diff options
Diffstat (limited to 'fs')
62 files changed, 1325 insertions, 1038 deletions
diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt index 58c2bbd385ad..57a27c42b5ac 100644 --- a/fs/Kconfig.binfmt +++ b/fs/Kconfig.binfmt @@ -1,6 +1,6 @@ config BINFMT_ELF bool "Kernel support for ELF binaries" - depends on MMU && (BROKEN || !FRV) + depends on MMU select ELFCORE default y ---help--- @@ -35,7 +35,7 @@ config ARCH_BINFMT_ELF_STATE config BINFMT_ELF_FDPIC bool "Kernel support for FDPIC ELF binaries" default y if !BINFMT_ELF - depends on (ARM || FRV || BLACKFIN || (SUPERH32 && !MMU) || C6X) + depends on (ARM || (SUPERH32 && !MMU) || C6X) select ELFCORE help ELF FDPIC binaries are based on ELF, but allow the individual load @@ -90,7 +90,6 @@ config BINFMT_SCRIPT config BINFMT_FLAT bool "Kernel support for flat binaries" depends on !MMU || ARM || M68K - depends on !FRV || BROKEN help Support uClinux FLAT format binaries. diff --git a/fs/Makefile b/fs/Makefile index add789ea270a..c9375fd2c8c4 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -11,7 +11,7 @@ obj-y := open.o read_write.o file_table.o super.o \ ioctl.o readdir.o select.o dcache.o inode.o \ attr.o bad_inode.o file.o filesystems.o namespace.o \ seq_file.o xattr.o libfs.o fs-writeback.o \ - pnode.o splice.o sync.o utimes.o \ + pnode.o splice.o sync.o utimes.o d_path.o \ stack.o fs_struct.o statfs.o fs_pin.o nsfs.o ifeq ($(CONFIG_BLOCK),y) diff --git a/fs/afs/cell.c b/fs/afs/cell.c index 9bb921d120d0..3d2c5e0e854e 100644 --- a/fs/afs/cell.c +++ b/fs/afs/cell.c @@ -25,7 +25,7 @@ static void afs_manage_cell(struct work_struct *); static void afs_dec_cells_outstanding(struct afs_net *net) { if (atomic_dec_and_test(&net->cells_outstanding)) - wake_up_atomic_t(&net->cells_outstanding); + wake_up_var(&net->cells_outstanding); } /* @@ -764,7 +764,7 @@ void afs_cell_purge(struct afs_net *net) afs_queue_cell_manager(net); _debug("wait"); - wait_on_atomic_t(&net->cells_outstanding, atomic_t_wait, - TASK_UNINTERRUPTIBLE); + wait_var_event(&net->cells_outstanding, + !atomic_read(&net->cells_outstanding)); _leave(""); } diff --git a/fs/afs/internal.h b/fs/afs/internal.h index f38d6a561a84..72217170b155 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -118,6 +118,7 @@ struct afs_call { bool ret_reply0; /* T if should return reply[0] on success */ bool upgrade; /* T to request service upgrade */ u16 service_id; /* Actual service ID (after upgrade) */ + unsigned int debug_id; /* Trace ID */ u32 operation_ID; /* operation ID for an incoming call */ u32 count; /* count for use in unmarshalling */ __be32 tmp; /* place to extract temporary data */ diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index e1126659f043..f7ae54b6a393 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -103,8 +103,8 @@ void afs_close_socket(struct afs_net *net) } _debug("outstanding %u", atomic_read(&net->nr_outstanding_calls)); - wait_on_atomic_t(&net->nr_outstanding_calls, atomic_t_wait, - TASK_UNINTERRUPTIBLE); + wait_var_event(&net->nr_outstanding_calls, + !atomic_read(&net->nr_outstanding_calls)); _debug("no outstanding calls"); kernel_sock_shutdown(net->socket, SHUT_RDWR); @@ -131,6 +131,7 @@ static struct afs_call *afs_alloc_call(struct afs_net *net, call->type = type; call->net = net; + call->debug_id = atomic_inc_return(&rxrpc_debug_id); atomic_set(&call->usage, 1); INIT_WORK(&call->async_work, afs_process_async_call); init_waitqueue_head(&call->waitq); @@ -169,13 +170,14 @@ void afs_put_call(struct afs_call *call) afs_put_server(call->net, call->cm_server); afs_put_cb_interest(call->net, call->cbi); kfree(call->request); - kfree(call); - o = atomic_dec_return(&net->nr_outstanding_calls); trace_afs_call(call, afs_call_trace_free, 0, o, __builtin_return_address(0)); + kfree(call); + + o = atomic_dec_return(&net->nr_outstanding_calls); if (o == 0) - wake_up_atomic_t(&net->nr_outstanding_calls); + wake_up_var(&net->nr_outstanding_calls); } } @@ -378,7 +380,8 @@ long afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, (async ? afs_wake_up_async_call : afs_wake_up_call_waiter), - call->upgrade); + call->upgrade, + call->debug_id); if (IS_ERR(rxcall)) { ret = PTR_ERR(rxcall); goto error_kill_call; @@ -727,7 +730,8 @@ void afs_charge_preallocation(struct work_struct *work) afs_wake_up_async_call, afs_rx_attach, (unsigned long)call, - GFP_KERNEL) < 0) + GFP_KERNEL, + call->debug_id) < 0) break; call = NULL; } diff --git a/fs/afs/server.c b/fs/afs/server.c index 1880f1b6a9f1..a43ef77dabae 100644 --- a/fs/afs/server.c +++ b/fs/afs/server.c @@ -25,7 +25,7 @@ static void afs_inc_servers_outstanding(struct afs_net *net) static void afs_dec_servers_outstanding(struct afs_net *net) { if (atomic_dec_and_test(&net->servers_outstanding)) - wake_up_atomic_t(&net->servers_outstanding); + wake_up_var(&net->servers_outstanding); } /* @@ -521,8 +521,8 @@ void afs_purge_servers(struct afs_net *net) afs_queue_server_manager(net); _debug("wait"); - wait_on_atomic_t(&net->servers_outstanding, atomic_t_wait, - TASK_UNINTERRUPTIBLE); + wait_var_event(&net->servers_outstanding, + !atomic_read(&net->servers_outstanding)); _leave(""); } @@ -68,9 +68,9 @@ struct aio_ring { #define AIO_RING_PAGES 8 struct kioctx_table { - struct rcu_head rcu; - unsigned nr; - struct kioctx *table[]; + struct rcu_head rcu; + unsigned nr; + struct kioctx __rcu *table[]; }; struct kioctx_cpu { @@ -115,7 +115,7 @@ struct kioctx { struct page **ring_pages; long nr_pages; - struct work_struct free_work; + struct rcu_work free_rwork; /* see free_ioctx() */ /* * signals when all in-flight requests are done @@ -329,7 +329,7 @@ static int aio_ring_mremap(struct vm_area_struct *vma) for (i = 0; i < table->nr; i++) { struct kioctx *ctx; - ctx = table->table[i]; + ctx = rcu_dereference(table->table[i]); if (ctx && ctx->aio_ring_file == file) { if (!atomic_read(&ctx->dead)) { ctx->user_id = ctx->mmap_base = vma->vm_start; @@ -588,10 +588,15 @@ static int kiocb_cancel(struct aio_kiocb *kiocb) return cancel(&kiocb->common); } +/* + * free_ioctx() should be RCU delayed to synchronize against the RCU + * protected lookup_ioctx() and also needs process context to call + * aio_free_ring(). Use rcu_work. + */ static void free_ioctx(struct work_struct *work) { - struct kioctx *ctx = container_of(work, struct kioctx, free_work); - + struct kioctx *ctx = container_of(to_rcu_work(work), struct kioctx, + free_rwork); pr_debug("freeing %p\n", ctx); aio_free_ring(ctx); @@ -609,8 +614,9 @@ static void free_ioctx_reqs(struct percpu_ref *ref) if (ctx->rq_wait && atomic_dec_and_test(&ctx->rq_wait->count)) complete(&ctx->rq_wait->comp); - INIT_WORK(&ctx->free_work, free_ioctx); - schedule_work(&ctx->free_work); + /* Synchronize against RCU protected table->table[] dereferences */ + INIT_RCU_WORK(&ctx->free_rwork, free_ioctx); + queue_rcu_work(system_wq, &ctx->free_rwork); } /* @@ -651,9 +657,9 @@ static int ioctx_add_table(struct kioctx *ctx, struct mm_struct *mm) while (1) { if (table) for (i = 0; i < table->nr; i++) - if (!table->table[i]) { + if (!rcu_access_pointer(table->table[i])) { ctx->id = i; - table->table[i] = ctx; + rcu_assign_pointer(table->table[i], ctx); spin_unlock(&mm->ioctx_lock); /* While kioctx setup is in progress, @@ -834,11 +840,11 @@ static int kill_ioctx(struct mm_struct *mm, struct kioctx *ctx, } table = rcu_dereference_raw(mm->ioctx_table); - WARN_ON(ctx != table->table[ctx->id]); - table->table[ctx->id] = NULL; + WARN_ON(ctx != rcu_access_pointer(table->table[ctx->id])); + RCU_INIT_POINTER(table->table[ctx->id], NULL); spin_unlock(&mm->ioctx_lock); - /* percpu_ref_kill() will do the necessary call_rcu() */ + /* free_ioctx_reqs() will do the necessary RCU synchronization */ wake_up_all(&ctx->wait); /* @@ -880,7 +886,8 @@ void exit_aio(struct mm_struct *mm) skipped = 0; for (i = 0; i < table->nr; ++i) { - struct kioctx *ctx = table->table[i]; + struct kioctx *ctx = + rcu_dereference_protected(table->table[i], true); if (!ctx) { skipped++; @@ -1069,7 +1076,7 @@ static struct kioctx *lookup_ioctx(unsigned long ctx_id) if (!table || id >= table->nr) goto out; - ctx = table->table[id]; + ctx = rcu_dereference(table->table[id]); if (ctx && ctx->user_id == ctx_id) { percpu_ref_get(&ctx->users); ret = ctx; diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c index b7c816f39404..26f6b4f41ce6 100644 --- a/fs/autofs4/dev-ioctl.c +++ b/fs/autofs4/dev-ioctl.c @@ -310,7 +310,7 @@ static int autofs_dev_ioctl_closemount(struct file *fp, struct autofs_sb_info *sbi, struct autofs_dev_ioctl *param) { - return sys_close(param->ioctlfd); + return ksys_close(param->ioctlfd); } /* diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index a7c5a9861bef..a41b48f82a70 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -241,7 +241,7 @@ ret: return retval; error: if (fd_binary > 0) - sys_close(fd_binary); + ksys_close(fd_binary); bprm->interp_flags = 0; bprm->interp_data = 0; goto ret; diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index f94b2d8c744a..26484648d090 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -1519,6 +1519,7 @@ int btrfs_check_shared(struct btrfs_root *root, u64 inum, u64 bytenr) if (!node) break; bytenr = node->val; + shared.share_count = 0; cond_resched(); } diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index c1618ab9fecf..e0460d7b5622 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -3990,7 +3990,7 @@ void btrfs_dec_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr) bg = btrfs_lookup_block_group(fs_info, bytenr); ASSERT(bg); if (atomic_dec_and_test(&bg->nocow_writers)) - wake_up_atomic_t(&bg->nocow_writers); + wake_up_var(&bg->nocow_writers); /* * Once for our lookup and once for the lookup done by a previous call * to btrfs_inc_nocow_writers() @@ -4001,8 +4001,7 @@ void btrfs_dec_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr) void btrfs_wait_nocow_writers(struct btrfs_block_group_cache *bg) { - wait_on_atomic_t(&bg->nocow_writers, atomic_t_wait, - TASK_UNINTERRUPTIBLE); + wait_var_event(&bg->nocow_writers, !atomic_read(&bg->nocow_writers)); } static const char *alloc_name(u64 flags) @@ -6526,7 +6525,7 @@ void btrfs_dec_block_group_reservations(struct btrfs_fs_info *fs_info, bg = btrfs_lookup_block_group(fs_info, start); ASSERT(bg); if (atomic_dec_and_test(&bg->reservations)) - wake_up_atomic_t(&bg->reservations); + wake_up_var(&bg->reservations); btrfs_put_block_group(bg); } @@ -6552,8 +6551,7 @@ void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg) down_write(&space_info->groups_sem); up_write(&space_info->groups_sem); - wait_on_atomic_t(&bg->reservations, atomic_t_wait, - TASK_UNINTERRUPTIBLE); + wait_var_event(&bg->reservations, !atomic_read(&bg->reservations)); } /** @@ -11061,7 +11059,7 @@ void btrfs_wait_for_snapshot_creation(struct btrfs_root *root) ret = btrfs_start_write_no_snapshotting(root); if (ret) break; - wait_on_atomic_t(&root->will_be_snapshotted, atomic_t_wait, - TASK_UNINTERRUPTIBLE); + wait_var_event(&root->will_be_snapshotted, + !atomic_read(&root->will_be_snapshotted)); } } diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 111ee282b777..3278ae592a2c 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -723,7 +723,7 @@ fail: btrfs_subvolume_release_metadata(fs_info, &pending_snapshot->block_rsv); dec_and_free: if (atomic_dec_and_test(&root->will_be_snapshotted)) - wake_up_atomic_t(&root->will_be_snapshotted); + wake_up_var(&root->will_be_snapshotted); free_pending: kfree(pending_snapshot->root_item); btrfs_free_path(pending_snapshot->path); diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index dec0907dfb8a..fcfc20de2df3 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -1370,6 +1370,7 @@ static int find_bio_stripe(struct btrfs_raid_bio *rbio, stripe_start = stripe->physical; if (physical >= stripe_start && physical < stripe_start + rbio->stripe_len && + stripe->dev->bdev && bio->bi_disk == stripe->dev->bdev->bd_disk && bio->bi_partno == stripe->dev->bdev->bd_partno) { return i; diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index d11c70bff5a9..a8bafed931f4 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -423,7 +423,7 @@ static ssize_t btrfs_nodesize_show(struct kobject *kobj, { struct btrfs_fs_info *fs_info = to_fs_info(kobj); - return snprintf(buf, PAGE_SIZE, "%u\n", fs_info->nodesize); + return snprintf(buf, PAGE_SIZE, "%u\n", fs_info->super_copy->nodesize); } BTRFS_ATTR(, nodesize, btrfs_nodesize_show); @@ -433,7 +433,8 @@ static ssize_t btrfs_sectorsize_show(struct kobject *kobj, { struct btrfs_fs_info *fs_info = to_fs_info(kobj); - return snprintf(buf, PAGE_SIZE, "%u\n", fs_info->sectorsize); + return snprintf(buf, PAGE_SIZE, "%u\n", + fs_info->super_copy->sectorsize); } BTRFS_ATTR(, sectorsize, btrfs_sectorsize_show); @@ -443,7 +444,8 @@ static ssize_t btrfs_clone_alignment_show(struct kobject *kobj, { struct btrfs_fs_info *fs_info = to_fs_info(kobj); - return snprintf(buf, PAGE_SIZE, "%u\n", fs_info->sectorsize); + return snprintf(buf, PAGE_SIZE, "%u\n", + fs_info->super_copy->sectorsize); } BTRFS_ATTR(, clone_alignment, btrfs_clone_alignment_show); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 9220f004001c..04f07144b45c 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1722,23 +1722,19 @@ static void update_super_roots(struct btrfs_fs_info *fs_info) super = fs_info->super_copy; - /* update latest btrfs_super_block::chunk_root refs */ root_item = &fs_info->chunk_root->root_item; - btrfs_set_super_chunk_root(super, root_item->bytenr); - btrfs_set_super_chunk_root_generation(super, root_item->generation); - btrfs_set_super_chunk_root_level(super, root_item->level); + super->chunk_root = root_item->bytenr; + super->chunk_root_generation = root_item->generation; + super->chunk_root_level = root_item->level; - /* update latest btrfs_super_block::root refs */ root_item = &fs_info->tree_root->root_item; - btrfs_set_super_root(super, root_item->bytenr); - btrfs_set_super_generation(super, root_item->generation); - btrfs_set_super_root_level(super, root_item->level); - + super->root = root_item->bytenr; + super->generation = root_item->generation; + super->root_level = root_item->level; if (btrfs_test_opt(fs_info, SPACE_CACHE)) - btrfs_set_super_cache_generation(super, root_item->generation); + super->cache_generation = root_item->generation; if (test_bit(BTRFS_FS_UPDATE_UUID_TREE_GEN, &fs_info->flags)) - btrfs_set_super_uuid_tree_generation(super, - root_item->generation); + super->uuid_tree_generation = root_item->generation; } int btrfs_transaction_in_commit(struct btrfs_fs_info *info) diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 6639926eed4e..b67eec3532a1 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -640,7 +640,8 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to, struct ceph_aio_request { struct kiocb *iocb; size_t total_len; - int