diff options
Diffstat (limited to 'fs/f2fs/file.c')
| -rw-r--r-- | fs/f2fs/file.c | 4469 |
1 files changed, 3706 insertions, 763 deletions
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 2706130c261b..d7047ca6b98d 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -1,17 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/file.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> #include <linux/f2fs_fs.h> #include <linux/stat.h> -#include <linux/buffer_head.h> #include <linux/writeback.h> #include <linux/blkdev.h> #include <linux/falloc.h> @@ -23,6 +19,11 @@ #include <linux/uio.h> #include <linux/uuid.h> #include <linux/file.h> +#include <linux/nls.h> +#include <linux/sched/signal.h> +#include <linux/fileattr.h> +#include <linux/fadvise.h> +#include <linux/iomap.h> #include "f2fs.h" #include "node.h" @@ -30,89 +31,161 @@ #include "xattr.h" #include "acl.h" #include "gc.h" -#include "trace.h" +#include "iostat.h" #include <trace/events/f2fs.h> +#include <uapi/linux/f2fs.h> -static int f2fs_filemap_fault(struct vm_fault *vmf) +static void f2fs_zero_post_eof_page(struct inode *inode, + loff_t new_size, bool lock) +{ + loff_t old_size = i_size_read(inode); + + if (old_size >= new_size) + return; + + if (mapping_empty(inode->i_mapping)) + return; + + if (lock) + filemap_invalidate_lock(inode->i_mapping); + /* zero or drop pages only in range of [old_size, new_size] */ + truncate_inode_pages_range(inode->i_mapping, old_size, new_size); + if (lock) + filemap_invalidate_unlock(inode->i_mapping); +} + +static vm_fault_t f2fs_filemap_fault(struct vm_fault *vmf) { struct inode *inode = file_inode(vmf->vma->vm_file); - int err; + vm_flags_t flags = vmf->vma->vm_flags; + vm_fault_t ret; - down_read(&F2FS_I(inode)->i_mmap_sem); - err = filemap_fault(vmf); - up_read(&F2FS_I(inode)->i_mmap_sem); + ret = filemap_fault(vmf); + if (ret & VM_FAULT_LOCKED) + f2fs_update_iostat(F2FS_I_SB(inode), inode, + APP_MAPPED_READ_IO, F2FS_BLKSIZE); - return err; + trace_f2fs_filemap_fault(inode, vmf->pgoff, flags, ret); + + return ret; } -static int f2fs_vm_page_mkwrite(struct vm_fault *vmf) +static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf) { - struct page *page = vmf->page; + struct folio *folio = page_folio(vmf->page); struct inode *inode = file_inode(vmf->vma->vm_file); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct dnode_of_data dn; - int err; + bool need_alloc = !f2fs_is_pinned_file(inode); + int err = 0; + vm_fault_t ret; - sb_start_pagefault(inode->i_sb); + if (unlikely(IS_IMMUTABLE(inode))) + return VM_FAULT_SIGBUS; - f2fs_bug_on(sbi, f2fs_has_inline_data(inode)); + if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) { + err = -EIO; + goto out; + } - /* block allocation */ - f2fs_lock_op(sbi); - set_new_dnode(&dn, inode, NULL, NULL, 0); - err = f2fs_reserve_block(&dn, page->index); - if (err) { - f2fs_unlock_op(sbi); + if (unlikely(f2fs_cp_error(sbi))) { + err = -EIO; goto out; } - f2fs_put_dnode(&dn); - f2fs_unlock_op(sbi); - f2fs_balance_fs(sbi, dn.node_changed); + if (!f2fs_is_checkpoint_ready(sbi)) { + err = -ENOSPC; + goto out; + } + + err = f2fs_convert_inline_inode(inode); + if (err) + goto out; + +#ifdef CONFIG_F2FS_FS_COMPRESSION + if (f2fs_compressed_file(inode)) { + int ret = f2fs_is_compressed_cluster(inode, folio->index); + + if (ret < 0) { + err = ret; + goto out; + } else if (ret) { + need_alloc = false; + } + } +#endif + /* should do out of any locked page */ + if (need_alloc) + f2fs_balance_fs(sbi, true); + + sb_start_pagefault(inode->i_sb); + + f2fs_bug_on(sbi, f2fs_has_inline_data(inode)); + + f2fs_zero_post_eof_page(inode, (folio->index + 1) << PAGE_SHIFT, true); file_update_time(vmf->vma->vm_file); - down_read(&F2FS_I(inode)->i_mmap_sem); - lock_page(page); - if (unlikely(page->mapping != inode->i_mapping || - page_offset(page) > i_size_read(inode) || - !PageUptodate(page))) { - unlock_page(page); + filemap_invalidate_lock_shared(inode->i_mapping); + + folio_lock(folio); + if (unlikely(folio->mapping != inode->i_mapping || + folio_pos(folio) > i_size_read(inode) || + !folio_test_uptodate(folio))) { + folio_unlock(folio); err = -EFAULT; goto out_sem; } + set_new_dnode(&dn, inode, NULL, NULL, 0); + if (need_alloc) { + /* block allocation */ + err = f2fs_get_block_locked(&dn, folio->index); + } else { + err = f2fs_get_dnode_of_data(&dn, folio->index, LOOKUP_NODE); + f2fs_put_dnode(&dn); + if (f2fs_is_pinned_file(inode) && + !__is_valid_data_blkaddr(dn.data_blkaddr)) + err = -EIO; + } + + if (err) { + folio_unlock(folio); + goto out_sem; + } + + f2fs_folio_wait_writeback(folio, DATA, false, true); + + /* wait for GCed page writeback via META_MAPPING */ + f2fs_wait_on_block_writeback(inode, dn.data_blkaddr); + /* * check to see if the page is mapped already (no holes) */ - if (PageMappedToDisk(page)) - goto mapped; + if (folio_test_mappedtodisk(folio)) + goto out_sem; /* page is wholly or partially inside EOF */ - if (((loff_t)(page->index + 1) << PAGE_SHIFT) > + if (((loff_t)(folio->index + 1) << PAGE_SHIFT) > i_size_read(inode)) { - unsigned offset; + loff_t offset; + offset = i_size_read(inode) & ~PAGE_MASK; - zero_user_segment(page, offset, PAGE_SIZE); + folio_zero_segment(folio, offset, folio_size(folio)); } - set_page_dirty(page); - if (!PageUptodate(page)) - SetPageUptodate(page); + folio_mark_dirty(folio); - trace_f2fs_vm_page_mkwrite(page, DATA); -mapped: - /* fill the page */ - f2fs_wait_on_page_writeback(page, DATA, false); - - /* wait for GCed encrypted page writeback */ - if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) - f2fs_wait_on_encrypted_page_writeback(sbi, dn.data_blkaddr); + f2fs_update_iostat(sbi, inode, APP_MAPPED_IO, F2FS_BLKSIZE); + f2fs_update_time(sbi, REQ_TIME); out_sem: - up_read(&F2FS_I(inode)->i_mmap_sem); -out: + filemap_invalidate_unlock_shared(inode->i_mapping); + sb_end_pagefault(inode->i_sb); - f2fs_update_time(sbi, REQ_TIME); - return block_page_mkwrite_return(err); +out: + ret = vmf_fs_error(err); + + trace_f2fs_vm_page_mkwrite(inode, folio->index, vmf->vma->vm_flags, ret); + return ret; } static const struct vm_operations_struct f2fs_file_vm_ops = { @@ -125,48 +198,63 @@ static int get_parent_ino(struct inode *inode, nid_t *pino) { struct dentry *dentry; - inode = igrab(inode); - dentry = d_find_any_alias(inode); - iput(inode); + /* + * Make sure to get the non-deleted alias. The alias associated with + * the open file descriptor being fsync()'ed may be deleted already. + */ + dentry = d_find_alias(inode); if (!dentry) return 0; - *pino = parent_ino(dentry); + *pino = d_parent_ino(dentry); dput(dentry); return 1; } -static inline bool need_do_checkpoint(struct inode *inode) +static inline enum cp_reason_type need_do_checkpoint(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - bool need_cp = false; + enum cp_reason_type cp_reason = CP_NO_NEEDED; - if (!S_ISREG(inode->i_mode) || inode->i_nlink != 1) - need_cp = true; + if (!S_ISREG(inode->i_mode)) + cp_reason = CP_NON_REGULAR; + else if (f2fs_compressed_file(inode)) + cp_reason = CP_COMPRESSED; + else if (inode->i_nlink != 1) + cp_reason = CP_HARDLINK; else if (is_sbi_flag_set(sbi, SBI_NEED_CP)) - need_cp = true; + cp_reason = CP_SB_NEED_CP; else if (file_wrong_pino(inode)) - need_cp = true; - else if (!space_for_roll_forward(sbi)) - need_cp = true; - else if (!is_checkpointed_node(sbi, F2FS_I(inode)->i_pino)) - need_cp = true; + cp_reason = CP_WRONG_PINO; + else if (!f2fs_space_for_roll_forward(sbi)) + cp_reason = CP_NO_SPC_ROLL; + else if (!f2fs_is_checkpointed_node(sbi, F2FS_I(inode)->i_pino)) + cp_reason = CP_NODE_NEED_CP; else if (test_opt(sbi, FASTBOOT)) - need_cp = true; - else if (sbi->active_logs == 2) - need_cp = true; - - return need_cp; + cp_reason = CP_FASTBOOT_MODE; + else if (F2FS_OPTION(sbi).active_logs == 2) + cp_reason = CP_SPEC_LOG_NUM; + else if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT && + f2fs_need_dentry_mark(sbi, inode->i_ino) && + f2fs_exist_written_data(sbi, F2FS_I(inode)->i_pino, + TRANS_DIR_INO)) + cp_reason = CP_RECOVER_DIR; + else if (f2fs_exist_written_data(sbi, F2FS_I(inode)->i_pino, + XATTR_DIR_INO)) + cp_reason = CP_XATTR_DIR; + + return cp_reason; } static bool need_inode_page_update(struct f2fs_sb_info *sbi, nid_t ino) { - struct page *i = find_get_page(NODE_MAPPING(sbi), ino); + struct folio *i = filemap_get_folio(NODE_MAPPING(sbi), ino); bool ret = false; /* But we need to avoid that there are some inode updates */ - if ((i && PageDirty(i)) || need_inode_block_update(sbi, ino)) + if ((!IS_ERR(i) && folio_test_dirty(i)) || + f2fs_need_inode_block_update(sbi, ino)) ret = true; - f2fs_put_page(i, 0); + f2fs_folio_put(i, false); return ret; } @@ -175,13 +263,13 @@ static void try_to_fix_pino(struct inode *inode) struct f2fs_inode_info *fi = F2FS_I(inode); nid_t pino; - down_write(&fi->i_sem); + f2fs_down_write(&fi->i_sem); if (file_wrong_pino(inode) && inode->i_nlink == 1 && get_parent_ino(inode, &pino)) { f2fs_i_pino_write(inode, pino); file_got_pino(inode); } - up_write(&fi->i_sem); + f2fs_up_write(&fi->i_sem); } static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end, @@ -191,26 +279,29 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end, struct f2fs_sb_info *sbi = F2FS_I_SB(inode); nid_t ino = inode->i_ino; int ret = 0; - bool need_cp = false; + enum cp_reason_type cp_reason = 0; struct writeback_control wbc = { .sync_mode = WB_SYNC_ALL, .nr_to_write = LONG_MAX, - .for_reclaim = 0, }; + unsigned int seq_id = 0; if (unlikely(f2fs_readonly(inode->i_sb))) return 0; trace_f2fs_sync_file_enter(inode); + if (S_ISDIR(inode->i_mode)) + goto go_write; + /* if fdatasync is triggered, let's do in-place-update */ if (datasync || get_dirty_pages(inode) <= SM_I(sbi)->min_fsync_blocks) set_inode_flag(inode, FI_NEED_IPU); - ret = filemap_write_and_wait_range(inode->i_mapping, start, end); + ret = file_write_and_wait_range(file, start, end); clear_inode_flag(inode, FI_NEED_IPU); - if (ret) { - trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret); + if (ret || is_sbi_flag_set(sbi, SBI_CP_DISABLED)) { + trace_f2fs_sync_file_exit(inode, cp_reason, datasync, ret); return ret; } @@ -224,27 +315,39 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end, * if there is no written data, don't waste time to write recovery info. */ if (!is_inode_flag_set(inode, FI_APPEND_WRITE) && - !exist_written_data(sbi, ino, APPEND_INO)) { + !f2fs_exist_written_data(sbi, ino, APPEND_INO)) { /* it may call write_inode just prior to fsync */ if (need_inode_page_update(sbi, ino)) goto go_write; if (is_inode_flag_set(inode, FI_UPDATE_WRITE) || - exist_written_data(sbi, ino, UPDATE_INO)) + f2fs_exist_written_data(sbi, ino, UPDATE_INO)) goto flush_out; goto out; + } else { + /* + * for OPU case, during fsync(), node can be persisted before + * data when lower device doesn't support write barrier, result + * in data corruption after SPO. + * So for strict fsync mode, force to use atomic write semantics + * to keep write order in between data/node and last node to + * avoid potential data corruption. + */ + if (F2FS_OPTION(sbi).fsync_mode == + FSYNC_MODE_STRICT && !atomic) + atomic = true; } go_write: /* * Both of fdatasync() and fsync() are able to be recovered from * sudden-power-off. */ - down_read(&F2FS_I(inode)->i_sem); - need_cp = need_do_checkpoint(inode); - up_read(&F2FS_I(inode)->i_sem); + f2fs_down_read(&F2FS_I(inode)->i_sem); + cp_reason = need_do_checkpoint(inode); + f2fs_up_read(&F2FS_I(inode)->i_sem); - if (need_cp) { + if (cp_reason) { /* all the dirty node pages should be flushed for POR */ ret = f2fs_sync_fs(inode->i_sb, 1); @@ -258,7 +361,9 @@ go_write: goto out; } sync_nodes: - ret = fsync_node_pages(sbi, inode, &wbc, atomic); + atomic_inc(&sbi->wb_sync_req[NODE]); + ret = f2fs_fsync_node_pages(sbi, inode, &wbc, atomic, &seq_id); + atomic_dec(&sbi->wb_sync_req[NODE]); if (ret) goto out; @@ -268,64 +373,77 @@ sync_nodes: goto out; } - if (need_inode_block_update(sbi, ino)) { + if (f2fs_need_inode_block_update(sbi, ino)) { f2fs_mark_inode_dirty_sync(inode, true); f2fs_write_inode(inode, NULL); goto sync_nodes; } - ret = wait_on_node_pages_writeback(sbi, ino); - if (ret) - goto out; + /* + * If it's atomic_write, it's just fine to keep write ordering. So + * here we don't need to wait for node write completion, since we use + * node chain which serializes node blocks. If one of node writes are + * reordered, we can see simply broken chain, resulting in stopping + * roll-forward recovery. It means we'll recover all or none node blocks + * given fsync mark. + */ + if (!atomic) { + ret = f2fs_wait_on_node_pages_writeback(sbi, seq_id); + if (ret) + goto out; + } /* once recovery info is written, don't need to tack this */ - remove_ino_entry(sbi, ino, APPEND_INO); + f2fs_remove_ino_entry(sbi, ino, APPEND_INO); clear_inode_flag(inode, FI_APPEND_WRITE); flush_out: - remove_ino_entry(sbi, ino, UPDATE_INO); - clear_inode_flag(inode, FI_UPDATE_WRITE); - if (!atomic) - ret = f2fs_issue_flush(sbi); + if (!atomic && F2FS_OPTION(sbi).fsync_mode != FSYNC_MODE_NOBARRIER) + ret = f2fs_issue_flush(sbi, inode->i_ino); + if (!ret) { + f2fs_remove_ino_entry(sbi, ino, UPDATE_INO); + clear_inode_flag(inode, FI_UPDATE_WRITE); + f2fs_remove_ino_entry(sbi, ino, FLUSH_INO); + } f2fs_update_time(sbi, REQ_TIME); out: - trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret); - f2fs_trace_ios(NULL, 1); + trace_f2fs_sync_file_exit(inode, cp_reason, datasync, ret); return ret; } int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) { + if (unlikely(f2fs_cp_error(F2FS_I_SB(file_inode(file))))) + return -EIO; return f2fs_do_sync_file(file, start, end, datasync, false); } -static pgoff_t __get_first_dirty_index(struct address_space *mapping, - pgoff_t pgofs, int whence) +static bool __found_offset(struct address_space *mapping, + struct dnode_of_data *dn, pgoff_t index, int whence) { - struct pagevec pvec; - int nr_pages; + block_t blkaddr = f2fs_data_blkaddr(dn); + struct inode *inode = mapping->host; + bool compressed_cluster = false; - if (whence != SEEK_DATA) - return 0; + if (f2fs_compressed_file(inode)) { + block_t first_blkaddr = data_blkaddr(dn->inode, dn->node_folio, + ALIGN_DOWN(dn->ofs_in_node, F2FS_I(inode)->i_cluster_size)); - /* find first dirty page index */ - pagevec_init(&pvec, 0); - nr_pages = pagevec_lookup_tag(&pvec, mapping, &pgofs, - PAGECACHE_TAG_DIRTY, 1); - pgofs = nr_pages ? pvec.pages[0]->index : ULONG_MAX; - pagevec_release(&pvec); - return pgofs; -} + compressed_cluster = first_blkaddr == COMPRESS_ADDR; + } -static bool __found_offset(block_t blkaddr, pgoff_t dirty, pgoff_t pgofs, - int whence) -{ switch (whence) { case SEEK_DATA: - if ((blkaddr == NEW_ADDR && dirty == pgofs) || - (blkaddr != NEW_ADDR && blkaddr != NULL_ADDR)) + if (__is_valid_data_blkaddr(blkaddr)) + return true; + if (blkaddr == NEW_ADDR && + xa_get_mark(&mapping->i_pages, index, PAGECACHE_TAG_DIRTY)) + return true; + if (compressed_cluster) return true; break; case SEEK_HOLE: + if (compressed_cluster) + return false; if (blkaddr == NULL_ADDR) return true; break; @@ -336,55 +454,66 @@ static bool __found_offset(block_t blkaddr, pgoff_t dirty, pgoff_t pgofs, static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence) { struct inode *inode = file->f_mapping->host; - loff_t maxbytes = inode->i_sb->s_maxbytes; + loff_t maxbytes = F2FS_BLK_TO_BYTES(max_file_blocks(inode)); struct dnode_of_data dn; - pgoff_t pgofs, end_offset, dirty; + pgoff_t pgofs, end_offset; loff_t data_ofs = offset; loff_t isize; int err = 0; - inode_lock(inode); + inode_lock_shared(inode); isize = i_size_read(inode); if (offset >= isize) goto fail; /* handle inline data case */ - if (f2fs_has_inline_data(inode) || f2fs_has_inline_dentry(inode)) { - if (whence == SEEK_HOLE) + if (f2fs_has_inline_data(inode)) { + if (whence == SEEK_HOLE) { data_ofs = isize; - goto found; + goto found; + } else if (whence == SEEK_DATA) { + data_ofs = offset; + goto found; + } } pgofs = (pgoff_t)(offset >> PAGE_SHIFT); - dirty = __get_first_dirty_index(inode->i_mapping, pgofs, whence); - for (; data_ofs < isize; data_ofs = (loff_t)pgofs << PAGE_SHIFT) { set_new_dnode(&dn, inode, NULL, NULL, 0); - err = get_dnode_of_data(&dn, pgofs, LOOKUP_NODE); + err = f2fs_get_dnode_of_data(&dn, pgofs, LOOKUP_NODE); if (err && err != -ENOENT) { goto fail; } else if (err == -ENOENT) { /* direct node does not exists */ if (whence == SEEK_DATA) { - pgofs = get_next_page_offset(&dn, pgofs); + pgofs = f2fs_get_next_page_offset(&dn, pgofs); continue; } else { goto found; } } - end_offset = ADDRS_PER_PAGE(dn.node_page, inode); + end_offset = ADDRS_PER_PAGE(dn.node_folio, inode); /* find data/hole in dnode block */ for (; dn.ofs_in_node < end_offset; dn.ofs_in_node++, pgofs++, data_ofs = (loff_t)pgofs << PAGE_SHIFT) { block_t blkaddr; - blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node); - if (__found_offset(blkaddr, dirty, pgofs, whence)) { + blkaddr = f2fs_data_blkaddr(&dn); + + if (__is_valid_data_blkaddr(blkaddr) && + !f2fs_is_valid_blkaddr(F2FS_I_SB(inode), + blkaddr, DATA_GENERIC_ENHANCE)) { + f2fs_put_dnode(&dn); + goto fail; + } + + if (__found_offset(file->f_mapping, &dn, + pgofs, whence)) { f2fs_put_dnode(&dn); goto found; } @@ -397,17 +526,17 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence) found: if (whence == SEEK_HOLE && data_ofs > isize) data_ofs = isize; - inode_unlock(inode); + inode_unlock_shared(inode); return vfs_setpos(file, data_ofs, maxbytes); fail: - inode_unlock(inode); + inode_unlock_shared(inode); return -ENXIO; } static loff_t f2fs_llseek(struct file *file, loff_t offset, int whence) { struct inode *inode = file->f_mapping->host; - loff_t maxbytes = inode->i_sb->s_maxbytes; + loff_t maxbytes = F2FS_BLK_TO_BYTES(max_file_blocks(inode)); switch (whence) { case SEEK_SET: @@ -425,74 +554,173 @@ static loff_t f2fs_llseek(struct file *file, loff_t offset, int whence) return -EINVAL; } -static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma) +static int f2fs_file_mmap_prepare(struct vm_area_desc *desc) { + struct file *file = desc->file; struct inode *inode = file_inode(file); - int err; - /* we don't need to use inline_data strictly */ - err = f2fs_convert_inline_inode(inode); - if (err) - return err; + if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) + return -EIO; + + if (!f2fs_is_compress_backend_ready(inode)) + return -EOPNOTSUPP; file_accessed(file); - vma->vm_ops = &f2fs_file_vm_ops; + desc->vm_ops = &f2fs_file_vm_ops; + + f2fs_down_read(&F2FS_I(inode)->i_sem); + set_inode_flag(inode, FI_MMAP_FILE); + f2fs_up_read(&F2FS_I(inode)->i_sem); + return 0; } +static int finish_preallocate_blocks(struct inode *inode) +{ + int ret = 0; + bool opened; + + f2fs_down_read(&F2FS_I(inode)->i_sem); + opened = is_inode_flag_set(inode, FI_OPENED_FILE); + f2fs_up_read(&F2FS_I(inode)->i_sem); + if (opened) + return 0; + + inode_lock(inode); + if (is_inode_flag_set(inode, FI_OPENED_FILE)) + goto out_unlock; + + if (!file_should_truncate(inode)) + goto out_update; + + f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + filemap_invalidate_lock(inode->i_mapping); + + truncate_setsize(inode, i_size_read(inode)); + ret = f2fs_truncate(inode); + + filemap_invalidate_unlock(inode->i_mapping); + f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + if (ret) + goto out_unlock; + + file_dont_truncate(inode); +out_update: + f2fs_down_write(&F2FS_I(inode)->i_sem); + set_inode_flag(inode, FI_OPENED_FILE); + f2fs_up_write(&F2FS_I(inode)->i_sem); +out_unlock: + inode_unlock(inode); + return ret; +} + static int f2fs_file_open(struct inode *inode, struct file *filp) { - struct dentry *dir; + int err = fscrypt_file_open(inode, filp); - if (f2fs_encrypted_inode(inode)) { - int ret = fscrypt_get_encryption_info(inode); - if (ret) - return -EACCES; - if (!fscrypt_has_encryption_key(inode)) - return -ENOKEY; - } - dir = dget_parent(file_dentry(filp)); - if (f2fs_encrypted_inode(d_inode(dir)) && - !fscrypt_has_permitted_context(d_inode(dir), inode)) { - dput(dir); - return -EPERM; - } - dput(dir); - return dquot_file_open(inode, filp); + if (err) + return err; + + if (!f2fs_is_compress_backend_ready(inode)) + return -EOPNOTSUPP; + + err = fsverity_file_open(inode, filp); + if (err) + return err; + + filp->f_mode |= FMODE_NOWAIT; + filp->f_mode |= FMODE_CAN_ODIRECT; + + err = dquot_file_open(inode, filp); + if (err) + return err; + + err = finish_preallocate_blocks(inode); + if (!err) + atomic_inc(&F2FS_I(inode)->open_count); + return err; } -int truncate_data_blocks_range(struct dnode_of_data *dn, int count) +void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count) { struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); - struct f2fs_node *raw_node; int nr_free = 0, ofs = dn->ofs_in_node, len = count; __le32 *addr; + bool compressed_cluster = false; + int cluster_index = 0, valid_blocks = 0; + int cluster_size = F2FS_I(dn->inode)->i_cluster_size; + bool released = !atomic_read(&F2FS_I(dn->inode)->i_compr_blocks); + block_t blkstart; + int blklen = 0; + + addr = get_dnode_addr(dn->inode, dn->node_folio) + ofs; + blkstart = le32_to_cpu(*addr); + + /* Assumption: truncation starts with cluster */ + for (; count > 0; count--, addr++, dn->ofs_in_node++, cluster_index++) { + block_t blkaddr = le32_to_cpu(*addr); - raw_node = F2FS_NODE(dn->node_page); - addr = blkaddr_in_node(raw_node) + ofs; + if (f2fs_compressed_file(dn->inode) && + !