diff options
Diffstat (limited to 'fs')
436 files changed, 8215 insertions, 3656 deletions
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index 550d0b169d7c..61e0c552083f 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -624,9 +624,9 @@ static void v9fs_mmap_vm_close(struct vm_area_struct *vma) struct writeback_control wbc = { .nr_to_write = LONG_MAX, .sync_mode = WB_SYNC_ALL, - .range_start = vma->vm_pgoff * PAGE_SIZE, + .range_start = (loff_t)vma->vm_pgoff * PAGE_SIZE, /* absolute end, byte at end included */ - .range_end = vma->vm_pgoff * PAGE_SIZE + + .range_end = (loff_t)vma->vm_pgoff * PAGE_SIZE + (vma->vm_end - vma->vm_start - 1), }; diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index a950a927a626..c94e0748fc32 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -656,14 +656,10 @@ v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode, if (stat->st_result_mask & P9_STATS_NLINK) set_nlink(inode, stat->st_nlink); if (stat->st_result_mask & P9_STATS_MODE) { - inode->i_mode = stat->st_mode; - if ((S_ISBLK(inode->i_mode)) || - (S_ISCHR(inode->i_mode))) - init_special_inode(inode, inode->i_mode, - inode->i_rdev); + mode = stat->st_mode & S_IALLUGO; + mode |= inode->i_mode & ~S_IALLUGO; + inode->i_mode = mode; } - if (stat->st_result_mask & P9_STATS_RDEV) - inode->i_rdev = new_decode_dev(stat->st_rdev); if (!(flags & V9FS_STAT2INODE_KEEP_ISIZE) && stat->st_result_mask & P9_STATS_SIZE) v9fs_i_size_write(inode, stat->st_size); diff --git a/fs/affs/file.c b/fs/affs/file.c index ba084b0b214b..82bb38370aa9 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -878,7 +878,7 @@ affs_truncate(struct inode *inode) if (inode->i_size > AFFS_I(inode)->mmu_private) { struct address_space *mapping = inode->i_mapping; struct page *page; - void *fsdata; + void *fsdata = NULL; loff_t isize = inode->i_size; int res; diff --git a/fs/affs/namei.c b/fs/affs/namei.c index 41c5749f4db7..5400a876d73f 100644 --- a/fs/affs/namei.c +++ b/fs/affs/namei.c @@ -460,8 +460,10 @@ affs_xrename(struct inode *old_dir, struct dentry *old_dentry, return -EIO; bh_new = affs_bread(sb, d_inode(new_dentry)->i_ino); - if (!bh_new) + if (!bh_new) { + affs_brelse(bh_old); return -EIO; + } /* Remove old header from its parent directory. */ affs_lock_dir(old_dir); diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 54e7f6f1405e..31055d71b788 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -383,8 +383,11 @@ static int afs_dir_iterate_block(struct dir_context *ctx, } /* skip if starts before the current position */ - if (offset < curr) + if (offset < curr) { + if (next > curr) + ctx->pos = blkoff + next * sizeof(union afs_xdr_dirent); continue; + } /* found the next entry */ if (!dir_emit(ctx, dire->u.name, nlen, @@ -884,7 +887,7 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry, static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) { struct afs_vnode *vnode, *dir; - struct afs_fid uninitialized_var(fid); + struct afs_fid fid; struct dentry *parent; struct inode *inode; struct key *key; diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c index fc6c42eeb659..ff21ce511f47 100644 --- a/fs/afs/dynroot.c +++ b/fs/afs/dynroot.c @@ -172,20 +172,9 @@ static int afs_dynroot_d_revalidate(struct dentry *dentry, unsigned int flags) return 1; } -/* - * Allow the VFS to enquire as to whether a dentry should be unhashed (mustn't - * sleep) - * - called from dput() when d_count is going to 0. - * - return 1 to request dentry be unhashed, 0 otherwise - */ -static int afs_dynroot_d_delete(const struct dentry *dentry) -{ - return d_really_is_positive(dentry); -} - const struct dentry_operations afs_dynroot_dentry_operations = { .d_revalidate = afs_dynroot_d_revalidate, - .d_delete = afs_dynroot_d_delete, + .d_delete = always_delete_dentry, .d_release = afs_d_release, .d_automount = afs_d_automount, }; diff --git a/fs/afs/inode.c b/fs/afs/inode.c index e6f11da5461b..0983d7e859c8 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -468,10 +468,23 @@ int afs_getattr(const struct path *path, struct kstat *stat, { struct inode *inode = d_inode(path->dentry); struct afs_vnode *vnode = AFS_FS_I(inode); - int seq = 0; + struct key *key; + int ret, seq = 0; _enter("{ ino=%lu v=%u }", inode->i_ino, inode->i_generation); + if (vnode->volume && + !(query_flags & AT_STATX_DONT_SYNC) && + !test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) { + key = afs_request_key(vnode->volume->cell); + if (IS_ERR(key)) + return PTR_ERR(key); + ret = afs_validate(vnode, key); + key_put(key); + if (ret < 0) + return ret; + } + do { read_seqbegin_or_lock(&vnode->cb_lock, &seq); generic_fillattr(inode, stat); diff --git a/fs/afs/main.c b/fs/afs/main.c index 107427688edd..2eecb2c0a3c0 100644 --- a/fs/afs/main.c +++ b/fs/afs/main.c @@ -190,7 +190,7 @@ static int __init afs_init(void) goto error_cache; #endif - ret = register_pernet_subsys(&afs_net_ops); + ret = register_pernet_device(&afs_net_ops); if (ret < 0) goto error_net; @@ -200,8 +200,8 @@ static int __init afs_init(void) goto error_fs; afs_proc_symlink = proc_symlink("fs/afs", NULL, "../self/net/afs"); - if (IS_ERR(afs_proc_symlink)) { - ret = PTR_ERR(afs_proc_symlink); + if (!afs_proc_symlink) { + ret = -ENOMEM; goto error_proc; } @@ -210,7 +210,7 @@ static int __init afs_init(void) error_proc: afs_fs_exit(); error_fs: - unregister_pernet_subsys(&afs_net_ops); + unregister_pernet_device(&afs_net_ops); error_net: #ifdef CONFIG_AFS_FSCACHE fscache_unregister_netfs(&afs_cache_netfs); @@ -241,7 +241,7 @@ static void __exit afs_exit(void) proc_remove(afs_proc_symlink); afs_fs_exit(); - unregister_pernet_subsys(&afs_net_ops); + unregister_pernet_device(&afs_net_ops); #ifdef CONFIG_AFS_FSCACHE fscache_unregister_netfs(&afs_cache_netfs); #endif diff --git a/fs/afs/security.c b/fs/afs/security.c index 66042b432baa..e12e532069ee 100644 --- a/fs/afs/security.c +++ b/fs/afs/security.c @@ -340,7 +340,7 @@ int afs_check_permit(struct afs_vnode *vnode, struct key *key, int afs_permission(struct inode *inode, int mask) { struct afs_vnode *vnode = AFS_FS_I(inode); - afs_access_t uninitialized_var(access); + afs_access_t access; struct key *key; int ret; @@ -176,8 +176,9 @@ struct poll_iocb { struct file *file; struct wait_queue_head *head; __poll_t events; - bool done; bool cancelled; + bool work_scheduled; + bool work_need_resched; struct wait_queue_entry wait; struct work_struct work; }; @@ -331,6 +332,9 @@ static int aio_ring_mremap(struct vm_area_struct *vma) spin_lock(&mm->ioctx_lock); rcu_read_lock(); table = rcu_dereference(mm->ioctx_table); + if (!table) + goto out_unlock; + for (i = 0; i < table->nr; i++) { struct kioctx *ctx; @@ -344,6 +348,7 @@ static int aio_ring_mremap(struct vm_area_struct *vma) } } +out_unlock: rcu_read_unlock(); spin_unlock(&mm->ioctx_lock); return res; @@ -1616,6 +1621,51 @@ static void aio_poll_put_work(struct work_struct *work) iocb_put(iocb); } +/* + * Safely lock the waitqueue which the request is on, synchronizing with the + * case where the ->poll() provider decides to free its waitqueue early. + * + * Returns true on success, meaning that req->head->lock was locked, req->wait + * is on req->head, and an RCU read lock was taken. Returns false if the + * request was already removed from its waitqueue (which might no longer exist). + */ +static bool poll_iocb_lock_wq(struct poll_iocb *req) +{ + wait_queue_head_t *head; + + /* + * While we hold the waitqueue lock and the waitqueue is nonempty, + * wake_up_pollfree() will wait for us. However, taking the waitqueue + * lock in the first place can race with the waitqueue being freed. + * + * We solve this as eventpoll does: by taking advantage of the fact that + * all users of wake_up_pollfree() will RCU-delay the actual free. If + * we enter rcu_read_lock() and see that the pointer to the queue is + * non-NULL, we can then lock it without the memory being freed out from + * under us, then check whether the request is still on the queue. + * + * Keep holding rcu_read_lock() as long as we hold the queue lock, in + * case the caller deletes the entry from the queue, leaving it empty. + * In that case, only RCU prevents the queue memory from being freed. + */ + rcu_read_lock(); + head = smp_load_acquire(&req->head); + if (head) { + spin_lock(&head->lock); + if (!list_empty(&req->wait.entry)) + return true; + spin_unlock(&head->lock); + } + rcu_read_unlock(); + return false; +} + +static void poll_iocb_unlock_wq(struct poll_iocb *req) +{ + spin_unlock(&req->head->lock); + rcu_read_unlock(); +} + static void aio_poll_complete_work(struct work_struct *work) { struct poll_iocb *req = container_of(work, struct poll_iocb, work); @@ -1635,14 +1685,27 @@ static void aio_poll_complete_work(struct work_struct *work) * avoid further branches in the fast path. */ spin_lock_irq(&ctx->ctx_lock); - if (!mask && !READ_ONCE(req->cancelled)) { - add_wait_queue(req->head, &req->wait); - spin_unlock_irq(&ctx->ctx_lock); - return; - } + if (poll_iocb_lock_wq(req)) { + if (!mask && !READ_ONCE(req->cancelled)) { + /* + * The request isn't actually ready to be completed yet. + * Reschedule completion if another wakeup came in. + */ + if (req->work_need_resched) { + schedule_work(&req->work); + req->work_need_resched = false; + } else { + req->work_scheduled = false; + } + poll_iocb_unlock_wq(req); + spin_unlock_irq(&ctx->ctx_lock); + return; + } + list_del_init(&req->wait.entry); + poll_iocb_unlock_wq(req); + } /* else, POLLFREE has freed the waitqueue, so we must complete */ list_del_init(&iocb->ki_list); iocb->ki_res.res = mangle_poll(mask); - req->done = true; spin_unlock_irq(&ctx->ctx_lock); iocb_put(iocb); @@ -1654,13 +1717,14 @@ static int aio_poll_cancel(struct kiocb *iocb) struct aio_kiocb *aiocb = container_of(iocb, struct aio_kiocb, rw); struct poll_iocb *req = &aiocb->poll; - spin_lock(&req->head->lock); - WRITE_ONCE(req->cancelled, true); - if (!list_empty(&req->wait.entry)) { - list_del_init(&req->wait.entry); - schedule_work(&aiocb->poll.work); - } - spin_unlock(&req->head->lock); + if (poll_iocb_lock_wq(req)) { + WRITE_ONCE(req->cancelled, true); + if (!req->work_scheduled) { + schedule_work(&aiocb->poll.work); + req->work_scheduled = true; + } + poll_iocb_unlock_wq(req); + } /* else, the request was force-cancelled by POLLFREE already */ return 0; } @@ -1677,20 +1741,26 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, if (mask && !(mask & req->events)) return 0; - list_del_init(&req->wait.entry); - - if (mask && spin_trylock_irqsave(&iocb->ki_ctx->ctx_lock, flags)) { + /* + * Complete the request inline if possible. This requires that three + * conditions be met: + * 1. An event mask must have been passed. If a plain wakeup was done + * instead, then mask == 0 and we have to call vfs_poll() to get + * the events, so inline completion isn't possible. + * 2. The completion work must not have already been scheduled. + * 3. ctx_lock must not be busy. We have to use trylock because we + * already hold the waitqueue lock, so this inverts the normal + * locking order. Use irqsave/irqrestore because not all + * filesystems (e.g. fuse) call this function with IRQs disabled, + * yet IRQs have to be disabled before ctx_lock is obtained. + */ + if (mask && !req->work_scheduled && + spin_trylock_irqsave(&iocb->ki_ctx->ctx_lock, flags)) { struct kioctx *ctx = iocb->ki_ctx; - /* - * Try to complete the iocb inline if we can. Use - * irqsave/irqrestore because not all filesystems (e.g. fuse) - * call this function with IRQs disabled and because IRQs - * have to be disabled before ctx_lock is obtained. - */ + list_del_init(&req->wait.entry); list_del(&iocb->ki_list); iocb->ki_res.res = mangle_poll(mask); - req->done = true; if (iocb->ki_eventfd && eventfd_signal_count()) { iocb = NULL; INIT_WORK(&req->work, aio_poll_put_work); @@ -1700,7 +1770,43 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, if (iocb) iocb_put(iocb); } else { - schedule_work(&req->work); + /* + * Schedule the completion work if needed. If it was already + * scheduled, record that another wakeup came in. + * + * Don't remove the request from the waitqueue here, as it might + * not actually be complete yet (we won't know until vfs_poll() + * is called), and we must not miss any wakeups. POLLFREE is an + * exception to this; see below. + */ + if (req->work_scheduled) { + req->work_need_resched = true; + } else { + schedule_work(&req->work); + req->work_scheduled = true; + } + + /* + * If the waitqueue is being freed early but we can't complete + * the request inline, we have to tear down the request as best + * we can. That means immediately removing the request from its + * waitqueue and preventing all further accesses to the + * waitqueue via the request. We also need to schedule the + * completion work (done above). Also mark the request as + * cancelled, to potentially skip an unneeded call to ->poll(). + */ + if (mask & POLLFREE) { + WRITE_ONCE(req->cancelled, true); + list_del_init(&req->wait.entry); + + /* + * Careful: this *must* be the last step, since as soon + * as req->head is NULL'ed out, the request can be + * completed and freed, since aio_poll_complete_work() + * will no longer need to take the waitqueue lock. + */ + smp_store_release(&req->head, NULL); + } } return 1; } @@ -1708,6 +1814,7 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, struct aio_poll_table { struct poll_table_struct pt; struct aio_kiocb *iocb; + bool queued; int error; }; @@ -1718,11 +1825,12 @@ aio_poll_queue_proc(struct file *file, struct wait_queue_head *head, struct aio_poll_table *pt = container_of(p, struct aio_poll_table, pt); /* multiple wait queues per file are not supported */ - if (unlikely(pt->iocb->poll.head)) { + if (unlikely(pt->queued)) { pt->error = -EINVAL; return; } + pt->queued = true; pt->error = 0; pt->iocb->poll.head = head; add_wait_queue(head, &pt->iocb->poll.wait); @@ -1747,12 +1855,14 @@ static ssize_t aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb) req->events = demangle_poll(iocb->aio_buf) | EPOLLERR | EPOLLHUP; req->head = NULL; - req->done = false; req->cancelled = false; + req->work_scheduled = false; + req->work_need_resched = false; apt.pt._qproc = aio_poll_queue_proc; apt.pt._key = req->events; apt.iocb = aiocb; + apt.queued = false; apt.error = -EINVAL; /* same as no support for IOCB_CMD_POLL */ /* initialized the list so that we can do list_empty checks */ @@ -1761,23 +1871,35 @@ static ssize_t aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb) mask = vfs_poll(req->file, &apt.pt) & req->events; spin_lock_irq(&ctx->ctx_lock); - if (likely(req->head)) { - spin_lock(&req->head->lock); - if (unlikely(list_empty(&req->wait.entry))) { - if (apt.error) + if (likely(apt.queued)) { + bool on_queue = poll_iocb_lock_wq(req); + + if (!on_queue || req->work_scheduled) { + /* + * aio_poll_wake() already either scheduled the async + * completion work, or completed the request inline. + */ + if (apt.error) /* unsupported case: multiple queues */ cancel = true; apt.error = 0; mask = 0; } if (mask || apt.error) { + /* Steal to complete synchronously. */ list_del_init(&req->wait.entry); } else if (cancel) { + /* Cancel if possible (may be too late though). */ WRITE_ONCE(req->cancelled, true); - } else if (!req->done) { /* actually waiting for an event */ + } else if (on_queue) { + /* + * Actually waiting for an event, so add the request to + * active_reqs so that it can be cancelled if needed. + */ list_add_tail(&aiocb->ki_list, &ctx->active_reqs); aiocb->ki_cancel = aio_poll_cancel; } - spin_unlock(&req->head->lock); + if (on_queue) + poll_iocb_unlock_wq(req); } if (mask) { /* no async, we'd stolen it */ aiocb->ki_res.res = mangle_poll(mask); diff --git a/fs/attr.c b/fs/attr.c index d22e8187477f..f064f08f5194 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -134,6 +134,8 @@ EXPORT_SYMBOL(setattr_prepare); */ int inode_newsize_ok(const struct inode *inode, loff_t offset) { + if (offset < 0) + return -EINVAL; if (inode->i_size < offset) { unsigned long limit; @@ -254,9 +256,25 @@ int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **de } if ((ia_valid & ATTR_MODE)) { - umode_t amode = attr->ia_mode; + /* + * Don't allow changing the mode of symlinks: + * + * (1) The vfs doesn't take the mode of symlinks into account + * during permission checking. + * (2) This has never worked correctly. Most major filesystems + * did return EOPNOTSUPP due to interactions with POSIX ACLs + * but did still updated the mode of the symlink. + * This inconsistency led system call wrapper providers such + * as libc to block changing the mode of symlinks with + * EOPNOTSUPP already. + * (3) To even do this in the first place one would have to use + * specific file descriptors and quite some effort. + */ + if (S_ISLNK(inode->i_mode)) + return -EOPNOTSUPP; + /* Flag setting protected by i_mutex */ - if (is_sxid(amode)) + if (is_sxid(attr->ia_mode)) inode->i_flags &= ~S_NOSEC; } diff --git a/fs/autofs/waitq.c b/fs/autofs/waitq.c index f6385c6ef0a5..44ba0cd4ebc4 100644 --- a/fs/autofs/waitq.c +++ b/fs/autofs/waitq.c @@ -35,8 +35,9 @@ void autofs_catatonic_mode(struct autofs_sb_info *sbi) wq->status = -ENOENT; /* Magic is gone - report failure */ kfree(wq->name.name); wq->name.name = NULL; - wq->wait_ctr--; wake_up_interruptible(&wq->queue); + if (!--wq->wait_ctr) + kfree(wq); wq = nwq; } fput(sbi->pipe); /* Close the pipe */ diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c index c3deb2e35f20..e7a9e8b56e71 100644 --- a/fs/binfmt_aout.c +++ b/fs/binfmt_aout.c @@ -244,6 +244,7 @@ static int load_aout_binary(struct linux_binprm * bprm) set_personality(PER_LINUX); #endif setup_new_exec(bprm); + install_exec_creds(bprm); current->mm->end_code = ex.a_text + (current->mm->start_code = N_TXTADDR(ex)); @@ -256,7 +257,6 @@ static int load_aout_binary(struct linux_binprm * bprm) if (retval < 0) return retval; - install_exec_creds(bprm); if (N_MAGIC(ex) == OMAGIC) { unsigned long text_addr, map_size; diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 975dd0dbc252..c41c568ad1b8 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -580,7 +580,7 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex, elf_prot |= PROT_EXEC; vaddr = eppnt->p_vaddr; if (interp_elf_ex->e_type == ET_EXEC || load_addr_set) - elf_type |= MAP_FIXED_NOREPLACE; + elf_type |= MAP_FIXED; else if (no_base && interp_elf_ex->e_type == ET_DYN) load_addr = -vaddr; diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index b53bb3729ac1..a7c2efcd0a4a 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -349,14 +349,14 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm) /* there's now no turning back... the old userspace image is dead, * defunct, deceased, etc. */ + SET_PERSONALITY(exec_params.hdr); if (elf_check_fdpic(&exec_params.hdr)) - set_personality(PER_LINUX_FDPIC); - else - set_personality(PER_LINUX); + current->personality |= PER_LINUX_FDPIC; if (elf_read_implies_exec(&exec_params.hdr, executable_stack)) current->personality |= READ_IMPLIES_EXEC; setup_new_exec(bprm); + install_exec_creds(bprm); set_binfmt(&elf_fdpic_format); @@ -438,9 +438,9 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm) current->mm->start_stack = current->mm->start_brk + stack_size; #endif - install_exec_creds(bprm); - if (create_elf_fdpic_tables(bprm, current->mm, - &exec_params, &interp_params) < 0) + retval = create_elf_fdpic_tables(bprm, current->mm, &exec_params, + &interp_params); + if (retval < 0) goto error; kdebug("- start_code %lx", current->mm->start_code); diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c index e4b59e76afb0..a909743b1a0e 100644 --- a/fs/binfmt_flat.c +++ b/fs/binfmt_flat.c @@ -408,6 +408,30 @@ static void old_reloc(unsigned long rl) /****************************************************************************/ +static inline u32 __user *skip_got_header(u32 __user *rp) +{ + if (IS_ENABLED(CONFIG_RISCV)) { + /* + * RISC-V has a 16 byte GOT PLT header for elf64-riscv + * and 8 byte GOT PLT header for elf32-riscv. + * Skip the whole GOT PLT header, since it is reserved + * for the dynamic linker (ld.so). + */ + u32 rp_val0, rp_val1; + + if (get_user(rp_val0, rp)) + return rp; + if (get_user(rp_val1, rp + 1)) + return rp; + + if (rp_val0 == 0xffffffff && rp_val1 == 0xffffffff) + rp += 4; + else if (rp_val0 == 0xffffffff) + rp += 2; + } + return rp; +} + static int load_flat_file(struct linux_binprm *bprm, struct lib_info *libinfo, int id, unsigned long *extra_stack) { @@ -517,6 +541,7 @@ static int load_flat_file(struct linux_binprm *bprm, /* OK, This is the point of no return */ set_personality(PER_LINUX_32BIT); setup_new_exec(bprm); + install_exec_creds(bprm); } /* @@ -745,7 +770,8 @@ static int load_flat_file(struct linux_binprm *bprm, * image. */ if (flags & FLAT_FLAG_GOTPIC) { - for (rp = (u32 __user *)datapos; ; rp++) { + rp = skip_got_header((u32 __user *) datapos); + for (; ; rp++) { u32 addr, rp_val; if (get_user(rp_val, rp)) return -EFAULT; @@ -940,8 +966,6 @@ static int load_flat_binary(struct linux_binprm *bprm) } } - install_exec_creds(bprm); - set_binfmt(&flat_format); #ifdef CONFIG_MMU diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index aa4a7a23ff99..8fe7edd2b001 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -42,10 +42,10 @@ static LIST_HEAD(entries); static int enabled = 1; enum {Enabled, Magic}; -#define MISC_FMT_PRESERVE_ARGV0 (1 << 31) -#define MISC_FMT_OPEN_BINARY (1 << 30) -#define MISC_FMT_CREDENTIALS (1 << 29) -#define MISC_FMT_OPEN_FILE (1 << 28) +#define MISC_FMT_PRESERVE_ARGV0 (1UL << 31) +#define MISC_FMT_OPEN_BINARY (1UL << 30) +#define MISC_FMT_CREDENTIALS (1UL << 29) +#define MISC_FMT_OPEN_FILE (1UL << 28) typedef struct { struct list_head list; @@ -694,12 +694,24 @@ static ssize_t bm_register_write(struct file *file, const char __user *buffer, struct super_block *sb = file_inode(file)->i_sb; struct dentry *root = sb->s_root, *dentry; int err = 0; + struct file *f = NULL; e = create_entry(buffer, count); if (IS_ERR(e)) return PTR_ERR(e); + if (e->flags & MISC_FMT_OPEN_FILE) { + f = open_exec(e->interpreter); + if (IS_ERR(f)) { + pr_notice("register: failed to install interpreter file %s\n", + e->interpreter); + kfree(e); + return PTR_ERR(f); + } + e->interp_file = f; + } + inode_lock(d_inode(root)); dentry = lookup_one_len(e->name, root, strlen(e->name)); err = PTR_ERR(dentry); @@ -723,21 +735,6 @@ static ssize_t bm_register_write(struct file *file, const char __user *buffer, goto out2; } - if (e->flags & MISC_FMT_OPEN_FILE) { - struct file *f; - - f = open_exec(e->interpreter); - if (IS_ERR(f)) { - err = PTR_ERR(f); - pr_notice("register: failed to install interpreter file %s\n", e->interpreter); - simple_release_fs(&bm_mnt, &entry_count); - iput(inode); - inode = NULL; - goto out2; - } - e->interp_file = f; - } - e->dentry = dget(dentry); inode->i_private = e; inode->i_fop = &bm_entry_operations; @@ -754,6 +751,8 @@ out: inode_unlock(d_inode(root)); if (err) { + if (f) + filp_close(f, NULL); kfree(e); return err; } diff --git a/fs/block_dev.c b/fs/block_dev.c index 9f3faac49025..5c6ff1572405 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1919,6 +1919,7 @@ ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from) struct inode *bd_inode = bdev_file_inode(file); loff_t size = i_size_read(bd_inode); struct blk_plug plug; + size_t shorted = 0; ssize_t ret; if (bdev_read_only(I_BDEV(bd_inode))) @@ -1933,12 +1934,17 @@ ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from) if ((iocb->ki_flags & (IOCB_NOWAIT | IOCB_DIRECT)) == IOCB_NOWAIT) return -EOPNOTSUPP; - iov_iter_truncate(from, size - iocb->ki_pos); + size -= iocb->ki_pos; + if (iov_iter_count(from) > size) { + shorted = iov_iter_count(from) - size; + iov_iter_truncate(from, size); + } blk_start_plug(&plug); ret = __generic_file_write_iter(iocb, from); if (ret > 0) ret = generic_write_sync(iocb, ret); + iov_iter_reexpand(from, iov_iter_count(from) + shorted); blk_finish_plug(&plug); return ret; } @@ -1950,13 +1956,21 @@ ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to) struct inode *bd_inode = bdev_file_inode(file); loff_t size = i_size_read(bd_inode); loff_t pos = iocb->ki_pos; + size_t shorted = 0; + ssize_t ret; if (pos >= size) return 0; size -= pos; - iov_iter_truncate(to, size); - return generic_file_read_iter(iocb, to); + if (iov_iter_count(to) > size) { + shorted = iov_iter_count(to) - size; + iov_iter_truncate(to, size); + } + + ret = generic_file_read_iter(iocb, to); + iov_iter_reexpand(to, iov_iter_count(to) + shorted); + return ret; } EXPORT_SYMBOL_GPL(blkdev_read_iter); @@ -2027,21 +2041,26 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start, if ((start | len) & (bdev_logical_block_size(bdev) - 1)) return -EINVAL; - /* Invalidate the page cache, including dirty pages. */ + /* + * Invalidate the page cache, including dirty pages, for valid + * de-allocate mode calls to fallocate(). + */ mapping = bdev->bd_inode->i_mapping; - truncate_inode_pages_range(mapping, start, end); switch (mode) { case FALLOC_FL_ZERO_RANGE: case FALLOC_FL_ZERO_RANGE | FALLOC_FL_KEEP_SIZE: + truncate_inode_pages_range(mapping, start, end); error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9, GFP_KERNEL, BLKDEV_ZERO_NOUNMAP); break; case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE: + truncate_inode_pages_range(mapping, start, end); error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9, GFP_KERNEL, BLKDEV_ZERO_NOFALLBACK); break; case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE | FALLOC_FL_NO_HIDE_STALE: + truncate_inode_pages_range(mapping, start, end); error = blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_KERNEL, 0); break; diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig index 23537bc8c827..7233127bb93a 100644 --- a/fs/btrfs/Kconfig +++ b/fs/btrfs/Kconfig @@ -12,6 +12,8 @@ config BTRFS_FS select RAID6_PQ select XOR_BLOCKS select SRCU + depends on !PPC_256K_PAGES # powerpc + depends on !PAGE_SIZE_256KB # hexagon help Btrfs is a general purpose copy-on-write filesystem with extents, diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c index f79c0cb7697a..21f8f475c894 100644 --- a/fs/btrfs/async-thread.c +++ b/fs/btrfs/async-thread.c @@ -270,6 +270,13 @@ static void run_ordered_work(struct __btrfs_workqueue *wq, ordered_list); if (!test_bit(WORK_DONE_BIT, &work->flags)) break; + /* + * Orders all subsequent loads after reading WORK_DONE_BIT, + * paired with the smp_mb__before_atomic in btrfs_work_helper + * this guarantees that the ordered function will see all + * updates from ordinary work function. + */ + smp_rmb(); /* * we are going to call the ordered done function, but @@ -355,6 +362,13 @@ static void normal_work_helper(struct btrfs_work *work) thresh_exec_hook(wq); work->func(work); if (need_order) { + /* + * Ensures all memory accesses done in the work function are + * ordered before setting the WORK_DONE_BIT. Ensuring the thread + * which is going to executed the ordered work sees them. + * Pairs with the smp_rmb in run_ordered_work. + */ + smp_mb__before_atomic(); set_bit(WORK_DONE_BIT, &work->flags); run_ordered_work(wq, work); } diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 6b8824de2abb..a1eb573fbb10 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -136,6 +136,7 @@ struct share_check { u64 root_objectid; u64 inum; int share_count; + bool have_delayed_delete_refs; }; static inline int extent_is_shared(struct share_check *sc) @@ -588,6 +589,18 @@ unode_aux_to_inode_list(struct ulist_node *node) return (struct extent_inode_elem *)(uintptr_t)node->aux; } +static void free_leaf_list(struct ulist *ulist) +{ + struct ulist_node *node; + struct ulist_iterator uiter; + + ULIST_ITER_INIT(&uiter); + while ((node = ulist_next(ulist, &uiter))) + free_inode_elem_list(unode_aux_to_inode_list(node)); + + ulist_free(ulist); +} + /* * We maintain three seperate rbtrees: one for direct refs, one for * indirect refs which have a key, and one for indirect refs which do not @@ -702,7 +715,11 @@ static int resolve_indirect_refs(struct btrfs_fs_info *fs_info, cond_resched(); } out: - ulist_free(parents); + /* + * We may have inode lists attached to refs in the parents ulist, so we + * must free them before freeing the ulist and its refs. + */ + free_leaf_list(parents); return ret; } @@ -760,16 +777,11 @@ static int add_delayed_refs(const struct btrfs_fs_info *fs_info, struct share_check *sc) { struct btrfs_delayed_ref_node *node; - struct btrfs_delayed_extent_op *extent_op = head->extent_op; struct btrfs_key key; - struct btrfs_key tmp_op_key; struct rb_node *n; int count; int ret = 0; - if (extent_op && extent_op->update_key) - btrfs_disk_key_to_cpu(&tmp_op_key, &extent_op->key); - spin_lock(&head->lock); for (n = rb_first(&head->ref_tree); n; n = rb_next(n)) { node = rb_entry(n, struct btrfs_delayed_ref_node, @@ -796,10 +808,16 @@ static int add_delayed_refs(const struct btrfs_fs_info *fs_info, case BTRFS_TREE_BLOCK_REF_KEY: { /* NORMAL INDIRECT METADATA backref */ struct btrfs_delayed_tree_ref *ref; + struct btrfs_key *key_ptr = NULL; + + if (head->extent_op && head->extent_op->update_key) { + btrfs_disk_key_to_cpu(&key, &head->extent_op->key); + key_ptr = &key; + } ref = btrfs_delayed_node_to_tree_ref(node); ret = add_indirect_ref(fs_info, preftrees, ref->root, - &tmp_op_key, ref->level + 1, + key_ptr, ref->level + 1, node->bytenr, count, sc, GFP_ATOMIC); break; @@ -825,13 +843,22 @@ static int add_delayed_refs(const struct btrfs_fs_info *fs_info, key.offset = ref->offset; /* - * Found a inum that doesn't match our known inum, we - * know it's shared. + * If we have a share check context and a reference for + * another inode, we can't exit immediately. This is + * because even if this is a BTRFS_ADD_DELAYED_REF + * reference we may find next a BTRFS_DROP_DELAYED_REF + * which cancels out this ADD reference. + * + * If this is a DROP reference and there was no previous + * ADD reference, then we need to signal that when we + * process references from the extent tree (through + * add_inline_refs() and add_keyed_refs()), we should + * not exit early if we find a reference for another + * inode, because one of the delayed DROP references + * may cancel that reference in the extent tree. */ - if (sc && sc->inum && ref->objectid != sc->inum) { - ret = BACKREF_FOUND_SHARED; - goto out; - } + if (sc && count < 0) + sc->have_delayed_delete_refs = true; ret = add_indirect_ref(fs_info, preftrees, ref->root, &key, 0, node->bytenr, count, sc, @@ -861,7 +888,7 @@ static int add_delayed_refs(const struct btrfs_fs_info *fs_info, } if (!ret) ret = extent_is_shared(sc); -out: + spin_unlock(&head->lock); return ret; } @@ -965,7 +992,8 @@ static int add_inline_refs(const struct btrfs_fs_info *fs_info, key.type = BTRFS_EXTENT_DATA_KEY; key.offset = btrfs_extent_data_ref_offset(leaf, dref); - if (sc && sc->inum && key.objectid != sc->inum) { + if (sc && sc->inum && key.objectid != sc->inum && + !sc->have_delayed_delete_refs) { ret = BACKREF_FOUND_SHARED; break; } @@ -975,6 +1003,7 @@ static int add_inline_refs(const struct btrfs_fs_info *fs_info, ret = add_indirect_ref(fs_info, preftrees, root, &key, 0, bytenr, count, sc, GFP_NOFS); + break; } default: @@ -1064,7 +1093,8 @@ static int add_keyed_refs(struct btrfs_fs_info *fs_info, key.type = BTRFS_EXTENT_DATA_KEY; key.offset = btrfs_extent_data_ref_offset(leaf, dref); - if (sc && sc->inum && key.objectid != sc->inum) { + if (sc && sc->inum && key.objectid != sc->inum && + !sc->have_delayed_delete_refs) { ret = BACKREF_FOUND_SHARED; break; } @@ -1160,7 +1190,12 @@ again: ret = btrfs_search_slot(trans, fs_info->extent_root, &key, path, 0, 0); if (ret < 0) goto out; - BUG_ON(ret == 0); + if (ret == 0) { + /* This shouldn't happen, indicates a bug or fs corruption. */ + ASSERT(ret != 0); + ret = -EUCLEAN; + goto out; + } #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS if (trans && likely(trans->type != __TRANS_DUMMY) && @@ -1308,10 +1343,18 @@ again: goto out; if (!ret && extent_item_pos) { /* - * we've recorded that parent, so we must extend - * its inode list here + * We've recorded that parent, so we must extend + * its inode list here. + * + * However if there was corruption we may not + * have found an eie, return an error in this + * case. */ - BUG_ON(!eie); + ASSERT(eie); + if (!eie) { + ret = -EUCLEAN; + goto out; + } while (eie->next) eie = eie->next; eie->next = ref->inode_list; @@ -1333,24 +1376,6 @@ out: return ret; } -static void free_leaf_list(struct ulist *blocks) -{ - struct ulist_node *node = NULL; - struct extent_inode_elem *eie; - struct ulist_iterator uiter; - - ULIST_ITER_INIT(&uiter); - while ((node = ulist_next(blocks, &uiter))) { - if (!node->aux) - continue; - eie = unode_aux_to_inode_list(node); - free_inode_elem_list(eie); - node->aux = 0; - } - - ulist_free(blocks); -} - /* * Finds all leafs with a reference to the specified combination of bytenr and * offset. key_list_head will point to a list of corresponding keys (caller must @@ -1477,6 +1502,7 @@ int btrfs_check_shared(struct btrfs_root *root, u64 inum, u64 bytenr) .root_objectid = root->objectid, .inum = inum, .share_count = 0, + .have_delayed_delete_refs = false, }; tmp = ulist_alloc(GFP_NOFS); @@ -1515,6 +1541,7 @@ int btrfs_check_shared(struct btrfs_root *root, u64 inum, u64 bytenr) break; bytenr = node->val; shared.share_count = 0; + shared.have_delayed_delete_refs = false; cond_resched(); } diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index c71e534ca7ef..919c033b9e31 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -270,8 +270,7 @@ static void end_compressed_bio_write(struct bio *bio) cb->start, cb->start + cb->len - 1, NULL, - bio->bi_status ? - BLK_STS_OK : BLK_STS_NOTSUPP); + !cb->errors); cb->compressed_pages[0]->mapping = NULL; end_compressed_writeback(inode, cb); diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 8007b6aacec6..e48c6d7a860f 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -267,9 +267,12 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans, ret = btrfs_inc_ref(trans, root, cow, 1); else ret = btrfs_inc_ref(trans, root, cow, 0); - - if (ret) + if (ret) { + btrfs_tree_unlock(cow); + free_extent_buffer(cow); + btrfs_abort_transaction(trans, ret); return ret; + } btrfs_mark_buffer_dirty(cow); *cow_ret = cow; @@ -1110,6 +1113,8 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, ret = update_ref_for_cow(trans, root, buf, cow, &last_ref); if (ret) { + btrfs_tree_unlock(cow); + free_extent_buffer(cow); btrfs_abort_transaction(trans, ret); return ret; } @@ -1117,6 +1122,8 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, if (test_bit(BTRFS_ROOT_REF_COWS, &root->state)) { ret = btrfs_reloc_cow_block(trans, root, buf, cow); if (ret) { + btrfs_tree_unlock(cow); + free_extent_buffer(cow); btrfs_abort_transaction(trans, ret); return ret; } @@ -1149,6 +1156,8 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, if (last_ref) { ret = tree_mod_log_free_eb(buf); if (ret) { + btrfs_tree_unlock(cow); + free_extent_buffer(cow); btrfs_abort_transaction(trans, ret); return ret; } @@ -1405,8 +1414,30 @@ get_old_root(struct btrfs_root *root, u64 time_seq) "failed to read tree block %llu from get_old_root", logical); } else { + struct tree_mod_elem *tm2; + + btrfs_tree_read_lock(old); eb = btrfs_clone_extent_buffer(old); + /* + * After the lookup for the most recent tree mod operation + * above and before we locked and cloned the extent buffer + * 'old', a new tree mod log operation may have been added. + * So lookup for a more recent one to make sure the number + * of mod log operations we replay is consistent with the + * number of items we have in the cloned extent buffer, + * otherwise we can hit a BUG_ON when rewinding the extent + * buffer. + */ + tm2 = tree_mod_log_search(fs_info, logical, time_seq); + btrfs_tree_read_unlock(old); free_extent_buffer(old); + ASSERT(tm2); + ASSERT(tm2 == tm || tm2->seq > tm->seq); + if (!tm2 || tm2->seq < tm->seq) { + free_extent_buffer(eb); + return NULL; + } + tm = tm2; } } else if (old_root) { eb_root_owner = btrfs_header_owner(eb_root); @@ -3559,6 +3590,8 @@ static noinline int split_node(struct btrfs_trans_handle *trans, ret = tree_mod_log_eb_copy(fs_info, split, c, 0, mid, c_nritems - mid); if (ret) { + btrfs_tree_unlock(split); + free_extent_buffer(split); btrfs_abort_transaction(trans, ret); return ret; } @@ -5120,10 +5153,12 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path) { struct btrfs_key key; + struct btrfs_key orig_key; struct btrfs_disk_key found_key; int ret; btrfs_item_key_to_cpu(path->nodes[0], &key, 0); + orig_key = key; if (key.offset > 0) { key.offset--; @@ -5140,8 +5175,36 @@ int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path) btrfs_release_path(path); ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); - if (ret < 0) + if (ret <= 0) return ret; + + /* + * Previous key not found. Even if we were at slot 0 of the leaf we had + * before releasing the path and calling btrfs_search_slot(), we now may + * be in a slot pointing to the same original key - this can happen if + * after we released the path, one of more items were moved from a + * sibling leaf into the front of the leaf we had due to an insertion + * (see push_leaf_right()). + * If we hit this case and our slot is > 0 and just decrement the slot + * so that the caller does not process the same key again, which may or + * may not break the caller, depending on its logic. + */ + if (path->slots[0] < btrfs_header_nritems(path->nodes[0])) { + btrfs_item_key(path->nodes[0], &found_key, path->slots[0]); + ret = comp_keys(&found_key, &orig_key); + if (ret == 0) { + if (path->slots[0] > 0) { + path->slots[0]--; + return 0; + } + /* + * At slot 0, same key as before, it means orig_key is + * the lowest, leftmost, key in the tree. We're done. + */ + return 1; + } + } + btrfs_item_key(path->nodes[0], &found_key, 0); ret = comp_keys(&found_key, &key); /* diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 554727d82d43..4d1c12faada8 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1459,6 +1459,21 @@ do { \ #define BTRFS_INODE_ROOT_ITEM_INIT (1 << 31) +#define BTRFS_INODE_FLAG_MASK \ + (BTRFS_INODE_NODATASUM | \ + BTRFS_INODE_NODATACOW | \ + BTRFS_INODE_READONLY | \ + BTRFS_INODE_NOCOMPRESS | \ + BTRFS_INODE_PREALLOC | \ + BTRFS_INODE_SYNC | \ + BTRFS_INODE_IMMUTABLE | \ + BTRFS_INODE_APPEND | \ + BTRFS_INODE_NODUMP | \ + BTRFS_INODE_NOATIME | \ + BTRFS_INODE_DIRSYNC | \ + BTRFS_INODE_COMPRESS | \ + BTRFS_INODE_ROOT_ITEM_INIT) + struct btrfs_map_token { const struct extent_buffer *eb; char *kaddr; diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 7374fb23381c..469a90b07d3f 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -620,8 +620,7 @@ static int btrfs_delayed_inode_reserve_metadata( */ if (!src_rsv || (!trans->bytes_reserved && src_rsv->type != BTRFS_BLOCK_RSV_DELALLOC)) { - ret = btrfs_qgroup_reserve_meta_prealloc(root, - fs_info->nodesize, true); + ret = btrfs_qgroup_reserve_meta_prealloc(root, num_bytes, true); if (ret < 0) return ret; ret = btrfs_block_rsv_add(root, dst_rsv, num_bytes, @@ -643,7 +642,7 @@ static int btrfs_delayed_inode_reserve_metadata( btrfs_ino(inode), num_bytes, 1); } else { - btrfs_qgroup_free_meta_prealloc(root, fs_info->nodesize); + btrfs_qgroup_free_meta_prealloc(root, num_bytes); } return ret; } @@ -1031,12 +1030,10 @@ static int __btrfs_update_delayed_inode(struct btrfs_trans_handle *trans, nofs_flag = memalloc_nofs_save(); ret = btrfs_lookup_inode(trans, root, path, &key, mod); memalloc_nofs_restore(nofs_flag); - if (ret > 0) { - btrfs_release_path(path); - return -ENOENT; - } else if (ret < 0) { - return ret; - } + if (ret > 0) + ret = -ENOENT; + if (ret < 0) + goto out; leaf = path->nodes[0]; inode_item = btrfs_item_ptr(leaf, path->slots[0], @@ -1074,6 +1071,14 @@ err_out: btrfs_delayed_inode_release_metadata(fs_info, node, (ret < 0)); btrfs_release_delayed_inode(node); + /* + * If we fail to update the delayed inode we need to abort the + * transaction, because we could leave the inode with the improper + * counts behind. + */ + if (ret && ret != -ENOENT) + btrfs_abort_transaction(trans, ret); + return ret; search: @@ -1166,20 +1171,33 @@ static int __btrfs_run_delayed_items(struct btrfs_trans_handle *trans, int nr) ret = __btrfs_commit_inode_delayed_items(trans, path, curr_node); if (ret) { - btrfs_release_delayed_node(curr_node); - curr_node = NULL; btrfs_abort_transaction(trans, ret); break; } prev_node = curr_node; curr_node = btrfs_next_delayed_node(curr_node); + /* + * See the comment below about releasing path before releasing + * node. If the commit of delayed items was successful the path + * should always be released, but in case of an error, it may + * point to locked extent buffers (a leaf at the very least). + */ + ASSERT(path->nodes[0] == NULL); btrfs_release_delayed_node(prev_node); } + /* + * Release the path to avoid a potential deadlock and lockdep splat when + * releasing the delayed node, as that requires taking the delayed node's + * mutex. If another task starts running delayed items before we take + * the mutex, it will first lock the mutex and then it may try to lock + * the same btree path (leaf). + */ + btrfs_free_path(path); + if (curr_node) btrfs_release_delayed_node(curr_node); - btrfs_free_path(path); trans->block_rsv = block_rsv; return ret; diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index 1b9c8ffb038f..4d1d2657d70c 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -54,6 +54,17 @@ int btrfs_init_dev_replace(struct btrfs_fs_info *fs_info) ret = btrfs_search_slot(NULL, dev_root, &key, path, 0, 0); if (ret) { no_valid_dev_replace_entry_found: + /* + * We don't have a replace item or it's corrupted. If there is + * a replace target, fail the mount. + */ + if (btrfs_find_device(fs_info->fs_devices, + BTRFS_DEV_REPLACE_DEVID, NULL, NULL, false)) { + btrfs_err(fs_info, + "found replace target device without a valid replace item"); + ret = -EUCLEAN; + goto out; + } ret = 0; dev_replace->replace_state = BTRFS_DEV_REPLACE_ITEM_STATE_NEVER_STARTED; @@ -107,8 +118,19 @@ no_valid_dev_replace_entry_found: case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED: case BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED: case BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED: - dev_replace->srcdev = NULL; - dev_replace->tgtdev = NULL; + /* + * We don't have an active replace item but if there is a + * replace target, fail the mount. + */ + if (btrfs_find_device(fs_info->fs_devices, + BTRFS_DEV_REPLACE_DEVID, NULL, NULL, false)) { + btrfs_err(fs_info, + "replace devid present without an active replace item"); + ret = -EUCLEAN; + } else { + dev_replace->srcdev = NULL; + dev_replace->tgtdev = NULL; + } break; case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED: case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED: @@ -190,7 +212,7 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info, int ret = 0; *device_out = NULL; - if (fs_info->fs_devices->seeding) { + if (srcdev->fs_devices->seeding) { btrfs_err(fs_info, "the filesystem is a seed filesystem!"); return -EINVAL; } diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index cb21ffd3bba7..437ca4691967 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2855,7 +2855,7 @@ int open_ctree(struct super_block *sb, ~BTRFS_FEATURE_INCOMPAT_SUPP; if (features) { btrfs_err(fs_info, - "cannot mount because of unsupported optional features (%llx)", + "cannot mount because of unsupported optional features (0x%llx)", features); err = -EINVAL; goto fail_alloc; @@ -2915,11 +2915,25 @@ int open_ctree(struct super_block *sb, ~BTRFS_FEATURE_COMPAT_RO_SUPP; if (!sb_rdonly(sb) && features) { btrfs_err(fs_info, - "cannot mount read-write because of unsupported optional features (%llx)", + "cannot mount read-write because of unsupported optional features (0x%llx)", features); err = -EINVAL; goto fail_alloc; } + /* + * We have unsupported RO compat features, although RO mounted, we + * should not cause any metadata write, including log replay. + * Or we could screw up whatever the new feature requires. + */ + if (unlikely(features && btrfs_super_log_root(disk_super) && + !btrfs_test_opt(fs_info, NOLOGREPLAY))) { + btrfs_err(fs_info, +"cannot replay dirty log with unsupported compat_ro features (0x%llx), try rescue=nologreplay", + features); + err = -EINVAL; + goto fail_alloc; + } + ret = btrfs_init_workqueues(fs_info, fs_devices); if (ret) { @@ -3095,7 +3109,8 @@ retry_root_backup: goto fail_sysfs; } - if (!sb_rdonly(sb) && !btrfs_check_rw_degradable(fs_info, NULL)) { + if (!sb_rdonly(sb) && fs_info->fs_devices->missing_devices && + !btrfs_check_rw_degradable(fs_info, NULL)) { btrfs_warn(fs_info, "writeable mount is not allowed due to too many missing devices"); goto fail_sysfs; @@ -3578,11 +3593,23 @@ static void btrfs_end_empty_barrier(struct bio *bio) */ static void write_dev_flush(struct btrfs_device *device) { - struct request_queue *q = bdev_get_queue(device->bdev); struct bio *bio = device->flush_bio; +#ifndef CONFIG_BTRFS_FS_CHECK_INTEGRITY + /* + * When a disk has write caching disabled, we skip submission of a bio + * with flush and sync requests before writing the superblock, since + * it's not needed. However when the integrity checker is enabled, this + * results in reports that there are metadata blocks referred by a + * superblock that were not properly flushed. So don't skip the bio + * submission only when the integrity checker is enabled for the sake + * of simplicity, since this is a debug tool and not meant for use in + * non-debug builds. + */ + struct request_queue *q = bdev_get_queue(device->bdev); if (!test_bit(QUEUE_FLAG_WC, &q->queue_flags)) return; +#endif bio_reset(bio); bio->bi_end_io = btrfs_end_empty_barrier; @@ -4321,7 +4348,11 @@ static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root) */ inode = igrab(&btrfs_inode->vfs_inode); if (inode) { + unsigned int nofs_flag; + + nofs_flag = memalloc_nofs_save(); invalidate_inode_pages2(inode->i_mapping); + memalloc_nofs_restore(nofs_flag); iput(inode); } spin_lock(&root->delalloc_lock); @@ -4439,7 +4470,12 @@ static void btrfs_cleanup_bg_io(struct btrfs_block_group_cache *cache) inode = cache->io_ctl.inode; if (inode) { + unsigned int nofs_flag; + + nofs_flag = memalloc_nofs_save(); invalidate_inode_pages2(inode->i_mapping); + memalloc_nofs_restore(nofs_flag); + BTRFS_I(inode)->generation = 0; cache->io_ctl.inode = NULL; iput(inode); diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c index 665ec85cb09b..ecc33e3a3c06 100644 --- a/fs/btrfs/export.c +++ b/fs/btrfs/export.c @@ -58,7 +58,7 @@ static int btrfs_encode_fh(struct inode *inode, u32 *fh, int *max_len, } struct dentry *btrfs_get_dentry(struct super_block *sb, u64 objectid, - u64 root_objectid, u32 generation, + u64 root_objectid, u64 generation, int check_generation) { struct btrfs_fs_info *fs_info = btrfs_sb(sb); diff --git a/fs/btrfs/export.h b/fs/btrfs/export.h index f32f4113c976..5afb7ca42828 100644 --- a/fs/btrfs/export.h +++ b/fs/btrfs/export.h @@ -19,7 +19,7 @@ struct btrfs_fid { } __attribute__ ((packed)); struct dentry *btrfs_get_dentry(struct super_block *sb, u64 objectid, - u64 root_objectid, u32 generation, + u64 root_objectid, u64 generation, int check_generation); struct dentry *btrfs_get_parent(struct dentry *child); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index ce5e0f6c6af4..902ab00bfd7a 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -1549,6 +1549,11 @@ again: err = -ENOENT; goto out; } else if (WARN_ON(ret)) { + btrfs_print_leaf(path->nodes[0]); + btrfs_err(fs_info, +"extent item not found for insert, bytenr %llu num_bytes %llu parent %llu root_objectid %llu owner %llu offset %llu", + bytenr, num_bytes, parent, root_objectid, owner, + offset); err = -EIO; goto out; } @@ -1984,16 +1989,20 @@ int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr, for (i = 0; i < bbio->num_stripes; i++, stripe++) { u64 bytes; struct request_queue *req_q; + struct btrfs_device *device = stripe->dev; - if (!stripe->dev->bdev) { + if (!device->bdev) { ASSERT(btrfs_test_opt(fs_info, DEGRADED)); continue; } - req_q = bdev_get_queue(stripe->dev->bdev); + req_q = bdev_get_queue(device->bdev); if (!blk_queue_discard(req_q)) continue; - ret = btrfs_issue_discard(stripe->dev->bdev, + if (!test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) + continue; + + ret = btrfs_issue_discard(device->bdev, stripe->physical, stripe->length, &bytes); @@ -2318,12 +2327,12 @@ static int run_delayed_tree_ref(struct btrfs_trans_handle *trans, parent = ref->parent; ref_root = ref->root; - if (node->ref_mod != 1) { + if (unlikely(node->ref_mod != 1)) { btrfs_err(trans->fs_info, - "btree block(%llu) has %d references rather than 1: action %d ref_root %llu parent %llu", + "btree block %llu has %d references rather than 1: action %d ref_root %llu parent %llu", node->bytenr, node->ref_mod, node->action, ref_root, parent); - return -EIO; + return -EUCLEAN; } if (node->action == BTRFS_ADD_DELAYED_REF && insert_reserved) { BUG_ON(!extent_op || !extent_op->update_flags); @@ -2501,7 +2510,7 @@ static int cleanup_ref_head(struct btrfs_trans_handle *trans, head->qgroup_reserved); btrfs_delayed_ref_unlock(head); btrfs_put_delayed_ref_head(head); - return 0; + return ret; } /* @@ -8323,6 +8332,7 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans, out_free_delayed: btrfs_free_delayed_extent_op(extent_op); out_free_buf: + btrfs_tree_unlock(buf); free_extent_buffer(buf); out_free_reserved: btrfs_free_reserved_extent(fs_info, ins.objectid, ins.offset, 0); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 82d597b16152..504d63fb81fa 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -138,7 +138,61 @@ static int add_extent_changeset(struct extent_state *state, unsigned bits, return ret; } -static void flush_write_bio(struct extent_page_data *epd); +static int __must_check submit_one_bio(struct bio *bio, int mirror_num, + unsigned long bio_flags) +{ + blk_status_t ret = 0; + struct bio_vec *bvec = bio_last_bvec_all(bio); + struct page *page = bvec->bv_page; + struct extent_io_tree *tree = bio->bi_private; + u64 start; + + start = page_offset(page) + bvec->bv_offset; + + bio->bi_private = NULL; + + if (tree->ops) + ret = tree->ops->submit_bio_hook(tree->private_data, bio, + mirror_num, bio_flags, start); + else + btrfsic_submit_bio(bio); + + return blk_status_to_errno(ret); +} + +/* Cleanup unsubmitted bios */ +static void end_write_bio(struct extent_page_data *epd, int ret) +{ + if (epd->bio) { + epd->bio->bi_status = errno_to_blk_status(ret); + bio_endio(epd->bio); + epd->bio = NULL; + } +} + +/* + * Submit bio from extent page data via submit_one_bio + * + * Return 0 if everything is OK. + * Return <0 for error. + */ +static int __must_check flush_write_bio(struct extent_page_data *epd) +{ + int ret = 0; + + if (epd->bio) { + ret = submit_one_bio(epd->bio, 0, 0); + /* + * Clean up of epd->bio is handled by its endio function. + * And endio is either triggered by successful bio execution + * or the error handler of submit bio hook. + * So at this point, no matter what happened, we don't need + * to clean up epd->bio. + */ + epd->bio = NULL; + } + return ret; +} int __init extent_io_init(void) { @@ -2710,28 +2764,6 @@ struct bio *btrfs_bio_clone_partial(struct bio *orig, int offset, int size) return bio; } -static int __must_check submit_one_bio(struct bio *bio, int mirror_num, - unsigned long bio_flags) -{ - blk_status_t ret = 0; - struct bio_vec *bvec = bio_last_bvec_all(bio); - struct page *page = bvec->bv_page; - struct extent_io_tree *tree = bio->bi_private; - u64 start; - - start = page_offset(page) + bvec->bv_offset; - - bio->bi_private = NULL; - - if (tree->ops) - ret = tree->ops->submit_bio_hook(tree->private_data, bio, - mirror_num, bio_flags, start); - else - btrfsic_submit_bio(bio); - - return blk_status_to_errno(ret); -} - /* * @opf: bio REQ_OP_* and REQ_* flags as one value * @tree: tree so we can call our merge_bio hook @@ -3439,6 +3471,9 @@ done: * records are inserted to lock ranges in the tree, and as dirty areas * are found, they are marked writeback. Then the lock bits are removed * and the end_io handler clears the writeback ranges + * + * Return 0 if everything goes well. + * Return <0 for error. */ static int __extent_writepage(struct page *page, struct writeback_control *wbc, struct extent_page_data *epd) @@ -3506,6 +3541,7 @@ done: end_extent_writepage(page, ret, start, page_end); } unlock_page(page); + ASSERT(ret <= 0); return ret; done_unlocked: @@ -3518,18 +3554,34 @@ void wait_on_extent_buffer_writeback(struct extent_buffer *eb) TASK_UNINTERRUPTIBLE); } +static void end_extent_buffer_writeback(struct extent_buffer *eb) +{ + clear_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags); + smp_mb__after_atomic(); + wake_up_bit(&eb->bflags, EXTENT_BUFFER_WRITEBACK); +} + +/* + * Lock eb pages and flush the bio if we can't the locks + * + * Return 0 if nothing went wrong + * Return >0 is same as 0, except bio is not submitted + * Return <0 if something went wrong, no page is locked + */ static noinline_for_stack int lock_extent_buffer_for_io(struct extent_buffer *eb, struct btrfs_fs_info *fs_info, struct extent_page_data *epd) { - int i, num_pages; + int i, num_pages, failed_page_nr; int flush = 0; int ret = 0; if (!btrfs_try_tree_write_lock(eb)) { + ret = flush_write_bio(epd); + if (ret < 0) + return ret; flush = 1; - flush_write_bio(epd); btrfs_tree_lock(eb); } @@ -3538,7 +3590,9 @@ lock_extent_buffer_for_io(struct extent_buffer *eb, if (!epd->sync_io) return 0; if (!flush) { - flush_write_bio(epd); + ret = flush_write_bio(epd); + if (ret < 0) + return ret; flush = 1; } while (1) { @@ -3579,7 +3633,14 @@ lock_extent_buffer_for_io(struct extent_buffer *eb, if (!trylock_page(p)) { if (!flush) { - flush_write_bio(epd); + int err; + + err = flush_write_bio(epd); + if (err < 0) { + ret = err; + failed_page_nr = i; + goto err_unlock; + } flush = 1; } lock_page(p); @@ -3587,13 +3648,25 @@ lock_extent_buffer_for_io(struct extent_buffer *eb, } return ret; -} - -static void end_extent_buffer_writeback(struct extent_buffer *eb) -{ - clear_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags); - smp_mb__after_atomic(); - wake_up_bit(&eb->bflags, EXTENT_BUFFER_WRITEBACK); +err_unlock: + /* Unlock already locked pages */ + for (i = 0; i < failed_page_nr; i++) + unlock_page(eb->pages[i]); + /* + * Clear EXTENT_BUFFER_WRITEBACK and wake up anyone waiting on it. + * Also set back EXTENT_BUFFER_DIRTY so future attempts to this eb can + * be made and undo everything done before. + */ + btrfs_tree_lock(eb); + spin_lock(&eb->refs_lock); + set_bit(EXTENT_BUFFER_DIRTY, &eb->bflags); + end_extent_buffer_writeback(eb); + spin_unlock(&eb->refs_lock); + percpu_counter_add_batch(&fs_info->dirty_metadata_bytes, eb->len, + fs_info->dirty_metadata_batch); + btrfs_clear_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN); + btrfs_tree_unlock(eb); + return ret; } static void set_btree_ioerr(struct page *page) @@ -3840,6 +3913,10 @@ retry: if (!ret) { free_extent_buffer(eb); continue; + } else if (ret < 0) { + done = 1; + free_extent_buffer(eb); + break; } ret = write_one_eb(eb, fs_info, wbc, &epd); @@ -3851,11 +3928,12 @@ retry: free_extent_buffer(eb); /* - * the filesystem may choose to bump up nr_to_write. + * The filesystem may choose to bump up nr_to_write. * We have to make sure to honor the new nr_to_write - * at any time + * at any time. */ - nr_to_write_done = wbc->nr_to_write <= 0; + nr_to_write_done = (wbc->sync_mode == WB_SYNC_NONE && + wbc->nr_to_write <= 0); } pagevec_release(&pvec); cond_resched(); @@ -3869,7 +3947,44 @@ retry: index = 0; goto retry; } - flush_write_bio(&epd); + ASSERT(ret <= 0); + if (ret < 0) { + end_write_bio(&epd, ret); + return ret; + } + /* + * If something went wrong, don't allow any metadata write bio to be + * submitted. + * + * This would prevent use-after-free if we had dirty pages not + * cleaned up, which can still happen by fuzzed images. + * + * - Bad extent tree + * Allowing existing tree block to be allocated for other trees. + * + * - Log tree operations + * Exiting tree blocks get allocated to log tree, bumps its + * generation, then get cleaned in tree re-balance. + * Such tree block will not be written back, since it's clean, + * thus no WRITTEN flag set. + * And after log writes back, this tree block is not traced by + * any dirty extent_io_tree. + * + * - Offending tree block gets re-dirtied from its original owner + * Since it has bumped generation, no WRITTEN flag, it can be + * reused without COWing. This tree block will not be traced + * by btrfs_transaction::dirty_pages. + * + * Now such dirty tree block will not be cleaned by any dirty + * extent io tree. Thus we don't want to submit such wild eb + * if the fs already has error. + */ + if (!test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) { + ret = flush_write_bio(&epd); + } else { + ret = -EUCLEAN; + end_write_bio(&epd, ret); + } return ret; } @@ -3966,7 +4081,8 @@ retry: * tmpfs file mapping */ if (!trylock_page(page)) { - flush_write_bio(epd); + ret = flush_write_bio(epd); + BUG_ON(ret < 0); lock_page(page); } @@ -3976,8 +4092,10 @@ retry: } if (wbc->sync_mode != WB_SYNC_NONE) { - if (PageWriteback(page)) - flush_write_bio(epd); + if (PageWriteback(page)) { + ret = flush_write_bio(epd); + BUG_ON(ret < 0); + } wait_on_page_writeback(page); } @@ -4022,8 +4140,9 @@ retry: * page in our current bio, and thus deadlock, so flush the * write bio here. */ - flush_write_bio(epd); - goto retry; + ret = flush_write_bio(epd); + if (!ret) + goto retry; } if (wbc->range_cyclic || (wbc->nr_to_write > 0 && range_whole)) @@ -4033,17 +4152,6 @@ retry: return ret; } -static void flush_write_bio(struct extent_page_data *epd) -{ - if (epd->bio) { - int ret; - - ret = submit_one_bio(epd->bio, 0, 0); - BUG_ON(ret < 0); /* -ENOMEM */ - epd->bio = NULL; - } -} - int extent_write_full_page(struct page *page, struct writeback_control *wbc) { int ret; @@ -4055,8 +4163,14 @@ int extent_write_full_page(struct page *page, struct writeback_control *wbc) }; ret = __extent_writepage(page, wbc, &epd); + ASSERT(ret <= 0); + if (ret < 0) { + end_write_bio(&epd, ret); + return ret; + } - flush_write_bio(&epd); + ret = flush_write_bio(&epd); + ASSERT(ret <= 0); return ret; } @@ -4064,6 +4178,7 @@ int extent_write_locked_range(struct inode *inode, u64 start, u64 end, int mode) { int ret = 0; + int flush_ret; struct address_space *mapping = inode->i_mapping; struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree; struct page *page; @@ -4098,7 +4213,8 @@ int extent_write_locked_range(struct inode *inode, u64 start, u64 end, start += PAGE_SIZE; } - flush_write_bio(&epd); + flush_ret = flush_write_bio(&epd); + BUG_ON(flush_ret < 0); return ret; } @@ -4106,6 +4222,7 @@ int extent_writepages(struct address_space *mapping, struct writeback_control *wbc) { int ret = 0; + int flush_ret; struct extent_page_data epd = { .bio = NULL, .tree = &BTRFS_I(mapping->host)->io_tree, @@ -4114,7 +4231,8 @@ int extent_writepages(struct address_space *mapping, }; ret = extent_write_cache_pages(mapping, wbc, &epd); - flush_write_bio(&epd); + flush_ret = flush_write_bio(&epd); + BUG_ON(flush_ret < 0); return ret; } diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index d5089cadd7c4..35a21a602e3a 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -197,7 +197,7 @@ struct extent_buffer { */ struct extent_changeset { /* How many bytes are set/cleared in this operation */ - unsigned int bytes_changed; + u64 bytes_changed; /* Changed ranges */ struct ulist range_changed; diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index 1b8a04b767ff..40db31b69ef7 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -586,7 +586,7 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans, u64 end_byte = bytenr + len; u64 csum_end; struct extent_buffer *leaf; - int ret; + int ret = 0; u16 csum_size = btrfs_super_csum_size(fs_info->super_copy); int blocksize_bits = fs_info->sb->s_blocksize_bits; @@ -605,6 +605,7 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans, path->leave_spinning = 1; ret = btrfs_search_slot(trans, root, &key, path, -1, 1); if (ret > 0) { + ret = 0; if (path->slots[0] == 0) break; path->slots[0]--; @@ -661,7 +662,7 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans, ret = btrfs_del_items(trans, root, path, path->slots[0], del_nr); if (ret) - goto out; + break; if (key.offset == bytenr) break; } else if (key.offset < bytenr && csum_end > end_byte) { @@ -705,8 +706,9 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans, ret = btrfs_split_item(trans, root, path, &key, offset); if (ret && ret != -EAGAIN) { btrfs_abort_transaction(trans, ret); - goto out; + break; } + ret = 0; key.offset = end_byte - 1; } else { @@ -716,8 +718,6 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans, } btrfs_release_path(path); } - ret = 0; -out: btrfs_free_path(path); return ret; } diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 646152f30584..41ad37f8062a 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1154,7 +1154,7 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans, int del_nr = 0; int del_slot = 0; int recow; - int ret; + int ret = 0; u64 ino = btrfs_ino(inode); path = btrfs_alloc_path(); @@ -1374,7 +1374,7 @@ again: } out: btrfs_free_path(path); - return 0; + return ret; } /* @@ -3016,8 +3016,11 @@ reserve_space: goto out; ret = btrfs_qgroup_reserve_data(inode, &data_reserved, alloc_start, bytes_to_reserve); - if (ret) + if (ret) { + unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, + lockend, &cached_state); goto out; + } ret = btrfs_prealloc_file_range(inode, mode, alloc_start, alloc_end - alloc_start, i_blocksize(inode), diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 652b0b16e93e..b623e9f3b4c4 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -743,8 +743,10 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode, while (num_entries) { e = kmem_cache_zalloc(btrfs_free_space_cachep, GFP_NOFS); - if (!e) + if (!e) { + ret = -ENOMEM; goto free_cache; + } ret = io_ctl_read_entry(&io_ctl, e, &type); if (ret) { @@ -753,6 +755,7 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode, } if (!e->bytes) { + ret = -1; kmem_cache_free(btrfs_free_space_cachep, e); goto free_cache; } @@ -773,21 +776,23 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode, e->bitmap = kmem_cache_zalloc( btrfs_free_space_bitmap_cachep, GFP_NOFS); if (!e->bitmap) { + ret = -ENOMEM; kmem_cache_free( btrfs_free_space_cachep, e); goto free_cache; } spin_lock(&ctl->tree_lock); ret = link_free_space(ctl, e); - ctl->total_bitmaps++; - ctl->op->recalc_thresholds(ctl); - spin_unlock(&ctl->tree_lock); if (ret) { + spin_unlock(&ctl->tree_lock); btrfs_err(fs_info, "Duplicate entries in free space cache, dumping"); kmem_cache_free(btrfs_free_space_cachep, e); goto free_cache; } + ctl->total_bitmaps++; + ctl->op->recalc_thresholds(ctl); + spin_unlock(&ctl->tree_lock); list_add_tail(&e->list, &bitmaps); } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 64d459ca76d0..e4a4074ef33d 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3162,6 +3162,18 @@ out: if (ret || truncated) { u64 start, end; + /* + * If we failed to finish this ordered extent for any reason we + * need to make sure BTRFS_ORDERED_IOERR is set on the ordered + * extent, and mark the inode with the error if it wasn't + * already set. Any error during writeback would have already + * set the mapping error, so we need to set it if we're the ones + * marking this ordered extent as failed. + */ + if (ret && !test_and_set_bit(BTRFS_ORDERED_IOERR, + &ordered_extent->flags)) + mapping_set_error(ordered_extent->inode->i_mapping, -EIO); + if (truncated) start = ordered_extent->file_offset + logical_len; else @@ -6608,7 +6620,7 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry, if (IS_ERR(trans)) return PTR_ERR(trans); - err = btrfs_find_free_ino(root, &objectid); + err = btrfs_find_free_objectid(root, &objectid); if (err) goto out_unlock; @@ -6672,7 +6684,7 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry, if (IS_ERR(trans)) return PTR_ERR(trans); - err = btrfs_find_free_ino(root, &objectid); + err = btrfs_find_free_objectid(root, &objectid); if (err) goto out_unlock; @@ -6825,7 +6837,7 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) if (IS_ERR(trans)) return PTR_ERR(trans); - err = btrfs_find_free_ino(root, &objectid); + err = btrfs_find_free_objectid(root, &objectid); if (err) goto out_fail; @@ -9472,7 +9484,7 @@ int __init btrfs_init_cachep(void) btrfs_free_space_bitmap_cachep = kmem_cache_create("btrfs_free_space_bitmap", PAGE_SIZE, PAGE_SIZE, - SLAB_RED_ZONE, NULL); + SLAB_MEM_SPREAD, NULL); if (!btrfs_free_space_bitmap_cachep) goto fail; @@ -9544,8 +9556,14 @@ static int btrfs_rename_exchange(struct inode *old_dir, bool sync_log_dest = false; bool commit_transaction = false; - /* we only allow rename subvolume link between subvolumes */ - if (old_ino != BTRFS_FIRST_FREE_OBJECTID && root != dest) + /* + * For non-subvolumes allow exchange only within one subvolume, in the + * same inode namespace. Two subvolumes (represented as directory) can + * be exchanged as they're a logical link and have a fixed inode number. + */ + if (root != dest && + (old_ino != BTRFS_FIRST_FREE_OBJECTID || + new_ino != BTRFS_FIRST_FREE_OBJECTID)) return -EXDEV; btrfs_init_log_ctx(&ctx_root, old_inode); @@ -9801,7 +9819,7 @@ static int btrfs_whiteout_for_rename(struct btrfs_trans_handle *trans, u64 objectid; u64 index; - ret = btrfs_find_free_ino(root, &objectid); + ret = btrfs_find_free_objectid(root, &objectid); if (ret) return ret; @@ -10298,7 +10316,7 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry, if (IS_ERR(trans)) return PTR_ERR(trans); - err = btrfs_find_free_ino(root, &objectid); + err = btrfs_find_free_objectid(root, &objectid); if (err) goto out_unlock; @@ -10582,7 +10600,7 @@ static int btrfs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) if (IS_ERR(trans)) return PTR_ERR(trans); - ret = btrfs_find_free_ino(root, &objectid); + ret = btrfs_find_free_objectid(root, &objectid); if (ret) goto out; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 01a90fa03c24..c76277ccf03b 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -656,8 +656,6 @@ static noinline int create_subvol(struct inode *dir, btrfs_set_root_otransid(root_item, trans->transid); btrfs_tree_unlock(leaf); - free_extent_buffer(leaf); - leaf = NULL; btrfs_set_root_dirid(root_item, new_dirid); @@ -666,8 +664,22 @@ static noinline int create_subvol(struct inode *dir, key.type = BTRFS_ROOT_ITEM_KEY; ret = btrfs_insert_root(trans, fs_info->tree_root, &key, root_item); - if (ret) + if (ret) { + /* + * Since we don't abort the transaction in this case, free the + * tree block so that we don't leak space and leave the + * filesystem in an inconsistent state (an extent item in the + * extent tree without backreferences). Also no need to have + * the tree block locked since it is not in any tree at this + * point, so no other task can find it and use it. + */ + btrfs_free_tree_block(trans, root, leaf, 0, 1); + free_extent_buffer(leaf); goto fail; + } + + free_extent_buffer(leaf); + leaf = NULL; key.offset = (u64)-1; new_root = btrfs_read_fs_root_no_name(fs_info, &key); @@ -1239,6 +1251,7 @@ static int cluster_pages_for_defrag(struct inode *inode, u64 page_start; u64 page_end; u64 page_cnt; + u64 start = (u64)start_index << PAGE_SHIFT; int ret; int i; int i_done; @@ -1255,8 +1268,7 @@ static int cluster_pages_for_defrag(struct inode *inode, page_cnt = min_t(u64, (u64)num_pages, (u64)file_end - start_index + 1); ret = btrfs_delalloc_reserve_space(inode, &data_reserved, - start_index << PAGE_SHIFT, - page_cnt << PAGE_SHIFT); + start, page_cnt << PAGE_SHIFT); if (ret) return ret; i_done = 0; @@ -1346,8 +1358,7 @@ again: btrfs_mod_outstanding_extents(BTRFS_I(inode), 1); spin_unlock(&BTRFS_I(inode)->lock); btrfs_delalloc_release_space(inode, data_reserved, - start_index << PAGE_SHIFT, - (page_cnt - i_done) << PAGE_SHIFT, true); + start, (page_cnt - i_done) << PAGE_SHIFT, true); } @@ -1374,8 +1385,7 @@ out: put_page(pages[i]); } btrfs_delalloc_release_space(inode, data_reserved, - start_index << PAGE_SHIFT, - page_cnt << PAGE_SHIFT, true); + start, page_cnt << PAGE_SHIFT, true); btrfs_delalloc_release_extents(BTRFS_I(inode), page_cnt << PAGE_SHIFT); extent_changeset_free(data_reserved); return ret; @@ -1779,6 +1789,15 @@ static noinline int btrfs_ioctl_snap_create_transid(struct file *file, * are limited to own subvolumes only */ ret = -EPERM; + } else if (btrfs_ino(BTRFS_I(src_inode)) != BTRFS_FIRST_FREE_OBJECTID) { + /* + * Snapshots must be made with the src_inode referring + * to the subvolume inode, otherwise the permission + * checking above is useless because we may have + * permission on a lower directory but not the subvol + * itself. + */ + ret = -EINVAL; } else { ret = btrfs_mksubvol(&file->f_path, name, namelen, BTRFS_I(src_inode)->root, @@ -1844,7 +1863,10 @@ static noinline int btrfs_ioctl_snap_create_v2(struct file *file, if (vol_args->flags & BTRFS_SUBVOL_RDONLY) readonly = true; if (vol_args->flags & BTRFS_SUBVOL_QGROUP_INHERIT) { - if (vol_args->size > PAGE_SIZE) { + u64 nums; + + if (vol_args->size < sizeof(*inherit) || + vol_args->size > PAGE_SIZE) { ret = -EINVAL; goto free_args; } @@ -1853,6 +1875,20 @@ static noinline int btrfs_ioctl_snap_create_v2(struct file *file, ret = PTR_ERR(inherit); goto free_args; } + + if (inherit->num_qgroups > PAGE_SIZE || + inherit->num_ref_copies > PAGE_SIZE || + inherit->num_excl_copies > PAGE_SIZE) { + ret = -EINVAL; + goto free_inherit; + } + + nums = inherit->num_qgroups + 2 * inherit->num_ref_copies + + 2 * inherit->num_excl_copies; + if (vol_args->size != struct_size(inherit, qgroups, nums)) { + ret = -EINVAL; + goto free_inherit; + } } ret = btrfs_ioctl_snap_create_transid(file, vol_args->name, @@ -2018,7 +2054,7 @@ static noinline int key_in_sk(struct btrfs_key *key, static noinline int copy_to_sk(struct btrfs_path *path, struct btrfs_key *key, struct btrfs_ioctl_search_key *sk, - size_t *buf_size, + u64 *buf_size, char __user *ubuf, unsigned long *sk_offset, int *num_found) @@ -2150,7 +2186,7 @@ out: static noinline int search_ioctl(struct inode *inode, struct btrfs_ioctl_search_key *sk, - size_t *buf_size, + u64 *buf_size, char __user *ubuf) { struct btrfs_fs_info *info = btrfs_sb(inode->i_sb); @@ -2222,7 +2258,7 @@ static noinline int btrfs_ioctl_tree_search(struct file *file, struct btrfs_ioctl_search_key sk; struct inode *inode; int ret; - size_t buf_size; + u64 buf_size; if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -2256,8 +2292,8 @@ static noinline int btrfs_ioctl_tree_search_v2(struct file *file, struct btrfs_ioctl_search_args_v2 args; struct inode *inode; int ret; - size_t buf_size; - const size_t buf_limit = SZ_16M; + u64 buf_size; + const u64 buf_limit = SZ_16M; if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -2732,6 +2768,8 @@ static int btrfs_ioctl_get_subvol_info(struct file *file, void __user *argp) } } + btrfs_free_path(path); + path = NULL; if (copy_to_user(argp, subvol_info, sizeof(*subvol_info))) ret = -EFAULT; @@ -2822,6 +2860,8 @@ static int btrfs_ioctl_get_subvol_rootref(struct file *file, void __user *argp) } out: + btrfs_free_path(path); + if (!ret || ret == -EOVERFLOW) { rootrefs->num_items = found; /* update min_treeid for next search */ @@ -2833,7 +2873,6 @@ out: } kfree(rootrefs); - btrfs_free_path(path); return ret; } @@ -3204,13 +3243,10 @@ static long btrfs_ioctl_dev_info(struct btrfs_fs_info *fs_info, di_args->bytes_used = btrfs_device_get_bytes_used(dev); di_args->total_bytes = btrfs_device_get_total_bytes(dev); memcpy(di_args->uuid, dev->uuid, sizeof(di_args->uuid)); - if (dev->name) { - strncpy(di_args->path, rcu_str_deref(dev->name), - sizeof(di_args->path) - 1); - di_args->path[sizeof(di_args->path) - 1] = 0; - } else { + if (dev->name) + strscpy(di_args->path, rcu_str_deref(dev->name), sizeof(di_args->path)); + else di_args->path[0] = '\0'; - } out: rcu_read_unlock(); @@ -4217,6 +4253,8 @@ process_slot: ret = -EINTR; goto out; } + + cond_resched(); } ret = 0; @@ -4497,7 +4535,7 @@ static void get_block_group_info(struct list_head *groups_list, static long btrfs_ioctl_space_info(struct btrfs_fs_info *fs_info, void __user *arg) { - struct btrfs_ioctl_space_args space_args; + struct btrfs_ioctl_space_args space_args = { 0 }; struct btrfs_ioctl_space_info space; struct btrfs_ioctl_space_info *dest; struct btrfs_ioctl_space_info *dest_orig; @@ -4693,6 +4731,11 @@ static long btrfs_ioctl_scrub(struct file *file, void __user *arg) if (IS_ERR(sa)) return PTR_ERR(sa); + if (sa->flags & ~BTRFS_SCRUB_SUPPORTED_FLAGS) { + ret = -EOPNOTSUPP; + goto out; + } + if (!(sa->flags & BTRFS_SCRUB_READONLY)) { ret = mnt_want_write_file(file); if (ret) @@ -4857,6 +4900,8 @@ static long btrfs_ioctl_ino_to_path(struct btrfs_root *root, void __user *arg) ipath->fspath->val[i] = rel_ptr; } + btrfs_free_path(path); + path = NULL; ret = copy_to_user((void __user *)(unsigned long)ipa->fspath, ipath->fspath, size); if (ret) { @@ -4927,21 +4972,20 @@ static long btrfs_ioctl_logical_to_ino(struct btrfs_fs_info *fs_info, size = min_t(u32, loi->size, SZ_16M); } - path = btrfs_alloc_path(); - if (!path) { - ret = -ENOMEM; - goto out; - } - inodes = init_data_container(size); if (IS_ERR(inodes)) { ret = PTR_ERR(inodes); - inodes = NULL; - goto out; + goto out_loi; } + path = btrfs_alloc_path(); + if (!path) { + ret = -ENOMEM; + goto out; + } ret = iterate_inodes_from_logical(loi->logical, fs_info, path, build_ino_list, inodes, ignore_offset); + btrfs_free_path(path); if (ret == -EINVAL) ret = -ENOENT; if (ret < 0) @@ -4953,7 +4997,6 @@ static long btrfs_ioctl_logical_to_ino(struct btrfs_fs_info *fs_info, ret = -EFAULT; out: - btrfs_free_path(path); kvfree(inodes); out_loi: kfree(loi); @@ -5850,7 +5893,7 @@ static int _btrfs_ioctl_send(struct file *file, void __user *argp, bool compat) if (compat) { #if defined(CONFIG_64BIT) && defined(CONFIG_COMPAT) - struct btrfs_ioctl_send_args_32 args32; + struct btrfs_ioctl_send_args_32 args32 = { 0 }; ret = copy_from_user(&args32, argp, sizeof(args32)); if (ret) diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c index 4b217e9a581c..e3de0c4ecbfc 100644 --- a/fs/btrfs/print-tree.c +++ b/fs/btrfs/print-tree.c @@ -109,10 +109,10 @@ static void print_extent_item(struct extent_buffer *eb, int slot, int type) pr_cont("shared data backref parent %llu count %u\n", offset, btrfs_shared_data_ref_count(eb, sref)); /* - * offset is supposed to be a tree block which - * must be aligned to nodesize. + * Offset is supposed to be a tree block which must be + * aligned to sectorsize. */ - if (!IS_ALIGNED(offset, eb->fs_info->nodesize)) + if (!IS_ALIGNED(offset, eb->fs_info->sectorsize)) pr_info( "\t\t\t(parent %llu not aligned to sectorsize %u)\n", offset, eb->fs_info->sectorsize); diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index c8ed4db73b84..ef95525fa6cd 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -488,13 +488,13 @@ next2: break; } out: + btrfs_free_path(path); fs_info->qgroup_flags |= flags; if (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_ON)) clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); else if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN && ret >= 0) ret = qgroup_rescan_init(fs_info, rescan_progress, 0); - btrfs_free_path(path); if (ret < 0) { ulist_free(fs_info->qgroup_ulist); @@ -1035,6 +1035,21 @@ out_add_root: fs_info->qgroup_rescan_running = true; btrfs_queue_work(fs_info->qgroup_rescan_workers, &fs_info->qgroup_rescan_work); + } else { + /* + * We have set both BTRFS_FS_QUOTA_ENABLED and + * BTRFS_QGROUP_STATUS_FLAG_ON, so we can only fail with + * -EINPROGRESS. That can happen because someone started the + * rescan worker by calling quota rescan ioctl before we + * attempted to initialize the rescan worker. Failure due to + * quotas disabled in the meanwhile is not possible, because + * we are holding a write lock on fs_info->subvol_sem, which + * is also acquired when disabling quotas. + * Ignore such error, and any other error would need to undo + * everything we did in the transaction we just committed. + */ + ASSERT(ret == -EINPROGRESS); + ret = 0; } out_free_path: @@ -1100,7 +1115,9 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info) goto end_trans; } + spin_lock(&fs_info->trans_lock); list_del("a_root->dirty_list); + spin_unlock(&fs_info->trans_lock); btrfs_tree_lock(quota_root->node); clean_tree_block(fs_info, quota_root->node); @@ -2353,14 +2370,7 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid, dstgroup->rsv_rfer = inherit->lim.rsv_rfer; dstgroup->rsv_excl = inherit->lim.rsv_excl; - ret = update_qgroup_limit_item(trans, dstgroup); - if (ret) { - fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT; - btrfs_info(fs_info, - "unable to update quota limit for %llu", - dstgroup->qgroupid); - goto unlock; - } + qgroup_dirty(fs_info, dstgroup); } if (srcid) { @@ -2774,6 +2784,12 @@ out: return ret; } +static bool rescan_should_stop(struct btrfs_fs_info *fs_info) +{ + return btrfs_fs_closing(fs_info) || + test_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state); +} + static void btrfs_qgroup_rescan_worker(struct btrfs_work *work) { struct btrfs_fs_info *fs_info = container_of(work, struct btrfs_fs_info, @@ -2782,6 +2798,7 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work) struct btrfs_trans_handle *trans = NULL; int err = -ENOMEM; int ret = 0; + bool stopped = false; path = btrfs_alloc_path(); if (!path) @@ -2794,7 +2811,7 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work) path->skip_locking = 1; err = 0; - while (!err && !btrfs_fs_closing(fs_info)) { + while (!err && !(stopped = rescan_should_stop(fs_info))) { trans = btrfs_start_transaction(fs_info->fs_root, 0); if (IS_ERR(trans)) { err = PTR_ERR(trans); @@ -2837,7 +2854,7 @@ out: } mutex_lock(&fs_info->qgroup_rescan_lock); - if (!btrfs_fs_closing(fs_info)) + if (!stopped) fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_RESCAN; if (trans) { ret = update_qgroup_status_item(trans); @@ -2856,7 +2873,7 @@ out: btrfs_end_transaction(trans); - if (btrfs_fs_closing(fs_info)) { + if (stopped) { btrfs_info(fs_info, "qgroup scan paused"); } else if (err >= 0) { btrfs_info(fs_info, "qgroup scan completed%s", diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index 927f9f3daddb..0ce7ab8f875a 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -318,6 +318,9 @@ static void merge_rbio(struct btrfs_raid_bio *dest, { bio_list_merge(&dest->bio_list, &victim->bio_list); dest->bio_list_bytes += victim->bio_list_bytes; + /* Also inherit the bitmaps from @victim. */ + bitmap_or(dest->dbitmap, victim->dbitmap, dest->dbitmap, + dest->stripe_npages); dest->generic_bio_cnt += victim->generic_bio_cnt; bio_list_init(&victim->bio_list); } @@ -862,6 +865,12 @@ static void rbio_orig_end_io(struct btrfs_raid_bio *rbio, blk_status_t err) if (rbio->generic_bio_cnt) btrfs_bio_counter_sub(rbio->fs_info, rbio->generic_bio_cnt); + /* + * Clear the data bitmap, as the rbio may be cached for later usage. + * do this before before unlock_stripe() so there will be no new bio + * for this bio. + */ + bitmap_clear(rbio->dbitmap, 0, rbio->stripe_npages); /* * At this moment, rbio->bio_list is empty, however since rbio does not @@ -1182,22 +1191,22 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio) int nr_data = rbio->nr_data; int stripe; int pagenr; - int p_stripe = -1; - int q_stripe = -1; + bool has_qstripe; struct bio_list bio_list; struct bio *bio; int ret; bio_list_init(&bio_list); - if (rbio->real_stripes - rbio->nr_data == 1) { - p_stripe = rbio->real_stripes - 1; - } else if (rbio->real_stripes - rbio->nr_data == 2) { - p_stripe = rbio->real_stripes - 2; - q_stripe = rbio->real_stripes - 1; - } else { + if (rbio->real_stripes - rbio->nr_data == 1) + has_qstripe = false; + else if (rbio->real_stripes - rbio->nr_data == 2) + has_qstripe = true; + else BUG(); - } + + /* We should have at least one data sector. */ + ASSERT(bitmap_weight(rbio->dbitmap, rbio->stripe_npages)); /* at this point we either have a full stripe, * or we've read the full stripe from the drive. @@ -1241,7 +1250,7 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio) SetPageUptodate(p); pointers[stripe++] = kmap(p); - if (q_stripe != -1) { + if (has_qstripe) { /* * raid6, add the qstripe and call the @@ -1272,6 +1281,11 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio) for (stripe = 0; stripe < rbio->real_stripes; stripe++) { for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) { struct page *page; + + /* This vertical stripe has no data, skip it. */ + if (!test_bit(pagenr, rbio->dbitmap)) + continue; + if (stripe < rbio->nr_data) { page = page_in_rbio(rbio, stripe, pagenr, 1); if (!page) @@ -1296,6 +1310,11 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio) for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) { struct page *page; + + /* This vertical stripe has no data, skip it. */ + if (!test_bit(pagenr, rbio->dbitmap)) + continue; + if (stripe < rbio->nr_data) { page = page_in_rbio(rbio, stripe, pagenr, 1); if (!page) @@ -1736,6 +1755,33 @@ static void btrfs_raid_unplug(struct blk_plug_cb *cb, bool from_schedule) run_plug(plug); } +/* Add the original bio into rbio->bio_list, and update rbio::dbitmap. */ +static void rbio_add_bio(struct btrfs_raid_bio *rbio, struct bio *orig_bio) +{ + const struct btrfs_fs_info *fs_info = rbio->fs_info; + const u64 orig_logical = orig_bio->bi_iter.bi_sector << SECTOR_SHIFT; + const u64 full_stripe_start = rbio->bbio->raid_map[0]; + const u32 orig_len = orig_bio->bi_iter.bi_size; + const u32 sectorsize = fs_info->sectorsize; + u64 cur_logical; + + ASSERT(orig_logical >= full_stripe_start && + orig_logical + orig_len <= full_stripe_start + + rbio->nr_data * rbio->stripe_len); + + bio_list_add(&rbio->bio_list, orig_bio); + rbio->bio_list_bytes += orig_bio->bi_iter.bi_size; + + /* Update the dbitmap. */ + for (cur_logical = orig_logical; cur_logical < orig_logical + orig_len; + cur_logical += sectorsize) { + int bit = ((u32)(cur_logical - full_stripe_start) >> + PAGE_SHIFT) % rbio->stripe_npages; + + set_bit(bit, rbio->dbitmap); + } +} + /* * our main entry point for writes from the rest of the FS. */ @@ -1752,9 +1798,8 @@ int raid56_parity_write(struct btrfs_fs_info *fs_info, struct bio *bio, btrfs_put_bbio(bbio); return PTR_ERR(rbio); } - bio_list_add(&rbio->bio_list, bio); - rbio->bio_list_bytes = bio->bi_iter.bi_size; rbio->operation = BTRFS_RBIO_WRITE; + rbio_add_bio(rbio, bio); btrfs_bio_counter_inc_noblocked(fs_info); rbio->generic_bio_cnt = 1; @@ -2056,9 +2101,12 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio) atomic_set(&rbio->error, 0); /* - * read everything that hasn't failed. Thanks to the - * stripe cache, it is possible that some or all of these - * pages are going to be uptodate. + * Read everything that hasn't failed. However this time we will + * not trust any cached sector. + * As we may read out some stale data but higher layer is not reading + * that stale part. + * + * So here we always re-read everything in recovery path. */ for (stripe = 0; stripe < rbio->real_stripes; stripe++) { if (rbio->faila == stripe || rbio->failb == stripe) { @@ -2067,16 +2115,6 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio) } for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) { - struct page *p; - - /* - * the rmw code may have already read this - * page in - */ - p = rbio_stripe_page(rbio, stripe, pagenr); - if (PageUptodate(p)) - continue; - ret = rbio_add_io_page(rbio, &bio_list, rbio_stripe_page(rbio, stripe, pagenr), stripe, pagenr, rbio->stripe_len); @@ -2158,8 +2196,7 @@ int raid56_parity_recover(struct btrfs_fs_info *fs_info, struct bio *bio, } rbio->operation = BTRFS_RBIO_READ_REBUILD; - bio_list_add(&rbio->bio_list, bio); - rbio->bio_list_bytes = bio->bi_iter.bi_size; + rbio_add_bio(rbio, bio); rbio->faila = find_logical_bio_stripe(rbio, bio); if (rbio->faila == -1) { @@ -2340,8 +2377,7 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio, int nr_data = rbio->nr_data; int stripe; int pagenr; - int p_stripe = -1; - int q_stripe = -1; + bool has_qstripe; struct page *p_page = NULL; struct page *q_page = NULL; struct bio_list bio_list; @@ -2351,14 +2387,12 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio, bio_list_init(&bio_list); - if (rbio->real_stripes - rbio->nr_data == 1) { - p_stripe = rbio->real_stripes - 1; - } else if (rbio->real_stripes - rbio->nr_data == 2) { - p_stripe = rbio->real_stripes - 2; - q_stripe = rbio->real_stripes - 1; - } else { + if (rbio->real_stripes - rbio->nr_data == 1) + has_qstripe = false; + else if (rbio->real_stripes - rbio->nr_data == 2) + has_qstripe = true; + else BUG(); - } if (bbio->num_tgtdevs && bbio->tgtdev_map[rbio->scrubp]) { is_replace = 1; @@ -2380,17 +2414,22 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio, goto cleanup; SetPageUptodate(p_page); - if (q_stripe != -1) { + if (has_qstripe) { + /* RAID6, allocate and map temp space for the Q stripe */ q_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM); if (!q_page) { __free_page(p_page); goto cleanup; } SetPageUptodate(q_page); + pointers[rbio->real_stripes - 1] = kmap(q_page); } atomic_set(&rbio->error, 0); + /* Map the parity stripe just once */ + pointers[nr_data] = kmap(p_page); + for_each_set_bit(pagenr, rbio->dbitmap, rbio->stripe_npages) { struct page *p; void *parity; @@ -2400,17 +2439,8 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio, pointers[stripe] = kmap(p); } - /* then add the parity stripe */ - pointers[stripe++] = kmap(p_page); - - if (q_stripe != -1) { - - /* - * raid6, add the qstripe and call the - * library function to fill in our p/q - */ - pointers[stripe++] = kmap(q_page); - + if (has_qstripe) { + /* RAID6, call the library function to fill in our P/Q */ raid6_call.gen_syndrome(rbio->real_stripes, PAGE_SIZE, pointers); } else { @@ -2431,12 +2461,14 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio, for (stripe = 0; stripe < nr_data; stripe++) kunmap(page_in_rbio(rbio, stripe, pagenr, 0)); - kunmap(p_page); } + kunmap(p_page); __free_page(p_page); - if (q_page) + if (q_page) { + kunmap(q_page); __free_page(q_page); + } writeback: /* diff --git a/fs/btrfs/rcu-string.h b/fs/btrfs/rcu-string.h index a97dc74a4d3d..02f15321cecc 100644 --- a/fs/btrfs/rcu-string.h +++ b/fs/btrfs/rcu-string.h @@ -18,7 +18,11 @@ static inline struct rcu_string *rcu_string_strdup(const char *src, gfp_t mask) (len * sizeof(char)), mask); if (!ret) return ret; - strncpy(ret->str, src, len); + /* Warn if the source got unexpectedly truncated. */ + if (WARN_ON(strscpy(ret->str, src, len) < 0)) { + kfree(ret); + return NULL; + } return ret; } diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c index 4c81ffe12385..368c349c5669 100644 --- a/fs/btrfs/reada.c +++ b/fs/btrfs/reada.c @@ -442,6 +442,8 @@ static struct reada_extent *reada_find_extent(struct btrfs_fs_info *fs_info, } have_zone = 1; } + if (!have_zone) + radix_tree_delete(&fs_info->reada_tree, index); spin_unlock(&fs_info->reada_lock); btrfs_dev_replace_read_unlock(&fs_info->dev_replace); diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c index 5dec52bd2897..b26739d0e991 100644 --- a/fs/btrfs/ref-verify.c +++ b/fs/btrfs/ref-verify.c @@ -854,6 +854,7 @@ int btrfs_ref_tree_mod(struct btrfs_root *root, u64 bytenr, u64 