diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2023-06-28 10:28:11 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2023-06-28 10:28:11 -0700 |
| commit | 6e17c6de3ddf3073741d9c91a796ee696914d8a0 (patch) | |
| tree | 2c425707f78642625dbe2c824c7fded2021e3dc7 /include/linux | |
| parent | 6aeadf7896bff4ca230702daba8788455e6b866e (diff) | |
| parent | acc72d59c7509540c27c49625cb4b5a8db1f1a84 (diff) | |
Merge tag 'mm-stable-2023-06-24-19-15' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Pull mm updates from Andrew Morton:
- Yosry Ahmed brought back some cgroup v1 stats in OOM logs
- Yosry has also eliminated cgroup's atomic rstat flushing
- Nhat Pham adds the new cachestat() syscall. It provides userspace
with the ability to query pagecache status - a similar concept to
mincore() but more powerful and with improved usability
- Mel Gorman provides more optimizations for compaction, reducing the
prevalence of page rescanning
- Lorenzo Stoakes has done some maintanance work on the
get_user_pages() interface
- Liam Howlett continues with cleanups and maintenance work to the
maple tree code. Peng Zhang also does some work on maple tree
- Johannes Weiner has done some cleanup work on the compaction code
- David Hildenbrand has contributed additional selftests for
get_user_pages()
- Thomas Gleixner has contributed some maintenance and optimization
work for the vmalloc code
- Baolin Wang has provided some compaction cleanups,
- SeongJae Park continues maintenance work on the DAMON code
- Huang Ying has done some maintenance on the swap code's usage of
device refcounting
- Christoph Hellwig has some cleanups for the filemap/directio code
- Ryan Roberts provides two patch series which yield some
rationalization of the kernel's access to pte entries - use the
provided APIs rather than open-coding accesses
- Lorenzo Stoakes has some fixes to the interaction between pagecache
and directio access to file mappings
- John Hubbard has a series of fixes to the MM selftesting code
- ZhangPeng continues the folio conversion campaign
- Hugh Dickins has been working on the pagetable handling code, mainly
with a view to reducing the load on the mmap_lock
- Catalin Marinas has reduced the arm64 kmalloc() minimum alignment
from 128 to 8
- Domenico Cerasuolo has improved the zswap reclaim mechanism by
reorganizing the LRU management
- Matthew Wilcox provides some fixups to make gfs2 work better with the
buffer_head code
- Vishal Moola also has done some folio conversion work
- Matthew Wilcox has removed the remnants of the pagevec code - their
functionality is migrated over to struct folio_batch
* tag 'mm-stable-2023-06-24-19-15' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (380 commits)
mm/hugetlb: remove hugetlb_set_page_subpool()
mm: nommu: correct the range of mmap_sem_read_lock in task_mem()
hugetlb: revert use of page_cache_next_miss()
Revert "page cache: fix page_cache_next/prev_miss off by one"
mm/vmscan: fix root proactive reclaim unthrottling unbalanced node
mm: memcg: rename and document global_reclaim()
mm: kill [add|del]_page_to_lru_list()
mm: compaction: convert to use a folio in isolate_migratepages_block()
mm: zswap: fix double invalidate with exclusive loads
mm: remove unnecessary pagevec includes
mm: remove references to pagevec
mm: rename invalidate_mapping_pagevec to mapping_try_invalidate
mm: remove struct pagevec
net: convert sunrpc from pagevec to folio_batch
i915: convert i915_gpu_error to use a folio_batch
pagevec: rename fbatch_count()
mm: remove check_move_unevictable_pages()
drm: convert drm_gem_put_pages() to use a folio_batch
i915: convert shmem_sg_free_table() to use a folio_batch
scatterlist: add sg_set_folio()
...
Diffstat (limited to 'include/linux')
38 files changed, 587 insertions, 637 deletions
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 1520793c72da..c794ea7096ba 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -263,7 +263,7 @@ extern int buffer_heads_over_limit; void block_invalidate_folio(struct folio *folio, size_t offset, size_t length); int block_write_full_page(struct page *page, get_block_t *get_block, struct writeback_control *wbc); -int __block_write_full_page(struct inode *inode, struct page *page, +int __block_write_full_folio(struct inode *inode, struct folio *folio, get_block_t *get_block, struct writeback_control *wbc, bh_end_io_t *handler); int block_read_full_folio(struct folio *, get_block_t *); @@ -278,7 +278,7 @@ int block_write_end(struct file *, struct address_space *, int generic_write_end(struct file *, struct address_space *, loff_t, unsigned, unsigned, struct page *, void *); -void page_zero_new_buffers(struct page *page, unsigned from, unsigned to); +void folio_zero_new_buffers(struct folio *folio, size_t from, size_t to); void clean_page_buffers(struct page *page); int cont_write_begin(struct file *, struct address_space *, loff_t, unsigned, struct page **, void **, diff --git a/include/linux/cache.h b/include/linux/cache.h index 5da1bbd96154..9900d20b76c2 100644 --- a/include/linux/cache.h +++ b/include/linux/cache.h @@ -98,4 +98,10 @@ struct cacheline_padding { #define CACHELINE_PADDING(name) #endif +#ifdef ARCH_DMA_MINALIGN +#define ARCH_HAS_DMA_MINALIGN +#else +#define ARCH_DMA_MINALIGN __alignof__(unsigned long long) +#endif + #endif /* __LINUX_CACHE_H */ diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 1261a47932a6..b307013b9c6c 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -691,7 +691,6 @@ static inline void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen) */ void cgroup_rstat_updated(struct cgroup *cgrp, int cpu); void cgroup_rstat_flush(struct cgroup *cgrp); -void cgroup_rstat_flush_atomic(struct cgroup *cgrp); void cgroup_rstat_flush_hold(struct cgroup *cgrp); void cgroup_rstat_flush_release(void); diff --git a/include/linux/compaction.h b/include/linux/compaction.h index a6e512cfb670..e94776496049 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -89,89 +89,17 @@ extern enum compact_result try_to_compact_pages(gfp_t gfp_mask, const struct alloc_context *ac, enum compact_priority prio, struct page **page); extern void reset_isolation_suitable(pg_data_t *pgdat); -extern enum compact_result compaction_suitable(struct zone *zone, int order, - unsigned int alloc_flags, int highest_zoneidx); +extern bool compaction_suitable(struct zone *zone, int order, + int highest_zoneidx); extern void compaction_defer_reset(struct zone *zone, int order, bool alloc_success); -/* Compaction has made some progress and retrying makes sense */ -static inline bool compaction_made_progress(enum compact_result result) -{ - /* - * Even though this might sound confusing this in fact tells us - * that the compaction successfully isolated and migrated some - * pageblocks. - */ - if (result == COMPACT_SUCCESS) - return true; - - return false; -} - -/* Compaction has failed and it doesn't make much sense to keep retrying. */ -static inline bool compaction_failed(enum compact_result result) -{ - /* All zones were scanned completely and still not result. */ - if (result == COMPACT_COMPLETE) - return true; - - return false; -} - -/* Compaction needs reclaim to be performed first, so it can continue. */ -static inline bool compaction_needs_reclaim(enum compact_result result) -{ - /* - * Compaction backed off due to watermark checks for order-0 - * so the regular reclaim has to try harder and reclaim something. - */ - if (result == COMPACT_SKIPPED) - return true; - - return false; -} - -/* - * Compaction has backed off for some reason after doing some work or none - * at all. It might be throttling or lock contention. Retrying might be still - * worthwhile, but with a higher priority if allowed. - */ -static inline bool compaction_withdrawn(enum compact_result result) -{ - /* - * If compaction is deferred for high-order allocations, it is - * because sync compaction recently failed. If this is the case - * and the caller requested a THP allocation, we do not want - * to heavily disrupt the system, so we fail the allocation - * instead of entering direct reclaim. - */ - if (result == COMPACT_DEFERRED) - return true; - - /* - * If compaction in async mode encounters contention or blocks higher - * priority task we back off early rather than cause stalls. - */ - if (result == COMPACT_CONTENDED) - return true; - - /* - * Page scanners have met but we haven't scanned full zones so this - * is a back off in fact. - */ - if (result == COMPACT_PARTIAL_SKIPPED) - return true; - - return false; -} - - bool compaction_zonelist_suitable(struct alloc_context *ac, int order, int alloc_flags); -extern void kcompactd_run(int nid); -extern void kcompactd_stop(int nid); +extern void __meminit kcompactd_run(int nid); +extern void __meminit kcompactd_stop(int nid); extern void wakeup_kcompactd(pg_data_t *pgdat, int order, int highest_zoneidx); #else @@ -179,32 +107,12 @@ static inline void reset_isolation_suitable(pg_data_t *pgdat) { } -static inline enum compact_result compaction_suitable(struct zone *zone, int order, - int alloc_flags, int highest_zoneidx) -{ - return COMPACT_SKIPPED; -} - -static inline bool compaction_made_progress(enum compact_result result) -{ - return false; -} - -static inline bool compaction_failed(enum compact_result result) -{ - return false; -} - -static inline bool compaction_needs_reclaim(enum compact_result result) +static inline bool compaction_suitable(struct zone *zone, int order, + int highest_zoneidx) { return false; } -static inline bool compaction_withdrawn(enum compact_result result) -{ - return true; -} - static inline void kcompactd_run(int nid) { } diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h index 31f114f486c4..9bf19b5bf755 100644 --- a/include/linux/dma-map-ops.h +++ b/include/linux/dma-map-ops.h @@ -8,6 +8,7 @@ #include <linux/dma-mapping.h> #include <linux/pgtable.h> +#include <linux/slab.h> struct cma; @@ -277,6 +278,66 @@ static inline bool dev_is_dma_coherent(struct device *dev) } #endif /* CONFIG_ARCH_HAS_DMA_COHERENCE_H */ +/* + * Check whether potential