mirror of
https://github.com/torvalds/linux.git
synced 2026-04-22 00:33:58 -04:00
Pull MM updates from Andrew Morton:
"Along with the usual shower of singleton patches, notable patch series
in this pull request are:
- "Align kvrealloc() with krealloc()" from Danilo Krummrich. Adds
consistency to the APIs and behaviour of these two core allocation
functions. This also simplifies/enables Rustification.
- "Some cleanups for shmem" from Baolin Wang. No functional changes -
mode code reuse, better function naming, logic simplifications.
- "mm: some small page fault cleanups" from Josef Bacik. No
functional changes - code cleanups only.
- "Various memory tiering fixes" from Zi Yan. A small fix and a
little cleanup.
- "mm/swap: remove boilerplate" from Yu Zhao. Code cleanups and
simplifications and .text shrinkage.
- "Kernel stack usage histogram" from Pasha Tatashin and Shakeel
Butt. This is a feature, it adds new feilds to /proc/vmstat such as
$ grep kstack /proc/vmstat
kstack_1k 3
kstack_2k 188
kstack_4k 11391
kstack_8k 243
kstack_16k 0
which tells us that 11391 processes used 4k of stack while none at
all used 16k. Useful for some system tuning things, but
partivularly useful for "the dynamic kernel stack project".
- "kmemleak: support for percpu memory leak detect" from Pavel
Tikhomirov. Teaches kmemleak to detect leaksage of percpu memory.
- "mm: memcg: page counters optimizations" from Roman Gushchin. "3
independent small optimizations of page counters".
- "mm: split PTE/PMD PT table Kconfig cleanups+clarifications" from
David Hildenbrand. Improves PTE/PMD splitlock detection, makes
powerpc/8xx work correctly by design rather than by accident.
- "mm: remove arch_make_page_accessible()" from David Hildenbrand.
Some folio conversions which make arch_make_page_accessible()
unneeded.
- "mm, memcg: cg2 memory{.swap,}.peak write handlers" fro David
Finkel. Cleans up and fixes our handling of the resetting of the
cgroup/process peak-memory-use detector.
- "Make core VMA operations internal and testable" from Lorenzo
Stoakes. Rationalizaion and encapsulation of the VMA manipulation
APIs. With a view to better enable testing of the VMA functions,
even from a userspace-only harness.
- "mm: zswap: fixes for global shrinker" from Takero Funaki. Fix
issues in the zswap global shrinker, resulting in improved
performance.
- "mm: print the promo watermark in zoneinfo" from Kaiyang Zhao. Fill
in some missing info in /proc/zoneinfo.
- "mm: replace follow_page() by folio_walk" from David Hildenbrand.
Code cleanups and rationalizations (conversion to folio_walk())
resulting in the removal of follow_page().
- "improving dynamic zswap shrinker protection scheme" from Nhat
Pham. Some tuning to improve zswap's dynamic shrinker. Significant
reductions in swapin and improvements in performance are shown.
- "mm: Fix several issues with unaccepted memory" from Kirill
Shutemov. Improvements to the new unaccepted memory feature,
- "mm/mprotect: Fix dax puds" from Peter Xu. Implements mprotect on
DAX PUDs. This was missing, although nobody seems to have notied
yet.
- "Introduce a store type enum for the Maple tree" from Sidhartha
Kumar. Cleanups and modest performance improvements for the maple
tree library code.
- "memcg: further decouple v1 code from v2" from Shakeel Butt. Move
more cgroup v1 remnants away from the v2 memcg code.
- "memcg: initiate deprecation of v1 features" from Shakeel Butt.
Adds various warnings telling users that memcg v1 features are
deprecated.
- "mm: swap: mTHP swap allocator base on swap cluster order" from
Chris Li. Greatly improves the success rate of the mTHP swap
allocation.
- "mm: introduce numa_memblks" from Mike Rapoport. Moves various
disparate per-arch implementations of numa_memblk code into generic
code.
