diff options
Diffstat (limited to 'mm')
-rw-r--r-- | mm/Kconfig.debug | 1 | ||||
-rw-r--r-- | mm/damon/core.c | 2 | ||||
-rw-r--r-- | mm/filemap.c | 57 | ||||
-rw-r--r-- | mm/gup.c | 58 | ||||
-rw-r--r-- | mm/gup_test.c | 1 | ||||
-rw-r--r-- | mm/internal.h | 6 | ||||
-rw-r--r-- | mm/kfence/kfence.h | 2 | ||||
-rw-r--r-- | mm/khugepaged.c | 1 | ||||
-rw-r--r-- | mm/memblock.c | 9 | ||||
-rw-r--r-- | mm/memfd.c | 9 | ||||
-rw-r--r-- | mm/mm_init.c | 7 | ||||
-rw-r--r-- | mm/mmap.c | 37 | ||||
-rw-r--r-- | mm/mprotect.c | 2 | ||||
-rw-r--r-- | mm/page_alloc.c | 173 | ||||
-rw-r--r-- | mm/page_io.c | 8 | ||||
-rw-r--r-- | mm/page_table_check.c | 6 | ||||
-rw-r--r-- | mm/shmem.c | 134 | ||||
-rw-r--r-- | mm/shrinker_debug.c | 54 | ||||
-rw-r--r-- | mm/swapfile.c | 6 | ||||
-rw-r--r-- | mm/vmalloc.c | 17 | ||||
-rw-r--r-- | mm/vmscan.c | 130 | ||||
-rw-r--r-- | mm/vmstat.c | 3 | ||||
-rw-r--r-- | mm/zsmalloc.c | 36 | ||||
-rw-r--r-- | mm/zswap.c | 27 |
24 files changed, 603 insertions, 183 deletions
diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug index a925415b4d10..018a5bd2f576 100644 --- a/mm/Kconfig.debug +++ b/mm/Kconfig.debug @@ -98,6 +98,7 @@ config PAGE_OWNER config PAGE_TABLE_CHECK bool "Check for invalid mappings in user page tables" depends on ARCH_SUPPORTS_PAGE_TABLE_CHECK + depends on EXCLUSIVE_SYSTEM_RAM select PAGE_EXTENSION help Check that anonymous page is not being mapped twice with read write diff --git a/mm/damon/core.c b/mm/damon/core.c index d9ef62047bf5..91cff7f2997e 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -551,6 +551,8 @@ int damon_set_attrs(struct damon_ctx *ctx, struct damon_attrs *attrs) return -EINVAL; if (attrs->min_nr_regions > attrs->max_nr_regions) return -EINVAL; + if (attrs->sample_interval > attrs->aggr_interval) + return -EINVAL; damon_update_monitoring_results(ctx, attrs); ctx->attrs = *attrs; diff --git a/mm/filemap.c b/mm/filemap.c index b4c9bd368b7e..00f01d8ead47 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1760,7 +1760,9 @@ bool __folio_lock_or_retry(struct folio *folio, struct mm_struct *mm, * * Return: The index of the gap if found, otherwise an index outside the * range specified (in which case 'return - index >= max_scan' will be true). - * In the rare case of index wrap-around, 0 will be returned. + * In the rare case of index wrap-around, 0 will be returned. 0 will also + * be returned if index == 0 and there is a gap at the index. We can not + * wrap-around if passed index == 0. */ pgoff_t page_cache_next_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan) @@ -1770,12 +1772,13 @@ pgoff_t page_cache_next_miss(struct address_space *mapping, while (max_scan--) { void *entry = xas_next(&xas); if (!entry || xa_is_value(entry)) - break; - if (xas.xa_index == 0) - break; + return xas.xa_index; + if (xas.xa_index == 0 && index != 0) + return xas.xa_index; } - return xas.xa_index; + /* No gaps in range and no wrap-around, return index beyond range */ + return xas.xa_index + 1; } EXPORT_SYMBOL(page_cache_next_miss); @@ -1796,7 +1799,9 @@ EXPORT_SYMBOL(page_cache_next_miss); * * Return: The index of the gap if found, otherwise an index outside the * range specified (in which case 'index - return >= max_scan' will be true). - * In the rare case of wrap-around, ULONG_MAX will be returned. + * In the rare case of wrap-around, ULONG_MAX will be returned. ULONG_MAX + * will also be returned if index == ULONG_MAX and there is a gap at the + * index. We can not wrap-around if passed index == ULONG_MAX. */ pgoff_t page_cache_prev_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan) @@ -1806,12 +1811,13 @@ pgoff_t page_cache_prev_miss(struct address_space *mapping, while (max_scan--) { void *entry = xas_prev(&xas); if (!entry || xa_is_value(entry)) - break; - if (xas.xa_index == ULONG_MAX) - break; + return xas.xa_index; + if (xas.xa_index == ULONG_MAX && index != ULONG_MAX) + return xas.xa_index; } - return xas.xa_index; + /* No gaps in range and no wrap-around, return index beyond range */ + return xas.xa_index - 1; } EXPORT_SYMBOL(page_cache_prev_miss); @@ -2687,8 +2693,7 @@ ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter, if (unlikely(iocb->ki_pos >= i_size_read(inode))) break; - error = filemap_get_pages(iocb, iter->count, &fbatch, - iov_iter_is_pipe(iter)); + error = filemap_get_pages(iocb, iter->count, &fbatch, false); if (error < 0) break; @@ -2872,9 +2877,24 @@ size_t splice_folio_into_pipe(struct pipe_inode_info *pipe, return spliced; } -/* - * Splice folios from the pagecache of a buffered (ie. non-O_DIRECT) file into - * a pipe. +/** + * filemap_splice_read - Splice data from a file's pagecache into a pipe + * @in: The file to read from + * @ppos: Pointer to the file position to read from + * @pipe: The pipe to splice into + * @len: The amount to splice + * @flags: The SPLICE_F_* flags + * + * This function gets folios from a file's pagecache and splices them into the + * pipe. Readahead will be called as necessary to fill more folios. This may + * be used for blockdevs also. + * + * Return: On success, the number of bytes read will be returned and *@ppos + * will be updated if appropriate; 0 will be returned if there is no more data + * to be read; -EAGAIN will be returned if the pipe had no space, and some + * other negative error code will be returned on error. A short read may occur + * if the pipe has insufficient space, we reach the end of the data or we hit a + * hole. */ ssize_t filemap_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, @@ -2887,6 +2907,9 @@ ssize_t filemap_splice_read(struct file *in, loff_t *ppos, bool writably_mapped; int i, error = 0; + if (unlikely(*ppos >= in->f_mapping->host->i_sb->s_maxbytes)) + return 0; + init_sync_kiocb(&iocb, in); iocb.ki_pos = *ppos; @@ -2900,7 +2923,7 @@ ssize_t filemap_splice_read(struct file *in, loff_t *ppos, do { cond_resched(); - if (*ppos >= i_size_read(file_inode(in))) + if (*ppos >= i_size_read(in->f_mapping->host)) break; iocb.ki_pos = *ppos; @@ -2916,7 +2939,7 @@ ssize_t