write; + bool write; + bool should_dirty; int error; struct list_head osd_reqs; unsigned num_reqs; @@ -750,7 +751,7 @@ static void ceph_aio_complete_req(struct ceph_osd_request *req) } } - ceph_put_page_vector(osd_data->pages, num_pages, !aio_req->write); + ceph_put_page_vector(osd_data->pages, num_pages, aio_req->should_dirty); ceph_osdc_put_request(req); if (rc < 0) @@ -847,6 +848,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, size_t count = iov_iter_count(iter); loff_t pos = iocb->ki_pos; bool write = iov_iter_rw(iter) == WRITE; + bool should_dirty = !write && iter_is_iovec(iter); if (write && ceph_snap(file_inode(file)) != CEPH_NOSNAP) return -EROFS; @@ -914,6 +916,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, if (aio_req) { aio_req->iocb = iocb; aio_req->write = write; + aio_req->should_dirty = should_dirty; INIT_LIST_HEAD(&aio_req->osd_reqs); if (write) { aio_req->mtime = mtime; @@ -971,7 +974,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, len = ret; } - ceph_put_page_vector(pages, num_pages, !write); + ceph_put_page_vector(pages, num_pages, should_dirty); ceph_osdc_put_request(req); if (ret < 0) diff --git a/fs/d_path.c b/fs/d_path.c new file mode 100644 index 000000000000..e8fce6b1174f --- /dev/null +++ b/fs/d_path.c @@ -0,0 +1,470 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <linux/syscalls.h> +#include <linux/export.h> +#include <linux/uaccess.h> +#include <linux/fs_struct.h> +#include <linux/fs.h> +#include <linux/slab.h> +#include <linux/prefetch.h> +#include "mount.h" + +static int prepend(char **buffer, int *buflen, const char *str, int namelen) +{ + *buflen -= namelen; + if (*buflen < 0) + return -ENAMETOOLONG; + *buffer -= namelen; + memcpy(*buffer, str, namelen); + return 0; +} + +/** + * prepend_name - prepend a pathname in front of current buffer pointer + * @buffer: buffer pointer + * @buflen: allocated length of the buffer + * @name: name string and length qstr structure + * + * With RCU path tracing, it may race with d_move(). Use READ_ONCE() to + * make sure that either the old or the new name pointer and length are + * fetched. However, there may be mismatch between length and pointer. + * The length cannot be trusted, we need to copy it byte-by-byte until + * the length is reached or a null byte is found. It also prepends "/" at + * the beginning of the name. The sequence number check at the caller will + * retry it again when a d_move() does happen. So any garbage in the buffer + * due to mismatched pointer and length will be discarded. + * + * Load acquire is needed to make sure that we see that terminating NUL. + */ +static int prepend_name(char **buffer, int *buflen, const struct qstr *name) +{ + const char *dname = smp_load_acquire(&name->name); /* ^^^ */ + u32 dlen = READ_ONCE(name->len); + char *p; + + *buflen -= dlen + 1; + if (*buflen < 0) + return -ENAMETOOLONG; + p = *buffer -= dlen + 1; + *p++ = '/'; + while (dlen--) { + char c = *dname++; + if (!c) + break; + *p++ = c; + } + return 0; +} + +/** + * prepend_path - Prepend path string to a buffer + * @path: the dentry/vfsmount to report + * @root: root vfsmnt/dentry + * @buffer: pointer to the end of the buffer + * @buflen: pointer to buffer length + * + * The function will first try to write out the pathname without taking any + * lock other than the RCU read lock to make sure that dentries won't go away. + * It only checks the sequence number of the global rename_lock as any change + * in the dentry's d_seq will be preceded by changes in the rename_lock + * sequence number. If the sequence number had been changed, it will restart + * the whole pathname back-tracing sequence again by taking the rename_lock. + * In this case, there is no need to take the RCU read lock as the recursive + * parent pointer references will keep the dentry chain alive as long as no + * rename operation is performed. + */ +static int prepend_path(const struct path *path, + const struct path *root, + char **buffer, int *buflen) +{ + struct dentry *dentry; + struct vfsmount *vfsmnt; + struct mount *mnt; + int error = 0; + unsigned seq, m_seq = 0; + char *bptr; + int blen; + + rcu_read_lock(); +restart_mnt: + read_seqbegin_or_lock(&mount_lock, &m_seq); + seq = 0; + rcu_read_lock(); +restart: + bptr = *buffer; + blen = *buflen; + error = 0; + dentry = path->dentry; + vfsmnt = path->mnt; + mnt = real_mount(vfsmnt); + read_seqbegin_or_lock(&rename_lock, &seq); + while (dentry != root->dentry || vfsmnt != root->mnt) { + struct dentry * parent; + + if (dentry == vfsmnt->mnt_root || IS_ROOT(dentry)) { + struct mount *parent = READ_ONCE(mnt->mnt_parent); + /* Escaped? */ + if (dentry != vfsmnt->mnt_root) { + bptr = *buffer; + blen = *buflen; + error = 3; + break; + } + /* Global root? */ + if (mnt != parent) { + dentry = READ_ONCE(mnt->mnt_mountpoint); + mnt = parent; + vfsmnt = &mnt->mnt; + continue; + } + if (!error) + error = is_mounted(vfsmnt) ? 1 : 2; + break; + } + parent = dentry->d_parent; + prefetch(parent); + error = prepend_name(&bptr, &blen, &dentry->d_name); + if (error) + break; + + dentry = parent; + } + if (!(seq & 1)) + rcu_read_unlock(); + if (need_seqretry(&rename_lock, seq)) { + seq = 1; + goto restart; + } + done_seqretry(&rename_lock, seq); + + if (!(m_seq & 1)) + rcu_read_unlock(); + if (need_seqretry(&mount_lock, m_seq)) { + m_seq = 1; + goto restart_mnt; + } + done_seqretry(&mount_lock, m_seq); + + if (error >= 0 && bptr == *buffer) { + if (--blen < 0) + error = -ENAMETOOLONG; + else + *--bptr = '/'; + } + *buffer = bptr; + *buflen = blen; + return error; +} + +/** + * __d_path - return the path of a dentry + * @path: the dentry/vfsmount to report + * @root: root vfsmnt/dentry + * @buf: buffer to return value in + * @buflen: buffer length + * + * Convert a dentry into an ASCII path name. + * + * Returns a pointer into the buffer or an error code if the + * path was too long. + * + * "buflen" should be positive. + * + * If the path is not reachable from the supplied root, return %NULL. + */ +char *__d_path(const struct path *path, + const struct path *root, + char *buf, int buflen) +{ + char *res = buf + buflen; + int error; + + prepend(&res, &buflen, "\0", 1); + error = prepend_path(path, root, &res, &buflen); + + if (error < 0) + return ERR_PTR(error); + if (error > 0) + return NULL; + return res; +} + +char *d_absolute_path(const struct path *path, + char *buf, int buflen) +{ + struct path root = {}; + char *res = buf + buflen; + int error; + + prepend(&res, &buflen, "\0", 1); + error = prepend_path(path, &root, &res, &buflen); + + if (error > 1) + error = -EINVAL; + if (error < 0) + return ERR_PTR(error); + return res; +} + +/* + * same as __d_path but appends "(deleted)" for unlinked files. + */ +static int path_with_deleted(const struct path *path, + const struct path *root, + char **buf, int *buflen) +{ + prepend(buf, buflen, "\0", 1); + if (d_unlinked(path->dentry)) { + int error = prepend(buf, buflen, " (deleted)", 10); + if (error) + return error; + } + + return prepend_path(path, root, buf, buflen); +} + +static int prepend_unreachable(char **buffer, int *buflen) +{ + return prepend(buffer, buflen, "(unreachable)", 13); +} + +static void get_fs_root_rcu(struct fs_struct *fs, struct path *root) +{ + unsigned seq; + + do { + seq = read_seqcount_begin(&fs->seq); + *root = fs->root; + } while (read_seqcount_retry(&fs->seq, seq)); +} + +/** + * d_path - return the path of a dentry + * @path: path to report + * @buf: buffer to return value in + * @buflen: buffer length + * + * Convert a dentry into an ASCII path name. If the entry has been deleted + * the string " (deleted)" is appended. Note that this is ambiguous. + * + * Returns a pointer into the buffer or an error code if the path was + * too long. Note: Callers should use the returned pointer, not the passed + * in buffer, to use the name! The implementation often starts at an offset + * into the buffer, and may leave 0 bytes at the start. + * + * "buflen" should be positive. + */ +char *d_path(const struct path *path, char *buf, int buflen) +{ + char *res = buf + buflen; + struct path root; + int error; + + /* + * We have various synthetic filesystems that never get mounted. On + * these filesystems dentries are never used for lookup purposes, and + * thus don't need to be hashed. They also don't need a name until a + * user wants to identify the object in /proc/pid/fd/. The little hack + * below allows us to generate a name for these objects on demand: + * + * Some pseudo inodes are mountable. When they are mounted + * path->dentry == path->mnt->mnt_root. In that case don't call d_dname + * and instead have d_path return the mounted path. + */ + if (path->dentry->d_op && path->dentry->d_op->d_dname && + (!IS_ROOT(path->dentry) || path->dentry != path->mnt->mnt_root)) + return path->dentry->d_op->d_dname(path->dentry, buf, buflen); + + rcu_read_lock(); + get_fs_root_rcu(current->fs, &root); + error = path_with_deleted(path, &root, &res, &buflen); + rcu_read_unlock(); + + if (error < 0) + res = ERR_PTR(error); + return res; +} +EXPORT_SYMBOL(d_path); + +/* + * Helper function for dentry_operations.d_dname() members + */ +char *dynamic_dname(struct dentry *dentry, char *buffer, int buflen, + const char *fmt, ...) +{ + va_list args; + char temp[64]; + int sz; + + va_start(args, fmt); + sz = vsnprintf(temp, sizeof(temp), fmt, args) + 1; + va_end(args); + + if (sz > sizeof(temp) || sz > buflen) + return ERR_PTR(-ENAMETOOLONG); + + buffer += buflen - sz; + return memcpy(buffer, temp, sz); +} + +char *simple_dname(struct dentry *dentry, char *buffer, int buflen) +{ + char *end = buffer + buflen; + /* these dentries are never renamed, so d_lock is not needed */ + if (prepend(&end, &buflen, " (deleted)", 11) || + prepend(&end, &buflen, dentry->d_name.name, dentry->d_name.len) || + prepend(&end, &buflen, "/", 1)) + end = ERR_PTR(-ENAMETOOLONG); + return end; +} +EXPORT_SYMBOL(simple_dname); + +/* + * Write full pathname from the root of the filesystem into the buffer. + */ +static char *__dentry_path(struct dentry *d, char *buf, int buflen) +{ + struct dentry *dentry; + char *end, *retval; + int len, seq = 0; + int error = 0; + + if (buflen < 2) + goto Elong; + + rcu_read_lock(); +restart: + dentry = d; + end = buf + buflen; + len = buflen; + prepend(&end, &len, "\0", 1); + /* Get '/' right */ + retval = end-1; + *retval = '/'; + read_seqbegin_or_lock(&rename_lock, &seq); + while (!IS_ROOT(dentry)) { + struct dentry *parent = dentry->d_parent; + + prefetch(parent); + error = prepend_name(&end, &len, &dentry->d_name); + if (error) + break; + + retval = end; + dentry = parent; + } + if (!(seq & 1)) + rcu_read_unlock(); + if (need_seqretry(&rename_lock, seq)) { + seq = 1; + goto restart; + } + done_seqretry(&rename_lock, seq); + if (error) + goto Elong; + return retval; +Elong: + return ERR_PTR(-ENAMETOOLONG); +} + +char *dentry_path_raw(struct dentry *dentry, char *buf, int buflen) +{ + return __dentry_path(dentry, buf, buflen); +} +EXPORT_SYMBOL(dentry_path_raw); + +char *dentry_path(struct dentry *dentry, char *buf, int buflen) +{ + char *p = NULL; + char *retval; + + if (d_unlinked(dentry)) { + p = buf + buflen; + if (prepend(&p, &buflen, "//deleted", 10) != 0) + goto Elong; + buflen++; + } + retval = __dentry_path(dentry, buf, buflen); + if (!IS_ERR(retval) && p) + *p = '/'; /* restore '/' overriden with '\0' */ + return retval; +Elong: + return ERR_PTR(-ENAMETOOLONG); +} + +static void get_fs_root_and_pwd_rcu(struct fs_struct *fs, struct path *root, + struct path *pwd) +{ + unsigned seq; + + do { + seq = read_seqcount_begin(&fs->seq); + *root = fs->root; + *pwd = fs->pwd; + } while (read_seqcount_retry(&fs->seq, seq)); +} + +/* + * NOTE! The user-level library version returns a + * character pointer. The kernel system call just + * returns the length of the buffer filled (which + * includes the ending '\0' character), or a negative + * error value. So libc would do something like + * + * char *getcwd(char * buf, size_t size) + * { + * int retval; + * + * retval = sys_getcwd(buf, size); + * if (retval >= 0) + * return buf; + * errno = -retval; + * return NULL; + * } + */ +SYSCALL_DEFINE2(getcwd, char __user *, buf, unsigned long, size) +{ + int error; + struct path pwd, root; + char *page = __getname(); + + if (!page) + return -ENOMEM; + + rcu_read_lock(); + get_fs_root_and_pwd_rcu(current->fs, &root, &pwd); + + error = -ENOENT; + if (!d_unlinked(pwd.dentry)) { + unsigned long len; + char *cwd = page + PATH_MAX; + int buflen = PATH_MAX; + + prepend(&cwd, &buflen, "\0", 1); + error = prepend_path(&pwd, &root, &cwd, &buflen); + rcu_read_unlock(); + + if (error < 0) + goto out; + + /* Unreachable from current root */ + if (error > 0) { + error = prepend_unreachable(&cwd, &buflen); + if (error) + goto out; + } + + error = -ERANGE; + len = PATH_MAX + page - cwd; + if (len <= size) { + error = len; + if (copy_to_user(buf, cwd, len)) + error = -EFAULT; + } + } else { + rcu_read_unlock(); + } + +out: + __putname(page); + return error; +} diff --git a/fs/dcache.c b/fs/dcache.c index 7c38f39958bc..593079176123 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -14,7 +14,7 @@ * the dcache entry is deleted or garbage collected. */ -#include <linux/syscalls.h> +#include <linux/ratelimit.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/fs.h> @@ -24,18 +24,11 @@ #include <linux/hash.h> #include <linux/cache.h> #include <linux/export.h> -#include <linux/mount.h> -#include <linux/file.h> -#include <linux/uaccess.h> #include <linux/security.h> #include <linux/seqlock.h> -#include <linux/swap.h> #include <linux/bootmem.h> -#include <linux/fs_struct.h> #include <linux/bit_spinlock.h> #include <linux/rculist_bl.h> -#include <linux/prefetch.h> -#include <linux/ratelimit.h> #include <linux/list_lru.h> #include "internal.h" #include "mount.h" @@ -74,9 +67,7 @@ * dentry->d_lock * * If no ancestor relationship: - * if (dentry1 < dentry2) - * dentry1->d_lock - * dentry2->d_lock + * arbitrary, since it's serialized on rename_lock */ int sysctl_vfs_cache_pressure __read_mostly = 100; EXPORT_SYMBOL_GPL(sysctl_vfs_cache_pressure); @@ -440,17 +431,6 @@ static void d_lru_shrink_move(struct list_lru_one *lru, struct dentry *dentry, list_lru_isolate_move(lru, &dentry->d_lru, list); } -/* - * dentry_lru_(add|del)_list) must be called with d_lock held. - */ -static void dentry_lru_add(struct dentry *dentry) -{ - if (unlikely(!(dentry->d_flags & DCACHE_LRU_LIST))) - d_lru_add(dentry); - else if (unlikely(!