(cluster_index & (cluster_size - 1))) { + if (compressed_cluster) + f2fs_i_compr_blocks_update(dn->inode, + valid_blocks, false); + compressed_cluster = (blkaddr == COMPRESS_ADDR); + valid_blocks = 0; + } - for (; count > 0; count--, addr++, dn->ofs_in_node++) { - block_t blkaddr = le32_to_cpu(*addr); if (blkaddr == NULL_ADDR) - continue; + goto next; + + f2fs_set_data_blkaddr(dn, NULL_ADDR); + + if (__is_valid_data_blkaddr(blkaddr)) { + if (time_to_inject(sbi, FAULT_BLKADDR_CONSISTENCE)) + goto next; + if (!f2fs_is_valid_blkaddr_raw(sbi, blkaddr, + DATA_GENERIC_ENHANCE)) + goto next; + if (compressed_cluster) + valid_blocks++; + } + + if (blkstart + blklen == blkaddr) { + blklen++; + } else { + f2fs_invalidate_blocks(sbi, blkstart, blklen); + blkstart = blkaddr; + blklen = 1; + } - dn->data_blkaddr = NULL_ADDR; - set_data_blkaddr(dn); - invalidate_blocks(sbi, blkaddr); - if (dn->ofs_in_node == 0 && IS_INODE(dn->node_page)) - clear_inode_flag(dn->inode, FI_FIRST_BLOCK_WRITTEN); - nr_free++; + if (!released || blkaddr != COMPRESS_ADDR) + nr_free++; + + continue; + +next: + if (blklen) + f2fs_invalidate_blocks(sbi, blkstart, blklen); + + blkstart = le32_to_cpu(*(addr + 1)); + blklen = 0; } + if (blklen) + f2fs_invalidate_blocks(sbi, blkstart, blklen); + + if (compressed_cluster) + f2fs_i_compr_blocks_update(dn->inode, valid_blocks, false); + if (nr_free) { pgoff_t fofs; /* * once we invalidate valid blkaddr in range [ofs, ofs + count], * we will invalidate all blkaddr in the whole range. */ - fofs = start_bidx_of_node(ofs_of_node(dn->node_page), + fofs = f2fs_start_bidx_of_node(ofs_of_node(dn->node_folio), dn->inode) + ofs; - f2fs_update_extent_cache_range(dn, fofs, 0, len); + f2fs_update_read_extent_cache_range(dn, fofs, 0, len); + f2fs_update_age_extent_cache_range(dn, fofs, len); dec_valid_block_count(sbi, dn->inode, nr_free); } dn->ofs_in_node = ofs; @@ -500,102 +728,115 @@ int truncate_data_blocks_range(struct dnode_of_data *dn, int count) f2fs_update_time(sbi, REQ_TIME); trace_f2fs_truncate_data_blocks_range(dn->inode, dn->nid, dn->ofs_in_node, nr_free); - return nr_free; -} - -void truncate_data_blocks(struct dnode_of_data *dn) -{ - truncate_data_blocks_range(dn, ADDRS_PER_BLOCK); } static int truncate_partial_data_page(struct inode *inode, u64 from, bool cache_only) { - unsigned offset = from & (PAGE_SIZE - 1); + loff_t offset = from & (PAGE_SIZE - 1); pgoff_t index = from >> PAGE_SHIFT; struct address_space *mapping = inode->i_mapping; - struct page *page; + struct folio *folio; if (!offset && !cache_only) return 0; if (cache_only) { - page = find_lock_page(mapping, index); - if (page && PageUptodate(page)) + folio = filemap_lock_folio(mapping, index); + if (IS_ERR(folio)) + return 0; + if (folio_test_uptodate(folio)) goto truncate_out; - f2fs_put_page(page, 1); + f2fs_folio_put(folio, true); return 0; } - page = get_lock_data_page(inode, index, true); - if (IS_ERR(page)) - return PTR_ERR(page) == -ENOENT ? 0 : PTR_ERR(page); + folio = f2fs_get_lock_data_folio(inode, index, true); + if (IS_ERR(folio)) + return PTR_ERR(folio) == -ENOENT ? 0 : PTR_ERR(folio); truncate_out: - f2fs_wait_on_page_writeback(page, DATA, true); - zero_user(page, offset, PAGE_SIZE - offset); + f2fs_folio_wait_writeback(folio, DATA, true, true); + folio_zero_segment(folio, offset, folio_size(folio)); /* An encrypted inode should have a key and truncate the last page. */ - f2fs_bug_on(F2FS_I_SB(inode), cache_only && f2fs_encrypted_inode(inode)); + f2fs_bug_on(F2FS_I_SB(inode), cache_only && IS_ENCRYPTED(inode)); if (!cache_only) - set_page_dirty(page); - f2fs_put_page(page, 1); + folio_mark_dirty(folio); + f2fs_folio_put(folio, true); return 0; } -int truncate_blocks(struct inode *inode, u64 from, bool lock) +int f2fs_do_truncate_blocks(struct inode *inode, u64 from, bool lock) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - unsigned int blocksize = inode->i_sb->s_blocksize; struct dnode_of_data dn; pgoff_t free_from; int count = 0, err = 0; - struct page *ipage; + struct folio *ifolio; bool truncate_page = false; trace_f2fs_truncate_blocks_enter(inode, from); - free_from = (pgoff_t)F2FS_BYTES_TO_BLK(from + blocksize - 1); + if (IS_DEVICE_ALIASING(inode) && from) { + err = -EINVAL; + goto out_err; + } + + free_from = (pgoff_t)F2FS_BLK_ALIGN(from); - if (free_from >= sbi->max_file_blocks) + if (free_from >= max_file_blocks(inode)) goto free_partial; if (lock) f2fs_lock_op(sbi); - ipage = get_node_page(sbi, inode->i_ino); - if (IS_ERR(ipage)) { - err = PTR_ERR(ipage); + ifolio = f2fs_get_inode_folio(sbi, inode->i_ino); + if (IS_ERR(ifolio)) { + err = PTR_ERR(ifolio); + goto out; + } + + if (IS_DEVICE_ALIASING(inode)) { + struct extent_tree *et = F2FS_I(inode)->extent_tree[EX_READ]; + struct extent_info ei = et->largest; + + f2fs_invalidate_blocks(sbi, ei.blk, ei.len); + + dec_valid_block_count(sbi, inode, ei.len); + f2fs_update_time(sbi, REQ_TIME); + + f2fs_folio_put(ifolio, true); goto out; } if (f2fs_has_inline_data(inode)) { - truncate_inline_inode(inode, ipage, from); - f2fs_put_page(ipage, 1); + f2fs_truncate_inline_inode(inode, ifolio, from); + f2fs_folio_put(ifolio, true); truncate_page = true; goto out; } - set_new_dnode(&dn, inode, ipage, NULL, 0); - err = get_dnode_of_data(&dn, free_from, LOOKUP_NODE_RA); + set_new_dnode(&dn, inode, ifolio, NULL, 0); + err = f2fs_get_dnode_of_data(&dn, free_from, LOOKUP_NODE_RA); if (err) { if (err == -ENOENT) goto free_next; goto out; } - count = ADDRS_PER_PAGE(dn.node_page, inode); + count = ADDRS_PER_PAGE(dn.node_folio, inode); count -= dn.ofs_in_node; f2fs_bug_on(sbi, count < 0); - if (dn.ofs_in_node || IS_INODE(dn.node_page)) { - truncate_data_blocks_range(&dn, count); + if (dn.ofs_in_node || IS_INODE(dn.node_folio)) { + f2fs_truncate_data_blocks_range(&dn, count); free_from += count; } f2fs_put_dnode(&dn); free_next: - err = truncate_inode_blocks(inode, free_from); + err = f2fs_truncate_inode_blocks(inode, free_from); out: if (lock) f2fs_unlock_op(sbi); @@ -603,94 +844,209 @@ free_partial: /* lastly zero out the first data page */ if (!err) err = truncate_partial_data_page(inode, from, truncate_page); - +out_err: trace_f2fs_truncate_blocks_exit(inode, err); return err; } +int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock) +{ + u64 free_from = from; + int err; + +#ifdef CONFIG_F2FS_FS_COMPRESSION + /* + * for compressed file, only support cluster size + * aligned truncation. + */ + if (f2fs_compressed_file(inode)) + free_from = round_up(from, + F2FS_I(inode)->i_cluster_size << PAGE_SHIFT); +#endif + + err = f2fs_do_truncate_blocks(inode, free_from, lock); + if (err) + return err; + +#ifdef CONFIG_F2FS_FS_COMPRESSION + /* + * For compressed file, after release compress blocks, don't allow write + * direct, but we should allow write direct after truncate to zero. + */ + if (f2fs_compressed_file(inode) && !free_from + && is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) + clear_inode_flag(inode, FI_COMPRESS_RELEASED); + + if (from != free_from) { + err = f2fs_truncate_partial_cluster(inode, from, lock); + if (err) + return err; + } +#endif + + return 0; +} + int f2fs_truncate(struct inode *inode) { int err; + if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) + return -EIO; + if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))) return 0; trace_f2fs_truncate(inode); -#ifdef CONFIG_F2FS_FAULT_INJECTION - if (time_to_inject(F2FS_I_SB(inode), FAULT_TRUNCATE)) { - f2fs_show_injection_info(FAULT_TRUNCATE); + if (time_to_inject(F2FS_I_SB(inode), FAULT_TRUNCATE)) return -EIO; - } -#endif + + err = f2fs_dquot_initialize(inode); + if (err) + return err; + /* we should check inline_data size */ if (!f2fs_may_inline_data(inode)) { err = f2fs_convert_inline_inode(inode); - if (err) + if (err) { + /* + * Always truncate page #0 to avoid page cache + * leak in evict() path. + */ + truncate_inode_pages_range(inode->i_mapping, + F2FS_BLK_TO_BYTES(0), + F2FS_BLK_END_BYTES(0)); return err; + } } - err = truncate_blocks(inode, i_size_read(inode), true); + err = f2fs_truncate_blocks(inode, i_size_read(inode), true); if (err) return err; - inode->i_mtime = inode->i_ctime = current_time(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); f2fs_mark_inode_dirty_sync(inode, false); return 0; } -int f2fs_getattr(const struct path *path, struct kstat *stat, - u32 request_mask, unsigned int query_flags) +static bool f2fs_force_buffered_io(struct inode *inode, int rw) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + + if (!fscrypt_dio_supported(inode)) + return true; + if (fsverity_active(inode)) + return true; + if (f2fs_compressed_file(inode)) + return true; + /* + * only force direct read to use buffered IO, for direct write, + * it expects inline data conversion before committing IO. + */ + if (f2fs_has_inline_data(inode) && rw == READ) + return true; + + /* disallow direct IO if any of devices has unaligned blksize */ + if (f2fs_is_multi_device(sbi) && !sbi->aligned_blksize) + return true; + /* + * for blkzoned device, fallback direct IO to buffered IO, so + * all IOs can be serialized by log-structured write. + */ + if (f2fs_sb_has_blkzoned(sbi) && (rw == WRITE) && + !f2fs_is_pinned_file(inode)) + return true; + if (is_sbi_flag_set(sbi, SBI_CP_DISABLED)) + return true; + + return false; +} + +int f2fs_getattr(struct mnt_idmap *idmap, const struct path *path, + struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); struct f2fs_inode_info *fi = F2FS_I(inode); + struct f2fs_inode *ri = NULL; unsigned int flags; - flags = fi->i_flags & FS_FL_USER_VISIBLE; - if (flags & FS_APPEND_FL) - stat->attributes |= STATX_ATTR_APPEND; - if (flags & FS_COMPR_FL) + if (f2fs_has_extra_attr(inode) && + f2fs_sb_has_inode_crtime(F2FS_I_SB(inode)) && + F2FS_FITS_IN_INODE(ri, fi->i_extra_isize, i_crtime)) { + stat->result_mask |= STATX_BTIME; + stat->btime.tv_sec = fi->i_crtime.tv_sec; + stat->btime.tv_nsec = fi->i_crtime.tv_nsec; + } + + /* + * Return the DIO alignment restrictions if requested. We only return + * this information when requested, since on encrypted files it might + * take a fair bit of work to get if the file wasn't opened recently. + * + * f2fs sometimes supports DIO reads but not DIO writes. STATX_DIOALIGN + * cannot represent that, so in that case we report no DIO support. + */ + if ((request_mask & STATX_DIOALIGN) && S_ISREG(inode->i_mode)) { + unsigned int bsize = i_blocksize(inode); + + stat->result_mask |= STATX_DIOALIGN; + if (!f2fs_force_buffered_io(inode, WRITE)) { + stat->dio_mem_align = bsize; + stat->dio_offset_align = bsize; + } + } + + flags = fi->i_flags; + if (flags & F2FS_COMPR_FL) stat->attributes |= STATX_ATTR_COMPRESSED; - if (f2fs_encrypted_inode(inode)) + if (flags & F2FS_APPEND_FL) + stat->attributes |= STATX_ATTR_APPEND; + if (IS_ENCRYPTED(inode)) stat->attributes |= STATX_ATTR_ENCRYPTED; - if (flags & FS_IMMUTABLE_FL) + if (flags & F2FS_IMMUTABLE_FL) stat->attributes |= STATX_ATTR_IMMUTABLE; - if (flags & FS_NODUMP_FL) + if (flags & F2FS_NODUMP_FL) stat->attributes |= STATX_ATTR_NODUMP; + if (IS_VERITY(inode)) + stat->attributes |= STATX_ATTR_VERITY; - stat->attributes_mask |= (STATX_ATTR_APPEND | - STATX_ATTR_COMPRESSED | + stat->attributes_mask |= (STATX_ATTR_COMPRESSED | + STATX_ATTR_APPEND | STATX_ATTR_ENCRYPTED | STATX_ATTR_IMMUTABLE | - STATX_ATTR_NODUMP); + STATX_ATTR_NODUMP | + STATX_ATTR_VERITY); + + generic_fillattr(idmap, request_mask, inode, stat); + + /* we need to show initial sectors used for inline_data/dentries */ + if ((S_ISREG(inode->i_mode) && f2fs_has_inline_data(inode)) || + f2fs_has_inline_dentry(inode)) + stat->blocks += (stat->size + 511) >> 9; - generic_fillattr(inode, stat); return 0; } #ifdef CONFIG_F2FS_FS_POSIX_ACL -static void __setattr_copy(struct inode *inode, const struct iattr *attr) +static void __setattr_copy(struct mnt_idmap *idmap, + struct inode *inode, const struct iattr *attr) { unsigned int ia_valid = attr->ia_valid; - if (ia_valid & ATTR_UID) - inode->i_uid = attr->ia_uid; - if (ia_valid & ATTR_GID) - inode->i_gid = attr->ia_gid; + i_uid_update(idmap, attr, inode); + i_gid_update(idmap, attr, inode); if (ia_valid & ATTR_ATIME) - inode->i_atime = timespec_trunc(attr->ia_atime, - inode->i_sb->s_time_gran); + inode_set_atime_to_ts(inode, attr->ia_atime); if (ia_valid & ATTR_MTIME) - inode->i_mtime = timespec_trunc(attr->ia_mtime, - inode->i_sb->s_time_gran); + inode_set_mtime_to_ts(inode, attr->ia_mtime); if (ia_valid & ATTR_CTIME) - inode->i_ctime = timespec_trunc(attr->ia_ctime, - inode->i_sb->s_time_gran); + inode_set_ctime_to_ts(inode, attr->ia_ctime); if (ia_valid & ATTR_MODE) { umode_t mode = attr->ia_mode; - if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID)) + if (!in_group_or_capable(idmap, inode, i_gid_into_vfsgid(idmap, inode))) mode &= ~S_ISGID; set_acl_inode(inode, mode); } @@ -699,82 +1055,143 @@ static void __setattr_copy(struct inode *inode, const struct iattr *attr) #define __setattr_copy setattr_copy #endif -int f2fs_setattr(struct dentry *dentry, struct iattr *attr) +int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, + struct iattr *attr) { struct inode *inode = d_inode(dentry); + struct f2fs_inode_info *fi = F2FS_I(inode); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); int err; - bool size_changed = false; - err = setattr_prepare(dentry, attr); + if (unlikely(f2fs_cp_error(sbi))) + return -EIO; + + err = setattr_prepare(idmap, dentry, attr); + if (err) + return err; + + err = fscrypt_prepare_setattr(dentry, attr); + if (err) + return err; + + err = fsverity_prepare_setattr(dentry, attr); if (err) return err; - if (is_quota_modification(inode, attr)) { - err = dquot_initialize(inode); + if (unlikely(IS_IMMUTABLE(inode))) + return -EPERM; + + if (unlikely(IS_APPEND(inode) && + (attr->ia_valid & (ATTR_MODE | ATTR_UID | + ATTR_GID | ATTR_TIMES_SET)))) + return -EPERM; + + if ((attr->ia_valid & ATTR_SIZE)) { + if (!f2fs_is_compress_backend_ready(inode) || + IS_DEVICE_ALIASING(inode)) + return -EOPNOTSUPP; + if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED) && + !IS_ALIGNED(attr->ia_size, + F2FS_BLK_TO_BYTES(fi->i_cluster_size))) + return -EINVAL; + /* + * To prevent scattered pin block generation, we don't allow + * smaller/equal size unaligned truncation for pinned file. + * We only support overwrite IO to pinned file, so don't + * care about larger size truncation. + */ + if (f2fs_is_pinned_file(inode) && + attr->ia_size <= i_size_read(inode) && + !IS_ALIGNED(attr->ia_size, + F2FS_BLK_TO_BYTES(CAP_BLKS_PER_SEC(sbi)))) + return -EINVAL; + } + + if (is_quota_modification(idmap, inode, attr)) { + err = f2fs_dquot_initialize(inode); if (err) return err; } - if ((attr->ia_valid & ATTR_UID && - !uid_eq(attr->ia_uid, inode->i_uid)) || - (attr->ia_valid & ATTR_GID && - !gid_eq(attr->ia_gid, inode->i_gid))) { - err = dquot_transfer(inode, attr); - if (err) + if (i_uid_needs_update(idmap, attr, inode) || + i_gid_needs_update(idmap, attr, inode)) { + f2fs_lock_op(sbi); + err = dquot_transfer(idmap, inode, attr); + if (err) { + set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR); + f2fs_unlock_op(sbi); return err; + } + /* + * update uid/gid under lock_op(), so that dquot and inode can + * be updated atomically. + */ + i_uid_update(idmap, attr, inode); + i_gid_update(idmap, attr, inode); + f2fs_mark_inode_dirty_sync(inode, true); + f2fs_unlock_op(sbi); } if (attr->ia_valid & ATTR_SIZE) { - if (f2fs_encrypted_inode(inode)) { - err = fscrypt_get_encryption_info(inode); + loff_t old_size = i_size_read(inode); + + if (attr->ia_size > MAX_INLINE_DATA(inode)) { + /* + * should convert inline inode before i_size_write to + * keep smaller than inline_data size with inline flag. + */ + err = f2fs_convert_inline_inode(inode); if (err) return err; - if (!fscrypt_has_encryption_key(inode)) - return -ENOKEY; } - if (attr->ia_size <= i_size_read(inode)) { - down_write(&F2FS_I(inode)->i_mmap_sem); - truncate_setsize(inode, attr->ia_size); + /* + * wait for inflight dio, blocks should be removed after + * IO completion. + */ + if (attr->ia_size < old_size) + inode_dio_wait(inode); + + f2fs_down_write(&fi->i_gc_rwsem[WRITE]); + filemap_invalidate_lock(inode->i_mapping); + + if (attr->ia_size > old_size) + f2fs_zero_post_eof_page(inode, attr->ia_size, false); + truncate_setsize(inode, attr->ia_size); + + if (attr->ia_size <= old_size) err = f2fs_truncate(inode); - up_write(&F2FS_I(inode)->i_mmap_sem); - if (err) - return err; - } else { - /* - * do not trim all blocks after i_size if target size is - * larger than i_size. - */ - down_write(&F2FS_I(inode)->i_mmap_sem); - truncate_setsize(inode, attr->ia_size); - up_write(&F2FS_I(inode)->i_mmap_sem); - - /* should convert inline inode here */ - if (!f2fs_may_inline_data(inode)) { - err = f2fs_convert_inline_inode(inode); - if (err) - return err; - } - inode->i_mtime = inode->i_ctime = current_time(inode); - } + /* + * do not trim all blocks after i_size if target size is + * larger than i_size. + */ + filemap_invalidate_unlock(inode->i_mapping); + f2fs_up_write(&fi->i_gc_rwsem[WRITE]); + if (err) + return err; - size_changed = true; + spin_lock(&fi->i_size_lock); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); + fi->last_disk_size = i_size_read(inode); + spin_unlock(&fi->i_size_lock); } - __setattr_copy(inode, attr); + __setattr_copy(idmap, inode, attr); if (attr->ia_valid & ATTR_MODE) { - err = posix_acl_chmod(inode, get_inode_mode(inode)); - if (err || is_inode_flag_set(inode, FI_ACL_MODE)) { - inode->i_mode = F2FS_I(inode)->i_acl_mode; + err = posix_acl_chmod(idmap, dentry, f2fs_get_inode_mode(inode)); + + if (is_inode_flag_set(inode, FI_ACL_MODE)) { + if (!err) + inode->i_mode = fi->i_acl_mode; clear_inode_flag(inode, FI_ACL_MODE); } } /* file size may changed here */ - f2fs_mark_inode_dirty_sync(inode, size_changed); + f2fs_mark_inode_dirty_sync(inode, true); /* inode change will produce dirty node pages flushed by checkpoint */ - f2fs_balance_fs(F2FS_I_SB(inode), true); + f2fs_balance_fs(sbi, true); return err; } @@ -782,19 +1199,19 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) const struct inode_operations f2fs_file_inode_operations = { .getattr = f2fs_getattr, .setattr = f2fs_setattr, - .get_acl = f2fs_get_acl, + .get_inode_acl = f2fs_get_acl, .set_acl = f2fs_set_acl, -#ifdef CONFIG_F2FS_FS_XATTR .listxattr = f2fs_listxattr, -#endif .fiemap = f2fs_fiemap, + .fileattr_get = f2fs_fileattr_get, + .fileattr_set = f2fs_fileattr_set, }; static int fill_zero(struct inode *inode, pgoff_t index, loff_t start, loff_t len) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct page *page; + struct folio *folio; if (!len) return 0; @@ -802,20 +1219,20 @@ static int fill_zero(struct inode *inode, pgoff_t index, f2fs_balance_fs(sbi, true); f2fs_lock_op(sbi); - page = get_new_data_page(inode, NULL, index, false); + folio = f2fs_get_new_data_folio(inode, NULL, index, false); f2fs_unlock_op(sbi); - if (IS_ERR(page)) - return PTR_ERR(page); + if (IS_ERR(folio)) + return PTR_ERR(folio); - f2fs_wait_on_page_writeback(page, DATA, true); - zero_user(page, start, len); - set_page_dirty(page); - f2fs_put_page(page, 1); + f2fs_folio_wait_writeback(folio, DATA, true, true); + folio_zero_range(folio, start, len); + folio_mark_dirty(folio); + f2fs_folio_put(folio, true); return 0; } -int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end) +int f2fs_truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end) { int err; @@ -824,21 +1241,22 @@ int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end) pgoff_t end_offset, count; set_new_dnode(&dn, inode, NULL, NULL, 0); - err = get_dnode_of_data(&dn, pg_start, LOOKUP_NODE); + err = f2fs_get_dnode_of_data(&dn, pg_start, LOOKUP_NODE); if (err) { if (err == -ENOENT) { - pg_start++; + pg_start = f2fs_get_next_page_offset(&dn, + pg_start); continue; } return err; } - end_offset = ADDRS_PER_PAGE(dn.node_page, inode); + end_offset = ADDRS_PER_PAGE(dn.node_folio, inode); count = min(end_offset - dn.ofs_in_node, pg_end - pg_start); f2fs_bug_on(F2FS_I_SB(inode), count == 0 || count > end_offset); - truncate_data_blocks_range(&dn, count); + f2fs_truncate_data_blocks_range(&dn, count); f2fs_put_dnode(&dn); pg_start += count; @@ -846,7 +1264,7 @@ int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end) return 0; } -static int punch_hole(struct inode *inode, loff_t offset, loff_t len) +static int f2fs_punch_hole(struct inode *inode, loff_t offset, loff_t len) { pgoff_t pg_start, pg_end; loff_t off_start, off_end; @@ -856,6 +1274,8 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len) if (ret) return ret; + f2fs_zero_post_eof_page(inode, offset + len, true); + pg_start = ((unsigned long long) offset) >> PAGE_SHIFT; pg_end = ((unsigned long long) offset + len) >> PAGE_SHIFT; @@ -881,7 +1301,6 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len) } if (pg_start < pg_end) { - struct address_space *mapping = inode->i_mapping; loff_t blk_start, blk_end; struct f2fs_sb_info *sbi = F2FS_I_SB(inode); @@ -889,14 +1308,18 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len) blk_start = (loff_t)pg_start << PAGE_SHIFT; blk_end = (loff_t)pg_end << PAGE_SHIFT; - down_write(&F2FS_I(inode)->i_mmap_sem); - truncate_inode_pages_range(mapping, blk_start, - blk_end - 1); + + f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + filemap_invalidate_lock(inode->i_mapping); + + truncate_pagecache_range(inode, blk_start, blk_end - 1); f2fs_lock_op(sbi); - ret = truncate_hole(inode, pg_start, pg_end); + ret = f2fs_truncate_hole(inode, pg_start, pg_end); f2fs_unlock_op(sbi); - up_write(&F2FS_I(inode)->i_mmap_sem); + + filemap_invalidate_unlock(inode->i_mapping); + f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); } } @@ -912,27 +1335,36 @@ static int __read_out_blkaddrs(struct inode *inode, block_t *blkaddr, next_dnode: set_new_dnode(&dn, inode, NULL, NULL, 0); - ret = get_dnode_of_data(&dn, off, LOOKUP_NODE_RA); + ret = f2fs_get_dnode_of_data(&dn, off, LOOKUP_NODE_RA); if (ret && ret != -ENOENT) { return ret; } else if (ret == -ENOENT) { if (dn.max_level == 0) return -ENOENT; - done = min((pgoff_t)ADDRS_PER_BLOCK - dn.ofs_in_node, len); + done = min((pgoff_t)ADDRS_PER_BLOCK(inode) - + dn.ofs_in_node, len); blkaddr += done; do_replace += done; goto next; } - done = min((pgoff_t)ADDRS_PER_PAGE(dn.node_page, inode) - + done = min((pgoff_t)ADDRS_PER_PAGE(dn.node_folio, inode) - dn.ofs_in_node, len); for (i = 0; i < done; i++, blkaddr++, do_replace++, dn.ofs_in_node++) { - *blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node); - if (!is_checkpointed_data(sbi, *blkaddr)) { + *blkaddr = f2fs_data_blkaddr(&dn); + + if (__is_valid_data_blkaddr(*blkaddr) && + !f2fs_is_valid_blkaddr(sbi, *blkaddr, + DATA_GENERIC_ENHANCE)) { + f2fs_put_dnode(&dn); + return -EFSCORRUPTED; + } - if (test_opt(sbi, LFS)) { + if (!f2fs_is_checkpointed_data(sbi, *blkaddr)) { + + if (f2fs_lfs_mode(sbi)) { f2fs_put_dnode(&dn); - return -ENOTSUPP; + return -EOPNOTSUPP; } /* do not invalidate this block address */ @@ -961,10 +1393,10 @@ static int __roll_back_blkaddrs(struct inode *inode, block_t *blkaddr, continue; set_new_dnode(&dn, inode, NULL, NULL, 0); - ret = get_dnode_of_data(&dn, off + i, LOOKUP_NODE_RA); + ret = f2fs_get_dnode_of_data(&dn, off + i, LOOKUP_NODE_RA); if (ret) { dec_valid_block_count(sbi, inode, 1); - invalidate_blocks(sbi, *blkaddr); + f2fs_invalidate_blocks(sbi, *blkaddr, 1); } else { f2fs_update_data_blkaddr(&dn, *blkaddr); } @@ -994,18 +1426,22 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode, pgoff_t ilen; set_new_dnode(&dn, dst_inode, NULL, NULL, 0); - ret = get_dnode_of_data(&dn, dst + i, ALLOC_NODE); + ret = f2fs_get_dnode_of_data(&dn, dst + i, ALLOC_NODE); if (ret) return ret; - get_node_info(sbi, dn.nid, &ni); + ret = f2fs_get_node_info(sbi, dn.nid, &ni, false); + if (ret) { + f2fs_put_dnode(&dn); + return ret; + } + ilen = min((pgoff_t) - ADDRS_PER_PAGE(dn.node_page, dst_inode) - + ADDRS_PER_PAGE(dn.node_folio, dst_inode) - dn.ofs_in_node, len - i); do { - dn.data_blkaddr = datablock_addr(dn.node_page, - dn.ofs_in_node); - truncate_data_blocks_range(&dn, 1); + dn.data_blkaddr = f2fs_data_blkaddr(&dn); + f2fs_truncate_data_blocks_range(&dn, 1); if (do_replace[i]) { f2fs_i_blocks_write(src_inode, @@ -1019,30 +1455,36 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode, } dn.ofs_in_node++; i++; - new_size = (dst + i) << PAGE_SHIFT; + new_size = (loff_t)(dst + i) << PAGE_SHIFT; if (dst_inode->i_size < new_size) f2fs_i_size_write(dst_inode, new_size); } while (--ilen && (do_replace[i] || blkaddr[i] == NULL_ADDR)); f2fs_put_dnode(&dn); } else { - struct page *psrc, *pdst; + struct folio *fsrc, *fdst; - psrc = get_lock_data_page(src_inode, src + i, true); - if (IS_ERR(psrc)) - return PTR_ERR(psrc); - pdst = get_new_data_page(dst_inode, NULL, dst + i, + fsrc = f2fs_get_lock_data_folio(src_inode, + src + i, true); + if (IS_ERR(fsrc)) + return PTR_ERR(fsrc); + fdst = f2fs_get_new_data_folio(dst_inode, NULL, dst + i, true); - if (IS_ERR(pdst)) { - f2fs_put_page(psrc, 1); - return PTR_ERR(pdst); + if (IS_ERR(fdst)) { + f2fs_folio_put(fsrc, true); + return PTR_ERR(fdst); } - f2fs_copy_page(psrc, pdst); - set_page_dirty(pdst); - f2fs_put_page(pdst, 1); - f2fs_put_page(psrc, 1); - ret = truncate_hole(src_inode, src + i, src + i + 1); + f2fs_folio_wait_writeback(fdst, DATA, true, true); + + memcpy_folio(fdst, 0, fsrc, 0, PAGE_SIZE); + folio_mark_dirty(fdst); + folio_set_f2fs_gcing(fdst); + f2fs_folio_put(fdst, true); + f2fs_folio_put(fsrc, true); + + ret = f2fs_truncate_hole(src_inode, + src + i, src + i + 1); if (ret) return ret; i++; @@ -1061,13 +1503,17 @@ static int __exchange_data_block(struct inode *src_inode, int ret; while (len) { - olen = min((pgoff_t)4 * ADDRS_PER_BLOCK, len); + olen = min((pgoff_t)4 * ADDRS_PER_BLOCK(src_inode), len); - src_blkaddr = kvzalloc(sizeof(block_t) * olen, GFP_KERNEL); + src_blkaddr = f2fs_kvzalloc(F2FS_I_SB(src_inode), + array_size(olen, sizeof(block_t)), + GFP_NOFS); if (!src_blkaddr) return -ENOMEM; - do_replace = kvzalloc(sizeof(int) * olen, GFP_KERNEL); + do_replace = f2fs_kvzalloc(F2FS_I_SB(src_inode), + array_size(olen, sizeof(int)), + GFP_NOFS); if (!do_replace) { kvfree(src_blkaddr); return -ENOMEM; @@ -1093,31 +1539,41 @@ static int __exchange_data_block(struct inode *src_inode, return 0; roll_back: - __roll_back_blkaddrs(src_inode, src_blkaddr, do_replace, src, len); + __roll_back_blkaddrs(src_inode, src_blkaddr, do_replace, src, olen); kvfree(src_blkaddr); kvfree(do_replace); return ret; } -static int f2fs_do_collapse(struct inode *inode, pgoff_t start, pgoff_t end) +static int f2fs_do_collapse(struct inode *inode, loff_t offset, loff_t len) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - pgoff_t nrpages = (i_size_read(inode) + PAGE_SIZE - 1) / PAGE_SIZE; + pgoff_t nrpages = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); + pgoff_t start = offset >> PAGE_SHIFT; + pgoff_t end = (offset + len) >> PAGE_SHIFT; int ret; f2fs_balance_fs(sbi, true); - f2fs_lock_op(sbi); - f2fs_drop_extent_tree(inode); + /* avoid gc operation during block exchange */ + f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + filemap_invalidate_lock(inode->i_mapping); + + f2fs_zero_post_eof_page(inode, offset + len, false); + f2fs_lock_op(sbi); + f2fs_drop_extent_tree(inode); + truncate_pagecache(inode, offset); ret = __exchange_data_block(inode, inode, end, start, nrpages - end, true); f2fs_unlock_op(sbi); + + filemap_invalidate_unlock(inode->i_mapping); + f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); return ret; } static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len) { - pgoff_t pg_start, pg_end; loff_t new_size; int ret; @@ -1132,34 +1588,25 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len) if (ret) return ret; - pg_start = offset >> PAGE_SHIFT; - pg_end = (offset + len) >> PAGE_SHIFT; - - down_write(&F2FS_I(inode)->i_mmap_sem); /* write out all dirty pages from offset */ ret = filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX); if (ret) - goto out; - - truncate_pagecache(inode, offset); + return ret; - ret = f2fs_do_collapse(inode, pg_start, pg_end); + ret = f2fs_do_collapse(inode, offset, len); if (ret) - goto out; + return ret; /* write out all moved pages, if possible */ + filemap_invalidate_lock(inode->i_mapping); filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX); truncate_pagecache(inode, offset); new_size = i_size_read(inode) - len; - truncate_pagecache(inode, new_size); - - ret = truncate_blocks(inode, new_size, true); + ret = f2fs_truncate_blocks(inode, new_size, true); + filemap_invalidate_unlock(inode->i_mapping); if (!ret) f2fs_i_size_write(inode, new_size); - -out: - up_write(&F2FS_I(inode)->i_mmap_sem); return ret; } @@ -1173,35 +1620,45 @@ static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start, int ret; for (; index < end; index++, dn->ofs_in_node++) { - if (datablock_addr(dn->node_page, dn->ofs_in_node) == NULL_ADDR) + if (f2fs_data_blkaddr(dn) == NULL_ADDR) count++; } dn->ofs_in_node = ofs_in_node; - ret = reserve_new_blocks(dn, count); + ret = f2fs_reserve_new_blocks(dn, count); if (ret) return ret; dn->ofs_in_node = ofs_in_node; for (index = start; index < end; index++, dn->ofs_in_node++) { - dn->data_blkaddr = - datablock_addr(dn->node_page, dn->ofs_in_node); + dn->data_blkaddr = f2fs_data_blkaddr(dn); /* - * reserve_new_blocks will not guarantee entire block + * f2fs_reserve_new_blocks will not guarantee entire block * allocation. */ if (dn->data_blkaddr == NULL_ADDR) { ret = -ENOSPC; break; } - if (dn->data_blkaddr != NEW_ADDR) { - invalidate_blocks(sbi, dn->data_blkaddr); - dn->data_blkaddr = NEW_ADDR; - set_data_blkaddr(dn); + + if (dn->data_blkaddr == NEW_ADDR) + continue; + + if (!f2fs_is_valid_blkaddr(sbi, dn->data_blkaddr, + DATA_GENERIC_ENHANCE)) { + ret = -EFSCORRUPTED; + break; } + + f2fs_invalidate_blocks(sbi, dn->data_blkaddr, 1); + f2fs_set_data_blkaddr(dn, NEW_ADDR); } - f2fs_update_extent_cache_range(dn, start, 0, index - start); + if (index > start) { + f2fs_update_read_extent_cache_range(dn, start, 0, + index - start); + f2fs_update_age_extent_cache_range(dn, start, index - start); + } return ret; } @@ -1224,12 +1681,11 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len, if (ret) return ret; - down_write(&F2FS_I(inode)->i_mmap_sem); ret = filemap_write_and_wait_range(mapping, offset, offset + len - 1); if (ret) - goto out_sem; + return ret; - truncate_pagecache_range(inode, offset, offset + len - 1); + f2fs_zero_post_eof_page(inode, offset + len, true); pg_start = ((unsigned long long) offset) >> PAGE_SHIFT; pg_end = ((unsigned long long) offset + len) >> PAGE_SHIFT; @@ -1241,7 +1697,7 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len, ret = fill_zero(inode, pg_start, off_start, off_end - off_start); if (ret) - goto out_sem; + return ret; new_size = max_t(loff_t, new_size, offset + len); } else { @@ -1249,7 +1705,7 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len, ret = fill_zero(inode, pg_start++, off_start, PAGE_SIZE - off_start); if (ret) - goto out_sem; + return ret; new_size = max_t(loff_t, new_size, (loff_t)pg_start << PAGE_SHIFT); @@ -1260,21 +1716,33 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len, unsigned int end_offset; pgoff_t end; + f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + filemap_invalidate_lock(mapping); + + truncate_pagecache_range(inode, + (loff_t)index << PAGE_SHIFT, + ((loff_t)pg_end << PAGE_SHIFT) - 1); + f2fs_lock_op(sbi); set_new_dnode(&dn, inode, NULL, NULL, 0); - ret = get_dnode_of_data(&dn, index, ALLOC_NODE); + ret = f2fs_get_dnode_of_data(&dn, index, ALLOC_NODE); if (ret) { f2fs_unlock_op(sbi); + filemap_invalidate_unlock(mapping); + f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); goto out; } - end_offset = ADDRS_PER_PAGE(dn.node_page, inode); + end_offset = ADDRS_PER_PAGE(dn.node_folio, inode); end = min(pg_end, end_offset - dn.ofs_in_node + index); ret = f2fs_do_zero_range(&dn, index, end); f2fs_put_dnode(&dn); + f2fs_unlock_op(sbi); + filemap_invalidate_unlock(mapping); + f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); f2fs_balance_fs(sbi, dn.node_changed); @@ -1296,17 +1764,19 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len, } out: - if (!(mode & FALLOC_FL_KEEP_SIZE) && i_size_read(inode) < new_size) - f2fs_i_size_write(inode, new_size); -out_sem: - up_write(&F2FS_I(inode)->i_mmap_sem); - + if (new_size > i_size_read(inode)) { + if (mode & FALLOC_FL_KEEP_SIZE) + file_set_keep_isize(inode); + else + f2fs_i_size_write(inode, new_size); + } return ret; } static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct address_space *mapping = inode->i_mapping; pgoff_t nr, pg_start, pg_end, delta, idx; loff_t new_size; int ret = 0; @@ -1329,22 +1799,28 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len) f2fs_balance_fs(sbi, true); - down_write(&F2FS_I(inode)->i_mmap_sem); - ret = truncate_blocks(inode, i_size_read(inode), true); + filemap_invalidate_lock(mapping); + ret = f2fs_truncate_blocks(inode, i_size_read(inode), true); + filemap_invalidate_unlock(mapping); if (ret) - goto out; + return ret; /* write out all dirty pages from offset */ - ret = filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX); + ret = filemap_write_and_wait_range(mapping, offset, LLONG_MAX); if (ret) - goto out; - - truncate_pagecache(inode, offset); + return ret; pg_start = offset >> PAGE_SHIFT; pg_end = (offset + len) >> PAGE_SHIFT; delta = pg_end - pg_start; - idx = (i_size_read(inode) + PAGE_SIZE - 1) / PAGE_SIZE; + idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); + + /* avoid gc operation during block exchange */ + f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + filemap_invalidate_lock(mapping); + + f2fs_zero_post_eof_page(inode, offset + len, false); + truncate_pagecache(inode, offset); while (!ret && idx > pg_start) { nr = idx - pg_start; @@ -1359,26 +1835,38 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len) idx + delta, nr, false); f2fs_unlock_op(sbi); } + filemap_invalidate_unlock(mapping); + f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + if (ret) + return ret; /* write out all moved pages, if possible */ - filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX); + filemap_invalidate_lock(mapping); + ret = filemap_write_and_wait_range(mapping, offset, LLONG_MAX); truncate_pagecache(inode, offset); + filemap_invalidate_unlock(mapping); if (!ret) f2fs_i_size_write(inode, new_size); -out: - up_write(&F2FS_I(inode)->i_mmap_sem); return ret; } -static int expand_inode_data(struct inode *inode, loff_t offset, +static int f2fs_expand_inode_data(struct inode *inode, loff_t offset, loff_t len, int mode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct f2fs_map_blocks map = { .m_next_pgofs = NULL }; - pgoff_t pg_end; - loff_t new_size = i_size_read(inode); + struct f2fs_map_blocks map = { .m_next_pgofs = NULL, + .m_next_extent = NULL, .m_seg_type = NO_CHECK_TYPE, + .m_may_create = true }; + struct f2fs_gc_control gc_control = { .victim_segno = NULL_SEGNO, + .init_gc_type = FG_GC, + .should_migrate_blocks = false, + .err_gc_skipped = true, + .nr_free_secs = 0 }; + pgoff_t pg_start, pg_end; + loff_t new_size; loff_t off_end; + block_t expanded = 0; int err; err = inode_newsize_ok(inode, (len + offset)); @@ -1389,34 +1877,98 @@ static int expand_inode_data(struct inode *inode, loff_t offset, if (err) return err; + f2fs_zero_post_eof_page(inode, offset + len, true); + f2fs_balance_fs(sbi, true); + pg_start = ((unsigned long long)offset) >> PAGE_SHIFT; pg_end = ((unsigned long long)offset + len) >> PAGE_SHIFT; off_end = (offset + len) & (PAGE_SIZE - 1); - map.m_lblk = ((unsigned long long)offset) >> PAGE_SHIFT; - map.m_len = pg_end - map.m_lblk; + map.m_lblk = pg_start; + map.m_len = pg_end - pg_start; if (off_end) map.m_len++; - err = f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_AIO); + if (!map.m_len) + return 0; + + if (f2fs_is_pinned_file(inode)) { + block_t sec_blks = CAP_BLKS_PER_SEC(sbi); + block_t sec_len = roundup(map.m_len, sec_blks); + + map.m_len = sec_blks; +next_alloc: + f2fs_down_write(&sbi->pin_sem); + + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) { + if (has_not_enough_free_secs(sbi, 0, 0)) { + f2fs_up_write(&sbi->pin_sem); + err = -ENOSPC; + f2fs_warn_ratelimited(sbi, + "ino:%lu, start:%lu, end:%lu, need to trigger GC to " + "reclaim enough free segment when checkpoint is enabled", + inode->i_ino, pg_start, pg_end); + goto out_err; + } + } + + if (has_not_enough_free_secs(sbi, 0, + sbi->reserved_pin_section)) { + f2fs_down_write(&sbi->gc_lock); + stat_inc_gc_call_count(sbi, FOREGROUND); + err = f2fs_gc(sbi, &gc_control); + if (err && err != -ENODATA) { + f2fs_up_write(&sbi->pin_sem); + goto out_err; + } + } + + err = f2fs_allocate_pinning_section(sbi); + if (err) { + f2fs_up_write(&sbi->pin_sem); + goto out_err; + } + + map.m_seg_type = CURSEG_COLD_DATA_PINNED; + err = f2fs_map_blocks(inode, &map, F2FS_GET_BLOCK_PRE_DIO); + file_dont_truncate(inode); + + f2fs_up_write(&sbi->pin_sem); + + expanded += map.m_len; + sec_len -= map.m_len; + map.m_lblk += map.m_len; + if (!err && sec_len) + goto next_alloc; + + map.m_len = expanded; + } else { + err = f2fs_map_blocks(inode, &map, F2FS_GET_BLOCK_PRE_AIO); + expanded = map.m_len; + } +out_err: if (err) { pgoff_t last_off; - if (!map.m_len) + if (!expanded) return err; - last_off = map.m_lblk + map.m_len - 1; + last_off = pg_start + expanded - 1; /* update new size to the failed position */ - new_size = (last_off == pg_end) ? offset + len: + new_size = (last_off == pg_end) ? offset + len : (loff_t)(last_off + 1) << PAGE_SHIFT; } else { new_size = ((loff_t)pg_end << PAGE_SHIFT) + off_end; } - if (!