num_bytes, "dropping a ref for a root that doesn't have a ref on the block"); dump_block_entry(fs_info, be); dump_ref_action(fs_info, ra); + kfree(ref); kfree(ra); goto out_unlock; } diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index eedcb7bf50e9..3b9318a3d421 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -1291,9 +1291,7 @@ static void __del_reloc_root(struct btrfs_root *root) RB_CLEAR_NODE(&node->rb_node); } spin_unlock(&rc->reloc_root_tree.lock); - if (!node) - return; - BUG_ON((struct btrfs_root *)node->data != root); + ASSERT(!node || (struct btrfs_root *)node->data == root); } spin_lock(&fs_info->trans_lock); @@ -1757,8 +1755,8 @@ int replace_path(struct btrfs_trans_handle *trans, int ret; int slot; - BUG_ON(src->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID); - BUG_ON(dest->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID); + ASSERT(src->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID); + ASSERT(dest->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID); last_snapshot = btrfs_root_last_snapshot(&src->root_item); again: @@ -1792,7 +1790,7 @@ again: struct btrfs_key first_key; level = btrfs_header_level(parent); - BUG_ON(level < lowest_level); + ASSERT(level >= lowest_level); ret = btrfs_bin_search(parent, &key, level, &slot); if (ret && slot > 0) @@ -2343,7 +2341,7 @@ again: list_splice(&reloc_roots, &rc->reloc_roots); if (!err) - btrfs_commit_transaction(trans); + err = btrfs_commit_transaction(trans); else btrfs_end_transaction(trans); return err; @@ -3932,8 +3930,12 @@ int prepare_to_relocate(struct reloc_control *rc) */ return PTR_ERR(trans); } - btrfs_commit_transaction(trans); - return 0; + + ret = btrfs_commit_transaction(trans); + if (ret) + unset_reloc_control(rc); + + return ret; } static noinline_for_stack int relocate_block_group(struct reloc_control *rc) @@ -4099,7 +4101,9 @@ restart: err = PTR_ERR(trans); goto out_free; } - btrfs_commit_transaction(trans); + ret = btrfs_commit_transaction(trans); + if (ret && !err) + err = ret; out_free: btrfs_free_block_rsv(fs_info, rc->block_rsv); btrfs_free_path(path); diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 2bc80d0b56db..cb584c044f8a 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -238,6 +238,7 @@ struct waiting_dir_move { * after this directory is moved, we can try to rmdir the ino rmdir_ino. */ u64 rmdir_ino; + u64 rmdir_gen; bool orphanized; }; @@ -308,7 +309,7 @@ static int is_waiting_for_move(struct send_ctx *sctx, u64 ino); static struct waiting_dir_move * get_waiting_dir_move(struct send_ctx *sctx, u64 ino); -static int is_waiting_for_rm(struct send_ctx *sctx, u64 dir_ino); +static int is_waiting_for_rm(struct send_ctx *sctx, u64 dir_ino, u64 gen); static int need_send_hole(struct send_ctx *sctx) { @@ -1305,6 +1306,7 @@ static int find_extent_clone(struct send_ctx *sctx, u64 disk_byte; u64 num_bytes; u64 extent_item_pos; + u64 extent_refs; u64 flags = 0; struct btrfs_file_extent_item *fi; struct extent_buffer *eb = path->nodes[0]; @@ -1372,14 +1374,22 @@ static int find_extent_clone(struct send_ctx *sctx, ei = btrfs_item_ptr(tmp_path->nodes[0], tmp_path->slots[0], struct btrfs_extent_item); + extent_refs = btrfs_extent_refs(tmp_path->nodes[0], ei); /* * Backreference walking (iterate_extent_inodes() below) is currently * too expensive when an extent has a large number of references, both * in time spent and used memory. So for now just fallback to write * operations instead of clone operations when an extent has more than * a certain amount of references. + * + * Also, if we have only one reference and only the send root as a clone + * source - meaning no clone roots were given in the struct + * btrfs_ioctl_send_args passed to the send ioctl - then it's our + * reference and there's no point in doing backref walking which is + * expensive, so exit early. */ - if (btrfs_extent_refs(tmp_path->nodes[0], ei) > SEND_MAX_EXTENT_REFS) { + if ((extent_refs == 1 && sctx->clone_roots_cnt == 1) || + extent_refs > SEND_MAX_EXTENT_REFS) { ret = -ENOENT; goto out; } @@ -2304,7 +2314,7 @@ static int get_cur_path(struct send_ctx *sctx, u64 ino, u64 gen, fs_path_reset(name); - if (is_waiting_for_rm(sctx, ino)) { + if (is_waiting_for_rm(sctx, ino, gen)) { ret = gen_unique_name(sctx, ino, gen, name); if (ret < 0) goto out; @@ -2863,8 +2873,8 @@ out: return ret; } -static struct orphan_dir_info * -add_orphan_dir_info(struct send_ctx *sctx, u64 dir_ino) +static struct orphan_dir_info *add_orphan_dir_info(struct send_ctx *sctx, + u64 dir_ino, u64 dir_gen) { struct rb_node **p = &sctx->orphan_dirs.rb_node; struct rb_node *parent = NULL; @@ -2873,20 +2883,23 @@ add_orphan_dir_info(struct send_ctx *sctx, u64 dir_ino) while (*p) { parent = *p; entry = rb_entry(parent, struct orphan_dir_info, node); - if (dir_ino < entry->ino) { + if (dir_ino < entry->ino) + p = &(*p)->rb_left; + else if (dir_ino > entry->ino) + p = &(*p)->rb_right; + else if (dir_gen < entry->gen) p = &(*p)->rb_left; - } else if (dir_ino > entry->ino) { + else if (dir_gen > entry->gen) p = &(*p)->rb_right; - } else { + else return entry; - } } odi = kmalloc(sizeof(*odi), GFP_KERNEL); if (!odi) return ERR_PTR(-ENOMEM); odi->ino = dir_ino; - odi->gen = 0; + odi->gen = dir_gen; odi->last_dir_index_offset = 0; rb_link_node(&odi->node, parent, p); @@ -2894,8 +2907,8 @@ add_orphan_dir_info(struct send_ctx *sctx, u64 dir_ino) return odi; } -static struct orphan_dir_info * -get_orphan_dir_info(struct send_ctx *sctx, u64 dir_ino) +static struct orphan_dir_info *get_orphan_dir_info(struct send_ctx *sctx, + u64 dir_ino, u64 gen) { struct rb_node *n = sctx->orphan_dirs.rb_node; struct orphan_dir_info *entry; @@ -2906,15 +2919,19 @@ get_orphan_dir_info(struct send_ctx *sctx, u64 dir_ino) n = n->rb_left; else if (dir_ino > entry->ino) n = n->rb_right; + else if (gen < entry->gen) + n = n->rb_left; + else if (gen > entry->gen) + n = n->rb_right; else return entry; } return NULL; } -static int is_waiting_for_rm(struct send_ctx *sctx, u64 dir_ino) +static int is_waiting_for_rm(struct send_ctx *sctx, u64 dir_ino, u64 gen) { - struct orphan_dir_info *odi = get_orphan_dir_info(sctx, dir_ino); + struct orphan_dir_info *odi = get_orphan_dir_info(sctx, dir_ino, gen); return odi != NULL; } @@ -2959,7 +2976,7 @@ static int can_rmdir(struct send_ctx *sctx, u64 dir, u64 dir_gen, key.type = BTRFS_DIR_INDEX_KEY; key.offset = 0; - odi = get_orphan_dir_info(sctx, dir); + odi = get_orphan_dir_info(sctx, dir, dir_gen); if (odi) key.offset = odi->last_dir_index_offset; @@ -2990,7 +3007,7 @@ static int can_rmdir(struct send_ctx *sctx, u64 dir, u64 dir_gen, dm = get_waiting_dir_move(sctx, loc.objectid); if (dm) { - odi = add_orphan_dir_info(sctx, dir); + odi = add_orphan_dir_info(sctx, dir, dir_gen); if (IS_ERR(odi)) { ret = PTR_ERR(odi); goto out; @@ -2998,12 +3015,13 @@ static int can_rmdir(struct send_ctx *sctx, u64 dir, u64 dir_gen, odi->gen = dir_gen; odi->last_dir_index_offset = found_key.offset; dm->rmdir_ino = dir; + dm->rmdir_gen = dir_gen; ret = 0; goto out; } if (loc.objectid > send_progress) { - odi = add_orphan_dir_info(sctx, dir); + odi = add_orphan_dir_info(sctx, dir, dir_gen); if (IS_ERR(odi)) { ret = PTR_ERR(odi); goto out; @@ -3043,6 +3061,7 @@ static int add_waiting_dir_move(struct send_ctx *sctx, u64 ino, bool orphanized) return -ENOMEM; dm->ino = ino; dm->rmdir_ino = 0; + dm->rmdir_gen = 0; dm->orphanized = orphanized; while (*p) { @@ -3188,7 +3207,7 @@ static int path_loop(struct send_ctx *sctx, struct fs_path *name, while (ino != BTRFS_FIRST_FREE_OBJECTID) { fs_path_reset(name); - if (is_waiting_for_rm(sctx, ino)) + if (is_waiting_for_rm(sctx, ino, gen)) break; if (is_waiting_for_move(sctx, ino)) { if (*ancestor_ino == 0) @@ -3228,6 +3247,7 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm) u64 parent_ino, parent_gen; struct waiting_dir_move *dm = NULL; u64 rmdir_ino = 0; + u64 rmdir_gen; u64 ancestor; bool is_orphan; int ret; @@ -3242,6 +3262,7 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm) dm = get_waiting_dir_move(sctx, pm->ino); ASSERT(dm); rmdir_ino = dm->rmdir_ino; + rmdir_gen = dm->rmdir_gen; is_orphan = dm->orphanized; free_waiting_dir_move(sctx, dm); @@ -3278,6 +3299,7 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm) dm = get_waiting_dir_move(sctx, pm->ino); ASSERT(dm); dm->rmdir_ino = rmdir_ino; + dm->rmdir_gen = rmdir_gen; } goto out; } @@ -3296,7 +3318,7 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm) struct orphan_dir_info *odi; u64 gen; - odi = get_orphan_dir_info(sctx, rmdir_ino); + odi = get_orphan_dir_info(sctx, rmdir_ino, rmdir_gen); if (!odi) { /* already deleted */ goto finish; @@ -3811,6 +3833,72 @@ static int update_ref_path(struct send_ctx *sctx, struct recorded_ref *ref) } /* + * When processing the new references for an inode we may orphanize an existing + * directory inode because its old name conflicts with one of the new references + * of the current inode. Later, when processing another new reference of our + * inode, we might need to orphanize another inode, but the path we have in the + * reference reflects the pre-orphanization name of the directory we previously + * orphanized. For example: + * + * parent snapshot looks like: + * + * . (ino 256) + * |----- f1 (ino 257) + * |----- f2 (ino 258) + * |----- d1/ (ino 259) + * |----- d2/ (ino 260) + * + * send snapshot looks like: + * + * . (ino 256) + * |----- d1 (ino 258) + * |----- f2/ (ino 259) + * |----- f2_link/ (ino 260) + * | |----- f1 (ino 257) + * | + * |----- d2 (ino 258) + * + * When processing inode 257 we compute the name for inode 259 as "d1", and we + * cache it in the name cache. Later when we start processing inode 258, when + * collecting all its new references we set a full path of "d1/d2" for its new + * reference with name "d2". When we start processing the new references we + * start by processing the new reference with name "d1", and this results in + * orphanizing inode 259, since its old reference causes a conflict. Then we + * move on the next new reference, with name "d2", and we find out we must + * orphanize inode 260, as its old reference conflicts with ours - but for the + * orphanization we use a source path corresponding to the path we stored in the + * new reference, which is "d1/d2" and not "o259-6-0/d2" - this makes the + * receiver fail since the path component "d1/" no longer exists, it was renamed + * to "o259-6-0/" when processing the previous new reference. So in this case we + * must recompute the path in the new reference and use it for the new + * orphanization operation. + */ +static int refresh_ref_path(struct send_ctx *sctx, struct recorded_ref *ref) +{ + char *name; + int ret; + + name = kmemdup(ref->name, ref->name_len, GFP_KERNEL); + if (!name) + return -ENOMEM; + + fs_path_reset(ref->full_path); + ret = get_cur_path(sctx, ref->dir, ref->dir_gen, ref->full_path); + if (ret < 0) + goto out; + + ret = fs_path_add(ref->full_path, name, ref->name_len); + if (ret < 0) + goto out; + + /* Update the reference's base name pointer. */ + set_ref_path(ref, ref->full_path); +out: + kfree(name); + return ret; +} + +/* * This does all the move/link/unlink/rmdir magic. */ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move) @@ -3940,6 +4028,12 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move) struct name_cache_entry *nce; struct waiting_dir_move *wdm; + if (orphanized_dir) { + ret = refresh_ref_path(sctx, cur); + if (ret < 0) + goto out; + } + ret = orphanize_inode(sctx, ow_inode, ow_gen, cur->full_path); if (ret < 0) @@ -3996,6 +4090,17 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move) if (ret < 0) goto out; } else { + /* + * If we previously orphanized a directory that + * collided with a new reference that we already + * processed, recompute the current path because + * that directory may be part of the path. + */ + if (orphanized_dir) { + ret = refresh_ref_path(sctx, cur); + if (ret < 0) + goto out; + } ret = send_unlink(sctx, cur->full_path); if (ret < 0) goto out; @@ -4860,6 +4965,10 @@ static ssize_t fill_read_buf(struct send_ctx *sctx, u64 offset, u32 len) lock_page(page); if (!PageUptodate(page)) { unlock_page(page); + btrfs_err(fs_info, + "send: IO error at offset %llu for inode %llu root %llu", + page_offset(page), sctx->cur_ino, + sctx->send_root->root_key.objectid); put_page(page); ret = -EIO; break; @@ -6717,10 +6826,10 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg) /* * Check that we don't overflow at later allocations, we request * clone_sources_count + 1 items, and compare to unsigned long inside - * access_ok. + * access_ok. Also set an upper limit for allocation size so this can't + * easily exhaust memory. Max number of clone sources is about 200K. */ - if (arg->clone_sources_count > - ULONG_MAX / sizeof(struct clone_root) - 1) { + if (arg->clone_sources_count > SZ_8M / sizeof(struct clone_root)) { ret = -EINVAL; goto out; } @@ -6751,7 +6860,7 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg) sctx->flags = arg->flags; sctx->send_filp = fget(arg->send_fd); - if (!sctx->send_filp) { + if (!sctx->send_filp || !(sctx->send_filp->f_mode & FMODE_WRITE)) { ret = -EBADF; goto out; } @@ -6787,7 +6896,7 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg) alloc_size = sizeof(struct clone_root) * (arg->clone_sources_count + 1); - sctx->clone_roots = kzalloc(alloc_size, GFP_KERNEL); + sctx->clone_roots = kvzalloc(alloc_size, GFP_KERNEL); if (!sctx->clone_roots) { ret = -ENOMEM; goto out; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 40f5b4dcb927..a59543951851 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1845,6 +1845,14 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) btrfs_scrub_cancel(fs_info); btrfs_pause_balance(fs_info); + /* + * Pause the qgroup rescan worker if it is running. We don't want + * it to be still running after we are in RO mode, as after that, + * by the time we unmount, it might have left a transaction open, + * so we would leak the transaction and/or crash. + */ + btrfs_qgroup_wait_for_completion(fs_info, false); + ret = btrfs_commit_super(fs_info); if (ret) goto restore; @@ -2188,7 +2196,7 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) * calculated f_bavail. */ if (!mixed && block_rsv->space_info->full && - total_free_meta - thresh < block_rsv->size) + (total_free_meta < thresh || total_free_meta - thresh < block_rsv->size)) buf->f_bavail = 0; buf->f_type = BTRFS_SUPER_MAGIC; diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c index 82d874b10438..86c6ff2cc689 100644 --- a/fs/btrfs/tests/btrfs-tests.c +++ b/fs/btrfs/tests/btrfs-tests.c @@ -174,7 +174,7 @@ void btrfs_free_dummy_fs_info(struct btrfs_fs_info *fs_info) void btrfs_free_dummy_root(struct btrfs_root *root) { - if (!root) + if (IS_ERR_OR_NULL(root)) return; /* Will be freed by btrfs_free_fs_roots */ if (WARN_ON(test_bit(BTRFS_ROOT_IN_RADIX, &root->state))) diff --git a/fs/btrfs/tests/qgroup-tests.c b/fs/btrfs/tests/qgroup-tests.c index d07dd26194b1..9b43907324a3 100644 --- a/fs/btrfs/tests/qgroup-tests.c +++ b/fs/btrfs/tests/qgroup-tests.c @@ -230,21 +230,21 @@ static int test_no_shared_qgroup(struct btrfs_root *root, ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots, false); if (ret) { - ulist_free(old_roots); test_err("couldn't find old roots: %d", ret); return ret; } ret = insert_normal_tree_ref(root, nodesize, nodesize, 0, BTRFS_FS_TREE_OBJECTID); - if (ret) + if (ret) { + ulist_free(old_roots); return ret; + } ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots, false); if (ret) { ulist_free(old_roots); - ulist_free(new_roots); test_err("couldn't find old roots: %d", ret); return ret; } @@ -256,31 +256,33 @@ static int test_no_shared_qgroup(struct btrfs_root *root, return ret; } + /* btrfs_qgroup_account_extent() always frees the ulists passed to it. */ + old_roots = NULL; + new_roots = NULL; + if (btrfs_verify_qgroup_counts(fs_info, BTRFS_FS_TREE_OBJECTID, nodesize, nodesize)) { test_err("qgroup counts didn't match expected values"); return -EINVAL; } - old_roots = NULL; - new_roots = NULL; ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots, false); if (ret) { - ulist_free(old_roots); test_err("couldn't find old roots: %d", ret); return ret; } ret = remove_extent_item(root, nodesize, nodesize); - if (ret) + if (ret) { + ulist_free(old_roots); return -EINVAL; + } ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots, false); if (ret) { ulist_free(old_roots); - ulist_free(new_roots); test_err("couldn't find old roots: %d", ret); return ret; } @@ -331,21 +333,21 @@ static int test_multiple_refs(struct btrfs_root *root, ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots, false); if (ret) { - ulist_free(old_roots); test_err("couldn't find old roots: %d", ret); return ret; } ret = insert_normal_tree_ref(root, nodesize, nodesize, 0, BTRFS_FS_TREE_OBJECTID); - if (ret) + if (ret) { + ulist_free(old_roots); return ret; + } ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots, false); if (ret) { ulist_free(old_roots); - ulist_free(new_roots); test_err("couldn't find old roots: %d", ret); return ret; } @@ -366,21 +368,21 @@ static int test_multiple_refs(struct btrfs_root *root, ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots, false); if (ret) { - ulist_free(old_roots); test_err("couldn't find old roots: %d", ret); return ret; } ret = add_tree_ref(root, nodesize, nodesize, 0, BTRFS_FIRST_FREE_OBJECTID); - if (ret) + if (ret) { + ulist_free(old_roots); return ret; + } ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots, false); if (ret) { ulist_free(old_roots); - ulist_free(new_roots); test_err("couldn't find old roots: %d", ret); return ret; } @@ -407,21 +409,21 @@ static int test_multiple_refs(struct btrfs_root *root, ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots, false); if (ret) { - ulist_free(old_roots); test_err("couldn't find old roots: %d", ret); return ret; } ret = remove_extent_ref(root, nodesize, nodesize, 0, BTRFS_FIRST_FREE_OBJECTID); - if (ret) + if (ret) { + ulist_free(old_roots); return ret; + } ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots, false); if (ret) { ulist_free(old_roots); - ulist_free(new_roots); test_err("couldn't find old roots: %d", ret); return ret; } diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 8829d89eb4af..a34c0436ebb1 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -200,10 +200,11 @@ loop: spin_unlock(&fs_info->trans_lock); /* - * If we are ATTACH, we just want to catch the current transaction, - * and commit it. If there is no transaction, just return ENOENT. + * If we are ATTACH or TRANS_JOIN_NOSTART, we just want to catch the + * current transaction, and commit it. If there is no transaction, just + * return ENOENT. */ - if (type == TRANS_ATTACH) + if (type == TRANS_ATTACH || type == TRANS_JOIN_NOSTART) return -ENOENT; /* @@ -703,8 +704,13 @@ btrfs_attach_transaction_barrier(struct btrfs_root *root) trans = start_transaction(root, 0, TRANS_ATTACH, BTRFS_RESERVE_NO_FLUSH, true); - if (trans == ERR_PTR(-ENOENT)) - btrfs_wait_for_commit(root->fs_info, 0); + if (trans == ERR_PTR(-ENOENT)) { + int ret; + + ret = btrfs_wait_for_commit(root->fs_info, 0); + if (ret) + return ERR_PTR(ret); + } return trans; } @@ -1249,7 +1255,6 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans) struct btrfs_root *gang[8]; int i; int ret; - int err = 0; spin_lock(&fs_info->fs_roots_radix_lock); while (1) { @@ -1261,6 +1266,8 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans) break; for (i = 0; i < ret; i++) { struct btrfs_root *root = gang[i]; + int ret2; + radix_tree_tag_clear(&fs_info->fs_roots_radix, (unsigned long)root->root_key.objectid, BTRFS_ROOT_TRANS_TAG); @@ -1282,17 +1289,17 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans) root->node); } - err = btrfs_update_root(trans, fs_info->tree_root, + ret2 = btrfs_update_root(trans, fs_info->tree_root, &root->root_key, &root->root_item); + if (ret2) + return ret2; spin_lock(&fs_info->fs_roots_radix_lock); - if (err) - break; btrfs_qgroup_free_meta_all_pertrans(root); } } spin_unlock(&fs_info->fs_roots_radix_lock); - return err; + return 0; } /* @@ -1310,8 +1317,10 @@ int btrfs_defrag_root(struct btrfs_root *root) while (1) { trans = btrfs_start_transaction(root, 0); - if (IS_ERR(trans)) - return PTR_ERR(trans); + if (IS_ERR(trans)) { + ret = PTR_ERR(trans); + break; + } ret = btrfs_defrag_leaves(trans, root); diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index d98ec885b72a..9023e6b46396 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -448,6 +448,320 @@ static int check_block_group_item(struct btrfs_fs_info *fs_info, return 0; } +__printf(5, 6) +__cold +static void chunk_err(const struct btrfs_fs_info *fs_info, + const struct extent_buffer *leaf, + const struct btrfs_chunk *chunk, u64 logical, + const char *fmt, ...) +{ + bool is_sb; + struct va_format vaf; + va_list args; + int i; + int slot = -1; + + /* Only superblock eb is able to have such small offset */ + is_sb = (leaf->start == BTRFS_SUPER_INFO_OFFSET); + + if (!is_sb) { + /* + * Get the slot number by iterating through all slots, this + * would provide better readability. + */ + for (i = 0; i < btrfs_header_nritems(leaf); i++) { + if (btrfs_item_ptr_offset(leaf, i) == + (unsigned long)chunk) { + slot = i; + break; + } + } + } + va_start(args, fmt); + vaf.fmt = fmt; + vaf.va = &args; + + if (is_sb) + btrfs_crit(fs_info, + "corrupt superblock syschunk array: chunk_start=%llu, %pV", + logical, &vaf); + else + btrfs_crit(fs_info, + "corrupt leaf: root=%llu block=%llu slot=%d chunk_start=%llu, %pV", + BTRFS_CHUNK_TREE_OBJECTID, leaf->start, slot, + logical, &vaf); + va_end(args); +} + +/* + * The common chunk check which could also work on super block sys chunk array. + * + * Return -EUCLEAN if anything is corrupted. + * Return 0 if everything is OK. + */ +int btrfs_check_chunk_valid(struct btrfs_fs_info *fs_info, + struct extent_buffer *leaf, + struct btrfs_chunk *chunk, u64 logical) +{ + u64 length; + u64 stripe_len; + u16 num_stripes; + u16 sub_stripes; + u64 type; + u64 features; + bool mixed = false; + + length = btrfs_chunk_length(leaf, chunk); + stripe_len = btrfs_chunk_stripe_len(leaf, chunk); + num_stripes = btrfs_chunk_num_stripes(leaf, chunk); + sub_stripes = btrfs_chunk_sub_stripes(leaf, chunk); + type = btrfs_chunk_type(leaf, chunk); + + if (!num_stripes) { + chunk_err(fs_info, leaf, chunk, logical, + "invalid chunk num_stripes, have %u", num_stripes); + return -EUCLEAN; + } + if (!IS_ALIGNED(logical, fs_info->sectorsize)) { + chunk_err(fs_info, leaf, chunk, logical, + "invalid chunk logical, have %llu should aligned to %u", + logical, fs_info->sectorsize); + return -EUCLEAN; + } + if (btrfs_chunk_sector_size(leaf, chunk) != fs_info->sectorsize) { + chunk_err(fs_info, leaf, chunk, logical, + "invalid chunk sectorsize, have %u expect %u", + btrfs_chunk_sector_size(leaf, chunk), + fs_info->sectorsize); + return -EUCLEAN; + } + if (!length || !IS_ALIGNED(length, fs_info->sectorsize)) { + chunk_err(fs_info, leaf, chunk, logical, + "invalid chunk length, have %llu", length); + return -EUCLEAN; + } + if (!is_power_of_2(stripe_len) || stripe_len != BTRFS_STRIPE_LEN) { + chunk_err(fs_info, leaf, chunk, logical, + "invalid chunk stripe length: %llu", + stripe_len); + return -EUCLEAN; + } + if (~(BTRFS_BLOCK_GROUP_TYPE_MASK | BTRFS_BLOCK_GROUP_PROFILE_MASK) & + type) { + chunk_err(fs_info, leaf, chunk, logical, + "unrecognized chunk type: 0x%llx", + ~(BTRFS_BLOCK_GROUP_TYPE_MASK | + BTRFS_BLOCK_GROUP_PROFILE_MASK) & + btrfs_chunk_type(leaf, chunk)); + return -EUCLEAN; + } + + if (!is_power_of_2(type & BTRFS_BLOCK_GROUP_PROFILE_MASK) && + (type & BTRFS_BLOCK_GROUP_PROFILE_MASK) != 0) { + chunk_err(fs_info, leaf, chunk, logical, + "invalid chunk profile flag: 0x%llx, expect 0 or 1 bit set", + type & BTRFS_BLOCK_GROUP_PROFILE_MASK); + return -EUCLEAN; + } + if ((type & BTRFS_BLOCK_GROUP_TYPE_MASK) == 0) { + chunk_err(fs_info, leaf, chunk, logical, + "missing chunk type flag, have 0x%llx one bit must be set in 0x%llx", + type, BTRFS_BLOCK_GROUP_TYPE_MASK); + return -EUCLEAN; + } + + if ((type & BTRFS_BLOCK_GROUP_SYSTEM) && + (type & (BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_DATA))) { + chunk_err(fs_info, leaf, chunk, logical, + "system chunk with data or metadata type: 0x%llx", + type); + return -EUCLEAN; + } + + features = btrfs_super_incompat_flags(fs_info->super_copy); + if (features & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS) + mixed = true; + + if (!mixed) { + if ((type & BTRFS_BLOCK_GROUP_METADATA) && + (type & BTRFS_BLOCK_GROUP_DATA)) { + chunk_err(fs_info, leaf, chunk, logical, + "mixed chunk type in non-mixed mode: 0x%llx", type); + return -EUCLEAN; + } + } + + if ((type & BTRFS_BLOCK_GROUP_RAID10 && sub_stripes != 2) || + (type & BTRFS_BLOCK_GROUP_RAID1 && num_stripes != 2) || + (type & BTRFS_BLOCK_GROUP_RAID5 && num_stripes < 2) || + (type & BTRFS_BLOCK_GROUP_RAID6 && num_stripes < 3) || + (type & BTRFS_BLOCK_GROUP_DUP && num_stripes != 2) || + ((type & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0 && num_stripes != 1)) { + chunk_err(fs_info, leaf, chunk, logical, + "invalid num_stripes:sub_stripes %u:%u for profile %llu", + num_stripes, sub_stripes, + type & BTRFS_BLOCK_GROUP_PROFILE_MASK); + return -EUCLEAN; + } + + return 0; +} + +__printf(4, 5) +__cold +static void dev_item_err(const struct btrfs_fs_info *fs_info, + const struct extent_buffer *eb, int slot, + const char *fmt, ...) +{ + struct btrfs_key key; + struct va_format vaf; + va_list args; + + btrfs_item_key_to_cpu(eb, &key, slot); + va_start(args, fmt); + + vaf.fmt = fmt; + vaf.va = &args; + + btrfs_crit(fs_info, + "corrupt %s: root=%llu block=%llu slot=%d devid=%llu %pV", + btrfs_header_level(eb) == 0 ? "leaf" : "node", + btrfs_header_owner(eb), btrfs_header_bytenr(eb), slot, + key.objectid, &vaf); + va_end(args); +} + +static int check_dev_item(struct btrfs_fs_info *fs_info, + struct extent_buffer *leaf, + struct btrfs_key *key, int slot) +{ + struct btrfs_dev_item *ditem; + + if (key->objectid != BTRFS_DEV_ITEMS_OBJECTID) { + dev_item_err(fs_info, leaf, slot, + "invalid objectid: has=%llu expect=%llu", + key->objectid, BTRFS_DEV_ITEMS_OBJECTID); + return -EUCLEAN; + } + ditem = btrfs_item_ptr(leaf, slot, struct btrfs_dev_item); + if (btrfs_device_id(leaf, ditem) != key->offset) { + dev_item_err(fs_info, leaf, slot, + "devid mismatch: key has=%llu item has=%llu", + key->offset, btrfs_device_id(leaf, ditem)); + return -EUCLEAN; + } + + /* + * For device total_bytes, we don't have reliable way to check it, as + * it can be 0 for device removal. Device size check can only be done + * by dev extents check. + */ + if (btrfs_device_bytes_used(leaf, ditem) > + btrfs_device_total_bytes(leaf, ditem)) { + dev_item_err(fs_info, leaf, slot, + "invalid bytes used: have %llu expect [0, %llu]", + btrfs_device_bytes_used(leaf, ditem), + btrfs_device_total_bytes(leaf, ditem)); + return -EUCLEAN; + } + /* + * Remaining members like io_align/type/gen/dev_group aren't really + * utilized. Skip them to make later usage of them easier. + */ + return 0; +} + +/* Inode item error output has the same format as dir_item_err() */ +#define inode_item_err(fs_info, eb, slot, fmt, ...) \ + dir_item_err(fs_info, eb, slot, fmt, __VA_ARGS__) + +static int check_inode_item(struct btrfs_fs_info *fs_info, + struct extent_buffer *leaf, + struct btrfs_key *key, int slot) +{ + struct btrfs_inode_item *iitem; + u64 super_gen = btrfs_super_generation(fs_info->super_copy); + u32 valid_mask = (S_IFMT | S_ISUID | S_ISGID | S_ISVTX | 0777); + u32 mode; + + if ((key->objectid < BTRFS_FIRST_FREE_OBJECTID || + key->objectid > BTRFS_LAST_FREE_OBJECTID) && + key->objectid != BTRFS_ROOT_TREE_DIR_OBJECTID && + key->objectid != BTRFS_FREE_INO_OBJECTID) { + generic_err(fs_info, leaf, slot, + "invalid key objectid: has %llu expect %llu or [%llu, %llu] or %llu", + key->objectid, BTRFS_ROOT_TREE_DIR_OBJECTID, + BTRFS_FIRST_FREE_OBJECTID, + BTRFS_LAST_FREE_OBJECTID, + BTRFS_FREE_INO_OBJECTID); + return -EUCLEAN; + } + if (key->offset != 0) { + inode_item_err(fs_info, leaf, slot, + "invalid key offset: has %llu expect 0", + key->offset); + return -EUCLEAN; + } + iitem = btrfs_item_ptr(leaf, slot, struct btrfs_inode_item); + + /* Here we use super block generation + 1 to handle log tree */ + if (btrfs_inode_generation(leaf, iitem) > super_gen + 1) { + inode_item_err(fs_info, leaf, slot, + "invalid inode generation: has %llu expect (0, %llu]", + btrfs_inode_generation(leaf, iitem), + super_gen + 1); + return -EUCLEAN; + } + /* Note for ROOT_TREE_DIR_ITEM, mkfs could set its transid 0 */ + if (btrfs_inode_transid(leaf, iitem) > super_gen + 1) { + inode_item_err(fs_info, leaf, slot, + "invalid inode transid: has %llu expect [0, %llu]", + btrfs_inode_transid(leaf, iitem), super_gen + 1); + return -EUCLEAN; + } + + /* + * For size and nbytes it's better not to be too strict, as for dir + * item its size/nbytes can easily get wrong, but doesn't affect + * anything in the fs. So here we skip the check. + */ + mode = btrfs_inode_mode(leaf, iitem); + if (mode & ~valid_mask) { + inode_item_err(fs_info, leaf, slot, + "unknown mode bit detected: 