(dentry->d_flags & DCACHE_REFERENCED))) - dentry->d_flags |= DCACHE_REFERENCED; -} - /** * d_drop - drop a dentry * @dentry: dentry to drop @@ -470,30 +450,29 @@ static void dentry_lru_add(struct dentry *dentry) */ static void ___d_drop(struct dentry *dentry) { - if (!d_unhashed(dentry)) { - struct hlist_bl_head *b; - /* - * Hashed dentries are normally on the dentry hashtable, - * with the exception of those newly allocated by - * d_obtain_root, which are always IS_ROOT: - */ - if (unlikely(IS_ROOT(dentry))) - b = &dentry->d_sb->s_roots; - else - b = d_hash(dentry->d_name.hash); + struct hlist_bl_head *b; + /* + * Hashed dentries are normally on the dentry hashtable, + * with the exception of those newly allocated by + * d_obtain_root, which are always IS_ROOT: + */ + if (unlikely(IS_ROOT(dentry))) + b = &dentry->d_sb->s_roots; + else + b = d_hash(dentry->d_name.hash); - hlist_bl_lock(b); - __hlist_bl_del(&dentry->d_hash); - hlist_bl_unlock(b); - /* After this call, in-progress rcu-walk path lookup will fail. */ - write_seqcount_invalidate(&dentry->d_seq); - } + hlist_bl_lock(b); + __hlist_bl_del(&dentry->d_hash); + hlist_bl_unlock(b); } void __d_drop(struct dentry *dentry) { - ___d_drop(dentry); - dentry->d_hash.pprev = NULL; + if (!d_unhashed(dentry)) { + ___d_drop(dentry); + dentry->d_hash.pprev = NULL; + write_seqcount_invalidate(&dentry->d_seq); + } } EXPORT_SYMBOL(__d_drop); @@ -589,47 +568,9 @@ static void __dentry_kill(struct dentry *dentry) dentry_free(dentry); } -/* - * Finish off a dentry we've decided to kill. - * dentry->d_lock must be held, returns with it unlocked. - * If ref is non-zero, then decrement the refcount too. - * Returns dentry requiring refcount drop, or NULL if we're done. - */ -static struct dentry *dentry_kill(struct dentry *dentry) - __releases(dentry->d_lock) -{ - struct inode *inode = dentry->d_inode; - struct dentry *parent = NULL; - - if (inode && unlikely(!spin_trylock(&inode->i_lock))) - goto failed; - - if (!IS_ROOT(dentry)) { - parent = dentry->d_parent; - if (unlikely(!spin_trylock(&parent->d_lock))) { - if (inode) - spin_unlock(&inode->i_lock); - goto failed; - } - } - - __dentry_kill(dentry); - return parent; - -failed: - spin_unlock(&dentry->d_lock); - return dentry; /* try again with same dentry */ -} - -static inline struct dentry *lock_parent(struct dentry *dentry) +static struct dentry *__lock_parent(struct dentry *dentry) { - struct dentry *parent = dentry->d_parent; - if (IS_ROOT(dentry)) - return NULL; - if (unlikely(dentry->d_lockref.count < 0)) - return NULL; - if (likely(spin_trylock(&parent->d_lock))) - return parent; + struct dentry *parent; rcu_read_lock(); spin_unlock(&dentry->d_lock); again: @@ -655,6 +596,91 @@ again: return parent; } +static inline struct dentry *lock_parent(struct dentry *dentry) +{ + struct dentry *parent = dentry->d_parent; + if (IS_ROOT(dentry)) + return NULL; + if (likely(spin_trylock(&parent->d_lock))) + return parent; + return __lock_parent(dentry); +} + +static inline bool retain_dentry(struct dentry *dentry) +{ + WARN_ON(d_in_lookup(dentry)); + + /* Unreachable? Get rid of it */ + if (unlikely(d_unhashed(dentry))) + return false; + + if (unlikely(dentry->d_flags & DCACHE_DISCONNECTED)) + return false; + + if (unlikely(dentry->d_flags & DCACHE_OP_DELETE)) { + if (dentry->d_op->d_delete(dentry)) + return false; + } + /* retain; LRU fodder */ + dentry->d_lockref.count--; + if (unlikely(!(dentry->d_flags & DCACHE_LRU_LIST))) + d_lru_add(dentry); + else if (unlikely(!(dentry->d_flags & DCACHE_REFERENCED))) + dentry->d_flags |= DCACHE_REFERENCED; + return true; +} + +/* + * Finish off a dentry we've decided to kill. + * dentry->d_lock must be held, returns with it unlocked. + * Returns dentry requiring refcount drop, or NULL if we're done. + */ +static struct dentry *dentry_kill(struct dentry *dentry) + __releases(dentry->d_lock) +{ + struct inode *inode = dentry->d_inode; + struct dentry *parent = NULL; + + if (inode && unlikely(!spin_trylock(&inode->i_lock))) + goto slow_positive; + + if (!IS_ROOT(dentry)) { + parent = dentry->d_parent; + if (unlikely(!spin_trylock(&parent->d_lock))) { + parent = __lock_parent(dentry); + if (likely(inode || !dentry->d_inode)) + goto got_locks; + /* negative that became positive */ + if (parent) + spin_unlock(&parent->d_lock); + inode = dentry->d_inode; + goto slow_positive; + } + } + __dentry_kill(dentry); + return parent; + +slow_positive: + spin_unlock(&dentry->d_lock); + spin_lock(&inode->i_lock); + spin_lock(&dentry->d_lock); + parent = lock_parent(dentry); +got_locks: + if (unlikely(dentry->d_lockref.count != 1)) { + dentry->d_lockref.count--; + } else if (likely(!retain_dentry(dentry))) { + __dentry_kill(dentry); + return parent; + } + /* we are keeping it, after all */ + if (inode) + spin_unlock(&inode->i_lock); + if (parent) + spin_unlock(&parent->d_lock); + spin_unlock(&dentry->d_lock); + return NULL; +} + /* * Try to do a lockless dput(), and return whether that was successful. * @@ -802,27 +828,11 @@ repeat: /* Slow case: now with the dentry lock held */ rcu_read_unlock(); - WARN_ON(d_in_lookup(dentry)); - - /* Unreachable? Get rid of it */ - if (unlikely(d_unhashed(dentry))) - goto kill_it; - - if (unlikely(dentry->d_flags & DCACHE_DISCONNECTED)) - goto kill_it; - - if (unlikely(dentry->d_flags & DCACHE_OP_DELETE)) { - if (dentry->d_op->d_delete(dentry)) - goto kill_it; + if (likely(retain_dentry(dentry))) { + spin_unlock(&dentry->d_lock); + return; } - dentry_lru_add(dentry); - - dentry->d_lockref.count--; - spin_unlock(&dentry->d_lock); - return; - -kill_it: dentry = dentry_kill(dentry); if (dentry) { cond_resched(); @@ -971,56 +981,83 @@ restart: } EXPORT_SYMBOL(d_prune_aliases); -static void shrink_dentry_list(struct list_head *list) +/* + * Lock a dentry from shrink list. + * Called under rcu_read_lock() and dentry->d_lock; the former + * guarantees that nothing we access will be freed under us. + * Note that dentry is *not* protected from concurrent dentry_kill(), + * d_delete(), etc. + * + * Return false if dentry has been disrupted or grabbed, leaving + * the caller to kick it off-list. Otherwise, return true and have + * that dentry's inode and parent both locked. + */ +static bool shrink_lock_dentry(struct dentry *dentry) { - struct dentry *dentry, *parent; + struct inode *inode; + struct dentry *parent; - while (!list_empty(list)) { - struct inode *inode; - dentry = list_entry(list->prev, struct dentry, d_lru); + if (dentry->d_lockref.count) + return false; + + inode = dentry->d_inode; + if (inode && unlikely(!spin_trylock(&inode->i_lock))) { + spin_unlock(&dentry->d_lock); + spin_lock(&inode->i_lock); spin_lock(&dentry->d_lock); - parent = lock_parent(dentry); + if (unlikely(dentry->d_lockref.count)) + goto out; + /* changed inode means that somebody had grabbed it */ + if (unlikely(inode != dentry->d_inode)) + goto out; + } - /* - * The dispose list is isolated and dentries are not accounted - * to the LRU here, so we can simply remove it from the list - * here regardless of whether it is referenced or not. - */ - d_shrink_del(dentry); + parent = dentry->d_parent; + if (IS_ROOT(dentry) || likely(spin_trylock(&parent->d_lock))) + return true; - /* - * We found an inuse dentry which was not removed from - * the LRU because of laziness during lookup. Do not free it. - */ - if (dentry->d_lockref.count > 0) { - spin_unlock(&dentry->d_lock); - if (parent) - spin_unlock(&parent->d_lock); - continue; - } + spin_unlock(&dentry->d_lock); + spin_lock(&parent->d_lock); + if (unlikely(parent != dentry->d_parent)) { + spin_unlock(&parent->d_lock); + spin_lock(&dentry->d_lock); + goto out; + } + spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); + if (likely(!dentry->d_lockref.count)) + return true; + spin_unlock(&parent->d_lock); +out: + if (inode) + spin_unlock(&inode->i_lock); + return false; +} +static void shrink_dentry_list(struct list_head *list) +{ + while (!list_empty(list)) { + struct dentry *dentry, *parent; - if (unlikely(dentry->d_flags & DCACHE_DENTRY_KILLED)) { - bool can_free = dentry->d_flags & DCACHE_MAY_FREE; + dentry = list_entry(list->prev, struct dentry, d_lru); + spin_lock(&dentry->d_lock); + rcu_read_lock(); + if (!shrink_lock_dentry(dentry)) { + bool can_free = false; + rcu_read_unlock(); + d_shrink_del(dentry); + if (dentry->d_lockref.count < 0) + can_free = dentry->d_flags & DCACHE_MAY_FREE; spin_unlock(&dentry->d_lock); - if (parent) - spin_unlock(&parent->d_lock); if (can_free) dentry_free(dentry); continue; } - - inode = dentry->d_inode; - if (inode && unlikely(!spin_trylock(&inode->i_lock))) { - d_shrink_add(dentry, list); - spin_unlock(&dentry->d_lock); - if (parent) - spin_unlock(&parent->d_lock); - continue; - } - + rcu_read_unlock(); + d_shrink_del(dentry); + parent = dentry->d_parent; __dentry_kill(dentry); - + if (parent == dentry) + continue; /* * We need to prune ancestors too. This is necessary to prevent * quadratic behavior of shrink_dcache_parent(), but is also @@ -1028,26 +1065,8 @@ static void shrink_dentry_list(struct list_head *list) * fragmentation. */ dentry = parent; - while (dentry && !lockref_put_or_lock(&dentry->d_lockref)) { - parent = lock_parent(dentry); - if (dentry->d_lockref.count != 1) { - dentry->d_lockref.count--; - spin_unlock(&dentry->d_lock); - if (parent) - spin_unlock(&parent->d_lock); - break; - } - inode = dentry->d_inode; /* can't be NULL */ - if (unlikely(!spin_trylock(&inode->i_lock))) { - spin_unlock(&dentry->d_lock); - if (parent) - spin_unlock(&parent->d_lock); - cpu_relax(); - continue; - } - __dentry_kill(dentry); - dentry = parent; - } + while (dentry && !lockref_put_or_lock(&dentry->d_lockref)) + dentry = dentry_kill(dentry); } } @@ -2374,32 +2393,22 @@ EXPORT_SYMBOL(d_hash_and_lookup); void d_delete(struct dentry * dentry) { - struct inode *inode; - int isdir = 0; + struct inode *inode = dentry->d_inode; + int isdir = d_is_dir(dentry); + + spin_lock(&inode->i_lock); + spin_lock(&dentry->d_lock); /* * Are we the only user? */ -again: - spin_lock(&dentry->d_lock); - inode = dentry->d_inode; - isdir = S_ISDIR(inode->i_mode); if (dentry->d_lockref.count == 1) { - if (!spin_trylock(&inode->i_lock)) { - spin_unlock(&dentry->d_lock); - cpu_relax(); - goto again; - } dentry->d_flags &= ~DCACHE_CANT_MOUNT; dentry_unlink_inode(dentry); - fsnotify_nameremove(dentry, isdir); - return; - } - - if (!d_unhashed(dentry)) + } else { __d_drop(dentry); - - spin_unlock(&dentry->d_lock); - + spin_unlock(&dentry->d_lock); + spin_unlock(&inode->i_lock); + } fsnotify_nameremove(dentry, isdir); } EXPORT_SYMBOL(d_delete); @@ -2474,7 +2483,7 @@ struct dentry *d_alloc_parallel(struct dentry *parent, retry: rcu_read_lock(); - seq = smp_load_acquire(&parent->d_inode->i_dir_seq) & ~1; + seq = smp_load_acquire(&parent->d_inode->i_dir_seq); r_seq = read_seqbegin(&rename_lock); dentry = __d_lookup_rcu(parent, name, &d_seq); if (unlikely(dentry)) { @@ -2495,8 +2504,14 @@ retry: rcu_read_unlock(); goto retry; } + + if (unlikely(seq & 1)) { + rcu_read_unlock(); + goto retry; + } + hlist_bl_lock(b); - if (unlikely(parent->d_inode->i_dir_seq != seq)) { + if (unlikely(READ_ONCE(parent->d_inode->i_dir_seq) != seq)) { hlist_bl_unlock(b); rcu_read_unlock(); goto retry; @@ -2758,57 +2773,6 @@ static void copy_name(struct dentry *dentry, struct dentry *target) kfree_rcu(old_name, u.head); } -static void dentry_lock_for_move(struct dentry *dentry, struct dentry *target) -{ - /* - * XXXX: do we really need to take target->d_lock? - */ - if (IS_ROOT(dentry) || dentry->d_parent == target->d_parent) - spin_lock(&target->d_parent->d_lock); - else { - if (d_ancestor(dentry->d_parent, target->d_parent)) { - spin_lock(&dentry->d_parent->d_lock); - spin_lock_nested(&target->d_parent->d_lock, - DENTRY_D_LOCK_NESTED); - } else { - spin_lock(&target->d_parent->d_lock); - spin_lock_nested(&dentry->d_parent->d_lock, - DENTRY_D_LOCK_NESTED); - } - } - if (target < dentry) { - spin_lock_nested(&target->d_lock, 2); - spin_lock_nested(&dentry->d_lock, 3); - } else { - spin_lock_nested(&dentry->d_lock, 2); - spin_lock_nested(&target->d_lock, 3); - } -} - -static void dentry_unlock_for_move(struct dentry *dentry, struct dentry *target) -{ - if (target->d_parent != dentry->d_parent) - spin_unlock(&dentry->d_parent->d_lock); - if (target->d_parent != target) - spin_unlock(&target->d_parent->d_lock); - spin_unlock(&target->d_lock); - spin_unlock(&dentry->d_lock); -} - -/* - * When switching names, the actual string doesn't strictly have to - * be preserved in the target - because we're dropping the target - * anyway. As such, we can just do a simple memcpy() to copy over - * the new name before we switch, unless we are going to rehash - * it. Note that if we *do* unhash the target, we are not allowed - * to rehash it without giving it a new name/hash key - whether - * we swap or overwrite the names here, resulting name won't match - * the reality in filesystem; it's only there for d_path() purposes. - * Note that all of this is happening under rename_lock, so the - * any hash lookup seeing it in the middle of manipulations will - * be discarded anyway. So we do not care what happens to the hash - * key in that case. - */ /* * __d_move - move a dentry * @dentry: entry to move @@ -2823,15 +2787,34 @@ static void dentry_unlock_for_move(struct dentry *dentry, struct dentry *target) static void __d_move(struct dentry *dentry, struct dentry *target, bool exchange) { + struct dentry *old_parent, *p; struct inode *dir = NULL; unsigned n; - if (!dentry->d_inode) - printk(KERN_WARNING "VFS: moving negative dcache entry\n"); - BUG_ON(d_ancestor(dentry, target)); + WARN_ON(!dentry->d_inode); + if (WARN_ON(dentry == target)) + return; + BUG_ON(d_ancestor(target, dentry)); + old_parent = dentry->d_parent; + p = d_ancestor(old_parent, target); + if (IS_ROOT(dentry)) { + BUG_ON(p); + spin_lock(&target->d_parent->d_lock); + } else if (!p) { + /* target is not a descendent of dentry->d_parent */ + spin_lock(&target->d_parent->d_lock); + spin_lock_nested(&old_parent->d_lock, DENTRY_D_LOCK_NESTED); + } else { + BUG_ON(p == dentry); + spin_lock(&old_parent->d_lock); + if (p != target) + spin_lock_nested(&target->d_parent->d_lock, + DENTRY_D_LOCK_NESTED); + } + spin_lock_nested(&dentry->d_lock, 2); + spin_lock_nested(&target->d_lock, 3); - dentry_lock_for_move(dentry, target); if (unlikely(d_in_lookup(target))) { dir = target->d_parent->d_inode; n = start_dir_add(dir); @@ -2842,47 +2825,44 @@ static void __d_move(struct dentry *dentry, struct dentry *target, write_seqcount_begin_nested(&target->d_seq, DENTRY_D_LOCK_NESTED); /* unhash both */ - /* ___d_drop does write_seqcount_barrier, but they're OK to nest. */ - ___d_drop(dentry); - ___d_drop(target); + if (!d_unhashed(dentry)) + ___d_drop(dentry); + if (!d_unhashed(target)) + ___d_drop(target); - /* Switch the names.. */ - if (exchange) - swap_names(dentry, target); - else + /* ... and switch them in the tree */ + dentry->d_parent = target->d_parent; + if (!exchange) { copy_name(dentry, target); - - /* rehash in new place(s) */ - __d_rehash(dentry); - if (exchange) - __d_rehash(target); - else target->d_hash.pprev = NULL; - - /* ... and switch them in the tree */ - if (IS_ROOT(dentry)) { - /* splicing a tree */ - dentry->d_flags |= DCACHE_RCUACCESS; - dentry->d_parent = target->d_parent; - target->d_parent = target; - list_del_init(&target->d_child); - list_move(&dentry->d_child, &dentry->d_parent->d_subdirs); + dentry->d_parent->d_lockref.count++; + if (dentry == old_parent) + dentry->d_flags |= DCACHE_RCUACCESS; + else + WARN_ON(!