They are used by READ_ONLY_THP_FOR_FS to handle writes to FSes without large folio support, so that read-only THPs created in these FSes are not seen by the FSes when the underlying fd becomes writable. Now read-only PMD THPs only appear in a FS with large folio support and the supported orders include PMD_ORDRE.
READ_ONLY_THP_FOR_FS was using mapping->nr_thps, inode->i_writecount, and smp_mb() to prevent writes to a read-only THP and collapsing writable folios into a THP. In collapse_file(), mapping->nr_thps is increased, then smp_mb(), and if inode->i_writecount > 0, collapse is stopped, while do_dentry_open() first increases inode->i_writecount, then a full memory fence, and if mapping->nr_thps > 0, all read-only THPs are truncated. Now this mechanism can be removed along with READ_ONLY_THP_FOR_FS code, since a dirty folio check has been added after try_to_unmap() and try_to_unmap_flush() in collapse_file() to make sure no writable folio can be collapsed. Signed-off-by: Zi Yan <[email protected]> --- fs/open.c | 27 --------------------------- include/linux/pagemap.h | 29 ----------------------------- mm/filemap.c | 1 - mm/huge_memory.c | 1 - mm/khugepaged.c | 28 ---------------------------- 5 files changed, 86 deletions(-) diff --git a/fs/open.c b/fs/open.c index 91f1139591ab..cef382d9d8b8 100644 --- a/fs/open.c +++ b/fs/open.c @@ -970,33 +970,6 @@ static int do_dentry_open(struct file *f, if ((f->f_flags & O_DIRECT) && !(f->f_mode & FMODE_CAN_ODIRECT)) return -EINVAL; - /* - * XXX: Huge page cache doesn't support writing yet. Drop all page - * cache for this file before processing writes. - */ - if (f->f_mode & FMODE_WRITE) { - /* - * Depends on full fence from get_write_access() to synchronize - * against collapse_file() regarding i_writecount and nr_thps - * updates. Ensures subsequent insertion of THPs into the page - * cache will fail. - */ - if (filemap_nr_thps(inode->i_mapping)) { - struct address_space *mapping = inode->i_mapping; - - filemap_invalidate_lock(inode->i_mapping); - /* - * unmap_mapping_range just need to be called once - * here, because the private pages is not need to be - * unmapped mapping (e.g. data segment of dynamic - * shared libraries here). - */ - unmap_mapping_range(mapping, 0, 0, 0); - truncate_inode_pages(mapping, 0); - filemap_invalidate_unlock(inode->i_mapping); - } - } - return 0; cleanup_all: diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index ec442af3f886..dad3f8846cdc 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -530,35 +530,6 @@ static inline size_t mapping_max_folio_size(const struct address_space *mapping) return PAGE_SIZE << mapping_max_folio_order(mapping); } -static inline int filemap_nr_thps(const struct address_space *mapping) -{ -#ifdef CONFIG_READ_ONLY_THP_FOR_FS - return atomic_read(&mapping->nr_thps); -#else - return 0; -#endif -} - -static inline void filemap_nr_thps_inc(struct address_space *mapping) -{ -#ifdef CONFIG_READ_ONLY_THP_FOR_FS - if (!mapping_large_folio_support(mapping)) - atomic_inc(&mapping->nr_thps); -#else - WARN_ON_ONCE(mapping_large_folio_support(mapping) == 0); -#endif -} - -static inline void filemap_nr_thps_dec(struct address_space *mapping) -{ -#ifdef CONFIG_READ_ONLY_THP_FOR_FS - if (!mapping_large_folio_support(mapping)) - atomic_dec(&mapping->nr_thps); -#else - WARN_ON_ONCE(mapping_large_folio_support(mapping) == 0); -#endif -} - struct address_space *folio_mapping(const struct folio *folio); /** diff --git a/mm/filemap.c b/mm/filemap.c index c568d9058ff8..e7da925ae310 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -189,7 +189,6 @@ static void filemap_unaccount_folio(struct address_space *mapping, lruvec_stat_mod_folio(folio, NR_SHMEM_THPS, -nr); } else if (folio_test_pmd_mappable(folio)) { lruvec_stat_mod_folio(folio, NR_FILE_THPS, -nr); - filemap_nr_thps_dec(mapping); } if (test_bit(AS_KERNEL_FILE, &folio->mapping->flags)) mod_node_page_state(folio_pgdat(folio), diff --git a/mm/huge_memory.c b/mm/huge_memory.c index a22bb2364bdc..5c9ee900ed90 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -3926,7 +3926,6 @@ static int __folio_freeze_and_split_unmapped(struct folio *folio, unsigned int n } else { lruvec_stat_mod_folio(folio, NR_FILE_THPS, -nr); - filemap_nr_thps_dec(mapping); } } } diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 79c985d7fa03..afd52e4c7ccd 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -2092,21 +2092,6 @@ static enum scan_result collapse_file(struct mm_struct *mm, unsigned long addr, goto xa_unlocked; } - if (!is_shmem) { - filemap_nr_thps_inc(mapping); - /* - * Paired with the fence in do_dentry_open() -> get_write_access() - * to ensure i_writecount is up to date and the update to nr_thps - * is visible. Ensures the page cache will be truncated if the - * file is opened writable. - */ - smp_mb(); - if (inode_is_open_for_write(mapping->host)) { - result = SCAN_FAIL; - filemap_nr_thps_dec(mapping); - } - } - xa_locked: xas_unlock_irq(&xas); xa_unlocked: @@ -2302,19 +2287,6 @@ static enum scan_result collapse_file(struct mm_struct *mm, unsigned long addr, folio_putback_lru(folio); folio_put(folio); } - /* - * Undo the updates of filemap_nr_thps_inc for non-SHMEM - * file only. This undo is not needed unless failure is - * due to SCAN_COPY_MC. - */ - if (!is_shmem && result == SCAN_COPY_MC) { - filemap_nr_thps_dec(mapping); - /* - * Paired with the fence in do_dentry_open() -> get_write_access() - * to ensure the update to nr_thps is visible. - */ - smp_mb(); - } new_folio->mapping = NULL; -- 2.43.0