filemap_splice_read(struct file *in, loff_t *ppos, * part of the page is not copied back to userspace (unless * another truncate extends the file - this is desired though). */ - isize = i_size_read(file_inode(in)); + isize = i_size_read(in->f_mapping->host); if (unlikely(*ppos >= isize)) break; end_offset = min_t(loff_t, isize, *ppos + len); @@ -51,7 +51,8 @@ static inline void sanity_check_pinned_pages(struct page **pages, struct page *page = *pages; struct folio *folio = page_folio(page); - if (!folio_test_anon(folio)) + if (is_zero_page(page) || + !folio_test_anon(folio)) continue; if (!folio_test_large(folio) || folio_test_hugetlb(folio)) VM_BUG_ON_PAGE(!PageAnonExclusive(&folio->page), page); @@ -132,6 +133,13 @@ struct folio *try_grab_folio(struct page *page, int refs, unsigned int flags) struct folio *folio; /* + * Don't take a pin on the zero page - it's not going anywhere + * and it is used in a *lot* of places. + */ + if (is_zero_page(page)) + return page_folio(page); + + /* * Can't do FOLL_LONGTERM + FOLL_PIN gup fast path if not in a * right zone, so fail and let the caller fall back to the slow * path. @@ -180,6 +188,8 @@ struct folio *try_grab_folio(struct page *page, int refs, unsigned int flags) static void gup_put_folio(struct folio *folio, int refs, unsigned int flags) { if (flags & FOLL_PIN) { + if (is_zero_folio(folio)) + return; node_stat_mod_folio(folio, NR_FOLL_PIN_RELEASED, refs); if (folio_test_large(folio)) atomic_sub(refs, &folio->_pincount); @@ -225,6 +235,13 @@ int __must_check try_grab_page(struct page *page, unsigned int flags) folio_ref_inc(folio); else if (flags & FOLL_PIN) { /* + * Don't take a pin on the zero page - it's not going anywhere + * and it is used in a *lot* of places. + */ + if (is_zero_page(page)) + return 0; + + /* * Similar to try_grab_folio(): be sure to *also* * increment the normal page refcount field at least once, * so that the page really is pinned. @@ -258,6 +275,33 @@ void unpin_user_page(struct page *page) } EXPORT_SYMBOL(unpin_user_page); +/** + * folio_add_pin - Try to get an additional pin on a pinned folio + * @folio: The folio to be pinned + * + * Get an additional pin on a folio we already have a pin on. Makes no change + * if the folio is a zero_page. + */ +void folio_add_pin(struct folio *folio) +{ + if (is_zero_folio(folio)) + return; + + /* + * Similar to try_grab_folio(): be sure to *also* increment the normal + * page refcount field at least once, so that the page really is + * pinned. + */ + if (folio_test_large(folio)) { + WARN_ON_ONCE(atomic_read(&folio->_pincount) < 1); + folio_ref_inc(folio); + atomic_inc(&folio->_pincount); + } else { + WARN_ON_ONCE(folio_ref_count(folio) < GUP_PIN_COUNTING_BIAS); + folio_ref_add(folio, GUP_PIN_COUNTING_BIAS); + } +} + static inline struct folio *gup_folio_range_next(struct page *start, unsigned long npages, unsigned long i, unsigned int *ntails) { @@ -3079,6 +3123,9 @@ EXPORT_SYMBOL_GPL(get_user_pages_fast); * * FOLL_PIN means that the pages must be released via unpin_user_page(). Please * see Documentation/core-api/pin_user_pages.rst for further details. + * + * Note that if a zero_page is amongst the returned pages, it will not have + * pins in it and unpin_user_page() will not remove pins from it. */ int pin_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages) @@ -3110,6 +3157,9 @@ EXPORT_SYMBOL_GPL(pin_user_pages_fast); * * FOLL_PIN means that the pages must be released via unpin_user_page(). Please * see Documentation/core-api/pin_user_pages.rst for details. + * + * Note that if a zero_page is amongst the returned pages, it will not have + * pins in it and unpin_user_page*() will not remove pins from it. */ long pin_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, @@ -3143,6 +3193,9 @@ EXPORT_SYMBOL(pin_user_pages_remote); * * FOLL_PIN means that the pages must be released via unpin_user_page(). Please * see Documentation/core-api/pin_user_pages.rst for details. + * + * Note that if a zero_page is amongst the returned pages, it will not have + * pins in it and unpin_user_page*() will not remove pins from it. */ long pin_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, @@ -3161,6 +3214,9 @@ EXPORT_SYMBOL(pin_user_pages); * pin_user_pages_unlocked() is the FOLL_PIN variant of * get_user_pages_unlocked(). Behavior is the same, except that this one sets * FOLL_PIN and rejects FOLL_GET. + * + * Note that if a zero_page is amongst the returned pages, it will not have + * pins in it and unpin_user_page*() will not remove pins from it. */ long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags) diff --git a/mm/gup_test.c b/mm/gup_test.c index 8ae7307a1bb6..c0421b786dcd 100644 --- a/mm/gup_test.c +++ b/mm/gup_test.c @@ -381,6 +381,7 @@ static int gup_test_release(struct inode *inode, struct file *file) static const struct file_operations gup_test_fops = { .open = nonseekable_open, .unlocked_ioctl = gup_test_ioctl, + .compat_ioctl = compat_ptr_ioctl, .release = gup_test_release, }; diff --git a/mm/internal.h b/mm/internal.h index 68410c6d97ac..e6029d94bdb2 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -179,12 +179,6 @@ extern unsigned long highest_memmap_pfn; #define MAX_RECLAIM_RETRIES 16 /* - * in mm/early_ioremap.c - */ -pgprot_t __init early_memremap_pgprot_adjust(resource_size_t phys_addr, - unsigned long size, pgprot_t prot); - -/* * in mm/vmscan.c: */ bool isolate_lru_page(struct page *page); diff --git a/mm/kfence/kfence.h b/mm/kfence/kfence.h index 2aafc46a4aaf..392fb273e7bd 100644 --- a/mm/kfence/kfence.h +++ b/mm/kfence/kfence.h @@ -29,7 +29,7 @@ * canary of every 8 bytes is the same. 64-bit memory can be filled and checked * at a time instead of byte by byte to improve performance. */ -#define KFENCE_CANARY_PATTERN_U64 ((u64)0xaaaaaaaaaaaaaaaa ^ (u64)(0x0706050403020100)) +#define KFENCE_CANARY_PATTERN_U64 ((u64)0xaaaaaaaaaaaaaaaa ^ (u64)(le64_to_cpu(0x0706050403020100))) /* Maximum stack depth for reports. */ #define KFENCE_STACK_DEPTH 64 diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 