--old_parent->d_lockref.count); } else { - /* swapping two dentries */ - swap(dentry->d_parent, target->d_parent); + target->d_parent = old_parent; + swap_names(dentry, target); list_move(&target->d_child, &target->d_parent->d_subdirs); - list_move(&dentry->d_child, &dentry->d_parent->d_subdirs); - if (exchange) - fsnotify_update_flags(target); - fsnotify_update_flags(dentry); + __d_rehash(target); + fsnotify_update_flags(target); } + list_move(&dentry->d_child, &dentry->d_parent->d_subdirs); + __d_rehash(dentry); + fsnotify_update_flags(dentry); write_seqcount_end(&target->d_seq); write_seqcount_end(&dentry->d_seq); if (dir) end_dir_add(dir, n); - dentry_unlock_for_move(dentry, target); + + if (dentry->d_parent != old_parent) + spin_unlock(&dentry->d_parent->d_lock); + if (dentry != old_parent) + spin_unlock(&old_parent->d_lock); + spin_unlock(&target->d_lock); + spin_unlock(&dentry->d_lock); } /* @@ -3030,12 +3010,14 @@ struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry) inode->i_sb->s_type->name, inode->i_sb->s_id); } else if (!IS_ROOT(new)) { + struct dentry *old_parent = dget(new->d_parent); int err = __d_unalias(inode, dentry, new); write_sequnlock(&rename_lock); if (err) { dput(new); new = ERR_PTR(err); } + dput(old_parent); } else { __d_move(new, dentry, false); write_sequnlock(&rename_lock); @@ -3050,467 +3032,6 @@ out: } EXPORT_SYMBOL(d_splice_alias); -static int prepend(char **buffer, int *buflen, const char *str, int namelen) -{ - *buflen -= namelen; - if (*buflen < 0) - return -ENAMETOOLONG; - *buffer -= namelen; - memcpy(*buffer, str, namelen); - return 0; -} - -/** - * prepend_name - prepend a pathname in front of current buffer pointer - * @buffer: buffer pointer - * @buflen: allocated length of the buffer - * @name: name string and length qstr structure - * - * With RCU path tracing, it may race with d_move(). Use READ_ONCE() to - * make sure that either the old or the new name pointer and length are - * fetched. However, there may be mismatch between length and pointer. - * The length cannot be trusted, we need to copy it byte-by-byte until - * the length is reached or a null byte is found. It also prepends "/" at - * the beginning of the name. The sequence number check at the caller will - * retry it again when a d_move() does happen. So any garbage in the buffer - * due to mismatched pointer and length will be discarded. - * - * Load acquire is needed to make sure that we see that terminating NUL. - */ -static int prepend_name(char **buffer, int *buflen, const struct qstr *name) -{ - const char *dname = smp_load_acquire(&name->name); /* ^^^ */ - u32 dlen = READ_ONCE(name->len); - char *p; - - *buflen -= dlen + 1; - if (*buflen < 0) - return -ENAMETOOLONG; - p = *buffer -= dlen + 1; - *p++ = '/'; - while (dlen--) { - char c = *dname++; - if (!c) - break; - *p++ = c; - } - return 0; -} - -/** - * prepend_path - Prepend path string to a buffer - * @path: the dentry/vfsmount to report - * @root: root vfsmnt/dentry - * @buffer: pointer to the end of the buffer - * @buflen: pointer to buffer length - * - * The function will first try to write out the pathname without taking any - * lock other than the RCU read lock to make sure that dentries won't go away. - * It only checks the sequence number of the global rename_lock as any change - * in the dentry's d_seq will be preceded by changes in the rename_lock - * sequence number. If the sequence number had been changed, it will restart - * the whole pathname back-tracing sequence again by taking the rename_lock. - * In this case, there is no need to take the RCU read lock as the recursive - * parent pointer references will keep the dentry chain alive as long as no - * rename operation is performed. - */ -static int prepend_path(const struct path *path, - const struct path *root, - char **buffer, int *buflen) -{ - struct dentry *dentry; - struct vfsmount *vfsmnt; - struct mount *mnt; - int error = 0; - unsigned seq, m_seq = 0; - char *bptr; - int blen; - - rcu_read_lock(); -restart_mnt: - read_seqbegin_or_lock(&mount_lock, &m_seq); - seq = 0; - rcu_read_lock(); -restart: - bptr = *buffer; - blen = *buflen; - error = 0; - dentry = path->dentry; - vfsmnt = path->mnt; - mnt = real_mount(vfsmnt); - read_seqbegin_or_lock(&rename_lock, &seq); - while (dentry != root->dentry || vfsmnt != root->mnt) { - struct dentry * parent; - - if (dentry == vfsmnt->mnt_root || IS_ROOT(dentry)) { - struct mount *parent = READ_ONCE(mnt->mnt_parent); - /* Escaped? */ - if (dentry != vfsmnt->mnt_root) { - bptr = *buffer; - blen = *buflen; - error = 3; - break; - } - /* Global root? */ - if (mnt != parent) { - dentry = READ_ONCE(mnt->mnt_mountpoint); - mnt = parent; - vfsmnt = &mnt->mnt; - continue; - } - if (!error) - error = is_mounted(vfsmnt) ? 1 : 2; - break; - } - parent = dentry->d_parent; - prefetch(parent); - error = prepend_name(&bptr, &blen, &dentry->d_name); - if (error) - break; - - dentry = parent; - } - if (!(seq & 1)) - rcu_read_unlock(); - if (need_seqretry(&rename_lock, seq)) { - seq = 1; - goto restart; - } - done_seqretry(&rename_lock, seq); - - if (!(m_seq & 1)) - rcu_read_unlock(); - if (need_seqretry(&mount_lock, m_seq)) { - m_seq = 1; - goto restart_mnt; - } - done_seqretry(&mount_lock, m_seq); - - if (error >= 0 && bptr == *buffer) { - if (--blen < 0) - error = -ENAMETOOLONG; - else - *--bptr = '/'; - } - *buffer = bptr; - *buflen = blen; - return error; -} - -/** - * __d_path - return the path of a dentry - * @path: the dentry/vfsmount to report - * @root: root vfsmnt/dentry - * @buf: buffer to return value in - * @buflen: buffer length - * - * Convert a dentry into an ASCII path name. - * - * Returns a pointer into the buffer or an error code if the - * path was too long. - * - * "buflen" should be positive. - * - * If the path is not reachable from the supplied root, return %NULL. - */ -char *__d_path(const struct path *path, - const struct path *root, - char *buf, int buflen) -{ - char *res = buf + buflen; - int error; - - prepend(&res, &buflen, "\0", 1); - error = prepend_path(path, root, &res, &buflen); - - if (error < 0) - return ERR_PTR(error); - if (error > 0) - return NULL; - return res; -} - -char *d_absolute_path(const struct path *path, - char *buf, int buflen) -{ - struct path root = {}; - char *res = buf + buflen; - int error; - - prepend(&res, &buflen, "\0", 1); - error = prepend_path(path, &root, &res, &buflen); - - if (error > 1) - error = -EINVAL; - if (error < 0) - return ERR_PTR(error); - return res; -} - -/* - * same as __d_path but appends "(deleted)" for unlinked files. - */ -static int path_with_deleted(const struct path *path, - const struct path *root, - char **buf, int *buflen) -{ - prepend(buf, buflen, "\0", 1); - if (d_unlinked(path->dentry)) { - int error = prepend(buf, buflen, " (deleted)", 10); - if (error) - return error; - } - - return prepend_path(path, root, buf, buflen); -} - -static int prepend_unreachable(char **buffer, int *buflen) -{ - return prepend(buffer, buflen, "(unreachable)", 13); -} - -static void get_fs_root_rcu(struct fs_struct *fs, struct path *root) -{ - unsigned seq; - - do { - seq = read_seqcount_begin(&fs->seq); - *root = fs->root; - } while (read_seqcount_retry(&fs->seq, seq)); -} - -/** - * d_path - return the path of a dentry - * @path: path to report - * @buf: buffer to return value in - * @buflen: buffer length - * - * Convert a dentry into an ASCII path name. If the entry has been deleted - * the string " (deleted)" is appended. Note that this is ambiguous. - * - * Returns a pointer into the buffer or an error code if the path was - * too long. Note: Callers should use the returned pointer, not the passed - * in buffer, to use the name! The implementation often starts at an offset - * into the buffer, and may leave 0 bytes at the start. - * - * "buflen" should be positive. - */ -char *d_path(const struct path *path, char *buf, int buflen) -{ - char *res = buf + buflen; - struct path root; - int error; - - /* - * We have various synthetic filesystems that never get mounted. On - * these filesystems dentries are never used for lookup purposes, and - * thus don't need to be hashed. They also don't need a name until a - * user wants to identify the object in /proc/pid/fd/. The little hack - * below allows us to generate a name for these objects on demand: - * - * Some pseudo inodes are mountable. When they are mounted - * path->dentry == path->mnt->mnt_root. In that case don't call d_dname - * and instead have d_path return the mounted path. - */ - if (path->dentry->d_op && path->dentry->d_op->d_dname && - (!IS_ROOT(path->dentry) || path->dentry != path->mnt->mnt_root)) - return path->dentry->d_op->d_dname(path->dentry, buf, buflen); - - rcu_read_lock(); - get_fs_root_rcu(current->fs, &root); - error = path_with_deleted(path, &root, &res, &buflen); - rcu_read_unlock(); - - if (error < 0) - res = ERR_PTR(error); - return res; -} -EXPORT_SYMBOL(d_path); - -/* - * Helper function for dentry_operations.d_dname() members - */ -char *dynamic_dname(struct dentry *dentry, char *buffer, int buflen, - const char *fmt, ...) -{ - va_list args; - char temp[64]; - int sz; - - va_start(args, fmt); - sz = vsnprintf(temp, sizeof(temp), fmt, args) + 1; - va_end(args); - - if (sz > sizeof(temp) || sz > buflen) - return ERR_PTR(-ENAMETOOLONG); - - buffer += buflen - sz; - return memcpy(buffer, temp, sz); -} - -char *simple_dname(struct dentry *dentry, char *buffer, int buflen) -{ - char *end = buffer + buflen; - /* these dentries are never renamed, so d_lock is not needed */ - if (prepend(&end, &buflen, " (deleted)", 11) || - prepend(&end, &buflen, dentry->d_name.name, dentry->d_name.len) || - prepend(&end, &buflen, "/", 1)) - end = ERR_PTR(-ENAMETOOLONG); - return end; -} -EXPORT_SYMBOL(simple_dname); - -/* - * Write full pathname from the root of the filesystem into the buffer. - */ -static char *__dentry_path(struct dentry *d, char *buf, int buflen) -{ - struct dentry *dentry; - char *end, *retval; - int len, seq = 0; - int error = 0; - - if (buflen < 2) - goto Elong; - - rcu_read_lock(); -restart: - dentry = d; - end = buf + buflen; - len = buflen; - prepend(&end, &len, "\0", 1); - /* Get '/' right */ - retval = end-1; - *retval = '/'; - read_seqbegin_or_lock(&rename_lock, &seq); - while (!IS_ROOT(dentry)) { - struct dentry *parent = dentry->d_parent; - - prefetch(parent); - error = prepend_name(&end, &len, &dentry->d_name); - if (error) - break; - - retval = end; - dentry = parent; - } - if (!(seq & 1)) - rcu_read_unlock(); - if (need_seqretry(&rename_lock, seq)) { - seq = 1; - goto restart; - } - done_seqretry(&rename_lock, seq); - if (error) - goto Elong; - return retval; -Elong: - return ERR_PTR(-ENAMETOOLONG); -} - -char *dentry_path_raw(struct dentry *dentry, char *buf, int buflen) -{ - return __dentry_path(dentry, buf, buflen); -} -EXPORT_SYMBOL(dentry_path_raw); - -char *dentry_path(struct dentry *dentry, char *buf, int buflen) -{ - char *p = NULL; - char *retval; - - if (d_unlinked(dentry)) { - p = buf + buflen; - if (prepend(&p, &buflen, "//deleted", 10) != 0) - goto Elong; - buflen++; - } - retval = __dentry_path(dentry, buf, buflen); - if (!IS_ERR(retval) && p) - *p = '/'; /* restore '/' overriden with '\0' */ - return retval; -Elong: - return ERR_PTR(-ENAMETOOLONG); -} - -static void get_fs_root_and_pwd_rcu(struct fs_struct *fs, struct path *root, - struct path *pwd) -{ - unsigned seq; - - do { - seq = read_seqcount_begin(&fs->seq); - *root = fs->root; - *pwd = fs->pwd; - } while (read_seqcount_retry(&fs->seq, seq)); -} - -/* - * NOTE! The user-level library version returns a - * character pointer. The kernel system call just - * returns the length of the buffer filled (which - * includes the ending '\0' character), or a negative - * error value. So libc would do something like - * - * char *getcwd(char * buf, size_t size) - * { - * int retval; - * - * retval = sys_getcwd(buf, size); - * if (retval >= 0) - * return buf; - * errno = -retval; - * return NULL; - * } - */ -SYSCALL_DEFINE2(getcwd, char __user *, buf, unsigned long, size) -{ - int error; - struct path pwd, root; - char *page = __getname(); - - if (!page) - return -ENOMEM; - - rcu_read_lock(); - get_fs_root_and_pwd_rcu(current->fs, &root, &pwd); - - error = -ENOENT; - if (!d_unlinked(pwd.dentry)) { - unsigned long len; - char *cwd = page + PATH_MAX; - int buflen = PATH_MAX; - - prepend(&cwd, &buflen, "\0", 1); - error = prepend_path(&pwd, &root, &cwd, &buflen); - rcu_read_unlock(); - - if (error < 0) - goto out; - - /* Unreachable from current root */ - if (error > 0) { - error = prepend_unreachable(&cwd, &buflen); - if (error) - goto out; - } - - error = -ERANGE; - len = PATH_MAX + page - cwd; - if (len <= size) { - error = len; - if (copy_to_user(buf, cwd, len)) - error = -EFAULT; - } - } else { - rcu_read_unlock(); - } - -out: - __putname(page); - return error; -} - /* * Test whether new_dentry is a subdirectory of old_dentry. * @@ -3574,6 +3095,8 @@ void d_genocide(struct dentry *parent) d_walk(parent, parent, d_genocide_kill, NULL); } +EXPORT_SYMBOL(d_genocide); + void d_tmpfile(struct dentry *dentry, struct inode *inode) { inode_dec_link_count(inode); @@ -3653,8 +3176,6 @@ static void __init dcache_init(void) struct kmem_cache *names_cachep __read_mostly; EXPORT_SYMBOL(names_cachep); -EXPORT_SYMBOL(d_genocide); - void __init vfs_caches_init_early(void) { int i; diff --git a/fs/dcookies.c b/fs/dcookies.c index 0d0461cf2431..57bc96435feb 100644 --- a/fs/dcookies.c +++ b/fs/dcookies.c @@ -146,7 +146,7 @@ out: /* And here is where the userspace process can look up the cookie value * to retrieve the path. */ -SYSCALL_DEFINE3(lookup_dcookie, u64, cookie64, char __user *, buf, size_t, len) +static int do_lookup_dcookie(u64 cookie64, char __user *buf, size_t len) { unsigned long cookie = (unsigned long)cookie64; int err = -EINVAL; @@ -203,13 +203,18 @@ out: return err; } +SYSCALL_DEFINE3(lookup_dcookie, u64, cookie64, char __user *, buf, size_t, len) +{ + return do_lookup_dcookie(cookie64, buf, len); +} + #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE4(lookup_dcookie, u32, w0, u32, w1, char __user *, buf, compat_size_t, len) { #ifdef __BIG_ENDIAN - return sys_lookup_dcookie(((u64)w0 << 32) | w1, buf, len); + return do_lookup_dcookie(((u64)w0 << 32) | w1, buf, len); #else - return sys_lookup_dcookie(((u64)w1 << 32) | w0, buf, len); + return