(mode & FALLOC_FL_KEEP_SIZE) && i_size_read(inode) < new_size) - f2fs_i_size_write(inode, new_size); + if (new_size > i_size_read(inode)) { + if (mode & FALLOC_FL_KEEP_SIZE) + file_set_keep_isize(inode); + else + f2fs_i_size_write(inode, new_size); + } return err; } @@ -1427,11 +1979,18 @@ static long f2fs_fallocate(struct file *file, int mode, struct inode *inode = file_inode(file); long ret = 0; + if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) + return -EIO; + if (!f2fs_is_checkpoint_ready(F2FS_I_SB(inode))) + return -ENOSPC; + if (!f2fs_is_compress_backend_ready(inode) || IS_DEVICE_ALIASING(inode)) + return -EOPNOTSUPP; + /* f2fs only support ->fallocate for regular file */ if (!S_ISREG(inode->i_mode)) return -EINVAL; - if (f2fs_encrypted_inode(inode) && + if (IS_ENCRYPTED(inode) && (mode & (FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_INSERT_RANGE))) return -EOPNOTSUPP; @@ -1442,11 +2001,32 @@ static long f2fs_fallocate(struct file *file, int mode, inode_lock(inode); + /* + * Pinned file should not support partial truncation since the block + * can be used by applications. + */ + if ((f2fs_compressed_file(inode) || f2fs_is_pinned_file(inode)) && + (mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_COLLAPSE_RANGE | + FALLOC_FL_ZERO_RANGE | FALLOC_FL_INSERT_RANGE))) { + ret = -EOPNOTSUPP; + goto out; + } + + ret = file_modified(file); + if (ret) + goto out; + + /* + * wait for inflight dio, blocks should be removed after IO + * completion. + */ + inode_dio_wait(inode); + if (mode & FALLOC_FL_PUNCH_HOLE) { if (offset >= inode->i_size) goto out; - ret = punch_hole(inode, offset, len); + ret = f2fs_punch_hole(inode, offset, len); } else if (mode & FALLOC_FL_COLLAPSE_RANGE) { ret = f2fs_collapse_range(inode, offset, len); } else if (mode & FALLOC_FL_ZERO_RANGE) { @@ -1454,14 +2034,12 @@ static long f2fs_fallocate(struct file *file, int mode, } else if (mode & FALLOC_FL_INSERT_RANGE) { ret = f2fs_insert_range(inode, offset, len); } else { - ret = expand_inode_data(inode, offset, len, mode); + ret = f2fs_expand_inode_data(inode, offset, len, mode); } if (!ret) { - inode->i_mtime = inode->i_ctime = current_time(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); f2fs_mark_inode_dirty_sync(inode, false); - if (mode & FALLOC_FL_KEEP_SIZE) - file_set_keep_isize(inode); f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); } @@ -1474,96 +2052,193 @@ out: static int f2fs_release_file(struct inode *inode, struct file *filp) { + if (atomic_dec_and_test(&F2FS_I(inode)->open_count)) + f2fs_remove_donate_inode(inode); + /* - * f2fs_relase_file is called at every close calls. So we should + * f2fs_release_file is called at every close calls. So we should * not drop any inmemory pages by close called by other process. */ if (!(filp->f_mode & FMODE_WRITE) || atomic_read(&inode->i_writecount) != 1) return 0; - /* some remained atomic pages should discarded */ - if (f2fs_is_atomic_file(inode)) - drop_inmem_pages(inode); - if (f2fs_is_volatile_file(inode)) { - clear_inode_flag(inode, FI_VOLATILE_FILE); - stat_dec_volatile_write(inode); - set_inode_flag(inode, FI_DROP_CACHE); - filemap_fdatawrite(inode->i_mapping); - clear_inode_flag(inode, FI_DROP_CACHE); - } + inode_lock(inode); + f2fs_abort_atomic_write(inode, true); + inode_unlock(inode); + return 0; } -#define F2FS_REG_FLMASK (~(FS_DIRSYNC_FL | FS_TOPDIR_FL)) -#define F2FS_OTHER_FLMASK (FS_NODUMP_FL | FS_NOATIME_FL) - -static inline __u32 f2fs_mask_flags(umode_t mode, __u32 flags) +static int f2fs_file_flush(struct file *file, fl_owner_t id) { - if (S_ISDIR(mode)) - return flags; - else if (S_ISREG(mode)) - return flags & F2FS_REG_FLMASK; - else - return flags & F2FS_OTHER_FLMASK; -} + struct inode *inode = file_inode(file); -static int f2fs_ioc_getflags(struct file *filp, unsigned long arg) -{ - struct inode *inode = file_inode(filp); - struct f2fs_inode_info *fi = F2FS_I(inode); - unsigned int flags = fi->i_flags & FS_FL_USER_VISIBLE; - return put_user(flags, (int __user *)arg); + /* + * If the process doing a transaction is crashed, we should do + * roll-back. Otherwise, other reader/write can see corrupted database + * until all the writers close its file. Since this should be done + * before dropping file lock, it needs to do in ->flush. + */ + if (F2FS_I(inode)->atomic_write_task == current && + (current->flags & PF_EXITING)) { + inode_lock(inode); + f2fs_abort_atomic_write(inode, true); + inode_unlock(inode); + } + + return 0; } -static int f2fs_ioc_setflags(struct file *filp, unsigned long arg) +static int f2fs_setflags_common(struct inode *inode, u32 iflags, u32 mask) { - struct inode *inode = file_inode(filp); struct f2fs_inode_info *fi = F2FS_I(inode); - unsigned int flags; - unsigned int oldflags; - int ret; + u32 masked_flags = fi->i_flags & mask; - if (!inode_owner_or_capable(inode)) - return -EACCES; + /* mask can be shrunk by flags_valid selector */ + iflags &= mask; - if (get_user(flags, (int __user *)arg)) - return -EFAULT; - - ret = mnt_want_write_file(filp); - if (ret) - return ret; + /* Is it quota file? Do not allow user to mess with it */ + if (IS_NOQUOTA(inode)) + return -EPERM; - inode_lock(inode); + if ((iflags ^ masked_flags) & F2FS_CASEFOLD_FL) { + if (!f2fs_sb_has_casefold(F2FS_I_SB(inode))) + return -EOPNOTSUPP; + if (!f2fs_empty_dir(inode)) + return -ENOTEMPTY; + } - /* Is it quota file? Do not allow user to mess with it */ - if (IS_NOQUOTA(inode)) { - ret = -EPERM; - goto unlock_out; + if (iflags & (F2FS_COMPR_FL | F2FS_NOCOMP_FL)) { + if (!f2fs_sb_has_compression(F2FS_I_SB(inode))) + return -EOPNOTSUPP; + if ((iflags & F2FS_COMPR_FL) && (iflags & F2FS_NOCOMP_FL)) + return -EINVAL; } - flags = f2fs_mask_flags(inode->i_mode, flags); + if ((iflags ^ masked_flags) & F2FS_COMPR_FL) { + if (masked_flags & F2FS_COMPR_FL) { + if (!f2fs_disable_compressed_file(inode)) + return -EINVAL; + } else { + /* try to convert inline_data to support compression */ + int err = f2fs_convert_inline_inode(inode); + if (err) + return err; - oldflags = fi->i_flags; + f2fs_down_write(&fi->i_sem); + if (!f2fs_may_compress(inode) || + atomic_read(&fi->writeback) || + (S_ISREG(inode->i_mode) && + F2FS_HAS_BLOCKS(inode))) { + f2fs_up_write(&fi->i_sem); + return -EINVAL; + } + err = set_compress_context(inode); + f2fs_up_write(&fi->i_sem); - if ((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL)) { - if (!capable(CAP_LINUX_IMMUTABLE)) { - ret = -EPERM; - goto unlock_out; + if (err) + return err; } } - flags = flags & FS_FL_USER_MODIFIABLE; - flags |= oldflags & ~FS_FL_USER_MODIFIABLE; - fi->i_flags = flags; + fi->i_flags = iflags | (fi->i_flags & ~mask); + f2fs_bug_on(F2FS_I_SB(inode), (fi->i_flags & F2FS_COMPR_FL) && + (fi->i_flags & F2FS_NOCOMP_FL)); + + if (fi->i_flags & F2FS_PROJINHERIT_FL) + set_inode_flag(inode, FI_PROJ_INHERIT); + else + clear_inode_flag(inode, FI_PROJ_INHERIT); - inode->i_ctime = current_time(inode); + inode_set_ctime_current(inode); f2fs_set_inode_flags(inode); - f2fs_mark_inode_dirty_sync(inode, false); -unlock_out: - inode_unlock(inode); - mnt_drop_write_file(filp); - return ret; + f2fs_mark_inode_dirty_sync(inode, true); + return 0; +} + +/* FS_IOC_[GS]ETFLAGS and FS_IOC_FS[GS]ETXATTR support */ + +/* + * To make a new on-disk f2fs i_flag gettable via FS_IOC_GETFLAGS, add an entry + * for it to f2fs_fsflags_map[], and add its FS_*_FL equivalent to + * F2FS_GETTABLE_FS_FL. To also make it settable via FS_IOC_SETFLAGS, also add + * its FS_*_FL equivalent to F2FS_SETTABLE_FS_FL. + * + * Translating flags to fsx_flags value used by FS_IOC_FSGETXATTR and + * FS_IOC_FSSETXATTR is done by the VFS. + */ + +static const struct { + u32 iflag; + u32 fsflag; +} f2fs_fsflags_map[] = { + { F2FS_COMPR_FL, FS_COMPR_FL }, + { F2FS_SYNC_FL, FS_SYNC_FL }, + { F2FS_IMMUTABLE_FL, FS_IMMUTABLE_FL }, + { F2FS_APPEND_FL, FS_APPEND_FL }, + { F2FS_NODUMP_FL, FS_NODUMP_FL }, + { F2FS_NOATIME_FL, FS_NOATIME_FL }, + { F2FS_NOCOMP_FL, FS_NOCOMP_FL }, + { F2FS_INDEX_FL, FS_INDEX_FL }, + { F2FS_DIRSYNC_FL, FS_DIRSYNC_FL }, + { F2FS_PROJINHERIT_FL, FS_PROJINHERIT_FL }, + { F2FS_CASEFOLD_FL, FS_CASEFOLD_FL }, +}; + +#define F2FS_GETTABLE_FS_FL ( \ + FS_COMPR_FL | \ + FS_SYNC_FL | \ + FS_IMMUTABLE_FL | \ + FS_APPEND_FL | \ + FS_NODUMP_FL | \ + FS_NOATIME_FL | \ + FS_NOCOMP_FL | \ + FS_INDEX_FL | \ + FS_DIRSYNC_FL | \ + FS_PROJINHERIT_FL | \ + FS_ENCRYPT_FL | \ + FS_INLINE_DATA_FL | \ + FS_NOCOW_FL | \ + FS_VERITY_FL | \ + FS_CASEFOLD_FL) + +#define F2FS_SETTABLE_FS_FL ( \ + FS_COMPR_FL | \ + FS_SYNC_FL | \ + FS_IMMUTABLE_FL | \ + FS_APPEND_FL | \ + FS_NODUMP_FL | \ + FS_NOATIME_FL | \ + FS_NOCOMP_FL | \ + FS_DIRSYNC_FL | \ + FS_PROJINHERIT_FL | \ + FS_CASEFOLD_FL) + +/* Convert f2fs on-disk i_flags to FS_IOC_{GET,SET}FLAGS flags */ +static inline u32 f2fs_iflags_to_fsflags(u32 iflags) +{ + u32 fsflags = 0; + int i; + + for (i = 0; i < ARRAY_SIZE(f2fs_fsflags_map); i++) + if (iflags & f2fs_fsflags_map[i].iflag) + fsflags |= f2fs_fsflags_map[i].fsflag; + + return fsflags; +} + +/* Convert FS_IOC_{GET,SET}FLAGS flags to f2fs on-disk i_flags */ +static inline u32 f2fs_fsflags_to_iflags(u32 fsflags) +{ + u32 iflags = 0; + int i; + + for (i = 0; i < ARRAY_SIZE(f2fs_fsflags_map); i++) + if (fsflags & f2fs_fsflags_map[i].fsflag) + iflags |= f2fs_fsflags_map[i].iflag; + + return iflags; } static int f2fs_ioc_getversion(struct file *filp, unsigned long arg) @@ -1573,23 +2248,39 @@ static int f2fs_ioc_getversion(struct file *filp, unsigned long arg) return put_user(inode->i_generation, (int __user *)arg); } -static int f2fs_ioc_start_atomic_write(struct file *filp) +static int f2fs_ioc_start_atomic_write(struct file *filp, bool truncate) { struct inode *inode = file_inode(filp); + struct mnt_idmap *idmap = file_mnt_idmap(filp); + struct f2fs_inode_info *fi = F2FS_I(inode); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + loff_t isize; int ret; - if (!inode_owner_or_capable(inode)) + if (!(filp->f_mode & FMODE_WRITE)) + return -EBADF; + + if (!inode_owner_or_capable(idmap, inode)) return -EACCES; if (!S_ISREG(inode->i_mode)) return -EINVAL; + if (filp->f_flags & O_DIRECT) + return -EINVAL; + ret = mnt_want_write_file(filp); if (ret) return ret; inode_lock(inode); + if (!f2fs_disable_compressed_file(inode) || + f2fs_is_pinned_file(inode)) { + ret = -EINVAL; + goto out; + } + if (f2fs_is_atomic_file(inode)) goto out; @@ -1597,25 +2288,72 @@ static int f2fs_ioc_start_atomic_write(struct file *filp) if (ret) goto out; + f2fs_down_write(&fi->i_gc_rwsem[WRITE]); + f2fs_down_write(&fi->i_gc_rwsem[READ]); + + /* + * Should wait end_io to count F2FS_WB_CP_DATA correctly by + * f2fs_is_atomic_file. + */ + if (get_dirty_pages(inode)) + f2fs_warn(sbi, "Unexpected flush for atomic writes: ino=%lu, npages=%u", + inode->i_ino, get_dirty_pages(inode)); + ret = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX); + if (ret) + goto out_unlock; + + /* Check if the inode already has a COW inode */ + if (fi->cow_inode == NULL) { + /* Create a COW inode for atomic write */ + struct dentry *dentry = file_dentry(filp); + struct inode *dir = d_inode(dentry->d_parent); + + ret = f2fs_get_tmpfile(idmap, dir, &fi->cow_inode); + if (ret) + goto out_unlock; + + set_inode_flag(fi->cow_inode, FI_COW_FILE); + clear_inode_flag(fi->cow_inode, FI_INLINE_DATA); + + /* Set the COW inode's atomic_inode to the atomic inode */ + F2FS_I(fi->cow_inode)->atomic_inode = inode; + } else { + /* Reuse the already created COW inode */ + f2fs_bug_on(sbi, get_dirty_pages(fi->cow_inode)); + + invalidate_mapping_pages(fi->cow_inode->i_mapping, 0, -1); + + ret = f2fs_do_truncate_blocks(fi->cow_inode, 0, true); + if (ret) + goto out_unlock; + } + + f2fs_write_inode(inode, NULL); + + stat_inc_atomic_inode(inode); + set_inode_flag(inode, FI_ATOMIC_FILE); - set_inode_flag(inode, FI_HOT_DATA); - f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); - if (!get_dirty_pages(inode)) - goto inc_stat; + isize = i_size_read(inode); + fi->original_i_size = isize; + if (truncate) { + set_inode_flag(inode, FI_ATOMIC_REPLACE); + truncate_inode_pages_final(inode->i_mapping); + f2fs_i_size_write(inode, 0); + isize = 0; + } + f2fs_i_size_write(fi->cow_inode, isize); - f2fs_msg(F2FS_I_SB(inode)->sb, KERN_WARNING, - "Unexpected flush for atomic writes: ino=%lu, npages=%u", - inode->i_ino, get_dirty_pages(inode)); - ret = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX); - if (ret) { - clear_inode_flag(inode, FI_ATOMIC_FILE); +out_unlock: + f2fs_up_write(&fi->i_gc_rwsem[READ]); + f2fs_up_write(&fi->i_gc_rwsem[WRITE]); + if (ret) goto out; - } -inc_stat: - stat_inc_atomic_write(inode); + f2fs_update_time(sbi, REQ_TIME); + fi->atomic_write_task = current; stat_update_max_atomic_write(inode); + fi->atomic_write_cnt = 0; out: inode_unlock(inode); mnt_drop_write_file(filp); @@ -1625,49 +2363,49 @@ out: static int f2fs_ioc_commit_atomic_write(struct file *filp) { struct inode *inode = file_inode(filp); + struct mnt_idmap *idmap = file_mnt_idmap(filp); int ret; - if (!inode_owner_or_capable(inode)) + if (!(filp->f_mode & FMODE_WRITE)) + return -EBADF; + + if (!inode_owner_or_capable(idmap, inode)) return -EACCES; ret = mnt_want_write_file(filp); if (ret) return ret; - inode_lock(inode); + f2fs_balance_fs(F2FS_I_SB(inode), true); - if (f2fs_is_volatile_file(inode)) - goto err_out; + inode_lock(inode); if (f2fs_is_atomic_file(inode)) { - ret = commit_inmem_pages(inode); - if (ret) - goto err_out; + ret = f2fs_commit_atomic_write(inode); + if (!ret) + ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true); - ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true); - if (!ret) { - clear_inode_flag(inode, FI_ATOMIC_FILE); - stat_dec_atomic_write(inode); - } + f2fs_abort_atomic_write(inode, ret); } else { - ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true); + ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 1, false); } -err_out: + inode_unlock(inode); mnt_drop_write_file(filp); return ret; } -static int f2fs_ioc_start_volatile_write(struct file *filp) +static int f2fs_ioc_abort_atomic_write(struct file *filp) { struct inode *inode = file_inode(filp); + struct mnt_idmap *idmap = file_mnt_idmap(filp); int ret; - if (!inode_owner_or_capable(inode)) - return -EACCES; + if (!(filp->f_mode & FMODE_WRITE)) + return -EBADF; - if (!S_ISREG(inode->i_mode)) - return -EINVAL; + if (!inode_owner_or_capable(idmap, inode)) + return -EACCES; ret = mnt_want_write_file(filp); if (ret) @@ -1675,79 +2413,84 @@ static int f2fs_ioc_start_volatile_write(struct file *filp) inode_lock(inode); - if (f2fs_is_volatile_file(inode)) - goto out; - - ret = f2fs_convert_inline_inode(inode); - if (ret) - goto out; - - stat_inc_volatile_write(inode); - stat_update_max_volatile_write(inode); + f2fs_abort_atomic_write(inode, true); - set_inode_flag(inode, FI_VOLATILE_FILE); - f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); -out: inode_unlock(inode); + mnt_drop_write_file(filp); + f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); return ret; } -static int f2fs_ioc_release_volatile_write(struct file *filp) +int f2fs_do_shutdown(struct f2fs_sb_info *sbi, unsigned int flag, + bool readonly, bool need_lock) { - struct inode *inode = file_inode(filp); - int ret; - - if (!inode_owner_or_capable(inode)) - return -EACCES; - - ret = mnt_want_write_file(filp); - if (ret) - return ret; - - inode_lock(inode); + struct super_block *sb = sbi->sb; + int ret = 0; - if (!f2fs_is_volatile_file(inode)) + switch (flag) { + case F2FS_GOING_DOWN_FULLSYNC: + ret = bdev_freeze(sb->s_bdev); + if (ret) + goto out; + f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_SHUTDOWN); + bdev_thaw(sb->s_bdev); + break; + case F2FS_GOING_DOWN_METASYNC: + /* do checkpoint only */ + ret = f2fs_sync_fs(sb, 1); + if (ret) { + if (ret == -EIO) + ret = 0; + goto out; + } + f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_SHUTDOWN); + break; + case F2FS_GOING_DOWN_NOSYNC: + f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_SHUTDOWN); + break; + case F2FS_GOING_DOWN_METAFLUSH: + f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_META_IO); + f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_SHUTDOWN); + break; + case F2FS_GOING_DOWN_NEED_FSCK: + set_sbi_flag(sbi, SBI_NEED_FSCK); + set_sbi_flag(sbi, SBI_CP_DISABLED_QUICK); + set_sbi_flag(sbi, SBI_IS_DIRTY); + /* do checkpoint only */ + ret = f2fs_sync_fs(sb, 1); + if (ret == -EIO) + ret = 0; goto out; - - if (!f2fs_is_first_block_written(inode)) { - ret = truncate_partial_data_page(inode, 0, true); + default: + ret = -EINVAL; goto out; } - ret = punch_hole(inode, 0, F2FS_BLKSIZE); -out: - inode_unlock(inode); - mnt_drop_write_file(filp); - return ret; -} + if (readonly) + goto out; -static int f2fs_ioc_abort_volatile_write(struct file *filp) -{ - struct inode *inode = file_inode(filp); - int ret; + /* + * grab sb->s_umount to avoid racing w/ remount() and other shutdown + * paths. + */ + if (need_lock) + down_write(&sbi->sb->s_umount); - if (!inode_owner_or_capable(inode)) - return -EACCES; + f2fs_stop_gc_thread(sbi); + f2fs_stop_discard_thread(sbi); - ret = mnt_want_write_file(filp); - if (ret) - return ret; + f2fs_drop_discard_cmd(sbi); + clear_opt(sbi, DISCARD); - inode_lock(inode); + if (need_lock) + up_write(&sbi->sb->s_umount); - if (f2fs_is_atomic_file(inode)) - drop_inmem_pages(inode); - if (f2fs_is_volatile_file(inode)) { - clear_inode_flag(inode, FI_VOLATILE_FILE); - stat_dec_volatile_write(inode); - ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true); - } + f2fs_update_time(sbi, REQ_TIME); +out: - inode_unlock(inode); + trace_f2fs_shutdown(sbi, flag, ret); - mnt_drop_write_file(filp); - f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); return ret; } @@ -1755,9 +2498,9 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct super_block *sb = sbi->sb; __u32 in; int ret; + bool need_drop = false, readonly = false; if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -1765,52 +2508,94 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg) if (get_user(in, (__u32 __user *)arg)) return -EFAULT; - ret = mnt_want_write_file(filp); - if (ret) - return ret; + if (in != F2FS_GOING_DOWN_FULLSYNC) { + ret = mnt_want_write_file(filp); + if (ret) { + if (ret != -EROFS) + return ret; - switch (in) { - case F2FS_GOING_DOWN_FULLSYNC: - sb = freeze_bdev(sb->s_bdev); - if (sb && !IS_ERR(sb)) { - f2fs_stop_checkpoint(sbi, false); - thaw_bdev(sb->s_bdev, sb); + /* fallback to nosync shutdown for readonly fs */ + in = F2FS_GOING_DOWN_NOSYNC; + readonly = true; + } else { + need_drop = true; } - break; - case F2FS_GOING_DOWN_METASYNC: - /* do checkpoint only */ - f2fs_sync_fs(sb, 1); - f2fs_stop_checkpoint(sbi, false); - break; - case F2FS_GOING_DOWN_NOSYNC: - f2fs_stop_checkpoint(sbi, false); - break; - case F2FS_GOING_DOWN_METAFLUSH: - sync_meta_pages(sbi, META, LONG_MAX); - f2fs_stop_checkpoint(sbi, false); - break; - default: - ret = -EINVAL; - goto out; } - f2fs_update_time(sbi, REQ_TIME); -out: - mnt_drop_write_file(filp); + + ret = f2fs_do_shutdown(sbi, in, readonly, true); + + if (need_drop) + mnt_drop_write_file(filp); + + return ret; +} + +static int f2fs_keep_noreuse_range(struct inode *inode, + loff_t offset, loff_t len) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + u64 max_bytes = F2FS_BLK_TO_BYTES(max_file_blocks(inode)); + u64 start, end; + int ret = 0; + + if (!S_ISREG(inode->i_mode)) + return 0; + + if (offset >= max_bytes || len > max_bytes || + (offset + len) > max_bytes) + return 0; + + start = offset >> PAGE_SHIFT; + end = DIV_ROUND_UP(offset + len, PAGE_SIZE); + + inode_lock(inode); + if (f2fs_is_atomic_file(inode)) { + inode_unlock(inode); + return 0; + } + + spin_lock(&sbi->inode_lock[DONATE_INODE]); + /* let's remove the range, if len = 0 */ + if (!len) { + if (!list_empty(&F2FS_I(inode)->gdonate_list)) { + list_del_init(&F2FS_I(inode)->gdonate_list); + sbi->donate_files--; + if (is_inode_flag_set(inode, FI_DONATE_FINISHED)) + ret = -EALREADY; + else + set_inode_flag(inode, FI_DONATE_FINISHED); + } else + ret = -ENOENT; + } else { + if (list_empty(&F2FS_I(inode)->gdonate_list)) { + list_add_tail(&F2FS_I(inode)->gdonate_list, + &sbi->inode_list[DONATE_INODE]); + sbi->donate_files++; + } else { + list_move_tail(&F2FS_I(inode)->gdonate_list, + &sbi->inode_list[DONATE_INODE]); + } + F2FS_I(inode)->donate_start = start; + F2FS_I(inode)->donate_end = end - 1; + clear_inode_flag(inode, FI_DONATE_FINISHED); + } + spin_unlock(&sbi->inode_lock[DONATE_INODE]); + inode_unlock(inode); + return ret; } static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); - struct super_block *sb = inode->i_sb; - struct request_queue *q = bdev_get_queue(sb->s_bdev); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct fstrim_range range; int ret; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!blk_queue_discard(q)) + if (!f2fs_hw_support_discard(sbi)) return -EOPNOTSUPP; if (copy_from_user(&range, (struct fstrim_range __user *)arg, @@ -1821,9 +2606,9 @@ static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg) if (ret) return ret; - range.minlen = max((unsigned int)range.minlen, - q->limits.discard_granularity); - ret = f2fs_trim_fs(F2FS_SB(sb), &range); + range.minlen = max_t(unsigned int, range.minlen, + f2fs_hw_discard_granularity(sbi)); + ret = f2fs_trim_fs(sbi, &range); mnt_drop_write_file(filp); if (ret < 0) return ret; @@ -1831,7 +2616,7 @@ static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg) if (copy_to_user((struct fstrim_range __user *)arg, &range, sizeof(range))) return -EFAULT; - f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); + f2fs_update_time(sbi, REQ_TIME); return 0; } @@ -1848,14 +2633,20 @@ static bool uuid_is_nonzero(__u8 u[16]) static int f2fs_ioc_set_encryption_policy(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); + int ret; - f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); + if (!f2fs_sb_has_encrypt(F2FS_I_SB(inode))) + return -EOPNOTSUPP; - return fscrypt_ioctl_set_policy(filp, (const void __user *)arg); + ret = fscrypt_ioctl_set_policy(filp, (const void __user *)arg); + f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); + return ret; } static int f2fs_ioc_get_encryption_policy(struct file *filp, unsigned long arg) { + if (!f2fs_sb_has_encrypt(F2FS_I_SB(file_inode(filp)))) + return -EOPNOTSUPP; return fscrypt_ioctl_get_policy(filp, (void __user *)arg); } @@ -1863,18 +2654,21 @@ static int f2fs_ioc_get_encryption_pwsalt(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + u8 encrypt_pw_salt[16]; int err; - if (!f2fs_sb_has_crypto(inode->i_sb)) + if (!f2fs_sb_has_encrypt(sbi)) return -EOPNOTSUPP; - if (uuid_is_nonzero(sbi->raw_super->encrypt_pw_salt)) - goto got_it; - err = mnt_want_write_file(filp); if (err) return err; + f2fs_down_write(&sbi->sb_lock); + + if (uuid_is_nonzero(sbi->raw_super->encrypt_pw_salt)) + goto got_it; + /* update superblock with uuid */ generate_random_uuid(sbi->raw_super->encrypt_pw_salt); @@ -1882,21 +2676,79 @@ static int f2fs_ioc_get_encryption_pwsalt(struct file *filp, unsigned long arg) if (err) { /* undo new data */ memset(sbi->raw_super->encrypt_pw_salt, 0, 16); - mnt_drop_write_file(filp); - return err; + goto out_err; } - mnt_drop_write_file(filp); got_it: - if (copy_to_user((__u8 __user *)arg, sbi->raw_super->encrypt_pw_salt, - 16)) - return -EFAULT; - return 0; + memcpy(encrypt_pw_salt, sbi->raw_super->encrypt_pw_salt, 16); +out_err: + f2fs_up_write(&sbi->sb_lock); + mnt_drop_write_file(filp); + + if (!err && copy_to_user((__u8 __user *)arg, encrypt_pw_salt, 16)) + err = -EFAULT; + + return err; +} + +static int f2fs_ioc_get_encryption_policy_ex(struct file *filp, + unsigned long arg) +{ + if (!f2fs_sb_has_encrypt(F2FS_I_SB(file_inode(filp)))) + return -EOPNOTSUPP; + + return fscrypt_ioctl_get_policy_ex(filp, (void __user *)arg); +} + +static int f2fs_ioc_add_encryption_key(struct file *filp, unsigned long arg) +{ + if (!f2fs_sb_has_encrypt(F2FS_I_SB(file_inode(filp)))) + return -EOPNOTSUPP; + + return fscrypt_ioctl_add_key(filp, (void __user *)arg); +} + +static int f2fs_ioc_remove_encryption_key(struct file *filp, unsigned long arg) +{ + if (!f2fs_sb_has_encrypt(F2FS_I_SB(file_inode(filp)))) + return -EOPNOTSUPP; + + return fscrypt_ioctl_remove_key(filp, (void __user *)arg); +} + +static int f2fs_ioc_remove_encryption_key_all_users(struct file *filp, + unsigned long arg) +{ + if (!f2fs_sb_has_encrypt(F2FS_I_SB(file_inode(filp)))) + return -EOPNOTSUPP; + + return fscrypt_ioctl_remove_key_all_users(filp, (void __user *)arg); +} + +static int f2fs_ioc_get_encryption_key_status(struct file *filp, + unsigned long arg) +{ + if (!f2fs_sb_has_encrypt(F2FS_I_SB(file_inode(filp)))) + return -EOPNOTSUPP; + + return fscrypt_ioctl_get_key_status(filp, (void __user *)arg); +} + +static int f2fs_ioc_get_encryption_nonce(struct file *filp, unsigned long arg) +{ + if (!f2fs_sb_has_encrypt(F2FS_I_SB(file_inode(filp)))) + return -EOPNOTSUPP; + + return fscrypt_ioctl_get_nonce(filp, (void __user *)arg); } static int f2fs_ioc_gc(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct f2fs_gc_control gc_control = { .victim_segno = NULL_SEGNO, + .no_bg_gc = false, + .should_migrate_blocks = false, + .nr_free_secs = 0 }; __u32 sync; int ret; @@ -1914,65 +2766,86 @@ static int f2fs_ioc_gc(struct file *filp, unsigned long arg) return ret; if (!sync) { - if (!mutex_trylock(&sbi->gc_mutex)) { + if (!f2fs_down_write_trylock(&sbi->gc_lock)) { ret = -EBUSY; goto out; } } else { - mutex_lock(&sbi->gc_mutex); + f2fs_down_write(&sbi->gc_lock); } - ret = f2fs_gc(sbi, sync, true, NULL_SEGNO); + gc_control.init_gc_type = sync ? FG_GC : BG_GC; + gc_control.err_gc_skipped = sync; + stat_inc_gc_call_count(sbi, FOREGROUND); + ret = f2fs_gc(sbi, &gc_control); out: mnt_drop_write_file(filp); return ret; } -static int f2fs_ioc_gc_range(struct file *filp, unsigned long arg) +static int __f2fs_ioc_gc_range(struct file *filp, struct f2fs_gc_range *range) { - struct inode *inode = file_inode(filp); - struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct f2fs_gc_range range; + struct f2fs_sb_info *sbi = F2FS_I_SB(file_inode(filp)); + struct f2fs_gc_control gc_control = { + .init_gc_type = range->sync ? FG_GC : BG_GC, + .no_bg_gc = false, + .should_migrate_blocks = false, + .err_gc_skipped = range->sync, + .nr_free_secs = 0 }; u64 end; int ret; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - - if (copy_from_user(&range, (struct f2fs_gc_range __user *)arg, - sizeof(range))) - return -EFAULT; - if (f2fs_readonly(sbi->sb)) return -EROFS; + end = range->start + range->len; + if (end < range->start || range->start < MAIN_BLKADDR(sbi) || + end >= MAX_BLKADDR(sbi)) + return -EINVAL; + ret = mnt_want_write_file(filp); if (ret) return ret; - end = range.start + range.len; - if (range.start < MAIN_BLKADDR(sbi) || end >= MAX_BLKADDR(sbi)) - return -EINVAL; do_more: - if (!range.sync) { - if (!mutex_trylock(&sbi->gc_mutex)) { + if (!range->sync) { + if (!f2fs_down_write_trylock(&sbi->gc_lock)) { ret = -EBUSY; goto out; } } else { - mutex_lock(&sbi->gc_mutex); + f2fs_down_write(&sbi->gc_lock); } - ret = f2fs_gc(sbi, range.sync, true, GET_SEGNO(sbi, range.start)); - range.start += sbi->blocks_per_seg; - if (range.start <= end) + gc_control.victim_segno = GET_SEGNO(sbi, range->start); + stat_inc_gc_call_count(sbi, FOREGROUND); + ret = f2fs_gc(sbi, &gc_control); + if (ret) { + if (ret == -EBUSY) + ret = -EAGAIN; + goto out; + } + range->start += CAP_BLKS_PER_SEC(sbi); + if (range->start <= end) goto do_more; out: mnt_drop_write_file(filp); return ret; } -static int f2fs_ioc_write_checkpoint(struct file *filp, unsigned long arg) +static int f2fs_ioc_gc_range(struct file *filp, unsigned long arg) +{ + struct f2fs_gc_range range; + + if (copy_from_user(&range, (struct f2fs_gc_range __user *)arg, + sizeof(range))) + return -EFAULT; + return __f2fs_ioc_gc_range(filp, &range); +} + +static int f2fs_ioc_write_checkpoint(struct file *filp) { struct inode *inode = file_inode(filp); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); @@ -1984,6 +2857,11 @@ static int f2fs_ioc_write_checkpoint(struct file *filp, unsigned long arg) if (f2fs_readonly(sbi->sb)) return -EROFS; + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) { + f2fs_info(sbi, "Skipping Checkpoint. Checkpoints currently disabled."); + return -EINVAL; + } + ret = mnt_want_write_file(filp); if (ret) return ret; @@ -1999,29 +2877,41 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi, struct f2fs_defragment *range) { struct inode *inode = file_inode(filp); - struct f2fs_map_blocks map = { .m_next_pgofs = NULL }; - struct extent_info ei = {0,0,0}; - pgoff_t pg_start, pg_end; - unsigned int blk_per_seg = sbi->blocks_per_seg; + struct f2fs_map_blocks map = { .m_next_extent = NULL, + .m_seg_type = NO_CHECK_TYPE, + .m_may_create = false }; + struct extent_info ei = {}; + pgoff_t pg_start, pg_end, next_pgofs; unsigned int total = 0, sec_num; block_t blk_end = 0; bool fragmented = false; int err; - /* if in-place-update policy is enabled, don't waste time here */ - if (need_inplace_update_policy(inode, NULL)) - return -EINVAL; + f2fs_balance_fs(sbi, true); + inode_lock(inode); pg_start = range->start >> PAGE_SHIFT; - pg_end = (range->start + range->len) >> PAGE_SHIFT; + pg_end = min_t(pgoff_t, + (range->start + range->len) >> PAGE_SHIFT, + DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE)); - f2fs_balance_fs(sbi, true); + if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED) || + f2fs_is_atomic_file(inode)) { + err = -EINVAL; + goto unlock_out; + } - inode_lock(inode); + /* if in-place-update policy is enabled, don't waste time here */ + set_inode_flag(inode, FI_OPU_WRITE); + if (f2fs_should_update_inplace(inode, NULL)) { + err = -EINVAL; + goto out; + } /* writeback all dirty pages in the range */ - err = filemap_write_and_wait_range(inode->i_mapping, range->start, - range->start + range->len - 1); + err = filemap_write_and_wait_range(inode->i_mapping, + pg_start << PAGE_SHIFT, + (pg_end << PAGE_SHIFT) - 1); if (err) goto out; @@ -2029,12 +2919,13 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi, * lookup mapping info in extent cache, skip defragmenting if physical * block addresses are continuous. */ - if (f2fs_lookup_extent_cache(inode, pg_start, &ei)) { - if (ei.fofs + ei.len >= pg_end) + if (f2fs_lookup_read_extent_cache(inode, pg_start, &ei)) { + if ((pgoff_t)ei.fofs + ei.len >= pg_end) goto out; } map.m_lblk = pg_start; + map.m_next_pgofs = &next_pgofs; /* * lookup mapping info in dnode page cache, skip defragmenting if all @@ -2043,31 +2934,32 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi, */ while (map.m_lblk < pg_end) { map.m_len = pg_end - map.m_lblk; - err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_READ); + err = f2fs_map_blocks(inode, &map, F2FS_GET_BLOCK_DEFAULT); if (err) goto out; if (!(map.m_flags & F2FS_MAP_FLAGS)) { - map.m_lblk++; + map.m_lblk = next_pgofs; continue; } - if (blk_end && blk_end != map.m_pblk) { + if (blk_end && blk_end != map.m_pblk) fragmented = true; - break; - } + + /* record total count of block that we're going to move */ + total += map.m_len; + blk_end = map.m_pblk + map.m_len; map.m_lblk += map.m_len; } - if (!fragmented) + if (!fragmented) { + total = 0; goto out; + } - map.m_lblk = pg_start; - map.m_len = pg_end - pg_start; - - sec_num = (map.m_len + BLKS_PER_SEC(sbi) - 1) / BLKS_PER_SEC(sbi); + sec_num = DIV_ROUND_UP(total, CAP_BLKS_PER_SEC(sbi)); /* * make sure there are enough free section for LFS allocation, this can @@ -2079,35 +2971,43 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi, goto out; } + map.m_lblk = pg_start; + map.m_len = pg_end - pg_start; + total = 0; + while (map.m_lblk < pg_end) { pgoff_t idx; int cnt = 0; do_map: map.m_len = pg_end - map.m_lblk; - err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_READ); + err = f2fs_map_blocks(inode, &map, F2FS_GET_BLOCK_DEFAULT); if (err) goto clear_out; if (!(map.m_flags & F2FS_MAP_FLAGS)) { - map.m_lblk++; - continue; + map.m_lblk = next_pgofs; + goto check; } - set_inode_flag(inode, FI_DO_DEFRAG); + set_inode_flag(inode, FI_SKIP_WRITES); idx = map.m_lblk; - while (idx < map.m_lblk + map.m_len && cnt < blk_per_seg) { - struct page *page; + while (idx < map.m_lblk + map.m_len && + cnt < BLKS_PER_SEG(sbi)) { + struct folio *folio; - page = get_lock_data_page(inode, idx, true); - if (IS_ERR(page)) { - err = PTR_ERR(page); + folio = f2fs_get_lock_data_folio(inode, idx, true); + if (IS_ERR(folio)) { + err = PTR_ERR(folio); goto clear_out; } - set_page_dirty(page); - f2fs_put_page(page, 1); + f2fs_folio_wait_writeback(folio, DATA, true, true); + + folio_mark_dirty(folio); + folio_set_f2fs_gcing(folio); + f2fs_folio_put(folio, true); idx++; cnt++; @@ -2115,19 +3015,21 @@ do_map: } map.m_lblk = idx; - - if (idx < pg_end && cnt < blk_per_seg) +check: + if (map.m_lblk < pg_end && cnt < BLKS_PER_SEG(sbi)) goto do_map; - clear_inode_flag(inode, FI_DO_DEFRAG); + clear_inode_flag(inode, FI_SKIP_WRITES); err = filemap_fdatawrite(inode->i_mapping); if (err) goto out; } clear_out: - clear_inode_flag(inode, FI_DO_DEFRAG); + clear_inode_flag(inode, FI_SKIP_WRITES); out: + clear_inode_flag(inode, FI_OPU_WRITE); +unlock_out: inode_unlock(inode); if (!err) range->len = (u64)total << PAGE_SHIFT; @@ -2144,7 +3046,7 @@ static int f2fs_ioc_defragment(struct file *filp, unsigned long arg) if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!S_ISREG(inode->i_mode) || f2fs_is_atomic_file(inode)) + if (!S_ISREG(inode->i_mode)) return -EINVAL; if (f2fs_readonly(sbi->sb)) @@ -2159,7 +3061,7 @@ static int f2fs_ioc_defragment(struct file *filp, unsigned long arg) return -EINVAL; if (unlikely((range.start + range.len) >> PAGE_SHIFT > - sbi->max_file_blocks)) + max_file_blocks(inode))) return -EINVAL; err = mnt_want_write_file(filp); @@ -2169,7 +3071,8 @@ static int f2fs_ioc_defragment(struct file *filp, unsigned long arg) err = f2fs_defragment_range(sbi, filp, &range); mnt_drop_write_file(filp); - f2fs_update_time(sbi, REQ_TIME); + if (range.len) + f2fs_update_time(sbi, REQ_TIME); if (err < 0) return err; @@ -2200,9 +3103,12 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in, if (!S_ISREG(src->i_mode) || !S_ISREG(dst->i_mode)) return -EINVAL; - if (f2fs_encrypted_inode(src) || f2fs_encrypted_inode(dst)) + if (IS_ENCRYPTED(src) || IS_ENCRYPTED(dst)) return -EOPNOTSUPP; + if (pos_out < 0 || pos_in < 0) + return -EINVAL; + if (src == dst) { if (pos_in == pos_out) return 0; @@ -2212,10 +3118,20 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in, inode_lock(src); if (src != dst) { - if (!inode_trylock(dst)) { - ret = -EBUSY; + ret = -EBUSY; + if (!inode_trylock(dst)) goto out; - } + } + + if (f2fs_compressed_file(src) || f2fs_compressed_file(dst) || + f2fs_is_pinned_file(src) || f2fs_is_pinned_file(dst)) { + ret = -EOPNOTSUPP; + goto out_unlock; + } + + if (f2fs_is_atomic_file(src) || f2fs_is_atomic_file(dst)) { + ret = -EINVAL; + goto out_unlock; } ret = -EINVAL; @@ -2260,10 +3176,18 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in, goto out_unlock; f2fs_balance_fs(sbi, true); + + f2fs_down_write(&F2FS_I(src)->i_gc_rwsem[WRITE]); + if (src != dst) { + ret = -EBUSY; + if (!f2fs_down_write_trylock(&F2FS_I(dst)->i_gc_rwsem[WRITE])) + goto out_src; + } + f2fs_lock_op(sbi); - ret = __exchange_data_block(src, dst, pos_in >> F2FS_BLKSIZE_BITS, - pos_out >> F2FS_BLKSIZE_BITS, - len >> F2FS_BLKSIZE_BITS, false); + ret = __exchange_data_block(src, dst, F2FS_BYTES_TO_BLK(pos_in), + F2FS_BYTES_TO_BLK(pos_out), + F2FS_BYTES_TO_BLK(len), false); if (!ret) { if (dst_max_i_size) @@ -2272,6 +3196,22 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in, f2fs_i_size_write(dst, dst_osize); } f2fs_unlock_op(sbi); + + if (src != dst) + f2fs_up_write(&F2FS_I(dst)->i_gc_rwsem[WRITE]); +out_src: + f2fs_up_write(&F2FS_I(src)->i_gc_rwsem[WRITE]); + if (ret) + goto out_unlock; + + inode_set_mtime_to_ts(src, inode_set_ctime_current(src)); + f2fs_mark_inode_dirty_sync(src, false); + if (src != dst) { + inode_set_mtime_to_ts(dst, inode_set_ctime_current(dst)); + f2fs_mark_inode_dirty_sync(dst, false); + } + f2fs_update_time(sbi, REQ_TIME); + out_unlock: if (src != dst) inode_unlock(dst); @@ -2280,48 +3220,43 @@ out: return ret; } -static int f2fs_ioc_move_range(struct file *filp, unsigned long arg) +static int __f2fs_ioc_move_range(struct file *filp, + struct f2fs_move_range *range) { - struct f2fs_move_range range; - struct fd dst; int err; if (!(filp->f_mode & FMODE_READ) || !(filp->f_mode & FMODE_WRITE)) return -EBADF; - if (copy_from_user(&range, (struct f2fs_move_range __user *)arg, - sizeof(range))) - return -EFAULT; - - dst = fdget(range.dst_fd); - if (!dst.file) + CLASS(fd, dst)(range->dst_fd); + if (fd_empty(dst)) return -EBADF; - if (!(dst.file->f_mode & FMODE_WRITE)) { - err = -EBADF; - goto err_out; - } + if (!