diff options
50 files changed, 438 insertions, 249 deletions
diff --git a/block/bdev.c b/block/bdev.c index da2a167a4d08..2af3dca56f3d 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -912,7 +912,7 @@ int bdev_open(struct block_device *bdev, blk_mode_t mode, void *holder, disk_unblock_events(disk); bdev_file->f_flags |= O_LARGEFILE; - bdev_file->f_mode |= FMODE_BUF_RASYNC | FMODE_CAN_ODIRECT; + bdev_file->f_mode |= FMODE_CAN_ODIRECT; if (bdev_nowait(bdev)) bdev_file->f_mode |= FMODE_NOWAIT; if (mode & BLK_OPEN_RESTRICT_WRITES) diff --git a/block/fops.c b/block/fops.c index 679d9b752fe8..af6c244314af 100644 --- a/block/fops.c +++ b/block/fops.c @@ -863,6 +863,7 @@ const struct file_operations def_blk_fops = { .splice_read = filemap_splice_read, .splice_write = iter_file_splice_write, .fallocate = blkdev_fallocate, + .fop_flags = FOP_BUFFER_RASYNC, }; static __init int blkdev_init(void) diff --git a/drivers/dax/device.c b/drivers/dax/device.c index 93ebedc5ec8c..c24ef4d3cf31 100644 --- a/drivers/dax/device.c +++ b/drivers/dax/device.c @@ -377,7 +377,7 @@ static const struct file_operations dax_fops = { .release = dax_release, .get_unmapped_area = dax_get_unmapped_area, .mmap = dax_mmap, - .mmap_supported_flags = MAP_SYNC, + .fop_flags = FOP_MMAP_SYNC, }; static void dev_dax_cdev_del(void *cdev) diff --git a/fs/afs/rotate.c b/fs/afs/rotate.c index ed04bd1eeae8..ed09d4d4c211 100644 --- a/fs/afs/rotate.c +++ b/fs/afs/rotate.c @@ -541,11 +541,13 @@ pick_server: test_bit(AFS_SE_EXCLUDED, &se->flags) || !test_bit(AFS_SERVER_FL_RESPONDING, &s->flags)) continue; - es = op->server_states->endpoint_state; + es = op->server_states[i].endpoint_state; sal = es->addresses; afs_get_address_preferences_rcu(op->net, sal); for (j = 0; j < sal->nr_addrs; j++) { + if (es->failed_set & (1 << j)) + continue; if (!sal->addrs[j].peer) continue; if (sal->addrs[j].prio > best_prio) { @@ -605,6 +607,8 @@ iterate_address: best_prio = -1; addr_index = 0; for (i = 0; i < alist->nr_addrs; i++) { + if (!(set & (1 << i))) + continue; if (alist->addrs[i].prio > best_prio) { addr_index = i; best_prio = alist->addrs[i].prio; @@ -674,7 +678,7 @@ no_more_servers: for (i = 0; i < op->server_list->nr_servers; i++) { struct afs_endpoint_state *estate; - estate = op->server_states->endpoint_state; + estate = op->server_states[i].endpoint_state; error = READ_ONCE(estate->error); if (error < 0) afs_op_accumulate_error(op, error, estate->abort_code); @@ -122,7 +122,7 @@ struct kioctx { unsigned long mmap_base; unsigned long mmap_size; - struct page **ring_pages; + struct folio **ring_folios; long nr_pages; struct rcu_work free_rwork; /* see free_ioctx() */ @@ -160,7 +160,7 @@ struct kioctx { spinlock_t completion_lock; } ____cacheline_aligned_in_smp; - struct page *internal_pages[AIO_RING_PAGES]; + struct folio *internal_folios[AIO_RING_PAGES]; struct file *aio_ring_file; unsigned id; @@ -334,19 +334,20 @@ static void aio_free_ring(struct kioctx *ctx) put_aio_ring_file(ctx); for (i = 0; i < ctx->nr_pages; i++) { - struct page *page; - pr_debug("pid(%d) [%d] page->count=%d\n", current->pid, i, - page_count(ctx->ring_pages[i])); - page = ctx->ring_pages[i]; - if (!page) + struct folio *folio = ctx->ring_folios[i]; + + if (!folio) continue; - ctx->ring_pages[i] = NULL; - put_page(page); + + pr_debug("pid(%d) [%d] folio->count=%d\n", current->pid, i, + folio_ref_count(folio)); + ctx->ring_folios[i] = NULL; + folio_put(folio); } - if (ctx->ring_pages && ctx->ring_pages != ctx->internal_pages) { - kfree(ctx->ring_pages); - ctx->ring_pages = NULL; + if (ctx->ring_folios && ctx->ring_folios != ctx->internal_folios) { + kfree(ctx->ring_folios); + ctx->ring_folios = NULL; } } @@ -441,7 +442,7 @@ static int aio_migrate_folio(struct address_space *mapping, struct folio *dst, idx = src->index; if (idx < (pgoff_t)ctx->nr_pages) { /* Make sure the old folio hasn't already been changed */ - if (ctx->ring_pages[idx] != &src->page) + if (ctx->ring_folios[idx] != src) rc = -EAGAIN; } else rc = -EINVAL; @@ -465,8 +466,8 @@ static int aio_migrate_folio(struct address_space *mapping, struct folio *dst, */ spin_lock_irqsave(&ctx->completion_lock, flags); folio_migrate_copy(dst, src); - BUG_ON(ctx->ring_pages[idx] != &src->page); - ctx->ring_pages[idx] = &dst->page; + BUG_ON(ctx->ring_folios[idx] != src); + ctx->ring_folios[idx] = dst; spin_unlock_irqrestore(&ctx->completion_lock, flags); /* The old folio is no longer accessible. */ @@ -516,28 +517,30 @@ static int aio_setup_ring(struct kioctx *ctx, unsigned int nr_events) nr_events = (PAGE_SIZE * nr_pages - sizeof(struct aio_ring)) / sizeof(struct io_event); - ctx->ring_pages = ctx->internal_pages; + ctx->ring_folios = ctx->internal_folios; if (nr_pages > AIO_RING_PAGES) { - ctx->ring_pages = kcalloc(nr_pages, sizeof(struct page *), - GFP_KERNEL); - if (!ctx->ring_pages) { + ctx->ring_folios = kcalloc(nr_pages, sizeof(struct folio *), + GFP_KERNEL); + if (!ctx->ring_folios) { put_aio_ring_file(ctx); return -ENOMEM; } } for (i = 0; i < nr_pages; i++) { - struct page *page; - page = find_or_create_page(file->f_mapping, - i, GFP_USER | __GFP_ZERO); - if (!page) + struct folio *folio; + + folio = __filemap_get_folio(file->f_mapping, i, + FGP_LOCK | FGP_ACCESSED | FGP_CREAT, + GFP_USER | __GFP_ZERO); + if (IS_ERR(folio)) break; - pr_debug("pid(%d) page[%d]->count=%d\n", - current->pid, i, page_count(page)); - SetPageUptodate(page); - unlock_page(page); - ctx->ring_pages[i] = page; + pr_debug("pid(%d) [%d] folio->count=%d\n", current->pid, i, + folio_ref_count(folio)); + folio_end_read(folio, true); + + ctx->ring_folios[i] = folio; } ctx->nr_pages = i; @@ -570,7 +573,7 @@ static int aio_setup_ring(struct kioctx *ctx, unsigned int nr_events) ctx->user_id = ctx->mmap_base; ctx->nr_events = nr_events; /* trusted copy */ - ring = page_address(ctx->ring_pages[0]); + ring = folio_address(ctx->ring_folios[0]); ring->nr = nr_events; /* user copy */ ring->id = ~0U; ring->head = ring->tail = 0; @@ -578,7 +581,7 @@ static int aio_setup_ring(struct kioctx *ctx, unsigned int nr_events) ring->compat_features = AIO_RING_COMPAT_FEATURES; ring->incompat_features = AIO_RING_INCOMPAT_FEATURES; ring->header_length = sizeof(struct aio_ring); - flush_dcache_page(ctx->ring_pages[0]); + flush_dcache_folio(ctx->ring_folios[0]); return 0; } @@ -689,9 +692,9 @@ static int ioctx_add_table(struct kioctx *ctx, struct mm_struct *mm) /* While kioctx setup is in progress, * we are protected from page migration - * changes ring_pages by ->ring_lock. + * changes ring_folios by ->ring_lock. */ - ring = page_address(ctx->ring_pages[0]); + ring = folio_address(ctx->ring_folios[0]); ring->id = ctx->id; return 0; } @@ -1033,7 +1036,7 @@ static void user_refill_reqs_available(struct kioctx *ctx) * against ctx->completed_events below will make sure we do the * safe/right thing. */ - ring = page_address(ctx->ring_pages[0]); + ring = folio_address(ctx->ring_folios[0]); head = ring->head; refill_reqs_available(ctx, head, ctx->tail); @@ -1145,12 +1148,12 @@ static void aio_complete(struct aio_kiocb *iocb) if (++tail >= ctx->nr_events) tail = 0; - ev_page = page_address(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]); + ev_page = folio_address(ctx->ring_folios[pos / AIO_EVENTS_PER_PAGE]); event = ev_page + pos % AIO_EVENTS_PER_PAGE; *event = iocb->ki_res; - flush_dcache_page(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]); + flush_dcache_folio(ctx->ring_folios[pos / AIO_EVENTS_PER_PAGE]); pr_debug("%p[%u]: %p: %p %Lx %Lx %Lx\n", ctx, tail, iocb, (void __user *)(unsigned long)iocb->ki_res.obj, @@ -1163,10 +1166,10 @@ static void aio_complete(struct