- "mm: batch free swaps for zap_pte_range()" from Barry Song. Greatly
improves the performance of munmap() of swap-filled ptes.
- "support large folio swap-out and swap-in for shmem" from Baolin
Wang. With this series we no longer split shmem large folios into
simgle-page folios when swapping out shmem.
- "mm/hugetlb: alloc/free gigantic folios" from Yu Zhao. Nice
performance improvements and code reductions for gigantic folios.
- "support shmem mTHP collapse" from Baolin Wang. Adds support for
khugepaged's collapsing of shmem mTHP folios.
- "mm: Optimize mseal checks" from Pedro Falcato. Fixes an mprotect()
performance regression due to the addition of mseal().
- "Increase the number of bits available in page_type" from Matthew
Wilcox. Increases the number of bits available in page_type!
- "Simplify the page flags a little" from Matthew Wilcox. Many legacy
page flags are now folio flags, so the page-based flags and their
accessors/mutators can be removed.
- "mm: store zero pages to be swapped out in a bitmap" from Usama
Arif. An optimization which permits us to avoid writing/reading
zero-filled zswap pages to backing store.
- "Avoid MAP_FIXED gap exposure" from Liam Howlett. Fixes a race
window which occurs when a MAP_FIXED operqtion is occurring during
an unrelated vma tree walk.
- "mm: remove vma_merge()" from Lorenzo Stoakes. Major rotorooting of
the vma_merge() functionality, making ot cleaner, more testable and
better tested.
- "misc fixups for DAMON {self,kunit} tests" from SeongJae Park.
Minor fixups of DAMON selftests and kunit tests.
- "mm: memory_hotplug: improve do_migrate_range()" from Kefeng Wang.
Code cleanups and folio conversions.
- "Shmem mTHP controls and stats improvements" from Ryan Roberts.
Cleanups for shmem controls and stats.
- "mm: count the number of anonymous THPs per size" from Barry Song.
Expose additional anon THP stats to userspace for improved tuning.
- "mm: finish isolate/putback_lru_page()" from Kefeng Wang: more
folio conversions and removal of now-unused page-based APIs.
- "replace per-quota region priorities histogram buffer with
per-context one" from SeongJae Park. DAMON histogram
rationalization.
- "Docs/damon: update GitHub repo URLs and maintainer-profile" from
SeongJae Park. DAMON documentation updates.
- "mm/vdpa: correct misuse of non-direct-reclaim __GFP_NOFAIL and
improve related doc and warn" from Jason Wang: fixes usage of page
allocator __GFP_NOFAIL and GFP_ATOMIC flags.
- "mm: split underused THPs" from Yu Zhao. Improve THP=always policy.
This was overprovisioning THPs in sparsely accessed memory areas.
- "zram: introduce custom comp backends API" frm Sergey Senozhatsky.
Add support for zram run-time compression algorithm tuning.
- "mm: Care about shadow stack guard gap when getting an unmapped
area" from Mark Brown. Fix up the various arch_get_unmapped_area()
implementations to better respect guard areas.
- "Improve mem_cgroup_iter()" from Kinsey Ho. Improve the reliability
of mem_cgroup_iter() and various code cleanups.
- "mm: Support huge pfnmaps" from Peter Xu. Extends the usage of huge
pfnmap support.
- "resource: Fix region_intersects() vs add_memory_driver_managed()"
from Huang Ying. Fix a bug in region_intersects() for systems with
CXL memory.
- "mm: hwpoison: two more poison recovery" from Kefeng Wang. Teaches
a couple more code paths to correctly recover from the encountering
of poisoned memry.