6b9d39d65b73..2d0d58fb4e7f 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -2070,7 +2070,6 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, TTU_IGNORE_MLOCK | TTU_BATCH_FLUSH); xas_lock_irq(&xas); - xas_set(&xas, index); VM_BUG_ON_PAGE(page != xas_load(&xas), page); diff --git a/mm/memblock.c b/mm/memblock.c index 3feafea06ab2..50b921119600 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1436,6 +1436,15 @@ done: */ kmemleak_alloc_phys(found, size, 0); + /* + * Some Virtual Machine platforms, such as Intel TDX or AMD SEV-SNP, + * require memory to be accepted before it can be used by the + * guest. + * + * Accept the memory of the allocated buffer. + */ + accept_memory(found, found + size); + return found; } diff --git a/mm/memfd.c b/mm/memfd.c index 69b90c31d38c..e763e76f1106 100644 --- a/mm/memfd.c +++ b/mm/memfd.c @@ -371,12 +371,15 @@ SYSCALL_DEFINE2(memfd_create, inode->i_mode &= ~0111; file_seals = memfd_file_seals_ptr(file); - *file_seals &= ~F_SEAL_SEAL; - *file_seals |= F_SEAL_EXEC; + if (file_seals) { + *file_seals &= ~F_SEAL_SEAL; + *file_seals |= F_SEAL_EXEC; + } } else if (flags & MFD_ALLOW_SEALING) { /* MFD_EXEC and MFD_ALLOW_SEALING are set */ file_seals = memfd_file_seals_ptr(file); - *file_seals &= ~F_SEAL_SEAL; + if (file_seals) + *file_seals &= ~F_SEAL_SEAL; } fd_install(fd, file); diff --git a/mm/mm_init.c b/mm/mm_init.c index 7f7f9c677854..1cfc08e25f93 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -1375,6 +1375,10 @@ static void __meminit zone_init_free_lists(struct zone *zone) INIT_LIST_HEAD(&zone->free_area[order].free_list[t]); zone->free_area[order].nr_free = 0; } + +#ifdef CONFIG_UNACCEPTED_MEMORY + INIT_LIST_HEAD(&zone->unaccepted_pages); +#endif } void __meminit init_currently_empty_zone(struct zone *zone, @@ -1960,6 +1964,9 @@ static void __init deferred_free_range(unsigned long pfn, return; } + /* Accept chunks smaller than MAX_ORDER upfront */ + accept_memory(PFN_PHYS(pfn), PFN_PHYS(pfn + nr_pages)); + for (i = 0; i < nr_pages; i++, page++, pfn++) { if (pageblock_aligned(pfn)) set_pageblock_migratetype(page, MIGRATE_MOVABLE); diff --git a/mm/mmap.c b/mm/mmap.c index 13678edaa22c..d600404580b2 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2318,21 +2318,6 @@ int split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, return __split_vma(vmi, vma, addr, new_below); } -static inline int munmap_sidetree(struct vm_area_struct *vma, - struct ma_state *mas_detach) -{ - vma_start_write(vma); - mas_set_range(mas_detach, vma->vm_start, vma->vm_end - 1); - if (mas_store_gfp(mas_detach, vma, GFP_KERNEL)) - return -ENOMEM; - - vma_mark_detached(vma, true); - if (vma->vm_flags & VM_LOCKED) - vma->vm_mm->locked_vm -= vma_pages(vma); - - return 0; -} - /* * do_vmi_align_munmap() - munmap the aligned region from @start to @end. * @vmi: The vma iterator @@ -2354,6 +2339,7 @@ do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, struct maple_tree mt_detach; int count = 0; int error = -ENOMEM; + unsigned long locked_vm = 0; MA_STATE(mas_detach, &mt_detach, 0, 0); mt_init_flags(&mt_detach, vmi->mas.tree->ma_flags & MT_FLAGS_LOCK_MASK); mt_set_external_lock(&mt_detach, &mm->mmap_lock); @@ -2399,9 +2385,13 @@ do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, if (error) goto end_split_failed; } - error = munmap_sidetree(next, &mas_detach); - if (error) - goto munmap_sidetree_failed; + vma_start_write(next); + mas_set_range(&mas_detach, next->vm_start, next->vm_end - 1); + if (mas_store_gfp(&mas_detach, next, GFP_KERNEL)) + goto munmap_gather_failed; + vma_mark_detached(next, true); + if (next->vm_flags & VM_LOCKED) + locked_vm += vma_pages(next); count++; #ifdef CONFIG_DEBUG_VM_MAPLE_TREE @@ -2447,10 +2437,12 @@ do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, } #endif /* Point of no return */ + error = -ENOMEM; vma_iter_set(vmi, start); if (vma_iter_clear_gfp(vmi, start, end, GFP_KERNEL)) - return -ENOMEM; + goto clear_tree_failed; + mm->locked_vm -= locked_vm; mm->map_count -= count; /* * Do not downgrade mmap_lock if we are next to VM_GROWSDOWN or @@ -2480,9 +2472,14 @@ do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, validate_mm(mm); return downgrade ? 1 : 0; +clear_tree_failed: userfaultfd_error: -munmap_sidetree_failed: +munmap_gather_failed: end_split_failed: + mas_set(&mas_detach, 0); + mas_for_each(&mas_detach, next, end) + vma_mark_detached(next, false); + __mt_destroy(&mt_detach); start_split_failed: map_count_exceeded: diff --git a/mm/mprotect.c b/mm/mprotect.c index 92d3d3ca390a..c59e7561698c 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -867,7 +867,7 @@ static int do_mprotect_pkey(unsigned long start, size_t len, } tlb_finish_mmu(&tlb); - if (!error && vma_iter_end(&vmi) < end) + if (!error && tmp < end) error = -ENOMEM; out: diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 47421bedc12b..d239fba3f31c 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -387,6 +387,12 @@ EXPORT_SYMBOL(nr_node_ids); EXPORT_SYMBOL(nr_online_nodes); #endif +static bool page_contains_unaccepted(struct page *page, unsigned int order); +static void accept_page(struct page *page, unsigned int order); +static bool try_to_accept_memory(struct zone *zone, unsigned int order); +static inline bool has_unaccepted_memory(void); +static bool __free_unaccepted(struct page *page); + int page_group_by_mobility_disabled __read_mostly; #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT @@ -1481,6 +1487,13 @@ void __free_pages_core(struct page *page, unsigned int order) atomic_long_add(nr_pages, &page_zone(page)->managed_pages); + if (page_contains_unaccepted(page, order)) { + if (order == MAX_ORDER && __free_unaccepted(page)) + return; + + accept_page(page, order); + } + /* * Bypass PCP and place fresh pages right to the tail, primarily * relevant for memory onlining. @@ -3159,6 +3172,9 @@ static inline long __zone_watermark_unusable_free(struct zone *z, if (!