do_lookup_dcookie(((u64)w1 << 32) | w0, buf, len); #endif } #endif diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 63a998c3f252..13b01351dd1c 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -270,10 +270,7 @@ struct dentry *debugfs_lookup(const char *name, struct dentry *parent) if (!parent) parent = debugfs_mount->mnt_root; - inode_lock(d_inode(parent)); - dentry = lookup_one_len(name, parent, strlen(name)); - inode_unlock(d_inode(parent)); - + dentry = lookup_one_len_unlocked(name, parent, strlen(name)); if (IS_ERR(dentry)) return NULL; if (!d_really_is_positive(dentry)) { diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index cff79ea0c01d..5243989a60cc 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -482,7 +482,6 @@ static void lowcomms_error_report(struct sock *sk) { struct connection *con; struct sockaddr_storage saddr; - int buflen; void (*orig_report)(struct sock *) = NULL; read_lock_bh(&sk->sk_callback_lock); @@ -492,7 +491,7 @@ static void lowcomms_error_report(struct sock *sk) orig_report = listen_sock.sk_error_report; if (con->sock == NULL || - kernel_getpeername(con->sock, (struct sockaddr *)&saddr, &buflen)) { + kernel_getpeername(con->sock, (struct sockaddr *)&saddr) < 0) { printk_ratelimited(KERN_ERR "dlm: node %d: socket error " "sending to node %d, port %d, " "sk_err=%d/%d\n", dlm_our_nodeid(), @@ -757,8 +756,8 @@ static int tcp_accept_from_sock(struct connection *con) /* Get the connected socket's peer */ memset(&peeraddr, 0, sizeof(peeraddr)); - if (newsock->ops->getname(newsock, (struct sockaddr *)&peeraddr, - &len, 2)) { + len = newsock->ops->getname(newsock, (struct sockaddr *)&peeraddr, 2); + if (len < 0) { result = -ECONNABORTED; goto accept_err; } diff --git a/fs/eventfd.c b/fs/eventfd.c index 012f5bd46dfa..08d3bd602f73 100644 --- a/fs/eventfd.c +++ b/fs/eventfd.c @@ -380,7 +380,7 @@ struct eventfd_ctx *eventfd_ctx_fileget(struct file *file) } EXPORT_SYMBOL_GPL(eventfd_ctx_fileget); -SYSCALL_DEFINE2(eventfd2, unsigned int, count, int, flags) +static int do_eventfd(unsigned int count, int flags) { struct eventfd_ctx *ctx; int fd; @@ -409,8 +409,13 @@ SYSCALL_DEFINE2(eventfd2, unsigned int, count, int, flags) return fd; } +SYSCALL_DEFINE2(eventfd2, unsigned int, count, int, flags) +{ + return do_eventfd(count, flags); +} + SYSCALL_DEFINE1(eventfd, unsigned int, count) { - return sys_eventfd2(count, 0); + return do_eventfd(count, 0); } diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 0f3494ed3ed0..602ca4285b2e 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1936,7 +1936,7 @@ static void clear_tfile_check_list(void) /* * Open an eventpoll file descriptor. */ -SYSCALL_DEFINE1(epoll_create1, int, flags) +static int do_epoll_create(int flags) { int error, fd; struct eventpoll *ep = NULL; @@ -1979,12 +1979,17 @@ out_free_ep: return error; } +SYSCALL_DEFINE1(epoll_create1, int, flags) +{ + return do_epoll_create(flags); +} + SYSCALL_DEFINE1(epoll_create, int, size) { if (size <= 0) return -EINVAL; - return sys_epoll_create1(0); + return do_epoll_create(0); } /* @@ -2148,8 +2153,8 @@ error_return: * Implement the event wait interface for the eventpoll file. It is the kernel * part of the user space epoll_wait(2). */ -SYSCALL_DEFINE4(epoll_wait, int, epfd, struct epoll_event __user *, events, - int, maxevents, int, timeout) +static int do_epoll_wait(int epfd, struct epoll_event __user *events, + int maxevents, int timeout) { int error; struct fd f; @@ -2190,6 +2195,12 @@ error_fput: return error; } +SYSCALL_DEFINE4(epoll_wait, int, epfd, struct epoll_event __user *, events, + int, maxevents, int, timeout) +{ + return do_epoll_wait(epfd, events, maxevents, timeout); +} + /* * Implement the event wait interface for the eventpoll file. It is the kernel * part of the user space epoll_pwait(2). @@ -2214,7 +2225,7 @@ SYSCALL_DEFINE6(epoll_pwait, int, epfd, struct epoll_event __user *, events, set_current_blocked(&ksigmask); } - error = sys_epoll_wait(epfd, events, maxevents, timeout); + error = do_epoll_wait(epfd, events, maxevents, timeout); /* * If we changed the signal mask, we need to restore the original one. @@ -2257,7 +2268,7 @@ COMPAT_SYSCALL_DEFINE6(epoll_pwait, int, epfd, set_current_blocked(&ksigmask); } - err = sys_epoll_wait(epfd, events, maxevents, timeout); + err = do_epoll_wait(epfd, events, maxevents, timeout); /* * If we changed the signal mask, we need to restore the original one. diff --git a/fs/fcntl.c b/fs/fcntl.c index 1e97f1fda90c..d737ff082472 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -607,8 +607,8 @@ static int fixup_compat_flock(struct flock *flock) return 0; } -COMPAT_SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, - compat_ulong_t, arg) +static long do_compat_fcntl64(unsigned int fd, unsigned int cmd, + compat_ulong_t arg) { struct fd f = fdget_raw(fd); struct flock flock; @@ -672,6 +672,12 @@ out_put: return err; } +COMPAT_SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, + compat_ulong_t, arg) +{ + return do_compat_fcntl64(fd, cmd, arg); +} + COMPAT_SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, compat_ulong_t, arg) { @@ -684,7 +690,7 @@ COMPAT_SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, case F_OFD_SETLKW: return -EINVAL; } - return compat_sys_fcntl64(fd, cmd, arg); + return do_compat_fcntl64(fd, cmd, arg); } #endif diff --git a/fs/file.c b/fs/file.c index 42f0db4bd0fb..7ffd6e9d103d 100644 --- a/fs/file.c +++ b/fs/file.c @@ -638,6 +638,7 @@ out_unlock: spin_unlock(&files->file_lock); return -EBADF; } +EXPORT_SYMBOL(__close_fd); /* for ksys_close() */ void do_close_on_exec(struct files_struct *files) { @@ -870,7 +871,7 @@ out_unlock: return err; } -SYSCALL_DEFINE3(dup3, unsigned int, oldfd, unsigned int, newfd, int, flags) +static int ksys_dup3(unsigned int oldfd, unsigned int newfd, int flags) { int err = -EBADF; struct file *file; @@ -904,6 +905,11 @@ out_unlock: return err; } +SYSCALL_DEFINE3(dup3, unsigned int, oldfd, unsigned int, newfd, int, flags) +{ + return ksys_dup3(oldfd, newfd, flags); +} + SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd) { if (unlikely(newfd == oldfd)) { /* corner case */ @@ -916,10 +922,10 @@ SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd) rcu_read_unlock(); return retval; } - return sys_dup3(oldfd, newfd, 0); + return ksys_dup3(oldfd, newfd, 0); } -SYSCALL_DEFINE1(dup, unsigned int, fildes) +int ksys_dup(unsigned int fildes) { int ret = -EBADF; struct file *file = fget_raw(fildes); @@ -934,6 +940,11 @@ SYSCALL_DEFINE1(dup, unsigned int, fildes) return ret; } +SYSCALL_DEFINE1(dup, unsigned int, fildes) +{ + return ksys_dup(fildes); +} + int f_dupfd(unsigned int from, struct file *file, unsigned flags) { int err; diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index ff84258132bb..d705125665f0 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -557,9 +557,10 @@ void __fscache_disable_cookie(struct fscache_cookie *cookie, bool invalidate) * n_active reaches 0). This makes sure outstanding reads and writes * have completed. */ - if (!atomic_dec_and_test(&cookie->n_active)) - wait_on_atomic_t(&cookie->n_active, atomic_t_wait, - TASK_UNINTERRUPTIBLE); + if (!atomic_dec_and_test(&cookie->n_active)) { + wait_var_event(&cookie->n_active, + !atomic_read(&cookie->n_active)); + } /* Make sure any pending writes are cancelled. */ if (cookie->def->type != FSCACHE_COOKIE_TYPE_INDEX) diff --git a/fs/hostfs/hostfs.h b/fs/hostfs/hostfs.h index ffaec2e7526c..cb8374af08a6 100644 --- a/fs/hostfs/hostfs.h +++ b/fs/hostfs/hostfs.h @@ -84,7 +84,7 @@ extern int set_attr(const char *file, struct hostfs_iattr *attrs, int fd); extern int make_symlink(const char *from, const char *to); extern int unlink_file(const char *file); extern int do_mkdir(const char *file, int mode); -extern int do_rmdir(const char *file); +extern int hostfs_do_rmdir(const char *file); extern int do_mknod(const char *file, int mode, unsigned int major, unsigned int minor); extern int link_file(const char *from, const char *to); diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index c148e7f4f451..3cd85eb5bbb1 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -706,7 +706,7 @@ static int hostfs_rmdir(struct inode *ino, struct dentry *dentry) if ((file = dentry_name(dentry)) == NULL) return -ENOMEM; - err = do_rmdir(file); + err = hostfs_do_rmdir(file); __putname(file); return err; } diff --git a/fs/hostfs/hostfs_user.c b/fs/hostfs/hostfs_user.c index 9c1e0f019880..5ecc4706172b 100644 --- a/fs/hostfs/hostfs_user.c +++ b/fs/hostfs/hostfs_user.c @@ -304,7 +304,7 @@ int do_mkdir(const char *file, int mode) return 0; } -int do_rmdir(const char *file) +int hostfs_do_rmdir(const char *file) { int err; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 8fe1b0aa2896..b9a254dcc0e7 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -108,6 +108,16 @@ static void huge_pagevec_release(struct pagevec *pvec) pagevec_reinit(pvec); } +/* + * Mask used when checking the page offset value passed in via system + * calls. This value will be converted to a loff_t which is signed. + * Therefore, we want to check the upper PAGE_SHIFT + 1 bits of the + * value. The extra bit (- 1 in the shift value) is to take the sign + * bit into account. + */ +#define PGOFF_LOFFT_MAX \ + (((1UL << (PAGE_SHIFT + 1)) - 1) << (BITS_PER_LONG - (PAGE_SHIFT + 1))) + static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) { struct inode *inode = file_inode(file); @@ -127,12 +137,13 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) vma->vm_ops = &hugetlb_vm_ops; /* - * Offset passed to mmap (before page shift) could have been - * negative when represented as a (l)off_t. + * page based offset in vm_pgoff could be sufficiently large to + * overflow a (l)off_t when converted to byte offset. */ - if (((loff_t)vma->vm_pgoff << PAGE_SHIFT) < 0) + if (vma->vm_pgoff & PGOFF_LOFFT_MAX) return -EINVAL; + /* must be huge page aligned */ if (vma->vm_pgoff & (~huge_page_mask(h) >> PAGE_SHIFT)) return -EINVAL; diff --git a/fs/internal.h b/fs/internal.h index df262f41a0ef..980d005b21b4 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -55,7 +55,15 @@ extern void __init chrdev_init(void); extern int user_path_mountpoint_at(int, const char __user *, unsigned int, struct path *); extern int vfs_path_lookup(struct dentry *, struct vfsmount *, const char *, unsigned int, struct path *); +long do_mknodat(int dfd, const char __user *filename, umode_t mode, + unsigned int dev); +long do_mkdirat(int dfd, const char __user *pathname, umode_t mode); +long do_rmdir(int dfd, const char __user *pathname); long do_unlinkat(int dfd, struct filename *name); +long do_symlinkat(const char __user *oldname, int newdfd, + const char __user *newname); +int do_linkat(int olddfd, const char __user *oldname, int newdfd, + const char __user *newname, int flags); /* * namespace.c @@ -111,6 +119,12 @@ extern struct file *do_filp_open(int dfd, struct filename *pathname, extern struct file *do_file_open_root(struct dentry *, struct vfsmount *, const char *, const struct open_flags *); +long do_sys_ftruncate(unsigned int fd, loff_t length, int small); +long do_faccessat(int dfd, const char __user *filename, int mode); +int do_fchmodat(int dfd, const char __user *filename, umode_t mode); +int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group, + int flag); + extern int open_check_o_direct(struct file *f); extern int vfs_open(const struct path *, struct file *, const struct cred *); extern struct file *filp_clone_open(struct file *); diff --git a/fs/ioctl.c b/fs/ioctl.c index 5ace7efb0d04..4823431d1c9d 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -689,7 +689,7 @@ int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd, return error; } -SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, unsigned long, arg) +int ksys_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg) { int error; struct fd f = fdget(fd); @@ -702,3 +702,8 @@ SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, unsigned long, arg) fdput(f); return error; } + +SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, unsigned long, arg) +{ + return ksys_ioctl(fd, cmd, arg); +} diff --git a/fs/minix/Kconfig b/fs/minix/Kconfig index f2a0cfcef11d..bcd53a79156f 100644 --- a/fs/minix/Kconfig +++ b/fs/minix/Kconfig @@ -18,7 +18,7 @@ config MINIX_FS config MINIX_FS_NATIVE_ENDIAN def_bool MINIX_FS - depends on M32R || MICROBLAZE || MIPS || S390 || SUPERH || SPARC || XTENSA || (M68K && !MMU) + depends on MICROBLAZE || MIPS || S390 || SUPERH || SPARC || XTENSA || (M68K && !MMU) config MINIX_FS_BIG_ENDIAN_16BIT_INDEXED def_bool MINIX_FS diff --git a/fs/namei.c b/fs/namei.c index 921ae32dbc80..a09419379f5d 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -559,9 +559,10 @@ static int __nd_alloc_stack(struct nameidata *nd) static bool path_connected(const struct path *path) { struct vfsmount *mnt = path->mnt; + struct super_block *sb = mnt->mnt_sb; - /* Only bind mounts can have disconnected paths */ - if (mnt->mnt_root == mnt->mnt_sb->s_root) + /* Bind mounts and multi-root filesystems can have disconnected paths */ + if (!