aio_kiocb *iocb) ctx->tail = tail; - ring = page_address(ctx->ring_pages[0]); + ring = folio_address(ctx->ring_folios[0]); head = ring->head; ring->tail = tail; - flush_dcache_page(ctx->ring_pages[0]); + flush_dcache_folio(ctx->ring_folios[0]); ctx->completed_events++; if (ctx->completed_events > 1) @@ -1238,8 +1241,8 @@ static long aio_read_events_ring(struct kioctx *ctx, sched_annotate_sleep(); mutex_lock(&ctx->ring_lock); - /* Access to ->ring_pages here is protected by ctx->ring_lock. */ - ring = page_address(ctx->ring_pages[0]); + /* Access to ->ring_folios here is protected by ctx->ring_lock. */ + ring = folio_address(ctx->ring_folios[0]); head = ring->head; tail = ring->tail; @@ -1260,20 +1263,20 @@ static long aio_read_events_ring(struct kioctx *ctx, while (ret < nr) { long avail; struct io_event *ev; - struct page *page; + struct folio *folio; avail = (head <= tail ? tail : ctx->nr_events) - head; if (head == tail) break; pos = head + AIO_EVENTS_OFFSET; - page = ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]; + folio = ctx->ring_folios[pos / AIO_EVENTS_PER_PAGE]; pos %= AIO_EVENTS_PER_PAGE; avail = min(avail, nr - ret); avail = min_t(long, avail, AIO_EVENTS_PER_PAGE - pos); - ev = page_address(page); + ev = folio_address(folio); copy_ret = copy_to_user(event + ret, ev + pos, sizeof(*ev) * avail); @@ -1287,9 +1290,9 @@ static long aio_read_events_ring(struct kioctx *ctx, head %= ctx->nr_events; } - ring = page_address(ctx->ring_pages[0]); + ring = folio_address(ctx->ring_folios[0]); ring->head = head; - flush_dcache_page(ctx->ring_pages[0]); + flush_dcache_folio(ctx->ring_folios[0]); pr_debug("%li h%u t%u\n", ret, head, tail); out: diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c index 0496cb5b6eab..42bd1cb7c9cd 100644 --- a/fs/anon_inodes.c +++ b/fs/anon_inodes.c @@ -149,6 +149,38 @@ struct file *anon_inode_getfile(const char *name, EXPORT_SYMBOL_GPL(anon_inode_getfile); /** + * anon_inode_getfile_fmode - creates a new file instance by hooking it up to an + * anonymous inode, and a dentry that describe the "class" + * of the file + * + * @name: [in] name of the "class" of the new file + * @fops: [in] file operations for the new file + * @priv: [in] private data for the new file (will be file's private_data) + * @flags: [in] flags + * @f_mode: [in] fmode + * + * Creates a new file by hooking it on a single inode. This is useful for files + * that do not need to have a full-fledged inode in order to operate correctly. + * All the files created with anon_inode_getfile() will share a single inode, + * hence saving memory and avoiding code duplication for the file/inode/dentry + * setup. Allows setting the fmode. Returns the newly created file* or an error + * pointer. + */ +struct file *anon_inode_getfile_fmode(const char *name, + const struct file_operations *fops, + void *priv, int flags, fmode_t f_mode) +{ + struct file *file; + + file = __anon_inode_getfile(name, fops, priv, flags, NULL, false); + if (!IS_ERR(file)) + file->f_mode |= f_mode; + + return file; +} +EXPORT_SYMBOL_GPL(anon_inode_getfile_fmode); + +/** * anon_inode_create_getfile - Like anon_inode_getfile(), but creates a new * !S_PRIVATE anon inode rather than reuse the * singleton anon inode and calls the @@ -271,6 +303,7 @@ int anon_inode_create_getfd(const char *name, const struct file_operations *fops return __anon_inode_getfd(name, fops, priv, flags, context_inode, true); } + static int __init anon_inode_init(void) { anon_inode_mnt = kern_mount(&anon_inode_fs_type); diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c index 6f114803c6f2..65b04b3c2679 100644 --- a/fs/bcachefs/fs.c +++ b/fs/bcachefs/fs.c @@ -844,6 +844,9 @@ static int bch2_getattr(struct mnt_idmap *idmap, stat->blksize = block_bytes(c); stat->blocks = inode->v.i_blocks; + stat->subvol = inode->ei_subvol; + stat->result_mask |= STATX_SUBVOL; + if (request_mask & STATX_BTIME) { stat->result_mask |= STATX_BTIME; stat->btime = bch2_time_to_timespec(c, inode->ei_inode.bi_otime); diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index f9d76072398d..1640c46f2153 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -3719,8 +3719,7 @@ static int btrfs_file_open(struct inode *inode, struct file *filp) { int ret; - filp->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC | FMODE_BUF_WASYNC | - FMODE_CAN_ODIRECT; + filp->f_mode |= FMODE_NOWAIT | FMODE_CAN_ODIRECT; ret = fsverity_file_open(inode, filp); if (ret) @@ -3850,6 +3849,7 @@ const struct file_operations btrfs_file_operations = { .compat_ioctl = btrfs_compat_ioctl, #endif .remap_file_range = btrfs_remap_file_range, + .fop_flags = FOP_BUFFER_RASYNC | FOP_BUFFER_WASYNC, }; int btrfs_fdatawrite_range(struct inode *inode, loff_t start, loff_t end) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 7fed887e700c..f454ba349683 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -8789,6 +8789,9 @@ static int btrfs_getattr(struct mnt_idmap *idmap, generic_fillattr(idmap, request_mask, inode, stat); stat->dev = BTRFS_I(inode)->root->anon_dev; + stat->subvol = BTRFS_I(inode)->root->root_key.objectid; + stat->result_mask |= STATX_SUBVOL; + spin_lock(&BTRFS_I(inode)->lock); delalloc_bytes = BTRFS_I(inode)->new_delalloc_bytes; inode_bytes = inode_get_bytes(inode); diff --git a/fs/dcache.c b/fs/dcache.c index 71a8e943a0fa..407095188f83 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -355,7 +355,7 @@ static inline void __d_clear_type_and_inode(struct dentry *dentry) flags &= ~DCACHE_ENTRY_TYPE; WRITE_ONCE(dentry->d_flags, flags); dentry->d_inode = NULL; - if (dentry->d_flags & DCACHE_LRU_LIST) + if (flags & DCACHE_LRU_LIST) this_cpu_inc(nr_dentry_negative); } diff --git a/fs/direct-io.c b/fs/direct-io.c index 62c97ff9e852..b0aafe640fa4 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -1217,7 +1217,6 @@ ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, */ inode_dio_begin(inode); - retval = 0; sdio.blkbits = blkbits; sdio.blkfactor = i_blkbits - blkbits; sdio.block_in_file = offset >> blkbits; diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c index 3fe41964c0d8..7f9f68c00ef6 100644 --- a/fs/ecryptfs/keystore.c +++ b/fs/ecryptfs/keystore.c @@ -300,9 +300,11 @@ write_tag_66_packet(char *signature, u8 cipher_code, * | Key Identifier Size | 1 or 2 bytes | * | Key Identifier | arbitrary | * | File Encryption Key Size | 1 or 2 bytes | + * | Cipher Code | 1 byte | * | File Encryption Key | arbitrary | + * | Checksum | 2 bytes | */ - data_len = (5 + ECRYPTFS_SIG_SIZE_HEX + crypt_stat->key_size); + data_len = (8 + ECRYPTFS_SIG_SIZE_HEX + crypt_stat->key_size); *packet = kmalloc(data_len, GFP_KERNEL); message = *packet; if (!message) { diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 54d6ff22585c..28c51b0cc4db 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -885,8 +885,7 @@ static int ext4_file_open(struct inode *inode, struct file *filp) return ret; } - filp->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC | - FMODE_DIO_PARALLEL_WRITE; + filp->f_mode |= FMODE_NOWAIT; return dquot_file_open(inode, filp); } @@ -938,7 +937,6 @@ const struct file_operations ext4_file_operations = { .compat_ioctl = ext4_compat_ioctl, #endif .mmap = ext4_file_mmap, - .mmap_supported_flags = MAP_SYNC, .open = ext4_file_open, .release = ext4_release_file, .fsync = ext4_sync_file, @@ -946,6 +944,8 @@ const struct file_operations ext4_file_operations = { .splice_read = ext4_file_splice_read, .splice_write = iter_file_splice_write, .fallocate = ext4_fallocate, + .fop_flags = FOP_MMAP_SYNC | FOP_BUFFER_RASYNC | + FOP_DIO_PARALLEL_WRITE, }; const struct inode_operations ext4_file_inode_operations = { diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 044135796f2b..3fce1b80c419 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1723,10 +1723,6 @@ static const struct constant_table ext4_param_dax[] = { {} }; -/* String parameter that allows empty argument */ -#define fsparam_string_empty(NAME, OPT) \ - __fsparam(fs_param_is_string, NAME, OPT, fs_param_can_be_empty, NULL) - /* * Mount option specification * We don't use fsparam_flag_no because of the way we set the diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 1761ad125f97..2b65e09822d4 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -569,7 +569,7 @@ static int f2fs_file_open(struct inode *inode, struct file *filp) if (err) return err; - filp->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC; + filp->f_mode |= FMODE_NOWAIT; filp->f_mode |= FMODE_CAN_ODIRECT; return dquot_file_open(inode, filp); @@ -5045,4 +5045,5 @@ const struct file_operations f2fs_file_operations = { .splice_read = f2fs_file_splice_read, .splice_write = iter_file_splice_write, .fadvise = f2fs_file_fadvise, + .fop_flags = FOP_BUFFER_RASYNC, }; diff --git a/fs/fcntl.c b/fs/fcntl.c index 54cc85d3338e..300e5d9ad913 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -327,6 +327,22 @@ static long fcntl_set_rw_hint(struct file *file, unsigned int cmd, return 0; } +/* Is the file descriptor a dup of the file? */ +static long f_dupfd_query(int fd, struct file *filp) +{ + CLASS(fd_raw, f)(fd); + + /* + * We can do the 'fdput()' immediately, as the only thing that + * matters is the pointer value which isn't changed by the fdput. + * + * Technically we didn't need a ref at all, and 'fdget()' was + * overkill, but given our lockless file pointer lookup, the + * alternatives are complicated. + */ + return f.file == filp; +} + static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, struct file *filp) { @@ -342,6 +358,9 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, case F_DUPFD_CLOEXEC: err = f_dupfd(argi, filp, O_CLOEXEC); break; + case F_DUPFD_QUERY: + err = f_dupfd_query(argi, filp); + break; case F_GETFD: err = get_close_on_exec(fd) ? FD_CLOEXEC : 0; break; @@ -446,6 +465,7 @@ static int check_fcntl_cmd(unsigned cmd) switch (cmd) { case F_DUPFD: case F_DUPFD_CLOEXEC: + case F_DUPFD_QUERY: case F_GETFD: case F_SETFD: case F_GETFL: diff --git a/fs/fhandle.c b/fs/fhandle.c index 57a12614addf..8a7f86c2139a 100644 --- a/fs/fhandle.c +++ b/fs/fhandle.c @@ -36,7 +36,7 @@ static long do_sys_name_to_handle(const struct path *path, if (f_handle.handle_bytes > MAX_HANDLE_SZ) return -EINVAL; - handle = kzalloc(sizeof(struct file_handle) + f_handle.handle_bytes, + handle = kzalloc(struct_size(handle, f_handle, f_handle.handle_bytes), GFP_KERNEL); if (!handle) return -ENOMEM; @@ -71,7 +71,7 @@ static long do_sys_name_to_handle(const struct path *path, /* copy the mount id */ if (put_user(real_mount(path->mnt)->mnt_id, mnt_id) || copy_to_user(ufh, handle, - sizeof(struct file_handle) + handle_bytes)) + struct_size(handle, f_handle, handle_bytes))) retval = -EFAULT; kfree(handle); return retval; @@ -192,7 +192,7 @@ static int handle_to_path(int mountdirfd, struct file_handle __user *ufh, retval = -EINVAL; goto out_err; } - handle = kmalloc(sizeof(struct file_handle) + f_handle.handle_bytes, + handle = kmalloc(struct_size(handle, f_handle, f_handle.handle_bytes), GFP_KERNEL); if (!handle) { retval = -ENOMEM; diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index e4f17c53ddfc..92a5b8283528 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -166,8 +166,7 @@ static void wb_wakeup_delayed(struct bdi_writeback *wb) spin_unlock_irq(&wb->work_lock); } -static void finish_writeback_work(struct bdi_writeback *wb, - struct wb_writeback_work *work) +static void finish_writeback_work(struct wb_writeback_work *work) { struct wb_completion *done = work->done; @@ -196,7 +195,7 @@ static void wb_queue_work(struct bdi_writeback *wb, list_add_tail(&work->list, &wb->work_list); mod_delayed_work(bdi_wq, &wb->dwork, 0); } else - finish_writeback_work(wb, work); + finish_writeback_work(work); spin_unlock_irq(&wb->work_lock); } @@ -1561,7 +1560,8 @@ static void inode_sleep_on_writeback(struct inode *inode) * thread's back can have unexpected consequences. */ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, - struct writeback_control *wbc) + struct writeback_control *wbc, + unsigned long dirtied_before) { if (inode->i_state & I_FREEING) return; @@ -1594,7 +1594,8 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, * We didn't write back all the pages. nfs_writepages() * sometimes bales out without doing anything. */ - if (wbc->nr_to_write <= 0) { + if (wbc->nr_to_write <= 0 && + !inode_dirtied_after(inode, dirtied_before)) { /* Slice used up. Queue for next turn. */ requeue_io(inode, wb); } else { @@ -1862,6 +1863,11 @@ static long writeback_sb_inodes(struct super_block *sb, unsigned long start_time = jiffies; long write_chunk; long total_wrote = 0; /* count both pages and inodes */ + unsigned long dirtied_before = jiffies; + + if (work->for_kupdate) + dirtied_before = jiffies - + msecs_to_jiffies(dirty_expire_interval * 10); while (!list_empty(&wb->b_io)) { struct inode *inode = wb_inode(wb->b_io.prev); @@ -1967,7 +1973,7 @@ static long writeback_sb_inodes(struct super_block *sb, spin_lock(&inode->i_lock); if (!(inode->i_state & I_DIRTY_ALL)) total_wrote++; - requeue_inode(inode, tmp_wb, &wbc); + requeue_inode(inode, tmp_wb, &wbc, dirtied_before); inode_sync_complete(inode); spin_unlock(&inode->i_lock); @@ -2069,6 +2075,7 @@ static long wb_writeback(struct bdi_writeback *wb, struct inode *inode; long progress; struct blk_plug plug; + bool queued = false; blk_start_plug(&plug); for (;;) { @@ -2098,21 +2105,24 @@ static long wb_writeback(struct bdi_writeback *wb, spin_lock(&wb->list_lock); - /* - * Kupdate and background works are special and we want to - * include all inodes that need writing. Livelock avoidance is - * handled by these works yielding to any other work so we are - * safe. - */ - if (work->for_kupdate) { - dirtied_before = jiffies - - msecs_to_jiffies(dirty_expire_interval * 10); - } else if (work->for_background) - dirtied_before = jiffies; - trace_writeback_start(wb, work); - if (list_empty(&wb->b_io)) + if (list_empty(&wb->b_io)) { + /* + * Kupdate and background works are special and we want + * to include all inodes that need writing. Livelock + * avoidance is handled by these works yielding to any + * other work so we are safe. + */ + if (work->for_kupdate) { + dirtied_before = jiffies - + msecs_to_jiffies(dirty_expire_interval * + 10); + } else if (work->for_background) + dirtied_before = jiffies; + queue_io(wb, work, dirtied_before); + queued = true; + } if (work->sb) progress = writeback_sb_inodes(work->sb, wb, work); else @@ -2127,7 +2137,7 @@ static long wb_writeback(struct bdi_writeback *wb, * mean the overall work is done. So we keep looping as long * as made some progress on cleaning pages or inodes. */ - if (progress) { + if (progress || !queued) { spin_unlock(&wb->list_lock); continue; } @@ -2262,7 +2272,7 @@ static long wb_do_writeback(struct bdi_writeback *wb) while ((work = get_next_work_item(wb)) != NULL) { trace_writeback_exec(wb, work); wrote += wb_writeback(wb, work); - finish_writeback_work(wb, work); + finish_writeback_work(work); } /* @@ -2322,8 +2332,7 @@ void wb_workfn(struct work_struct *work) } /* - * Start writeback of `nr_pages' pages on this bdi. If `nr_pages' is zero, - * write back the whole world. + * Start writeback of all dirty pages on this bdi. */ static void __wakeup_flusher_threads_bdi(struct