(fd_file(dst)->f_mode & FMODE_WRITE)) + return -EBADF; err = mnt_want_write_file(filp); if (err) - goto err_out; + return err; - err = f2fs_move_file_range(filp, range.pos_in, dst.file, - range.pos_out, range.len); + err = f2fs_move_file_range(filp, range->pos_in, fd_file(dst), + range->pos_out, range->len); mnt_drop_write_file(filp); - if (err) - goto err_out; - - if (copy_to_user((struct f2fs_move_range __user *)arg, - &range, sizeof(range))) - err = -EFAULT; -err_out: - fdput(dst); return err; } +static int f2fs_ioc_move_range(struct file *filp, unsigned long arg) +{ + struct f2fs_move_range range; + + if (copy_from_user(&range, (struct f2fs_move_range __user *)arg, + sizeof(range))) + return -EFAULT; + return __f2fs_ioc_move_range(filp, &range); +} + static int f2fs_ioc_flush_device(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); @@ -2330,6 +3265,11 @@ static int f2fs_ioc_flush_device(struct file *filp, unsigned long arg) unsigned int start_segno = 0, end_segno = 0; unsigned int dev_start_segno = 0, dev_end_segno = 0; struct f2fs_flush_device range; + struct f2fs_gc_control gc_control = { + .init_gc_type = FG_GC, + .should_migrate_blocks = true, + .err_gc_skipped = true, + .nr_free_secs = 0 }; int ret; if (!capable(CAP_SYS_ADMIN)) @@ -2338,16 +3278,17 @@ static int f2fs_ioc_flush_device(struct file *filp, unsigned long arg) if (f2fs_readonly(sbi->sb)) return -EROFS; + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) + return -EINVAL; + if (copy_from_user(&range, (struct f2fs_flush_device __user *)arg, sizeof(range))) return -EFAULT; - if (sbi->s_ndevs <= 1 || sbi->s_ndevs - 1 <= range.dev_num || - sbi->segs_per_sec != 1) { - f2fs_msg(sbi->sb, KERN_WARNING, - "Can't flush %u in %d for segs_per_sec %u != 1\n", - range.dev_num, sbi->s_ndevs, - sbi->segs_per_sec); + if (!f2fs_is_multi_device(sbi) || sbi->s_ndevs - 1 <= range.dev_num || + __is_large_section(sbi)) { + f2fs_warn(sbi, "Can't flush %u in %d for SEGS_PER_SEC %u != 1", + range.dev_num, sbi->s_ndevs, SEGS_PER_SEC(sbi)); return -EINVAL; } @@ -2365,14 +3306,17 @@ static int f2fs_ioc_flush_device(struct file *filp, unsigned long arg) end_segno = min(start_segno + range.segments, dev_end_segno); while (start_segno < end_segno) { - if (!mutex_trylock(&sbi->gc_mutex)) { + if (!f2fs_down_write_trylock(&sbi->gc_lock)) { ret = -EBUSY; goto out; } sm->last_victim[GC_CB] = end_segno + 1; sm->last_victim[GC_GREEDY] = end_segno + 1; sm->last_victim[ALLOC_NEXT] = end_segno + 1; - ret = f2fs_gc(sbi, true, true, start_segno); + + gc_control.victim_segno = start_segno; + stat_inc_gc_call_count(sbi, FOREGROUND); + ret = f2fs_gc(sbi, &gc_control); if (ret == -EAGAIN) ret = 0; else if (ret < 0) @@ -2384,134 +3328,2133 @@ out: return ret; } +static int f2fs_ioc_get_features(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + u32 sb_feature = le32_to_cpu(F2FS_I_SB(inode)->raw_super->feature); + + /* Must validate to set it with SQLite behavior in Android. */ + sb_feature |= F2FS_FEATURE_ATOMIC_WRITE; -long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) + return put_user(sb_feature, (u32 __user *)arg); +} + +#ifdef CONFIG_QUOTA +int f2fs_transfer_project_quota(struct inode *inode, kprojid_t kprojid) +{ + struct dquot *transfer_to[MAXQUOTAS] = {}; + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct super_block *sb = sbi->sb; + int err; + + transfer_to[PRJQUOTA] = dqget(sb, make_kqid_projid(kprojid)); + if (IS_ERR(transfer_to[PRJQUOTA])) + return PTR_ERR(transfer_to[PRJQUOTA]); + + err = __dquot_transfer(inode, transfer_to); + if (err) + set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR); + dqput(transfer_to[PRJQUOTA]); + return err; +} + +static int f2fs_ioc_setproject(struct inode *inode, __u32 projid) +{ + struct f2fs_inode_info *fi = F2FS_I(inode); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct f2fs_inode *ri = NULL; + kprojid_t kprojid; + int err; + + if (!f2fs_sb_has_project_quota(sbi)) { + if (projid != F2FS_DEF_PROJID) + return -EOPNOTSUPP; + else + return 0; + } + + if (!f2fs_has_extra_attr(inode)) + return -EOPNOTSUPP; + + kprojid = make_kprojid(&init_user_ns, (projid_t)projid); + + if (projid_eq(kprojid, fi->i_projid)) + return 0; + + err = -EPERM; + /* Is it quota file? Do not allow user to mess with it */ + if (IS_NOQUOTA(inode)) + return err; + + if (!F2FS_FITS_IN_INODE(ri, fi->i_extra_isize, i_projid)) + return -EOVERFLOW; + + err = f2fs_dquot_initialize(inode); + if (err) + return err; + + f2fs_lock_op(sbi); + err = f2fs_transfer_project_quota(inode, kprojid); + if (err) + goto out_unlock; + + fi->i_projid = kprojid; + inode_set_ctime_current(inode); + f2fs_mark_inode_dirty_sync(inode, true); +out_unlock: + f2fs_unlock_op(sbi); + return err; +} +#else +int f2fs_transfer_project_quota(struct inode *inode, kprojid_t kprojid) +{ + return 0; +} + +static int f2fs_ioc_setproject(struct inode *inode, __u32 projid) +{ + if (projid != F2FS_DEF_PROJID) + return -EOPNOTSUPP; + return 0; +} +#endif + +int f2fs_fileattr_get(struct dentry *dentry, struct file_kattr *fa) +{ + struct inode *inode = d_inode(dentry); + struct f2fs_inode_info *fi = F2FS_I(inode); + u32 fsflags = f2fs_iflags_to_fsflags(fi->i_flags); + + if (IS_ENCRYPTED(inode)) + fsflags |= FS_ENCRYPT_FL; + if (IS_VERITY(inode)) + fsflags |= FS_VERITY_FL; + if (f2fs_has_inline_data(inode) || f2fs_has_inline_dentry(inode)) + fsflags |= FS_INLINE_DATA_FL; + if (is_inode_flag_set(inode, FI_PIN_FILE)) + fsflags |= FS_NOCOW_FL; + + fileattr_fill_flags(fa, fsflags & F2FS_GETTABLE_FS_FL); + + if (f2fs_sb_has_project_quota(F2FS_I_SB(inode))) + fa->fsx_projid = from_kprojid(&init_user_ns, fi->i_projid); + + return 0; +} + +int f2fs_fileattr_set(struct mnt_idmap *idmap, + struct dentry *dentry, struct file_kattr *fa) +{ + struct inode *inode = d_inode(dentry); + u32 fsflags = fa->flags, mask = F2FS_SETTABLE_FS_FL; + u32 iflags; + int err; + + if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) + return -EIO; + if (!f2fs_is_checkpoint_ready(F2FS_I_SB(inode))) + return -ENOSPC; + if (fsflags & ~F2FS_GETTABLE_FS_FL) + return -EOPNOTSUPP; + fsflags &= F2FS_SETTABLE_FS_FL; + if (!fa->flags_valid) + mask &= FS_COMMON_FL; + + iflags = f2fs_fsflags_to_iflags(fsflags); + if (f2fs_mask_flags(inode->i_mode, iflags) != iflags) + return -EOPNOTSUPP; + + err = f2fs_setflags_common(inode, iflags, f2fs_fsflags_to_iflags(mask)); + if (!err) + err = f2fs_ioc_setproject(inode, fa->fsx_projid); + + return err; +} + +int f2fs_pin_file_control(struct inode *inode, bool inc) +{ + struct f2fs_inode_info *fi = F2FS_I(inode); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + + if (IS_DEVICE_ALIASING(inode)) + return -EINVAL; + + if (fi->i_gc_failures >= sbi->gc_pin_file_threshold) { + f2fs_warn(sbi, "%s: Enable GC = ino %lx after %x GC trials", + __func__, inode->i_ino, fi->i_gc_failures); + clear_inode_flag(inode, FI_PIN_FILE); + return -EAGAIN; + } + + /* Use i_gc_failures for normal file as a risk signal. */ + if (inc) + f2fs_i_gc_failures_write(inode, fi->i_gc_failures + 1); + + return 0; +} + +static int f2fs_ioc_set_pin_file(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + __u32 pin; + int ret = 0; + + if (get_user(pin, (__u32 __user *)arg)) + return -EFAULT; + + if (!S_ISREG(inode->i_mode)) + return -EINVAL; + + if (f2fs_readonly(sbi->sb)) + return -EROFS; + + if (!pin && IS_DEVICE_ALIASING(inode)) + return -EOPNOTSUPP; + + ret = mnt_want_write_file(filp); + if (ret) + return ret; + + inode_lock(inode); + + if (f2fs_is_atomic_file(inode)) { + ret = -EINVAL; + goto out; + } + + if (!pin) { + clear_inode_flag(inode, FI_PIN_FILE); + f2fs_i_gc_failures_write(inode, 0); + goto done; + } else if (f2fs_is_pinned_file(inode)) { + goto done; + } + + if (F2FS_HAS_BLOCKS(inode)) { + ret = -EFBIG; + goto out; + } + + /* Let's allow file pinning on zoned device. */ + if (!f2fs_sb_has_blkzoned(sbi) && + f2fs_should_update_outplace(inode, NULL)) { + ret = -EINVAL; + goto out; + } + + if (f2fs_pin_file_control(inode, false)) { + ret = -EAGAIN; + goto out; + } + + ret = f2fs_convert_inline_inode(inode); + if (ret) + goto out; + + if (!f2fs_disable_compressed_file(inode)) { + ret = -EOPNOTSUPP; + goto out; + } + + set_inode_flag(inode, FI_PIN_FILE); + ret = F2FS_I(inode)->i_gc_failures; +done: + f2fs_update_time(sbi, REQ_TIME); +out: + inode_unlock(inode); + mnt_drop_write_file(filp); + return ret; +} + +static int f2fs_ioc_get_pin_file(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + __u32 pin = 0; + + if (is_inode_flag_set(inode, FI_PIN_FILE)) + pin = F2FS_I(inode)->i_gc_failures; + return put_user(pin, (u32 __user *)arg); +} + +static int f2fs_ioc_get_dev_alias_file(struct file *filp, unsigned long arg) +{ + return put_user(IS_DEVICE_ALIASING(file_inode(filp)) ? 1 : 0, + (u32 __user *)arg); +} + +static int f2fs_ioc_io_prio(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + __u32 level; + + if (get_user(level, (__u32 __user *)arg)) + return -EFAULT; + + if (!S_ISREG(inode->i_mode) || level >= F2FS_IOPRIO_MAX) + return -EINVAL; + + inode_lock(inode); + F2FS_I(inode)->ioprio_hint = level; + inode_unlock(inode); + return 0; +} + +int f2fs_precache_extents(struct inode *inode) +{ + struct f2fs_inode_info *fi = F2FS_I(inode); + struct f2fs_map_blocks map; + pgoff_t m_next_extent; + loff_t end; + int err; + + if (is_inode_flag_set(inode, FI_NO_EXTENT)) + return -EOPNOTSUPP; + + map.m_lblk = 0; + map.m_pblk = 0; + map.m_next_pgofs = NULL; + map.m_next_extent = &m_next_extent; + map.m_seg_type = NO_CHECK_TYPE; + map.m_may_create = false; + end = F2FS_BLK_ALIGN(i_size_read(inode)); + + while (map.m_lblk < end) { + map.m_len = end - map.m_lblk; + + f2fs_down_write(&fi->i_gc_rwsem[WRITE]); + err = f2fs_map_blocks(inode, &map, F2FS_GET_BLOCK_PRECACHE); + f2fs_up_write(&fi->i_gc_rwsem[WRITE]); + if (err || !map.m_len) + return err; + + map.m_lblk = m_next_extent; + } + + return 0; +} + +static int f2fs_ioc_precache_extents(struct file *filp) +{ + return f2fs_precache_extents(file_inode(filp)); +} + +static int f2fs_ioc_resize_fs(struct file *filp, unsigned long arg) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(file_inode(filp)); + __u64 block_count; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (f2fs_readonly(sbi->sb)) + return -EROFS; + + if (copy_from_user(&block_count, (void __user *)arg, + sizeof(block_count))) + return -EFAULT; + + return f2fs_resize_fs(filp, block_count); +} + +static int f2fs_ioc_enable_verity(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + + f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); + + if (!f2fs_sb_has_verity(F2FS_I_SB(inode))) { + f2fs_warn(F2FS_I_SB(inode), + "Can't enable fs-verity on inode %lu: the verity feature is not enabled on this filesystem", + inode->i_ino); + return -EOPNOTSUPP; + } + + return fsverity_ioctl_enable(filp, (const void __user *)arg); +} + +static int f2fs_ioc_measure_verity(struct file *filp, unsigned long arg) +{ + if (!f2fs_sb_has_verity(F2FS_I_SB(file_inode(filp)))) + return -EOPNOTSUPP; + + return fsverity_ioctl_measure(filp, (void __user *)arg); +} + +static int f2fs_ioc_read_verity_metadata(struct file *filp, unsigned long arg) +{ + if (!f2fs_sb_has_verity(F2FS_I_SB(file_inode(filp)))) + return -EOPNOTSUPP; + + return fsverity_ioctl_read_metadata(filp, (const void __user *)arg); +} + +static int f2fs_ioc_getfslabel(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + char *vbuf; + int count; + int err = 0; + + vbuf = f2fs_kzalloc(sbi, MAX_VOLUME_NAME, GFP_KERNEL); + if (!vbuf) + return -ENOMEM; + + f2fs_down_read(&sbi->sb_lock); + count = utf16s_to_utf8s(sbi->raw_super->volume_name, + ARRAY_SIZE(sbi->raw_super->volume_name), + UTF16_LITTLE_ENDIAN, vbuf, MAX_VOLUME_NAME); + f2fs_up_read(&sbi->sb_lock); + + if (copy_to_user((char __user *)arg, vbuf, + min(FSLABEL_MAX, count))) + err = -EFAULT; + + kfree(vbuf); + return err; +} + +static int f2fs_ioc_setfslabel(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + char *vbuf; + int err = 0; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + vbuf = strndup_user((const char __user *)arg, FSLABEL_MAX); + if (IS_ERR(vbuf)) + return PTR_ERR(vbuf); + + err = mnt_want_write_file(filp); + if (err) + goto out; + + f2fs_down_write(&sbi->sb_lock); + + memset(sbi->raw_super->volume_name, 0, + sizeof(sbi->raw_super->volume_name)); + utf8s_to_utf16s(vbuf, strlen(vbuf), UTF16_LITTLE_ENDIAN, + sbi->raw_super->volume_name, + ARRAY_SIZE(sbi->raw_super->volume_name)); + + err = f2fs_commit_super(sbi, false); + + f2fs_up_write(&sbi->sb_lock); + + mnt_drop_write_file(filp); +out: + kfree(vbuf); + return err; +} + +static int f2fs_get_compress_blocks(struct inode *inode, __u64 *blocks) +{ + if (!f2fs_sb_has_compression(F2FS_I_SB(inode))) + return -EOPNOTSUPP; + + if (!f2fs_compressed_file(inode)) + return -EINVAL; + + *blocks = atomic_read(&F2FS_I(inode)->i_compr_blocks); + + return 0; +} + +static int f2fs_ioc_get_compress_blocks(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + __u64 blocks; + int ret; + + ret = f2fs_get_compress_blocks(inode, &blocks); + if (ret < 0) + return ret; + + return put_user(blocks, (u64 __user *)arg); +} + +static int release_compress_blocks(struct dnode_of_data *dn, pgoff_t count) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); + unsigned int released_blocks = 0; + int cluster_size = F2FS_I(dn->inode)->i_cluster_size; + block_t blkaddr; + int i; + + for (i = 0; i < count; i++) { + blkaddr = data_blkaddr(dn->inode, dn->node_folio, + dn->ofs_in_node + i); + + if (!__is_valid_data_blkaddr(blkaddr)) + continue; + if (unlikely(!f2fs_is_valid_blkaddr(sbi, blkaddr, + DATA_GENERIC_ENHANCE))) + return -EFSCORRUPTED; + } + + while (count) { + int compr_blocks = 0; + + for (i = 0; i < cluster_size; i++, dn->ofs_in_node++) { + blkaddr = f2fs_data_blkaddr(dn); + + if (i == 0) { + if (blkaddr == COMPRESS_ADDR) + continue; + dn->ofs_in_node += cluster_size; + goto next; + } + + if (__is_valid_data_blkaddr(blkaddr)) + compr_blocks++; + + if (blkaddr != NEW_ADDR) + continue; + + f2fs_set_data_blkaddr(dn, NULL_ADDR); + } + + f2fs_i_compr_blocks_update(dn->inode, compr_blocks, false); + dec_valid_block_count(sbi, dn->inode, + cluster_size - compr_blocks); + + released_blocks += cluster_size - compr_blocks; +next: + count -= cluster_size; + } + + return released_blocks; +} + +static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + struct f2fs_inode_info *fi = F2FS_I(inode); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + pgoff_t page_idx = 0, last_idx; + unsigned int released_blocks = 0; + int ret; + int writecount; + + if (!f2fs_sb_has_compression(sbi)) + return -EOPNOTSUPP; + + if (f2fs_readonly(sbi->sb)) + return -EROFS; + + ret = mnt_want_write_file(filp); + if (ret) + return ret; + + f2fs_balance_fs(sbi, true); + + inode_lock(inode); + + writecount = atomic_read(&inode->i_writecount); + if ((filp->f_mode & FMODE_WRITE && writecount != 1) || + (!(filp->f_mode & FMODE_WRITE) && writecount)) { + ret = -EBUSY; + goto out; + } + + if (!f2fs_compressed_file(inode) || + is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) { + ret = -EINVAL; + goto out; + } + + ret = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX); + if (ret) + goto out; + + if (!atomic_read(&fi->i_compr_blocks)) { + ret = -EPERM; + goto out; + } + + set_inode_flag(inode, FI_COMPRESS_RELEASED); + inode_set_ctime_current(inode); + f2fs_mark_inode_dirty_sync(inode, true); + + f2fs_down_write(&fi->i_gc_rwsem[WRITE]); + filemap_invalidate_lock(inode->i_mapping); + + last_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); + + while (page_idx < last_idx) { + struct dnode_of_data dn; + pgoff_t end_offset, count; + + f2fs_lock_op(sbi); + + set_new_dnode(&dn, inode, NULL, NULL, 0); + ret = f2fs_get_dnode_of_data(&dn, page_idx, LOOKUP_NODE); + if (ret) { + f2fs_unlock_op(sbi); + if (ret == -ENOENT) { + page_idx = f2fs_get_next_page_offset(&dn, + page_idx); + ret = 0; + continue; + } + break; + } + + end_offset = ADDRS_PER_PAGE(dn.node_folio, inode); + count = min(end_offset - dn.ofs_in_node, last_idx - page_idx); + count = round_up(count, fi->i_cluster_size); + + ret = release_compress_blocks(&dn, count); + + f2fs_put_dnode(&dn); + + f2fs_unlock_op(sbi); + + if (ret < 0) + break; + + page_idx += count; + released_blocks += ret; + } + + filemap_invalidate_unlock(inode->i_mapping); + f2fs_up_write(&fi->i_gc_rwsem[WRITE]); +out: + if (released_blocks) + f2fs_update_time(sbi, REQ_TIME); + inode_unlock(inode); + + mnt_drop_write_file(filp); + + if (ret >= 0) { + ret = put_user(released_blocks, (u64 __user *)arg); + } else if (released_blocks && + atomic_read(&fi->i_compr_blocks)) { + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_warn(sbi, "%s: partial blocks were released i_ino=%lx " + "iblocks=%llu, released=%u, compr_blocks=%u, " + "run fsck to fix.", + __func__, inode->i_ino, inode->i_blocks, + released_blocks, + atomic_read(&fi->i_compr_blocks)); + } + + return ret; +} + +static int reserve_compress_blocks(struct dnode_of_data *dn, pgoff_t count, + unsigned int *reserved_blocks) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); + int cluster_size = F2FS_I(dn->inode)->i_cluster_size; + block_t blkaddr; + int i; + + for (i = 0; i < count; i++) { + blkaddr = data_blkaddr(dn->inode, dn->node_folio, + dn->ofs_in_node + i); + + if (!