diff options
Diffstat (limited to 'mm')
-rw-r--r-- | mm/Kconfig.debug | 1 | ||||
-rw-r--r-- | mm/filemap.c | 31 | ||||
-rw-r--r-- | mm/gup.c | 64 | ||||
-rw-r--r-- | mm/internal.h | 6 | ||||
-rw-r--r-- | mm/memblock.c | 9 | ||||
-rw-r--r-- | mm/mm_init.c | 7 | ||||
-rw-r--r-- | mm/mmap.c | 37 | ||||
-rw-r--r-- | mm/mremap.c | 3 | ||||
-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/slab.h | 53 | ||||
-rw-r--r-- | mm/slub.c | 139 | ||||
-rw-r--r-- | mm/swapfile.c | 6 | ||||
-rw-r--r-- | mm/vmstat.c | 3 |
16 files changed, 570 insertions, 110 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/filemap.c b/mm/filemap.c index 758bbdf300e7..9e44a49bbd74 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2655,8 +2655,7 @@ 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; @@ -2873,9 +2872,24 @@ 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, @@ -2888,6 +2902,9 @@ 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; @@ -2901,7 +2918,7 @@ 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; @@ -2917,7 +2934,7 @@ 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); @@ -52,7 +52,8 @@ 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); @@ -132,12 +133,19 @@ struct folio *try_grab_folio(struct page *page, int refs, unsigned int flags) if (unlikely(!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(page))) return NULL; - folio = try_get_folio(page, refs); - if (flags & FOLL_GET) - return folio; + return try_get_folio(page, refs); /* FOLL_PIN is set */ + + /* + * 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); + + folio = try_get_folio(page, refs); if (!folio) return NULL; @@ -181,6 +189,8 @@ 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); @@ -226,6 +236,13 @@ 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. @@ -259,6 +276,33 @@ 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) { @@ -3190,6 +3234,9 @@ 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) @@ -3219,6 +3266,9 @@ 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, @@ -3250,6 +3300,9 @@ 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) @@ -3267,6 +3320,9 @@ 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/internal.h b/mm/internal.h index a19255615bf2..a7d9e980429a 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/memblock.c b/mm/memblock.c index 46739551d4d1..388bc0c78998 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/mm_init.c b/mm/mm_init.c index 7ffa609673ea..a1963c3322af 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -1380,6 +1380,10 @@ 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, @@ -1974,6 +1978,9 @@ 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 4fc496bc5b95..8f1000bc35df 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2331,21 +2331,6 @@ 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 @@ -2367,6 +2352,7 @@ 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); @@ -2412,9 +2398,13 @@ 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++; if (unlikely(uf)) { @@ -2464,10 +2454,12 @@ 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 @@ -2497,9 +2489,14 @@ 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/mremap.c b/mm/mremap.c index 8ec184ac90ff..fe6b722ae633 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -926,7 +926,8 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, * mapping address intact. A non-zero tag will cause the subsequent * range checks to reject the address as invalid. * - * See Documentation/arm64/tagged-address-abi.rst for more information. + * See Documentation/arch/arm64/tagged-address-abi.rst for more + * information. */ addr = untagged_addr(addr); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 158f24d186e6..7d3460c7a480 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -311,6 +311,12 @@ 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 @@ -1334,6 +1340,13 @@ 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. @@ -2857,6 +2870,9 @@ 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; } @@ -3156,6 +3172,11 @@ 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 @@ -3208,6 +3229,11 @@ 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()) { @@ -6590,3 +6616,150 @@ 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 8f89f9c8f0df..93ec7690a0d8 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 c606ab89693a..2f2e0e618072 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; @@ -3974,7 +4106,7 @@ 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/slab.h b/mm/slab.h index 592590fcddae..a59c8e5d2441 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -6,6 +6,38 @@ */ void __init kmem_cache_init(void); +#ifdef CONFIG_64BIT +# ifdef system_has_cmpxchg128 +# define system_has_freelist_aba() system_has_cmpxchg128() +# define try_cmpxchg_freelist try_cmpxchg128 +# endif +#define this_cpu_try_cmpxchg_freelist this_cpu_try_cmpxchg128 +typedef u128 freelist_full_t; +#else /* CONFIG_64BIT */ +# ifdef system_has_cmpxchg64 +# define system_has_freelist_aba() system_has_cmpxchg64() +# define try_cmpxchg_freelist try_cmpxchg64 +# endif +#define this_cpu_try_cmpxchg_freelist this_cpu_try_cmpxchg64 +typedef u64 freelist_full_t; +#endif /* CONFIG_64BIT */ + +#if defined(system_has_freelist_aba) && !defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE) +#undef system_has_freelist_aba +#endif + +/* + * Freelist pointer and counter to cmpxchg together, avoids the typical ABA + * problems with cmpxchg of just a pointer. + */ +typedef union { + struct { + void *freelist; + unsigned long counter; + }; + freelist_full_t full; +} freelist_aba_t; + /* Reuses the bits in struct page */ struct slab { unsigned long __page_flags; @@ -38,14 +70,21 @@ struct slab { #endif }; /* Double-word boundary */ - void *freelist; /* first free object */ union { - unsigned long counters; struct { - unsigned inuse:16; - unsigned objects:15; - unsigned frozen:1; + void *freelist; /* first free object */ + union { + unsigned long counters; + struct { + unsigned inuse:16; + unsigned objects:15; + unsigned frozen:1; + }; + }; }; +#ifdef system_has_freelist_aba + freelist_aba_t freelist_counter; +#endif }; }; struct rcu_head rcu_head; @@ -72,8 +111,8 @@ SLAB_MATCH(memcg_data, memcg_data); #endif #undef SLAB_MATCH static_assert(sizeof(struct slab) <= sizeof(struct page)); -#if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) && defined(CONFIG_SLUB) -static_assert(IS_ALIGNED(offsetof(struct slab, freelist), 2*sizeof(void *))); +#if defined(system_has_freelist_aba) && defined(CONFIG_SLUB) +static_assert(IS_ALIGNED(offsetof(struct slab, freelist), sizeof(freelist_aba_t))); #endif /** diff --git a/mm/slub.c b/mm/slub.c index c87628cd8a9a..7529626bbec2 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -292,7 +292,12 @@ static inline bool kmem_cache_has_cpu_partial(struct kmem_cache *s) /* Poison object */ #define __OBJECT_POISON ((slab_flags_t __force)0x80000000U) /* Use cmpxchg_double */ + +#ifdef system_has_freelist_aba #define __CMPXCHG_DOUBLE ((slab_flags_t __force)0x40000000U) +#else +#define __CMPXCHG_DOUBLE ((slab_flags_t __force)0U) +#endif /* * Tracking user of a slab. @@ -512,6 +517,40 @@ static __always_inline void slab_unlock(struct slab *slab) __bit_spin_unlock(PG_locked, &page->flags); } +static inline bool +__update_freelist_fast(struct slab *slab, + void *freelist_old, unsigned long counters_old, + void *freelist_new, unsigned long counters_new) +{ +#ifdef system_has_freelist_aba + freelist_aba_t old = { .freelist = freelist_old, .counter = counters_old }; + freelist_aba_t new = { .freelist = freelist_new, .counter = counters_new }; + + return try_cmpxchg_freelist(&slab->freelist_counter.full, &old.full, new.full); +#else + return false; +#endif +} + +static inline bool +__update_freelist_slow(struct slab *slab, + void *freelist_old, unsigned long counters_old, + void *freelist_new, unsigned long counters_new) +{ + bool ret = false; + + slab_lock(slab); + if (slab->freelist == freelist_old && + slab->counters == counters_old) { + slab->freelist = freelist_new; + slab->counters = counters_new; + ret = true; + } + slab_unlock(slab); + + return ret; +} + /* * Interrupts must be disabled (for the fallback code to work right), typically * by an _irqsave() lock variant. On PREEMPT_RT the preempt_disable(), which is @@ -519,33 +558,25 @@ static __always_inline void slab_unlock(struct slab *slab) * allocation/ free operation in hardirq context. Therefore nothing can * interrupt the operation. */ -static inline bool __cmpxchg_double_slab(struct kmem_cache *s, struct slab *slab, +static inline bool __slab_update_freelist(struct kmem_cache *s, struct slab *slab, void *freelist_old, unsigned long counters_old, void *freelist_new, unsigned long counters_new, const char *n) { + bool ret; + if (USE_LOCKLESS_FAST_PATH()) lockdep_assert_irqs_disabled(); -#if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) && \ - defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE) + if (s->flags & __CMPXCHG_DOUBLE) { - if (cmpxchg_double(&slab->freelist, &slab->counters, - freelist_old, counters_old, - freelist_new, counters_new)) - return true; - } else -#endif - { - slab_lock(slab); - if (slab->freelist == freelist_old && - slab->counters == counters_old) { - slab->freelist = freelist_new; - slab->counters = counters_new; - slab_unlock(slab); - return true; - } - slab_unlock(slab); + ret = __update_freelist_fast(slab, freelist_old, counters_old, + freelist_new, counters_new); + } else { + ret = __update_freelist_slow(slab, freelist_old, counters_old, + freelist_new, counters_new); } + if (likely(ret)) + return true; cpu_relax(); stat(s, CMPXCHG_DOUBLE_FAIL); @@ -557,36 +588,26 @@ static inline bool __cmpxchg_double_slab(struct kmem_cache *s, struct slab *slab return false; } -static inline bool cmpxchg_double_slab(struct kmem_cache *s, struct slab *slab, +static inline bool slab_update_freelist(struct kmem_cache *s, struct slab *slab, void *freelist_old, unsigned long counters_old, void *freelist_new, unsigned long counters_new, const char *n) { -#if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) && \ - defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE) + bool ret; + if (s->flags & __CMPXCHG_DOUBLE) { - if (cmpxchg_double(&slab->freelist, &slab->counters, - freelist_old, counters_old, - freelist_new, counters_new)) - return true; - } else -#endif - { + ret = __update_freelist_fast(slab, freelist_old, counters_old, + freelist_new, counters_new); + } else { unsigned long flags; local_irq_save(flags); - slab_lock(slab); - if (slab->freelist == freelist_old && - slab->counters == counters_old) { - slab->freelist = freelist_new; - slab->counters = counters_new; - slab_unlock(slab); - local_irq_restore(flags); - return true; - } - slab_unlock(slab); + ret = __update_freelist_slow(slab, freelist_old, counters_old, + freelist_new, counters_new); local_irq_restore(flags); } + if (likely(ret)) + return true; cpu_relax(); stat(s, CMPXCHG_DOUBLE_FAIL); @@ -2228,7 +2249,7 @@ static inline void *acquire_slab(struct kmem_cache *s, VM_BUG_ON(new.frozen); new.frozen = 1; - if (!__cmpxchg_double_slab(s, slab, + if (!__slab_update_freelist(s, slab, freelist, counters, new.freelist, new.counters, "acquire_slab")) @@ -2554,7 +2575,7 @@ redo: } - if (!cmpxchg_double_slab(s, slab, + if (!slab_update_freelist(s, slab, old.freelist, old.counters, new.freelist, new.counters, "unfreezing slab")) { @@ -2611,7 +2632,7 @@ static void __unfreeze_partials(struct kmem_cache *s, struct slab *partial_slab) new.frozen = 0; - } while (!__cmpxchg_double_slab(s, slab, + } while (!__slab_update_freelist(s, slab, old.freelist, old.counters, new.freelist, new.counters, "unfreezing slab")); @@ -3008,6 +3029,18 @@ static inline bool pfmemalloc_match(struct slab *slab, gfp_t gfpflags) } #ifndef CONFIG_SLUB_TINY +static inline bool +__update_cpu_freelist_fast(struct kmem_cache *s, + void *freelist_old, void *freelist_new, + unsigned long tid) +{ + freelist_aba_t old = { .freelist = freelist_old, .counter = tid }; + freelist_aba_t new = { .freelist = freelist_new, .counter = next_tid(tid) }; + + return this_cpu_try_cmpxchg_freelist(s->cpu_slab->freelist_tid.full, + &old.full, new.full); +} + /* * Check the slab->freelist and either transfer the freelist to the * per cpu freelist or deactivate the slab. @@ -3034,7 +3067,7 @@ static inline void *get_freelist(struct kmem_cache *s, struct slab *slab) new.inuse = slab->objects; new.frozen = freelist != NULL; - } while (!__cmpxchg_double_slab(s, slab, + } while (!__slab_update_freelist(s, slab, freelist, counters, NULL, new.counters, "get_freelist")); @@ -3359,11 +3392,7 @@ redo: * against code executing on this cpu *not* from access by * other cpus. */ - if (unlikely(!this_cpu_cmpxchg_double( - s->cpu_slab->freelist, s->cpu_slab->tid, - object, tid, - next_object, next_tid(tid)))) { - + if (unlikely(!__update_cpu_freelist_fast(s, object, next_object, tid))) { note_cmpxchg_failure("slab_alloc", s, tid); goto redo; } @@ -3631,7 +3660,7 @@ static void __slab_free(struct kmem_cache *s, struct slab *slab, } } - } while (!cmpxchg_double_slab(s, slab, + } while (!slab_update_freelist(s, slab, prior, counters, head, new.counters, "__slab_free")); @@ -3736,11 +3765,7 @@ redo: set_freepointer(s, tail_obj, freelist); - if (unlikely(!this_cpu_cmpxchg_double( - s->cpu_slab->freelist, s->cpu_slab->tid, - freelist, tid, - head, next_tid(tid)))) { - + if (unlikely(!__update_cpu_freelist_fast(s, freelist, head, tid))) { note_cmpxchg_failure("slab_free", s, tid); goto redo; } @@ -4505,11 +4530,11 @@ static int kmem_cache_open(struct kmem_cache *s, slab_flags_t flags) } } -#if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) && \ - defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE) - if (system_has_cmpxchg_double() && (s->flags & SLAB_NO_CMPXCHG) == 0) +#ifdef system_has_freelist_aba + if (system_has_freelist_aba() && !(s->flags & SLAB_NO_CMPXCHG)) { /* Enable fast mode */ s->flags |= __CMPXCHG_DOUBLE; + } #endif /* diff --git a/mm/swapfile.c b/mm/swapfile.c index 92ed7cba2268..8e6dde68b389 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2530,7 +2530,7 @@ 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); @@ -2761,7 +2761,7 @@ 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; @@ -3212,7 +3212,7 @@ 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/vmstat.c b/mm/vmstat.c index c7499e3ee9d5..b731d57996c5 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1181,6 +1181,9 @@ 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 |