kmalloc() buffers are safe for non-coherent DMA. + */ +static inline bool dma_kmalloc_safe(struct device *dev, + enum dma_data_direction dir) +{ + /* + * If DMA bouncing of kmalloc() buffers is disabled, the kmalloc() + * caches have already been aligned to a DMA-safe size. + */ + if (!IS_ENABLED(CONFIG_DMA_BOUNCE_UNALIGNED_KMALLOC)) + return true; + + /* + * kmalloc() buffers are DMA-safe irrespective of size if the device + * is coherent or the direction is DMA_TO_DEVICE (non-desctructive + * cache maintenance and benign cache line evictions). + */ + if (dev_is_dma_coherent(dev) || dir == DMA_TO_DEVICE) + return true; + + return false; +} + +/* + * Check whether the given size, assuming it is for a kmalloc()'ed buffer, is + * sufficiently aligned for non-coherent DMA. + */ +static inline bool dma_kmalloc_size_aligned(size_t size) +{ + /* + * Larger kmalloc() sizes are guaranteed to be aligned to + * ARCH_DMA_MINALIGN. + */ + if (size >= 2 * ARCH_DMA_MINALIGN || + IS_ALIGNED(kmalloc_size_roundup(size), dma_get_cache_alignment())) + return true; + + return false; +} + +/* + * Check whether the given object size may have originated from a kmalloc() + * buffer with a slab alignment below the DMA-safe alignment and needs + * bouncing for non-coherent DMA. The pointer alignment is not considered and + * in-structure DMA-safe offsets are the responsibility of the caller. Such + * code should use the static ARCH_DMA_MINALIGN for compiler annotations. + * + * The heuristics can have false positives, bouncing unnecessarily, though the + * buffers would be small. False negatives are theoretically possible if, for + * example, multiple small kmalloc() buffers are coalesced into a larger + * buffer that passes the alignment check. There are no such known constructs + * in the kernel. + */ +static inline bool dma_kmalloc_needs_bounce(struct device *dev, size_t size, + enum dma_data_direction dir) +{ + return !dma_kmalloc_safe(dev, dir) && !dma_kmalloc_size_aligned(size); +} + void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs); void arch_dma_free(struct device *dev, size_t size, void *cpu_addr, diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 0ee20b764000..e13050eb9777 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -2,6 +2,7 @@ #ifndef _LINUX_DMA_MAPPING_H #define _LINUX_DMA_MAPPING_H +#include <linux/cache.h> #include <linux/sizes.h> #include <linux/string.h> #include <linux/device.h> @@ -543,13 +544,15 @@ static inline int dma_set_min_align_mask(struct device *dev, return 0; } +#ifndef dma_get_cache_alignment static inline int dma_get_cache_alignment(void) { -#ifdef ARCH_DMA_MINALIGN +#ifdef ARCH_HAS_DMA_MINALIGN return ARCH_DMA_MINALIGN; #endif return 1; } +#endif static inline void *dmam_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp) diff --git a/include/linux/fault-inject.h b/include/linux/fault-inject.h index 481abf530b3c..6d5edef09d45 100644 --- a/include/linux/fault-inject.h +++ b/include/linux/fault-inject.h @@ -93,6 +93,15 @@ struct kmem_cache; bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order); +#ifdef CONFIG_FAIL_PAGE_ALLOC +bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order); +#else +static inline bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) +{ + return false; +} +#endif /* CONFIG_FAIL_PAGE_ALLOC */ + int should_failslab(struct kmem_cache *s, gfp_t gfpflags); #ifdef CONFIG_FAILSLAB extern bool __should_failslab(struct kmem_cache *s, gfp_t gfpflags); diff --git a/include/linux/frontswap.h b/include/linux/frontswap.h index a631bac12220..eaa0ac5f9003 100644 --- a/include/linux/frontswap.h +++ b/include/linux/frontswap.h @@ -10,7 +10,7 @@ struct frontswap_ops { void (*init)(unsigned); /* this swap type was just swapon'ed */ int (*store)(unsigned, pgoff_t, struct page *); /* store a page */ - int (*load)(unsigned, pgoff_t, struct page *); /* load a page */ + int (*load)(unsigned, pgoff_t, struct page *, bool *); /* load a page */ void (*invalidate_page)(unsigned, pgoff_t); /* page no longer needed */ void (*invalidate_area)(unsigned); /* swap type just swapoff'ed */ }; diff --git a/include/linux/fs.h b/include/linux/fs.h index ed5b32dc2625..122b218b66c9 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2763,6 +2763,8 @@ extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *); ssize_t generic_perform_write(struct kiocb *, struct iov_iter *); +ssize_t direct_write_fallback(struct kiocb *iocb, struct iov_iter *iter, + ssize_t direct_written, ssize_t buffered_written); ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags); @@ -2860,11 +2862,6 @@ static inline void inode_dio_end(struct inode *inode) wake_up_bit(&inode->i_state, __I_DIO_WAKEUP); } -/* - * Warn about a page cache invalidation failure diring a direct I/O write. - */ -void dio_warn_stale_pagecache(struct file *filp); - extern void inode_set_flags(struct inode *inode, unsigned int flags, unsigned int mask); diff --git a/include/linux/gfp.h b/include/linux/gfp.h index ed8cb537c6a7..665f06675c83 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -338,19 +338,12 @@ extern gfp_t gfp_allowed_mask; /* Returns true if the gfp_mask allows use of ALLOC_NO_WATERMARK */ bool gfp_pfmemalloc_allowed(gfp_t gfp_mask); -extern void pm_restrict_gfp_mask(void); -extern void pm_restore_gfp_mask(void); - -extern gfp_t vma_thp_gfp_mask(struct vm_area_struct *vma); - -#ifdef CONFIG_PM_SLEEP -extern bool pm_suspended_storage(void); -#else -static inline bool pm_suspended_storage(void) +static inline bool gfp_has_io_fs(gfp_t gfp) { - return false; + return (gfp & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS); } -#endif /* CONFIG_PM_SLEEP */ + +extern gfp_t vma_thp_gfp_mask(struct vm_area_struct *vma); #ifdef CONFIG_CONTIG_ALLOC /* The below functions must be run on a range from a single zone. */ diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 6d041aa9f0fe..ca3c8e10f24a 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -133,9 +133,8 @@ int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct page *hugetlb_follow_page_mask(struct vm_area_struct *vma, unsigned long address, unsigned int flags); long follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, - struct page **, struct vm_area_struct **, - unsigned long *, unsigned long *, long, unsigned int, - int *); + struct page **, unsigned long *, unsigned long *, + long, unsigned int, int *); void unmap_hugepage_range(struct vm_area_struct *, unsigned long, unsigned long, struct page *, zap_flags_t); @@ -306,9 +305,8 @@ static inline struct page *hugetlb_follow_page_mask(struct vm_area_struct *vma, static inline long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, struct page **pages, - struct vm_area_struct **vmas, unsigned long *position, - unsigned long *nr_pages, long i, unsigned int flags, - int *nonblocking) + unsigned long *position, unsigned long *nr_pages, + long i, unsigned int flags, int *nonblocking) { BUG(); return 0; @@ -757,26 +755,12 @@ static inline struct hugepage_subpool *hugetlb_folio_subpool(struct folio *folio return folio->_hugetlb_subpool; } -/* - * hugetlb page subpool pointer located in hpage[2].hugetlb_subpool - */ -static inline struct hugepage_subpool *hugetlb_page_subpool(struct page *hpage) -{ - return hugetlb_folio_subpool(page_folio(hpage)); -} - static inline void hugetlb_set_folio_subpool(struct folio *folio, struct hugepage_subpool *subpool) { folio->_hugetlb_subpool = subpool; } -static inline void hugetlb_set_page_subpool(struct page *hpage, - struct hugepage_subpool *subpool) -{ - hugetlb_set_folio_subpool(page_folio(hpage), subpool); -} - static inline struct hstate *hstate_file(struct file *f) { return hstate_inode(file_inode(f)); @@ -1031,11 +1015,6 @@ static inline struct hugepage_subpool *hugetlb_folio_subpool(struct folio *folio return NULL; } -static inline struct hugepage_subpool *hugetlb_page_subpool(struct page *hpage) -{ - return NULL; -} - static inline int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list) { @@ -1200,7 +1179,11 @@ static inline void hugetlb_count_sub(long l, struct mm_struct *mm) static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { +#ifdef CONFIG_MMU + return ptep_get(ptep); +#else return *ptep; +#endif } static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 81413cd3a3e7..d28a5e8097e4 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -722,7 +722,7 @@ static inline void *iio_device_get_drvdata(const struct iio_dev *indio_dev) * must not share cachelines with the rest of the structure, thus making * them safe for use with non-coherent DMA. */ -#define IIO_DMA_MINALIGN ARCH_KMALLOC_MINALIGN +#define IIO_DMA_MINALIGN ARCH_DMA_MINALIGN struct iio_dev *iio_device_alloc(struct device *parent, int sizeof_priv); /* The information at the returned address is guaranteed to be cacheline aligned */ diff --git a/include/linux/kasan.h b/include/linux/kasan.h index f7ef70661ce2..819b6bc8ac08 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -343,7 +343,7 @@ static inline void *kasan_reset_tag(const void *addr) * @is_write: whether the bad access is a write or a read * @ip: instruction pointer for the accessibility check or the bad access itself */ -bool kasan_report(unsigned long addr, size_t size, +bool kasan_report(const void *addr, size_t size, bool is_write, unsigned long ip); #else /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS */ diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h index 1fadb5f5978b..295548cca8b3 100644 --- a/include/linux/maple_tree.h +++ b/include/linux/maple_tree.h @@ -455,7 +455,9 @@ void *mas_erase(struct ma_state *mas); int mas_store_gfp(struct ma_state *mas, void *entry, gfp_t gfp); void mas_store_prealloc(struct ma_state *mas, void *entry); void *mas_find(struct ma_state *mas, unsigned long max); +void *mas_find_range(struct ma_state *mas, unsigned long max); void *mas_find_rev(struct ma_state *mas, unsigned long min); +void *mas_find_range_rev(struct ma_state *mas, unsigned long max); int mas_preallocate(struct ma_state *mas, gfp_t gfp); bool mas_is_err(struct ma_state *mas); @@ -466,10 +468,18 @@ void mas_destroy(struct ma_state *mas); int mas_expected_entries(struct ma_state *mas, unsigned long nr_entries); void *mas_prev(struct ma_state *mas, unsigned long min); +void *mas_prev_range(struct ma_state *mas, unsigned long max); void *mas_next(struct ma_state *mas, unsigned long max); +void *mas_next_range(struct ma_state *mas, unsigned long max); int mas_empty_area(struct ma_state *mas, unsigned long min, unsigned long max, unsigned long size); +/* + * This finds an empty area from the highest address to the lowest. + * AKA "Topdown" version, + */ +int mas_empty_area_rev(struct ma_state *mas, unsigned long min, + unsigned long max, unsigned long size); static inline void mas_init(struct ma_state *mas, struct maple_tree *tree, unsigned long addr) @@ -482,23 +492,17 @@ static inline void mas_init(struct ma_state *mas, struct maple_tree *tree, } /* Checks if a mas has not found anything */ -static inline bool mas_is_none(struct ma_state *mas) +static inline bool mas_is_none(const struct ma_state *mas) { return mas->node == MAS_NONE; } /* Checks if a mas has been paused */ -static inline bool mas_is_paused(struct ma_state *mas) +static inline bool mas_is_paused(const struct ma_state *mas) { return mas->node == MAS_PAUSE; } -/* - * This finds an empty area from the highest address to the lowest. - * AKA "Topdown" version, - */ -int mas_empty_area_rev(struct ma_state *mas, unsigned long min, - unsigned long max, unsigned long size); /** * mas_reset() - Reset a Maple Tree operation state. * @mas: Maple Tree operation state. @@ -528,7 +532,6 @@ static inline void mas_reset(struct ma_state *mas) #define mas_for_each(__mas, __entry, __max) \ while (((__entry) = mas_find((__mas), (__max))) != NULL) - /** * mas_set_range() - Set up Maple Tree operation state for a different index. * @mas: Maple Tree operation state. @@ -616,7 +619,7 @@ static inline void mt_clear_in_rcu(struct maple_tree *mt) return; if (mt_external_lock(mt)) { - BUG_ON(!mt_lock_is_held(mt)); + WARN_ON(!mt_lock_is_held(mt)); mt->ma_flags &= ~MT_FLAGS_USE_RCU; } else { mtree_lock(mt); @@ -635,7 +638,7 @@ static inline void mt_set_in_rcu(struct maple_tree *mt) return; if (mt_external_lock(mt)) { - BUG_ON(!mt_lock_is_held(mt)); + WARN_ON(!mt_lock_is_held(mt)); mt->ma_flags |= MT_FLAGS_USE_RCU; } else { mtree_lock(mt); @@ -670,10 +673,17 @@ void *mt_next(struct maple_tree *mt, unsigned long index, unsigned long max); #ifdef CONFIG_DEBUG_MAPLE_TREE +enum mt_dump_format { + mt_dump_dec, + mt_dump_hex, +}; + extern atomic_t maple_tree_tests_run; extern atomic_t maple_tree_tests_passed; -void mt_dump(const struct maple_tree *mt); +void mt_dump(const struct maple_tree *mt, enum mt_dump_format format); +void mas_dump(const struct ma_state *mas); +void mas_wr_dump(const struct ma_wr_state *wr_mas); void mt_validate(struct maple_tree *mt); void mt_cache_shrink(void); #define MT_BUG_ON(__tree, __x) do { \ @@ -681,7 +691,23 @@ void mt_cache_shrink(void); if (__x) { \ pr_info("BUG at %s:%d (%u)\n", \ __func__, __LINE__, __x); \ - mt_dump(__tree); \ + mt_dump(__tree, mt_dump_hex); \ + pr_info("Pass: %u Run:%u\n", \ + atomic_read(&maple_tree_tests_passed), \ + atomic_read(&maple_tree_tests_run)); \ + dump_stack(); \ + } else { \ + atomic_inc(&maple_tree_tests_passed); \ + } \ +} while (0) + +#define MAS_BUG_ON(__mas, __x) do { \ + atomic_inc(&maple_tree_tests_run); \ + if (__x) { \ + pr_info("BUG at %s:%d (%u)\n", \ + __func__, __LINE__, __x); \ + mas_dump(__mas); \ + mt_dump((__mas)->tree, mt_dump_hex); \ pr_info("Pass: %u Run:%u\n", \ atomic_read(&maple_tree_tests_passed), \ atomic_read(&maple_tree_tests_run)); \ @@ -690,8 +716,84 @@ void mt_cache_shrink(void); atomic_inc(&maple_tree_tests_passed); \ } \ } while (0) + +#define MAS_WR_BUG_ON(__wrmas, __x) do { \ + atomic_inc(&maple_tree_tests_run); \ + if (__x) { \ + pr_info("BUG at %s:%d (%u)\n", \ + __func__, __LINE__, __x); \ + mas_wr_dump(__wrmas); \ + mas_dump((__wrmas)->mas); \ + mt_dump((__wrmas)->mas->tree, mt_dump_hex); \ + pr_info("Pass: %u Run:%u\n", \ + atomic_read(&maple_tree_tests_passed), \ + atomic_read(&maple_tree_tests_run)); \ + dump_stack(); \ + } else { \ + atomic_inc(&maple_tree_tests_passed); \ + } \ +} while (0) + +#define MT_WARN_ON(__tree, __x) ({ \ + int ret = !!(__x); \ + atomic_inc(&maple_tree_tests_run); \ + if (ret) { \ + pr_info("WARN at %s:%d (%u)\n", \ + __func__, __LINE__, __x); \ + mt_dump(__tree, mt_dump_hex); \ + pr_info("Pass: %u Run:%u\n", \ + atomic_read(&maple_tree_tests_passed), \ + atomic_read(&maple_tree_tests_run)); \ + dump_stack(); \ + } else { \ + atomic_inc(&maple_tree_tests_passed); \ + } \ + unlikely(ret); \ +}) + +#define MAS_WARN_ON(__mas, __x) ({ \ + int ret = !!(__x); \ + atomic_inc(&maple_tree_tests_run); \ + if (ret) { \ + pr_info("WARN at %s:%d (%u)\n", \ + __func__, __LINE__, __x); \ + mas_dump(__mas); \ + mt_dump((__mas)->tree, mt_dump_hex); \ + pr_info("Pass: %u Run:%u\n", \ + atomic_read(&maple_tree_tests_passed), \ + atomic_read(&maple_tree_tests_run)); \ + dump_stack(); \ + } else { \ + atomic_inc(&maple_tree_tests_passed); \ + } \ + unlikely(ret); \ +}) + +#define MAS_WR_WARN_ON(__wrmas, __x) ({ \ + int ret = !!(__x); \ + atomic_inc(&maple_tree_tests_run); \ + if (ret) { \ + pr_info("WARN at %s:%d (%u)\n", \ + __func__, __LINE__, __x); \ + mas_wr_dump(__wrmas); \ + mas_dump((__wrmas)->mas); \ + mt_dump((__wrmas)->mas->tree, mt_dump_hex); \ + pr_info("Pass: %u Run:%u\n", \ + atomic_read(&maple_tree_tests_passed), \ + atomic_read(&maple_tree_tests_run)); \ + dump_stack(); \ + } else { \ + atomic_inc(&maple_tree_tests_passed); \ + } \ + unlikely(ret); \ +}) #else -#define MT_BUG_ON(__tree, __x) BUG_ON(__x) +#define MT_BUG_ON(__tree, __x) BUG_ON(__x) +#define MAS_BUG_ON(__mas, __x) BUG_ON(__x) +#define MAS_WR_BUG_ON(__mas, __x) BUG_ON(__x) +#define MT_WARN_ON(__tree, __x) WARN_ON(__x) +#define MAS_WARN_ON(__mas, __x) WARN_ON(__x) +#define MAS_WR_WARN_ON(__mas, __x) WARN_ON(__x) #endif /* CONFIG_DEBUG_MAPLE_TREE */ #endif /*_LINUX_MAPLE_TREE_H */ diff --git a/include/linux/memblock.h b/include/linux/memblock.h index f82ee3fac1cd..f71ff9f0ec81 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -128,7 +128,6 @@ int memblock_clear_nomap(phys_addr_t base, phys_addr_t size); void memblock_free_all(void); void memblock_free(void *ptr, size_t size); -void reset_node_managed_pages(pg_data_t *pgdat); void reset_all_zones_managed_pages(void); /* Low level functions */ diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 222d7370134c..5818af8eca5a 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -419,7 +419,7 @@ static inline struct obj_cgroup *__folio_objcg(struct folio *folio) * * - the folio lock * - LRU isolation - * - lock_page_memcg() + * - folio_memcg_lock() * - exclusive reference * - mem_cgroup_trylock_pages() * @@ -820,8 +820,8 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *, struct mem_cgroup *, struct mem_cgroup_reclaim_cookie *); void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *); -int mem_cgroup_scan_tasks(struct mem_cgroup *, - int (*)(struct task_struct *, void *), void *); +void mem_cgroup_scan_tasks(struct mem_cgroup *memcg, + int (*)(struct task_struct *, void *), void *arg); static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg) { @@ -949,8 +949,6 @@ void mem_cgroup_print_oom_group(struct mem_cgroup *memcg); void folio_memcg_lock(struct folio *folio); void folio_memcg_unlock(struct folio *folio); -void lock_page_memcg(struct page *page); -void unlock_page_memcg(struct page *page); void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val); @@ -1038,7 +1036,6 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, } void mem_cgroup_flush_stats(void); -void mem_cgroup_flush_stats_atomic(void); void mem_cgroup_flush_stats_ratelimited(void); void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, @@ -1367,10 +1364,9 @@ static inline void mem_cgroup_iter_break(struct mem_cgroup *root, { } -static inline int mem_cgroup_scan_tasks(struct mem_cgroup *memcg, +static inline void mem_cgroup_scan_tasks(struct mem_cgroup *memcg, int (*fn)(struct task_struct *, void *), void *arg) { - return 0; } static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg) @@ -1439,14 +1435,6 @@ mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg) { } -static inline void lock_page_memcg(struct page *page) -{ -} - -static inline void unlock_page_memcg(struct page *page) -{ -} - static inline void folio_memcg_lock(struct folio *folio) { } @@ -1537,10 +1525,6 @@ static inline void mem_cgroup_flush_stats(void) { } -static inline void mem_cgroup_flush_stats_atomic(void) -{ -} - static inline void mem_cgroup_flush_stats_ratelimited(void) { } diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 9fcbf5706595..013c69753c91 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -326,9 +326,6 @@ static inline int remove_memory(u64 start, u64 size) static inline void __remove_memory(u64 start, u64 size) {} #endif /* CONFIG_MEMORY_HOTREMOVE */ -extern void set_zone_contiguous(struct zone *zone); -extern void clear_zone_contiguous(struct zone *zone); - #ifdef CONFIG_MEMORY_HOTPLUG extern void __ref free_area_init_core_hotplug(struct pglist_data *pgdat); extern int __add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags); @@ -347,9 +344,8 @@ extern void remove_pfn_range_from_zone(struct zone *zone, extern int sparse_add_section(int nid, unsigned long pfn, unsigned long nr_pages, struct vmem_altmap *altmap, struct dev_pagemap *pgmap); -extern void sparse_remove_section(struct mem_section *ms, - unsigned long pfn, unsigned long nr_pages, - unsigned long map_offset, struct vmem_altmap *altmap); +extern void sparse_remove_section(unsigned long pfn, unsigned long nr_pages, + struct vmem_altmap *altmap); extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map, unsigned long pnum); extern struct zone *zone_for_pfn_range(int online_type, int nid, diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 6241a1596a75..711dd9412561 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -7,8 +7,8 @@ #include <linux/migrate_mode.h> #include <linux/hugetlb.h> -typedef struct page *new_page_t(struct page *page, unsigned long private); -typedef void free_page_t(struct page *page, unsigned long private); +typedef struct folio *new_folio_t(struct folio *folio, unsigned long private); +typedef void free_folio_t(struct folio *folio, unsigned long private); struct migration_target_control; @@ -67,16 +67,16 @@ int migrate_folio_extra(struct address_space *mapping, struct folio *dst, struct folio *src, enum migrate_mode mode, int extra_count); int migrate_folio(struct address_space *mapping, struct folio *dst, struct folio *src, enum migrate_mode mode); -int migrate_pages(struct list_head *l, new_page_t new, free_page_t free, +int migrate_pages(struct list_head *l, new_folio_t new, free_folio_t free, unsigned long private, enum migrate_mode mode, int reason, unsigned int *ret_succeeded); -struct page *alloc_migration_target(struct page *page, unsigned long private); +struct folio *alloc_migration_target(struct folio *src, unsigned long private); bool isolate_movable_page(struct page *page, isolate_mode_t mode); int migrate_huge_page_move_mapping(struct address_space *mapping, struct folio *dst, struct folio *src); -void migration_entry_wait_on_locked(swp_entry_t entry, pte_t *ptep, - spinlock_t *ptl); +void migration_entry_wait_on_locked(swp_entry_t entry, spinlock_t *ptl) + __releases(ptl); void folio_migrate_flags(struct folio *newfolio, struct folio *folio); void folio_migrate_copy(struct folio *newfolio, struct folio *folio); int folio_migrate_mapping(struct address_space *mapping, @@ -85,11 +85,11 @@ int folio_migrate_mapping(struct address_space *mapping, #else static inline void putback_movable_pages(struct list_head *l) {} -static inline int migrate_pages(struct list_head *l, new_page_t new, - free_page_t free, unsigned long private, enum migrate_mode mode, - int reason, unsigned int *ret_succeeded) +static inline int migrate_pages(struct list_head *l, new_folio_t new, + free_folio_t free, unsigned long private, + enum migrate_mode mode, int reason, unsigned int *ret_succeeded) { return -ENOSYS; } -static inline struct page *alloc_migration_target(struct page *page, +static inline struct folio *alloc_migration_target(struct folio *src, unsigned long private) { return NULL; } static inline bool isolate_movable_page(struct page *page, isolate_mode_t mode) diff --git a/include/linux/mm.h b/include/linux/mm.h index fec149585985..ae866bc9bad6 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -725,7 +725,6 @@ struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, #else /* CONFIG_PER_VMA_LOCK */ -static inline void vma_init_lock(struct vm_area_struct *vma) {} static inline bool vma_start_read(struct vm_area_struct *vma) { return false; } static inline void vma_end_read(struct vm_area_struct *vma) {} @@ -866,11 +865,24 @@ static inline struct vm_area_struct *vma_next(struct vma_iterator *vmi) return mas_find(&vmi->mas, ULONG_MAX); } +static inline +struct vm_area_struct *vma_iter_next_range(struct vma_iterator *vmi) +{ + return mas_next_range(&vmi->mas, ULONG_MAX); +} + + static inline struct vm_area_struct *vma_prev(struct vma_iterator *vmi) { return mas_prev(&vmi->mas, 0); } +static inline +struct vm_area_struct *vma_iter_prev_range(struct vma_iterator *vmi) +{ + return mas_prev_range(&vmi->mas, 0); +} + static inline unsigned long vma_iter_addr(struct vma_iterator *vmi) { return vmi->mas.index; @@ -1208,17 +1220,6 @@ enum compound_dtor_id { #endif NR_COMPOUND_DTORS, }; -extern compound_page_dtor * const compound_page_dtors[NR_COMPOUND_DTORS]; - -static inline void set_compound_page_dtor(struct page *page, - enum compound_dtor_id compound_dtor) -{ - struct folio *folio = (struct folio *)page; - - VM_BUG_ON_PAGE(compound_dtor >= NR_COMPOUND_DTORS, page); - VM_BUG_ON_PAGE(!PageHead(page), page); - folio->_folio_dtor = compound_dtor; -} static inline void folio_set_compound_dtor(struct folio *folio, enum compound_dtor_id compound_dtor) @@ -1229,16 +1230,6 @@ static inline void folio_set_compound_dtor(struct folio *folio, void destroy_large_folio(struct folio *folio); -static inline void set_compound_order(struct page *page, unsigned int order) -{ - struct folio *folio = (struct folio *)page; - - folio->_folio_order = order; -#ifdef CONFIG_64BIT - folio->_folio_nr_pages = 1U << order; -#endif -} - /* Returns the number of bytes in this potentially compound page. */ static inline unsigned long page_size(struct page *page) { @@ -1932,39 +1923,35 @@ static inline bool is_zero_folio(const struct folio *folio) return is_zero_page(&folio->page); } -/* MIGRATE_CMA and ZONE_MOVABLE do not allow pin pages */ +/* MIGRATE_CMA and ZONE_MOVABLE do not allow pin folios */ #ifdef CONFIG_MIGRATION -static inline bool is_longterm_pinnable_page(struct page *page) +static inline bool folio_is_longterm_pinnable(struct folio *folio) { #ifdef CONFIG_CMA - int mt = get_pageblock_migratetype(page); + int mt = folio_migratetype(folio); if (mt == MIGRATE_CMA || mt == MIGRATE_ISOLATE) return false; #endif /* The zero page can be "pinned" but gets special handling. */ - if (is_zero_page(page)) + if (is_zero_folio(folio)) return true; /* Coherent device memory must always allow eviction. */ - if (is_device_coherent_page(page)) + if (folio_is_device_coherent(folio)) return false; - /* Otherwise, non-movable zone pages can be pinned. */ - return !is_zone_movable_page(page); + /* Otherwise, non-movable zone folios can be pinned. */ + return !folio_is_zone_movable(folio); + } #else -static inline bool is_longterm_pinnable_page(struct page *page) +static inline bool folio_is_longterm_pinnable(struct folio *folio) { return true; } #endif -static inline bool folio_is_longterm_pinnable(struct folio *folio) -{ - return is_longterm_pinnable_page(&folio->page); -} - static inline void set_page_zone(struct page *page, enum zone_type zone) { page->flags &= ~(ZONES_MASK << ZONES_PGSHIFT); @@ -2375,6 +2362,9 @@ static inline void unmap_shared_mapping_range(struct address_space *mapping, unmap_mapping_range(mapping, holebegin, holelen, 0); } +static inline struct vm_area_struct *vma_lookup(struct mm_struct *mm, + unsigned long addr); + extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, unsigned int gup_flags); extern int access_remote_vm(struct mm_struct *mm, unsigned long addr, @@ -2383,19 +2373,42 @@ extern int __access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, int len, unsigned int gup_flags); long get_user_pages_remote(struct mm_struct *mm, - unsigned long start, unsigned long nr_pages, - unsigned int gup_flags, struct page **pages, - struct vm_area_struct **vmas, int *locked); + unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages, + int *locked); long pin_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, - struct vm_area_struct **vmas, int *locked); + int *locked); + +static inline struct page *get_user_page_vma_remote(struct mm_struct *mm, + unsigned long addr, + int gup_flags, + struct vm_area_struct **vmap) +{ + struct page *page; + struct vm_area_struct *vma; + int got = get_user_pages_remote(mm, addr, 1, gup_flags, &page, NULL); + + if (got < 0) + return ERR_PTR(got); + if (got == 0) + return NULL; + + vma = vma_lookup(mm, addr); + if (WARN_ON_ONCE(!vma)) { + put_page(page); + return ERR_PTR(-EINVAL); + } + + *vmap = vma; + return page; +} + long get_user_pages(unsigned long start, unsigned long nr_pages, - unsigned int gup_flags, struct page **pages, - struct vm_area_struct **vmas); + unsigned int gup_flags, struct page **pages); long pin_user_pages(unsigned long start, unsigned long nr_pages, - unsigned int gup_flags, struct page **pages, - struct vm_area_struct **vmas); + unsigned int gup_flags, struct page **pages); long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags); long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages, @@ -2445,6 +2458,7 @@ extern unsigned long move_page_tables(struct vm_area_struct *vma, #define MM_CP_UFFD_WP_ALL (MM_CP_UFFD_WP | \ MM_CP_UFFD_WP_RESOLVE) +bool vma_needs_dirty_tracking(struct vm_area_struct *vma); int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot); static inline bool vma_wants_manual_pte_write_upgrade(struct vm_area_struct *vma) { @@ -2810,14 +2824,25 @@ static inline void pgtable_pte_page_dtor(struct page *page) dec_lruvec_page_state(page, NR_PAGETABLE); } -#define pte_offset_map_lock(mm, pmd, address, ptlp) \ -({ \ - spinlock_t *__ptl = pte_lockptr(mm, pmd); \ - pte_t *__pte = pte_offset_map(pmd, address); \ - *(ptlp) = __ptl; \ - spin_lock(__ptl); \ - __pte; \ -}) +pte_t *__pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp); +static inline pte_t *pte_offset_map(pmd_t *pmd, unsigned long addr) +{ + return __pte_offset_map(pmd, addr, NULL); +} + +pte_t *__pte_offset_map_lock(struct mm_struct *mm, pmd_t *pmd, + unsigned long addr, spinlock_t **ptlp); +static inline pte_t *pte_offset_map_lock(struct mm_struct *mm, pmd_t *pmd, + unsigned long addr, spinlock_t **ptlp) +{ + pte_t *pte; + + __cond_lock(*ptlp, pte = __pte_offset_map_lock(mm, pmd, addr, ptlp)); + return pte; +} + +pte_t *pte_offset_map_nolock(struct mm_struct *mm, pmd_t *pmd, + unsigned long addr, spinlock_t **ptlp); #define pte_unmap_unlock(pte, ptl) do { \ spin_unlock(ptl); \ @@ -2938,7 +2963,8 @@ extern unsigned long free_reserved_area(void *start, void *end, extern void adjust_managed_page_count(struct page *page, long count); -extern void reserve_bootmem_region(phys_addr_t start, phys_addr_t end); +extern void reserve_bootmem_region(phys_addr_t start, + phys_addr_t end, int nid); /* Free the reserved page into the buddy system, so it gets managed. */ static inline void free_reserved_page(struct page *page) @@ -3017,12 +3043,6 @@ extern int __meminit early_pfn_to_nid(unsigned long pfn); #endif extern void set_dma_reserve(unsigned long new_dma_reserve); -extern void memmap_init_range(unsigned long, int, unsigned long, - unsigned long, unsigned long, enum meminit_context, - struct vmem_altmap *, int migratetype); -extern void setup_per_zone_wmarks(void); -extern