(alloc_flags & ALLOC_CMA)) unusable_free += zone_page_state(z, NR_FREE_CMA_PAGES); #endif +#ifdef CONFIG_UNACCEPTED_MEMORY + unusable_free += zone_page_state(z, NR_UNACCEPTED); +#endif return unusable_free; } @@ -3458,6 +3474,11 @@ retry: gfp_mask)) { int ret; + if (has_unaccepted_memory()) { + if (try_to_accept_memory(zone, order)) + goto try_this_zone; + } + #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT /* * Watermark failed for this zone, but see if we can @@ -3510,6 +3531,11 @@ try_this_zone: return page; } else { + if (has_unaccepted_memory()) { + if (try_to_accept_memory(zone, order)) + goto try_this_zone; + } + #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT /* Try again if zone has deferred pages */ if (deferred_pages_enabled()) { @@ -7215,3 +7241,150 @@ bool has_managed_dma(void) return false; } #endif /* CONFIG_ZONE_DMA */ + +#ifdef CONFIG_UNACCEPTED_MEMORY + +/* Counts number of zones with unaccepted pages. */ +static DEFINE_STATIC_KEY_FALSE(zones_with_unaccepted_pages); + +static bool lazy_accept = true; + +static int __init accept_memory_parse(char *p) +{ + if (!strcmp(p, "lazy")) { + lazy_accept = true; + return 0; + } else if (!strcmp(p, "eager")) { + lazy_accept = false; + return 0; + } else { + return -EINVAL; + } +} +early_param("accept_memory", accept_memory_parse); + +static bool page_contains_unaccepted(struct page *page, unsigned int order) +{ + phys_addr_t start = page_to_phys(page); + phys_addr_t end = start + (PAGE_SIZE << order); + + return range_contains_unaccepted_memory(start, end); +} + +static void accept_page(struct page *page, unsigned int order) +{ + phys_addr_t start = page_to_phys(page); + + accept_memory(start, start + (PAGE_SIZE << order)); +} + +static bool try_to_accept_memory_one(struct zone *zone) +{ + unsigned long flags; + struct page *page; + bool last; + + if (list_empty(&zone->unaccepted_pages)) + return false; + + spin_lock_irqsave(&zone->lock, flags); + page = list_first_entry_or_null(&zone->unaccepted_pages, + struct page, lru); + if (!page) { + spin_unlock_irqrestore(&zone->lock, flags); + return false; + } + + list_del(&page->lru); + last = list_empty(&zone->unaccepted_pages); + + __mod_zone_freepage_state(zone, -MAX_ORDER_NR_PAGES, MIGRATE_MOVABLE); + __mod_zone_page_state(zone, NR_UNACCEPTED, -MAX_ORDER_NR_PAGES); + spin_unlock_irqrestore(&zone->lock, flags); + + accept_page(page, MAX_ORDER); + + __free_pages_ok(page, MAX_ORDER, FPI_TO_TAIL); + + if (last) + static_branch_dec(&zones_with_unaccepted_pages); + + return true; +} + +static bool try_to_accept_memory(struct zone *zone, unsigned int order) +{ + long to_accept; + int ret = false; + + /* How much to accept to get to high watermark? */ + to_accept = high_wmark_pages(zone) - + (zone_page_state(zone, NR_FREE_PAGES) - + __zone_watermark_unusable_free(zone, order, 0)); + + /* Accept at least one page */ + do { + if (!try_to_accept_memory_one(zone)) + break; + ret = true; + to_accept -= MAX_ORDER_NR_PAGES; + } while (to_accept > 0); + + return ret; +} + +static inline bool has_unaccepted_memory(void) +{ + return static_branch_unlikely(&zones_with_unaccepted_pages); +} + +static bool __free_unaccepted(struct page *page) +{ + struct zone *zone = page_zone(page); + unsigned long flags; + bool first = false; + + if (!lazy_accept) + return false; + + spin_lock_irqsave(&zone->lock, flags); + first = list_empty(&zone->unaccepted_pages); + list_add_tail(&page->lru, &zone->unaccepted_pages); + __mod_zone_freepage_state(zone, MAX_ORDER_NR_PAGES, MIGRATE_MOVABLE); + __mod_zone_page_state(zone, NR_UNACCEPTED, MAX_ORDER_NR_PAGES); + spin_unlock_irqrestore(&zone->lock, flags); + + if (first) + static_branch_inc(&zones_with_unaccepted_pages); + + return true; +} + +#else + +static bool page_contains_unaccepted(struct page *page, unsigned int order) +{ + return false; +} + +static void accept_page(struct page *page, unsigned int order) +{ +} + +static bool try_to_accept_memory(struct zone *zone, unsigned int order) +{ + return false; +} + +static inline bool has_unaccepted_memory(void) +{ + return false; +} + +static bool __free_unaccepted(struct page *page) +{ + BUILD_BUG(); + return false; +} + +#endif /* CONFIG_UNACCEPTED_MEMORY */ diff --git a/mm/page_io.c b/mm/page_io.c index 87b682d18850..684cd3c7b59b 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -338,7 +338,7 @@ static void swap_writepage_bdev_sync(struct page *page, bio_init(&bio, sis->bdev, &bv, 1, REQ_OP_WRITE | REQ_SWAP | wbc_to_write_flags(wbc)); bio.bi_iter.bi_sector = swap_page_sector(page); - bio_add_page(&bio, page, thp_size(page), 0); + __bio_add_page(&bio, page, thp_size(page), 0); bio_associate_blkg_from_page(&bio, page); count_swpout_vm_event(page); @@ -360,7 +360,7 @@ static void swap_writepage_bdev_async(struct page *page, GFP_NOIO); bio->bi_iter.bi_sector = swap_page_sector(page); bio->bi_end_io = end_swap_bio_write; - bio_add_page(bio, page, thp_size(page), 0); + __bio_add_page(bio, page, thp_size(page), 0); bio_associate_blkg_from_page(bio, page); count_swpout_vm_event(page); @@ -468,7 +468,7 @@ static void swap_readpage_bdev_sync(struct page *page, bio_init(&bio, sis->bdev, &bv, 1, REQ_OP_READ); bio.bi_iter.bi_sector = swap_page_sector(page); - bio_add_page(&bio, page, thp_size(page), 0); + __bio_add_page(&bio, page, thp_size(page), 0); /* * Keep this task valid during swap readpage because the oom killer may * attempt to access it in the page fault retry time check. @@ -488,7 +488,7 @@ static void swap_readpage_bdev_async(struct page *page, bio = bio_alloc(sis->bdev, 1, REQ_OP_READ, GFP_KERNEL); bio->bi_iter.bi_sector = swap_page_sector(page); bio->bi_end_io = end_swap_bio_read; - bio_add_page(bio, page, thp_size(page), 0); + __bio_add_page(bio, page, thp_size(page), 0); count_vm_event(PSWPIN); submit_bio(bio); } diff --git a/mm/page_table_check.c b/mm/page_table_check.c index 25d8610c0042..f2baf97d5f38 100644 --- a/mm/page_table_check.c +++ b/mm/page_table_check.c @@ -71,6 +71,8 @@ static void page_table_check_clear(struct mm_struct *mm, unsigned long addr, page = pfn_to_page(pfn); page_ext = page_ext_get(page); + + BUG_ON(PageSlab(page)); anon = PageAnon(page); for (i = 0; i < pgcnt; i++) { @@ -107,6 +109,8 @@ static void page_table_check_set(struct mm_struct *mm, unsigned long addr, page = pfn_to_page(pfn); page_ext = page_ext_get(page); + + BUG_ON(PageSlab(page)); anon = PageAnon(page); for (i = 0; i < pgcnt; i++) { @@ -133,6 +137,8 @@ void __page_table_check_zero(struct page *page, unsigned int order) struct page_ext *page_ext; unsigned long i; + BUG_ON(PageSlab(page)); + page_ext = page_ext_get(page); BUG_ON(!page_ext); for (i = 0; i < (1ul << order); i++) { diff --git a/mm/shmem.c b/mm/shmem.c index e40a08c5c6d7..1f504ed982cf 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2731,6 +2731,138 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) return retval ? retval : error; } +static bool zero_pipe_buf_get(struct pipe_inode_info *pipe, + struct pipe_buffer *buf) +{ + return true; +} + +static void zero_pipe_buf_release(struct pipe_inode_info *pipe, + struct pipe_buffer *buf) +{ +} + +static bool zero_pipe_buf_try_steal(struct pipe_inode_info *pipe, + struct pipe_buffer *buf) +{ + return false; +} + +static const struct pipe_buf_operations zero_pipe_buf_ops = { + .release = zero_pipe_buf_release, + .try_steal = zero_pipe_buf_try_steal, + .get = zero_pipe_buf_get, +}; + +static size_t splice_zeropage_into_pipe(struct pipe_inode_info *pipe, + loff_t fpos, size_t size) +{ + size_t offset = fpos & ~PAGE_MASK; + + size = min_t(size_t, size, PAGE_SIZE - offset); + + if (!pipe_full(pipe->head, pipe->tail, pipe->max_usage)) { + struct pipe_buffer *buf = pipe_head_buf(pipe); + + *buf = (struct pipe_buffer) { + .ops = &zero_pipe_buf_ops, + .page = ZERO_PAGE(0), + .offset = offset, + .len = size, + }; + pipe->head++; + } + + return size; +} + +static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, + size_t len, unsigned int flags) +{ + struct inode *inode = file_inode(in); + struct address_space *mapping = inode->i_mapping; + struct folio *folio = NULL; + size_t total_spliced = 0, used, npages, n, part; + loff_t isize; + int error = 0; + + /* Work out how much data we can actually add into the pipe */ + used = pipe_occupancy(pipe->head, pipe->tail); + npages = max_t(ssize_t, pipe->max_usage - used, 0); + len = min_t(size_t, len, npages * PAGE_SIZE); + + do { + if (*ppos >= i_size_read(inode)) + break; + + error = shmem_get_folio(inode, *ppos / PAGE_SIZE, &folio, SGP_READ); + if (error) { + if (error == -EINVAL) + error = 0; + break; + } + if (folio) { + folio_unlock(folio); + + if (folio_test_hwpoison(folio)) { + error = -EIO; + break; + } + } + + /* + * i_size must be checked after we know the pages are Uptodate. + * + * Checking i_size after the check allows us to calculate + * the correct value for "nr", which means the zero-filled + * part of the page is not copied back to userspace (unless + * another truncate extends the file - this is desired though). + */ + isize = i_size_read(inode); + if (unlikely(*ppos >= isize)) + break; + part = min_t(loff_t, isize - *ppos, len); + + if (folio) { + /* + * If users can be writing to this page using arbitrary + * virtual addresses, take care about potential aliasing + * before reading the page on the kernel side. + */ + if (mapping_writably_mapped(mapping)) + flush_dcache_folio(folio); + folio_mark_accessed(folio); + /* + * Ok, we have the page, and it's up-to-date, so we can + * now splice it into the pipe. + */ + n = splice_folio_into_pipe(pipe, folio, *ppos, part); + folio_put(folio); + folio = NULL; + } else { + n = splice_zeropage_into_pipe(pipe, *ppos, len); + } + + if (!n) + break; + len -= n; + total_spliced += n; + *ppos += n; + in->f_ra.prev_pos = *ppos; + if (pipe_full(pipe->head, pipe->tail, pipe->max_usage)) + break; + + cond_resched(); + } while (len); + + if (folio) + folio_put(folio); + + file_accessed(in); + return total_spliced ? total_spliced : error; +} + static loff_t shmem_file_llseek(struct file *file, loff_t offset, int whence) { struct address_space *mapping = file->f_mapping; @@ -3971,7 +4103,7 @@ static const struct file_operations shmem_file_operations = { .read_iter = shmem_file_read_iter, .write_iter = generic_file_write_iter, .fsync = noop_fsync, - .splice_read = generic_file_splice_read, + .splice_read = shmem_file_splice_read, .splice_write = iter_file_splice_write, .fallocate = shmem_fallocate, #endif diff --git a/mm/shrinker_debug.c b/mm/shrinker_debug.c index 3f83b10c5031..3ab53fad8876 100644 --- a/mm/shrinker_debug.c +++ b/mm/shrinker_debug.c @@ -5,12 +5,10 @@ #include <linux/seq_file.h> #include <linux/shrinker.h> #include <linux/memcontrol.h> -#include <linux/srcu.h> /* defined in vmscan.c */ -extern struct mutex shrinker_mutex; +extern struct rw_semaphore shrinker_rwsem; extern struct list_head shrinker_list; -extern struct srcu_struct shrinker_srcu; static DEFINE_IDA(shrinker_debugfs_ida); static struct dentry *shrinker_debugfs_root; @@ -51,13 +49,18 @@ static int shrinker_debugfs_count_show(struct seq_file *m, void *v) struct mem_cgroup *memcg; unsigned long total; bool memcg_aware; - int ret = 0, nid, srcu_idx; + int ret, nid; count_per_node = kcalloc(nr_node_ids, sizeof(unsigned long), GFP_KERNEL); if (!count_per_node) return -ENOMEM; - srcu_idx = srcu_read_lock(&shrinker_srcu); + ret = down_read_killable(&shrinker_rwsem); + if (ret) { + kfree(count_per_node); + return ret; + } + rcu_read_lock(); memcg_aware = shrinker->flags & SHRINKER_MEMCG_AWARE; @@ -88,7 +91,8 @@ static int shrinker_debugfs_count_show(struct seq_file *m, void *v) } } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL); - srcu_read_unlock(&shrinker_srcu, srcu_idx); + rcu_read_unlock(); + up_read(&shrinker_rwsem); kfree(count_per_node); return ret; @@ -111,8 +115,9 @@ static ssize_t shrinker_debugfs_scan_write(struct file *file, .gfp_mask = GFP_KERNEL, }; struct mem_cgroup *memcg = NULL; - int nid, srcu_idx; + int nid; char kbuf[72]; + ssize_t ret; read_len = size < (sizeof(kbuf) - 1) ? size : (sizeof(kbuf) - 1); if (copy_from_user(kbuf, buf, read_len)) @@ -141,7 +146,11 @@ static ssize_t shrinker_debugfs_scan_write(struct file *file, return -EINVAL; } - srcu_idx = srcu_read_lock(&shrinker_srcu); + ret = down_read_killable(&shrinker_rwsem); + if (ret) { + mem_cgroup_put(memcg); + return ret; + } sc.nid = nid; sc.memcg = memcg; @@ -150,7 +159,7 @@ static ssize_t shrinker_debugfs_scan_write(struct file *file, shrinker->scan_objects(shrinker, &sc); - srcu_read_unlock(&shrinker_srcu, srcu_idx); + up_read(&shrinker_rwsem); mem_cgroup_put(memcg); return size; @@ -168,7 +177,7 @@ int shrinker_debugfs_add(struct shrinker *shrinker) char buf[128]; int id; - lockdep_assert_held(&shrinker_mutex); + lockdep_assert_held(&shrinker_rwsem); /* debugfs isn't initialized yet, add debugfs entries later. */ if (!shrinker_debugfs_root) @@ -211,7 +220,7 @@ int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...) if (!new) return -ENOMEM; - mutex_lock(&shrinker_mutex); + down_write(&shrinker_rwsem); old = shrinker->name; shrinker->name = new; @@ -229,7 +238,7 @@ int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...) shrinker->debugfs_entry = entry; } - mutex_unlock(&shrinker_mutex); + up_write(&shrinker_rwsem); kfree_const(old); @@ -237,23 +246,28 @@ int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...) } EXPORT_SYMBOL(shrinker_debugfs_rename); -struct dentry *shrinker_debugfs_remove(struct shrinker *shrinker) +struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, + int *debugfs_id) { struct dentry *entry = shrinker->debugfs_entry; - lockdep_assert_held(&shrinker_mutex); + lockdep_assert_held(&shrinker_rwsem); kfree_const(shrinker->name); shrinker->name = NULL; - if (entry) { - ida_free(&shrinker_debugfs_ida, shrinker->debugfs_id); - shrinker->debugfs_entry = NULL; - } + *debugfs_id = entry ? shrinker->debugfs_id : -1; + shrinker->debugfs_entry = NULL; return entry; } +void shrinker_debugfs_remove(struct dentry *debugfs_entry, int debugfs_id) +{ + debugfs_remove_recursive(debugfs_entry); + ida_free(&shrinker_debugfs_ida, debugfs_id); +} + static int __init shrinker_debugfs_init(void) { struct shrinker *shrinker; @@ -266,14 +280,14 @@ static int __init shrinker_debugfs_init(void) shrinker_debugfs_root = dentry; /* Create debugfs entries for shrinkers registered at boot */ - mutex_lock(&shrinker_mutex); + down_write(&shrinker_rwsem); list_for_each_entry(shrinker, &shrinker_list, list) if (!shrinker->debugfs_entry) { ret = shrinker_debugfs_add(shrinker); if (ret) break; } - mutex_unlock(&shrinker_mutex); + up_write(&shrinker_rwsem); return ret; } diff --git a/mm/swapfile.c b/mm/swapfile.c index 274bbf797480..6bc83060df9a 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2539,7 +2539,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) struct block_device *bdev = I_BDEV(inode); set_blocksize(bdev, old_block_size); - blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); + blkdev_put(bdev, p); } inode_lock(inode); @@ -2770,7 +2770,7 @@ static int claim_swapfile(struct swap_info_struct *p, struct inode *inode) if (S_ISBLK(inode->i_mode)) { p->bdev = blkdev_get_by_dev(inode->i_rdev, - FMODE_READ | FMODE_WRITE | FMODE_EXCL, p); + BLK_OPEN_READ | BLK_OPEN_WRITE, p, NULL); if (IS_ERR(p->bdev)) { error = PTR_ERR(p->bdev); p->bdev = NULL; @@ -3221,7 +3221,7 @@ bad_swap: p->cluster_next_cpu = NULL; if (inode && S_ISBLK(inode->i_mode) && p->bdev) { set_blocksize(p->bdev, p->old_block_size); - blkdev_put(p->bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); + blkdev_put(p->bdev, p); } inode = NULL; destroy_swap_extents(p); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 9683573f1225..1d13d71687d7 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -3098,11 +3098,20 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, * allocation request, free them via vfree() if any. */ if (area->nr_pages != nr_small_pages) { - /* vm_area_alloc_pages() can also fail due to a fatal signal */ - if (!fatal_signal_pending(current)) + /* + * vm_area_alloc_pages() can fail due to insufficient memory but + * also:- + * + * - a pending fatal signal + * - insufficient huge page-order pages + * + * Since we always retry allocations at order-0 in the huge page + * case a warning for either is spurious. + */ + if (!fatal_signal_pending(current) && page_order == 0) warn_alloc(gfp_mask, NULL, - "vmalloc error: size %lu, page order %u, failed to allocate pages", - area->nr_pages * PAGE_SIZE, page_order); + "vmalloc error: size %lu, failed to allocate pages", + area->nr_pages * PAGE_SIZE); goto fail; } diff --git a/mm/vmscan.c b/mm/vmscan.c index d257916f39e5..5bf98d0a22c9 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -35,7 +35,7 @@ #include <linux/cpuset.h> #include <linux/compaction.h> #include <linux/notifier.h> -#include <linux/mutex.h> +#include <linux/rwsem.h> #include <linux/delay.h> #include <linux/kthread.h> #include <linux/freezer.h> @@ -57,7 +57,6 @@ #include <linux/khugepaged.h> #include <linux/rculist_nulls.h> #include <linux/random.h> -#include <linux/srcu.h> #include <asm/tlbflush.h> #include <asm/div64.h> @@ -190,9 +189,7 @@ struct scan_control { int vm_swappiness = 60; LIST_HEAD(shrinker_list); -DEFINE_MUTEX(shrinker_mutex); -DEFINE_SRCU(shrinker_srcu); -static atomic_t shrinker_srcu_generation = ATOMIC_INIT(0); +DECLARE_RWSEM(shrinker_rwsem); #ifdef CONFIG_MEMCG static int shrinker_nr_max; @@ -211,21 +208,8 @@ static inline int shrinker_defer_size(int nr_items) static struct shrinker_info *shrinker_info_protected(struct mem_cgroup *memcg, int nid) { - return srcu_dereference_check(memcg->nodeinfo[nid]->shrinker_info, - &shrinker_srcu, - lockdep_is_held(&shrinker_mutex)); -} - -static struct shrinker_info *shrinker_info_srcu(struct mem_cgroup *memcg, - int nid) -{ - return srcu_dereference(memcg->nodeinfo[nid]->shrinker_info, - &shrinker_srcu); -} - -static void free_shrinker_info_rcu(struct rcu_head *head) -{ - kvfree(container_of(head, struct shrinker_info, rcu)); + return rcu_dereference_protected(memcg->nodeinfo[nid]->shrinker_info, + lockdep_is_held(&shrinker_rwsem)); } static