backing_dev_info *bdi, enum wb_reason reason) @@ -2726,7 +2735,7 @@ EXPORT_SYMBOL(writeback_inodes_sb_nr); */ void writeback_inodes_sb(struct super_block *sb, enum wb_reason reason) { - return writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason); + writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason); } EXPORT_SYMBOL(writeback_inodes_sb); diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 6502c7e776d1..34ac73cc36b1 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -40,7 +40,7 @@ #include <linux/sched/mm.h> static const struct address_space_operations hugetlbfs_aops; -const struct file_operations hugetlbfs_file_operations; +static const struct file_operations hugetlbfs_file_operations; static const struct inode_operations hugetlbfs_dir_inode_operations; static const struct inode_operations hugetlbfs_inode_operations; @@ -1301,13 +1301,14 @@ static void init_once(void *foo) inode_init_once(&ei->vfs_inode); } -const struct file_operations hugetlbfs_file_operations = { +static const struct file_operations hugetlbfs_file_operations = { .read_iter = hugetlbfs_read_iter, .mmap = hugetlbfs_file_mmap, .fsync = noop_fsync, .get_unmapped_area = hugetlb_get_unmapped_area, .llseek = default_llseek, .fallocate = hugetlbfs_fallocate, + .fop_flags = FOP_HUGE_PAGES, }; static const struct inode_operations hugetlbfs_dir_inode_operations = { diff --git a/fs/jffs2/xattr.c b/fs/jffs2/xattr.c index 00224f3a8d6e..defb4162c3d5 100644 --- a/fs/jffs2/xattr.c +++ b/fs/jffs2/xattr.c @@ -1110,6 +1110,9 @@ int do_jffs2_setxattr(struct inode *inode, int xprefix, const char *xname, return rc; request = PAD(sizeof(struct jffs2_raw_xattr) + strlen(xname) + 1 + size); + if (request > c->sector_size - c->cleanmarker_size) + return -ERANGE; + rc = jffs2_reserve_space(c, request, &length, ALLOC_NORMAL, JFFS2_SUMMARY_XATTR_SIZE); if (rc) { diff --git a/fs/libfs.c b/fs/libfs.c index 3a6f2cb364f8..b635ee5adbcc 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -295,6 +295,18 @@ int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry) return 0; } +static int simple_offset_replace(struct offset_ctx *octx, struct dentry *dentry, + long offset) +{ + int ret; + + ret = mtree_store(&octx->mt, offset, dentry, GFP_KERNEL); + if (ret) + return ret; + offset_set(dentry, offset); + return 0; +} + /** * simple_offset_remove - Remove an entry to a directory's offset map * @octx: directory offset ctx to be updated @@ -346,12 +358,45 @@ int simple_offset_empty(struct dentry *dentry) } /** + * simple_offset_rename - handle directory offsets for rename + * @old_dir: parent directory of source entry + * @old_dentry: dentry of source entry + * @new_dir: parent_directory of destination entry + * @new_dentry: dentry of destination + * + * Caller provides appropriate serialization. + * + * User space expects the directory offset value of the replaced + * (new) directory entry to be unchanged after a rename. + * + * Returns zero on success, a negative errno value on failure. + */ +int simple_offset_rename(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry) +{ + struct offset_ctx *old_ctx = old_dir->i_op->get_offset_ctx(old_dir); + struct offset_ctx *new_ctx = new_dir->i_op->get_offset_ctx(new_dir); + long new_offset = dentry2offset(new_dentry); + + simple_offset_remove(old_ctx, old_dentry); + + if (new_offset) { + offset_set(new_dentry, 0); + return simple_offset_replace(new_ctx, old_dentry, new_offset); + } + return simple_offset_add(new_ctx, old_dentry); +} + +/** * simple_offset_rename_exchange - exchange rename with directory offsets * @old_dir: parent of dentry being moved * @old_dentry: dentry being moved * @new_dir: destination parent * @new_dentry: destination dentry * + * This API preserves the directory offset values. Caller provides + * appropriate serialization. + * * Returns zero on success. Otherwise a negative errno is returned and the * rename is rolled back. */ @@ -369,11 +414,11 @@ int simple_offset_rename_exchange(struct inode *old_dir, simple_offset_remove(old_ctx, old_dentry); simple_offset_remove(new_ctx, new_dentry); - ret = simple_offset_add(new_ctx, old_dentry); + ret = simple_offset_replace(new_ctx, old_dentry, new_index); if (ret) goto out_restore; - ret = simple_offset_add(old_ctx, new_dentry); + ret = simple_offset_replace(old_ctx, new_dentry, old_index); if (ret) { simple_offset_remove(new_ctx, old_dentry); goto out_restore; @@ -388,10 +433,8 @@ int simple_offset_rename_exchange(struct inode *old_dir, return 0; out_restore: - offset_set(old_dentry, old_index); - mtree_store(&old_ctx->mt, old_index, old_dentry, GFP_KERNEL); - offset_set(new_dentry, new_index); - mtree_store(&new_ctx->mt, new_index, new_dentry, GFP_KERNEL); + (void)simple_offset_replace(old_ctx, old_dentry, old_index); + (void)simple_offset_replace(new_ctx, new_dentry, new_index); return ret; } diff --git a/fs/namei.c b/fs/namei.c index c5b2a25be7d0..cb5dde0e309f 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2422,6 +2422,14 @@ static const char *path_init(struct nameidata *nd, unsigned flags) if (!f.file) return ERR_PTR(-EBADF); + if (flags & LOOKUP_LINKAT_EMPTY) { + if (f.file->f_cred != current_cred() && + !ns_capable(f.file->f_cred->user_ns, CAP_DAC_READ_SEARCH)) { + fdput(f); + return ERR_PTR(-ENOENT); + } + } + dentry = f.file->f_path.dentry; if (*s && unlikely(!d_can_lookup(dentry))) { @@ -4641,14 +4649,13 @@ int do_linkat(int olddfd, struct filename *old, int newdfd, goto out_putnames; } /* - * To use null names we require CAP_DAC_READ_SEARCH + * To use null names we require CAP_DAC_READ_SEARCH or + * that the open-time creds of the dfd matches current. * This ensures that not everyone will be able to create - * handlink using the passed filedescriptor. + * a hardlink using the passed file descriptor. */ - if (flags & AT_EMPTY_PATH && !capable(CAP_DAC_READ_SEARCH)) { - error = -ENOENT; - goto out_putnames; - } + if (flags & AT_EMPTY_PATH) + how |= LOOKUP_LINKAT_EMPTY; if (flags & AT_SYMLINK_FOLLOW) how |= LOOKUP_FOLLOW; diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c index f1a01c191cf5..8be471ce4f19 100644 --- a/fs/nilfs2/ioctl.c +++ b/fs/nilfs2/ioctl.c @@ -60,7 +60,7 @@ static int nilfs_ioctl_wrap_copy(struct the_nilfs *nilfs, if (argv->v_nmembs == 0) return 0; - if (argv->v_size > PAGE_SIZE) + if ((size_t)argv->v_size > PAGE_SIZE) return -EINVAL; /* diff --git a/fs/orangefs/dcache.c b/fs/orangefs/dcache.c index 8bbe9486e3a6..395a00ed8ac7 100644 --- a/fs/orangefs/dcache.c +++ b/fs/orangefs/dcache.c @@ -33,9 +33,7 @@ static int orangefs_revalidate_lookup(struct dentry *dentry) new_op->upcall.req.lookup.sym_follow = ORANGEFS_LOOKUP_LINK_NO_FOLLOW; new_op->upcall.req.lookup.parent_refn = parent->refn; - strncpy(new_op->upcall.req.lookup.d_name, - dentry->d_name.name, - ORANGEFS_NAME_MAX - 1); + strscpy(new_op->upcall.req.lookup.d_name, dentry->d_name.name); gossip_debug(GOSSIP_DCACHE_DEBUG, "%s:%s:%d interrupt flag [%d]\n", diff --git a/fs/orangefs/namei.c b/fs/orangefs/namei.c index c9dfd5c6a097..200558ec72f0 100644 --- a/fs/orangefs/namei.c +++ b/fs/orangefs/namei.c @@ -41,8 +41,7 @@ static int orangefs_create(struct mnt_idmap *idmap, fill_default_sys_attrs(new_op->upcall.req.create.attributes, ORANGEFS_TYPE_METAFILE, mode); - strncpy(new_op->upcall.req.create.d_name, - dentry->d_name.name, ORANGEFS_NAME_MAX - 1); + strscpy(new_op->upcall.req.create.d_name, dentry->d_name.name); ret = service_operation(new_op, __func__, get_interruptible_flag(dir)); @@ -137,8 +136,7 @@ static struct dentry *orangefs_lookup(struct inode *dir, struct dentry *dentry, &parent->refn.khandle); new_op->upcall.req.lookup.parent_refn = parent->refn; - strncpy(new_op->upcall.req.lookup.d_name, dentry->d_name.name, - ORANGEFS_NAME_MAX - 1); + strscpy(new_op->upcall.req.lookup.d_name, dentry->d_name.name); gossip_debug(GOSSIP_NAME_DEBUG, "%s: doing lookup on %s under %pU,%d\n", @@ -192,8 +190,7 @@ static int orangefs_unlink(struct inode *dir, struct dentry *dentry) return -ENOMEM; new_op->upcall.req.remove.parent_refn = parent->refn; - strncpy(new_op->upcall.req.remove.d_name, dentry->d_name.name, - ORANGEFS_NAME_MAX - 1); + strscpy(new_op->upcall.req.remove.d_name, dentry->d_name.name); ret = service_operation(new_op, "orangefs_unlink", get_interruptible_flag(inode)); @@ -247,10 +244,8 @@ static int orangefs_symlink(struct mnt_idmap *idmap, ORANGEFS_TYPE_SYMLINK, mode); - strncpy(new_op->upcall.req.sym.entry_name, - dentry->d_name.name, - ORANGEFS_NAME_MAX - 1); - strncpy(new_op->upcall.req.sym.target, symname, ORANGEFS_NAME_MAX - 1); + strscpy(new_op->upcall.req.sym.entry_name, dentry->d_name.name); + strscpy(new_op->upcall.req.sym.target, symname); ret = service_operation(new_op, __func__, get_interruptible_flag(dir)); @@ -324,8 +319,7 @@ static int orangefs_mkdir(struct mnt_idmap *idmap, struct inode *dir, fill_default_sys_attrs(new_op->upcall.req.mkdir.attributes, ORANGEFS_TYPE_DIRECTORY, mode); - strncpy(new_op->upcall.req.mkdir.d_name, - dentry->d_name.name, ORANGEFS_NAME_MAX - 1); + strscpy(new_op->upcall.req.mkdir.d_name, dentry->d_name.name); ret = service_operation(new_op, __func__, get_interruptible_flag(dir)); @@ -405,12 +399,8 @@ static int orangefs_rename(struct mnt_idmap *idmap, new_op->upcall.req.rename.old_parent_refn = ORANGEFS_I(old_dir)->refn; new_op->upcall.req.rename.new_parent_refn = ORANGEFS_I(new_dir)->refn; - strncpy(new_op->upcall.req.rename.d_old_name, - old_dentry->d_name.name, - ORANGEFS_NAME_MAX - 1); - strncpy(new_op->upcall.req.rename.d_new_name, - new_dentry->d_name.name, - ORANGEFS_NAME_MAX - 1); + strscpy(new_op->upcall.req.rename.d_old_name, old_dentry->d_name.name); + strscpy(new_op->upcall.req.rename.d_new_name, new_dentry->d_name.name); ret = service_operation(new_op, "orangefs_rename", diff --git a/fs/orangefs/super.c b/fs/orangefs/super.c index 34849b4a3243..fb4d09c2f531 100644 --- a/fs/orangefs/super.c +++ b/fs/orangefs/super.c @@ -253,9 +253,8 @@ int orangefs_remount(struct orangefs_sb_info_s *orangefs_sb) new_op = op_alloc(ORANGEFS_VFS_OP_FS_MOUNT); if (!new_op) return -ENOMEM; - strncpy(new_op->upcall.req.fs_mount.orangefs_config_server, - orangefs_sb->devname, - ORANGEFS_MAX_SERVER_ADDR_LEN); + strscpy(new_op->upcall.req.fs_mount.orangefs_config_server, + orangefs_sb->devname); gossip_debug(GOSSIP_SUPER_DEBUG, "Attempting ORANGEFS Remount via host %s\n", @@ -400,8 +399,7 @@ static int orangefs_unmount(int id, __s32 fs_id, const char *devname) return -ENOMEM; op->upcall.req.fs_umount.id = id; op->upcall.req.fs_umount.fs_id = fs_id; - strncpy(op->upcall.req.fs_umount.orangefs_config_server, - devname, ORANGEFS_MAX_SERVER_ADDR_LEN - 1); + strscpy(op->upcall.req.fs_umount.orangefs_config_server, devname); r = service_operation(op, "orangefs_fs_umount", 0); /* Not much to do about an error here. */ if (r) @@ -494,9 +492,7 @@ struct dentry *orangefs_mount(struct file_system_type *fst, if (!new_op) return ERR_PTR(-ENOMEM); - strncpy(new_op->upcall.req.fs_mount.orangefs_config_server, - devname, - ORANGEFS_MAX_SERVER_ADDR_LEN - 1); + strscpy(new_op->upcall.req.fs_mount.orangefs_config_server, devname); gossip_debug(GOSSIP_SUPER_DEBUG, "Attempting ORANGEFS Mount via host %s\n", @@ -543,9 +539,8 @@ struct dentry *orangefs_mount(struct file_system_type *fst, * on successful mount, store the devname and data * used */ - strncpy(ORANGEFS_SB(sb)->devname, - devname, - ORANGEFS_MAX_SERVER_ADDR_LEN - 1); + strscpy(ORANGEFS_SB(sb)->devname, devname); + /* mount_pending must be cleared */ ORANGEFS_SB(sb)->mount_pending = 0; diff --git a/fs/overlayfs/params.c b/fs/overlayfs/params.c index 36dcc530ac28..4860fcc4611b 100644 --- a/fs/overlayfs/params.c +++ b/fs/overlayfs/params.c @@ -139,10 +139,6 @@ static int ovl_verity_mode_def(void) return OVL_VERITY_OFF; } -#define fsparam_string_empty(NAME, OPT) \ - __fsparam(fs_param_is_string, NAME, OPT, fs_param_can_be_empty, NULL) - - const struct fs_parameter_spec ovl_parameter_spec[] = { fsparam_string_empty("lowerdir", Opt_lowerdir), fsparam_string("lowerdir+", Opt_lowerdir_add), diff --git a/fs/proc/fd.c b/fs/proc/fd.c index 6e72e5ad42bc..f4b1c8b42a51 100644 --- a/fs/proc/fd.c +++ b/fs/proc/fd.c @@ -74,7 +74,18 @@ out: return 0; } -static int proc_fdinfo_access_allowed(struct inode *inode) +static int seq_fdinfo_open(struct inode *inode, struct file *file) +{ + return single_open(file, seq_show, inode); +} + +/** + * Shared /proc/pid/fdinfo and /proc/pid/fdinfo/fd permission helper to ensure + * that the current task has PTRACE_MODE_READ in addition to the normal + * POSIX-like checks. + */ +static int proc_fdinfo_permission(struct mnt_idmap *idmap, struct inode *inode, + int mask) { bool allowed = false; struct task_struct *task = get_proc_task(inode); @@ -88,18 +99,13 @@ static int proc_fdinfo_access_allowed(struct inode *inode) if (!allowed) return -EACCES; - return 0; + return generic_permission(idmap, inode, mask); } -static int seq_fdinfo_open(struct inode *inode, struct file *file) -{ - int ret = proc_fdinfo_access_allowed(inode); - - if (ret) - return ret; - - return single_open(file, seq_show, inode); -} +static const struct inode_operations proc_fdinfo_file_inode_operations = { + .permission = proc_fdinfo_permission, + .setattr = proc_setattr, +}; static const struct file_operations proc_fdinfo_file_operations = { .open = seq_fdinfo_open, @@ -388,6 +394,8 @@ static struct dentry *proc_fdinfo_instantiate(struct dentry *dentry, ei = PROC_I(inode); ei->fd = data->fd; + inode->i_op = &proc_fdinfo_file_inode_operations; + inode->i_fop = &proc_fdinfo_file_operations; tid_fd_update_inode(task, inode, 0); @@ -407,23 +415,13 @@ static int proc_readfdinfo(struct file *file, struct dir_context *ctx) proc_fdinfo_instantiate); } -static int proc_open_fdinfo(struct inode *inode, struct file *file) -{ - int ret = proc_fdinfo_access_allowed(inode); - - if (ret) - return ret; - - return 0; -} - const struct inode_operations proc_fdinfo_inode_operations = { .lookup = proc_lookupfdinfo, + .permission = proc_fdinfo_permission, .setattr = proc_setattr, }; const struct file_operations proc_fdinfo_operations = { - .open = proc_open_fdinfo, .read = generic_read_dir, .iterate_shared = proc_readfdinfo, .llseek = generic_file_llseek, diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c index 2ba31b6d68c0..52f0b75cbce2 100644 --- a/fs/proc/proc_net.c +++ b/fs/proc/proc_net.c @@ -135,6 +135,7 @@ EXPORT_SYMBOL_GPL(proc_create_net_data); * @parent: The parent directory in which to create. * @ops: The seq_file ops with which to read the file. * @write: The write method with which to 'modify' the file. + * @state_size: The size of the per-file private state to allocate. * @data: Data for retrieval by pde_data(). * * Create a network namespaced proc file in the @parent directory with the diff --git a/fs/read_write.c b/fs/read_write.c index d4c036e82b6c..2115d1f40bd5 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -1685,7 +1685,7 @@ int generic_write_checks_count(struct kiocb *iocb, loff_t *count) if ((iocb->ki_flags & IOCB_NOWAIT) && !