void calculate_min_free_kbytes(void); -extern int __meminit init_per_zone_wmark_min(void); extern void mem_init(void); extern void __init mmap_init(void); @@ -3043,11 +3063,6 @@ void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...); extern void setup_per_cpu_pageset(void); -/* page_alloc.c */ -extern int min_free_kbytes; -extern int watermark_boost_factor; -extern int watermark_scale_factor; - /* nommu.c */ extern atomic_long_t mmap_pages_allocated; extern int nommu_shrink_inode_mappings(struct inode *, size_t, size_t); @@ -3494,9 +3509,58 @@ static inline void debug_pagealloc_unmap_pages(struct page *page, int numpages) if (debug_pagealloc_enabled_static()) __kernel_map_pages(page, numpages, 0); } + +extern unsigned int _debug_guardpage_minorder; +DECLARE_STATIC_KEY_FALSE(_debug_guardpage_enabled); + +static inline unsigned int debug_guardpage_minorder(void) +{ + return _debug_guardpage_minorder; +} + +static inline bool debug_guardpage_enabled(void) +{ + return static_branch_unlikely(&_debug_guardpage_enabled); +} + +static inline bool page_is_guard(struct page *page) +{ + if (!debug_guardpage_enabled()) + return false; + + return PageGuard(page); +} + +bool __set_page_guard(struct zone *zone, struct page *page, unsigned int order, + int migratetype); +static inline bool set_page_guard(struct zone *zone, struct page *page, + unsigned int order, int migratetype) +{ + if (!debug_guardpage_enabled()) + return false; + return __set_page_guard(zone, page, order, migratetype); +} + +void __clear_page_guard(struct zone *zone, struct page *page, unsigned int order, + int migratetype); +static inline void clear_page_guard(struct zone *zone, struct page *page, + unsigned int order, int migratetype) +{ + if (!debug_guardpage_enabled()) + return; + __clear_page_guard(zone, page, order, migratetype); +} + #else /* CONFIG_DEBUG_PAGEALLOC */ static inline void debug_pagealloc_map_pages(struct page *page, int numpages) {} static inline void debug_pagealloc_unmap_pages(struct page *page, int numpages) {} +static inline unsigned int debug_guardpage_minorder(void) { return 0; } +static inline bool debug_guardpage_enabled(void) { return false; } +static inline bool page_is_guard(struct page *page) { return false; } +static inline bool set_page_guard(struct zone *zone, struct page *page, + unsigned int order, int migratetype) { return false; } +static inline void clear_page_guard(struct zone *zone, struct page *page, + unsigned int order, int migratetype) {} #endif /* CONFIG_DEBUG_PAGEALLOC */ #ifdef __HAVE_ARCH_GATE_AREA @@ -3609,6 +3673,10 @@ extern void shake_page(struct page *p); extern atomic_long_t num_poisoned_pages __read_mostly; extern int soft_offline_page(unsigned long pfn, int flags); #ifdef CONFIG_MEMORY_FAILURE +/* + * Sysfs entries for memory failure handling statistics. + */ +extern const struct attribute_group memory_failure_attr_group; extern void memory_failure_queue(unsigned long pfn, int flags); extern int __get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared); @@ -3701,11 +3769,6 @@ enum mf_action_page_type { MF_MSG_UNKNOWN, }; -/* - * Sysfs entries for memory failure handling statistics. - */ -extern const struct attribute_group memory_failure_attr_group; - #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS) extern void clear_huge_page(struct page *page, unsigned long addr_hint, @@ -3735,33 +3798,6 @@ static inline bool vma_is_special_huge(const struct vm_area_struct *vma) #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */ -#ifdef CONFIG_DEBUG_PAGEALLOC -extern unsigned int _debug_guardpage_minorder; -DECLARE_STATIC_KEY_FALSE(_debug_guardpage_enabled); - -static inline unsigned int debug_guardpage_minorder(void) -{ - return _debug_guardpage_minorder; -} - -static inline bool debug_guardpage_enabled(void) -{ - return static_branch_unlikely(&_debug_guardpage_enabled); -} - -static inline bool page_is_guard(struct page *page) -{ - if (!debug_guardpage_enabled()) - return false; - - return PageGuard(page); -} -#else -static inline unsigned int debug_guardpage_minorder(void) { return 0; } -static inline bool debug_guardpage_enabled(void) { return false; } -static inline bool page_is_guard(struct page *page) { return false; } -#endif /* CONFIG_DEBUG_PAGEALLOC */ - #if MAX_NUMNODES > 1 void __init setup_nr_node_ids(void); #else diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 0e1d239a882c..21d6c72bcc71 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -323,12 +323,6 @@ void lruvec_add_folio(struct lruvec *lruvec, struct folio *folio) list_add(&folio->lru, &lruvec->lists[lru]); } -static __always_inline void add_page_to_lru_list(struct page *page, - struct lruvec *lruvec) -{ - lruvec_add_folio(lruvec, page_folio(page)); -} - static __always_inline void lruvec_add_folio_tail(struct lruvec *lruvec, struct folio *folio) { @@ -357,12 +351,6 @@ void lruvec_del_folio(struct lruvec *lruvec, struct folio *folio) -folio_nr_pages(folio)); } -static __always_inline void del_page_from_lru_list(struct page *page, - struct lruvec *lruvec) -{ - lruvec_del_folio(lruvec, page_folio(page)); -} - #ifdef CONFIG_ANON_VMA_NAME /* * mmap_lock should be read-locked when calling anon_vma_name(). Caller should @@ -555,7 +543,7 @@ pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, bool arm_uffd_pte = false; /* The current status of the pte should be "cleared" before calling */ - WARN_ON_ONCE(!pte_none(*pte)); + WARN_ON_ONCE(!pte_none(ptep_get(pte))); /* * NOTE: userfaultfd_wp_unpopulated() doesn't need this whole diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 306a3d1a0fa6..de10fc797c8e 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -583,6 +583,21 @@ struct mm_cid { struct kioctx_table; struct mm_struct { struct { + /* + * Fields which are often written to are placed in a separate + * cache line. + */ + struct { + /** + * @mm_count: The number of references to &struct + * mm_struct (@mm_users count as 1). + * + * Use mmgrab()/mmdrop() to modify. When this drops to + * 0, the &struct mm_struct is freed. + */ + atomic_t mm_count; + } ____cacheline_aligned_in_smp; + struct maple_tree mm_mt; #ifdef CONFIG_MMU unsigned long (*get_unmapped_area) (struct file *filp, @@ -620,14 +635,6 @@ struct mm_struct { */ atomic_t mm_users; - /** - * @mm_count: The number of references to &struct mm_struct - * (@mm_users count as 1). - * - * Use mmgrab()/mmdrop() to modify. When this drops to 0, the - * &struct mm_struct is freed. - */ - atomic_t mm_count; #ifdef CONFIG_SCHED_MM_CID /** * @pcpu_cid: Per-cpu current cid. diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h index b8728d11c949..7c3e7b0b0e8f 100644 --- a/include/linux/mmdebug.h +++ b/include/linux/mmdebug.h @@ -8,10 +8,12 @@ struct page; struct vm_area_struct; struct mm_struct; +struct vma_iterator; void dump_page(struct page *page, const char *reason); void dump_vma(const struct vm_area_struct *vma); void dump_mm(const struct mm_struct *mm); +void vma_iter_dump_tree(const struct vma_iterator *vmi); #ifdef CONFIG_DEBUG_VM #define VM_BUG_ON(cond) BUG_ON(cond) @@ -74,6 +76,17 @@ void dump_mm(const struct mm_struct *mm); } \ unlikely(__ret_warn_once); \ }) +#define VM_WARN_ON_ONCE_MM(cond, mm) ({ \ + static bool __section(".data.once") __warned; \ + int __ret_warn_once = !!(cond); \ + \ + if (unlikely(__ret_warn_once && !__warned)) { \ + dump_mm(mm); \ + __warned = true; \ + WARN_ON(1); \ + } \ + unlikely(__ret_warn_once); \ +}) #define VM_WARN_ON(cond) (void)WARN_ON(cond) #define VM_WARN_ON_ONCE(cond) (void)WARN_ON_ONCE(cond) @@ -90,6 +103,7 @@ void dump_mm(const struct mm_struct *mm); #define VM_WARN_ON_ONCE_PAGE(cond, page) BUILD_BUG_ON_INVALID(cond) #define VM_WARN_ON_FOLIO(cond, folio) BUILD_BUG_ON_INVALID(cond) #define VM_WARN_ON_ONCE_FOLIO(cond, folio) BUILD_BUG_ON_INVALID(cond) +#define VM_WARN_ON_ONCE_MM(cond, mm) BUILD_BUG_ON_INVALID(cond) #define VM_WARN_ONCE(cond, format...) BUILD_BUG_ON_INVALID(cond) #define VM_WARN(cond, format...) BUILD_BUG_ON_INVALID(cond) #endif diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 6c1c2fc13017..5e50b78d58ea 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -105,6 +105,9 @@ extern int page_group_by_mobility_disabled; #define get_pageblock_migratetype(page) \ get_pfnblock_flags_mask(page, page_to_pfn(page), MIGRATETYPE_MASK) +#define folio_migratetype(folio) \ + get_pfnblock_flags_mask(&folio->page, folio_pfn(folio), \ + MIGRATETYPE_MASK) struct free_area { struct list_head free_list[MIGRATE_TYPES]; unsigned long nr_free; @@ -293,9 +296,21 @@ static inline bool is_active_lru(enum lru_list lru) #define ANON_AND_FILE 2 enum lruvec_flags { - LRUVEC_CONGESTED, /* lruvec has many dirty pages - * backed by a congested BDI - */ + /* + * An lruvec has many dirty pages backed by a congested BDI: + * 1. LRUVEC_CGROUP_CONGESTED is set by cgroup-level reclaim. + * It can be cleared by cgroup reclaim or kswapd. + * 2. LRUVEC_NODE_CONGESTED is set by kswapd node-level reclaim. + * It can only be cleared by kswapd. + * + * Essentially, kswapd can unthrottle an lruvec throttled by cgroup + * reclaim, but not vice versa. This only applies to the root cgroup. + * The goal is to prevent cgroup reclaim on the root cgroup (e.g. + * memory.reclaim) to unthrottle an unbalanced node (that was throttled + * by kswapd). + */ + LRUVEC_CGROUP_CONGESTED, + LRUVEC_NODE_CONGESTED, }; #endif /* !