- "mm: enable large folios swap-in support" from Barry Song. Support
the swapin of mTHP memory into appropriately-sized folios, rather
than into single-page folios"
* tag 'mm-stable-2024-09-20-02-31' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (416 commits)
zram: free secondary algorithms names
uprobes: turn xol_area->pages[2] into xol_area->page
uprobes: introduce the global struct vm_special_mapping xol_mapping
Revert "uprobes: use vm_special_mapping close() functionality"
mm: support large folios swap-in for sync io devices
mm: add nr argument in mem_cgroup_swapin_uncharge_swap() helper to support large folios
mm: fix swap_read_folio_zeromap() for large folios with partial zeromap
mm/debug_vm_pgtable: Use pxdp_get() for accessing page table entries
set_memory: add __must_check to generic stubs
mm/vma: return the exact errno in vms_gather_munmap_vmas()
memcg: cleanup with !CONFIG_MEMCG_V1
mm/show_mem.c: report alloc tags in human readable units
mm: support poison recovery from copy_present_page()
mm: support poison recovery from do_cow_fault()
resource, kunit: add test case for region_intersects()
resource: make alloc_free_mem_region() works for iomem_resource
mm: z3fold: deprecate CONFIG_Z3FOLD
vfio/pci: implement huge_fault support
mm/arm64: support large pfn mappings
mm/x86: support large pfn mappings
...
144 lines
4.2 KiB
C
144 lines
4.2 KiB
C
/*
|
|
* Compressed RAM block device
|
|
*
|
|
* Copyright (C) 2008, 2009, 2010 Nitin Gupta
|
|
* 2012, 2013 Minchan Kim
|
|
*
|
|
* This code is released using a dual license strategy: BSD/GPL
|
|
* You can choose the licence that better fits your requirements.
|
|
*
|
|
* Released under the terms of 3-clause BSD License
|
|
* Released under the terms of GNU General Public License Version 2.0
|
|
*
|
|
*/
|
|
|
|
#ifndef _ZRAM_DRV_H_
|
|
#define _ZRAM_DRV_H_
|
|
|
|
#include <linux/rwsem.h>
|
|
#include <linux/zsmalloc.h>
|
|
#include <linux/crypto.h>
|
|
|
|
#include "zcomp.h"
|
|
|
|
#define SECTORS_PER_PAGE_SHIFT (PAGE_SHIFT - SECTOR_SHIFT)
|
|
#define SECTORS_PER_PAGE (1 << SECTORS_PER_PAGE_SHIFT)
|
|
#define ZRAM_LOGICAL_BLOCK_SHIFT 12
|
|
#define ZRAM_LOGICAL_BLOCK_SIZE (1 << ZRAM_LOGICAL_BLOCK_SHIFT)
|
|
#define ZRAM_SECTOR_PER_LOGICAL_BLOCK \
|
|
(1 << (ZRAM_LOGICAL_BLOCK_SHIFT - SECTOR_SHIFT))
|
|
|
|
|
|
/*
|
|
* ZRAM is mainly used for memory efficiency so we want to keep memory
|
|
* footprint small and thus squeeze size and zram pageflags into a flags
|
|
* member. The lower ZRAM_FLAG_SHIFT bits is for object size (excluding
|
|
* header), which cannot be larger than PAGE_SIZE (requiring PAGE_SHIFT
|
|
* bits), the higher bits are for zram_pageflags.
|
|
*
|
|
* We use BUILD_BUG_ON() to make sure that zram pageflags don't overflow.