(sb->s_iflags & SB_I_MULTIROOT) && (mnt->mnt_root == sb->s_root)) return true; return is_subdir(path->dentry, mnt->mnt_root); @@ -1473,43 +1474,36 @@ static struct dentry *lookup_dcache(const struct qstr *name, } /* - * Call i_op->lookup on the dentry. The dentry must be negative and - * unhashed. - * - * dir->d_inode->i_mutex must be held + * Parent directory has inode locked exclusive. This is one + * and only case when ->lookup() gets called on non in-lookup + * dentries - as the matter of fact, this only gets called + * when directory is guaranteed to have no in-lookup children + * at all. */ -static struct dentry *lookup_real(struct inode *dir, struct dentry *dentry, - unsigned int flags) -{ - struct dentry *old; - - /* Don't create child dentry for a dead directory. */ - if (unlikely(IS_DEADDIR(dir))) { - dput(dentry); - return ERR_PTR(-ENOENT); - } - - old = dir->i_op->lookup(dir, dentry, flags); - if (unlikely(old)) { - dput(dentry); - dentry = old; - } - return dentry; -} - static struct dentry *__lookup_hash(const struct qstr *name, struct dentry *base, unsigned int flags) { struct dentry *dentry = lookup_dcache(name, base, flags); + struct dentry *old; + struct inode *dir = base->d_inode; if (dentry) return dentry; + /* Don't create child dentry for a dead directory. */ + if (unlikely(IS_DEADDIR(dir))) + return ERR_PTR(-ENOENT); + dentry = d_alloc(base, name); if (unlikely(!dentry)) return ERR_PTR(-ENOMEM); - return lookup_real(base->d_inode, dentry, flags); + old = dir->i_op->lookup(dir, dentry, flags); + if (unlikely(old)) { + dput(dentry); + dentry = old; + } + return dentry; } static int lookup_fast(struct nameidata *nd, @@ -3728,8 +3722,8 @@ static int may_mknod(umode_t mode) } } -SYSCALL_DEFINE4(mknodat, int, dfd, const char __user *, filename, umode_t, mode, - unsigned, dev) +long do_mknodat(int dfd, const char __user *filename, umode_t mode, + unsigned int dev) { struct dentry *dentry; struct path path; @@ -3772,9 +3766,15 @@ out: return error; } +SYSCALL_DEFINE4(mknodat, int, dfd, const char __user *, filename, umode_t, mode, + unsigned int, dev) +{ + return do_mknodat(dfd, filename, mode, dev); +} + SYSCALL_DEFINE3(mknod, const char __user *, filename, umode_t, mode, unsigned, dev) { - return sys_mknodat(AT_FDCWD, filename, mode, dev); + return do_mknodat(AT_FDCWD, filename, mode, dev); } int vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) @@ -3803,7 +3803,7 @@ int vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) } EXPORT_SYMBOL(vfs_mkdir); -SYSCALL_DEFINE3(mkdirat, int, dfd, const char __user *, pathname, umode_t, mode) +long do_mkdirat(int dfd, const char __user *pathname, umode_t mode) { struct dentry *dentry; struct path path; @@ -3828,9 +3828,14 @@ retry: return error; } +SYSCALL_DEFINE3(mkdirat, int, dfd, const char __user *, pathname, umode_t, mode) +{ + return do_mkdirat(dfd, pathname, mode); +} + SYSCALL_DEFINE2(mkdir, const char __user *, pathname, umode_t, mode) { - return sys_mkdirat(AT_FDCWD, pathname, mode); + return do_mkdirat(AT_FDCWD, pathname, mode); } int vfs_rmdir(struct inode *dir, struct dentry *dentry) @@ -3872,7 +3877,7 @@ out: } EXPORT_SYMBOL(vfs_rmdir); -static long do_rmdir(int dfd, const char __user *pathname) +long do_rmdir(int dfd, const char __user *pathname) { int error = 0; struct filename *name; @@ -4108,8 +4113,8 @@ int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname) } EXPORT_SYMBOL(vfs_symlink); -SYSCALL_DEFINE3(symlinkat, const char __user *, oldname, - int, newdfd, const char __user *, newname) +long do_symlinkat(const char __user *oldname, int newdfd, + const char __user *newname) { int error; struct filename *from; @@ -4139,9 +4144,15 @@ out_putname: return error; } +SYSCALL_DEFINE3(symlinkat, const char __user *, oldname, + int, newdfd, const char __user *, newname) +{ + return do_symlinkat(oldname, newdfd, newname); +} + SYSCALL_DEFINE2(symlink, const char __user *, oldname, const char __user *, newname) { - return sys_symlinkat(oldname, AT_FDCWD, newname); + return do_symlinkat(oldname, AT_FDCWD, newname); } /** @@ -4233,8 +4244,8 @@ EXPORT_SYMBOL(vfs_link); * with linux 2.0, and to avoid hard-linking to directories * and other special files. --ADM */ -SYSCALL_DEFINE5(linkat, int, olddfd, const char __user *, oldname, - int, newdfd, const char __user *, newname, int, flags) +int do_linkat(int olddfd, const char __user *oldname, int newdfd, + const char __user *newname, int flags) { struct dentry *new_dentry; struct path old_path, new_path; @@ -4298,9 +4309,15 @@ out: return error; } +SYSCALL_DEFINE5(linkat, int, olddfd, const char __user *, oldname, + int, newdfd, const char __user *, newname, int, flags) +{ + return do_linkat(olddfd, oldname, newdfd, newname, flags); +} + SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname) { - return sys_linkat(AT_FDCWD, oldname, AT_FDCWD, newname, 0); + return do_linkat(AT_FDCWD, oldname, AT_FDCWD, newname, 0); } /** @@ -4478,8 +4495,8 @@ out: } EXPORT_SYMBOL(vfs_rename); -SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname, - int, newdfd, const char __user *, newname, unsigned int, flags) +static int do_renameat2(int olddfd, const char __user *oldname, int newdfd, + const char __user *newname, unsigned int flags) { struct dentry *old_dentry, *new_dentry; struct dentry *trap; @@ -4621,15 +4638,21 @@ exit: return error; } +SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname, + int, newdfd, const char __user *, newname, unsigned int, flags) +{ + return do_renameat2(olddfd, oldname, newdfd, newname, flags); +} + SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname) { - return sys_renameat2(olddfd, oldname, newdfd, newname, 0); + return do_renameat2(olddfd, oldname, newdfd, newname, 0); } SYSCALL_DEFINE2(rename, const char __user *, oldname, const char __user *, newname) { - return sys_renameat2(AT_FDCWD, oldname, AT_FDCWD, newname, 0); + return do_renameat2(AT_FDCWD, oldname, AT_FDCWD, newname, 0); } int vfs_whiteout(struct inode *dir, struct dentry *dentry) diff --git a/fs/namespace.c b/fs/namespace.c index 9d1374ab6e06..e398f32d7541 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1680,7 +1680,7 @@ static inline bool may_mandlock(void) * unixes. Our API is identical to OSF/1 to avoid making a mess of AMD */ -SYSCALL_DEFINE2(umount, char __user *, name, int, flags) +int ksys_umount(char __user *name, int flags) { struct path path; struct mount *mnt; @@ -1720,6 +1720,11 @@ out: return retval; } +SYSCALL_DEFINE2(umount, char __user *, name, int, flags) +{ + return ksys_umount(name, flags); +} + #ifdef __ARCH_WANT_SYS_OLDUMOUNT /* @@ -1727,7 +1732,7 @@ out: */ SYSCALL_DEFINE1(oldumount, char __user *, name) { - return sys_umount(name, 0); + return ksys_umount(name, 0); } #endif @@ -3032,8 +3037,8 @@ struct dentry *mount_subtree(struct vfsmount *mnt, const char *name) } EXPORT_SYMBOL(mount_subtree); -SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name, - char __user *, type, unsigned long, flags, void __user *, data) +int ksys_mount(char __user *dev_name, char __user *dir_name, char __user *type, + unsigned long flags, void __user *data) { int ret; char *kernel_type; @@ -3066,6 +3071,12 @@ out_type: return ret; } +SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name, + char __user *, type, unsigned long, flags, void __user *, data) +{ + return ksys_mount(dev_name, dir_name, type, flags, data); +} + /* * Return true if path is reachable from root * diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 8c10b0562e75..621c517b325c 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -86,10 +86,10 @@ struct nfs_direct_req { struct nfs_direct_mirror mirrors[NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX]; int mirror_count; + loff_t io_start; /* Start offset for I/O */ ssize_t count, /* bytes actually processed */ max_count, /* max expected count */ bytes_left, /* bytes left to be sent */ - io_start, /* start of IO */ error; /* any reported error */ struct completion completion; /* wait for i/o completion */ diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 7d893543cf3b..d17a90c4fa37 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -85,11 +85,6 @@ int nfs_wait_bit_killable(struct wait_bit_key *key, int mode) } EXPORT_SYMBOL_GPL(nfs_wait_bit_killable); -int nfs_wait_atomic_killable(atomic_t *p, unsigned int mode) -{ - return nfs_wait_killable(mode); -} - /** * nfs_compat_user_ino64 - returns the user-visible inode number * @fileid: 64-bit fileid diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 18a7626ac638..67d19cd92e44 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -98,8 +98,8 @@ nfs_page_free(struct nfs_page *p) int nfs_iocounter_wait(struct nfs_lock_context *l_ctx) { - return wait_on_atomic_t(&l_ctx->io_count, nfs_wait_atomic_killable, - TASK_KILLABLE); + return wait_var_event_killable(&l_ctx->io_count, + !atomic_read(&l_ctx->io_count)); } /** @@ -395,7 +395,7 @@ static void nfs_clear_request(struct nfs_page *req) } if (l_ctx != NULL) { if (atomic_dec_and_test(&l_ctx->io_count)) { - wake_up_atomic_t(&l_ctx->io_count); + wake_up_var(&l_ctx->io_count); if (test_bit(NFS_CONTEXT_UNLOCK, &ctx->flags)) rpc_wake_up(&NFS_SERVER(d_inode(ctx->dentry))->uoc_rpcwaitq); } diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index c13e826614b5..ee723aa153a3 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -292,8 +292,11 @@ pnfs_detach_layout_hdr(struct pnfs_layout_hdr *lo) void pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo) { - struct inode *inode = lo->plh_inode; + struct inode *inode; + if (!lo) + return; + inode = lo->plh_inode; pnfs_layoutreturn_before_put_layout_hdr(lo); if (refcount_dec_and_lock(&lo->plh_refcount, &inode->i_lock)) { @@ -1241,10 +1244,12 @@ retry: spin_lock(&ino->i_lock); lo = nfsi->layout; if (!lo || !pnfs_layout_is_valid(lo) || - test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags)) + test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags)) { + lo = NULL; goto out_noroc; + } + pnfs_get_layout_hdr(lo); if (test_bit(NFS_LAYOUT_RETURN_LOCK, &lo->plh_flags)) { - pnfs_get_layout_hdr(lo); spin_unlock(&ino->i_lock); wait_on_bit(&lo->plh_flags, NFS_LAYOUT_RETURN, TASK_UNINTERRUPTIBLE); @@ -1312,10 +1317,12 @@ out_noroc: struct pnfs_layoutdriver_type *ld = NFS_SERVER(ino)->pnfs_curr_ld; if (ld->prepare_layoutreturn) ld->prepare_layoutreturn(args); + pnfs_put_layout_hdr(lo); return true; } if (layoutreturn) pnfs_send_layoutreturn(lo, &stateid, iomode, true); + pnfs_put_layout_hdr(lo); return false; } diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index 03aaa60c7768..32ba2d471853 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -245,7 +245,7 @@ pnfs_generic_commit_cancel_empty_pagelist(struct list_head *pages, { if (list_empty(pages)) { if (atomic_dec_and_test(&cinfo->mds->rpcs_out)) - wake_up_atomic_t(&cinfo->mds->rpcs_out); + wake_up_var(&cinfo->mds->rpcs_out); /* don't call nfs_commitdata_release - it tries to put * the open_context which is not acquired until nfs_init_commit * which has not been called on @data */ diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 29bacdc56f6a..5e470e233c83 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -2631,6 +2631,8 @@ struct dentry *nfs_fs_mount_common(struct nfs_server *server, /* initial superblock/root creation */ mount_info->fill_super(s, mount_info); nfs_get_cache_cookie(s, mount_info->parsed, mount_info->cloned); + if (!(server->flags & NFS_MOUNT_UNSHARED)) + s->s_iflags |= SB_I_MULTIROOT; } mntroot = nfs_get_root(s, mount_info->mntfh, dev_name); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 7428a669d7a7..6579f3b367bd 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1620,8 +1620,8 @@ static void nfs_writeback_result(struct rpc_task *task, static int wait_on_commit(struct nfs_mds_commit_info *cinfo) { - return wait_on_atomic_t(&cinfo->rpcs_out, - nfs_wait_atomic_killable, TASK_KILLABLE); + return wait_var_event_killable(&cinfo->rpcs_out, + !atomic_read(&cinfo->rpcs_out)); } static void nfs_commit_begin(struct nfs_mds_commit_info *cinfo) @@ -1632,7 +1632,7 @@ static void nfs_commit_begin(struct nfs_mds_commit_info *cinfo) static void nfs_commit_end(struct nfs_mds_commit_info *cinfo) { if (atomic_dec_and_test(&cinfo->rpcs_out)) - wake_up_atomic_t(&cinfo->rpcs_out); + wake_up_var(&cinfo->rpcs_out); } void nfs_commitdata_release(struct nfs_commit_data *data) @@ -1876,40 +1876,43 @@ int nfs_generic_commit_list(struct inode *inode, struct list_head *head, return status; } -int nfs_commit_inode(struct inode *inode, int how) +static int __nfs_commit_inode(struct inode *inode, int how, + struct writeback_control *wbc) { LIST_HEAD(head); struct nfs_commit_info cinfo; int may_wait = how & FLUSH_SYNC; - int error = 0; - int res; + int ret, nscan; nfs_init_cinfo_from_inode(&cinfo, inode); nfs_commit_begin(cinfo.mds); - res = nfs_scan_commit(inode, &head, &cinfo); - if (res) - error = nfs_generic_commit_list(inode, &head, how, &cinfo); + for (;;) { + ret = nscan = nfs_scan_commit(inode, &head, &cinfo); + if (ret <= 0) + break; + ret = nfs_generic_commit_list(inode, &head, how, &cinfo); + if (ret < 0) + break; + ret = 0; + if (wbc && wbc->sync_mode == WB_SYNC_NONE) { + if (nscan < wbc->nr_to_write) + wbc->nr_to_write -= nscan; + else + wbc->nr_to_write = 0; + } + if (nscan < INT_MAX) + break; + cond_resched(); + } nfs_commit_end(cinfo.mds); - if (res == 0) - return res; - if (error < 0) - goto out_error; - if (!may_wait) - goto out_mark_dirty; - error = wait_on_commit(cinfo.mds); - if (error < 0) - return error; - return res; -out_error: - res = error; - /* Note: If we exit without ensuring that the commit is complete, - * we must mark the inode as dirty. Otherwise, future calls to - * sync_inode() with the WB_SYNC_ALL flag set will fail to ensure - * that the data is on the disk. - */ -out_mark_dirty: - __mark_inode_dirty(inode, I_DIRTY_DATASYNC); - return res; + if (ret || !may_wait) + return ret; + return wait_on_commit(cinfo.mds); +} + +int nfs_commit_inode(struct inode *inode, int how) +{ + return __nfs_commit_inode(inode, how, NULL); } EXPORT_SYMBOL_GPL(nfs_commit_inode); @@ -1919,11 +1922,11 @@ int nfs_write_inode(struct inode *inode, struct writeback_control *wbc) int flags = FLUSH_SYNC; int ret = 0; - /* no commits means nothing needs to be done */ - if (!atomic_long_read(&nfsi->commit_info.ncommit)) - return ret; - if (wbc->sync_mode == WB_SYNC_NONE) { + /* no commits means nothing needs to be done */ + if (!atomic_long_read(&nfsi->commit_info.ncommit)) + goto check_requests_outstanding; + /* Don't commit yet if this is a non-blocking flush and there * are a lot of outstanding writes for this mapping. */ @@ -1934,16 +1937,16 @@ int nfs_write_inode(struct inode *inode, struct writeback_control *wbc) flags = 0; } - ret = nfs_commit_inode(inode, flags); - if (ret >= 0) { - if (wbc->sync_mode == WB_SYNC_NONE) { - if (ret < wbc->nr_to_write) - wbc->nr_to_write -= ret; - else - wbc->nr_to_write = 0; - } - return 0; - } + ret = __nfs_commit_inode(inode, flags, wbc); + if (!ret) { + if (flags & FLUSH_SYNC) + return 0; + } else if (atomic_long_read(&nfsi->commit_info.ncommit)) + goto out_mark_dirty; + +check_requests_outstanding: + if (!atomic_read(&nfsi->commit_info.rpcs_out)) + return ret; out_mark_dirty: __mark_inode_dirty(inode, I_DIRTY_DATASYNC); return ret; diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 150521c9671b..61b770e39809 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -268,6 +268,35 @@ free_blocked_lock(struct nfsd4_blocked_lock *nbl) kfree(nbl); } +static void +remove_blocked_locks(struct nfs4_lockowner *lo) +{ + struct nfs4_client *clp = lo->lo_owner.so_client; + struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); + struct nfsd4_blocked_lock *nbl; + LIST_HEAD(reaplist); + + /* Dequeue all blocked locks */ + spin_lock(&nn->blocked_locks_lock); + while (!list_empty(&lo->lo_blocked)) { + nbl = list_first_entry(&lo->lo_blocked, + struct nfsd4_blocked_lock, + nbl_list); + list_del_init(&nbl->nbl_list); + list_move(&nbl->nbl_lru, &reaplist); + } + spin_unlock(&nn->blocked_locks_lock); + + /* Now free them */ + while (!list_empty(&reaplist)) { + nbl = list_first_entry(&reaplist, struct nfsd4_blocked_lock, + nbl_lru); + list_del_init(&nbl->nbl_lru); + posix_unblock_lock(&nbl->nbl_lock); + free_blocked_lock(nbl); + } +} + static int nfsd4_cb_notify_lock_done(struct nfsd4_callback *cb, struct rpc_task *task) { @@ -1866,6 +1895,7 @@ static __be32 mark_client_expired_locked(struct nfs4_client *clp) static void __destroy_client(struct