__GENERATING_BOUNDS_H */ @@ -537,7 +552,7 @@ void lru_gen_exit_memcg(struct mem_cgroup *memcg); void lru_gen_online_memcg(struct mem_cgroup *memcg); void lru_gen_offline_memcg(struct mem_cgroup *memcg); void lru_gen_release_memcg(struct mem_cgroup *memcg); -void lru_gen_soft_reclaim(struct lruvec *lruvec); +void lru_gen_soft_reclaim(struct mem_cgroup *memcg, int nid); #else /* !CONFIG_MEMCG */ @@ -588,7 +603,7 @@ static inline void lru_gen_release_memcg(struct mem_cgroup *memcg) { } -static inline void lru_gen_soft_reclaim(struct lruvec *lruvec) +static inline void lru_gen_soft_reclaim(struct mem_cgroup *memcg, int nid) { } @@ -1124,6 +1139,11 @@ static inline bool is_zone_movable_page(const struct page *page) { return page_zonenum(page) == ZONE_MOVABLE; } + +static inline bool folio_is_zone_movable(const struct folio *folio) +{ + return folio_zonenum(folio) == ZONE_MOVABLE; +} #endif /* @@ -1520,27 +1540,6 @@ static inline bool has_managed_dma(void) } #endif -/* These two functions are used to setup the per zone pages min values */ -struct ctl_table; - -int min_free_kbytes_sysctl_handler(struct ctl_table *, int, void *, size_t *, - loff_t *); -int watermark_scale_factor_sysctl_handler(struct ctl_table *, int, void *, - size_t *, loff_t *); -extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES]; -int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int, void *, - size_t *, loff_t *); -int percpu_pagelist_high_fraction_sysctl_handler(struct ctl_table *, int, - void *, size_t *, loff_t *); -int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *, int, - void *, size_t *, loff_t *); -int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *, int, - void *, size_t *, loff_t *); -int numa_zonelist_order_handler(struct ctl_table *, int, - void *, size_t *, loff_t *); -extern int percpu_pagelist_high_fraction; -extern char numa_zonelist_order[]; -#define NUMA_ZONELIST_ORDER_LEN 16 #ifndef CONFIG_NUMA diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h index 5456b7be38ae..4ac34392823a 100644 --- a/include/linux/page-isolation.h +++ b/include/linux/page-isolation.h @@ -37,27 +37,12 @@ void set_pageblock_migratetype(struct page *page, int migratetype); int move_freepages_block(struct zone *zone, struct page *page, int migratetype, int *num_movable); -/* - * Changes migrate type in [start_pfn, end_pfn) to be MIGRATE_ISOLATE. - */ -int -start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, - int migratetype, int flags, gfp_t gfp_flags); +int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, + int migratetype, int flags, gfp_t gfp_flags); -/* - * Changes MIGRATE_ISOLATE to MIGRATE_MOVABLE. - * target range is [start_pfn, end_pfn) - */ -void -undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, - int migratetype); +void undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, + int migratetype); -/* - * Test all pages in [start_pfn, end_pfn) are isolated or not. - */ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn, int isol_flags); - -struct page *alloc_migrate_target(struct page *page, unsigned long private); - #endif diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index a56308a9d1a4..716953ee1ebd 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -30,6 +30,9 @@ static inline void invalidate_remote_inode(struct inode *inode) int invalidate_inode_pages2(struct address_space *mapping); int invalidate_inode_pages2_range(struct address_space *mapping, pgoff_t start, pgoff_t end); +int kiocb_invalidate_pages(struct kiocb *iocb, size_t count); +void kiocb_invalidate_post_direct_write(struct kiocb *iocb, size_t count); + int write_inode_now(struct inode *, int sync); int filemap_fdatawrite(struct address_space *); int filemap_flush(struct address_space *); @@ -54,6 +57,7 @@ int filemap_check_errors(struct address_space *mapping); void __filemap_set_wb_err(struct address_space *mapping, int err); int filemap_fdatawrite_wbc(struct address_space *mapping, struct writeback_control *wbc); +int kiocb_write_and_wait(struct kiocb *iocb, size_t count); static inline int filemap_write_and_wait(struct address_space *mapping) { @@ -1078,8 +1082,6 @@ int filemap_migrate_folio(struct address_space *mapping, struct folio *dst, #else #define filemap_migrate_folio NULL #endif -void page_endio(struct page *page, bool is_write, int err); - void folio_end_private_2(struct folio *folio); void folio_wait_private_2(struct folio *folio); int folio_wait_private_2_killable(struct folio *folio); diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h index f582f7213ea5..87cc678adc85 100644 --- a/include/linux/pagevec.h +++ b/include/linux/pagevec.h @@ -3,65 +3,18 @@ * include/linux/pagevec.h * * In many places it is efficient to batch an operation up against multiple - * pages. A pagevec is a multipage container which is used for that. + * folios. A folio_batch is a container which is used for that. */ #ifndef _LINUX_PAGEVEC_H #define _LINUX_PAGEVEC_H -#include <linux/xarray.h> +#include <linux/types.h> -/* 15 pointers + header align the pagevec structure to a power of two */ +/* 15 pointers + header align the folio_batch structure to a power of two */ #define PAGEVEC_SIZE 15 -struct page; struct folio; -struct address_space; - -/* Layout must match folio_batch */ -struct pagevec { - unsigned char nr; - bool percpu_pvec_drained; - struct page *pages[PAGEVEC_SIZE]; -}; - -void __pagevec_release(struct pagevec *pvec); - -static inline void pagevec_init(struct pagevec *pvec) -{ - pvec->nr = 0; - pvec->percpu_pvec_drained = false; -} - -static inline void pagevec_reinit(struct pagevec *pvec) -{ - pvec->nr = 0; -} - -static inline unsigned pagevec_count(struct pagevec *pvec) -{ - return pvec->nr; -} - -static inline unsigned pagevec_space(struct pagevec *pvec) -{ - return PAGEVEC_SIZE - pvec->nr; -} - -/* - * Add a page to a pagevec. Returns the number of slots still available. - */ -static inline unsigned pagevec_add(struct pagevec *pvec, struct page *page) -{ - pvec->pages[pvec->nr++] = page; - return pagevec_space(pvec); -} - -static inline void pagevec_release(struct pagevec *pvec) -{ - if (pagevec_count(pvec)) - __pagevec_release(pvec); -} /** * struct folio_batch - A collection of folios. @@ -78,11 +31,6 @@ struct folio_batch { struct folio *folios[PAGEVEC_SIZE]; }; -/* Layout must match pagevec */ -static_assert(sizeof(struct pagevec) == sizeof(struct folio_batch)); -static_assert(offsetof(struct pagevec, pages) == - offsetof(struct folio_batch, folios)); - /** * folio_batch_init() - Initialise a batch of folios * @fbatch: The folio batch. @@ -105,7 +53,7 @@ static inline unsigned int folio_batch_count(struct folio_batch *fbatch) return fbatch->nr; } -static inline unsigned int fbatch_space(struct folio_batch *fbatch) +static inline unsigned int folio_batch_space(struct folio_batch *fbatch) { return PAGEVEC_SIZE - fbatch->nr; } @@ -124,12 +72,15 @@ static inline unsigned folio_batch_add(struct folio_batch *fbatch, struct folio *folio) { fbatch->folios[fbatch->nr++] = folio; - return fbatch_space(fbatch); + return folio_batch_space(fbatch); } +void __folio_batch_release(struct folio_batch *pvec); + static inline void folio_batch_release(struct folio_batch *fbatch) { - pagevec_release((struct pagevec *)fbatch); + if (folio_batch_count(fbatch)) + __folio_batch_release(fbatch); } void folio_batch_remove_exceptionals(struct folio_batch *fbatch); diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index c5a51481bbb9..5063b482e34f 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -94,14 +94,22 @@ static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long address) #define pte_offset_kernel pte_offset_kernel #endif -#if defined(CONFIG_HIGHPTE) -#define pte_offset_map(dir, address) \ - ((pte_t *)kmap_atomic(pmd_page(*(dir))) + \ - pte_index((address))) -#define pte_unmap(pte) kunmap_atomic((pte)) +#ifdef CONFIG_HIGHPTE +#define __pte_map(pmd, address) \ + ((pte_t *)kmap_local_page(pmd_page(*(pmd))) + pte_index((address))) +#define pte_unmap(pte) do { \ + kunmap_local((pte)); \ + /* rcu_read_unlock() to be added later */ \ +} while (0) #else -#define pte_offset_map(dir, address) pte_offset_kernel((dir), (address)) -#define pte_unmap(pte) ((void)(pte)) /* NOP */ +static inline pte_t *__pte_map(pmd_t *pmd, unsigned long address) +{ + return pte_offset_kernel(pmd, address); +} +static inline void pte_unmap(pte_t *pte) +{ + /* rcu_read_unlock() to be added later */ +} #endif /* Find an entry in the second-level page table.. */ @@ -204,12 +212,26 @@ static inline int pudp_set_access_flags(struct vm_area_struct *vma, #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif +#ifndef ptep_get +static inline pte_t ptep_get(pte_t *ptep) +{ + return READ_ONCE(*ptep); +} +#endif + +#ifndef pmdp_get +static inline pmd_t pmdp_get(pmd_t *pmdp) +{ + return READ_ONCE(*pmdp); +} +#endif + #ifndef __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { - pte_t pte = *ptep; + pte_t pte = ptep_get(ptep); int r = 1; if (!pte_young(pte)) r = 0; @@ -296,7 +318,7 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long address, pte_t *ptep) { - pte_t pte = *ptep; + pte_t pte = ptep_get(ptep); pte_clear(mm, address, ptep); page_table_check_pte_clear(mm, address, pte); return pte; @@ -309,20 +331,6 @@ static inline void ptep_clear(struct mm_struct *mm, unsigned long addr, ptep_get_and_clear(mm, addr, ptep); } -#ifndef ptep_get -static inline pte_t ptep_get(pte_t *ptep) -{ - return READ_ONCE(*ptep); -} -#endif - -#ifndef pmdp_get -static inline pmd_t pmdp_get(pmd_t *pmdp) -{ - return READ_ONCE(*pmdp); -} -#endif - #ifdef CONFIG_GUP_GET_PXX_LOW_HIGH /* * For walking the pagetables without holding any locks. Some architectures @@ -511,7 +519,7 @@ extern pud_t pudp_huge_clear_flush(struct vm_area_struct *vma, struct mm_struct; static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep) { - pte_t old_pte = *ptep; + pte_t old_pte = ptep_get(ptep); set_pte_at(mm, address, ptep, pte_wrprotect(old_pte)); } #endif @@ -591,6 +599,10 @@ extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp); #endif +#ifndef arch_needs_pgtable_deposit +#define arch_needs_pgtable_deposit() (false) +#endif + #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * This is an implementation of pmdp_establish() that is only suitable for an @@ -1292,9 +1304,10 @@ static inline int pud_trans_huge(pud_t pud) } #endif -/* See pmd_none_or_trans_huge_or_clear_bad for discussion. */ -static inline int pud_none_or_trans_huge_or_dev_or_clear_bad(pud_t *pud) +static inline int pud_trans_unstable(pud_t *pud) { +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ + defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) pud_t pudval = READ_ONCE(*pud); if (pud_none(pudval) || pud_trans_huge(pudval) || pud_devmap(pudval)) @@ -1303,121 +1316,10 @@ static inline int pud_none_or_trans_huge_or_dev_or_clear_bad(pud_t *pud) pud_clear_bad(pud); return 1; } - return 0; -} - -/* See pmd_trans_unstable for discussion. */ -static inline int pud_trans_unstable(pud_t *pud) -{ -#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ - defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) - return pud_none_or_trans_huge_or_dev_or_clear_bad(pud); -#else - return 0; -#endif -} - -#ifndef arch_needs_pgtable_deposit -#define arch_needs_pgtable_deposit() (false) -#endif -/* - * This function is meant to be used by sites walking pagetables with - * the mmap_lock held in read mode to protect against MADV_DONTNEED and - * transhuge page faults. MADV_DONTNEED can convert a transhuge pmd - * into a null pmd and the transhuge page fault can convert a null pmd - * into an hugepmd or into a regular pmd (if the hugepage allocation - * fails). While holding the mmap_lock in read mode the pmd becomes - * stable and stops changing under us only if it's not null and not a - * transhuge pmd. When those races occurs and this function makes a - * difference vs the standard pmd_none_or_clear_bad, the result is - * undefined so behaving like if the pmd was none is safe (because it - * can return none anyway). The compiler level barrier() is critically - * important to compute the two checks atomically on the same pmdval. - * - * For 32bit kernels with a 64bit large pmd_t this automatically takes - * care of reading the pmd atomically to avoid SMP race conditions - * against pmd_populate() when the mmap_lock is hold for reading by the - * caller (a special atomic read not done by "gcc" as in the generic - * version above, is also needed when THP is disabled because the page - * fault can populate the pmd from under us). - */ -static inline int pmd_none_or_trans_huge_or_clear_bad(pmd_t *pmd) -{ - pmd_t pmdval = pmdp_get_lockless(pmd); - /* - * The barrier will stabilize the pmdval in a register or on - * the stack so that it will stop changing under the code. - * - * When CONFIG_TRANSPARENT_HUGEPAGE=y on x86 32bit PAE, - * pmdp_get_lockless is allowed to return a not atomic pmdval - * (for example pointing to an hugepage that has never been - * mapped in the pmd). The below checks will only care about - * the low part of the pmd with 32bit PAE x86 anyway, with the - * exception of pmd_none(). So the important thing is that if - * the low part of the pmd is found null, the high part will - * be also null or the pmd_none() check below would be - * confused. - */ -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - barrier(); #endif - /* - * !pmd_present() checks for pmd migration entries - * - * The complete check uses is_pmd_migration_entry() in linux/swapops.h - * But using that requires moving current function and pmd_trans_unstable() - * to linux/swapops.h to resolve dependency, which is too much code move. - * - * !pmd_present() is equivalent to is_pmd_migration_entry() currently, - * because !pmd_present() pages can only be under migration not swapped - * out. - * - * pmd_none() is preserved for future condition checks on pmd migration - * entries and not confusing with this function name, although it is - * redundant with !pmd_present(). - */ - if (pmd_none(pmdval) || pmd_trans_huge(pmdval) || - (IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION) && !pmd_present(pmdval))) - return 1; - if (unlikely(pmd_bad(pmdval))) { - pmd_clear_bad(pmd); - return 1; - } return 0; } -/* - * This is a noop if Transparent Hugepage Support is not built into - * the kernel. Otherwise it is equivalent to - * pmd_none_or_trans_huge_or_clear_bad(), and shall only be called in - * places that already verified the pmd is not none and they want to - * walk ptes while holding the mmap sem in read mode (write mode don't - * need this). If THP is not enabled, the pmd can't go away under the - * code even if MADV_DONTNEED runs, but if THP is enabled we need to - * run a pmd_trans_unstable before walking the ptes after - * split_huge_pmd returns (because it may have run when the pmd become - * null, but then a page fault can map in a THP and not a regular page). - */ -static inline int pmd_trans_unstable(pmd_t *pmd) -{ -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - return pmd_none_or_trans_huge_or_clear_bad(pmd); -#else - return 0; -#endif -} - -/* - * the ordering of these checks is important for pmds with _page_devmap set. - * if we check pmd_trans_unstable() first we will trip the bad_pmd() check - * inside of pmd_none_or_trans_huge_or_clear_bad(). this will end up correctly - * returning 1 but not before it spams dmesg with the pmd_clear_bad() output. - */ -static inline int pmd_devmap_trans_unstable(pmd_t *pmd) -{ - return pmd_devmap(*pmd) || pmd_trans_unstable(pmd); -} - #ifndef CONFIG_NUMA_BALANCING /* * Technically a PTE can be PROTNONE even when not doing NUMA balancing but diff --git a/include/linux/ramfs.h b/include/linux/ramfs.h index 917528d102c4..d506dc63dd47 100644 --- a/include/linux/ramfs.h +++ b/include/linux/ramfs.h @@ -7,6 +7,7 @@ struct inode *ramfs_get_inode(struct super_block *sb, const struct inode *dir, umode_t mode, dev_t dev); extern int ramfs_init_fs_context(struct fs_context *fc); +extern void ramfs_kill_sb(struct super_block *sb); #ifdef CONFIG_MMU static inline int diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h index 375a5e90d86a..77df3d7b18a6 100644 --- a/include/linux/scatterlist.h +++ b/include/linux/scatterlist.h @@ -16,7 +16,7 @@ struct scatterlist { #ifdef CONFIG_NEED_SG_DMA_LENGTH unsigned int dma_length; #endif -#ifdef CONFIG_PCI_P2PDMA +#ifdef CONFIG_NEED_SG_DMA_FLAGS unsigned int dma_flags; #endif }; @@ -141,6 +141,30 @@ static inline void sg_set_page(struct scatterlist *sg, struct page *page, sg->length = len; } +/** + * sg_set_folio - Set sg entry to point at given folio + * @sg: SG entry + * @folio: The folio + * @len: Length of data + * @offset: Offset into folio + * + * Description: + * Use this function to set an sg entry pointing at a folio, never assign + * the folio directly. We encode sg table information in the lower bits + * of the folio pointer. See sg_page() for looking up the page belonging + * to an sg entry. + * + **/ +static inline void sg_set_folio(struct scatterlist *sg, struct folio *folio, + size_t len, size_t offset) +{ + WARN_ON_ONCE(len > UINT_MAX); + WARN_ON_ONCE(offset > UINT_MAX); + sg_assign_page(sg, &folio->page); + sg->offset = offset; + sg->length = len; +} + static inline struct page *sg_page(struct scatterlist *sg) { #ifdef CONFIG_DEBUG_SG @@ -249,17 +273,18 @@ static inline void sg_unmark_end(struct scatterlist *sg) } /* - * CONFGI_PCI_P2PDMA depends on CONFIG_64BIT which means there is 4 bytes - * in struct scatterlist (assuming also CONFIG_NEED_SG_DMA_LENGTH is set). - * Use this padding for DMA flags bits to indicate when a specific - * dma address is a bus address. + * One 64-bit architectures there is a 4-byte padding in struct scatterlist + * (assuming also CONFIG_NEED_SG_DMA_LENGTH is set). Use this padding for DMA + * flags bits to indicate when a specific dma address is a bus address or the + * buffer may have been bounced via SWIOTLB. */ -#ifdef CONFIG_PCI_P2PDMA +#ifdef CONFIG_NEED_SG_DMA_FLAGS -#define SG_DMA_BUS_ADDRESS (1 << 0) +#define SG_DMA_BUS_ADDRESS (1 << 0) +#define SG_DMA_SWIOTLB (1 << 1) /** - * sg_dma_is_bus address - Return whether a given segment was marked + * sg_dma_is_bus_address - Return whether a given segment was marked * as a bus address * @sg: SG entry * @@ -267,13 +292,13 @@ static inline void sg_unmark_end(struct scatterlist *sg) * Returns true if sg_dma_mark_bus_address() has been called on * this segment. **/ -static inline bool sg_is_dma_bus_address(struct scatterlist *sg) +static inline bool sg_dma_is_bus_address(struct scatterlist *sg) { return sg->dma_flags & SG_DMA_BUS_ADDRESS; } /** - * sg_dma_mark_bus address - Mark the scatterlist entry as a bus address + * sg_dma_mark_bus_address - Mark the scatterlist entry as a bus address * @sg: SG entry * * Description: @@ -299,9 +324,37 @@ static inline void sg_dma_unmark_bus_address(struct scatterlist *sg) sg->dma_flags &= ~SG_DMA_BUS_ADDRESS; } +/** + * sg_dma_is_swiotlb - Return whether the scatterlist was marked for SWIOTLB + * bouncing + * @sg: SG entry + * + * Description: + * Returns true if the scatterlist was marked for SWIOTLB bouncing. Not all + * elements may have been bounced, so the caller would have to check + * individual SG entries with is_swiotlb_buffer(). + */ +static inline bool sg_dma_is_swiotlb(struct scatterlist *sg) +{ + return sg->dma_flags & SG_DMA_SWIOTLB; +} + +/** + * sg_dma_mark_swiotlb - Mark the scatterlist for SWIOTLB bouncing + * @sg: SG entry + * + * Description: + * Marks a a scatterlist for SWIOTLB bounce. Not all SG entries may be + * bounced. + */ +static inline void sg_dma_mark_swiotlb(struct scatterlist *sg) +{ + sg->dma_flags |= SG_DMA_SWIOTLB; +} + #else -static inline bool sg_is_dma_bus_address(struct scatterlist *sg) +static inline bool sg_dma_is_bus_address(struct scatterlist *sg) { return false; } @@ -311,8 +364,15 @@ static inline void sg_dma_mark_bus_address(struct scatterlist *sg) static inline void sg_dma_unmark_bus_address(struct scatterlist *sg) { } +static inline bool sg_dma_is_swiotlb(struct scatterlist *sg) +{ + return false; +} +static inline void sg_dma_mark_swiotlb(struct scatterlist *sg) +{ +} -#endif +#endif /* CONFIG_NEED_SG_DMA_FLAGS */ /** * sg_phys - Return physical address of an sg entry diff --git a/include/linux/sched.h b/include/linux/sched.h index b0011c50da4f..609bde814cb0 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -41,7 +41,6 @@ /* task_struct member predeclarations (sorted alphabetically): */ struct audit_context; -struct backing_dev_info; struct bio_list; struct blk_plug; struct bpf_local_storage; @@ -1186,8 +1185,6 @@ struct task_struct { /* VM state: */ struct reclaim_state *reclaim_state; - struct backing_dev_info *backing_dev_info; - struct io_context *io_context; #ifdef CONFIG_COMPACTION diff --git a/include/linux/slab.h b/include/linux/slab.h index 6b3e155b70bf..ca53425e9b32 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -12,6 +12,7 @@ #ifndef _LINUX_SLAB_H #define _LINUX_SLAB_H +#include <linux/cache.h> #include <linux/gfp.h> #include <linux/overflow.h> #include <linux/types.h> @@ -235,12 +236,17 @@ void kmem_dump_obj(void *object); * alignment larger than the alignment of a 64-bit integer. * Setting ARCH_DMA_MINALIGN in arch headers allows that. */ -#if defined(ARCH_DMA_MINALIGN) && ARCH_DMA_MINALIGN > 8 +#ifdef ARCH_HAS_DMA_MINALIGN +#if ARCH_DMA_MINALIGN > 8 && !defined(ARCH_KMALLOC_MINALIGN) #define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN -#define KMALLOC_MIN_SIZE ARCH_DMA_MINALIGN -#define KMALLOC_SHIFT_LOW ilog2(ARCH_DMA_MINALIGN) -#else +#endif +#endif + +#ifndef ARCH_KMALLOC_MINALIGN #define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long) +#elif ARCH_KMALLOC_MINALIGN > 8 +#define KMALLOC_MIN_SIZE ARCH_KMALLOC_MINALIGN +#define KMALLOC_SHIFT_LOW ilog2(KMALLOC_MIN_SIZE) #endif /* diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 3b10636c51a9..b4903b87362a 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -223,7 +223,7 @@ struct svc_rqst { struct page * *rq_next_page; /* next reply page to use */ struct page * *rq_page_end; /* one past the last page */ - struct pagevec rq_pvec; + struct folio_batch rq_fbatch; struct kvec rq_vec[RPCSVC_MAXPAGES]; /* generally useful.. */ struct bio_vec rq_bvec[RPCSVC_MAXPAGES]; diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 4d0095e8989e..ef503088942d 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -367,9 +367,6 @@ struct pbe { struct pbe *next; }; -/* mm/page_alloc.c */ -extern void mark_free_pages(struct zone *zone); - /** * struct platform_hibernation_ops - hibernation platform support * @@ -513,6 +510,11 @@ extern void pm_report_max_hw_sleep(u64 t); /* drivers/base/power/wakeup.c */ extern bool events_check_enabled; +static inline bool pm_suspended_storage(void) +{ + return !gfp_has_io_fs(gfp_allowed_mask); +} + extern bool pm_wakeup_pending(void); extern void pm_system_wakeup(void); extern void pm_system_cancel_wakeup(void); @@ -546,6 +548,7 @@ static inline void ksys_sync_helper(void) {} #define pm_notifier(fn, pri) do { (void)(fn); } while (0) +static inline bool pm_suspended_storage(void) { return false; } static inline bool pm_wakeup_pending(void) { return false; } static inline void pm_system_wakeup(void) {} static inline void pm_wakeup_clear(bool reset) {} diff --git a/include/linux/swap.h b/include/linux/swap.h index 3c69cb653cb9..456546443f1f 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -337,25 +337,6 @@ struct swap_info_struct { */ }; -#ifdef CONFIG_64BIT -#define SWAP_RA_ORDER_CEILING 5 -#else -/* Avoid stack overflow, because we need to save part of page table */ -#define SWAP_RA_ORDER_CEILING 3 -#define SWAP_RA_PTE_CACHE_SIZE (1 << SWAP_RA_ORDER_CEILING) -#endif - -struct vma_swap_readahead { - unsigned short win; - unsigned short offset; - unsigned short nr_pte; -#ifdef CONFIG_64BIT - pte_t *ptes; -#else - pte_t ptes[SWAP_RA_PTE_CACHE_SIZE]; -#endif -}; - static inline swp_entry_t folio_swap_entry(struct folio *folio) { swp_entry_t entry = { .val = page_private(&folio->page) }; @@ -368,6 +349,7 @@ static inline void folio_set_swap_entry(struct folio *folio, swp_entry_t entry) } /* linux/mm/workingset.c */ +bool workingset_test_recent(void *shadow, bool file, bool *workingset); void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages); void *workingset_eviction(struct folio *folio, struct mem_cgroup *target_memcg); void workingset_refault(struct folio *folio, void *shadow); @@ -457,10 +439,9 @@ static inline bool node_reclaim_enabled(void) } void check_move_unevictable_folios(struct folio_batch *fbatch); -void check_move_unevictable_pages(struct pagevec *pvec); -extern void kswapd_run(int nid); -extern void kswapd_stop(int nid); +extern void __meminit kswapd_run(int nid); +extern void __meminit kswapd_stop(int nid); #ifdef CONFIG_SWAP @@ -512,7 +493,7 @@ int find_first_swap(dev_t *device); extern unsigned int count_swap_pages(int, int); extern sector_t swapdev_block(int, pgoff_t); extern int __swap_count(swp_entry_t entry); -extern int __swp_swapcount(swp_entry_t entry); +extern int swap_swapcount(struct swap_info_struct *si, swp_entry_t entry); extern int swp_swapcount(swp_entry_t entry); extern struct swap_info_struct *page_swap_info(struct page *); extern struct swap_info_struct *swp_swap_info(swp_entry_t entry); @@ -590,7 +571,7 @@ static inline int __swap_count(swp_entry_t entry) return 0; } -static inline int __swp_swapcount(swp_entry_t entry) +static inline int swap_swapcount(struct swap_info_struct *si, swp_entry_t entry) { return 0; } diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 3a451b7afcb3..4c932cb45e0b 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -332,15 +332,9 @@ static inline bool is_migration_entry_dirty(swp_entry_t entry) return false; } -extern void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, - spinlock_t *ptl); extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address); -#ifdef CONFIG_HUGETLB_PAGE -extern void __migration_entry_wait_huge(struct vm_area_struct *vma, - pte_t *ptep, spinlock_t *ptl); extern void migration_entry_wait_huge(struct vm_area_struct *vma, pte_t *pte); -#endif /* CONFIG_HUGETLB_PAGE */ #else /* CONFIG_MIGRATION */ static inline swp_entry_t make_readable_migration_entry(pgoff_t offset) { @@ -362,15 +356,10 @@ static inline int is_migration_entry(swp_entry_t swp) return 0; } -static inline void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, - spinlock_t *ptl) { } static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, - unsigned long address) { } -#ifdef CONFIG_HUGETLB_PAGE -static inline void __migration_entry_wait_huge(struct vm_area_struct *vma, - pte_t *ptep, spinlock_t *ptl) { } -static inline void migration_entry_wait_huge(struct vm_area_struct *vma, pte_t *pte) { } -#endif /* CONFIG_HUGETLB_PAGE */ + unsigned long address) { } +static inline void migration_entry_wait_huge(struct vm_area_struct *vma, + pte_t *pte) { } static inline int is_writable_migration_entry(swp_entry_t entry) { return 0; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 24871f8ec8bb..d18ce144037e 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -72,6 +72,8 @@ struct open_how; struct mount_attr; struct landlock_ruleset_attr; enum landlock_rule_type; +struct cachestat_range; +struct cachestat; #include <linux/types.h> #include <linux/aio_abi.h> @@ -1058,6 +1060,9 @@ asmlinkage long sys_memfd_secret(unsigned int flags); asmlinkage long sys_set_mempolicy_home_node(unsigned long start, unsigned long len, unsigned long home_node, unsigned long flags); +asmlinkage long sys_cachestat(unsigned int fd, + struct cachestat_range __user *cstat_range, + struct cachestat __user *cstat, unsigned int flags); /* * Architecture-specific system calls diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index d78b01524349..ac7b0c96d351 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -188,8 +188,8 @@ extern bool userfaultfd_remove(struct vm_area_struct *vma, unsigned long start, unsigned long end); -extern int userfaultfd_unmap_prep(struct mm_struct *mm, unsigned long start, - unsigned long end, struct list_head *uf); +extern int userfaultfd_unmap_prep(struct vm_area_struct *vma, + unsigned long start, unsigned long end, struct list_head *uf); extern void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf); extern bool userfaultfd_wp_unpopulated(struct vm_area_struct *vma); @@ -271,7 +271,7 @@ static inline bool userfaultfd_remove(struct vm_area_struct *vma, return true; } -static inline int userfaultfd_unmap_prep(struct mm_struct *mm, +static inline int userfaultfd_unmap_prep(struct vm_area_struct *vma, unsigned long start, unsigned long end, struct list_head *uf) { diff --git a/include/linux/zpool.h b/include/linux/zpool.h index e8997010612a..3296438eec06 100644 --- a/include/linux/zpool.h +++ b/include/linux/zpool.h @@ -14,10 +14,6 @@ struct zpool; -struct zpool_ops { - int (*evict)(struct zpool *pool, unsigned long handle); -}; - /* * Control how a handle is mapped. It will be ignored if the * implementation does not support it. Its use is optional. @@ -39,8 +35,7 @@ enum zpool_mapmode { bool zpool_has_pool(char *type); -struct zpool *zpool_create_pool(const char *type, const char *name, - gfp_t gfp, const struct zpool_ops *ops); +struct zpool *zpool_create_pool(const char *type, const char *name, gfp_t gfp); const char *zpool_get_type(struct zpool *pool); @@ -53,9 +48,6 @@ int zpool_malloc(struct zpool *pool, size_t size, gfp_t gfp, void zpool_free(struct zpool *pool, unsigned long handle); -int zpool_shrink(struct zpool *pool, unsigned int pages, - unsigned int *reclaimed); - void *zpool_map_handle(struct zpool *pool, unsigned long handle, enum zpool_mapmode mm); @@ -72,7 +64,6 @@ u64 zpool_get_total_size(struct zpool *pool); * @destroy: destroy a pool. * @malloc: allocate mem from a pool. * @free: free mem from a pool. - * @shrink: shrink the pool. * @sleep_mapped: whether zpool driver can sleep during map. * @map: map a handle. * @unmap: unmap a handle. @@ -87,10 +78,7 @@ struct zpool_driver { atomic_t refcount; struct list_head list; - void *(*create)(const char *name, - gfp_t gfp, - const struct zpool_ops *ops, - struct zpool *zpool); + void *(*create)(const char *name, gfp_t gfp); void (*destroy)(void *pool); bool malloc_support_movable; @@ -98,9 +86,6 @@ struct zpool_driver { unsigned long *handle); void (*free)(void *pool, unsigned long handle); - int (*shrink)(void *pool, unsigned int pages, - unsigned int *reclaimed); - bool sleep_mapped; void *(*map)(void *pool, unsigned long handle, enum zpool_mapmode mm); @@ -113,7 +98,6 @@ void zpool_register_driver(struct zpool_driver *driver); int zpool_unregister_driver(struct zpool_driver *driver); -bool zpool_evictable(struct zpool *pool); bool zpool_can_sleep_mapped(struct zpool *pool); #endif |