0x%x", + mode & ~valid_mask); + return -EUCLEAN; + } + + /* + * S_IFMT is not bit mapped so we can't completely rely on is_power_of_2, + * but is_power_of_2() can save us from checking FIFO/CHR/DIR/REG. + * Only needs to check BLK, LNK and SOCKS + */ + if (!is_power_of_2(mode & S_IFMT)) { + if (!S_ISLNK(mode) && !S_ISBLK(mode) && !S_ISSOCK(mode)) { + inode_item_err(fs_info, leaf, slot, + "invalid mode: has 0%o expect valid S_IF* bit(s)", + mode & S_IFMT); + return -EUCLEAN; + } + } + if (S_ISDIR(mode) && btrfs_inode_nlink(leaf, iitem) > 1) { + inode_item_err(fs_info, leaf, slot, + "invalid nlink: has %u expect no more than 1 for dir", + btrfs_inode_nlink(leaf, iitem)); + return -EUCLEAN; + } + if (btrfs_inode_flags(leaf, iitem) & ~BTRFS_INODE_FLAG_MASK) { + inode_item_err(fs_info, leaf, slot, + "unknown flags detected: 0x%llx", + btrfs_inode_flags(leaf, iitem) & + ~BTRFS_INODE_FLAG_MASK); + return -EUCLEAN; + } + return 0; +} + /* * Common point to switch the item-specific validation. */ @@ -456,6 +770,7 @@ static int check_leaf_item(struct btrfs_fs_info *fs_info, struct btrfs_key *key, int slot) { int ret = 0; + struct btrfs_chunk *chunk; switch (key->type) { case BTRFS_EXTENT_DATA_KEY: @@ -472,6 +787,17 @@ static int check_leaf_item(struct btrfs_fs_info *fs_info, case BTRFS_BLOCK_GROUP_ITEM_KEY: ret = check_block_group_item(fs_info, leaf, key, slot); break; + case BTRFS_CHUNK_ITEM_KEY: + chunk = btrfs_item_ptr(leaf, slot, struct btrfs_chunk); + ret = btrfs_check_chunk_valid(fs_info, leaf, chunk, + key->offset); + break; + case BTRFS_DEV_ITEM_KEY: + ret = check_dev_item(fs_info, leaf, key, slot); + break; + case BTRFS_INODE_ITEM_KEY: + ret = check_inode_item(fs_info, leaf, key, slot); + break; } return ret; } diff --git a/fs/btrfs/tree-checker.h b/fs/btrfs/tree-checker.h index ff043275b784..4df45e8a6659 100644 --- a/fs/btrfs/tree-checker.h +++ b/fs/btrfs/tree-checker.h @@ -25,4 +25,8 @@ int btrfs_check_leaf_relaxed(struct btrfs_fs_info *fs_info, struct extent_buffer *leaf); int btrfs_check_node(struct btrfs_fs_info *fs_info, struct extent_buffer *node); +int btrfs_check_chunk_valid(struct btrfs_fs_info *fs_info, + struct extent_buffer *leaf, + struct btrfs_chunk *chunk, u64 logical); + #endif diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 3e903e6a3387..23ec766eeb0a 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -881,9 +881,11 @@ out: } /* - * helper function to see if a given name and sequence number found - * in an inode back reference are already in a directory and correctly - * point to this inode + * See if a given name and sequence number found in an inode back reference are + * already in a directory and correctly point to this inode. + * + * Returns: < 0 on error, 0 if the directory entry does not exists and 1 if it + * exists. */ static noinline int inode_in_dir(struct btrfs_root *root, struct btrfs_path *path, @@ -892,29 +894,35 @@ static noinline int inode_in_dir(struct btrfs_root *root, { struct btrfs_dir_item *di; struct btrfs_key location; - int match = 0; + int ret = 0; di = btrfs_lookup_dir_index_item(NULL, root, path, dirid, index, name, name_len, 0); - if (di && !IS_ERR(di)) { + if (IS_ERR(di)) { + if (PTR_ERR(di) != -ENOENT) + ret = PTR_ERR(di); + goto out; + } else if (di) { btrfs_dir_item_key_to_cpu(path->nodes[0], di, &location); if (location.objectid != objectid) goto out; - } else + } else { goto out; - btrfs_release_path(path); + } + btrfs_release_path(path); di = btrfs_lookup_dir_item(NULL, root, path, dirid, name, name_len, 0); - if (di && !IS_ERR(di)) { - btrfs_dir_item_key_to_cpu(path->nodes[0], di, &location); - if (location.objectid != objectid) - goto out; - } else + if (IS_ERR(di)) { + ret = PTR_ERR(di); goto out; - match = 1; + } else if (di) { + btrfs_dir_item_key_to_cpu(path->nodes[0], di, &location); + if (location.objectid == objectid) + ret = 1; + } out: btrfs_release_path(path); - return match; + return ret; } /* @@ -1073,7 +1081,9 @@ again: extref = btrfs_lookup_inode_extref(NULL, root, path, name, namelen, inode_objectid, parent_objectid, 0, 0); - if (!IS_ERR_OR_NULL(extref)) { + if (IS_ERR(extref)) { + return PTR_ERR(extref); + } else if (extref) { u32 item_size; u32 cur_offset = 0; unsigned long base; @@ -1141,7 +1151,10 @@ next: /* look for a conflicting sequence number */ di = btrfs_lookup_dir_index_item(trans, root, path, btrfs_ino(dir), ref_index, name, namelen, 0); - if (di && !IS_ERR(di)) { + if (IS_ERR(di)) { + if (PTR_ERR(di) != -ENOENT) + return PTR_ERR(di); + } else if (di) { ret = drop_one_dir_item(trans, root, path, dir, di); if (ret) return ret; @@ -1151,7 +1164,9 @@ next: /* look for a conflicing name */ di = btrfs_lookup_dir_item(trans, root, path, btrfs_ino(dir), name, namelen, 0); - if (di && !IS_ERR(di)) { + if (IS_ERR(di)) { + return PTR_ERR(di); + } else if (di) { ret = drop_one_dir_item(trans, root, path, dir, di); if (ret) return ret; @@ -1276,6 +1291,15 @@ again: inode, name, namelen); kfree(name); iput(dir); + /* + * Whenever we need to check if a name exists or not, we + * check the subvolume tree. So after an unlink we must + * run delayed items, so that future checks for a name + * during log replay see that the name does not exists + * anymore. + */ + if (!ret) + ret = btrfs_run_delayed_items(trans); if (ret) goto out; goto again; @@ -1416,10 +1440,12 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans, if (ret) goto out; - /* if we already have a perfect match, we're done */ - if (!inode_in_dir(root, path, btrfs_ino(BTRFS_I(dir)), - btrfs_ino(BTRFS_I(inode)), ref_index, - name, namelen)) { + ret = inode_in_dir(root, path, btrfs_ino(BTRFS_I(dir)), + btrfs_ino(BTRFS_I(inode)), ref_index, + name, namelen); + if (ret < 0) { + goto out; + } else if (ret == 0) { /* * look for a conflicting back reference in the * metadata. if we find one we have to unlink that name @@ -1465,6 +1491,15 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans, */ if (!ret && inode->i_nlink == 0) inc_nlink(inode); + /* + * Whenever we need to check if a name exists or + * not, we check the subvolume tree. So after an + * unlink we must run delayed items, so that future + * checks for a name during log replay see that the + * name does not exists anymore. + */ + if (!ret) + ret = btrfs_run_delayed_items(trans); } if (ret < 0) goto out; @@ -1478,6 +1513,7 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans, btrfs_update_inode(trans, root, inode); } + /* Else, ret == 1, we already have a perfect match, we're done. */ ref_ptr = (unsigned long)(ref_ptr + ref_struct_size) + namelen; kfree(name); @@ -1699,6 +1735,7 @@ static noinline int fixup_inode_link_counts(struct btrfs_trans_handle *trans, break; if (ret == 1) { + ret = 0; if (path->slots[0] == 0) break; path->slots[0]--; @@ -1711,17 +1748,19 @@ static noinline int fixup_inode_link_counts(struct btrfs_trans_handle *trans, ret = btrfs_del_item(trans, root, path); if (ret) - goto out; + break; btrfs_release_path(path); inode = read_one_inode(root, key.offset); - if (!inode) - return -EIO; + if (!inode) { + ret = -EIO; + break; + } ret = fixup_inode_link_count(trans, root, inode); iput(inode); if (ret) - goto out; + break; /* * fixup on a directory may create new entries, @@ -1730,8 +1769,6 @@ static noinline int fixup_inode_link_counts(struct btrfs_trans_handle *trans, */ key.offset = (u64)-1; } - ret = 0; -out: btrfs_release_path(path); return ret; } @@ -1770,8 +1807,6 @@ static noinline int link_to_fixup_dir(struct btrfs_trans_handle *trans, ret = btrfs_update_inode(trans, root, inode); } else if (ret == -EEXIST) { ret = 0; - } else { - BUG(); /* Logic Error */ } iput(inode); @@ -1867,8 +1902,8 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans, struct btrfs_key log_key; struct inode *dir; u8 log_type; - int exists; - int ret = 0; + bool exists; + int ret; bool update_size = (key->type == BTRFS_DIR_INDEX_KEY); bool name_added = false; @@ -1888,12 +1923,12 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans, name_len); btrfs_dir_item_key_to_cpu(eb, di, &log_key); - exists = btrfs_lookup_inode(trans, root, path, &log_key, 0); - if (exists == 0) - exists = 1; - else - exists = 0; + ret = btrfs_lookup_inode(trans, root, path, &log_key, 0); btrfs_release_path(path); + if (ret < 0) + goto out; + exists = (ret == 0); + ret = 0; if (key->type == BTRFS_DIR_ITEM_KEY) { dst_di = btrfs_lookup_dir_item(trans, root, path, key->objectid, @@ -1908,7 +1943,14 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans, ret = -EINVAL; goto out; } - if (IS_ERR_OR_NULL(dst_di)) { + + if (dst_di == ERR_PTR(-ENOENT)) + dst_di = NULL; + + if (IS_ERR(dst_di)) { + ret = PTR_ERR(dst_di); + goto out; + } else if (!dst_di) { /* we need a sequence number to insert, so we only * do inserts for the BTRFS_DIR_INDEX_KEY types */ @@ -2390,7 +2432,9 @@ again: else { ret = find_dir_range(log, path, dirid, key_type, &range_start, &range_end); - if (ret != 0) + if (ret < 0) + goto out; + else if (ret > 0) break; } @@ -3589,6 +3633,7 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans, * search and this search we'll not find the key again and can just * bail. */ +search: ret = btrfs_search_slot(NULL, root, &min_key, path, 0, 0); if (ret != 0) goto done; @@ -3608,6 +3653,13 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans, if (min_key.objectid != ino || min_key.type != key_type) goto done; + + if (need_resched()) { + btrfs_release_path(path); + cond_resched(); + goto search; + } + ret = overwrite_item(trans, log, dst_path, src, i, &min_key); if (ret) { @@ -4184,7 +4236,7 @@ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans, struct extent_buffer *leaf; int slot; int ins_nr = 0; - int start_slot; + int start_slot = 0; int ret; if (!(inode->flags & BTRFS_INODE_PREALLOC)) @@ -4857,6 +4909,18 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, } /* + * For symlinks, we must always log their content, which is stored in an + * inline extent, otherwise we could end up with an empty symlink after + * log replay, which is invalid on linux (symlink(2) returns -ENOENT if + * one attempts to create an empty symlink). + * We don't need to worry about flushing delalloc, because when we create + * the inline extent when the symlink is created (we never have delalloc + * for symlinks). + */ + if (S_ISLNK(inode->vfs_inode.i_mode)) + inode_only = LOG_INODE_ALL; + + /* * a brute force approach to making sure we get the most uptodate * copies of everything. */ @@ -5412,7 +5476,7 @@ process_leaf: } ctx->log_new_dentries = false; - if (type == BTRFS_FT_DIR || type == BTRFS_FT_SYMLINK) + if (type == BTRFS_FT_DIR) log_mode = LOG_INODE_ALL; ret = btrfs_log_inode(trans, root, BTRFS_I(di_inode), log_mode, 0, LLONG_MAX, ctx); @@ -5963,6 +6027,7 @@ next: error: if (wc.trans) btrfs_end_transaction(wc.trans); + clear_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags); btrfs_free_path(path); return ret; } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 815b655b8f10..ceced5e56c5a 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -28,6 +28,7 @@ #include "math.h" #include "dev-replace.h" #include "sysfs.h" +#include "tree-checker.h" const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = { [BTRFS_RAID_RAID10] = { @@ -856,17 +857,25 @@ static noinline struct btrfs_device *device_list_add(const char *path, if (device->bdev != path_bdev) { bdput(path_bdev); mutex_unlock(&fs_devices->device_list_mutex); - btrfs_warn_in_rcu(device->fs_info, - "duplicate device fsid:devid for %pU:%llu old:%s new:%s", - disk_super->fsid, devid, - rcu_str_deref(device->name), path); + /* + * device->fs_info may not be reliable here, so + * pass in a NULL instead. This avoids a + * possible use-after-free when the fs_info and + * fs_info->sb are already torn down. + */ + btrfs_warn_in_rcu(NULL, + "duplicate device %s devid %llu generation %llu scanned by %s (%d)", + path, devid, found_transid, + current->comm, + task_pid_nr(current)); return ERR_PTR(-EEXIST); } bdput(path_bdev); btrfs_info_in_rcu(device->fs_info, - "device fsid %pU devid %llu moved old:%s new:%s", - disk_super->fsid, devid, - rcu_str_deref(device->name), path); + "devid %llu device path %s changed to %s scanned by %s (%d)", + devid, rcu_str_deref(device->name), + path, current->comm, + task_pid_nr(current)); } name = rcu_string_strdup(path, GFP_NOFS); @@ -971,22 +980,13 @@ again: continue; } - if (device->devid == BTRFS_DEV_REPLACE_DEVID) { - /* - * In the first step, keep the device which has - * the correct fsid and the devid that is used - * for the dev_replace procedure. - * In the second step, the dev_replace state is - * read from the device tree and it is known - * whether the procedure is really active or - * not, which means whether this device is - * used or whether it should be removed. - */ - if (step == 0 || test_bit(BTRFS_DEV_STATE_REPLACE_TGT, - &device->dev_state)) { - continue; - } - } + /* + * We have already validated the presence of BTRFS_DEV_REPLACE_DEVID, + * in btrfs_init_dev_replace() so just continue. + */ + if (device->devid == BTRFS_DEV_REPLACE_DEVID) + continue; + if (device->bdev) { blkdev_put(device->bdev, device->mode); device->bdev = NULL; @@ -995,9 +995,7 @@ again: if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) { list_del_init(&device->dev_alloc_list); clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state); - if (!test_bit(BTRFS_DEV_STATE_REPLACE_TGT, - &device->dev_state)) - fs_devices->rw_devices--; + fs_devices->rw_devices--; } list_del_init(&device->dev_list); fs_devices->num_devices--; @@ -1050,8 +1048,13 @@ static void btrfs_close_one_device(struct btrfs_device *device) fs_devices->rw_devices--; } - if (test_bit(BTRFS_DEV_STATE_MISSING, &device->dev_state)) + if (device->devid == BTRFS_DEV_REPLACE_DEVID) + clear_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state); + + if (test_bit(BTRFS_DEV_STATE_MISSING, &device->dev_state)) { + clear_bit(BTRFS_DEV_STATE_MISSING, &device->dev_state); fs_devices->missing_devices--; + } btrfs_close_bdev(device); @@ -1415,7 +1418,7 @@ again: goto out; } - while (1) { + while (search_start < search_end) { l = path->nodes[0]; slot = path->slots[0]; if (slot >= btrfs_header_nritems(l)) { @@ -1438,6 +1441,9 @@ again: if (key.type != BTRFS_DEV_EXTENT_KEY) goto next; + if (key.offset > search_end) + break; + if (key.offset > search_start) { hole_size = key.offset - search_start; @@ -1512,6 +1518,7 @@ next: else ret = 0; + ASSERT(max_hole_start + max_hole_size <= search_end); out: btrfs_free_path(path); *start = max_hole_start; @@ -2456,9 +2463,6 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path btrfs_set_super_num_devices(fs_info->super_copy, orig_super_num_devices + 1); - /* add sysfs device entry */ - btrfs_sysfs_add_device_link(fs_devices, device); - /* * we've got more storage, clear any full flags on the space * infos @@ -2466,6 +2470,10 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path btrfs_clear_space_info_full(fs_info); mutex_unlock(&fs_info->chunk_mutex); + + /* Add sysfs device entry */ + btrfs_sysfs_add_device_link(fs_devices, device); + mutex_unlock(&fs_devices->device_list_mutex); if (seeding_dev) { @@ -2752,7 +2760,7 @@ static struct extent_map *get_chunk_map(struct btrfs_fs_info *fs_info, return ERR_PTR(-EINVAL); } - if (em->start > logical || em->start + em->len < logical) { + if (em->start > logical || em->start + em->len <= logical) { btrfs_crit(fs_info, "found a bad mapping, wanted %llu-%llu, found %llu-%llu", logical, length, em->start, em->start + em->len); @@ -4013,6 +4021,8 @@ int btrfs_recover_balance(struct btrfs_fs_info *fs_info) btrfs_warn(fs_info, "balance: cannot set exclusive op status, resume manually"); + btrfs_release_path(path); + mutex_lock(&fs_info->balance_mutex); BUG_ON(fs_info->balance_ctl); spin_lock(&fs_info->balance_lock); @@ -4096,8 +4106,7 @@ int btrfs_cancel_balance(struct btrfs_fs_info *fs_info) } } - BUG_ON(fs_info->balance_ctl || - test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags)); + ASSERT(!test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags)); atomic_dec(&fs_info->balance_cancel_req); mutex_unlock(&fs_info->balance_mutex); return 0; @@ -4603,15 +4612,6 @@ static void check_raid56_incompat_flag(struct btrfs_fs_info *info, u64 type) btrfs_set_fs_incompat(info, RAID56); } -#define BTRFS_MAX_DEVS(info) ((BTRFS_MAX_ITEM_SIZE(info) \ - - sizeof(struct btrfs_chunk)) \ - / sizeof(struct btrfs_stripe) + 1) - -#define BTRFS_MAX_DEVS_SYS_CHUNK ((BTRFS_SYSTEM_CHUNK_ARRAY_SIZE \ - - 2 * sizeof(struct btrfs_disk_key) \ - - 2 * sizeof(struct btrfs_chunk)) \ - / sizeof(struct btrfs_stripe) + 1) - static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans, u64 start, u64 type) { @@ -6368,99 +6368,6 @@ struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info, return dev; } -/* Return -EIO if any error, otherwise return 0. */ -static int btrfs_check_chunk_valid(struct btrfs_fs_info *fs_info, - struct extent_buffer *leaf, - struct btrfs_chunk *chunk, u64 logical) -{ - u64 length; - u64 stripe_len; - u16 num_stripes; - u16 sub_stripes; - u64 type; - u64 features; - bool mixed = false; - - length = btrfs_chunk_length(leaf, chunk); - stripe_len = btrfs_chunk_stripe_len(leaf, chunk); - num_stripes = btrfs_chunk_num_stripes(leaf, chunk); - sub_stripes = btrfs_chunk_sub_stripes(leaf, chunk); - type = btrfs_chunk_type(leaf, chunk); - - if (!num_stripes) { - btrfs_err(fs_info, "invalid chunk num_stripes: %u", - num_stripes); - return -EIO; - } - if (!IS_ALIGNED(logical, fs_info->sectorsize)) { - btrfs_err(fs_info, "invalid chunk logical %llu", logical); - return -EIO; - } - if (btrfs_chunk_sector_size(leaf, chunk) != fs_info->sectorsize) { - btrfs_err(fs_info, "invalid chunk sectorsize %u", - btrfs_chunk_sector_size(leaf, chunk)); - return -EIO; - } - if (!length || !IS_ALIGNED(length, fs_info->sectorsize)) { - btrfs_err(fs_info, "invalid chunk length %llu", length); - return -EIO; - } - if (!is_power_of_2(stripe_len) || stripe_len != BTRFS_STRIPE_LEN) { - btrfs_err(fs_info, "invalid chunk stripe length: %llu", - stripe_len); - return -EIO; - } - if (~(BTRFS_BLOCK_GROUP_TYPE_MASK | BTRFS_BLOCK_GROUP_PROFILE_MASK) & - type) { - btrfs_err(fs_info, "unrecognized chunk type: %llu", - ~(BTRFS_BLOCK_GROUP_TYPE_MASK | - BTRFS_BLOCK_GROUP_PROFILE_MASK) & - btrfs_chunk_type(leaf, chunk)); - return -EIO; - } - - if ((type & BTRFS_BLOCK_GROUP_TYPE_MASK) == 0) { - btrfs_err(fs_info, "missing chunk type flag: 0x%llx", type); - return -EIO; - } - - if ((type & BTRFS_BLOCK_GROUP_SYSTEM) && - (type & (BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_DATA))) { - btrfs_err(fs_info, - "system chunk with data or metadata type: 0x%llx", type); - return -EIO; - } - - features = btrfs_super_incompat_flags(fs_info->super_copy); - if (features & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS) - mixed = true; - - if (!mixed) { - if ((type & BTRFS_BLOCK_GROUP_METADATA) && - (type & BTRFS_BLOCK_GROUP_DATA)) { - btrfs_err(fs_info, - "mixed chunk type in non-mixed mode: 0x%llx", type); - return -EIO; - } - } - - if ((type & BTRFS_BLOCK_GROUP_RAID10 && sub_stripes != 2) || - (type & BTRFS_BLOCK_GROUP_RAID1 && num_stripes != 2) || - (type & BTRFS_BLOCK_GROUP_RAID5 && num_stripes < 2) || - (type & BTRFS_BLOCK_GROUP_RAID6 && num_stripes < 3) || - (type & BTRFS_BLOCK_GROUP_DUP && num_stripes != 2) || - ((type & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0 && - num_stripes != 1)) { - btrfs_err(fs_info, - "invalid num_stripes:sub_stripes %u:%u for profile %llu", - num_stripes, sub_stripes, - type & BTRFS_BLOCK_GROUP_PROFILE_MASK); - return -EIO; - } - - return 0; -} - static void btrfs_report_missing_device(struct btrfs_fs_info *fs_info, u64 devid, u8 *uuid, bool error) { @@ -6491,9 +6398,15 @@ static int read_one_chunk(struct btrfs_fs_info *fs_info, struct btrfs_key *key, length = btrfs_chunk_length(leaf, chunk); num_stripes = btrfs_chunk_num_stripes(leaf, chunk); - ret = btrfs_check_chunk_valid(fs_info, leaf, chunk, logical); - if (ret) - return ret; + /* + * Only need to verify chunk item if we're reading from sys chunk array, + * as chunk item in tree block is already verified by tree-checker. + */ + if (leaf->start == BTRFS_SUPER_INFO_OFFSET) { + ret = btrfs_check_chunk_valid(fs_info, leaf, chunk, logical); + if (ret) + return ret; + } read_lock(&map_tree->map_tree.lock); em = lookup_extent_mapping(&map_tree->map_tree, logical, 1); @@ -7015,12 +6928,12 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info) * do another round of validation checks. */ if (total_dev != fs_info->fs_devices->total_devices) { - btrfs_err(fs_info, - "super_num_devices %llu mismatch with num_devices %llu found here", + btrfs_warn(fs_info, +"super block num_devices %llu mismatch with DEV_ITEM count %llu, will be repaired on next transaction commit", btrfs_super_num_devices(fs_info->super_copy), total_dev); - ret = -EINVAL; - goto error; + fs_info->fs_devices->total_devices = total_dev; + btrfs_set_super_num_devices(fs_info->super_copy, total_dev); } if (btrfs_super_total_bytes(fs_info->super_copy) < fs_info->fs_devices->total_rw_bytes) { diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 8e8bf3246de1..65cd023b097c 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -257,6 +257,15 @@ struct btrfs_fs_devices { #define BTRFS_BIO_INLINE_CSUM_SIZE 64 +#define BTRFS_MAX_DEVS(info) ((BTRFS_MAX_ITEM_SIZE(info) \ + - sizeof(struct btrfs_chunk)) \ + / sizeof(struct btrfs_stripe) + 1) + +#define BTRFS_MAX_DEVS_SYS_CHUNK ((BTRFS_SYSTEM_CHUNK_ARRAY_SIZE \ + - 2 * sizeof(struct btrfs_disk_key) \ + - 2 * sizeof(struct btrfs_chunk)) \ + / sizeof(struct btrfs_stripe) + 1) + /* * we need the mirror number and stripe index to be passed around * the call chain while we are processing end_io (especially errors). diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index f141b45ce349..6adee94637a9 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -369,6 +369,9 @@ static int btrfs_xattr_handler_set(const struct xattr_handler *handler, const char *name, const void *buffer, size_t size, int flags) { + if (btrfs_root_readonly(BTRFS_I(inode)->root)) + return -EROFS; + name = xattr_full_name(handler, name); return btrfs_setxattr(NULL, inode, name, buffer, size, flags); } diff --git a/fs/buffer.c b/fs/buffer.c index 362a86876459..5bc0877f223f 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2321,7 +2321,7 @@ int generic_cont_expand_simple(struct inode *inode, loff_t size) { struct address_space *mapping = inode->i_mapping; struct page *page; - void *fsdata; + void *fsdata = NULL; int err; err = inode_newsize_ok(inode, size); @@ -2347,7 +2347,7 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping, struct inode *inode = mapping->host; unsigned int blocksize = i_blocksize(inode); struct page *page; - void *fsdata; + void *fsdata = NULL; pgoff_t index, curidx; loff_t curpos; unsigned zerofrom, offset, len; @@ -2742,16 +2742,6 @@ int nobh_writepage(struct page *page, get_block_t *get_block, /* Is the page fully outside i_size? (truncate in progress) */ offset = i_size & (PAGE_SIZE-1); if (page->index >= end_index+1 || !offset) { - /* - * The page may have dirty, unmapped buffers. For example, - * they may have been added in ext3_writepage(). Make them - * freeable here, so the page does not leak. - */ -#if 0 - /* Not really sure about this - do we need this ? */ - if (page->mapping->a_ops->invalidatepage) - page->mapping->a_ops->invalidatepage(page, offset); -#endif unlock_page(page); return 0; /* don't care */ } @@ -2946,12 +2936,6 @@ int block_write_full_page(struct page *page, get_block_t *get_block, /* Is the page fully outside i_size? (truncate in progress) */ offset = i_size & (PAGE_SIZE-1); if (page->index >= end_index+1 || !offset) { - /* - * The page may have dirty, unmapped buffers. For example, - * they may have been added in ext3_writepage(). Make them - * freeable here, so the page does not leak. - */ - do_invalidatepage(page, 0, PAGE_SIZE); unlock_page(page); return 0; /* don't care */ } diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c index f822ac9e3cb0..f5bf10729a87 100644 --- a/fs/cachefiles/rdwr.c +++ b/fs/cachefiles/rdwr.c @@ -125,7 +125,7 @@ static int cachefiles_read_reissue(struct cachefiles_object *object, _debug("reissue read"); ret = bmapping->a_ops->readpage(NULL, backpage); if (ret < 0) - goto unlock_discard; + goto discard; } /* but the page may have been read before the monitor was installed, so @@ -142,6 +142,7 @@ static int cachefiles_read_reissue(struct cachefiles_object *object, unlock_discard: unlock_page(backpage); +discard: spin_lock_irq(&object->work_lock); list_del(&monitor->op_link); spin_unlock_irq(&object->work_lock); diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 476728bdae8c..de10899da837 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -75,10 +75,6 @@ static int ceph_set_page_dirty(struct page *page) struct inode *inode; struct ceph_inode_info *ci; struct ceph_snap_context *snapc; - int ret; - - if (unlikely(!mapping)) - return !TestSetPageDirty(page); if (PageDirty(page)) { dout("%p set_page_dirty %p idx %lu -- already dirty\n", @@ -124,11 +120,7 @@ static int ceph_set_page_dirty(struct page *page) page->private = (unsigned long)snapc; SetPagePrivate(page); - ret = __set_page_dirty_nobuffers(page); - WARN_ON(!PageLocked(page)); - WARN_ON(!page->mapping); - - return ret; + return __set_page_dirty_nobuffers(page); } /* @@ -1437,7 +1429,7 @@ static vm_fault_t ceph_filemap_fault(struct vm_fault *vmf) struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_file_info *fi = vma->vm_file->private_data; struct page *pinned_page = NULL; - loff_t off = vmf->pgoff << PAGE_SHIFT; + loff_t off = (loff_t)vmf->pgoff << PAGE_SHIFT; int want, got, err; sigset_t oldset; vm_fault_t ret = VM_FAULT_SIGBUS; diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index c0dbf8b7762b..fcfba2af5f98 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -1047,12 +1047,19 @@ void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release) { struct ceph_mds_session *session = cap->session; struct ceph_inode_info *ci = cap->ci; - struct ceph_mds_client *mdsc = - ceph_sb_to_client(ci->vfs_inode.i_sb)->mdsc; + struct ceph_mds_client *mdsc; int removed = 0; + /* 'ci' being NULL means the remove have already occurred */ + if (!ci) { + dout("%s: cap inode is NULL\n", __func__); + return; + } + dout("__ceph_remove_cap %p from %p\n", cap, &ci->vfs_inode); + mdsc = ceph_inode_to_client(&ci->vfs_inode)->mdsc; + /* remove from inode's cap rbtree, and clear auth cap */ rb_erase(&cap->ci_node, &ci->i_caps); if (ci->i_auth_cap == cap) @@ -1547,6 +1554,7 @@ void ceph_flush_snaps(struct ceph_inode_info *ci, struct inode *inode = &ci->vfs_inode; struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc; struct ceph_mds_session *session = NULL; + bool need_put = false; int mds; dout("ceph_flush_snaps %p\n", inode); @@ -1600,8 +1608,13 @@ out: } /* we flushed them all; remove this inode from the queue */ spin_lock(&mdsc->snap_flush_lock); + if (!list_empty(&ci->i_snap_flush_item)) + need_put = true; list_del_init(&ci->i_snap_flush_item); spin_unlock(&mdsc->snap_flush_lock); + + if (need_put) + iput(inode); } /* @@ -1767,11 +1780,14 @@ static int __mark_caps_flushing(struct inode *inode, * try to invalidate mapping pages without blocking. */ static int try_nonblocking_invalidate(struct inode *inode) + __releases(ci->i_ceph_lock) + __acquires(ci->i_ceph_lock) { struct ceph_inode_info *ci = ceph_inode(inode); u32 invalidating_gen = ci->i_rdcache_gen; spin_unlock(&ci->i_ceph_lock); + ceph_fscache_invalidate(inode); invalidate_mapping_pages(&inode->i_data, 0, -1); spin_lock(&ci->i_ceph_lock); @@ -3269,6 +3285,15 @@ static void handle_cap_grant(struct inode *inode, } BUG_ON(cap->issued & ~cap->implemented); + /* don't let check_caps skip sending a response to MDS for revoke msgs */ + if (le32_to_cpu(grant->op) == CEPH_CAP_OP_REVOKE) { + cap->mds_wanted = 0; + if (cap == ci->i_auth_cap) + check_caps = 1; /* check auth cap only */ + else + check_caps = 2; /* check all caps */ + } + if (extra_info->inline_version > 0 && extra_info->inline_version >= ci->i_inline_version) { ci->i_inline_version = extra_info->inline_version; diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c index abdf98deeec4..e6b7d43b5077 100644 --- a/fs/ceph/debugfs.c +++ b/fs/ceph/debugfs.c @@ -251,7 +251,7 @@ int ceph_fs_debugfs_init(struct ceph_fs_client *fsc) goto out; snprintf(name, sizeof(name), "../../bdi/%s", - dev_name(fsc->sb->s_bdi->dev)); + bdi_dev_name(fsc->sb->s_bdi)); fsc->debugfs_bdi = debugfs_create_symlink("bdi", fsc->client->debugfs_dir, diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 4ce2752c8b71..95d7906fb9ea 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -446,6 +446,12 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry, if (dentry->d_name.len > NAME_MAX) return -ENAMETOOLONG; + /* + * Do not truncate the file, since atomic_open is called before the + * permission check. The caller will do the truncation afterward. + */ + flags &= ~O_TRUNC; + if (flags & O_CREAT) { if (ceph_quota_is_max_files_exceeded(dir)) return -EDQUOT; @@ -478,9 +484,7 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry, req->r_parent = dir; set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags); - err = ceph_mdsc_do_request(mdsc, - (flags & (O_CREAT|O_TRUNC)) ? dir : NULL, - req); + err = ceph_mdsc_do_request(mdsc, (flags & O_CREAT) ? dir : NULL, req); err = ceph_handle_snapdir(req, dentry, err); if (err) goto out_req; diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 3c24fb77ef32..d6f181e3c1ac 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -631,9 +631,7 @@ int ceph_fill_file_size(struct inode *inode, int issued, ci->i_truncate_seq = truncate_seq; /* the MDS should have revoked these caps */ - WARN_ON_ONCE(issued & (CEPH_CAP_FILE_EXCL | - CEPH_CAP_FILE_RD | - CEPH_CAP_FILE_WR | + WARN_ON_ONCE(issued & (CEPH_CAP_FILE_RD | CEPH_CAP_FILE_LAZYIO)); /* * If we hold relevant caps, or in the case where we're @@ -1823,6 +1821,7 @@ static void ceph_invalidate_work(struct work_struct *work) orig_gen = ci->i_rdcache_gen; spin_unlock(&ci->i_ceph_lock); + ceph_fscache_invalidate(inode); if (invalidate_inode_pages2(inode->i_mapping) < 0) { pr_err("invalidate_pages %p fails\n", inode); } diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index 5cf7b5f4db94..4f727f2c98db 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -623,8 +623,10 @@ int __ceph_finish_cap_snap(struct ceph_inode_info *ci, capsnap->size); spin_lock(&mdsc->snap_flush_lock); - if (list_empty(&ci->i_snap_flush_item)) + if (list_empty(&ci->i_snap_flush_item)) { + ihold(inode); list_add_tail(&ci->i_snap_flush_item, &mdsc->snap_flush_list); + } spin_unlock(&mdsc->snap_flush_lock); return 1; /* caller may want to ceph_flush_snaps */ } @@ -671,14 +673,17 @@ int ceph_update_snap_trace(struct ceph_mds_client *mdsc, struct ceph_mds_snap_realm *ri; /* encoded */ __le64 *snaps; /* encoded */ __le64 *prior_parent_snaps; /* encoded */ - struct ceph_snap_realm *realm = NULL; + struct ceph_snap_realm *realm; struct ceph_snap_realm *first_realm = NULL; - int invalidate = 0; + struct ceph_snap_realm *realm_to_rebuild = NULL; + int rebuild_snapcs; int err = -ENOMEM; LIST_HEAD(dirty_realms); dout("update_snap_trace deletion=%d\n", deletion); more: + realm = NULL; + rebuild_snapcs = 0; ceph_decode_need(&p, e, sizeof(*ri), bad); ri = p; p += sizeof(*ri); @@ -702,7 +707,7 @@ more: err = adjust_snap_realm_parent(mdsc, realm, le64_to_cpu(ri->parent)); if (err < 0) goto fail; - invalidate += err; + rebuild_snapcs += err; if (le64_to_cpu(ri->seq) > realm->seq) { dout("update_snap_trace updating %llx %p %lld -> %lld\n", @@ -727,22 +732,30 @@ more: if (realm->seq > mdsc->last_snap_seq) mdsc->last_snap_seq = realm->seq; - invalidate = 1; + rebuild_snapcs = 1; } else if (!realm->cached_context) { dout("update_snap_trace %llx %p seq %lld new\n", realm->ino, realm, realm->seq); - invalidate = 1; + rebuild_snapcs = 1; } else { dout("update_snap_trace %llx %p seq %lld unchanged\n", realm->ino, realm, realm->seq); } - dout("done with %llx %p, invalidated=%d, %p %p\n", realm->ino, - realm, invalidate, p, e); + dout("done with %llx %p, rebuild_snapcs=%d, %p %p\n", realm->ino, + realm, rebuild_snapcs, p, e); + + /* + * this will always track the uppest parent realm from which + * we need to rebuild the snapshot contexts _downward_ in + * hierarchy. + */ + if (rebuild_snapcs) + realm_to_rebuild = realm; - /* invalidate when we reach the _end_ (root) of the trace */ - if (invalidate && p >= e) - rebuild_snap_realms(realm, &dirty_realms); + /* rebuild_snapcs when we reach the _end_ (root) of the trace */ + if (realm_to_rebuild && p >= e) + rebuild_snap_realms(realm_to_rebuild, &dirty_realms); if (!first_realm) first_realm = realm; @@ -965,6 +978,19 @@ skip_inode: continue; adjust_snap_realm_parent(mdsc, child, realm->ino); } + } else { + /* + * In the non-split case both 'num_split_inos' and + * 'num_split_realms' should be 0, making this a no-op. + * However the MDS happens to populate 'split_realms' list + * in one of the UPDATE op cases by mistake. + * + * Skip both lists just in case to ensure that 'p' is + * positioned at the start of realm info, as expected by + * ceph_update_snap_trace(). + */ + p += sizeof(u64) * num_split_inos; + p += sizeof(u64) * num_split_realms; } /* diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c index a09ce27ab220..6fa9a784676b 100644 --- a/fs/ceph/xattr.c +++ b/fs/ceph/xattr.c @@ -273,6 +273,14 @@ static size_t ceph_vxattrcb_quota_max_files(struct ceph_inode_info *ci, } #define XATTR_RSTAT_FIELD(_type, _name) \ XATTR_NAME_CEPH(_type, _name, VXATTR_FLAG_RSTAT) +#define XATTR_RSTAT_FIELD_UPDATABLE(_type, _name) \ + { \ + .name = CEPH_XATTR_NAME(_type, _name), \ + .name_size = sizeof (CEPH_XATTR_NAME(_type, _name)), \ + .getxattr_cb = ceph_vxattrcb_ ## _type ## _ ## _name, \ + .exists_cb = NULL, \ + .flags = VXATTR_FLAG_RSTAT, \ + } #define XATTR_LAYOUT_FIELD(_type, _name, _field) \ { \ .name = CEPH_XATTR_NAME2(_type, _name, _field), \ @@ -310,7 +318,7 @@ static struct ceph_vxattr ceph_dir_vxattrs[] = { XATTR_RSTAT_FIELD(dir, rfiles), XATTR_RSTAT_FIELD(dir, rsubdirs), XATTR_RSTAT_FIELD(dir, rbytes), - XATTR_RSTAT_FIELD(dir, rctime), + XATTR_RSTAT_FIELD_UPDATABLE(dir, rctime), { .name = "ceph.quota", .name_size = sizeof("ceph.quota"), diff --git a/fs/char_dev.c b/fs/char_dev.c index 5fffd5050fb7..2c3d519b21c2 100644 --- a/fs/char_dev.c +++ b/fs/char_dev.c @@ -553,7 +553,7 @@ int cdev_device_add(struct cdev *cdev, struct device *dev) } rc = device_add(dev); - if (rc) + if (rc && dev->devt) cdev_del(cdev); return rc; diff --git a/fs/cifs/asn1.c b/fs/cifs/asn1.c index 3d19595eb352..4a9b53229fba 100644 --- a/fs/cifs/asn1.c +++ b/fs/cifs/asn1.c @@ -541,8 +541,8 @@ decode_negTokenInit(unsigned char *security_blob, int length, return 0; } else if ((cls != ASN1_CTX) || (con != ASN1_CON) || (tag != ASN1_EOC)) { - cifs_dbg(FYI, "cls = %d con = %d tag = %d end = %p (%d) exit 0\n", - cls, con, tag, end, *end); + cifs_dbg(FYI, "cls = %d con = %d tag = %d end = %p exit 0\n", + cls, con, tag, end); return 0; } @@ -552,8 +552,8 @@ decode_negTokenInit(unsigned char *security_blob, int length, return 0; } else if ((cls != ASN1_UNI) || (con != ASN1_CON) || (tag != ASN1_SEQ)) { - cifs_dbg(FYI, "cls = %d con = %d tag = %d end = %p (%d) exit 1\n", - cls, con, tag, end, *end); + cifs_dbg(FYI, "cls = %d con = %d tag = %d end = %p exit 1\n", + cls, con, tag, end); return 0; } @@ -563,8 +563,8 @@ decode_negTokenInit(unsigned char *security_blob, int length, return 0; } else if ((cls != ASN1_CTX) || (con != ASN1_CON) || (tag != ASN1_EOC)) { - cifs_dbg(FYI, "cls = %d con = %d tag = %d end = %p (%d) exit 0\n", - cls, con, tag, end, *end); + cifs_dbg(FYI, "cls = %d con = %d tag = %d end = %p exit 0\n", + cls, con, tag, end); return 0; } @@ -575,8 +575,8 @@ decode_negTokenInit(unsigned char *security_blob, int length, return 0; } else if ((cls != ASN1_UNI) || (con != ASN1_CON) || (tag != ASN1_SEQ)) { - cifs_dbg(FYI, "cls = %d con = %d tag = %d end = %p (%d) exit 1\n", - cls, con, tag, end, *end); + cifs_dbg(FYI, "cls = %d con = %d tag = %d sequence_end = %p exit 1\n", + cls, con, tag, sequence_end); return 0; } diff --git a/fs/cifs/cifs_spnego.c b/fs/cifs/cifs_spnego.c index 7f01c6e60791..6eb65988321f 100644 --- a/fs/cifs/cifs_spnego.c +++ b/fs/cifs/cifs_spnego.c @@ -76,8 +76,8 @@ struct key_type cifs_spnego_key_type = { * strlen(";sec=ntlmsspi") */ #define MAX_MECH_STR_LEN 13 -/* strlen of "host=" */ -#define HOST_KEY_LEN 5 +/* strlen of ";host=" */ +#define HOST_KEY_LEN 6 /* strlen of ";ip4=" or ";ip6=" */ #define IP_KEY_LEN 5 diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c index a2b2355e7f01..7932e20555d2 100644 --- a/fs/cifs/cifs_unicode.c +++ b/fs/cifs/cifs_unicode.c @@ -371,14 +371,9 @@ cifs_strndup_from_utf16(const char *src, const int maxlen, if (!dst) return NULL; cifs_from_utf16(dst, (__le16 *) src, len, maxlen, codepage, - NO_MAP_UNI_RSVD); + NO_MAP_UNI_RSVD); } else { - len = strnlen(src, maxlen); - len++; - dst = kmalloc(len, GFP_KERNEL); - if (!dst) - return NULL; - strlcpy(dst, src, len); + dst = kstrndup(src, maxlen, GFP_KERNEL); } return dst; @@ -501,7 +496,13 @@ cifsConvertToUTF16(__le16 *target, const char *source, int srclen, else if (map_chars == SFM_MAP_UNI_RSVD) { bool end_of_string; - if (i == srclen - 1) + /** + * Remap spaces and periods found at the end of every + * component of the path. The special cases of '.' and + * '..' do not need to be dealt with explicitly because + * they are addressed in namei.c:link_path_walk(). + **/ + if ((i == srclen - 1) || (source[i+1] == '\\')) end_of_string = true; else end_of_string = false; diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index d5457015801d..7c9e5ed1644b 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -229,7 +229,7 @@ cifs_statfs(struct dentry *dentry, struct kstatfs *buf) rc = server->ops->queryfs(xid, tcon, buf); free_xid(xid); - return 0; + return rc; } static long cifs_fallocate(struct file *file, int mode, loff_t off, loff_t len) @@ -663,11 +663,6 @@ cifs_get_root(struct smb_vol *vol, struct super_block *sb) struct inode *dir = d_inode(dentry); struct dentry *child; - if (!dir) { - dput(dentry); - dentry = ERR_PTR(-ENOENT); - break; - } if (!S_ISDIR(dir->i_mode)) { dput(dentry); dentry = ERR_PTR(-ENOTDIR); @@ -684,7 +679,7 @@ cifs_get_root(struct smb_vol *vol, struct super_block *sb) while (*s && *s != sep) s++; - child = lookup_one_len_unlocked(p, dentry, s - p); + child = lookup_positive_unlocked(p, dentry, s - p); dput(dentry); dentry = child; } while (!IS_ERR(dentry)); @@ -779,6 +774,7 @@ cifs_smb3_do_mount(struct file_system_type *fs_type, out_super: deactivate_locked_super(sb); + return root; out: cifs_cleanup_volume_info(volume_info); return root; @@ -812,7 +808,7 @@ cifs_loose_read_iter(struct kiocb *iocb, struct iov_iter *iter) ssize_t rc; struct inode *inode = file_inode(iocb->ki_filp); - if (iocb->ki_filp->f_flags & O_DIRECT) + if (iocb->ki_flags & IOCB_DIRECT) return cifs_user_readv(iocb, iter); rc = cifs_revalidate_mapping(inode); @@ -974,6 +970,7 @@ const struct inode_operations cifs_file_inode_ops = { const struct inode_operations cifs_symlink_inode_ops = { .get_link = cifs_get_link, + .setattr = cifs_setattr, .permission = cifs_permission, .listxattr = cifs_listxattr, }; diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index f047e87871a1..c1d5daa4b351 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -121,7 +121,10 @@ extern const struct dentry_operations cifs_ci_dentry_ops; #ifdef CONFIG_CIFS_DFS_UPCALL extern struct vfsmount *cifs_dfs_d_automount(struct path *path); #else -#define cifs_dfs_d_automount NULL +static inline struct vfsmount *cifs_dfs_d_automount(struct path *path) +{ + return ERR_PTR(-EREMOTE); +} #endif /* Functions related to symlinks */ diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index cb70f0c6aa1b..d16fd8d1f291 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -4895,8 +4895,13 @@ CIFSGetDFSRefer(const unsigned int xid, struct cifs_ses *ses, return -ENODEV; getDFSRetry: - rc = smb_init(SMB_COM_TRANSACTION2, 15, ses->tcon_ipc, (void **) &pSMB, - (void **) &pSMBr); + /* + * Use smb_init_no_reconnect() instead of smb_init() as + * CIFSGetDFSRefer() may be called from cifs_reconnect_tcon() and thus + * causing an infinite recursion. + */ + rc = smb_init_no_reconnect(SMB_COM_TRANSACTION2, 15, ses->tcon_ipc, + (void **)&pSMB, (void **)&pSMBr); if (rc) return rc; diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 6335ca143292..37e91f27f49b 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -429,7 +429,8 @@ cifs_reconnect(struct TCP_Server_Info *server) server->ssocket->state, server->ssocket->flags); sock_release(server->ssocket); server->ssocket = NULL; - } + } else if (cifs_rdma_enabled(server)) + smbd_destroy(server); server->sequence_number = 0; server->session_estab = false; kfree(server->session_key.response); @@ -777,6 +778,8 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server) list_del_init(&server->tcp_ses_list); spin_unlock(&cifs_tcp_ses_lock); + cancel_delayed_work_sync(&server->echo); + spin_lock(&GlobalMid_Lock); server->tcpStatus = CifsExiting; spin_unlock(&GlobalMid_Lock); @@ -797,10 +800,8 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server) wake_up_all(&server->request_q); /* give those requests time to exit */ msleep(125); - if (cifs_rdma_enabled(server) && server->smbd_conn) { - smbd_destroy(server->smbd_conn); - server->smbd_conn = NULL; - } + if (cifs_rdma_enabled(server)) + smbd_destroy(server); if (server->ssocket) { sock_release(server->ssocket); server->ssocket = NULL; @@ -2938,7 +2939,7 @@ cifs_set_cifscreds(struct smb_vol *vol __attribute__((unused)), static struct cifs_ses * cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb_vol *volume_info) { - int rc = -ENOMEM; + int rc = 0; unsigned int xid; struct cifs_ses *ses; struct sockaddr_in *addr = (struct sockaddr_in *)&server->dstaddr; @@ -2980,6 +2981,8 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb_vol *volume_info) return ses; } + rc = -ENOMEM; + cifs_dbg(FYI, "Existing smb sess not found\n"); ses = sesInfoAlloc(); if (ses == NULL) @@ -3372,9 +3375,10 @@ cifs_match_super(struct super_block *sb, void *data) spin_lock(&cifs_tcp_ses_lock); cifs_sb = CIFS_SB(sb); tlink = cifs_get_tlink(cifs_sb_master_tlink(cifs_sb)); - if (IS_ERR(tlink)) { + if (tlink == NULL) { + /* can not match superblock if tlink were ever null */ spin_unlock(&cifs_tcp_ses_lock); - return rc; + return 0; } tcon = tlink_tcon(tlink); ses = tcon->ses; diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index f6e3c0089825..c7e162c9383d 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -840,6 +840,7 @@ static int cifs_d_revalidate(struct dentry *direntry, unsigned int flags) { struct inode *inode; + int rc; if (flags & LOOKUP_RCU) return -ECHILD; @@ -849,8 +850,25 @@ cifs_d_revalidate(struct dentry *direntry, unsigned int flags) if ((flags & LOOKUP_REVAL) && !CIFS_CACHE_READ(CIFS_I(inode))) CIFS_I(inode)->time = 0; /* force reval */ - if (cifs_revalidate_dentry(direntry)) - return 0; + rc = cifs_revalidate_dentry(direntry); + if (rc) { + cifs_dbg(FYI, "cifs_revalidate_dentry failed with rc=%d", rc); + switch (rc) { + case -ENOENT: + case -ESTALE: + /* + * Those errors mean the dentry is invalid + * (file was deleted or recreated) + */ + return 0; + default: + /* + * Otherwise some unexpected error happened + * report it as-is to VFS layer + */ + return rc; + } + } else { /* * If the inode wasn't known to be a dfs entry when diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 5cb15649adb0..0613b86cc3fd 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -163,6 +163,7 @@ int cifs_posix_open(char *full_path, struct inode **pinode, goto posix_open_ret; } } else { + cifs_revalidate_mapping(*pinode); cifs_fattr_to_inode(*pinode, &fattr); } @@ -3990,9 +3991,9 @@ static int cifs_readpage_worker(struct file *file, struct page *page, io_error: kunmap(page); - unlock_page(page); read_complete: + unlock_page(page); return rc; } diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 4a38f16d944d..d30eb4350656 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -2550,13 +2550,18 @@ cifs_setattr(struct dentry *direntry, struct iattr *attrs) { struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb); struct cifs_tcon *pTcon = cifs_sb_master_tcon(cifs_sb); + int rc, retries = 0; - if (pTcon->unix_ext) - return cifs_setattr_unix(direntry, attrs); - - return cifs_setattr_nounix(direntry, attrs); + do { + if (pTcon->unix_ext) + rc = cifs_setattr_unix(direntry, attrs); + else + rc = cifs_setattr_nounix(direntry, attrs); + retries++; + } while (is_retryable_error(rc) && retries < 2); /* BB: add cifs_setattr_legacy for really old servers */ + return rc; } #if 0 diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c index 54f32f9143a9..5a7020e767e4 100644 --- a/fs/cifs/ioctl.c +++ b/fs/cifs/ioctl.c @@ -149,7 +149,7 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) rc = put_user(ExtAttrBits & FS_FL_USER_VISIBLE, (int __user *)arg); - if (rc != EOPNOTSUPP) + if (rc != -EOPNOTSUPP) break; } #endif /* CONFIG_CIFS_POSIX */ @@ -178,7 +178,7 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) * pSMBFile->fid.netfid, * extAttrBits, * &ExtAttrMask); - * if (rc != EOPNOTSUPP) + * if (rc != -EOPNOTSUPP) * break; */ diff --git a/fs/cifs/link.c b/fs/cifs/link.c index 2148b0f60e5e..f590149e21ba 100644 --- a/fs/cifs/link.c +++ b/fs/cifs/link.c @@ -97,6 +97,9 @@ parse_mf_symlink(const u8 *buf, unsigned int buf_len, unsigned int *_link_len, if (rc != 1) return -EINVAL; + if (link_len > CIFS_MF_SYMLINK_LINK_MAXLEN) + return -EINVAL; + rc = symlink_hash(link_len, link_str, md5_hash); if (rc) { cifs_dbg(FYI, "%s: MD5 hash failure: %d\n", __func__, rc); @@ -478,6 +481,7 @@ smb3_create_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, oparms.disposition = FILE_CREATE; oparms.fid = &fid; oparms.reconnect = false; + oparms.mode = 0644; rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL, NULL); diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index dd67f56ea61e..c9ebfff5190a 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -338,6 +338,10 @@ checkSMB(char *buf, unsigned int total_read, struct TCP_Server_Info *server) cifs_dbg(VFS, "Length less than smb header size\n"); } return -EIO; + } else if (total_read < sizeof(*smb) + 2 * smb->WordCount) { + cifs_dbg(VFS, "%s: can't read BCC due to invalid WordCount(%u)\n", + __func__, smb->WordCount); + return -EIO; } /* otherwise, there is enough to get to the BCC */ diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index aa23c00367ec..0113dba28eb0 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -602,7 +602,7 @@ sess_alloc_buffer(struct sess_data *sess_data, int wct) return 0; out_free_smb_buf: - kfree(smb_buf); + cifs_small_buf_release(smb_buf); sess_data->iov[0].iov_base = NULL; sess_data->iov[0].iov_len = 0; sess_data->buf0_type = CIFS_NO_BUFFER; diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index 7d875a47d022..d3d5d2c6c401 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -302,6 +302,9 @@ static const bool has_smb2_data_area[NUMBER_OF_SMB2_COMMANDS] = { char * smb2_get_data_area_len(int *off, int *len, struct smb2_sync_hdr *shdr) { + const int max_off = 4096; + const int max_len = 128 * 1024; + *off = 0; *len = 0; @@ -369,29 +372,20 @@ smb2_get_data_area_len(int *off, int *len, struct smb2_sync_hdr *shdr) * Invalid length or offset probably means data area is invalid, but * we have little choice but to ignore the data area in this case. */ - if (*off > 4096) { - cifs_dbg(VFS, "offset %d too large, data area ignored\n", *off); - *len = 0; + if (unlikely(*off < 0 || *off > max_off || + *len < 0 || *len > max_len)) { + cifs_dbg(VFS, "%s: invalid data area (off=%d len=%d)\n", + __func__, *off, *len); *off = 0; - } else if (*off < 0) { - cifs_dbg(VFS, "negative offset %d to data invalid ignore data area\n", - *off); - *off = 0; - *len = 0; - } else if (*len < 0) { - cifs_dbg(VFS, "negative data length %d invalid, data area ignored\n", - *len); *len = 0; - } else if (*len > 128 * 1024) { - cifs_dbg(VFS, "data area larger than 128K: %d\n", *len); + } else if (*off == 0) { *len = 0; } /* return pointer to beginning of data area, ie offset from SMB start */ - if ((*off != 0) && (*len != 0)) + if (*off > 0 && *len > 0) return (char *)shdr + *off; - else - return NULL; + return NULL; } /* @@ -738,8 +732,8 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server) } } spin_unlock(&cifs_tcp_ses_lock); - cifs_dbg(FYI, "Can not process oplock break for non-existent connection\n"); - return false; + cifs_dbg(FYI, "No file id matched, oplock break ignored\n"); + return true; } void diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 3d63c76ed098..01ab4496cb89 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -79,6 +79,7 @@ smb2_add_credits(struct TCP_Server_Info *server, const unsigned int add, *val = 65000; /* Don't get near 64K credits, avoid srv bugs */ printk_once(KERN_WARNING "server overflowed SMB3 credits\n"); } + WARN_ON_ONCE(server->in_flight == 0); server->in_flight--; if (server->in_flight == 0 && (optype & CIFS_OP_MASK) != CIFS_NEG_OP) rc = change_conf(server); @@ -366,7 +367,8 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf, goto out; } - if (bytes_left || p->Next) + /* Azure rounds the buffer size up 8, to a 16 byte boundary */ + if ((bytes_left > 8) || p->Next) cifs_dbg(VFS, "%s: incomplete interface info\n", __func__); @@ -385,8 +387,8 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf, p = buf; while (bytes_left >= sizeof(*p)) { info->speed = le64_to_cpu(p->LinkSpeed); - info->rdma_capable = le32_to_cpu(p->Capability & RDMA_CAPABLE); - info->rss_capable = le32_to_cpu(p->Capability & RSS_CAPABLE); + info->rdma_capable = le32_to_cpu(p->Capability & RDMA_CAPABLE) ? 1 : 0; + info->rss_capable = le32_to_cpu(p->Capability & RSS_CAPABLE) ? 1 : 0; cifs_dbg(FYI, "%s: adding iface %zu\n", __func__, *iface_count); cifs_dbg(FYI, "%s: speed %zu bps\n", __func__, info->speed); @@ -474,7 +476,7 @@ SMB3_request_interfaces(const unsigned int xid, struct cifs_tcon *tcon) if (rc == -EOPNOTSUPP) { cifs_dbg(FYI, "server does not support query network interfaces\n"); - goto out; + ret_data_len = 0; } else if (rc != 0) { cifs_dbg(VFS, "error %d on ioctl to get interface list\n", rc); goto out; @@ -761,9 +763,7 @@ move_smb2_ea_to_cifs(char *dst, size_t dst_size, size_t name_len, value_len, user_name_len; while (src_size > 0) { - name = &src->ea_data[0]; name_len = (size_t)src->ea_name_length; - value = &src->ea_data[src->ea_name_length + 1]; value_len = (size_t)le16_to_cpu(src->ea_value_length); if (name_len == 0) { @@ -776,6 +776,9 @@ move_smb2_ea_to_cifs(char *dst, size_t dst_size, goto out; } + name = &src->ea_data[0]; + value = &src->ea_data[src->ea_name_length + 1]; + if (ea_name) { if (ea_name_len == name_len && memcmp(ea_name, name, name_len) == 0) { @@ -1143,9 +1146,17 @@ smb2_copychunk_range(const unsigned int xid, int chunks_copied = 0; bool chunk_sizes_updated = false; ssize_t bytes_written, total_bytes_written = 0; + struct inode *inode; pcchunk = kmalloc(sizeof(struct copychunk_ioctl), GFP_KERNEL); + /* + * We need to flush all unwritten data before we can send the + * copychunk ioctl to the server. + */ + inode = d_inode(trgtfile->dentry); + filemap_write_and_wait(inode->i_mapping); + if (pcchunk == NULL) return -ENOMEM; @@ -1170,9 +1181,11 @@ smb2_copychunk_range(const unsigned int xid, pcchunk->SourceOffset = cpu_to_le64(src_off); pcchunk->TargetOffset = cpu_to_le64(dest_off); pcchunk->Length = - cpu_to_le32(min_t(u32, len, tcon->max_bytes_chunk)); + cpu_to_le32(min_t(u64, len, tcon->max_bytes_chunk)); /* Request server copy to target from src identified by key */ + kfree(retbuf); + retbuf = NULL; rc = SMB2_ioctl(xid, tcon, trgtfile->fid.persistent_fid, trgtfile->fid.volatile_fid, FSCTL_SRV_COPYCHUNK_WRITE, true /* is_fsctl */, (char *)pcchunk, @@ -2699,7 +2712,7 @@ smb2_get_enc_key(struct TCP_Server_Info *server, __u64 ses_id, int enc, u8 *key) } spin_unlock(&cifs_tcp_ses_lock); - return 1; + return -EAGAIN; } /* * Encrypt or decrypt @rqst message. @rqst[0] has the following format: @@ -2730,7 +2743,7 @@ crypt_message(struct TCP_Server_Info *server, int num_rqst, if (rc) { cifs_dbg(VFS, "%s: Could not get %scryption key\n", __func__, enc ? "en" : "de"); - return 0; + return rc; } rc = smb3_crypto_aead_allocate(server); diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 379ac8caa29a..50c6405befc4 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -265,6 +265,9 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon) rc = -EHOSTDOWN; mutex_unlock(&tcon->ses->session_mutex); goto failed; + } else if (rc) { + mutex_unlock(&ses->session_mutex); + goto out; } } if (rc || !tcon->need_reconnect) { @@ -406,8 +409,8 @@ build_preauth_ctxt(struct smb2_preauth_neg_context *pneg_ctxt) pneg_ctxt->ContextType = SMB2_PREAUTH_INTEGRITY_CAPABILITIES; pneg_ctxt->DataLength = cpu_to_le16(38); pneg_ctxt->HashAlgorithmCount = cpu_to_le16(1); - pneg_ctxt->SaltLength = cpu_to_le16(SMB311_SALT_SIZE); - get_random_bytes(pneg_ctxt->Salt, SMB311_SALT_SIZE); + pneg_ctxt->SaltLength = cpu_to_le16(SMB311_LINUX_CLIENT_SALT_SIZE); + get_random_bytes(pneg_ctxt->Salt, SMB311_LINUX_CLIENT_SALT_SIZE); pneg_ctxt->HashAlgorithms = SMB2_PREAUTH_INTEGRITY_SHA512; } @@ -461,6 +464,9 @@ static void decode_preauth_context(struct smb2_preauth_neg_context *ctxt) if (len < MIN_PREAUTH_CTXT_DATA_LEN) { printk_once(KERN_WARNING "server sent bad preauth context\n"); return; + } else if (len < MIN_PREAUTH_CTXT_DATA_LEN + le16_to_cpu(ctxt->SaltLength)) { + pr_warn_once("server sent invalid SaltLength\n"); + return; } if (le16_to_cpu(ctxt->HashAlgorithmCount) != 1) printk_once(KERN_WARNING "illegal SMB3 hash algorithm count\n"); @@ -788,6 +794,13 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses) /* Internal types */ server->capabilities |= SMB2_NT_FIND | SMB2_LARGE_FILES; + /* + * SMB3.0 supports only 1 cipher and doesn't have a encryption neg context + * Set the cipher type manually. + */ + if (server->dialect == SMB30_PROT_ID && (server->capabilities & SMB2_GLOBAL_CAP_ENCRYPTION)) + server->cipher_type = SMB2_ENCRYPTION_AES128_CCM; + security_blob = smb2_get_data_area_len(&blob_offset, &blob_length, (struct smb2_sync_hdr *)rsp); /* @@ -3114,10 +3127,10 @@ smb2_new_read_req(void **buf, unsigned int *total_len, * Related requests use info from previous read request * in chain. */ - shdr->SessionId = 0xFFFFFFFF; + shdr->SessionId = 0xFFFFFFFFFFFFFFFF; shdr->TreeId = 0xFFFFFFFF; - req->PersistentFileId = 0xFFFFFFFF; - req->VolatileFileId = 0xFFFFFFFF; + req->PersistentFileId = 0xFFFFFFFFFFFFFFFF; + req->VolatileFileId = 0xFFFFFFFFFFFFFFFF; } } if (remaining_bytes > io_parms->length) @@ -3139,12 +3152,15 @@ smb2_readv_callback(struct mid_q_entry *mid) (struct smb2_sync_hdr *)rdata->iov[0].iov_base; unsigned int credits_received = 0; struct smb_rqst rqst = { .rq_iov = &rdata->iov[1], - .rq_nvec = 1, - .rq_pages = rdata->pages, - .rq_offset = rdata->page_offset, - .rq_npages = rdata->nr_pages, - .rq_pagesz = rdata->pagesz, - .rq_tailsz = rdata->tailsz }; + .rq_nvec = 1, }; + + if (rdata->got_bytes) { + rqst.rq_pages = rdata->pages; + rqst.rq_offset = rdata->page_offset; + rqst.rq_npages = rdata->nr_pages; + rqst.rq_pagesz = rdata->pagesz; + rqst.rq_tailsz = rdata->tailsz; + } cifs_dbg(FYI, "%s: mid=%llu state=%d result=%d bytes=%u\n", __func__, mid->mid, mid->mid_state, rdata->result, diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index 44501f8cbd75..dd6e749b2400 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -222,7 +222,7 @@ struct smb2_negotiate_req { __le32 NegotiateContextOffset; /* SMB3.1.1 only. MBZ earlier */ __le16 NegotiateContextCount; /* SMB3.1.1 only. MBZ earlier */ __le16 Reserved2; - __le16 Dialects[1]; /* One dialect (vers=) at a time for now */ + __le16 Dialects[4]; /* BB expand this if autonegotiate > 4 dialects */ } __packed; /* Dialects */ @@ -257,12 +257,20 @@ struct smb2_neg_context { /* Followed by array of data */ } __packed; -#define SMB311_SALT_SIZE 32 +#define SMB311_LINUX_CLIENT_SALT_SIZE 32 /* Hash Algorithm Types */ #define SMB2_PREAUTH_INTEGRITY_SHA512 cpu_to_le16(0x0001) #define SMB2_PREAUTH_HASH_SIZE 64 -#define MIN_PREAUTH_CTXT_DATA_LEN (SMB311_SALT_SIZE + 6) +/* + * SaltLength that the server send can be zero, so the only three required + * fields (all __le16) end up six bytes total, so the minimum context data len + * in the response is six bytes which accounts for + * + * HashAlgorithmCount, SaltLength, and 1 HashAlgorithm. + */ +#define MIN_PREAUTH_CTXT_DATA_LEN 6 + struct smb2_preauth_neg_context { __le16 ContextType; /* 1 */ __le16 DataLength; @@ -270,7 +278,7 @@ struct smb2_preauth_neg_context { __le16 HashAlgorithmCount; /* 1 */ __le16 SaltLength; __le16 HashAlgorithms; /* HashAlgorithms[0] since only one defined */ - __u8 Salt[SMB311_SALT_SIZE]; + __u8 Salt[SMB311_LINUX_CLIENT_SALT_SIZE]; } __packed; /* Encryption Algorithms Ciphers */ @@ -602,7 +610,7 @@ struct smb2_tree_disconnect_rsp { #define SMB2_CREATE_SD_BUFFER "SecD" /* security descriptor */ #define SMB2_CREATE_DURABLE_HANDLE_REQUEST "DHnQ" #define SMB2_CREATE_DURABLE_HANDLE_RECONNECT "DHnC" -#define SMB2_CREATE_ALLOCATION_SIZE "AISi" +#define SMB2_CREATE_ALLOCATION_SIZE "AlSi" #define SMB2_CREATE_QUERY_MAXIMAL_ACCESS_REQUEST "MxAc" #define SMB2_CREATE_TIMEWARP_REQUEST "TWrp" #define SMB2_CREATE_QUERY_ON_DISK_ID "QFid" diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c index 784628ec4bc4..117dc475bea8 100644 --- a/fs/cifs/smbdirect.c +++ b/fs/cifs/smbdirect.c @@ -320,6 +320,9 @@ static int smbd_conn_upcall( info->transport_status = SMBD_DISCONNECTED; smbd_process_disconnected(info); + wake_up(&info->disconn_wait); + wake_up_interruptible(&info->wait_reassembly_queue); + wake_up_interruptible_all(&info->wait_send_queue); break; default: @@ -703,8 +706,13 @@ static struct rdma_cm_id *smbd_create_id( log_rdma_event(ERR, "rdma_resolve_addr() failed %i\n", rc); goto out; } - wait_for_completion_interruptible_timeout( + rc = wait_for_completion_interruptible_timeout( &info->ri_done, msecs_to_jiffies(RDMA_RESOLVE_TIMEOUT)); + /* e.g. if interrupted