((iocb->ki_flags & IOCB_DIRECT) || - (file->f_mode & FMODE_BUF_WASYNC))) + (file->f_op->fop_flags & FOP_BUFFER_WASYNC))) return -EINVAL; return generic_write_check_limits(iocb->ki_filp, iocb->ki_pos, count); diff --git a/fs/seq_file.c b/fs/seq_file.c index f5fdaf3b1572..e676c8b0cf5d 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -669,18 +669,11 @@ void seq_putc(struct seq_file *m, char c) } EXPORT_SYMBOL(seq_putc); -void seq_puts(struct seq_file *m, const char *s) +void __seq_puts(struct seq_file *m, const char *s) { - int len = strlen(s); - - if (m->count + len >= m->size) { - seq_set_overflow(m); - return; - } - memcpy(m->buf + m->count, s, len); - m->count += len; + seq_write(m, s, strlen(s)); } -EXPORT_SYMBOL(seq_puts); +EXPORT_SYMBOL(__seq_puts); /** * seq_put_decimal_ull_width - A helper routine for putting decimal numbers diff --git a/fs/stat.c b/fs/stat.c index 77cdc69eb422..70bd3e888cfa 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -658,6 +658,7 @@ cp_statx(const struct kstat *stat, struct statx __user *buffer) tmp.stx_mnt_id = stat->mnt_id; tmp.stx_dio_mem_align = stat->dio_mem_align; tmp.stx_dio_offset_align = stat->dio_offset_align; + tmp.stx_subvol = stat->subvol; return copy_to_user(buffer, &tmp, sizeof(tmp)) ? -EFAULT : 0; } diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 632653e00906..2ce302b4885f 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -1230,8 +1230,7 @@ xfs_file_open( { if (xfs_is_shutdown(XFS_M(inode->i_sb))) return -EIO; - file->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC | FMODE_BUF_WASYNC | - FMODE_DIO_PARALLEL_WRITE | FMODE_CAN_ODIRECT; + file->f_mode |= FMODE_NOWAIT | FMODE_CAN_ODIRECT; return generic_file_open(inode, file); } @@ -1244,7 +1243,9 @@ xfs_dir_open( unsigned int mode; int error; - error = xfs_file_open(inode, file); + if (xfs_is_shutdown(ip->i_mount)) + return -EIO; + error = generic_file_open(inode, file); if (error) return error; @@ -1490,7 +1491,6 @@ const struct file_operations xfs_file_operations = { .compat_ioctl = xfs_file_compat_ioctl, #endif .mmap = xfs_file_mmap, - .mmap_supported_flags = MAP_SYNC, .open = xfs_file_open, .release = xfs_file_release, .fsync = xfs_file_fsync, @@ -1498,6 +1498,8 @@ const struct file_operations xfs_file_operations = { .fallocate = xfs_file_fallocate, .fadvise = xfs_file_fadvise, .remap_file_range = xfs_file_remap_range, + .fop_flags = FOP_MMAP_SYNC | FOP_BUFFER_RASYNC | + FOP_BUFFER_WASYNC | FOP_DIO_PARALLEL_WRITE, }; const struct file_operations xfs_dir_file_operations = { diff --git a/include/linux/anon_inodes.h b/include/linux/anon_inodes.h index 93a5f16d03f3..edef565c2a1a 100644 --- a/include/linux/anon_inodes.h +++ b/include/linux/anon_inodes.h @@ -9,12 +9,17 @@ #ifndef _LINUX_ANON_INODES_H #define _LINUX_ANON_INODES_H +#include <linux/types.h> + struct file_operations; struct inode; struct file *anon_inode_getfile(const char *name, const struct file_operations *fops, void *priv, int flags); +struct file *anon_inode_getfile_fmode(const char *name, + const struct file_operations *fops, + void *priv, int flags, fmode_t f_mode); struct file *anon_inode_create_getfile(const char *name, const struct file_operations *fops, void *priv, int flags, diff --git a/include/linux/file.h b/include/linux/file.h index 169692cb1906..45d0f4800abd 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -84,6 +84,7 @@ static inline void fdput_pos(struct fd f) } DEFINE_CLASS(fd, struct fd, fdput(_T), fdget(fd), int fd) +DEFINE_CLASS(fd_raw, struct fd, fdput(_T), fdget_raw(fd), int fd) extern int f_dupfd(unsigned int from, struct file *file, unsigned flags); extern int replace_fd(unsigned fd, struct file *file, unsigned flags); diff --git a/include/linux/fs.h b/include/linux/fs.h index 8dfd53b52744..de946a1fd845 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -110,23 +110,26 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, */ /* file is open for reading */ -#define FMODE_READ ((__force fmode_t)0x1) +#define FMODE_READ ((__force fmode_t)(1 << 0)) /* file is open for writing */ -#define FMODE_WRITE ((__force fmode_t)0x2) +#define FMODE_WRITE ((__force fmode_t)(1 << 1)) /* file is seekable */ -#define FMODE_LSEEK ((__force fmode_t)0x4) +#define FMODE_LSEEK ((__force fmode_t)(1 << 2)) /* file can be accessed using pread */ -#define FMODE_PREAD ((__force fmode_t)0x8) +#define FMODE_PREAD ((__force fmode_t)(1 << 3)) /* file can be accessed using pwrite */ -#define FMODE_PWRITE ((__force fmode_t)0x10) +#define FMODE_PWRITE ((__force fmode_t)(1 << 4)) /* File is opened for execution with sys_execve / sys_uselib */ -#define FMODE_EXEC ((__force fmode_t)0x20) +#define FMODE_EXEC ((__force fmode_t)(1 << 5)) /* File writes are restricted (block device specific) */ -#define FMODE_WRITE_RESTRICTED ((__force fmode_t)0x40) +#define FMODE_WRITE_RESTRICTED ((__force fmode_t)(1 << 6)) + +/* FMODE_* bits 7 to 8 */ + /* 32bit hashes as llseek() offset (for directories) */ -#define FMODE_32BITHASH ((__force fmode_t)0x200) +#define FMODE_32BITHASH ((__force fmode_t)(1 << 9)) /* 64bit hashes as llseek() offset (for directories) */ -#define FMODE_64BITHASH ((__force fmode_t)0x400) +#define FMODE_64BITHASH ((__force fmode_t)(1 << 10)) /* * Don't update ctime and mtime. @@ -134,60 +137,53 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, * Currently a special hack for the XFS open_by_handle ioctl, but we'll * hopefully graduate it to a proper O_CMTIME flag supported by open(2) soon. */ -#define FMODE_NOCMTIME ((__force fmode_t)0x800) +#define FMODE_NOCMTIME ((__force fmode_t)(1 << 11)) /* Expect random access pattern */ -#define FMODE_RANDOM ((__force fmode_t)0x1000) +#define FMODE_RANDOM ((__force fmode_t)(1 << 12)) /* File is huge (eg. /dev/mem): treat loff_t as unsigned */ -#define FMODE_UNSIGNED_OFFSET ((__force fmode_t)0x2000) +#define FMODE_UNSIGNED_OFFSET ((__force fmode_t)(1 << 13)) /* File is opened with O_PATH; almost nothing can be done with it */ -#define FMODE_PATH ((__force fmode_t)0x4000) +#define FMODE_PATH ((__force fmode_t)(1 << 14)) /* File needs atomic accesses to f_pos */ -#define FMODE_ATOMIC_POS ((__force fmode_t)0x8000) +#define FMODE_ATOMIC_POS ((__force fmode_t)(1 << 15)) /* Write access to underlying fs */ -#define FMODE_WRITER ((__force fmode_t)0x10000) +#define FMODE_WRITER ((__force fmode_t)(1 << 16)) /* Has read method(s) */ -#define FMODE_CAN_READ ((__force fmode_t)0x20000) +#define FMODE_CAN_READ ((__force fmode_t)(1 << 17)) /* Has write method(s) */ -#define FMODE_CAN_WRITE ((__force fmode_t)0x40000) +#define FMODE_CAN_WRITE ((__force fmode_t)(1 << 18)) -#define FMODE_OPENED ((__force fmode_t)0x80000) -#define FMODE_CREATED ((__force fmode_t)0x100000) +#define FMODE_OPENED ((__force fmode_t)(1 << 19)) +#define FMODE_CREATED ((__force fmode_t)(1 << 20)) /* File is stream-like */ -#define FMODE_STREAM ((__force fmode_t)0x200000) +#define FMODE_STREAM ((__force fmode_t)(1 << 21)) /* File supports DIRECT IO */ -#define FMODE_CAN_ODIRECT ((__force fmode_t)0x400000) +#define FMODE_CAN_ODIRECT ((__force fmode_t)(1 << 22)) -#define FMODE_NOREUSE ((__force fmode_t)0x800000) +#define FMODE_NOREUSE ((__force fmode_t)(1 << 23)) -/* File supports non-exclusive O_DIRECT writes from multiple threads */ -#define FMODE_DIO_PARALLEL_WRITE ((__force fmode_t)0x1000000) +/* FMODE_* bit 24 */ /* File is embedded in backing_file object */ -#define FMODE_BACKING ((__force fmode_t)0x2000000) +#define FMODE_BACKING ((__force fmode_t)(1 << 25)) /* File was opened by fanotify and shouldn't generate fanotify events */ -#define FMODE_NONOTIFY ((__force fmode_t)0x4000000) +#define FMODE_NONOTIFY ((__force fmode_t)(1 << 26)) /* File is capable of returning -EAGAIN if I/O will block */ -#define FMODE_NOWAIT ((__force fmode_t)0x8000000) +#define FMODE_NOWAIT ((__force fmode_t)(1 << 27)) /* File represents mount that needs unmounting */ -#define FMODE_NEED_UNMOUNT ((__force fmode_t)0x10000000) +#define FMODE_NEED_UNMOUNT ((__force fmode_t)(1 << 28)) /* File does not contribute to nr_files count */ -#define FMODE_NOACCOUNT ((__force fmode_t)0x20000000) - -/* File supports async buffered reads */ -#define FMODE_BUF_RASYNC ((__force fmode_t)0x40000000) - -/* File supports async nowait buffered writes */ -#define FMODE_BUF_WASYNC ((__force fmode_t)0x80000000) +#define FMODE_NOACCOUNT ((__force fmode_t)(1 << 29)) /* * Attribute flags. These should be or-ed together to figure out what @@ -1035,12 +1031,13 @@ struct file_handle { __u32 handle_bytes; int handle_type; /* file identifier */ - unsigned char f_handle[]; + unsigned char f_handle[] __counted_by(handle_bytes); }; static inline struct file *get_file(struct file *f) { - atomic_long_inc(&f->f_count); + long prior = atomic_long_fetch_inc_relaxed(&f->f_count); + WARN_ONCE(!prior, "struct file::f_count incremented from zero; use-after-free condition present!