nfs4_client *clp) { + int i; struct nfs4_openowner *oo; struct nfs4_delegation *dp; struct list_head reaplist; @@ -1895,6 +1925,16 @@ __destroy_client(struct nfs4_client *clp) nfs4_get_stateowner(&oo->oo_owner); release_openowner(oo); } + for (i = 0; i < OWNER_HASH_SIZE; i++) { + struct nfs4_stateowner *so, *tmp; + + list_for_each_entry_safe(so, tmp, &clp->cl_ownerstr_hashtbl[i], + so_strhash) { + /* Should be no openowners at this point */ + WARN_ON_ONCE(so->so_is_open_owner); + remove_blocked_locks(lockowner(so)); + } + } nfsd4_return_all_client_layouts(clp); nfsd4_shutdown_callback(clp); if (clp->cl_cb_conn.cb_xprt) @@ -6355,6 +6395,7 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp, } spin_unlock(&clp->cl_lock); free_ol_stateid_reaplist(&reaplist); + remove_blocked_locks(lo); nfs4_put_stateowner(&lo->lo_owner); return status; @@ -7140,6 +7181,8 @@ nfs4_state_destroy_net(struct net *net) } } + WARN_ON(!list_empty(&nn->blocked_locks_lru)); + for (i = 0; i < CLIENT_HASH_SIZE; i++) { while (!list_empty(&nn->unconf_id_hashtbl[i])) { clp = list_entry(nn->unconf_id_hashtbl[i].next, struct nfs4_client, cl_idhash); @@ -7206,7 +7249,6 @@ nfs4_state_shutdown_net(struct net *net) struct nfs4_delegation *dp = NULL; struct list_head *pos, *next, reaplist; struct nfsd_net *nn = net_generic(net, nfsd_net_id); - struct nfsd4_blocked_lock *nbl; cancel_delayed_work_sync(&nn->laundromat_work); locks_end_grace(&nn->nfsd4_manager); @@ -7227,24 +7269,6 @@ nfs4_state_shutdown_net(struct net *net) nfs4_put_stid(&dp->dl_stid); } - BUG_ON(!list_empty(&reaplist)); - spin_lock(&nn->blocked_locks_lock); - while (!list_empty(&nn->blocked_locks_lru)) { - nbl = list_first_entry(&nn->blocked_locks_lru, - struct nfsd4_blocked_lock, nbl_lru); - list_move(&nbl->nbl_lru, &reaplist); - list_del_init(&nbl->nbl_list); - } - spin_unlock(&nn->blocked_locks_lock); - - while (!list_empty(&reaplist)) { - nbl = list_first_entry(&reaplist, - struct nfsd4_blocked_lock, nbl_lru); - list_del_init(&nbl->nbl_lru); - posix_unblock_lock(&nbl->nbl_lock); - free_blocked_lock(nbl); - } - nfsd4_client_tracking_exit(net); nfs4_state_destroy_net(net); } diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index c07eb3d655ea..fa803a58a605 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -820,9 +820,8 @@ out_destroy_group: return fd; } -SYSCALL_DEFINE5(fanotify_mark, int, fanotify_fd, unsigned int, flags, - __u64, mask, int, dfd, - const char __user *, pathname) +static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, + int dfd, const char __user *pathname) { struct inode *inode = NULL; struct vfsmount *mnt = NULL; @@ -928,13 +927,20 @@ fput_and_out: return ret; } +SYSCALL_DEFINE5(fanotify_mark, int, fanotify_fd, unsigned int, flags, + __u64, mask, int, dfd, + const char __user *, pathname) +{ + return do_fanotify_mark(fanotify_fd, flags, mask, dfd, pathname); +} + #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE6(fanotify_mark, int, fanotify_fd, unsigned int, flags, __u32, mask0, __u32, mask1, int, dfd, const char __user *, pathname) { - return sys_fanotify_mark(fanotify_fd, flags, + return do_fanotify_mark(fanotify_fd, flags, #ifdef __BIG_ENDIAN ((__u64)mask0 << 32) | mask1, #else diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index 2c908b31d6c9..43c23653ce2e 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -635,7 +635,7 @@ static struct fsnotify_group *inotify_new_group(unsigned int max_events) /* inotify syscalls */ -SYSCALL_DEFINE1(inotify_init1, int, flags) +static int do_inotify_init(int flags) { struct fsnotify_group *group; int ret; @@ -660,9 +660,14 @@ SYSCALL_DEFINE1(inotify_init1, int, flags) return ret; } +SYSCALL_DEFINE1(inotify_init1, int, flags) +{ + return do_inotify_init(flags); +} + SYSCALL_DEFINE0(inotify_init) { - return sys_inotify_init1(0); + return do_inotify_init(0); } SYSCALL_DEFINE3(inotify_add_watch, int, fd, const char __user *, pathname, diff --git a/fs/nsfs.c b/fs/nsfs.c index 36b0772701a0..60702d677bd4 100644 --- a/fs/nsfs.c +++ b/fs/nsfs.c @@ -184,6 +184,7 @@ int open_related_ns(struct ns_common *ns, return fd; } +EXPORT_SYMBOL_GPL(open_related_ns); static long ns_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index eac5140aac47..e5076185cc1e 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -1819,7 +1819,7 @@ int o2net_register_hb_callbacks(void) static int o2net_accept_one(struct socket *sock, int *more) { - int ret, slen; + int ret; struct sockaddr_in sin; struct socket *new_sock = NULL; struct o2nm_node *node = NULL; @@ -1864,9 +1864,7 @@ static int o2net_accept_one(struct socket *sock, int *more) goto out; } - slen = sizeof(sin); - ret = new_sock->ops->getname(new_sock, (struct sockaddr *) &sin, - &slen, 1); + ret = new_sock->ops->getname(new_sock, (struct sockaddr *) &sin, 1); if (ret < 0) goto out; diff --git a/fs/ocfs2/filecheck.c b/fs/ocfs2/filecheck.c index e87279e49ba3..6b92cb241138 100644 --- a/fs/ocfs2/filecheck.c +++ b/fs/ocfs2/filecheck.c @@ -134,9 +134,10 @@ ocfs2_filecheck_sysfs_free(struct ocfs2_filecheck_sysfs_entry *entry) { struct ocfs2_filecheck_entry *p; - if (!atomic_dec_and_test(&entry->fs_count)) - wait_on_atomic_t(&entry->fs_count, atomic_t_wait, - TASK_UNINTERRUPTIBLE); + if (!atomic_dec_and_test(&entry->fs_count)) { + wait_var_event(&entry->fs_count, + !atomic_read(&entry->fs_count)); + } spin_lock(&entry->fs_fcheck->fc_lock); while (!list_empty(&entry->fs_fcheck->fc_head)) { @@ -183,7 +184,7 @@ static void ocfs2_filecheck_sysfs_put(struct ocfs2_filecheck_sysfs_entry *entry) { if (atomic_dec_and_test(&entry->fs_count)) - wake_up_atomic_t(&entry->fs_count); + wake_up_var(&entry->fs_count); } static struct ocfs2_filecheck_sysfs_entry * diff --git a/fs/open.c b/fs/open.c index 7ea118471dce..d0e955b558ad 100644 --- a/fs/open.c +++ b/fs/open.c @@ -128,7 +128,7 @@ out: } EXPORT_SYMBOL_GPL(vfs_truncate); -static long do_sys_truncate(const char __user *pathname, loff_t length) +long do_sys_truncate(const char __user *pathname, loff_t length) { unsigned int lookup_flags = LOOKUP_FOLLOW; struct path path; @@ -162,7 +162,7 @@ COMPAT_SYSCALL_DEFINE2(truncate, const char __user *, path, compat_off_t, length } #endif -static long do_sys_ftruncate(unsigned int fd, loff_t length, int small) +long do_sys_ftruncate(unsigned int fd, loff_t length, int small) { struct inode *inode; struct dentry *dentry; @@ -333,7 +333,7 @@ int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len) } EXPORT_SYMBOL_GPL(vfs_fallocate); -SYSCALL_DEFINE4(fallocate, int, fd, int, mode, loff_t, offset, loff_t, len) +int ksys_fallocate(int fd, int mode, loff_t offset, loff_t len) { struct fd f = fdget(fd); int error = -EBADF; @@ -345,12 +345,17 @@ SYSCALL_DEFINE4(fallocate, int, fd, int, mode, loff_t, offset, loff_t, len) return error; } +SYSCALL_DEFINE4(fallocate, int, fd, int, mode, loff_t, offset, loff_t, len) +{ + return ksys_fallocate(fd, mode, offset, len); +} + /* * access() needs to use the real uid/gid, not the effective uid/gid. * We do this by temporarily clearing all FS-related capabilities and * switching the fsuid/fsgid around to the real ones. */ -SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode) +long do_faccessat(int dfd, const char __user *filename, int mode) { const struct cred *old_cred; struct cred *override_cred; @@ -426,12 +431,17 @@ out: return res; } +SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode) +{ + return do_faccessat(dfd, filename, mode); +} + SYSCALL_DEFINE2(access, const char __user *, filename, int, mode) { - return sys_faccessat(AT_FDCWD, filename, mode); + return do_faccessat(AT_FDCWD, filename, mode); } -SYSCALL_DEFINE1(chdir, const char __user *, filename) +int ksys_chdir(const char __user *filename) { struct path path; int error; @@ -457,6 +467,11 @@ out: return error; } +SYSCALL_DEFINE1(chdir, const char __user *, filename) +{ + return ksys_chdir(filename); +} + SYSCALL_DEFINE1(fchdir, unsigned int, fd) { struct fd f = fdget_raw(fd); @@ -479,7 +494,7 @@ out: return error; } -SYSCALL_DEFINE1(chroot, const char __user *, filename) +int ksys_chroot(const char __user *filename) { struct path path; int error; @@ -512,6 +527,11 @@ out: return error; } +SYSCALL_DEFINE1(chroot, const char __user *, filename) +{ + return ksys_chroot(filename); +} + static int chmod_common(const struct path *path, umode_t mode) { struct inode *inode = path->dentry->d_inode; @@ -541,7 +561,7 @@ out_unlock: return error; } -SYSCALL_DEFINE2(fchmod, unsigned int, fd, umode_t, mode) +int ksys_fchmod(unsigned int fd, umode_t mode) { struct fd f = fdget(fd); int err = -EBADF; @@ -554,7 +574,12 @@ SYSCALL_DEFINE2(fchmod, unsigned int, fd, umode_t, mode) return err; } -SYSCALL_DEFINE3(fchmodat, int, dfd, const char __user *, filename, umode_t, mode) +SYSCALL_DEFINE2(fchmod, unsigned int, fd, umode_t, mode) +{ + return ksys_fchmod(fd, mode); +} + +int do_fchmodat(int dfd, const char __user *filename, umode_t mode) { struct path path; int error; @@ -572,9 +597,15 @@ retry: return error; } +SYSCALL_DEFINE3(fchmodat, int, dfd, const char __user *, filename, + umode_t, mode) +{ + return do_fchmodat(dfd, filename, mode); +} + SYSCALL_DEFINE2(chmod, const char __user *, filename, umode_t, mode) { - return sys_fchmodat(AT_FDCWD, filename, mode); + return do_fchmodat(AT_FDCWD, filename, mode); } static int chown_common(const struct path *path, uid_t user, gid_t group) @@ -619,8 +650,8 @@ retry_deleg: return error; } -SYSCALL_DEFINE5(fchownat, int, dfd, const char __user *, filename, uid_t, user, - gid_t, group, int, flag) +int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group, + int flag) { struct path path; int error = -EINVAL; @@ -651,18 +682,24 @@ out: return error; } +SYSCALL_DEFINE5(fchownat, int, dfd, const char __user *, filename, uid_t, user, + gid_t, group, int, flag) +{ + return do_fchownat(dfd, filename, user, group, flag); +} + SYSCALL_DEFINE3(chown, const char __user *, filename, uid_t, user, gid_t, group) { - return sys_fchownat(AT_FDCWD, filename, user, group, 0); + return do_fchownat(AT_FDCWD, filename, user, group, 0); } SYSCALL_DEFINE3(lchown, const char __user *, filename, uid_t, user, gid_t, group) { - return sys_fchownat(AT_FDCWD, filename, user, group, - AT_SYMLINK_NOFOLLOW); + return do_fchownat(AT_FDCWD, filename, user, group, + AT_SYMLINK_NOFOLLOW); } -SYSCALL_DEFINE3(fchown, unsigned int, fd, uid_t, user, gid_t, group) +int ksys_fchown(unsigned int fd, uid_t user, gid_t group) { struct fd f = fdget(fd); int error = -EBADF; @@ -682,6 +719,11 @@ out: return error; } +SYSCALL_DEFINE3(fchown, unsigned int, fd, uid_t, user, gid_t, group) +{ + return ksys_fchown(fd, user, group); +} + int open_check_o_direct(struct file *f) { /* NB: we're sure to have correct a_ops only after f_op->open */ @@ -1114,7 +1156,7 @@ COMPAT_SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, fla */ SYSCALL_DEFINE2(creat, const char __user *, pathname, umode_t, mode) { - return sys_open(pathname, O_CREAT | O_WRONLY | O_TRUNC, mode); + return ksys_open(pathname, O_CREAT | O_WRONLY | O_TRUNC, mode); } #endif @@ -1163,7 +1205,6 @@ SYSCALL_DEFINE1(close, unsigned int, fd) return retval; } -EXPORT_SYMBOL(sys_close); /* * This routine simulates a hangup on the tty, to arrange that users diff --git a/fs/pipe.c b/fs/pipe.c index 7b1954caf388..39d6f431da83 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -841,7 +841,7 @@ int do_pipe_flags(int *fd, int flags) * sys_pipe() is the normal C calling standard for creating * a pipe. It's not the way Unix traditionally does this, though. */ -SYSCALL_DEFINE2(pipe2, int __user *, fildes, int, flags) +static int do_pipe2(int __user *fildes, int flags) { struct file *files[2]; int fd[2]; @@ -863,9 +863,14 @@ SYSCALL_DEFINE2(pipe2, int __user *, fildes, int, flags) return error; } +SYSCALL_DEFINE2(pipe2, int __user *, fildes, int, flags) +{ + return do_pipe2(fildes, flags); +} + SYSCALL_DEFINE1(pipe, int __user *, fildes) { - return sys_pipe2(fildes, 0); + return do_pipe2(fildes, 0); } static int wait_for_partner(struct pipe_inode_info *pipe, unsigned int *cnt) diff --git a/fs/proc/base.c b/fs/proc/base.c index 9298324325ed..d53246863cfb 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -94,9 +94,6 @@ #include <linux/sched/stat.h> #include <linux/flex_array.h> #include <linux/posix-timers.h> -#ifdef CONFIG_HARDWALL -#include <asm/hardwall.h> -#endif #include <trace/events/oom.h> #include "internal.h" #include "fd.h" @@ -3002,9 +2999,6 @@ static const struct pid_entry tgid_base_stuff[] = { #ifdef CONFIG_TASK_IO_ACCOUNTING ONE("io", S_IRUSR, proc_tgid_io_accounting), #endif -#ifdef CONFIG_HARDWALL - ONE("hardwall", S_IRUGO, proc_pid_hardwall), -#endif #ifdef CONFIG_USER_NS REG("uid_map", S_IRUGO|S_IWUSR, proc_uid_map_operations), REG("gid_map", S_IRUGO|S_IWUSR, proc_gid_map_operations), @@ -3393,9 +3387,6 @@ static const struct pid_entry tid_base_stuff[] = { #ifdef CONFIG_TASK_IO_ACCOUNTING ONE("io", S_IRUSR, proc_tid_io_accounting), #endif -#ifdef CONFIG_HARDWALL - ONE("hardwall", S_IRUGO, proc_pid_hardwall), -#endif #ifdef CONFIG_USER_NS REG("uid_map", S_IRUGO|S_IWUSR, proc_uid_map_operations), REG("gid_map", S_IRUGO|S_IWUSR, proc_gid_map_operations), diff --git a/fs/quota/compat.c b/fs/quota/compat.c index 779caed4f078..c30572857619 100644 --- a/fs/quota/compat.c +++ b/fs/quota/compat.c @@ -41,8 +41,9 @@ struct compat_fs_quota_stat { __u16 qs_iwarnlimit; }; -asmlinkage long sys32_quotactl(unsigned int cmd, const char __user *special, - qid_t id, void __user *addr) +COMPAT_SYSCALL_DEFINE4(quotactl32, unsigned int, cmd, + const char __user *, special, qid_t, id, + void __user *, addr) { unsigned int cmds; struct if_dqblk __user *dqblk; @@ -59,7 +60,7 @@ asmlinkage long sys32_quotactl(unsigned int cmd, const char __user *special, case Q_GETQUOTA: dqblk = compat_alloc_user_space(sizeof(struct if_dqblk)); compat_dqblk = addr; - ret = sys_quotactl(cmd, special, id, dqblk); + ret = kernel_quotactl(cmd, special, id, dqblk); if (ret) break; if (copy_in_user(compat_dqblk, dqblk, sizeof(*compat_dqblk)) || @@ -75,12 +76,12 @@ asmlinkage long sys32_quotactl(unsigned int cmd, const char __user *special, get_user(data, &compat_dqblk->dqb_valid) || put_user(data, &dqblk->dqb_valid)) break; - ret = sys_quotactl(cmd, special, id, dqblk); + ret = kernel_quotactl(cmd, special, id, dqblk); break; case Q_XGETQSTAT: fsqstat = compat_alloc_user_space(sizeof(struct fs_quota_stat)); compat_fsqstat = addr; - ret = sys_quotactl(cmd, special, id, fsqstat); + ret = kernel_quotactl(cmd, special, id, fsqstat); if (ret) break; ret = -EFAULT; @@ -113,7 +114,7 @@ asmlinkage long sys32_quotactl(unsigned int cmd, const char __user *special, ret = 0; break; default: - ret = sys_quotactl(cmd, special, id, addr); + ret = kernel_quotactl(cmd, special, id, addr); } return ret; } diff --git a/fs/quota/quota.c b/fs/quota/quota.c index 