returns -ERESTARTSYS */ + if (rc < 0) { + log_rdma_event(ERR, "rdma_resolve_addr timeout rc: %i\n", rc); + goto out; + } rc = info->ri_rc; if (rc) { log_rdma_event(ERR, "rdma_resolve_addr() completed %i\n", rc); @@ -717,8 +725,13 @@ static struct rdma_cm_id *smbd_create_id( log_rdma_event(ERR, "rdma_resolve_route() failed %i\n", rc); goto out; } - wait_for_completion_interruptible_timeout( + rc = wait_for_completion_interruptible_timeout( &info->ri_done, msecs_to_jiffies(RDMA_RESOLVE_TIMEOUT)); + /* e.g. if interrupted returns -ERESTARTSYS */ + if (rc < 0) { + log_rdma_event(ERR, "rdma_resolve_addr timeout rc: %i\n", rc); + goto out; + } rc = info->ri_rc; if (rc) { log_rdma_event(ERR, "rdma_resolve_route() completed %i\n", rc); @@ -1478,21 +1491,102 @@ static void idle_connection_timer(struct work_struct *work) info->keep_alive_interval*HZ); } -/* Destroy this SMBD connection, called from upper layer */ -void smbd_destroy(struct smbd_connection *info) +/* + * Destroy the transport and related RDMA and memory resources + * Need to go through all the pending counters and make sure on one is using + * the transport while it is destroyed + */ +void smbd_destroy(struct TCP_Server_Info *server) { + struct smbd_connection *info = server->smbd_conn; + struct smbd_response *response; + unsigned long flags; + + if (!info) { + log_rdma_event(INFO, "rdma session already destroyed\n"); + return; + } + log_rdma_event(INFO, "destroying rdma session\n"); + if (info->transport_status != SMBD_DISCONNECTED) { + rdma_disconnect(server->smbd_conn->id); + log_rdma_event(INFO, "wait for transport being disconnected\n"); + wait_event( + info->disconn_wait, + info->transport_status == SMBD_DISCONNECTED); + } - /* Kick off the disconnection process */ - smbd_disconnect_rdma_connection(info); + log_rdma_event(INFO, "destroying qp\n"); + ib_drain_qp(info->id->qp); + rdma_destroy_qp(info->id); + + log_rdma_event(INFO, "cancelling idle timer\n"); + cancel_delayed_work_sync(&info->idle_timer_work); + log_rdma_event(INFO, "cancelling send immediate work\n"); + cancel_delayed_work_sync(&info->send_immediate_work); + + log_rdma_event(INFO, "wait for all send posted to IB to finish\n"); + wait_event(info->wait_send_pending, + atomic_read(&info->send_pending) == 0); + wait_event(info->wait_send_payload_pending, + atomic_read(&info->send_payload_pending) == 0); + + /* It's not posssible for upper layer to get to reassembly */ + log_rdma_event(INFO, "drain the reassembly queue\n"); + do { + spin_lock_irqsave(&info->reassembly_queue_lock, flags); + response = _get_first_reassembly(info); + if (response) { + list_del(&response->list); + spin_unlock_irqrestore( + &info->reassembly_queue_lock, flags); + put_receive_buffer(info, response); + } else + spin_unlock_irqrestore( + &info->reassembly_queue_lock, flags); + } while (response); + info->reassembly_data_length = 0; + + log_rdma_event(INFO, "free receive buffers\n"); + wait_event(info->wait_receive_queues, + info->count_receive_queue + info->count_empty_packet_queue + == info->receive_credit_max); + destroy_receive_buffers(info); + + /* + * For performance reasons, memory registration and deregistration + * are not locked by srv_mutex. It is possible some processes are + * blocked on transport srv_mutex while holding memory registration. + * Release the transport srv_mutex to allow them to hit the failure + * path when sending data, and then release memory registartions. + */ + log_rdma_event(INFO, "freeing mr list\n"); + wake_up_interruptible_all(&info->wait_mr); + while (atomic_read(&info->mr_used_count)) { + mutex_unlock(&server->srv_mutex); + msleep(1000); + mutex_lock(&server->srv_mutex); + } + destroy_mr_list(info); - log_rdma_event(INFO, "wait for transport being destroyed\n"); - wait_event(info->wait_destroy, - info->transport_status == SMBD_DESTROYED); + ib_free_cq(info->send_cq); + ib_free_cq(info->recv_cq); + ib_dealloc_pd(info->pd); + rdma_destroy_id(info->id); + + /* free mempools */ + mempool_destroy(info->request_mempool); + kmem_cache_destroy(info->request_cache); + + mempool_destroy(info->response_mempool); + kmem_cache_destroy(info->response_cache); + + info->transport_status = SMBD_DESTROYED; destroy_workqueue(info->workqueue); log_rdma_event(INFO, "rdma session destroyed\n"); kfree(info); + server->smbd_conn = NULL; } /* @@ -1514,17 +1608,9 @@ int smbd_reconnect(struct TCP_Server_Info *server) */ if (server->smbd_conn->transport_status == SMBD_CONNECTED) { log_rdma_event(INFO, "disconnecting transport\n"); - smbd_disconnect_rdma_connection(server->smbd_conn); + smbd_destroy(server); } - /* wait until the transport is destroyed */ - if (!wait_event_timeout(server->smbd_conn->wait_destroy, - server->smbd_conn->transport_status == SMBD_DESTROYED, 5*HZ)) - return -EAGAIN; - - destroy_workqueue(server->smbd_conn->workqueue); - kfree(server->smbd_conn); - create_conn: log_rdma_event(INFO, "creating rdma session\n"); server->smbd_conn = smbd_get_connection( @@ -1741,12 +1827,13 @@ static struct smbd_connection *_smbd_get_connection( conn_param.retry_count = SMBD_CM_RETRY; conn_param.rnr_retry_count = SMBD_CM_RNR_RETRY; conn_param.flow_control = 0; - init_waitqueue_head(&info->wait_destroy); log_rdma_event(INFO, "connecting to IP %pI4 port %d\n", &addr_in->sin_addr, port); init_waitqueue_head(&info->conn_wait); + init_waitqueue_head(&info->disconn_wait); + init_waitqueue_head(&info->wait_reassembly_queue); rc = rdma_connect(info->id, &conn_param); if (rc) { log_rdma_event(ERR, "rdma_connect() failed with %i\n", rc); @@ -1770,8 +1857,6 @@ static struct smbd_connection *_smbd_get_connection( } init_waitqueue_head(&info->wait_send_queue); - init_waitqueue_head(&info->wait_reassembly_queue); - INIT_DELAYED_WORK(&info->idle_timer_work, idle_connection_timer); INIT_DELAYED_WORK(&info->send_immediate_work, send_immediate_work); queue_delayed_work(info->workqueue, &info->idle_timer_work, @@ -1812,7 +1897,8 @@ static struct smbd_connection *_smbd_get_connection( allocate_mr_failed: /* At this point, need to a full transport shutdown */ - smbd_destroy(info); + server->smbd_conn = info; + smbd_destroy(server); return NULL; negotiation_failed: @@ -2378,6 +2464,7 @@ static int allocate_mr_list(struct smbd_connection *info) atomic_set(&info->mr_ready_count, 0); atomic_set(&info->mr_used_count, 0); init_waitqueue_head(&info->wait_for_mr_cleanup); + INIT_WORK(&info->mr_recovery_work, smbd_mr_recovery_work); /* Allocate more MRs (2x) than hardware responder_resources */ for (i = 0; i < info->responder_resources * 2; i++) { smbdirect_mr = kzalloc(sizeof(*smbdirect_mr), GFP_KERNEL); @@ -2406,13 +2493,13 @@ static int allocate_mr_list(struct smbd_connection *info) list_add_tail(&smbdirect_mr->list, &info->mr_list); atomic_inc(&info->mr_ready_count); } - INIT_WORK(&info->mr_recovery_work, smbd_mr_recovery_work); return 0; out: kfree(smbdirect_mr); list_for_each_entry_safe(smbdirect_mr, tmp, &info->mr_list, list) { + list_del(&smbdirect_mr->list); ib_dereg_mr(smbdirect_mr->mr); kfree(smbdirect_mr->sgl); kfree(smbdirect_mr); diff --git a/fs/cifs/smbdirect.h b/fs/cifs/smbdirect.h index b5c240ff2191..b0ca7df41454 100644 --- a/fs/cifs/smbdirect.h +++ b/fs/cifs/smbdirect.h @@ -71,6 +71,7 @@ struct smbd_connection { struct completion ri_done; wait_queue_head_t conn_wait; wait_queue_head_t wait_destroy; + wait_queue_head_t disconn_wait; struct completion negotiate_completion; bool negotiate_done; @@ -288,7 +289,7 @@ struct smbd_connection *smbd_get_connection( /* Reconnect SMBDirect session */ int smbd_reconnect(struct TCP_Server_Info *server); /* Destroy SMBDirect session */ -void smbd_destroy(struct smbd_connection *info); +void smbd_destroy(struct TCP_Server_Info *server); /* Interface for carrying upper layer I/O through send/recv */ int smbd_recv(struct smbd_connection *info, struct msghdr *msg); @@ -331,7 +332,7 @@ struct smbd_connection {}; static inline void *smbd_get_connection( struct TCP_Server_Info *server, struct sockaddr *dstaddr) {return NULL;} static inline int smbd_reconnect(struct TCP_Server_Info *server) {return -1; } -static inline void smbd_destroy(struct smbd_connection *info) {} +static inline void smbd_destroy(struct TCP_Server_Info *server) {} static inline int smbd_recv(struct smbd_connection *info, struct msghdr *msg) {return -1; } static inline int smbd_send(struct TCP_Server_Info *server, int num_rqst, struct smb_rqst *rqst) {return -1; } #endif diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 70412944b267..3f9029cf09fc 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -168,8 +168,8 @@ smb_send_kvec(struct TCP_Server_Info *server, struct msghdr *smb_msg, *sent = 0; - smb_msg->msg_name = (struct sockaddr *) &server->dstaddr; - smb_msg->msg_namelen = sizeof(struct sockaddr); + smb_msg->msg_name = NULL; + smb_msg->msg_namelen = 0; smb_msg->msg_control = NULL; smb_msg->msg_controllen = 0; if (server->noblocksnd) @@ -891,9 +891,12 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, /* * Compounding is never used during session establish. */ - if ((ses->status == CifsNew) || (optype & CIFS_NEG_OP)) + if ((ses->status == CifsNew) || (optype & CIFS_NEG_OP)) { + mutex_lock(&ses->server->srv_mutex); smb311_update_preauth_hash(ses, rqst[0].rq_iov, rqst[0].rq_nvec); + mutex_unlock(&ses->server->srv_mutex); + } if (timeout == CIFS_ASYNC_OP) goto out; @@ -964,7 +967,9 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, .iov_base = resp_iov[0].iov_base, .iov_len = resp_iov[0].iov_len }; + mutex_lock(&ses->server->srv_mutex); smb311_update_preauth_hash(ses, &iov, 1); + mutex_unlock(&ses->server->srv_mutex); } out: diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index f9628fc20fec..796a6cd5f302 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -50,6 +50,14 @@ DECLARE_RWSEM(configfs_rename_sem); */ DEFINE_SPINLOCK(configfs_dirent_lock); +/* + * All of link_obj/unlink_obj/link_group/unlink_group require that + * subsys->su_mutex is held. + * But parent configfs_subsystem is NULL when config_item is root. + * Use this mutex when config_item is root. + */ +static DEFINE_MUTEX(configfs_subsystem_mutex); + static void configfs_d_iput(struct dentry * dentry, struct inode * inode) { @@ -1937,7 +1945,9 @@ int configfs_register_subsystem(struct configfs_subsystem *subsys) group->cg_item.ci_name = group->cg_item.ci_namebuf; sd = root->d_fsdata; + mutex_lock(&configfs_subsystem_mutex); link_group(to_config_group(sd->s_element), group); + mutex_unlock(&configfs_subsystem_mutex); inode_lock_nested(d_inode(root), I_MUTEX_PARENT); @@ -1962,7 +1972,9 @@ int configfs_register_subsystem(struct configfs_subsystem *subsys) inode_unlock(d_inode(root)); if (err) { + mutex_lock(&configfs_subsystem_mutex); unlink_group(group); + mutex_unlock(&configfs_subsystem_mutex); configfs_release_fs(); } put_fragment(frag); @@ -2008,7 +2020,9 @@ void configfs_unregister_subsystem(struct configfs_subsystem *subsys) dput(dentry); + mutex_lock(&configfs_subsystem_mutex); unlink_group(group); + mutex_unlock(&configfs_subsystem_mutex); configfs_release_fs(); } diff --git a/fs/configfs/file.c b/fs/configfs/file.c index bb0a427517e9..38eb80e29715 100644 --- a/fs/configfs/file.c +++ b/fs/configfs/file.c @@ -392,7 +392,7 @@ static int __configfs_open_file(struct inode *inode, struct file *file, int type attr = to_attr(dentry); if (!attr) - goto out_put_item; + goto out_free_buffer; if (type & CONFIGFS_ITEM_BIN_ATTR) { buffer->bin_attr = to_bin_attr(dentry); @@ -405,7 +405,7 @@ static int __configfs_open_file(struct inode *inode, struct file *file, int type /* Grab the module reference for this attribute if we have one */ error = -ENODEV; if (!try_module_get(buffer->owner)) - goto out_put_item; + goto out_free_buffer; error = -EACCES; if (!buffer->item->ci_type) @@ -449,8 +449,6 @@ static int __configfs_open_file(struct inode *inode, struct file *file, int type out_put_module: module_put(buffer->owner); -out_put_item: - config_item_put(buffer->item); out_free_buffer: up_read(&frag->frag_sem); kfree(buffer); @@ -498,13 +496,13 @@ static int configfs_release_bin_file(struct inode *inode, struct file *file) buffer->bin_buffer_size); } up_read(&frag->frag_sem); - /* vfree on NULL is safe */ - vfree(buffer->bin_buffer); - buffer->bin_buffer = NULL; - buffer->bin_buffer_size = 0; - buffer->needs_read_fill = 1; } + vfree(buffer->bin_buffer); + buffer->bin_buffer = NULL; + buffer->bin_buffer_size = 0; + buffer->needs_read_fill = 1; + configfs_release(inode, file); return 0; } diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c index c83ddff3ff4a..04a3c2c92b21 100644 --- a/fs/crypto/crypto.c +++ b/fs/crypto/crypto.c @@ -314,45 +314,47 @@ int fscrypt_decrypt_page(const struct inode *inode, struct page *page, EXPORT_SYMBOL(fscrypt_decrypt_page); /* - * Validate dentries for encrypted directories to make sure we aren't - * potentially caching stale data after a key has been added or - * removed. + * Validate dentries in encrypted directories to make sure we aren't potentially + * caching stale dentries after a key has been added. */ static int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags) { struct dentry *dir; - int dir_has_key, cached_with_key; + int err; + int valid; + + /* + * Plaintext names are always valid, since fscrypt doesn't support + * reverting to ciphertext names without evicting the directory's inode + * -- which implies eviction of the dentries in the directory. + */ + if (!(dentry->d_flags & DCACHE_ENCRYPTED_NAME)) + return 1; + + /* + * Ciphertext name; valid if the directory's key is still unavailable. + * + * Although fscrypt forbids rename() on ciphertext names, we still must + * use dget_parent() here rather than use ->d_parent directly. That's + * because a corrupted fs image may contain directory hard links, which + * the VFS handles by moving the directory's dentry tree in the dcache + * each time ->lookup() finds the directory and it already has a dentry + * elsewhere. Thus ->d_parent can be changing, and we must safely grab + * a reference to some ->d_parent to prevent it from being freed. + */ if (flags & LOOKUP_RCU) return -ECHILD; dir = dget_parent(dentry); - if (!IS_ENCRYPTED(d_inode(dir))) { - dput(dir); - return 0; - } - - spin_lock(&dentry->d_lock); - cached_with_key = dentry->d_flags & DCACHE_ENCRYPTED_WITH_KEY; - spin_unlock(&dentry->d_lock); - dir_has_key = (d_inode(dir)->i_crypt_info != NULL); + err = fscrypt_get_encryption_info(d_inode(dir)); + valid = !fscrypt_has_encryption_key(d_inode(dir)); dput(dir); - /* - * If the dentry was cached without the key, and it is a - * negative dentry, it might be a valid name. We can't check - * if the key has since been made available due to locking - * reasons, so we fail the validation so ext4_lookup() can do - * this check. - * - * We also fail the validation if the dentry was created with - * the key present, but we no longer have the key, or vice versa. - */ - if ((!cached_with_key && d_is_negative(dentry)) || - (!cached_with_key && dir_has_key) || - (cached_with_key && !dir_has_key)) - return 0; - return 1; + if (err < 0) + return err; + + return valid; } const struct dentry_operations fscrypt_d_ops = { diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c index d7a0f682ca12..052c137f1e70 100644 --- a/fs/crypto/fname.c +++ b/fs/crypto/fname.c @@ -275,13 +275,8 @@ int fscrypt_fname_disk_to_usr(struct inode *inode, oname->name); return 0; } - if (hash) { - digested_name.hash = hash; - digested_name.minor_hash = minor_hash; - } else { - digested_name.hash = 0; - digested_name.minor_hash = 0; - } + digested_name.hash = hash; + digested_name.minor_hash = minor_hash; memcpy(digested_name.digest, FSCRYPT_FNAME_DIGEST(iname->name, iname->len), FSCRYPT_FNAME_DIGEST_SIZE); @@ -354,6 +349,7 @@ int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname, } if (!lookup) return -ENOKEY; + fname->is_ciphertext_name = true; /* * We don't have the key and we are doing a lookup; decode the diff --git a/fs/crypto/hooks.c b/fs/crypto/hooks.c index 926e5df20ec3..ae7a413c0bdd 100644 --- a/fs/crypto/hooks.c +++ b/fs/crypto/hooks.c @@ -49,7 +49,8 @@ int fscrypt_file_open(struct inode *inode, struct file *filp) } EXPORT_SYMBOL_GPL(fscrypt_file_open); -int __fscrypt_prepare_link(struct inode *inode, struct inode *dir) +int __fscrypt_prepare_link(struct inode *inode, struct inode *dir, + struct dentry *dentry) { int err; @@ -57,8 +58,12 @@ int __fscrypt_prepare_link(struct inode *inode, struct inode *dir) if (err) return err; + /* ... in case we looked up no-key name before key was added */ + if (fscrypt_is_nokey_name(dentry)) + return -ENOKEY; + if (!fscrypt_has_permitted_context(dir, inode)) - return -EPERM; + return -EXDEV; return 0; } @@ -78,37 +83,42 @@ int __fscrypt_prepare_rename(struct inode *old_dir, struct dentry *old_dentry, if (err) return err; + /* ... in case we looked up no-key name(s) before key was added */ + if (fscrypt_is_nokey_name(old_dentry) || + fscrypt_is_nokey_name(new_dentry)) + return -ENOKEY; + if (old_dir != new_dir) { if (IS_ENCRYPTED(new_dir) && !fscrypt_has_permitted_context(new_dir, d_inode(old_dentry))) - return -EPERM; + return -EXDEV; if ((flags & RENAME_EXCHANGE) && IS_ENCRYPTED(old_dir) && !fscrypt_has_permitted_context(old_dir, d_inode(new_dentry))) - return -EPERM; + return -EXDEV; } return 0; } EXPORT_SYMBOL_GPL(__fscrypt_prepare_rename); -int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry) +int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry, + struct fscrypt_name *fname) { - int err = fscrypt_get_encryption_info(dir); + int err = fscrypt_setup_filename(dir, &dentry->d_name, 1, fname); - if (err) + if (err && err != -ENOENT) return err; - if (fscrypt_has_encryption_key(dir)) { + if (fname->is_ciphertext_name) { spin_lock(&dentry->d_lock); - dentry->d_flags |= DCACHE_ENCRYPTED_WITH_KEY; + dentry->d_flags |= DCACHE_ENCRYPTED_NAME; spin_unlock(&dentry->d_lock); + d_set_d_op(dentry, &fscrypt_d_ops); } - - d_set_d_op(dentry, &fscrypt_d_ops); - return 0; + return err; } EXPORT_SYMBOL_GPL(__fscrypt_prepare_lookup); @@ -269,3 +279,47 @@ err_kfree: return ERR_PTR(err); } EXPORT_SYMBOL_GPL(fscrypt_get_symlink); + +/** + * fscrypt_symlink_getattr() - set the correct st_size for encrypted symlinks + * @path: the path for the encrypted symlink being queried + * @stat: the struct being filled with the symlink's attributes + * + * Override st_size of encrypted symlinks to be the length of the decrypted + * symlink target (or the no-key encoded symlink target, if the key is + * unavailable) rather than the length of the encrypted symlink target. This is + * necessary for st_size to match the symlink target that userspace actually + * sees. POSIX requires this, and some userspace programs depend on it. + * + * This requires reading the symlink target from disk if needed, setting up the + * inode's encryption key if possible, and then decrypting or encoding the + * symlink target. This makes lstat() more heavyweight than is normally the + * case. However, decrypted symlink targets will be cached in ->i_link, so + * usually the symlink won't have to be read and decrypted again later if/when + * it is actually followed, readlink() is called, or lstat() is called again. + * + * Return: 0 on success, -errno on failure + */ +int fscrypt_symlink_getattr(const struct path *path, struct kstat *stat) +{ + struct dentry *dentry = path->dentry; + struct inode *inode = d_inode(dentry); + const char *link; + DEFINE_DELAYED_CALL(done); + + /* + * To get the symlink target that userspace will see (whether it's the + * decrypted target or the no-key encoded target), we can just get it in + * the same way the VFS does during path resolution and readlink(). + */ + link = READ_ONCE(inode->i_link); + if (!link) { + link = inode->i_op->get_link(dentry, inode, &done); + if (IS_ERR(link)) + return PTR_ERR(link); + } + stat->size = strlen(link); + do_delayed_call(&done); + return 0; +} +EXPORT_SYMBOL_GPL(fscrypt_symlink_getattr); diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c index 4288839501e9..e9d975f39f46 100644 --- a/fs/crypto/policy.c +++ b/fs/crypto/policy.c @@ -153,8 +153,7 @@ EXPORT_SYMBOL(fscrypt_ioctl_get_policy); * malicious offline violations of this constraint, while the link and rename * checks are needed to prevent online violations of this constraint. * - * Return: 1 if permitted, 0 if forbidden. If forbidden, the caller must fail - * the filesystem operation with EPERM. + * Return: 1 if permitted, 0 if forbidden. */ int fscrypt_has_permitted_context(struct inode *parent, struct inode *child) { @@ -907,7 +907,8 @@ static void dax_mapping_entry_mkclean(struct address_space *mapping, if (!pmd_dirty(*pmdp) && !pmd_write(*pmdp)) goto unlock_pmd; - flush_cache_page(vma, address, pfn); + flush_cache_range(vma, address, + address + HPAGE_PMD_SIZE); pmd = pmdp_invalidate(vma, address, pmdp); pmd = pmd_wrprotect(pmd); pmd = pmd_mkclean(pmd); diff --git a/fs/dcache.c b/fs/dcache.c index 20370a0997bf..1897833a4668 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -2713,6 +2713,20 @@ static void copy_name(struct dentry *dentry, struct dentry *target) } /* + * When d_splice_alias() moves a directory's encrypted alias to its decrypted + * alias as a result of the encryption key being added, DCACHE_ENCRYPTED_NAME + * must be cleared. Note that we don't have to support arbitrary moves of this + * flag because fscrypt doesn't allow encrypted aliases to be the source or + * target of a rename(). + */ +static inline void fscrypt_handle_d_move(struct dentry *dentry) +{ +#if IS_ENABLED(CONFIG_FS_ENCRYPTION) + dentry->d_flags &= ~DCACHE_ENCRYPTED_NAME; +#endif +} + +/* * __d_move - move a dentry * @dentry: entry to move * @target: new dentry @@ -2787,6 +2801,7 @@ static void __d_move(struct dentry *dentry, struct dentry *target, list_move(&dentry->d_child, &dentry->d_parent->d_subdirs); __d_rehash(dentry); fsnotify_update_flags(dentry); + fscrypt_handle_d_move(dentry); write_seqcount_end(&target->d_seq); write_seqcount_end(&dentry->d_seq); diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index 4fce1da7db23..acdc802bfe9a 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -18,6 +18,7 @@ #include <linux/slab.h> #include <linux/atomic.h> #include <linux/device.h> +#include <linux/pm_runtime.h> #include <linux/poll.h> #include "internal.h" @@ -330,8 +331,8 @@ ssize_t debugfs_attr_read(struct file *file, char __user *buf, } EXPORT_SYMBOL_GPL(debugfs_attr_read); -ssize_t debugfs_attr_write(struct file *file, const char __user *buf, - size_t len, loff_t *ppos) +static ssize_t debugfs_attr_write_xsigned(struct file *file, const char __user *buf, + size_t len, loff_t *ppos, bool is_signed) { struct dentry *dentry = F_DENTRY(file); ssize_t ret; @@ -339,12 +340,28 @@ ssize_t debugfs_attr_write(struct file *file, const char __user *buf, ret = debugfs_file_get(dentry); if (unlikely(ret)) return ret; - ret = simple_attr_write(file, buf, len, ppos); + if (is_signed) + ret = simple_attr_write_signed(file, buf, len, ppos); + else + ret = simple_attr_write(file, buf, len, ppos); debugfs_file_put(dentry); return ret; } + +ssize_t debugfs_attr_write(struct file *file, const char __user *buf, + size_t len, loff_t *ppos) +{ + return debugfs_attr_write_xsigned(file, buf, len, ppos, false); +} EXPORT_SYMBOL_GPL(debugfs_attr_write); +ssize_t debugfs_attr_write_signed(struct file *file, const char __user *buf, + size_t len, loff_t *ppos) +{ + return debugfs_attr_write_xsigned(file, buf, len, ppos, true); +} +EXPORT_SYMBOL_GPL(debugfs_attr_write_signed); + static struct dentry *debugfs_create_mode_unsafe(const char *name, umode_t mode, struct dentry *parent, void *value, const struct file_operations *fops, @@ -742,11 +759,11 @@ static int debugfs_atomic_t_get(void *data, u64 *val) *val = atomic_read((atomic_t *)data); return 0; } -DEFINE_DEBUGFS_ATTRIBUTE(fops_atomic_t, debugfs_atomic_t_get, +DEFINE_DEBUGFS_ATTRIBUTE_SIGNED(fops_atomic_t, debugfs_atomic_t_get, debugfs_atomic_t_set, "%lld\n"); -DEFINE_DEBUGFS_ATTRIBUTE(fops_atomic_t_ro, debugfs_atomic_t_get, NULL, +DEFINE_DEBUGFS_ATTRIBUTE_SIGNED(fops_atomic_t_ro, debugfs_atomic_t_get, NULL, "%lld\n"); -DEFINE_DEBUGFS_ATTRIBUTE(fops_atomic_t_wo, NULL, debugfs_atomic_t_set, +DEFINE_DEBUGFS_ATTRIBUTE_SIGNED(fops_atomic_t_wo, NULL, debugfs_atomic_t_set, "%lld\n"); /** @@ -1068,7 +1085,14 @@ static int debugfs_show_regset32(struct seq_file *s, void *data) { struct debugfs_regset32 *regset = s->private; + if (regset->dev) + pm_runtime_get_sync(regset->dev); + debugfs_print_regs32(s, regset->regs, regset->nregs, regset->base, ""); + + if (regset->dev) + pm_runtime_put(regset->dev); + return 0; } diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index e5126fad57c5..1e4ae78f64a8 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -275,13 +275,9 @@ struct dentry *debugfs_lookup(const char *name, struct dentry *parent) if (!parent) parent = debugfs_mount->mnt_root; - dentry = lookup_one_len_unlocked(name, parent, strlen(name)); + dentry = lookup_positive_unlocked(name, parent, strlen(name)); if (IS_ERR(dentry)) return NULL; - if (!d_really_is_positive(dentry)) { - dput(dentry); - return NULL; - } return dentry; } EXPORT_SYMBOL_GPL(debugfs_lookup); @@ -767,6 +763,28 @@ void debugfs_remove_recursive(struct dentry *dentry) EXPORT_SYMBOL_GPL(debugfs_remove_recursive); /** + * debugfs_lookup_and_remove - lookup a directory or file and recursively remove it + * @name: a pointer to a string containing the name of the item to look up. + * @parent: a pointer to the parent dentry of the item. + * + * This is the equlivant of doing something like + * debugfs_remove(debugfs_lookup(..)) but with the proper reference counting + * handled for the directory being looked up. + */ +void debugfs_lookup_and_remove(const char *name, struct dentry *parent) +{ + struct dentry *dentry; + + dentry = debugfs_lookup(name, parent); + if (!dentry) + return; + + debugfs_remove(dentry); + dput(dentry); +} +EXPORT_SYMBOL_GPL(debugfs_lookup_and_remove); + +/** * debugfs_rename - rename a file/directory in the debugfs filesystem * @old_dir: a pointer to the parent dentry for the renamed object. This * should be a directory dentry. diff --git a/fs/direct-io.c b/fs/direct-io.c index 1abb7634b2d5..ec7c7d1c0329 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -856,6 +856,7 @@ submit_page_section(struct dio *dio, struct dio_submit *sdio, struct page *page, struct buffer_head *map_bh) { int ret = 0; + int boundary = sdio->boundary; /* dio_send_cur_page may clear it */ if (dio->op == REQ_OP_WRITE) { /* @@ -894,10 +895,10 @@ submit_page_section(struct dio *dio, struct dio_submit *sdio, struct page *page, sdio->cur_page_fs_offset = sdio->block_in_file << sdio->blkbits; out: /* - * If sdio->boundary then we want to schedule the IO now to + * If boundary then we want to schedule the IO now to * avoid metadata seeks. */ - if (sdio->boundary) { + if (boundary) { ret = dio_send_cur_page(dio, sdio, map_bh); if (sdio->bio) dio_bio_submit(dio, sdio); diff --git a/fs/dlm/ast.c b/fs/dlm/ast.c index 47ee66d70109..0b6fc9f8e8a7 100644 --- a/fs/dlm/ast.c +++ b/fs/dlm/ast.c @@ -200,13 +200,13 @@ void dlm_add_cb(struct dlm_lkb *lkb, uint32_t flags, int mode, int status, if (!prev_seq) { kref_get(&lkb->lkb_ref); + mutex_lock(&ls->ls_cb_mutex); if (test_bit(LSFL_CB_DELAY, &ls->ls_flags)) { - mutex_lock(&ls->ls_cb_mutex); list_add(&lkb->lkb_cb_list, &ls->ls_cb_delay); - mutex_unlock(&ls->ls_cb_mutex); } else { queue_work(ls->ls_callback_wq, &lkb->lkb_cb_work); } + mutex_unlock(&ls->ls_cb_mutex); } out: mutex_unlock(&lkb->lkb_cb_mutex); @@ -286,7 +286,9 @@ void dlm_callback_stop(struct dlm_ls *ls) void dlm_callback_suspend(struct dlm_ls *ls) { + mutex_lock(&ls->ls_cb_mutex); set_bit(LSFL_CB_DELAY, &ls->ls_flags); + mutex_unlock(&ls->ls_cb_mutex); if (ls->ls_callback_wq) flush_workqueue(ls->ls_callback_wq); diff --git a/fs/dlm/config.c b/fs/dlm/config.c index 1270551d24e3..42b53e2a4e96 100644 --- a/fs/dlm/config.c +++ b/fs/dlm/config.c @@ -80,6 +80,9 @@ struct dlm_cluster { unsigned int cl_new_rsb_count; unsigned int cl_recover_callbacks; char cl_cluster_name[DLM_LOCKSPACE_LEN]; + + struct dlm_spaces *sps; + struct dlm_comms *cms; }; static struct dlm_cluster *config_item_to_cluster(struct config_item *i) @@ -218,6 +221,7 @@ struct dlm_space { struct list_head members; struct mutex members_lock; int members_count; + struct dlm_nodes *nds; }; struct dlm_comms { @@ -355,6 +359,9 @@ static struct config_group *make_cluster(struct config_group *g, if (!cl || !sps || !cms) goto fail; + cl->sps = sps; + cl->cms = cms; + config_group_init_type_name(&cl->group, name, &cluster_type); config_group_init_type_name(&sps->ss_group, "spaces", &spaces_type); config_group_init_type_name(&cms->cs_group, "comms", &comms_type); @@ -404,6 +411,9 @@ static void drop_cluster(struct config_group *g, struct config_item *i) static void release_cluster(struct config_item *i) { struct dlm_cluster *cl = config_item_to_cluster(i); + + kfree(cl->sps); + kfree(cl->cms); kfree(cl); } @@ -426,6 +436,7 @@ static struct config_group *make_space(struct config_group *g, const char *name) INIT_LIST_HEAD(&sp->members); mutex_init(&sp->members_lock); sp->members_count = 0; + sp->nds = nds; return &sp->group; fail: @@ -447,6 +458,7 @@ static void drop_space(struct config_group *g, struct config_item *i) static void release_space(struct config_item *i) { struct dlm_space *sp = config_item_to_space(i); + kfree(sp->nds); kfree(sp); } diff --git a/fs/dlm/debug_fs.c b/fs/dlm/debug_fs.c index fa08448e35dd..bb87dad03cd4 100644 --- a/fs/dlm/debug_fs.c +++ b/fs/dlm/debug_fs.c @@ -544,6 +544,7 @@ static void *table_seq_next(struct seq_file *seq, void *iter_ptr, loff_t *pos) if (bucket >= ls->ls_rsbtbl_size) { kfree(ri); + ++*pos; return NULL; } tree = toss ? &ls->ls_rsbtbl[bucket].toss : &ls->ls_rsbtbl[bucket].keep; diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c index a928ba008d7d..0864481d8551 100644 --- a/fs/dlm/lock.c +++ b/fs/dlm/lock.c @@ -1553,6 +1553,7 @@ static int _remove_from_waiters(struct dlm_lkb *lkb, int mstype, lkb->lkb_wait_type = 0; lkb->lkb_flags &= ~DLM_IFL_OVERLAP_CANCEL; lkb->lkb_wait_count--; + unhold_lkb(lkb); goto out_del; } @@ -1579,6 +1580,7 @@ static int _remove_from_waiters(struct dlm_lkb *lkb, int mstype, log_error(ls, "remwait error %x reply %d wait_type %d overlap", lkb->lkb_id, mstype, lkb->lkb_wait_type); lkb->lkb_wait_count--; + unhold_lkb(lkb); lkb->lkb_wait_type = 0; } @@ -1856,7 +1858,7 @@ static void del_timeout(struct dlm_lkb *lkb) void dlm_scan_timeout(struct dlm_ls *ls) { struct dlm_rsb *r; - struct dlm_lkb *lkb; + struct dlm_lkb *lkb = NULL, *iter; int do_cancel, do_warn; s64 wait_us; @@ -1867,27 +1869,28 @@ void dlm_scan_timeout(struct dlm_ls *ls) do_cancel = 0; do_warn = 0; mutex_lock(&ls->ls_timeout_mutex); - list_for_each_entry(lkb, &ls->ls_timeout, lkb_time_list) { + list_for_each_entry(iter, &ls->ls_timeout, lkb_time_list) { wait_us = ktime_to_us(ktime_sub(ktime_get(), - lkb->lkb_timestamp)); + iter->lkb_timestamp)); - if ((lkb->lkb_exflags & DLM_LKF_TIMEOUT) && - wait_us >= (lkb->lkb_timeout_cs * 10000)) + if ((iter->lkb_exflags & DLM_LKF_TIMEOUT) && + wait_us >= (iter->lkb_timeout_cs * 10000)) do_cancel = 1; - if ((lkb->lkb_flags & DLM_IFL_WATCH_TIMEWARN) && + if ((iter->lkb_flags & DLM_IFL_WATCH_TIMEWARN) && wait_us >= dlm_config.ci_timewarn_cs * 10000) do_warn = 1; if (!do_cancel && !do_warn) continue; - hold_lkb(lkb); + hold_lkb(iter); + lkb = iter; break; } mutex_unlock(&ls->ls_timeout_mutex); - if (!do_cancel && !do_warn) + if (!lkb) break; r = lkb->lkb_resource; @@ -2888,24 +2891,24 @@ static int set_unlock_args(uint32_t flags, void *astarg, struct dlm_args *args) static int validate_lock_args(struct dlm_ls *ls, struct dlm_lkb *lkb, struct dlm_args *args) { - int rv = -EINVAL; + int rv = -EBUSY; if (args->flags & DLM_LKF_CONVERT) { - if (lkb->lkb_flags & DLM_IFL_MSTCPY) + if (lkb->lkb_status != DLM_LKSTS_GRANTED) goto out; - if (args->flags & DLM_LKF_QUECVT && - !