\n"); return f; } @@ -2003,8 +2000,11 @@ struct iov_iter; struct io_uring_cmd; struct offset_ctx; +typedef unsigned int __bitwise fop_flags_t; + struct file_operations { struct module *owner; + fop_flags_t fop_flags; loff_t (*llseek) (struct file *, loff_t, int); ssize_t (*read) (struct file *, char __user *, size_t, loff_t *); ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *); @@ -2017,7 +2017,6 @@ struct file_operations { long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long); long (*compat_ioctl) (struct file *, unsigned int, unsigned long); int (*mmap) (struct file *, struct vm_area_struct *); - unsigned long mmap_supported_flags; int (*open) (struct inode *, struct file *); int (*flush) (struct file *, fl_owner_t id); int (*release) (struct inode *, struct file *); @@ -2048,6 +2047,17 @@ struct file_operations { unsigned int poll_flags); } __randomize_layout; +/* Supports async buffered reads */ +#define FOP_BUFFER_RASYNC ((__force fop_flags_t)(1 << 0)) +/* Supports async buffered writes */ +#define FOP_BUFFER_WASYNC ((__force fop_flags_t)(1 << 1)) +/* Supports synchronous page faults for mappings */ +#define FOP_MMAP_SYNC ((__force fop_flags_t)(1 << 2)) +/* Supports non-exclusive O_DIRECT writes from multiple threads */ +#define FOP_DIO_PARALLEL_WRITE ((__force fop_flags_t)(1 << 3)) +/* Contains huge pages */ +#define FOP_HUGE_PAGES ((__force fop_flags_t)(1 << 4)) + /* Wrap a directory iterator that needs exclusive inode access */ int wrap_directory_iterator(struct file *, struct dir_context *, int (*) (struct file *, struct dir_context *)); @@ -2253,7 +2263,13 @@ static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags #define IS_DEADDIR(inode) ((inode)->i_flags & S_DEAD) #define IS_NOCMTIME(inode) ((inode)->i_flags & S_NOCMTIME) + +#ifdef CONFIG_SWAP #define IS_SWAPFILE(inode) ((inode)->i_flags & S_SWAPFILE) +#else +#define IS_SWAPFILE(inode) ((void)(inode), 0U) +#endif + #define IS_PRIVATE(inode) ((inode)->i_flags & S_PRIVATE) #define IS_IMA(inode) ((inode)->i_flags & S_IMA) #define IS_AUTOMOUNT(inode) ((inode)->i_flags & S_AUTOMOUNT) @@ -3340,6 +3356,8 @@ void simple_offset_init(struct offset_ctx *octx); int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry); void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry); int simple_offset_empty(struct dentry *dentry); +int simple_offset_rename(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry); int simple_offset_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, diff --git a/include/linux/fs_parser.h b/include/linux/fs_parser.h index 01542c4b87a2..d3350979115f 100644 --- a/include/linux/fs_parser.h +++ b/include/linux/fs_parser.h @@ -132,4 +132,8 @@ static inline bool fs_validate_description(const char *name, #define fsparam_path(NAME, OPT) __fsparam(fs_param_is_path, NAME, OPT, 0, NULL) #define fsparam_fd(NAME, OPT) __fsparam(fs_param_is_fd, NAME, OPT, 0, NULL) +/* String parameter that allows empty argument */ +#define fsparam_string_empty(NAME, OPT) \ + __fsparam(fs_param_is_string, NAME, OPT, fs_param_can_be_empty, NULL) + #endif /* _LINUX_FS_PARSER_H */ diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 77b30a8c6076..b06f7c426d38 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -554,17 +554,13 @@ static inline struct hugetlbfs_inode_info *HUGETLBFS_I(struct inode *inode) return container_of(inode, struct hugetlbfs_inode_info, vfs_inode); } -extern const struct file_operations hugetlbfs_file_operations; extern const struct vm_operations_struct hugetlb_vm_ops; struct file *hugetlb_file_setup(const char *name, size_t size, vm_flags_t acct, int creat_flags, int page_size_log); -static inline bool is_file_hugepages(struct file *file) +static inline bool is_file_hugepages(const struct file *file) { - if (file->f_op == &hugetlbfs_file_operations) - return true; - - return is_file_shm_hugepages(file); + return file->f_op->fop_flags & FOP_HUGE_PAGES; } static inline struct hstate *hstate_inode(struct inode *i) diff --git a/include/linux/namei.h b/include/linux/namei.h index 74e0cc14ebf8..967aa9ea9f96 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -44,6 +44,7 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT}; #define LOOKUP_BENEATH 0x080000 /* No escaping from starting point. */ #define LOOKUP_IN_ROOT 0x100000 /* Treat dirfd as fs root. */ #define LOOKUP_CACHED 0x200000 /* Only do cached lookup */ +#define LOOKUP_LINKAT_EMPTY 0x400000 /* Linkat request with empty path. */ /* LOOKUP_* flags which do scope-related checks based on the dirfd. */ #define LOOKUP_IS_SCOPED (LOOKUP_BENEATH | LOOKUP_IN_ROOT) diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index 234bcdb1fba4..8bd4fda6e027 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -118,7 +118,18 @@ void seq_vprintf(struct seq_file *m, const char *fmt, va_list args); __printf(2, 3) void seq_printf(struct seq_file *m, const char *fmt, ...); void seq_putc(struct seq_file *m, char c); -void seq_puts(struct seq_file *m, const char *s); +void __seq_puts(struct seq_file *m, const char *s); + +static __always_inline void seq_puts(struct seq_file *m, const char *s) +{ + if (!__builtin_constant_p(*s)) + __seq_puts(m, s); + else if (s[0] && !s[1]) + seq_putc(m, s[0]); + else + seq_write(m, s, __builtin_strlen(s)); +} + void seq_put_decimal_ull_width(struct seq_file *m, const char *delimiter, unsigned long long num, unsigned int width); void seq_put_decimal_ull(struct seq_file *m, const char *delimiter, diff --git a/include/linux/shm.h b/include/linux/shm.h index c55bef0538e5..1d3d3ae958fb 100644 --- a/include/linux/shm.h +++ b/include/linux/shm.h @@ -16,7 +16,6 @@ struct sysv_shm { long do_shmat(int shmid, char __user *shmaddr, int shmflg, unsigned long *addr, unsigned long shmlba); -bool is_file_shm_hugepages(struct file *file); void exit_shm(struct task_struct *task); #define shm_init_task(task) INIT_LIST_HEAD(&(task)->sysvshm.shm_clist) #else @@ -30,10 +29,6 @@ static inline long do_shmat(int shmid, char __user *shmaddr, { return -ENOSYS; } -static inline bool is_file_shm_hugepages(struct file *file) -{ - return false; -} static inline void exit_shm(struct task_struct *task) { } diff --git a/include/linux/stat.h b/include/linux/stat.h index 52150570d37a..bf92441dbad2 100644 --- a/include/linux/stat.h +++ b/include/linux/stat.h @@ -53,6 +53,7 @@ struct kstat { u32 dio_mem_align; u32 dio_offset_align; u64 change_cookie; + u64 subvol; }; /* These definitions are internal to the kernel for now. Mainly used by nfsd. */ diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h index 282e90aeb163..c0bcc185fa48 100644 --- a/include/uapi/linux/fcntl.h +++ b/include/uapi/linux/fcntl.h @@ -9,6 +9,14 @@ #define F_GETLEASE (F_LINUX_SPECIFIC_BASE + 1) /* + * Request nofications on a directory. + * See below for events that may be notified. + */ +#define F_NOTIFY (F_LINUX_SPECIFIC_BASE + 2) + +#define F_DUPFD_QUERY (F_LINUX_SPECIFIC_BASE + 3) + +/* * Cancel a blocking posix lock; internal use only until we expose an * asynchronous lock api to userspace: */ @@ -18,12 +26,6 @@ #define F_DUPFD_CLOEXEC (F_LINUX_SPECIFIC_BASE + 6) /* - * Request nofications on a directory. - * See below for events that may be notified. - */ -#define F_NOTIFY (F_LINUX_SPECIFIC_BASE+2) - -/* * Set and get of pipe page size array */ #define F_SETPIPE_SZ (F_LINUX_SPECIFIC_BASE + 7) diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h index 2f2ee82d5517..67626d535316 100644 --- a/include/uapi/linux/stat.h +++ b/include/uapi/linux/stat.h @@ -126,8 +126,9 @@ struct statx { __u64 stx_mnt_id; __u32 stx_dio_mem_align; /* Memory buffer alignment for direct I/O */ __u32 stx_dio_offset_align; /* File offset alignment for direct I/O */ + __u64 stx_subvol; /* Subvolume identifier */ /* 0xa0 */ - __u64 __spare3[12]; /* Spare space for future expansion */ + __u64 __spare3[11]; /* Spare space for future expansion */ /* 0x100 */ }; @@ -155,6 +156,7 @@ struct statx { #define STATX_MNT_ID 0x00001000U /* Got stx_mnt_id */ #define STATX_DIOALIGN 0x00002000U /* Want/got direct I/O alignment info */ #define STATX_MNT_ID_UNIQUE 0x00004000U /* Want/got extended stx_mount_id */ +#define STATX_SUBVOL 0x00008000U /* Want/got stx_subvol */ #define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */ diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index c170a2b8d2cf..380b9ce1d301 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -471,7 +471,7 @@ static void io_prep_async_work(struct io_kiocb *req) /* don't serialize this request if the fs doesn't need it */ if (should_hash && (req->file->f_flags & O_DIRECT) && - (req->file->f_mode & FMODE_DIO_PARALLEL_WRITE)) + (req->file->f_op->fop_flags & FOP_DIO_PARALLEL_WRITE)) should_hash = false; if (should_hash || (ctx->flags & IORING_SETUP_IOPOLL)) io_wq_hash_work(&req->work, file_inode(req->file)); diff --git a/io_uring/rw.c b/io_uring/rw.c index c8d48287439e..2382116aa4b2 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -683,7 +683,8 @@ static bool io_rw_should_retry(struct io_kiocb *req) * just use poll if we can, and don't attempt if the fs doesn't * support callback based unlocks */ - if (io_file_can_poll(req) || !(req->file->f_mode & FMODE_BUF_RASYNC)) + if (io_file_can_poll(req) || + !(req->file->f_op->fop_flags & FOP_BUFFER_RASYNC)) return false; wait->wait.func = io_async_buf_func; @@ -1029,10 +1030,10 @@ int io_write(struct io_kiocb *req, unsigned int issue_flags) if (unlikely(!io_file_supports_nowait(req))) goto copy_iov; - /* File path supports NOWAIT for non-direct_IO only for block devices. */ + /* Check if we can support NOWAIT. */ if (!(kiocb->ki_flags & IOCB_DIRECT) && - !(kiocb->ki_filp->f_mode & FMODE_BUF_WASYNC) && - (req->flags & REQ_F_ISREG)) + !(req->file->f_op->fop_flags & FOP_BUFFER_WASYNC) && + (req->flags & REQ_F_ISREG)) goto copy_iov; kiocb->ki_flags |= IOCB_NOWAIT; diff --git a/ipc/shm.c b/ipc/shm.c index a89f001a8bf0..3e3071252dac 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -662,8 +662,8 @@ static const struct file_operations shm_file_operations = { }; /* - * shm_file_operations_huge is now identical to shm_file_operations, - * but we keep it distinct for the sake of is_file_shm_hugepages(). + * shm_file_operations_huge is now identical to shm_file_operations + * except for fop_flags */ static const struct file_operations shm_file_operations_huge = { .mmap = shm_mmap, @@ -672,13 +672,9 @@ static const struct file_operations shm_file_operations_huge = { .get_unmapped_area = shm_get_unmapped_area, .llseek = noop_llseek, .fallocate = shm_fallocate, + .fop_flags = FOP_HUGE_PAGES, }; -bool is_file_shm_hugepages(struct file *file) -{ - return file->f_op == &shm_file_operations_huge; -} - static const struct vm_operations_struct shm_vm_ops = { .open = shm_open, /* callback for a new vm-area open */ .close = shm_close, /* callback for when the vm-area is released */ diff --git a/mm/mmap.c b/mm/mmap.c index 6dbda99a47da..3490af70f259 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1294,7 +1294,9 @@ unsigned long do_mmap(struct file *file, unsigned long addr, if (!file_mmap_ok(file, inode, pgoff, len)) return -EOVERFLOW; - flags_mask = LEGACY_MAP_MASK | file->f_op->mmap_supported_flags; + flags_mask = LEGACY_MAP_MASK; + if (file->f_op->fop_flags & FOP_MMAP_SYNC) + flags_mask |= MAP_SYNC; switch (flags & MAP_TYPE) { case MAP_SHARED: diff --git a/mm/shmem.c b/mm/shmem.c index 94ab99b6b574..1f84a41aeb85 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -3467,8 +3467,7 @@ static int shmem_rename2(struct mnt_idmap *idmap, return error; } - simple_offset_remove(shmem_get_offset_ctx(old_dir), old_dentry); - error = simple_offset_add(shmem_get_offset_ctx(new_dir), old_dentry); + error = simple_offset_rename(old_dir, old_dentry, new_dir, new_dentry); if (error) return error; diff --git a/tools/testing/selftests/core/close_range_test.c b/tools/testing/selftests/core/close_range_test.c index c59e4adb905d..991c473e3859 100644 --- a/tools/testing/selftests/core/close_range_test.c +++ b/tools/testing/selftests/core/close_range_test.c @@ -17,6 +17,15 @@ #include "../kselftest_harness.h" #include "../clone3/clone3_selftests.h" + +#ifndef F_LINUX_SPECIFIC_BASE +#define F_LINUX_SPECIFIC_BASE 1024 +#endif + +#ifndef F_DUPFD_QUERY +#define F_DUPFD_QUERY (F_LINUX_SPECIFIC_BASE + 3) +#endif + static inline int sys_close_range(unsigned int fd, unsigned int max_fd, unsigned int flags) { @@ -45,6 +54,15 @@ TEST(core_close_range) SKIP(return, "close_range() syscall not supported"); } + for (i = 0; i < 100; i++) { + ret = fcntl(open_fds[i], F_DUPFD_QUERY, open_fds[i + 1]); + if (ret < 0) { + EXPECT_EQ(errno, EINVAL); + } else { + EXPECT_EQ(ret, 0); + } + } + EXPECT_EQ(0, sys_close_range(open_fds[0], open_fds[50], 0)); for (i = 0; i <= 50; i++) @@ -358,7 +376,7 @@ TEST(close_range_cloexec_unshare) */ TEST(close_range_cloexec_syzbot) { - int fd1, fd2, fd3, flags, ret, status; + int fd1, fd2, fd3, fd4, flags, ret, status; pid_t pid; struct __clone_args args = { .flags = CLONE_FILES, @@ -372,6 +390,13 @@ TEST(close_range_cloexec_syzbot) fd2 = dup2(fd1, 1000); EXPECT_GT(fd2, 0); + flags = fcntl(fd1, F_DUPFD_QUERY, fd2); + if (flags < 0) { + EXPECT_EQ(errno, EINVAL); + } else { + EXPECT_EQ(flags, 1); + } + pid = sys_clone3(&args, sizeof(args)); ASSERT_GE(pid, 0); @@ -396,6 +421,15 @@ TEST(close_range_cloexec_syzbot) fd3 = dup2(fd1, 42); EXPECT_GT(fd3, 0); + flags = fcntl(fd1, F_DUPFD_QUERY, fd3); + if (flags < 0) { + EXPECT_EQ(errno, EINVAL); + } else { + EXPECT_EQ(flags, 1); + } + + + /* * Duplicating the file descriptor must remove the * FD_CLOEXEC flag. @@ -426,6 +460,24 @@ TEST(close_range_cloexec_syzbot) fd3 = dup2(fd1, 42); EXPECT_GT(fd3, 0); + flags = fcntl(fd1, F_DUPFD_QUERY, fd3); + if (flags < 0) { + EXPECT_EQ(errno, EINVAL); + } else { + EXPECT_EQ(flags, 1); + } + + fd4 = open("/dev/null", O_RDWR); + EXPECT_GT(fd4, 0); + + /* Same inode, different file pointers. */ + flags = fcntl(fd1, F_DUPFD_QUERY, fd4); + if (flags < 0) { + EXPECT_EQ(errno, EINVAL); + } else { + EXPECT_EQ(flags, 0); + } + flags = fcntl(fd3, F_GETFD); EXPECT_GT(flags, -1); EXPECT_EQ(flags & FD_CLOEXEC, 0); @@ -433,6 +485,7 @@ TEST(close_range_cloexec_syzbot) EXPECT_EQ(close(fd1), 0); EXPECT_EQ(close(fd2), 0); EXPECT_EQ(close(fd3), 0); + EXPECT_EQ(close(fd4), 0); } /* |