43612e2a73af..860bfbe7a07a 100644 --- a/fs/quota/quota.c +++ b/fs/quota/quota.c @@ -833,8 +833,8 @@ static struct super_block *quotactl_block(const char __user *special, int cmd) * calls. Maybe we need to add the process quotas etc. in the future, * but we probably should use rlimits for that. */ -SYSCALL_DEFINE4(quotactl, unsigned int, cmd, const char __user *, special, - qid_t, id, void __user *, addr) +int kernel_quotactl(unsigned int cmd, const char __user *special, + qid_t id, void __user *addr) { uint cmds, type; struct super_block *sb = NULL; @@ -885,3 +885,9 @@ out: path_put(pathp); return ret; } + +SYSCALL_DEFINE4(quotactl, unsigned int, cmd, const char __user *, special, + qid_t, id, void __user *, addr) +{ + return kernel_quotactl(cmd, special, id, addr); +} diff --git a/fs/read_write.c b/fs/read_write.c index f8547b82dfb3..c4eabbfc90df 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -301,7 +301,7 @@ loff_t vfs_llseek(struct file *file, loff_t offset, int whence) } EXPORT_SYMBOL(vfs_llseek); -SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, whence) +off_t ksys_lseek(unsigned int fd, off_t offset, unsigned int whence) { off_t retval; struct fd f = fdget_pos(fd); @@ -319,10 +319,15 @@ SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, whence) return retval; } +SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, whence) +{ + return ksys_lseek(fd, offset, whence); +} + #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE3(lseek, unsigned int, fd, compat_off_t, offset, unsigned int, whence) { - return sys_lseek(fd, offset, whence); + return ksys_lseek(fd, offset, whence); } #endif @@ -563,7 +568,7 @@ static inline void file_pos_write(struct file *file, loff_t pos) file->f_pos = pos; } -SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count) +ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count) { struct fd f = fdget_pos(fd); ssize_t ret = -EBADF; @@ -578,8 +583,12 @@ SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count) return ret; } -SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf, - size_t, count) +SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count) +{ + return ksys_read(fd, buf, count); +} + +ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count) { struct fd f = fdget_pos(fd); ssize_t ret = -EBADF; @@ -595,8 +604,14 @@ SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf, return ret; } -SYSCALL_DEFINE4(pread64, unsigned int, fd, char __user *, buf, - size_t, count, loff_t, pos) +SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf, + size_t, count) +{ + return ksys_write(fd, buf, count); +} + +ssize_t ksys_pread64(unsigned int fd, char __user *buf, size_t count, + loff_t pos) { struct fd f; ssize_t ret = -EBADF; @@ -615,8 +630,14 @@ SYSCALL_DEFINE4(pread64, unsigned int, fd, char __user *, buf, return ret; } -SYSCALL_DEFINE4(pwrite64, unsigned int, fd, const char __user *, buf, - size_t, count, loff_t, pos) +SYSCALL_DEFINE4(pread64, unsigned int, fd, char __user *, buf, + size_t, count, loff_t, pos) +{ + return ksys_pread64(fd, buf, count, pos); +} + +ssize_t ksys_pwrite64(unsigned int fd, const char __user *buf, + size_t count, loff_t pos) { struct fd f; ssize_t ret = -EBADF; @@ -635,6 +656,12 @@ SYSCALL_DEFINE4(pwrite64, unsigned int, fd, const char __user *, buf, return ret; } +SYSCALL_DEFINE4(pwrite64, unsigned int, fd, const char __user *, buf, + size_t, count, loff_t, pos) +{ + return ksys_pwrite64(fd, buf, count, pos); +} + static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter, loff_t *ppos, int type, rwf_t flags) { diff --git a/fs/readdir.c b/fs/readdir.c index 1b83b0ad183b..d97f548e6323 100644 --- a/fs/readdir.c +++ b/fs/readdir.c @@ -292,8 +292,8 @@ efault: return -EFAULT; } -SYSCALL_DEFINE3(getdents64, unsigned int, fd, - struct linux_dirent64 __user *, dirent, unsigned int, count) +int ksys_getdents64(unsigned int fd, struct linux_dirent64 __user *dirent, + unsigned int count) { struct fd f; struct linux_dirent64 __user * lastdirent; @@ -326,6 +326,13 @@ SYSCALL_DEFINE3(getdents64, unsigned int, fd, return error; } + +SYSCALL_DEFINE3(getdents64, unsigned int, fd, + struct linux_dirent64 __user *, dirent, unsigned int, count) +{ + return ksys_getdents64(fd, dirent, count); +} + #ifdef CONFIG_COMPAT struct compat_old_linux_dirent { compat_ulong_t d_ino; diff --git a/fs/select.c b/fs/select.c index b6c36254028a..ba879c51288f 100644 --- a/fs/select.c +++ b/fs/select.c @@ -675,8 +675,8 @@ out_nofds: return ret; } -SYSCALL_DEFINE5(select, int, n, fd_set __user *, inp, fd_set __user *, outp, - fd_set __user *, exp, struct timeval __user *, tvp) +static int kern_select(int n, fd_set __user *inp, fd_set __user *outp, + fd_set __user *exp, struct timeval __user *tvp) { struct timespec64 end_time, *to = NULL; struct timeval tv; @@ -699,6 +699,12 @@ SYSCALL_DEFINE5(select, int, n, fd_set __user *, inp, fd_set __user *, outp, return ret; } +SYSCALL_DEFINE5(select, int, n, fd_set __user *, inp, fd_set __user *, outp, + fd_set __user *, exp, struct timeval __user *, tvp) +{ + return kern_select(n, inp, outp, exp, tvp); +} + static long do_pselect(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timespec __user *tsp, const sigset_t __user *sigmask, size_t sigsetsize) @@ -784,7 +790,7 @@ SYSCALL_DEFINE1(old_select, struct sel_arg_struct __user *, arg) if (copy_from_user(&a, arg, sizeof(a))) return -EFAULT; - return sys_select(a.n, a.inp, a.outp, a.exp, a.tvp); + return kern_select(a.n, a.inp, a.outp, a.exp, a.tvp); } #endif @@ -1259,9 +1265,9 @@ out_nofds: return ret; } -COMPAT_SYSCALL_DEFINE5(select, int, n, compat_ulong_t __user *, inp, - compat_ulong_t __user *, outp, compat_ulong_t __user *, exp, - struct compat_timeval __user *, tvp) +static int do_compat_select(int n, compat_ulong_t __user *inp, + compat_ulong_t __user *outp, compat_ulong_t __user *exp, + struct compat_timeval __user *tvp) { struct timespec64 end_time, *to = NULL; struct compat_timeval tv; @@ -1284,6 +1290,13 @@ COMPAT_SYSCALL_DEFINE5(select, int, n, compat_ulong_t __user *, inp, return ret; } +COMPAT_SYSCALL_DEFINE5(select, int, n, compat_ulong_t __user *, inp, + compat_ulong_t __user *, outp, compat_ulong_t __user *, exp, + struct compat_timeval __user *, tvp) +{ + return do_compat_select(n, inp, outp, exp, tvp); +} + struct compat_sel_arg_struct { compat_ulong_t n; compat_uptr_t inp; @@ -1298,8 +1311,8 @@ COMPAT_SYSCALL_DEFINE1(old_select, struct compat_sel_arg_struct __user *, arg) if (copy_from_user(&a, arg, sizeof(a))) return -EFAULT; - return compat_sys_select(a.n, compat_ptr(a.inp), compat_ptr(a.outp), - compat_ptr(a.exp), compat_ptr(a.tvp)); + return do_compat_select(a.n, compat_ptr(a.inp), compat_ptr(a.outp), + compat_ptr(a.exp), compat_ptr(a.tvp)); } static long do_compat_pselect(int n, compat_ulong_t __user *inp, diff --git a/fs/signalfd.c b/fs/signalfd.c index 76bf9cc62074..d2187a813376 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -256,8 +256,8 @@ static const struct file_operations signalfd_fops = { .llseek = noop_llseek, }; -SYSCALL_DEFINE4(signalfd4, int, ufd, sigset_t __user *, user_mask, - size_t, sizemask, int, flags) +static int do_signalfd4(int ufd, sigset_t __user *user_mask, size_t sizemask, + int flags) { sigset_t sigmask; struct signalfd_ctx *ctx; @@ -310,17 +310,22 @@ SYSCALL_DEFINE4(signalfd4, int, ufd, sigset_t __user *, user_mask, return ufd; } +SYSCALL_DEFINE4(signalfd4, int, ufd, sigset_t __user *, user_mask, + size_t, sizemask, int, flags) +{ + return do_signalfd4(ufd, user_mask, sizemask, flags); +} + SYSCALL_DEFINE3(signalfd, int, ufd, sigset_t __user *, user_mask, size_t, sizemask) { - return sys_signalfd4(ufd, user_mask, sizemask, 0); + return do_signalfd4(ufd, user_mask, sizemask, 0); } #ifdef CONFIG_COMPAT -COMPAT_SYSCALL_DEFINE4(signalfd4, int, ufd, - const compat_sigset_t __user *,sigmask, - compat_size_t, sigsetsize, - int, flags) +static long do_compat_signalfd4(int ufd, + const compat_sigset_t __user *sigmask, + compat_size_t sigsetsize, int flags) { sigset_t tmp; sigset_t __user *ksigmask; @@ -333,13 +338,21 @@ COMPAT_SYSCALL_DEFINE4(signalfd4, int, ufd, if (copy_to_user(ksigmask, &tmp, sizeof(sigset_t))) return -EFAULT; - return sys_signalfd4(ufd, ksigmask, sizeof(sigset_t), flags); + return do_signalfd4(ufd, ksigmask, sizeof(sigset_t), flags); +} + +COMPAT_SYSCALL_DEFINE4(signalfd4, int, ufd, + const compat_sigset_t __user *, sigmask, + compat_size_t, sigsetsize, + int, flags) +{ + return do_compat_signalfd4(ufd, sigmask, sigsetsize, flags); } COMPAT_SYSCALL_DEFINE3(signalfd, int, ufd, const compat_sigset_t __user *,sigmask, compat_size_t, sigsetsize) { - return compat_sys_signalfd4(ufd, sigmask, sigsetsize, 0); + return do_compat_signalfd4(ufd, sigmask, sigsetsize, 0); } #endif diff --git a/fs/splice.c b/fs/splice.c index 39e2dc01ac12..005d09cf3fa8 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -1331,8 +1331,8 @@ static long vmsplice_to_pipe(struct file *file, const struct iovec __user *uiov, * Currently we punt and implement it as a normal copy, see pipe_to_user(). * */ -SYSCALL_DEFINE4(vmsplice, int, fd, const struct iovec __user *, iov, - unsigned long, nr_segs, unsigned int, flags) +static long do_vmsplice(int fd, const struct iovec __user *iov, + unsigned long nr_segs, unsigned int flags) { struct fd f; long error; @@ -1358,6 +1358,12 @@ SYSCALL_DEFINE4(vmsplice, int, fd, const struct iovec __user *, iov, return error; } +SYSCALL_DEFINE4(vmsplice, int, fd, const struct iovec __user *, iov, + unsigned long, nr_segs, unsigned int, flags) +{ + return do_vmsplice(fd, iov, nr_segs, flags); +} + #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE4(vmsplice, int, fd, const struct compat_iovec __user *, iov32, unsigned int, nr_segs, unsigned int, flags) @@ -1375,7 +1381,7 @@ COMPAT_SYSCALL_DEFINE4(vmsplice, int, fd, const struct compat_iovec __user *, io put_user(v.iov_len, &iov[i].iov_len)) return -EFAULT; } - return sys_vmsplice(fd, iov, nr_segs, flags); + return do_vmsplice(fd, iov, nr_segs, flags); } #endif diff --git a/fs/stat.c b/fs/stat.c index 873785dae022..f8e6fb2c3657 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -379,8 +379,8 @@ SYSCALL_DEFINE2(newfstat, unsigned int, fd, struct stat __user *, statbuf) return error; } -SYSCALL_DEFINE4(readlinkat, int, dfd, const char __user *, pathname, - char __user *, buf, int, bufsiz) +static int do_readlinkat(int dfd, const char __user *pathname, + char __user *buf, int bufsiz) { struct path path; int error; @@ -415,10 +415,16 @@ retry: return error; } +SYSCALL_DEFINE4(readlinkat, int, dfd, const char __user *, pathname, + char __user *, buf, int, bufsiz) +{ + return do_readlinkat(dfd, pathname, buf, bufsiz); +} + SYSCALL_DEFINE3(readlink, const char __user *, path, char __user *, buf, int, bufsiz) { - return sys_readlinkat(AT_FDCWD, path, buf, bufsiz); + return do_readlinkat(AT_FDCWD, path, buf, bufsiz); } diff --git a/fs/sync.c b/fs/sync.c index 09f0259724ff..b54e0541ad89 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -105,7 +105,7 @@ static void fdatawait_one_bdev(struct block_device *bdev, void *arg) * just write metadata (such as inodes or bitmaps) to block device page cache * and do not sync it on their own in ->sync_fs(). */ -SYSCALL_DEFINE0(sync) +void ksys_sync(void) { int nowait = 0, wait = 1; @@ -117,6 +117,11 @@ SYSCALL_DEFINE0(sync) iterate_bdevs(fdatawait_one_bdev, NULL); if (unlikely(laptop_mode)) laptop_sync_completion(); +} + +SYSCALL_DEFINE0(sync) +{ + ksys_sync(); return 0; } @@ -276,8 +281,8 @@ SYSCALL_DEFINE1(fdatasync, unsigned int, fd) * already-instantiated disk blocks, there are no guarantees here that the data * will be available after a crash. */ -SYSCALL_DEFINE4(sync_file_range, int, fd, loff_t, offset, loff_t, nbytes, - unsigned int, flags) +int ksys_sync_file_range(int fd, loff_t offset, loff_t nbytes, + unsigned int flags) { int ret; struct fd f; @@ -355,10 +360,16 @@ out: return ret; } +SYSCALL_DEFINE4(sync_file_range, int, fd, loff_t, offset, loff_t, nbytes, + unsigned int, flags) +{ + return ksys_sync_file_range(fd, offset, nbytes, flags); +} + /* It would be nice if people remember that not all the world's an i386 when they introduce new system calls */ SYSCALL_DEFINE4(sync_file_range2, int, fd, unsigned int, flags, loff_t, offset, loff_t, nbytes) { - return sys_sync_file_range(fd, offset, nbytes, flags); + return ksys_sync_file_range(fd, offset, nbytes, flags); } diff --git a/fs/sysfs/symlink.c b/fs/sysfs/symlink.c index 8664db25a9a6..215c225b2ca1 100644 --- a/fs/sysfs/symlink.c +++ b/fs/sysfs/symlink.c @@ -106,6 +106,7 @@ int sysfs_create_link_nowarn(struct kobject *kobj, struct kobject *target, { return sysfs_do_create_link(kobj, target, name, 0); } +EXPORT_SYMBOL_GPL(sysfs_create_link_nowarn); /** * sysfs_delete_link - remove symlink in object's directory. diff --git a/fs/utimes.c b/fs/utimes.c index e4b3d7c2c9f5..69d4b6ba1bfb 100644 --- a/fs/utimes.c +++ b/fs/utimes.c @@ -184,8 +184,8 @@ SYSCALL_DEFINE4(utimensat, int, dfd, const char __user *, filename, return do_utimes(dfd, filename, utimes ? tstimes : NULL, flags); } -SYSCALL_DEFINE3(futimesat, int, dfd, const char __user *, filename, - struct timeval __user *, utimes) +static long do_futimesat(int dfd, const char __user *filename, + struct timeval __user *utimes) { struct timeval times[2]; struct timespec64 tstimes[2]; @@ -212,10 +212,17 @@ SYSCALL_DEFINE3(futimesat, int, dfd, const char __user *, filename, return do_utimes(dfd, filename, utimes ? tstimes : NULL, 0); } + +SYSCALL_DEFINE3(futimesat, int, dfd, const char __user *, filename, + struct timeval __user *, utimes) +{ + return do_futimesat(dfd, filename, utimes); +} + SYSCALL_DEFINE2(utimes, char __user *, filename, struct timeval __user *, utimes) { - return sys_futimesat(AT_FDCWD, filename, utimes); + return do_futimesat(AT_FDCWD, filename, utimes); } #ifdef CONFIG_COMPAT @@ -253,7 +260,8 @@ COMPAT_SYSCALL_DEFINE4(utimensat, unsigned int, dfd, const char __user *, filena return do_utimes(dfd, filename, t ? tv : NULL, flags); } -COMPAT_SYSCALL_DEFINE3(futimesat, unsigned int, dfd, const char __user *, filename, struct compat_timeval __user *, t) +static long do_compat_futimesat(unsigned int dfd, const char __user *filename, + struct compat_timeval __user *t) { struct timespec64 tv[2]; @@ -272,8 +280,15 @@ COMPAT_SYSCALL_DEFINE3(futimesat, unsigned int, dfd, const char __user *, filena return do_utimes(dfd, filename, t ? tv : NULL, 0); } +COMPAT_SYSCALL_DEFINE3(futimesat, unsigned int, dfd, + const char __user *, filename, + struct compat_timeval __user *, t) +{ + return do_compat_futimesat(dfd, filename, t); +} + COMPAT_SYSCALL_DEFINE2(utimes, const char __user *, filename, struct compat_timeval __user *, t) { - return compat_sys_futimesat(AT_FDCWD, filename, t); + return do_compat_futimesat(AT_FDCWD, filename, t); } #endif |