|
|
*/
|
|
#define ZRAM_FLAG_SHIFT (PAGE_SHIFT + 1)
|
|
|
|
/* Only 2 bits are allowed for comp priority index */
|
|
#define ZRAM_COMP_PRIORITY_MASK 0x3
|
|
|
|
/* Flags for zram pages (table[page_no].flags) */
|
|
enum zram_pageflags {
|
|
ZRAM_SAME = ZRAM_FLAG_SHIFT, /* Page consists the same element */
|
|
ZRAM_WB, /* page is stored on backing_device */
|
|
ZRAM_UNDER_WB, /* page is under writeback */
|
|
ZRAM_HUGE, /* Incompressible page */
|
|
ZRAM_IDLE, /* not accessed page since last idle marking */
|
|
ZRAM_INCOMPRESSIBLE, /* none of the algorithms could compress it */
|
|
|
|
ZRAM_COMP_PRIORITY_BIT1, /* First bit of comp priority index */
|
|
ZRAM_COMP_PRIORITY_BIT2, /* Second bit of comp priority index */
|
|
|
|
__NR_ZRAM_PAGEFLAGS,
|
|
};
|
|
|
|
/*-- Data structures */
|
|
|
|
/* Allocated for each disk page */
|
|
struct zram_table_entry {
|
|
union {
|
|
unsigned long handle;
|
|
unsigned long element;
|
|
};
|
|
unsigned int flags;
|
|
spinlock_t lock;
|
|
#ifdef CONFIG_ZRAM_TRACK_ENTRY_ACTIME
|
|
ktime_t ac_time;
|
|
#endif
|
|
};
|
|
|
|
struct zram_stats {
|
|
atomic64_t compr_data_size; /* compressed size of pages stored */
|
|
atomic64_t failed_reads; /* can happen when memory is too low */
|
|
atomic64_t failed_writes; /* can happen when memory is too low */
|
|
atomic64_t notify_free; /* no. of swap slot free notifications */
|
|
atomic64_t same_pages; /* no. of same element filled pages */
|
|
atomic64_t huge_pages; /* no. of huge pages */
|
|
atomic64_t huge_pages_since; /* no. of huge pages since zram set up */
|
|
atomic64_t pages_stored; /* no. of pages currently stored */
|
|
atomic_long_t max_used_pages; /* no. of maximum pages stored */
|
|
atomic64_t writestall; /* no. of write slow paths */
|
|
atomic64_t miss_free; /* no. of missed free */
|
|
#ifdef CONFIG_ZRAM_WRITEBACK
|
|
atomic64_t bd_count; /* no. of pages in backing device */
|
|
atomic64_t bd_reads; /* no. of reads from backing device */
|
|
atomic64_t bd_writes; /* no. of writes from backing device */
|
|
#endif
|
|
};
|
|
|
|
#ifdef CONFIG_ZRAM_MULTI_COMP
|
|
#define ZRAM_PRIMARY_COMP 0U
|
|
#define ZRAM_SECONDARY_COMP 1U
|
|
#define ZRAM_MAX_COMPS 4U
|
|
#else
|
|
#define ZRAM_PRIMARY_COMP 0U
|
|
#define ZRAM_SECONDARY_COMP 0U
|
|
#define ZRAM_MAX_COMPS 1U
|
|
#endif
|
|
|
|
struct zram {
|
|
struct zram_table_entry *table;
|
|
struct zs_pool *mem_pool;
|
|
struct zcomp *comps[ZRAM_MAX_COMPS];
|
|
struct zcomp_params params[ZRAM_MAX_COMPS];
|
|
struct gendisk *disk;
|
|
/* Prevent concurrent execution of device init */
|
|
struct rw_semaphore init_lock;
|
|
/*
|
|
* the number of pages zram can consume for storing compressed data
|
|
*/
|
|
unsigned long limit_pages;
|
|
|
|
struct zram_stats stats;
|
|
/*
|
|
* This is the limit on amount of *uncompressed* worth of data
|
|
* we can store in a disk.
|
|
*/
|
|
u64 disksize; /* bytes */
|
|
const char *comp_algs[ZRAM_MAX_COMPS];
|
|
s8 num_active_comps;
|
|
/*
|
|
* zram is claimed so open request will be failed
|
|
*/
|
|
bool claim; /* Protected by disk->open_mutex */
|
|
#ifdef CONFIG_ZRAM_WRITEBACK
|
|
struct file *backing_dev;
|
|
spinlock_t wb_limit_lock;
|
|
bool wb_limit_enable;
|
|
u64 bd_wb_limit;
|
|
struct block_device *bdev;
|
|
unsigned long *bitmap;
|
|
unsigned long nr_pages;
|
|
#endif
|
|
#ifdef CONFIG_ZRAM_MEMORY_TRACKING
|
|
struct dentry *debugfs_dir;
|
|
#endif
|
|
};
|
|
#endif
|