__is_valid_data_blkaddr(blkaddr)) + continue; + if (unlikely(!f2fs_is_valid_blkaddr(sbi, blkaddr, + DATA_GENERIC_ENHANCE))) + return -EFSCORRUPTED; + } + + while (count) { + int compr_blocks = 0; + blkcnt_t reserved = 0; + blkcnt_t to_reserved; + int ret; + + for (i = 0; i < cluster_size; i++) { + blkaddr = data_blkaddr(dn->inode, dn->node_folio, + dn->ofs_in_node + i); + + if (i == 0) { + if (blkaddr != COMPRESS_ADDR) { + dn->ofs_in_node += cluster_size; + goto next; + } + continue; + } + + /* + * compressed cluster was not released due to it + * fails in release_compress_blocks(), so NEW_ADDR + * is a possible case. + */ + if (blkaddr == NEW_ADDR) { + reserved++; + continue; + } + if (__is_valid_data_blkaddr(blkaddr)) { + compr_blocks++; + continue; + } + } + + to_reserved = cluster_size - compr_blocks - reserved; + + /* for the case all blocks in cluster were reserved */ + if (reserved && to_reserved == 1) { + dn->ofs_in_node += cluster_size; + goto next; + } + + ret = inc_valid_block_count(sbi, dn->inode, + &to_reserved, false); + if (unlikely(ret)) + return ret; + + for (i = 0; i < cluster_size; i++, dn->ofs_in_node++) { + if (f2fs_data_blkaddr(dn) == NULL_ADDR) + f2fs_set_data_blkaddr(dn, NEW_ADDR); + } + + f2fs_i_compr_blocks_update(dn->inode, compr_blocks, true); + + *reserved_blocks += to_reserved; +next: + count -= cluster_size; + } + + return 0; +} + +static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + struct f2fs_inode_info *fi = F2FS_I(inode); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + pgoff_t page_idx = 0, last_idx; + unsigned int reserved_blocks = 0; + int ret; + + if (!f2fs_sb_has_compression(sbi)) + return -EOPNOTSUPP; + + if (f2fs_readonly(sbi->sb)) + return -EROFS; + + ret = mnt_want_write_file(filp); + if (ret) + return ret; + + f2fs_balance_fs(sbi, true); + + inode_lock(inode); + + if (!f2fs_compressed_file(inode) || + !is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) { + ret = -EINVAL; + goto unlock_inode; + } + + if (atomic_read(&fi->i_compr_blocks)) + goto unlock_inode; + + f2fs_down_write(&fi->i_gc_rwsem[WRITE]); + filemap_invalidate_lock(inode->i_mapping); + + last_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); + + while (page_idx < last_idx) { + struct dnode_of_data dn; + pgoff_t end_offset, count; + + f2fs_lock_op(sbi); + + set_new_dnode(&dn, inode, NULL, NULL, 0); + ret = f2fs_get_dnode_of_data(&dn, page_idx, LOOKUP_NODE); + if (ret) { + f2fs_unlock_op(sbi); + if (ret == -ENOENT) { + page_idx = f2fs_get_next_page_offset(&dn, + page_idx); + ret = 0; + continue; + } + break; + } + + end_offset = ADDRS_PER_PAGE(dn.node_folio, inode); + count = min(end_offset - dn.ofs_in_node, last_idx - page_idx); + count = round_up(count, fi->i_cluster_size); + + ret = reserve_compress_blocks(&dn, count, &reserved_blocks); + + f2fs_put_dnode(&dn); + + f2fs_unlock_op(sbi); + + if (ret < 0) + break; + + page_idx += count; + } + + filemap_invalidate_unlock(inode->i_mapping); + f2fs_up_write(&fi->i_gc_rwsem[WRITE]); + + if (!ret) { + clear_inode_flag(inode, FI_COMPRESS_RELEASED); + inode_set_ctime_current(inode); + f2fs_mark_inode_dirty_sync(inode, true); + } +unlock_inode: + if (reserved_blocks) + f2fs_update_time(sbi, REQ_TIME); + inode_unlock(inode); + mnt_drop_write_file(filp); + + if (!ret) { + ret = put_user(reserved_blocks, (u64 __user *)arg); + } else if (reserved_blocks && + atomic_read(&fi->i_compr_blocks)) { + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_warn(sbi, "%s: partial blocks were reserved i_ino=%lx " + "iblocks=%llu, reserved=%u, compr_blocks=%u, " + "run fsck to fix.", + __func__, inode->i_ino, inode->i_blocks, + reserved_blocks, + atomic_read(&fi->i_compr_blocks)); + } + + return ret; +} + +static int f2fs_secure_erase(struct block_device *bdev, struct inode *inode, + pgoff_t off, block_t block, block_t len, u32 flags) +{ + sector_t sector = SECTOR_FROM_BLOCK(block); + sector_t nr_sects = SECTOR_FROM_BLOCK(len); + int ret = 0; + + if (flags & F2FS_TRIM_FILE_DISCARD) { + if (bdev_max_secure_erase_sectors(bdev)) + ret = blkdev_issue_secure_erase(bdev, sector, nr_sects, + GFP_NOFS); + else + ret = blkdev_issue_discard(bdev, sector, nr_sects, + GFP_NOFS); + } + + if (!ret && (flags & F2FS_TRIM_FILE_ZEROOUT)) { + if (IS_ENCRYPTED(inode)) + ret = fscrypt_zeroout_range(inode, off, block, len); + else + ret = blkdev_issue_zeroout(bdev, sector, nr_sects, + GFP_NOFS, 0); + } + + return ret; +} + +static int f2fs_sec_trim_file(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct address_space *mapping = inode->i_mapping; + struct block_device *prev_bdev = NULL; + struct f2fs_sectrim_range range; + pgoff_t index, pg_end, prev_index = 0; + block_t prev_block = 0, len = 0; + loff_t end_addr; + bool to_end = false; + int ret = 0; + + if (!(filp->f_mode & FMODE_WRITE)) + return -EBADF; + + if (copy_from_user(&range, (struct f2fs_sectrim_range __user *)arg, + sizeof(range))) + return -EFAULT; + + if (range.flags == 0 || (range.flags & ~F2FS_TRIM_FILE_MASK) || + !S_ISREG(inode->i_mode)) + return -EINVAL; + + if (((range.flags & F2FS_TRIM_FILE_DISCARD) && + !f2fs_hw_support_discard(sbi)) || + ((range.flags & F2FS_TRIM_FILE_ZEROOUT) && + IS_ENCRYPTED(inode) && f2fs_is_multi_device(sbi))) + return -EOPNOTSUPP; + + ret = mnt_want_write_file(filp); + if (ret) + return ret; + inode_lock(inode); + + if (f2fs_is_atomic_file(inode) || f2fs_compressed_file(inode) || + range.start >= inode->i_size) { + ret = -EINVAL; + goto err; + } + + if (range.len == 0) + goto err; + + if (inode->i_size - range.start > range.len) { + end_addr = range.start + range.len; + } else { + end_addr = range.len == (u64)-1 ? + sbi->sb->s_maxbytes : inode->i_size; + to_end = true; + } + + if (!IS_ALIGNED(range.start, F2FS_BLKSIZE) || + (!to_end && !IS_ALIGNED(end_addr, F2FS_BLKSIZE))) { + ret = -EINVAL; + goto err; + } + + index = F2FS_BYTES_TO_BLK(range.start); + pg_end = DIV_ROUND_UP(end_addr, F2FS_BLKSIZE); + + ret = f2fs_convert_inline_inode(inode); + if (ret) + goto err; + + f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + filemap_invalidate_lock(mapping); + + ret = filemap_write_and_wait_range(mapping, range.start, + to_end ? LLONG_MAX : end_addr - 1); + if (ret) + goto out; + + truncate_inode_pages_range(mapping, range.start, + to_end ? -1 : end_addr - 1); + + while (index < pg_end) { + struct dnode_of_data dn; + pgoff_t end_offset, count; + int i; + + set_new_dnode(&dn, inode, NULL, NULL, 0); + ret = f2fs_get_dnode_of_data(&dn, index, LOOKUP_NODE); + if (ret) { + if (ret == -ENOENT) { + index = f2fs_get_next_page_offset(&dn, index); + continue; + } + goto out; + } + + end_offset = ADDRS_PER_PAGE(dn.node_folio, inode); + count = min(end_offset - dn.ofs_in_node, pg_end - index); + for (i = 0; i < count; i++, index++, dn.ofs_in_node++) { + struct block_device *cur_bdev; + block_t blkaddr = f2fs_data_blkaddr(&dn); + + if (!__is_valid_data_blkaddr(blkaddr)) + continue; + + if (!f2fs_is_valid_blkaddr(sbi, blkaddr, + DATA_GENERIC_ENHANCE)) { + ret = -EFSCORRUPTED; + f2fs_put_dnode(&dn); + goto out; + } + + cur_bdev = f2fs_target_device(sbi, blkaddr, NULL); + if (f2fs_is_multi_device(sbi)) { + int di = f2fs_target_device_index(sbi, blkaddr); + + blkaddr -= FDEV(di).start_blk; + } + + if (len) { + if (prev_bdev == cur_bdev && + index == prev_index + len && + blkaddr == prev_block + len) { + len++; + } else { + ret = f2fs_secure_erase(prev_bdev, + inode, prev_index, prev_block, + len, range.flags); + if (ret) { + f2fs_put_dnode(&dn); + goto out; + } + + len = 0; + } + } + + if (!len) { + prev_bdev = cur_bdev; + prev_index = index; + prev_block = blkaddr; + len = 1; + } + } + + f2fs_put_dnode(&dn); + + if (fatal_signal_pending(current)) { + ret = -EINTR; + goto out; + } + cond_resched(); + } + + if (len) + ret = f2fs_secure_erase(prev_bdev, inode, prev_index, + prev_block, len, range.flags); + f2fs_update_time(sbi, REQ_TIME); +out: + filemap_invalidate_unlock(mapping); + f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); +err: + inode_unlock(inode); + mnt_drop_write_file(filp); + + return ret; +} + +static int f2fs_ioc_get_compress_option(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + struct f2fs_comp_option option; + + if (!f2fs_sb_has_compression(F2FS_I_SB(inode))) + return -EOPNOTSUPP; + + inode_lock_shared(inode); + + if (!f2fs_compressed_file(inode)) { + inode_unlock_shared(inode); + return -ENODATA; + } + + option.algorithm = F2FS_I(inode)->i_compress_algorithm; + option.log_cluster_size = F2FS_I(inode)->i_log_cluster_size; + + inode_unlock_shared(inode); + + if (copy_to_user((struct f2fs_comp_option __user *)arg, &option, + sizeof(option))) + return -EFAULT; + + return 0; +} + +static int f2fs_ioc_set_compress_option(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + struct f2fs_inode_info *fi = F2FS_I(inode); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct f2fs_comp_option option; + int ret = 0; + + if (!f2fs_sb_has_compression(sbi)) + return -EOPNOTSUPP; + + if (!(filp->f_mode & FMODE_WRITE)) + return -EBADF; + + if (copy_from_user(&option, (struct f2fs_comp_option __user *)arg, + sizeof(option))) + return -EFAULT; + + if (option.log_cluster_size < MIN_COMPRESS_LOG_SIZE || + option.log_cluster_size > MAX_COMPRESS_LOG_SIZE || + option.algorithm >= COMPRESS_MAX) + return -EINVAL; + + ret = mnt_want_write_file(filp); + if (ret) + return ret; + inode_lock(inode); + + f2fs_down_write(&F2FS_I(inode)->i_sem); + if (!f2fs_compressed_file(inode)) { + ret = -EINVAL; + goto out; + } + + if (f2fs_is_mmap_file(inode) || get_dirty_pages(inode)) { + ret = -EBUSY; + goto out; + } + + if (F2FS_HAS_BLOCKS(inode)) { + ret = -EFBIG; + goto out; + } + + fi->i_compress_algorithm = option.algorithm; + fi->i_log_cluster_size = option.log_cluster_size; + fi->i_cluster_size = BIT(option.log_cluster_size); + /* Set default level */ + if (fi->i_compress_algorithm == COMPRESS_ZSTD) + fi->i_compress_level = F2FS_ZSTD_DEFAULT_CLEVEL; + else + fi->i_compress_level = 0; + /* Adjust mount option level */ + if (option.algorithm == F2FS_OPTION(sbi).compress_algorithm && + F2FS_OPTION(sbi).compress_level) + fi->i_compress_level = F2FS_OPTION(sbi).compress_level; + f2fs_mark_inode_dirty_sync(inode, true); + + if (!f2fs_is_compress_backend_ready(inode)) + f2fs_warn(sbi, "compression algorithm is successfully set, " + "but current kernel doesn't support this algorithm."); +out: + f2fs_up_write(&fi->i_sem); + inode_unlock(inode); + mnt_drop_write_file(filp); + + return ret; +} + +static int redirty_blocks(struct inode *inode, pgoff_t page_idx, int len) +{ + DEFINE_READAHEAD(ractl, NULL, NULL, inode->i_mapping, page_idx); + struct address_space *mapping = inode->i_mapping; + struct folio *folio; + pgoff_t redirty_idx = page_idx; + int page_len = 0, ret = 0; + + page_cache_ra_unbounded(&ractl, len, 0); + + do { + folio = read_cache_folio(mapping, page_idx, NULL, NULL); + if (IS_ERR(folio)) { + ret = PTR_ERR(folio); + break; + } + page_len += folio_nr_pages(folio) - (page_idx - folio->index); + page_idx = folio_next_index(folio); + } while (page_len < len); + + do { + folio = filemap_lock_folio(mapping, redirty_idx); + + /* It will never fail, when folio has pinned above */ + f2fs_bug_on(F2FS_I_SB(inode), IS_ERR(folio)); + + f2fs_folio_wait_writeback(folio, DATA, true, true); + + folio_mark_dirty(folio); + folio_set_f2fs_gcing(folio); + redirty_idx = folio_next_index(folio); + folio_unlock(folio); + folio_put_refs(folio, 2); + } while (redirty_idx < page_idx); + + return ret; +} + +static int f2fs_ioc_decompress_file(struct file *filp) +{ + struct inode *inode = file_inode(filp); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct f2fs_inode_info *fi = F2FS_I(inode); + pgoff_t page_idx = 0, last_idx, cluster_idx; + int ret; + + if (!f2fs_sb_has_compression(sbi) || + F2FS_OPTION(sbi).compress_mode != COMPR_MODE_USER) + return -EOPNOTSUPP; + + if (!(filp->f_mode & FMODE_WRITE)) + return -EBADF; + + f2fs_balance_fs(sbi, true); + + ret = mnt_want_write_file(filp); + if (ret) + return ret; + inode_lock(inode); + + if (!f2fs_is_compress_backend_ready(inode)) { + ret = -EOPNOTSUPP; + goto out; + } + + if (!f2fs_compressed_file(inode) || + is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) { + ret = -EINVAL; + goto out; + } + + ret = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX); + if (ret) + goto out; + + if (!atomic_read(&fi->i_compr_blocks)) + goto out; + + last_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); + last_idx >>= fi->i_log_cluster_size; + + for (cluster_idx = 0; cluster_idx < last_idx; cluster_idx++) { + page_idx = cluster_idx << fi->i_log_cluster_size; + + if (!f2fs_is_compressed_cluster(inode, page_idx)) + continue; + + ret = redirty_blocks(inode, page_idx, fi->i_cluster_size); + if (ret < 0) + break; + + if (get_dirty_pages(inode) >= BLKS_PER_SEG(sbi)) { + ret = filemap_fdatawrite(inode->i_mapping); + if (ret < 0) + break; + } + + cond_resched(); + if (fatal_signal_pending(current)) { + ret = -EINTR; + break; + } + } + + if (!ret) + ret = filemap_write_and_wait_range(inode->i_mapping, 0, + LLONG_MAX); + + if (ret) + f2fs_warn(sbi, "%s: The file might be partially decompressed (errno=%d). Please delete the file.", + __func__, ret); + f2fs_update_time(sbi, REQ_TIME); +out: + inode_unlock(inode); + mnt_drop_write_file(filp); + + return ret; +} + +static int f2fs_ioc_compress_file(struct file *filp) +{ + struct inode *inode = file_inode(filp); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct f2fs_inode_info *fi = F2FS_I(inode); + pgoff_t page_idx = 0, last_idx, cluster_idx; + int ret; + + if (!f2fs_sb_has_compression(sbi) || + F2FS_OPTION(sbi).compress_mode != COMPR_MODE_USER) + return -EOPNOTSUPP; + + if (!(filp->f_mode & FMODE_WRITE)) + return -EBADF; + + f2fs_balance_fs(sbi, true); + + ret = mnt_want_write_file(filp); + if (ret) + return ret; + inode_lock(inode); + + if (!f2fs_is_compress_backend_ready(inode)) { + ret = -EOPNOTSUPP; + goto out; + } + + if (!f2fs_compressed_file(inode) || + is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) { + ret = -EINVAL; + goto out; + } + + ret = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX); + if (ret) + goto out; + + set_inode_flag(inode, FI_ENABLE_COMPRESS); + + last_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); + last_idx >>= fi->i_log_cluster_size; + + for (cluster_idx = 0; cluster_idx < last_idx; cluster_idx++) { + page_idx = cluster_idx << fi->i_log_cluster_size; + + if (f2fs_is_sparse_cluster(inode, page_idx)) + continue; + + ret = redirty_blocks(inode, page_idx, fi->i_cluster_size); + if (ret < 0) + break; + + if (get_dirty_pages(inode) >= BLKS_PER_SEG(sbi)) { + ret = filemap_fdatawrite(inode->i_mapping); + if (ret < 0) + break; + } + + cond_resched(); + if (fatal_signal_pending(current)) { + ret = -EINTR; + break; + } + } + + if (!ret) + ret = filemap_write_and_wait_range(inode->i_mapping, 0, + LLONG_MAX); + + clear_inode_flag(inode, FI_ENABLE_COMPRESS); + + if (ret) + f2fs_warn(sbi, "%s: The file might be partially compressed (errno=%d). Please delete the file.", + __func__, ret); + f2fs_update_time(sbi, REQ_TIME); +out: + inode_unlock(inode); + mnt_drop_write_file(filp); + + return ret; +} + +static long __f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { switch (cmd) { - case F2FS_IOC_GETFLAGS: - return f2fs_ioc_getflags(filp, arg); - case F2FS_IOC_SETFLAGS: - return f2fs_ioc_setflags(filp, arg); - case F2FS_IOC_GETVERSION: + case FS_IOC_GETVERSION: return f2fs_ioc_getversion(filp, arg); case F2FS_IOC_START_ATOMIC_WRITE: - return f2fs_ioc_start_atomic_write(filp); + return f2fs_ioc_start_atomic_write(filp, false); + case F2FS_IOC_START_ATOMIC_REPLACE: + return f2fs_ioc_start_atomic_write(filp, true); case F2FS_IOC_COMMIT_ATOMIC_WRITE: return f2fs_ioc_commit_atomic_write(filp); + case F2FS_IOC_ABORT_ATOMIC_WRITE: + return f2fs_ioc_abort_atomic_write(filp); case F2FS_IOC_START_VOLATILE_WRITE: - return f2fs_ioc_start_volatile_write(filp); case F2FS_IOC_RELEASE_VOLATILE_WRITE: - return f2fs_ioc_release_volatile_write(filp); - case F2FS_IOC_ABORT_VOLATILE_WRITE: - return f2fs_ioc_abort_volatile_write(filp); + return -EOPNOTSUPP; case F2FS_IOC_SHUTDOWN: return f2fs_ioc_shutdown(filp, arg); case FITRIM: return f2fs_ioc_fitrim(filp, arg); - case F2FS_IOC_SET_ENCRYPTION_POLICY: + case FS_IOC_SET_ENCRYPTION_POLICY: return f2fs_ioc_set_encryption_policy(filp, arg); - case F2FS_IOC_GET_ENCRYPTION_POLICY: + case FS_IOC_GET_ENCRYPTION_POLICY: return f2fs_ioc_get_encryption_policy(filp, arg); - case F2FS_IOC_GET_ENCRYPTION_PWSALT: + case FS_IOC_GET_ENCRYPTION_PWSALT: return f2fs_ioc_get_encryption_pwsalt(filp, arg); + case FS_IOC_GET_ENCRYPTION_POLICY_EX: + return f2fs_ioc_get_encryption_policy_ex(filp, arg); + case FS_IOC_ADD_ENCRYPTION_KEY: + return f2fs_ioc_add_encryption_key(filp, arg); + case FS_IOC_REMOVE_ENCRYPTION_KEY: + return f2fs_ioc_remove_encryption_key(filp, arg); + case FS_IOC_REMOVE_ENCRYPTION_KEY_ALL_USERS: + return f2fs_ioc_remove_encryption_key_all_users(filp, arg); + case FS_IOC_GET_ENCRYPTION_KEY_STATUS: + return f2fs_ioc_get_encryption_key_status(filp, arg); + case FS_IOC_GET_ENCRYPTION_NONCE: + return f2fs_ioc_get_encryption_nonce(filp, arg); case F2FS_IOC_GARBAGE_COLLECT: return f2fs_ioc_gc(filp, arg); case F2FS_IOC_GARBAGE_COLLECT_RANGE: return f2fs_ioc_gc_range(filp, arg); case F2FS_IOC_WRITE_CHECKPOINT: - return f2fs_ioc_write_checkpoint(filp, arg); + return f2fs_ioc_write_checkpoint(filp); case F2FS_IOC_DEFRAGMENT: return f2fs_ioc_defragment(filp, arg); case F2FS_IOC_MOVE_RANGE: return f2fs_ioc_move_range(filp, arg); case F2FS_IOC_FLUSH_DEVICE: return f2fs_ioc_flush_device(filp, arg); + case F2FS_IOC_GET_FEATURES: + return f2fs_ioc_get_features(filp, arg); + case F2FS_IOC_GET_PIN_FILE: + return f2fs_ioc_get_pin_file(filp, arg); + case F2FS_IOC_SET_PIN_FILE: + return f2fs_ioc_set_pin_file(filp, arg); + case F2FS_IOC_PRECACHE_EXTENTS: + return f2fs_ioc_precache_extents(filp); + case F2FS_IOC_RESIZE_FS: + return f2fs_ioc_resize_fs(filp, arg); + case FS_IOC_ENABLE_VERITY: + return f2fs_ioc_enable_verity(filp, arg); + case FS_IOC_MEASURE_VERITY: + return f2fs_ioc_measure_verity(filp, arg); + case FS_IOC_READ_VERITY_METADATA: + return f2fs_ioc_read_verity_metadata(filp, arg); + case FS_IOC_GETFSLABEL: + return f2fs_ioc_getfslabel(filp, arg); + case FS_IOC_SETFSLABEL: + return f2fs_ioc_setfslabel(filp, arg); + case F2FS_IOC_GET_COMPRESS_BLOCKS: + return f2fs_ioc_get_compress_blocks(filp, arg); + case F2FS_IOC_RELEASE_COMPRESS_BLOCKS: + return f2fs_release_compress_blocks(filp, arg); + case F2FS_IOC_RESERVE_COMPRESS_BLOCKS: + return f2fs_reserve_compress_blocks(filp, arg); + case F2FS_IOC_SEC_TRIM_FILE: + return f2fs_sec_trim_file(filp, arg); + case F2FS_IOC_GET_COMPRESS_OPTION: + return f2fs_ioc_get_compress_option(filp, arg); + case F2FS_IOC_SET_COMPRESS_OPTION: + return f2fs_ioc_set_compress_option(filp, arg); + case F2FS_IOC_DECOMPRESS_FILE: + return f2fs_ioc_decompress_file(filp); + case F2FS_IOC_COMPRESS_FILE: + return f2fs_ioc_compress_file(filp); + case F2FS_IOC_GET_DEV_ALIAS_FILE: + return f2fs_ioc_get_dev_alias_file(filp, arg); + case F2FS_IOC_IO_PRIO: + return f2fs_ioc_io_prio(filp, arg); default: return -ENOTTY; } } -static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) +long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) +{ + if (unlikely(f2fs_cp_error(F2FS_I_SB(file_inode(filp))))) + return -EIO; + if (!f2fs_is_checkpoint_ready(F2FS_I_SB(file_inode(filp)))) + return -ENOSPC; + + return __f2fs_ioctl(filp, cmd, arg); +} + +/* + * Return %true if the given read or write request should use direct I/O, or + * %false if it should use buffered I/O. + */ +static bool f2fs_should_use_dio(struct inode *inode, struct kiocb *iocb, + struct iov_iter *iter) +{ + unsigned int align; + + if (!