int expand_one_shrinker_info(struct mem_cgroup *memcg, @@ -266,7 +250,7 @@ static int expand_one_shrinker_info(struct mem_cgroup *memcg, defer_size - old_defer_size); rcu_assign_pointer(pn->shrinker_info, new); - call_srcu(&shrinker_srcu, &old->rcu, free_shrinker_info_rcu); + kvfree_rcu(old, rcu); } return 0; @@ -292,7 +276,7 @@ int alloc_shrinker_info(struct mem_cgroup *memcg) int nid, size, ret = 0; int map_size, defer_size = 0; - mutex_lock(&shrinker_mutex); + down_write(&shrinker_rwsem); map_size = shrinker_map_size(shrinker_nr_max); defer_size = shrinker_defer_size(shrinker_nr_max); size = map_size + defer_size; @@ -308,7 +292,7 @@ int alloc_shrinker_info(struct mem_cgroup *memcg) info->map_nr_max = shrinker_nr_max; rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_info, info); } - mutex_unlock(&shrinker_mutex); + up_write(&shrinker_rwsem); return ret; } @@ -324,7 +308,7 @@ static int expand_shrinker_info(int new_id) if (!root_mem_cgroup) goto out; - lockdep_assert_held(&shrinker_mutex); + lockdep_assert_held(&shrinker_rwsem); map_size = shrinker_map_size(new_nr_max); defer_size = shrinker_defer_size(new_nr_max); @@ -352,16 +336,15 @@ void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id) { if (shrinker_id >= 0 && memcg && !mem_cgroup_is_root(memcg)) { struct shrinker_info *info; - int srcu_idx; - srcu_idx = srcu_read_lock(&shrinker_srcu); - info = shrinker_info_srcu(memcg, nid); + rcu_read_lock(); + info = rcu_dereference(memcg->nodeinfo[nid]->shrinker_info); if (!WARN_ON_ONCE(shrinker_id >= info->map_nr_max)) { /* Pairs with smp mb in shrink_slab() */ smp_mb__before_atomic(); set_bit(shrinker_id, info->map); } - srcu_read_unlock(&shrinker_srcu, srcu_idx); + rcu_read_unlock(); } } @@ -374,7 +357,8 @@ static int prealloc_memcg_shrinker(struct shrinker *shrinker) if (mem_cgroup_disabled()) return -ENOSYS; - mutex_lock(&shrinker_mutex); + down_write(&shrinker_rwsem); + /* This may call shrinker, so it must use down_read_trylock() */ id = idr_alloc(&shrinker_idr, shrinker, 0, 0, GFP_KERNEL); if (id < 0) goto unlock; @@ -388,7 +372,7 @@ static int prealloc_memcg_shrinker(struct shrinker *shrinker) shrinker->id = id; ret = 0; unlock: - mutex_unlock(&shrinker_mutex); + up_write(&shrinker_rwsem); return ret; } @@ -398,7 +382,7 @@ static void unregister_memcg_shrinker(struct shrinker *shrinker) BUG_ON(id < 0); - lockdep_assert_held(&shrinker_mutex); + lockdep_assert_held(&shrinker_rwsem); idr_remove(&shrinker_idr, id); } @@ -408,7 +392,7 @@ static long xchg_nr_deferred_memcg(int nid, struct shrinker *shrinker, { struct shrinker_info *info; - info = shrinker_info_srcu(memcg, nid); + info = shrinker_info_protected(memcg, nid); return atomic_long_xchg(&info->nr_deferred[shrinker->id], 0); } @@ -417,7 +401,7 @@ static long add_nr_deferred_memcg(long nr, int nid, struct shrinker *shrinker, { struct shrinker_info *info; - info = shrinker_info_srcu(memcg, nid); + info = shrinker_info_protected(memcg, nid); return atomic_long_add_return(nr, &info->nr_deferred[shrinker->id]); } @@ -433,7 +417,7 @@ void reparent_shrinker_deferred(struct mem_cgroup *memcg) parent = root_mem_cgroup; /* Prevent from concurrent shrinker_info expand */ - mutex_lock(&shrinker_mutex); + down_read(&shrinker_rwsem); for_each_node(nid) { child_info = shrinker_info_protected(memcg, nid); parent_info = shrinker_info_protected(parent, nid); @@ -442,7 +426,7 @@ void reparent_shrinker_deferred(struct mem_cgroup *memcg) atomic_long_add(nr, &parent_info->nr_deferred[i]); } } - mutex_unlock(&shrinker_mutex); + up_read(&shrinker_rwsem); } static bool cgroup_reclaim(struct scan_control *sc) @@ -743,9 +727,9 @@ void free_prealloced_shrinker(struct shrinker *shrinker) shrinker->name = NULL; #endif if (shrinker->flags & SHRINKER_MEMCG_AWARE) { - mutex_lock(&shrinker_mutex); + down_write(&shrinker_rwsem); unregister_memcg_shrinker(shrinker); - mutex_unlock(&shrinker_mutex); + up_write(&shrinker_rwsem); return; } @@ -755,11 +739,11 @@ void free_prealloced_shrinker(struct shrinker *shrinker) void register_shrinker_prepared(struct shrinker *shrinker) { - mutex_lock(&shrinker_mutex); - list_add_tail_rcu(&shrinker->list, &shrinker_list); + down_write(&shrinker_rwsem); + list_add_tail(&shrinker->list, &shrinker_list); shrinker->flags |= SHRINKER_REGISTERED; shrinker_debugfs_add(shrinker); - mutex_unlock(&shrinker_mutex); + up_write(&shrinker_rwsem); } static int __register_shrinker(struct shrinker *shrinker) @@ -805,22 +789,20 @@ EXPORT_SYMBOL(register_shrinker); void unregister_shrinker(struct shrinker *shrinker) { struct dentry *debugfs_entry; + int debugfs_id; if (!(shrinker->flags & SHRINKER_REGISTERED)) return; - mutex_lock(&shrinker_mutex); - list_del_rcu(&shrinker->list); + down_write(&shrinker_rwsem); + list_del(&shrinker->list); shrinker->flags &= ~SHRINKER_REGISTERED; if (shrinker->flags & SHRINKER_MEMCG_AWARE) unregister_memcg_shrinker(shrinker); - debugfs_entry = shrinker_debugfs_remove(shrinker); - mutex_unlock(&shrinker_mutex); + debugfs_entry = shrinker_debugfs_detach(shrinker, &debugfs_id); + up_write(&shrinker_rwsem); - atomic_inc(&shrinker_srcu_generation); - synchronize_srcu(&shrinker_srcu); - - debugfs_remove_recursive(debugfs_entry); + shrinker_debugfs_remove(debugfs_entry, debugfs_id); kfree(shrinker->nr_deferred); shrinker->nr_deferred = NULL; @@ -830,13 +812,15 @@ EXPORT_SYMBOL(unregister_shrinker); /** * synchronize_shrinkers - Wait for all running shrinkers to complete. * - * This is useful to guarantee that all shrinker invocations have seen an - * update, before freeing memory. + * This is equivalent to calling unregister_shrink() and register_shrinker(), + * but atomically and with less overhead. This is useful to guarantee that all + * shrinker invocations have seen an update, before freeing memory, similar to + * rcu. */ void synchronize_shrinkers(void) { - atomic_inc(&shrinker_srcu_generation); - synchronize_srcu(&shrinker_srcu); + down_write(&shrinker_rwsem); + up_write(&shrinker_rwsem); } EXPORT_SYMBOL(synchronize_shrinkers); @@ -945,20 +929,19 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, { struct shrinker_info *info; unsigned long ret, freed = 0; - int srcu_idx, generation; - int i = 0; + int i; if (!mem_cgroup_online(memcg)) return 0; -again: - srcu_idx = srcu_read_lock(&shrinker_srcu); - info = shrinker_info_srcu(memcg, nid); + if (!down_read_trylock(&shrinker_rwsem)) + return 0; + + info = shrinker_info_protected(memcg, nid); if (unlikely(!info)) goto unlock; - generation = atomic_read(&shrinker_srcu_generation); - for_each_set_bit_from(i, info->map, info->map_nr_max) { + for_each_set_bit(i, info->map, info->map_nr_max) { struct shrink_control sc = { .gfp_mask = gfp_mask, .nid = nid, @@ -1004,14 +987,14 @@ again: set_shrinker_bit(memcg, nid, i); } freed += ret; - if (atomic_read(&shrinker_srcu_generation) != generation) { - srcu_read_unlock(&shrinker_srcu, srcu_idx); - i++; - goto again; + + if (rwsem_is_contended(&shrinker_rwsem)) { + freed = freed ? : 1; + break; } } unlock: - srcu_read_unlock(&shrinker_srcu, srcu_idx); + up_read(&shrinker_rwsem); return freed; } #else /* CONFIG_MEMCG */ @@ -1048,7 +1031,6 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid, { unsigned long ret, freed = 0; struct shrinker *shrinker; - int srcu_idx, generation; /* * The root memcg might be allocated even though memcg is disabled @@ -1060,11 +1042,10 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid, if (!mem_cgroup_disabled() && !mem_cgroup_is_root(memcg)) return shrink_slab_memcg(gfp_mask, nid, memcg, priority); - srcu_idx = srcu_read_lock(&shrinker_srcu); + if (!down_read_trylock(&shrinker_rwsem)) + goto out; - generation = atomic_read(&shrinker_srcu_generation); - list_for_each_entry_srcu(shrinker, &shrinker_list, list, - srcu_read_lock_held(&shrinker_srcu)) { + list_for_each_entry(shrinker, &shrinker_list, list) { struct shrink_control sc = { .gfp_mask = gfp_mask, .nid = nid, @@ -1075,14 +1056,19 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid, if (ret == SHRINK_EMPTY) ret = 0; freed += ret; - - if (atomic_read(&shrinker_srcu_generation) != generation) { + /* + * Bail out if someone want to register a new shrinker to + * prevent the registration from being stalled for long periods + * by parallel ongoing shrinking. + */ + if (rwsem_is_contended(&shrinker_rwsem)) { freed = freed ? : 1; break; } } - srcu_read_unlock(&shrinker_srcu, srcu_idx); + up_read(&shrinker_rwsem); +out: cond_resched(); return freed; } diff --git a/mm/vmstat.c b/mm/vmstat.c index c28046371b45..282349cabf01 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1180,6 +1180,9 @@ const char * const vmstat_text[] = { "nr_zspages", #endif "nr_free_cma", +#ifdef CONFIG_UNACCEPTED_MEMORY + "nr_unaccepted", +#endif /* enum numa_stat_item counters */ #ifdef CONFIG_NUMA diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 44ddaf5d601e..02f7f414aade 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -1331,31 +1331,6 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle, obj_to_location(obj, &page, &obj_idx); zspage = get_zspage(page); -#ifdef CONFIG_ZPOOL - /* - * Move the zspage to front of pool's LRU. - * - * Note that this is swap-specific, so by definition there are no ongoing - * accesses to the memory while the page is swapped out that would make - * it "hot". A new entry is hot, then ages to the tail until it gets either - * written back or swaps back in. - * - * Furthermore, map is also called during writeback. We must not put an - * isolated page on the LRU mid-reclaim. - * - * As a result, only update the LRU when the page is mapped for write - * when it's first instantiated. - * - * This is a deviation from the other backends, which perform this update - * in the allocation function (zbud_alloc, z3fold_alloc). - */ - if (mm == ZS_MM_WO) { - if (!list_empty(&zspage->lru)) - list_del(&zspage->lru); - list_add(&zspage->lru, &pool->lru); - } -#endif - /* * migration cannot move any zpages in this zspage. Here, pool->lock * is too heavy since callers would take some time until they calls @@ -1525,9 +1500,8 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp) fix_fullness_group(class, zspage); record_obj(handle, obj); class_stat_inc(class, ZS_OBJS_INUSE, 1); - spin_unlock(&pool->lock); - return handle; + goto out; } spin_unlock(&pool->lock); @@ -1550,6 +1524,14 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp) /* We completely set up zspage so mark them as movable */ SetZsPageMovable(pool, zspage); +out: +#ifdef CONFIG_ZPOOL + /* Add/move zspage to beginning of LRU */ + if (!list_empty(&zspage->lru)) + list_del(&zspage->lru); + list_add(&zspage->lru, &pool->lru); +#endif + spin_unlock(&pool->lock); return handle; diff --git a/mm/zswap.c b/mm/zswap.c index e1e621d0b6a0..30092d9a3b23 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -1020,6 +1020,22 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle) goto fail; case ZSWAP_SWAPCACHE_NEW: /* page is locked */ + /* + * Having a local reference to the zswap entry doesn't exclude + * swapping from invalidating and recycling the swap slot. Once + * the swapcache is secured against concurrent swapping to and + * from the slot, recheck that the entry is still current before + * writing. + */ + spin_lock(&tree->lock); + if (zswap_rb_search(&tree->rbroot, entry->offset) != entry) { + spin_unlock(&tree->lock); + delete_from_swap_cache(page_folio(page)); + ret = -ENOMEM; + goto fail; + } + spin_unlock(&tree->lock); + /* decompress */ acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx); dlen = PAGE_SIZE; @@ -1158,9 +1174,16 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset, goto reject; } + /* + * XXX: zswap reclaim does not work with cgroups yet. Without a + * cgroup-aware entry LRU, we will push out entries system-wide based on + * local cgroup limits. + */ objcg = get_obj_cgroup_from_page(page); - if (objcg && !obj_cgroup_may_zswap(objcg)) - goto shrink; + if (objcg && !obj_cgroup_may_zswap(objcg)) { + ret = -ENOMEM; + goto reject; + } /* reclaim space if needed */ if (zswap_is_full()) { |