmscan: skip increasing kswapd_failures when reclaim was boosted
  pagemap: update BUDDY flag documentation
  mm: swap: remove scan_swap_map_slots() references from comments
  mm: swap: change swap_alloc_slow() to void
  mm, swap: remove redundant comment for read_swap_cache_async
  mm, swap: use SWP_SOLIDSTATE to determine if swap is rotational
  ...
2025-12-05 13:52:43 -08:00

211 lines
6.7 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>
#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;
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 */
/*
* 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 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);
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;
};
struct notifier_block;
struct mem_section;
/*
* Priorities for the hotplug memory callback routines. Invoked from
* high to low. Higher priorities correspond to higher numbers.
*/
#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;
}
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(enum memory_block_state state, void *v)
{
return 0;
}
static inline int hotplug_memory_notifier(notifier_fn_t fn, int pri)
{
return 0;
}
static inline int memory_block_advise_max_size(unsigned long size)
{
return -ENODEV;
}
static inline unsigned long memory_block_advised_max_size(void)
{
return 0;
}
#else /* CONFIG_MEMORY_HOTPLUG */
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,
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); \
})
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
* can sleep.
*/
extern struct mutex text_mutex;
#endif /* _LINUX_MEMORY_H_ */