(iocb->ki_flags & IOCB_DIRECT)) + return false; + + if (f2fs_force_buffered_io(inode, iov_iter_rw(iter))) + return false; + + /* + * Direct I/O not aligned to the disk's logical_block_size will be + * attempted, but will fail with -EINVAL. + * + * f2fs additionally requires that direct I/O be aligned to the + * filesystem block size, which is often a stricter requirement. + * However, f2fs traditionally falls back to buffered I/O on requests + * that are logical_block_size-aligned but not fs-block aligned. + * + * The below logic implements this behavior. + */ + align = iocb->ki_pos | iov_iter_alignment(iter); + if (!IS_ALIGNED(align, i_blocksize(inode)) && + IS_ALIGNED(align, bdev_logical_block_size(inode->i_sb->s_bdev))) + return false; + + return true; +} + +static int f2fs_dio_read_end_io(struct kiocb *iocb, ssize_t size, int error, + unsigned int flags) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(file_inode(iocb->ki_filp)); + + dec_page_count(sbi, F2FS_DIO_READ); + if (error) + return error; + f2fs_update_iostat(sbi, NULL, APP_DIRECT_READ_IO, size); + return 0; +} + +static const struct iomap_dio_ops f2fs_iomap_dio_read_ops = { + .end_io = f2fs_dio_read_end_io, +}; + +static ssize_t f2fs_dio_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); - struct blk_plug plug; + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct f2fs_inode_info *fi = F2FS_I(inode); + const loff_t pos = iocb->ki_pos; + const size_t count = iov_iter_count(to); + struct iomap_dio *dio; ssize_t ret; - inode_lock(inode); - ret = generic_write_checks(iocb, from); + if (count == 0) + return 0; /* skip atime update */ + + trace_f2fs_direct_IO_enter(inode, iocb, count, READ); + + if (iocb->ki_flags & IOCB_NOWAIT) { + if (!f2fs_down_read_trylock(&fi->i_gc_rwsem[READ])) { + ret = -EAGAIN; + goto out; + } + } else { + f2fs_down_read(&fi->i_gc_rwsem[READ]); + } + + /* dio is not compatible w/ atomic file */ + if (f2fs_is_atomic_file(inode)) { + f2fs_up_read(&fi->i_gc_rwsem[READ]); + ret = -EOPNOTSUPP; + goto out; + } + + /* + * We have to use __iomap_dio_rw() and iomap_dio_complete() instead of + * the higher-level function iomap_dio_rw() in order to ensure that the + * F2FS_DIO_READ counter will be decremented correctly in all cases. + */ + inc_page_count(sbi, F2FS_DIO_READ); + dio = __iomap_dio_rw(iocb, to, &f2fs_iomap_ops, + &f2fs_iomap_dio_read_ops, 0, NULL, 0); + if (IS_ERR_OR_NULL(dio)) { + ret = PTR_ERR_OR_ZERO(dio); + if (ret != -EIOCBQUEUED) + dec_page_count(sbi, F2FS_DIO_READ); + } else { + ret = iomap_dio_complete(dio); + } + + f2fs_up_read(&fi->i_gc_rwsem[READ]); + + file_accessed(file); +out: + trace_f2fs_direct_IO_exit(inode, pos, count, READ, ret); + return ret; +} + +static void f2fs_trace_rw_file_path(struct file *file, loff_t pos, size_t count, + int rw) +{ + struct inode *inode = file_inode(file); + char *buf, *path; + + buf = f2fs_getname(F2FS_I_SB(inode)); + if (!buf) + return; + path = dentry_path_raw(file_dentry(file), buf, PATH_MAX); + if (IS_ERR(path)) + goto free_buf; + if (rw == WRITE) + trace_f2fs_datawrite_start(inode, pos, count, + current->pid, path, current->comm); + else + trace_f2fs_dataread_start(inode, pos, count, + current->pid, path, current->comm); +free_buf: + f2fs_putname(buf); +} + +static ssize_t f2fs_file_read_iter(struct kiocb *iocb, struct iov_iter *to) +{ + struct inode *inode = file_inode(iocb->ki_filp); + const loff_t pos = iocb->ki_pos; + ssize_t ret; + bool dio; + + if (!f2fs_is_compress_backend_ready(inode)) + return -EOPNOTSUPP; + + if (trace_f2fs_dataread_start_enabled()) + f2fs_trace_rw_file_path(iocb->ki_filp, iocb->ki_pos, + iov_iter_count(to), READ); + + dio = f2fs_should_use_dio(inode, iocb, to); + + /* In LFS mode, if there is inflight dio, wait for its completion */ + if (f2fs_lfs_mode(F2FS_I_SB(inode)) && + get_pages(F2FS_I_SB(inode), F2FS_DIO_WRITE) && + (!f2fs_is_pinned_file(inode) || !dio)) + inode_dio_wait(inode); + + if (dio) { + ret = f2fs_dio_read_iter(iocb, to); + } else { + ret = filemap_read(iocb, to, 0); + if (ret > 0) + f2fs_update_iostat(F2FS_I_SB(inode), inode, + APP_BUFFERED_READ_IO, ret); + } + trace_f2fs_dataread_end(inode, pos, ret); + return ret; +} + +static ssize_t f2fs_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); + const loff_t pos = *ppos; + ssize_t ret; + + if (!f2fs_is_compress_backend_ready(inode)) + return -EOPNOTSUPP; + + if (trace_f2fs_dataread_start_enabled()) + f2fs_trace_rw_file_path(in, pos, len, READ); + + ret = filemap_splice_read(in, ppos, pipe, len, flags); + if (ret > 0) + f2fs_update_iostat(F2FS_I_SB(inode), inode, + APP_BUFFERED_READ_IO, ret); + + trace_f2fs_dataread_end(inode, pos, ret); + return ret; +} + +static ssize_t f2fs_write_checks(struct kiocb *iocb, struct iov_iter *from) +{ + struct file *file = iocb->ki_filp; + struct inode *inode = file_inode(file); + ssize_t count; + int err; + + if (IS_IMMUTABLE(inode)) + return -EPERM; + + if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) + return -EPERM; + + count = generic_write_checks(iocb, from); + if (count <= 0) + return count; + + err = file_modified(file); + if (err) + return err; + + f2fs_zero_post_eof_page(inode, + iocb->ki_pos + iov_iter_count(from), true); + return count; +} + +/* + * Preallocate blocks for a write request, if it is possible and helpful to do + * so. Returns a positive number if blocks may have been preallocated, 0 if no + * blocks were preallocated, or a negative errno value if something went + * seriously wrong. Also sets FI_PREALLOCATED_ALL on the inode if *all* the + * requested blocks (not just some of them) have been allocated. + */ +static int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *iter, + bool dio) +{ + struct inode *inode = file_inode(iocb->ki_filp); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + const loff_t pos = iocb->ki_pos; + const size_t count = iov_iter_count(iter); + struct f2fs_map_blocks map = {}; + int flag; + int ret; + + /* If it will be an out-of-place direct write, don't bother. */ + if (dio && f2fs_lfs_mode(sbi)) + return 0; + /* + * Don't preallocate holes aligned to DIO_SKIP_HOLES which turns into + * buffered IO, if DIO meets any holes. + */ + if (dio && i_size_read(inode) && + (F2FS_BYTES_TO_BLK(pos) < F2FS_BLK_ALIGN(i_size_read(inode)))) + return 0; + + /* No-wait I/O can't allocate blocks. */ + if (iocb->ki_flags & IOCB_NOWAIT) + return 0; + + /* If it will be a short write, don't bother. */ + if (fault_in_iov_iter_readable(iter, count)) + return 0; + + if (f2fs_has_inline_data(inode)) { + /* If the data will fit inline, don't bother. */ + if (pos + count <= MAX_INLINE_DATA(inode)) + return 0; + ret = f2fs_convert_inline_inode(inode); + if (ret) + return ret; + } + + /* Do not preallocate blocks that will be written partially in 4KB. */ + map.m_lblk = F2FS_BLK_ALIGN(pos); + map.m_len = F2FS_BYTES_TO_BLK(pos + count); + if (map.m_len > map.m_lblk) + map.m_len -= map.m_lblk; + else + return 0; + + if (!IS_DEVICE_ALIASING(inode)) + map.m_may_create = true; + if (dio) { + map.m_seg_type = f2fs_rw_hint_to_seg_type(sbi, + inode->i_write_hint); + flag = F2FS_GET_BLOCK_PRE_DIO; + } else { + map.m_seg_type = NO_CHECK_TYPE; + flag = F2FS_GET_BLOCK_PRE_AIO; + } + + ret = f2fs_map_blocks(inode, &map, flag); + /* -ENOSPC|-EDQUOT are fine to report the number of allocated blocks. */ + if (ret < 0 && !((ret == -ENOSPC || ret == -EDQUOT) && map.m_len > 0)) + return ret; + if (ret == 0) + set_inode_flag(inode, FI_PREALLOCATED_ALL); + return map.m_len; +} + +static ssize_t f2fs_buffered_write_iter(struct kiocb *iocb, + struct iov_iter *from) +{ + struct file *file = iocb->ki_filp; + struct inode *inode = file_inode(file); + ssize_t ret; + + if (iocb->ki_flags & IOCB_NOWAIT) + return -EOPNOTSUPP; + + ret = generic_perform_write(iocb, from); + if (ret > 0) { - int err; + f2fs_update_iostat(F2FS_I_SB(inode), inode, + APP_BUFFERED_IO, ret); + } + return ret; +} - if (iov_iter_fault_in_readable(from, iov_iter_count(from))) - set_inode_flag(inode, FI_NO_PREALLOC); +static int f2fs_dio_write_end_io(struct kiocb *iocb, ssize_t size, int error, + unsigned int flags) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(file_inode(iocb->ki_filp)); - err = f2fs_preallocate_blocks(iocb, from); - if (err) { - inode_unlock(inode); - return err; + dec_page_count(sbi, F2FS_DIO_WRITE); + if (error) + return error; + f2fs_update_time(sbi, REQ_TIME); + f2fs_update_iostat(sbi, NULL, APP_DIRECT_IO, size); + return 0; +} + +static void f2fs_dio_write_submit_io(const struct iomap_iter *iter, + struct bio *bio, loff_t file_offset) +{ + struct inode *inode = iter->inode; + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + enum log_type type = f2fs_rw_hint_to_seg_type(sbi, inode->i_write_hint); + enum temp_type temp = f2fs_get_segment_temp(sbi, type); + + bio->bi_write_hint = f2fs_io_type_to_rw_hint(sbi, DATA, temp); + submit_bio(bio); +} + +static const struct iomap_dio_ops f2fs_iomap_dio_write_ops = { + .end_io = f2fs_dio_write_end_io, + .submit_io = f2fs_dio_write_submit_io, +}; + +static void f2fs_flush_buffered_write(struct address_space *mapping, + loff_t start_pos, loff_t end_pos) +{ + int ret; + + ret = filemap_write_and_wait_range(mapping, start_pos, end_pos); + if (ret < 0) + return; + invalidate_mapping_pages(mapping, + start_pos >> PAGE_SHIFT, + end_pos >> PAGE_SHIFT); +} + +static ssize_t f2fs_dio_write_iter(struct kiocb *iocb, struct iov_iter *from, + bool *may_need_sync) +{ + struct file *file = iocb->ki_filp; + struct inode *inode = file_inode(file); + struct f2fs_inode_info *fi = F2FS_I(inode); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + const bool do_opu = f2fs_lfs_mode(sbi); + const loff_t pos = iocb->ki_pos; + const ssize_t count = iov_iter_count(from); + unsigned int dio_flags; + struct iomap_dio *dio; + ssize_t ret; + + trace_f2fs_direct_IO_enter(inode, iocb, count, WRITE); + + if (iocb->ki_flags & IOCB_NOWAIT) { + /* f2fs_convert_inline_inode() and block allocation can block */ + if (f2fs_has_inline_data(inode) || + !f2fs_overwrite_io(inode, pos, count)) { + ret = -EAGAIN; + goto out; + } + + if (!f2fs_down_read_trylock(&fi->i_gc_rwsem[WRITE])) { + ret = -EAGAIN; + goto out; + } + if (do_opu && !f2fs_down_read_trylock(&fi->i_gc_rwsem[READ])) { + f2fs_up_read(&fi->i_gc_rwsem[WRITE]); + ret = -EAGAIN; + goto out; + } + } else { + ret = f2fs_convert_inline_inode(inode); + if (ret) + goto out; + + f2fs_down_read(&fi->i_gc_rwsem[WRITE]); + if (do_opu) + f2fs_down_read(&fi->i_gc_rwsem[READ]); + } + + /* + * We have to use __iomap_dio_rw() and iomap_dio_complete() instead of + * the higher-level function iomap_dio_rw() in order to ensure that the + * F2FS_DIO_WRITE counter will be decremented correctly in all cases. + */ + inc_page_count(sbi, F2FS_DIO_WRITE); + dio_flags = 0; + if (pos + count > inode->i_size) + dio_flags |= IOMAP_DIO_FORCE_WAIT; + dio = __iomap_dio_rw(iocb, from, &f2fs_iomap_ops, + &f2fs_iomap_dio_write_ops, dio_flags, NULL, 0); + if (IS_ERR_OR_NULL(dio)) { + ret = PTR_ERR_OR_ZERO(dio); + if (ret == -ENOTBLK) + ret = 0; + if (ret != -EIOCBQUEUED) + dec_page_count(sbi, F2FS_DIO_WRITE); + } else { + ret = iomap_dio_complete(dio); + } + + if (do_opu) + f2fs_up_read(&fi->i_gc_rwsem[READ]); + f2fs_up_read(&fi->i_gc_rwsem[WRITE]); + + if (ret < 0) + goto out; + if (pos + ret > inode->i_size) + f2fs_i_size_write(inode, pos + ret); + if (!do_opu) + set_inode_flag(inode, FI_UPDATE_WRITE); + + if (iov_iter_count(from)) { + ssize_t ret2; + loff_t bufio_start_pos = iocb->ki_pos; + + /* + * The direct write was partial, so we need to fall back to a + * buffered write for the remainder. + */ + + ret2 = f2fs_buffered_write_iter(iocb, from); + if (iov_iter_count(from)) + f2fs_write_failed(inode, iocb->ki_pos); + if (ret2 < 0) + goto out; + + /* + * Ensure that the pagecache pages are written to disk and + * invalidated to preserve the expected O_DIRECT semantics. + */ + if (ret2 > 0) { + loff_t bufio_end_pos = bufio_start_pos + ret2 - 1; + + ret += ret2; + + f2fs_flush_buffered_write(file->f_mapping, + bufio_start_pos, + bufio_end_pos); + } + } else { + /* iomap_dio_rw() already handled the generic_write_sync(). */ + *may_need_sync = false; + } +out: + trace_f2fs_direct_IO_exit(inode, pos, count, WRITE, ret); + return ret; +} + +static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) +{ + struct inode *inode = file_inode(iocb->ki_filp); + const loff_t orig_pos = iocb->ki_pos; + const size_t orig_count = iov_iter_count(from); + loff_t target_size; + bool dio; + bool may_need_sync = true; + int preallocated; + const loff_t pos = iocb->ki_pos; + const ssize_t count = iov_iter_count(from); + ssize_t ret; + + if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) { + ret = -EIO; + goto out; + } + + if (!f2fs_is_compress_backend_ready(inode)) { + ret = -EOPNOTSUPP; + goto out; + } + + if (iocb->ki_flags & IOCB_NOWAIT) { + if (!inode_trylock(inode)) { + ret = -EAGAIN; + goto out; } - blk_start_plug(&plug); - ret = __generic_file_write_iter(iocb, from); - blk_finish_plug(&plug); - clear_inode_flag(inode, FI_NO_PREALLOC); + } else { + inode_lock(inode); + } + + if (f2fs_is_pinned_file(inode) && + !f2fs_overwrite_io(inode, pos, count)) { + ret = -EIO; + goto out_unlock; + } + + ret = f2fs_write_checks(iocb, from); + if (ret <= 0) + goto out_unlock; + + /* Determine whether we will do a direct write or a buffered write. */ + dio = f2fs_should_use_dio(inode, iocb, from); + + /* dio is not compatible w/ atomic write */ + if (dio && f2fs_is_atomic_file(inode)) { + ret = -EOPNOTSUPP; + goto out_unlock; + } + + /* Possibly preallocate the blocks for the write. */ + target_size = iocb->ki_pos + iov_iter_count(from); + preallocated = f2fs_preallocate_blocks(iocb, from, dio); + if (preallocated < 0) { + ret = preallocated; + } else { + if (trace_f2fs_datawrite_start_enabled()) + f2fs_trace_rw_file_path(iocb->ki_filp, iocb->ki_pos, + orig_count, WRITE); + + /* Do the actual write. */ + ret = dio ? + f2fs_dio_write_iter(iocb, from, &may_need_sync) : + f2fs_buffered_write_iter(iocb, from); + + trace_f2fs_datawrite_end(inode, orig_pos, ret); } + + /* Don't leave any preallocated blocks around past i_size. */ + if (preallocated && i_size_read(inode) < target_size) { + f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + filemap_invalidate_lock(inode->i_mapping); + if (!f2fs_truncate(inode)) + file_dont_truncate(inode); + filemap_invalidate_unlock(inode->i_mapping); + f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + } else { + file_dont_truncate(inode); + } + + clear_inode_flag(inode, FI_PREALLOCATED_ALL); +out_unlock: inode_unlock(inode); +out: + trace_f2fs_file_write_iter(inode, orig_pos, orig_count, ret); - if (ret > 0) + if (ret > 0 && may_need_sync) ret = generic_write_sync(iocb, ret); + + /* If buffered IO was forced, flush and drop the data from + * the page cache to preserve O_DIRECT semantics + */ + if (ret > 0 && !dio && (iocb->ki_flags & IOCB_DIRECT)) + f2fs_flush_buffered_write(iocb->ki_filp->f_mapping, + orig_pos, + orig_pos + ret - 1); + return ret; } +static int f2fs_file_fadvise(struct file *filp, loff_t offset, loff_t len, + int advice) +{ + struct address_space *mapping; + struct backing_dev_info *bdi; + struct inode *inode = file_inode(filp); + int err; + + trace_f2fs_fadvise(inode, offset, len, advice); + + if (advice == POSIX_FADV_SEQUENTIAL) { + if (S_ISFIFO(inode->i_mode)) + return -ESPIPE; + + mapping = filp->f_mapping; + if (!mapping || len < 0) + return -EINVAL; + + bdi = inode_to_bdi(mapping->host); + filp->f_ra.ra_pages = bdi->ra_pages * + F2FS_I_SB(inode)->seq_file_ra_mul; + spin_lock(&filp->f_lock); + filp->f_mode &= ~FMODE_RANDOM; + spin_unlock(&filp->f_lock); + return 0; + } else if (advice == POSIX_FADV_WILLNEED && offset == 0) { + /* Load extent cache at the first readahead. */ + f2fs_precache_extents(inode); + } + + err = generic_fadvise(filp, offset, len, advice); + if (err) + return err; + + if (advice == POSIX_FADV_DONTNEED && + (test_opt(F2FS_I_SB(inode), COMPRESS_CACHE) && + f2fs_compressed_file(inode))) + f2fs_invalidate_compress_pages(F2FS_I_SB(inode), inode->i_ino); + else if (advice == POSIX_FADV_NOREUSE) + err = f2fs_keep_noreuse_range(inode, offset, len); + return err; +} + #ifdef CONFIG_COMPAT +struct compat_f2fs_gc_range { + u32 sync; + compat_u64 start; + compat_u64 len; +}; +#define F2FS_IOC32_GARBAGE_COLLECT_RANGE _IOW(F2FS_IOCTL_MAGIC, 11,\ + struct compat_f2fs_gc_range) + +static int f2fs_compat_ioc_gc_range(struct file *file, unsigned long arg) +{ + struct compat_f2fs_gc_range __user *urange; + struct f2fs_gc_range range; + int err; + + urange = compat_ptr(arg); + err = get_user(range.sync, &urange->sync); + err |= get_user(range.start, &urange->start); + err |= get_user(range.len, &urange->len); + if (err) + return -EFAULT; + + return __f2fs_ioc_gc_range(file, &range); +} + +struct compat_f2fs_move_range { + u32 dst_fd; + compat_u64 pos_in; + compat_u64 pos_out; + compat_u64 len; +}; +#define F2FS_IOC32_MOVE_RANGE _IOWR(F2FS_IOCTL_MAGIC, 9, \ + struct compat_f2fs_move_range) + +static int f2fs_compat_ioc_move_range(struct file *file, unsigned long arg) +{ + struct compat_f2fs_move_range __user *urange; + struct f2fs_move_range range; + int err; + + urange = compat_ptr(arg); + err = get_user(range.dst_fd, &urange->dst_fd); + err |= get_user(range.pos_in, &urange->pos_in); + err |= get_user(range.pos_out, &urange->pos_out); + err |= get_user(range.len, &urange->len); + if (err) + return -EFAULT; + + return __f2fs_ioc_move_range(file, &range); +} + long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { + if (unlikely(f2fs_cp_error(F2FS_I_SB(file_inode(file))))) + return -EIO; + if (!f2fs_is_checkpoint_ready(F2FS_I_SB(file_inode(file)))) + return -ENOSPC; + switch (cmd) { - case F2FS_IOC32_GETFLAGS: - cmd = F2FS_IOC_GETFLAGS; - break; - case F2FS_IOC32_SETFLAGS: - cmd = F2FS_IOC_SETFLAGS; - break; - case F2FS_IOC32_GETVERSION: - cmd = F2FS_IOC_GETVERSION; + case FS_IOC32_GETVERSION: + cmd = FS_IOC_GETVERSION; break; + case F2FS_IOC32_GARBAGE_COLLECT_RANGE: + return f2fs_compat_ioc_gc_range(file, arg); + case F2FS_IOC32_MOVE_RANGE: + return f2fs_compat_ioc_move_range(file, arg); case F2FS_IOC_START_ATOMIC_WRITE: + case F2FS_IOC_START_ATOMIC_REPLACE: case F2FS_IOC_COMMIT_ATOMIC_WRITE: case F2FS_IOC_START_VOLATILE_WRITE: case F2FS_IOC_RELEASE_VOLATILE_WRITE: - case F2FS_IOC_ABORT_VOLATILE_WRITE: + case F2FS_IOC_ABORT_ATOMIC_WRITE: case F2FS_IOC_SHUTDOWN: - case F2FS_IOC_SET_ENCRYPTION_POLICY: - case F2FS_IOC_GET_ENCRYPTION_PWSALT: - case F2FS_IOC_GET_ENCRYPTION_POLICY: + case FITRIM: + case FS_IOC_SET_ENCRYPTION_POLICY: + case FS_IOC_GET_ENCRYPTION_PWSALT: + case FS_IOC_GET_ENCRYPTION_POLICY: + case FS_IOC_GET_ENCRYPTION_POLICY_EX: + case FS_IOC_ADD_ENCRYPTION_KEY: + case FS_IOC_REMOVE_ENCRYPTION_KEY: + case FS_IOC_REMOVE_ENCRYPTION_KEY_ALL_USERS: + case FS_IOC_GET_ENCRYPTION_KEY_STATUS: + case FS_IOC_GET_ENCRYPTION_NONCE: case F2FS_IOC_GARBAGE_COLLECT: - case F2FS_IOC_GARBAGE_COLLECT_RANGE: case F2FS_IOC_WRITE_CHECKPOINT: case F2FS_IOC_DEFRAGMENT: - case F2FS_IOC_MOVE_RANGE: case F2FS_IOC_FLUSH_DEVICE: + case F2FS_IOC_GET_FEATURES: + case F2FS_IOC_GET_PIN_FILE: + case F2FS_IOC_SET_PIN_FILE: + case F2FS_IOC_PRECACHE_EXTENTS: + case F2FS_IOC_RESIZE_FS: + case FS_IOC_ENABLE_VERITY: + case FS_IOC_MEASURE_VERITY: + case FS_IOC_READ_VERITY_METADATA: + case FS_IOC_GETFSLABEL: + case FS_IOC_SETFSLABEL: + case F2FS_IOC_GET_COMPRESS_BLOCKS: + case F2FS_IOC_RELEASE_COMPRESS_BLOCKS: + case F2FS_IOC_RESERVE_COMPRESS_BLOCKS: + case F2FS_IOC_SEC_TRIM_FILE: + case F2FS_IOC_GET_COMPRESS_OPTION: + case F2FS_IOC_SET_COMPRESS_OPTION: + case F2FS_IOC_DECOMPRESS_FILE: + case F2FS_IOC_COMPRESS_FILE: + case F2FS_IOC_GET_DEV_ALIAS_FILE: + case F2FS_IOC_IO_PRIO: break; default: return -ENOIOCTLCMD; } - return f2fs_ioctl(file, cmd, (unsigned long) compat_ptr(arg)); + return __f2fs_ioctl(file, cmd, (unsigned long) compat_ptr(arg)); } #endif const struct file_operations f2fs_file_operations = { .llseek = f2fs_llseek, - .read_iter = generic_file_read_iter, + .read_iter = f2fs_file_read_iter, .write_iter = f2fs_file_write_iter, + .iopoll = iocb_bio_iopoll, .open = f2fs_file_open, .release = f2fs_release_file, - .mmap = f2fs_file_mmap, + .mmap_prepare = f2fs_file_mmap_prepare, + .flush = f2fs_file_flush, .fsync = f2fs_sync_file, .fallocate = f2fs_fallocate, .unlocked_ioctl = f2fs_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = f2fs_compat_ioctl, #endif - .splice_read = generic_file_splice_read, + .splice_read = f2fs_file_splice_read, .splice_write = iter_file_splice_write, + .fadvise = f2fs_file_fadvise, + .fop_flags = FOP_BUFFER_RASYNC, }; |