__quecvt_compat_matrix[lkb->lkb_grmode+1][args->mode+1]) + if (lkb->lkb_wait_type) goto out; - rv = -EBUSY; - if (lkb->lkb_status != DLM_LKSTS_GRANTED) + if (is_overlap(lkb)) goto out; - if (lkb->lkb_wait_type) + rv = -EINVAL; + if (lkb->lkb_flags & DLM_IFL_MSTCPY) goto out; - if (is_overlap(lkb)) + if (args->flags & DLM_LKF_QUECVT && + !__quecvt_compat_matrix[lkb->lkb_grmode+1][args->mode+1]) goto out; } @@ -3977,6 +3980,14 @@ static int validate_message(struct dlm_lkb *lkb, struct dlm_message *ms) int from = ms->m_header.h_nodeid; int error = 0; + /* currently mixing of user/kernel locks are not supported */ + if (ms->m_flags & DLM_IFL_USER && ~lkb->lkb_flags & DLM_IFL_USER) { + log_error(lkb->lkb_resource->res_ls, + "got user dlm message for a kernel lock"); + error = -EINVAL; + goto out; + } + switch (ms->m_type) { case DLM_MSG_CONVERT: case DLM_MSG_UNLOCK: @@ -4005,6 +4016,7 @@ static int validate_message(struct dlm_lkb *lkb, struct dlm_message *ms) error = -EINVAL; } +out: if (error) log_error(lkb->lkb_resource->res_ls, "ignore invalid message %d from %d %x %x %x %d", @@ -4058,13 +4070,14 @@ static void send_repeat_remove(struct dlm_ls *ls, char *ms_name, int len) rv = _create_message(ls, sizeof(struct dlm_message) + len, dir_nodeid, DLM_MSG_REMOVE, &ms, &mh); if (rv) - return; + goto out; memcpy(ms->m_extra, name, len); ms->m_hash = hash; send_message(mh, ms); +out: spin_lock(&ls->ls_remove_spin); ls->ls_remove_len = 0; memset(ls->ls_remove_name, 0, DLM_RESNAME_MAXLEN); @@ -5231,21 +5244,18 @@ void dlm_recover_waiters_pre(struct dlm_ls *ls) static struct dlm_lkb *find_resend_waiter(struct dlm_ls *ls) { - struct dlm_lkb *lkb; - int found = 0; + struct dlm_lkb *lkb = NULL, *iter; mutex_lock(&ls->ls_waiters_mutex); - list_for_each_entry(lkb, &ls->ls_waiters, lkb_wait_reply) { - if (lkb->lkb_flags & DLM_IFL_RESEND) { - hold_lkb(lkb); - found = 1; + list_for_each_entry(iter, &ls->ls_waiters, lkb_wait_reply) { + if (iter->lkb_flags & DLM_IFL_RESEND) { + hold_lkb(iter); + lkb = iter; break; } } mutex_unlock(&ls->ls_waiters_mutex); - if (!found) - lkb = NULL; return lkb; } @@ -5305,11 +5315,16 @@ int dlm_recover_waiters_post(struct dlm_ls *ls) lkb->lkb_flags &= ~DLM_IFL_OVERLAP_UNLOCK; lkb->lkb_flags &= ~DLM_IFL_OVERLAP_CANCEL; lkb->lkb_wait_type = 0; - lkb->lkb_wait_count = 0; + /* drop all wait_count references we still + * hold a reference for this iteration. + */ + while (lkb->lkb_wait_count) { + lkb->lkb_wait_count--; + unhold_lkb(lkb); + } mutex_lock(&ls->ls_waiters_mutex); list_del_init(&lkb->lkb_wait_reply); mutex_unlock(&ls->ls_waiters_mutex); - unhold_lkb(lkb); /* for waiters list */ if (oc || ou) { /* do an unlock or cancel instead of resending */ @@ -5899,37 +5914,36 @@ int dlm_user_adopt_orphan(struct dlm_ls *ls, struct dlm_user_args *ua_tmp, int mode, uint32_t flags, void *name, unsigned int namelen, unsigned long timeout_cs, uint32_t *lkid) { - struct dlm_lkb *lkb; + struct dlm_lkb *lkb = NULL, *iter; struct dlm_user_args *ua; int found_other_mode = 0; - int found = 0; int rv = 0; mutex_lock(&ls->ls_orphans_mutex); - list_for_each_entry(lkb, &ls->ls_orphans, lkb_ownqueue) { - if (lkb->lkb_resource->res_length != namelen) + list_for_each_entry(iter, &ls->ls_orphans, lkb_ownqueue) { + if (iter->lkb_resource->res_length != namelen) continue; - if (memcmp(lkb->lkb_resource->res_name, name, namelen)) + if (memcmp(iter->lkb_resource->res_name, name, namelen)) continue; - if (lkb->lkb_grmode != mode) { + if (iter->lkb_grmode != mode) { found_other_mode = 1; continue; } - found = 1; - list_del_init(&lkb->lkb_ownqueue); - lkb->lkb_flags &= ~DLM_IFL_ORPHAN; - *lkid = lkb->lkb_id; + lkb = iter; + list_del_init(&iter->lkb_ownqueue); + iter->lkb_flags &= ~DLM_IFL_ORPHAN; + *lkid = iter->lkb_id; break; } mutex_unlock(&ls->ls_orphans_mutex); - if (!found && found_other_mode) { + if (!lkb && found_other_mode) { rv = -EAGAIN; goto out; } - if (!found) { + if (!lkb) { rv = -ENOENT; goto out; } diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index a93ebffe84b3..f476a90e8aae 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -609,7 +609,7 @@ static void close_connection(struct connection *con, bool and_other, } if (con->othercon && and_other) { /* Will only re-enter once. */ - close_connection(con->othercon, false, true, true); + close_connection(con->othercon, false, tx, rx); } if (con->rx_page) { __free_page(con->rx_page); diff --git a/fs/dlm/netlink.c b/fs/dlm/netlink.c index 43a96c330570..ea50f59610e5 100644 --- a/fs/dlm/netlink.c +++ b/fs/dlm/netlink.c @@ -115,7 +115,7 @@ static void fill_data(struct dlm_lock_data *data, struct dlm_lkb *lkb) void dlm_timeout_warn(struct dlm_lkb *lkb) { - struct sk_buff *uninitialized_var(send_skb); + struct sk_buff *send_skb; struct dlm_lock_data *data; size_t size; int rv; diff --git a/fs/dlm/plock.c b/fs/dlm/plock.c index c7d5a2ea3d03..c6079f6c6a79 100644 --- a/fs/dlm/plock.c +++ b/fs/dlm/plock.c @@ -22,20 +22,20 @@ static struct list_head recv_list; static wait_queue_head_t send_wq; static wait_queue_head_t recv_wq; -struct plock_op { - struct list_head list; - int done; - struct dlm_plock_info info; -}; - -struct plock_xop { - struct plock_op xop; - int (*callback)(struct file_lock *fl, int result); +struct plock_async_data { void *fl; void *file; struct file_lock flc; + int (*callback)(struct file_lock *fl, int result); }; +struct plock_op { + struct list_head list; + int done; + struct dlm_plock_info info; + /* if set indicates async handling */ + struct plock_async_data *data; +}; static inline void set_version(struct dlm_plock_info *info) { @@ -61,6 +61,12 @@ static int check_version(struct dlm_plock_info *info) return 0; } +static void dlm_release_plock_op(struct plock_op *op) +{ + kfree(op->data); + kfree(op); +} + static void send_op(struct plock_op *op) { set_version(&op->info); @@ -77,8 +83,7 @@ static void send_op(struct plock_op *op) abandoned waiter. So, we have to insert the unlock-close when the lock call is interrupted. */ -static void do_unlock_close(struct dlm_ls *ls, u64 number, - struct file *file, struct file_lock *fl) +static void do_unlock_close(const struct dlm_plock_info *info) { struct plock_op *op; @@ -87,15 +92,12 @@ static void do_unlock_close(struct dlm_ls *ls, u64 number, return; op->info.optype = DLM_PLOCK_OP_UNLOCK; - op->info.pid = fl->fl_pid; - op->info.fsid = ls->ls_global_id; - op->info.number = number; + op->info.pid = info->pid; + op->info.fsid = info->fsid; + op->info.number = info->number; op->info.start = 0; op->info.end = OFFSET_MAX; - if (fl->fl_lmops && fl->fl_lmops->lm_grant) - op->info.owner = (__u64) fl->fl_pid; - else - op->info.owner = (__u64)(long) fl->fl_owner; + op->info.owner = info->owner; op->info.flags |= DLM_PLOCK_FL_CLOSE; send_op(op); @@ -104,22 +106,21 @@ static void do_unlock_close(struct dlm_ls *ls, u64 number, int dlm_posix_lock(dlm_lockspace_t *lockspace, u64 number, struct file *file, int cmd, struct file_lock *fl) { + struct plock_async_data *op_data; struct dlm_ls *ls; struct plock_op *op; - struct plock_xop *xop; int rv; ls = dlm_find_lockspace_local(lockspace); if (!ls) return -EINVAL; - xop = kzalloc(sizeof(*xop), GFP_NOFS); - if (!xop) { + op = kzalloc(sizeof(*op), GFP_NOFS); + if (!op) { rv = -ENOMEM; goto out; } - op = &xop->xop; op->info.optype = DLM_PLOCK_OP_LOCK; op->info.pid = fl->fl_pid; op->info.ex = (fl->fl_type == F_WRLCK); @@ -128,36 +129,45 @@ int dlm_posix_lock(dlm_lockspace_t *lockspace, u64 number, struct file *file, op->info.number = number; op->info.start = fl->fl_start; op->info.end = fl->fl_end; + /* async handling */ if (fl->fl_lmops && fl->fl_lmops->lm_grant) { + op_data = kzalloc(sizeof(*op_data), GFP_NOFS); + if (!op_data) { + dlm_release_plock_op(op); + rv = -ENOMEM; + goto out; + } + /* fl_owner is lockd which doesn't distinguish processes on the nfs client */ op->info.owner = (__u64) fl->fl_pid; - xop->callback = fl->fl_lmops->lm_grant; - locks_init_lock(&xop->flc); - locks_copy_lock(&xop->flc, fl); - xop->fl = fl; - xop->file = file; + op_data->callback = fl->fl_lmops->lm_grant; + locks_init_lock(&op_data->flc); + locks_copy_lock(&op_data->flc, fl); + op_data->fl = fl; + op_data->file = file; + + op->data = op_data; + + send_op(op); + rv = FILE_LOCK_DEFERRED; + goto out; } else { op->info.owner = (__u64)(long) fl->fl_owner; - xop->callback = NULL; } send_op(op); - if (xop->callback == NULL) { - rv = wait_event_interruptible(recv_wq, (op->done != 0)); - if (rv == -ERESTARTSYS) { - log_debug(ls, "dlm_posix_lock: wait killed %llx", - (unsigned long long)number); - spin_lock(&ops_lock); - list_del(&op->list); - spin_unlock(&ops_lock); - kfree(xop); - do_unlock_close(ls, number, file, fl); - goto out; - } - } else { - rv = FILE_LOCK_DEFERRED; + rv = wait_event_killable(recv_wq, (op->done != 0)); + if (rv == -ERESTARTSYS) { + spin_lock(&ops_lock); + list_del(&op->list); + spin_unlock(&ops_lock); + log_debug(ls, "%s: wait interrupted %x %llx pid %d", + __func__, ls->ls_global_id, + (unsigned long long)number, op->info.pid); + dlm_release_plock_op(op); + do_unlock_close(&op->info); goto out; } @@ -177,7 +187,7 @@ int dlm_posix_lock(dlm_lockspace_t *lockspace, u64 number, struct file *file, (unsigned long long)number); } - kfree(xop); + dlm_release_plock_op(op); out: dlm_put_lockspace(ls); return rv; @@ -187,11 +197,11 @@ EXPORT_SYMBOL_GPL(dlm_posix_lock); /* Returns failure iff a successful lock operation should be canceled */ static int dlm_plock_callback(struct plock_op *op) { + struct plock_async_data *op_data = op->data; struct file *file; struct file_lock *fl; struct file_lock *flc; int (*notify)(struct file_lock *fl, int result) = NULL; - struct plock_xop *xop = (struct plock_xop *)op; int rv = 0; spin_lock(&ops_lock); @@ -203,10 +213,10 @@ static int dlm_plock_callback(struct plock_op *op) spin_unlock(&ops_lock); /* check if the following 2 are still valid or make a copy */ - file = xop->file; - flc = &xop->flc; - fl = xop->fl; - notify = xop->callback; + file = op_data->file; + flc = &op_data->flc; + fl = op_data->fl; + notify = op_data->callback; if (op->info.rv) { notify(fl, op->info.rv); @@ -237,7 +247,7 @@ static int dlm_plock_callback(struct plock_op *op) } out: - kfree(xop); + dlm_release_plock_op(op); return rv; } @@ -307,7 +317,7 @@ int dlm_posix_unlock(dlm_lockspace_t *lockspace, u64 number, struct file *file, rv = 0; out_free: - kfree(op); + dlm_release_plock_op(op); out: dlm_put_lockspace(ls); fl->fl_flags = fl_flags; @@ -367,13 +377,15 @@ int dlm_posix_get(dlm_lockspace_t *lockspace, u64 number, struct file *file, locks_init_lock(fl); fl->fl_type = (op->info.ex) ? F_WRLCK : F_RDLCK; fl->fl_flags = FL_POSIX; - fl->fl_pid = -op->info.pid; + fl->fl_pid = op->info.pid; + if (op->info.nodeid != dlm_our_nodeid()) + fl->fl_pid = -fl->fl_pid; fl->fl_start = op->info.start; fl->fl_end = op->info.end; rv = 0; } - kfree(op); + dlm_release_plock_op(op); out: dlm_put_lockspace(ls); return rv; @@ -396,7 +408,7 @@ static ssize_t dev_read(struct file *file, char __user *u, size_t count, if (op->info.flags & DLM_PLOCK_FL_CLOSE) list_del(&op->list); else - list_move(&op->list, &recv_list); + list_move_tail(&op->list, &recv_list); memcpy(&info, &op->info, sizeof(info)); } spin_unlock(&ops_lock); @@ -409,7 +421,7 @@ static ssize_t dev_read(struct file *file, char __user *u, size_t count, (the process did not make an unlock call). */ if (op->info.flags & DLM_PLOCK_FL_CLOSE) - kfree(op); + dlm_release_plock_op(op); if (copy_to_user(u, &info, sizeof(info))) return -EFAULT; @@ -421,9 +433,9 @@ static ssize_t dev_read(struct file *file, char __user *u, size_t count, static ssize_t dev_write(struct file *file, const char __user *u, size_t count, loff_t *ppos) { + struct plock_op *op = NULL, *iter; struct dlm_plock_info info; - struct plock_op *op; - int found = 0, do_callback = 0; + int do_callback = 0; if (count != sizeof(info)) return -EINVAL; @@ -434,32 +446,63 @@ static ssize_t dev_write(struct file *file, const char __user *u, size_t count, if (check_version(&info)) return -EINVAL; + /* + * The results for waiting ops (SETLKW) can be returned in any + * order, so match all fields to find the op. The results for + * non-waiting ops are returned in the order that they were sent + * to userspace, so match the result with the first non-waiting op. + */ spin_lock(&ops_lock); - list_for_each_entry(op, &recv_list, list) { - if (op->info.fsid == info.fsid && - op->info.number == info.number && - op->info.owner == info.owner) { - struct plock_xop *xop = (struct plock_xop *)op; - list_del_init(&op->list); - memcpy(&op->info, &info, sizeof(info)); - if (xop->callback) - do_callback = 1; - else - op->done = 1; - found = 1; - break; + if (info.wait) { + list_for_each_entry(iter, &recv_list, list) { + if (iter->info.fsid == info.fsid && + iter->info.number == info.number && + iter->info.owner == info.owner && + iter->info.pid == info.pid && + iter->info.start == info.start && + iter->info.end == info.end && + iter->info.ex == info.ex && + iter->info.wait) { + op = iter; + break; + } } + } else { + list_for_each_entry(iter, &recv_list, list) { + if (!iter->info.wait && + iter->info.fsid == info.fsid) { + op = iter; + break; + } + } + } + + if (op) { + /* Sanity check that op and info match. */ + if (info.wait) + WARN_ON(op->info.optype != DLM_PLOCK_OP_LOCK); + else + WARN_ON(op->info.number != info.number || + op->info.owner != info.owner || + op->info.optype != info.optype); + + list_del_init(&op->list); + memcpy(&op->info, &info, sizeof(info)); + if (op->data) + do_callback = 1; + else + op->done = 1; } spin_unlock(&ops_lock); - if (found) { + if (op) { if (do_callback) dlm_plock_callback(op); else wake_up(&recv_wq); } else - log_print("dev_write no op %x %llx", info.fsid, - (unsigned long long)info.number); + log_print("%s: no op %x %llx", __func__, + info.fsid, (unsigned long long)info.number); return count; } diff --git a/fs/dlm/recover.c b/fs/dlm/recover.c index ce2aa54ca2e2..98b710cc9cf3 100644 --- a/fs/dlm/recover.c +++ b/fs/dlm/recover.c @@ -734,10 +734,9 @@ void dlm_recovered_lock(struct dlm_rsb *r) static void recover_lvb(struct dlm_rsb *r) { - struct dlm_lkb *lkb, *high_lkb = NULL; + struct dlm_lkb *big_lkb = NULL, *iter, *high_lkb = NULL; uint32_t high_seq = 0; int lock_lvb_exists = 0; - int big_lock_exists = 0; int lvblen = r->res_ls->ls_lvblen; if (!rsb_flag(r, RSB_NEW_MASTER2) && @@ -753,37 +752,37 @@ static void recover_lvb(struct dlm_rsb *r) /* we are the new master, so figure out if VALNOTVALID should be set, and set the rsb lvb from the best lkb available. */ - list_for_each_entry(lkb, &r->res_grantqueue, lkb_statequeue) { - if (!(lkb->lkb_exflags & DLM_LKF_VALBLK)) + list_for_each_entry(iter, &r->res_grantqueue, lkb_statequeue) { + if (!(iter->lkb_exflags & DLM_LKF_VALBLK)) continue; lock_lvb_exists = 1; - if (lkb->lkb_grmode > DLM_LOCK_CR) { - big_lock_exists = 1; + if (iter->lkb_grmode > DLM_LOCK_CR) { + big_lkb = iter; goto setflag; } - if (((int)lkb->lkb_lvbseq - (int)high_seq) >= 0) { - high_lkb = lkb; - high_seq = lkb->lkb_lvbseq; + if (((int)iter->lkb_lvbseq - (int)high_seq) >= 0) { + high_lkb = iter; + high_seq = iter->lkb_lvbseq; } } - list_for_each_entry(lkb, &r->res_convertqueue, lkb_statequeue) { - if (!(lkb->lkb_exflags & DLM_LKF_VALBLK)) + list_for_each_entry(iter, &r->res_convertqueue, lkb_statequeue) { + if (!(iter->lkb_exflags & DLM_LKF_VALBLK)) continue; lock_lvb_exists = 1; - if (lkb->lkb_grmode > DLM_LOCK_CR) { - big_lock_exists = 1; + if (iter->lkb_grmode > DLM_LOCK_CR) { + big_lkb = iter; goto setflag; } - if (((int)lkb->lkb_lvbseq - (int)high_seq) >= 0) { - high_lkb = lkb; - high_seq = lkb->lkb_lvbseq; + if (((int)iter->lkb_lvbseq - (int)high_seq) >= 0) { + high_lkb = iter; + high_seq = iter->lkb_lvbseq; } } @@ -792,7 +791,7 @@ static void recover_lvb(struct dlm_rsb *r) goto out; /* lvb is invalidated if only NL/CR locks remain */ - if (!big_lock_exists) + if (!big_lkb) rsb_set_flag(r, RSB_VALNOTVALID); if (!r->res_lvbptr) { @@ -801,9 +800,9 @@ static void recover_lvb(struct dlm_rsb *r) goto out; } - if (big_lock_exists) { - r->res_lvbseq = lkb->lkb_lvbseq; - memcpy(r->res_lvbptr, lkb->lkb_lvbptr, lvblen); + if (big_lkb) { + r->res_lvbseq = big_lkb->lkb_lvbseq; + memcpy(r->res_lvbptr, big_lkb->lkb_lvbptr, lvblen); } else if (high_lkb) { r->res_lvbseq = high_lkb->lkb_lvbseq; memcpy(r->res_lvbptr, high_lkb->lkb_lvbptr, lvblen); diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c index 8e5353bd72cf..708f931c36f1 100644 --- a/fs/ecryptfs/crypto.c +++ b/fs/ecryptfs/crypto.c @@ -325,10 +325,8 @@ static int crypt_scatterlist(struct ecryptfs_crypt_stat *crypt_stat, struct extent_crypt_result ecr; int rc = 0; - if (!crypt_stat || !crypt_stat->tfm - || !(crypt_stat->flags & ECRYPTFS_STRUCT_INITIALIZED)) - return -EINVAL; - + BUG_ON(!crypt_stat || !crypt_stat->tfm + || !(crypt_stat->flags & ECRYPTFS_STRUCT_INITIALIZED)); if (unlikely(ecryptfs_verbosity > 0)) { ecryptfs_printk(KERN_DEBUG, "Key size [%zd]; key:\n", crypt_stat->key_size); diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c index 025d66a705db..b86a9b3a39c0 100644 --- a/fs/ecryptfs/main.c +++ b/fs/ecryptfs/main.c @@ -506,6 +506,12 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags goto out; } + if (!dev_name) { + rc = -EINVAL; + err = "Device name cannot be null"; + goto out; + } + rc = ecryptfs_parse_options(sbi, raw_data, &check_ruid); if (rc) { err = "Error parsing options"; diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c index 8c6ab6c95727..7f40343b39b0 100644 --- a/fs/efivarfs/inode.c +++ b/fs/efivarfs/inode.c @@ -10,6 +10,7 @@ #include <linux/efi.h> #include <linux/fs.h> #include <linux/ctype.h> +#include <linux/kmemleak.h> #include <linux/slab.h> #include <linux/uuid.h> @@ -106,6 +107,7 @@ static int efivarfs_create(struct inode *dir, struct dentry *dentry, var->var.VariableName[i] = '\0'; inode->i_private = var; + kmemleak_ignore(var); err = efivar_entry_add(var, &efivarfs_list); if (err) diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index 5b68e4294faa..834615f13f3e 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -145,6 +145,9 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor, name[len + EFI_VARIABLE_GUID_LEN+1] = '\0'; + /* replace invalid slashes like kobject_set_name_vargs does for /sys/firmware/efi/vars. */ + strreplace(name, '/', '!'); + inode = efivarfs_get_inode(sb, d_inode(root), S_IFREG | 0644, 0, is_removable); if (!inode) diff --git a/fs/eventfd.c b/fs/eventfd.c index ce1d1711fbba..66864100b823 100644 --- a/fs/eventfd.c +++ b/fs/eventfd.c @@ -174,11 +174,14 @@ static __poll_t eventfd_poll(struct file *file, poll_table *wait) return events; } -static void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt) +void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt) { - *cnt = (ctx->flags & EFD_SEMAPHORE) ? 1 : ctx->count; + lockdep_assert_held(&ctx->wqh.lock); + + *cnt = ((ctx->flags & EFD_SEMAPHORE) && ctx->count) ? 1 : ctx->count; ctx->count -= *cnt; } +EXPORT_SYMBOL_GPL(eventfd_ctx_do_read); /** * eventfd_ctx_remove_wait_queue - Read the current counter and removes wait queue. diff --git a/fs/exec.c b/fs/exec.c index cece8c14f377..28e3b5eb2f4a 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -984,7 +984,7 @@ int kernel_read_file_from_fd(int fd, void **buf, loff_t *size, loff_t max_size, struct fd f = fdget(fd); int ret = -EBADF; - if (!f.file) + if (!f.file || !(f.file->f_mode & FMODE_READ)) goto out; ret = kernel_read_file(f.file, buf, size, max_size, id); @@ -1011,7 +1011,7 @@ static int exec_mmap(struct mm_struct *mm) /* Notify parent that we're no longer interested in the old VM */ tsk = current; old_mm = current->mm; - mm_release(tsk, old_mm); + exec_mm_release(tsk, old_mm); if (old_mm) { sync_mm_rss(old_mm); @@ -1028,10 +1028,23 @@ static int exec_mmap(struct mm_struct *mm) } } task_lock(tsk); + + local_irq_disable(); active_mm = tsk->active_mm; - tsk->mm = mm; tsk->active_mm = mm; + tsk->mm = mm; + /* + * This prevents preemption while active_mm is being loaded and + * it and mm are being updated, which could cause problems for + * lazy tlb mm refcounting when these are updated by context + * switches. Not all architectures can handle irqs off over + * activate_mm yet. + */ + if (!IS_ENABLED(CONFIG_ARCH_WANT_IRQS_OFF_ACTIVATE_MM)) + local_irq_enable(); activate_mm(active_mm, mm); + if (IS_ENABLED(CONFIG_ARCH_WANT_IRQS_OFF_ACTIVATE_MM)) + local_irq_enable(); tsk->mm->vmacache_seqnum = 0; vmacache_flush(tsk); task_unlock(tsk); @@ -1792,6 +1805,9 @@ static int __do_execve_file(int fd, struct filename *filename, goto out_unmark; bprm->argc = count(argv, MAX_ARG_STRINGS); + if (bprm->argc == 0) + pr_warn_once("process '%s' launched '%s' with NULL argv: empty string added\n", + current->comm, bprm->filename); if ((retval = bprm->argc) < 0) goto out; @@ -1816,6 +1832,20 @@ static int __do_execve_file(int fd, struct filename *filename, if (retval < 0) goto out; + /* + * When argv is empty, add an empty string ("") as argv[0] to + * ensure confused userspace programs that start processing + * from argv[1] won't end up walking envp. See also + * bprm_stack_limits(). + */ + if (bprm->argc == 0) { + const char *argv[] = { "", NULL }; + retval = copy_strings_kernel(1, argv, bprm); + if (retval < 0) + goto out; + bprm->argc = 1; + } + retval = exec_binprm(bprm); if (retval < 0) goto out; diff --git a/fs/ext2/balloc.c b/fs/ext2/balloc.c index 33db13365c5e..fc59e0557e50 100644 --- a/fs/ext2/balloc.c +++ b/fs/ext2/balloc.c @@ -48,10 +48,9 @@ struct ext2_group_desc * ext2_get_group_desc(struct super_block * sb, struct ext2_sb_info *sbi = EXT2_SB(sb); if (block_group >= sbi->s_groups_count) { - ext2_error (sb, "ext2_get_group_desc", - "block_group >= groups_count - " - "block_group = %d, groups_count = %lu", - block_group, sbi->s_groups_count); + WARN(1, "block_group >= groups_count - " + "block_group = %d, groups_count = %lu", + block_group, sbi->s_groups_count); return NULL; } @@ -59,10 +58,9 @@ struct ext2_group_desc * ext2_get_group_desc(struct super_block * sb, group_desc = block_group >> EXT2_DESC_PER_BLOCK_BITS(sb); offset = block_group & (EXT2_DESC_PER_BLOCK(sb) - 1); if (!sbi->s_group_desc[group_desc]) { - ext2_error (sb, "ext2_get_group_desc", - "Group descriptor not loaded - " - "block_group = %d, group_desc = %lu, desc = %lu", - block_group, group_desc, offset); + WARN(1, "Group descriptor not loaded - " + "block_group = %d, group_desc = %lu, desc = %lu", + block_group, group_desc, offset); return NULL; } diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index 00e759f05161..598dc2874808 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -68,10 +68,7 @@ struct mb_cache; * second extended-fs super-block data in memory */ struct ext2_sb_info { - unsigned long s_frag_size; /* Size of a fragment in bytes */ - unsigned long s_frags_per_block;/* Number of fragments per block */ unsigned long s_inodes_per_block;/* Number of inodes per block */ - unsigned long s_frags_per_group;/* Number of fragments in a group */ unsigned long s_blocks_per_group;/* Number of blocks in a group */ unsigned long s_inodes_per_group;/* Number of inodes in a group */ unsigned long s_itb_per_group; /* Number of inode table blocks per group */ @@ -177,6 +174,7 @@ static inline struct ext2_sb_info *EXT2_SB(struct super_block *sb) #define EXT2_MIN_BLOCK_SIZE 1024 #define EXT2_MAX_BLOCK_SIZE 4096 #define EXT2_MIN_BLOCK_LOG_SIZE 10 +#define EXT2_MAX_BLOCK_LOG_SIZE 16 #define EXT2_BLOCK_SIZE(s) ((s)->s_blocksize) #define EXT2_ADDR_PER_BLOCK(s) (EXT2_BLOCK_SIZE(s) / sizeof (__u32)) #define EXT2_BLOCK_SIZE_BITS(s) ((s)->s_blocksize_bits) @@ -185,15 +183,6 @@ static inline struct ext2_sb_info *EXT2_SB(struct super_block *sb) #define EXT2_FIRST_INO(s) (EXT2_SB(s)->s_first_ino) /* - * Macro-instructions used to manage fragments - */ -#define EXT2_MIN_FRAG_SIZE 1024 -#define EXT2_MAX_FRAG_SIZE 4096 -#define EXT2_MIN_FRAG_LOG_SIZE 10 -#define EXT2_FRAG_SIZE(s) (EXT2_SB(s)->s_frag_size) -#define EXT2_FRAGS_PER_BLOCK(s) (EXT2_SB(s)->s_frags_per_block) - -/* * Structure of a blocks group descriptor */ struct ext2_group_desc diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 80a3038e0e46..5c0af53f2e8f 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -691,10 +691,9 @@ static int ext2_setup_super (struct super_block * sb, es->s_max_mnt_count = cpu_to_le16(EXT2_DFL_MAX_MNT_COUNT); le16_add_cpu(&es->s_mnt_count, 1); if (test_opt (sb, DEBUG)) - ext2_msg(sb, KERN_INFO, "%s, %s, bs=%lu, fs=%lu, gc=%lu, " + ext2_msg(sb, KERN_INFO, "%s, %s, bs=%lu, gc=%lu, " "bpg=%lu, ipg=%lu, mo=%04lx]", EXT2FS_VERSION, EXT2FS_DATE, sb->s_blocksize, - sbi->s_frag_size, sbi->s_groups_count, EXT2_BLOCKS_PER_GROUP(sb), EXT2_INODES_PER_GROUP(sb), @@ -780,8 +779,12 @@ static loff_t ext2_max_size(int bits) res += 1LL << (bits-2); res += 1LL << (2*(bits-2)); res += 1LL << (3*(bits-2)); + /* Compute how many metadata blocks are needed */ + meta_blocks = 1; + meta_blocks += 1 + ppb; + meta_blocks += 1 + ppb + ppb * ppb; /* Does block tree limit file size? */ - if (res < upper_limit) + if (res + meta_blocks <= upper_limit) goto check_lfs; res = upper_limit; @@ -974,6 +977,13 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount; } + if (le32_to_cpu(es->s_log_block_size) > + (EXT2_MAX_BLOCK_LOG_SIZE - BLOCK_SIZE_BITS)) { + ext2_msg(sb, KERN_ERR, + "Invalid log block size: %u", + le32_to_cpu(es->s_log_block_size)); + goto failed_mount; + } blocksize = BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size); if (sbi->s_mount_opt & EXT2_MOUNT_DAX) { @@ -1029,14 +1039,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) } } - sbi->s_frag_size = EXT2_MIN_FRAG_SIZE << - le32_to_cpu(es->s_log_frag_size); - if (sbi->s_frag_size == 0) - goto cantfind_ext2; - sbi->s_frags_per_block = sb->s_blocksize / sbi->s_frag_size; - sbi->s_blocks_per_group = le32_to_cpu(es->s_blocks_per_group); - sbi->s_frags_per_group = le32_to_cpu(es->s_frags_per_group); sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group); if (EXT2_INODE_SIZE(sb) == 0) @@ -1064,11 +1067,10 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount; } - if (sb->s_blocksize != sbi->s_frag_size) { + if (es->s_log_frag_size != es->s_log_block_size) { ext2_msg(sb, KERN_ERR, - "error: fragsize %lu != blocksize %lu" - "(not supported yet)", - sbi->s_frag_size, sb->s_blocksize); + "error: fragsize log %u != blocksize log %u", + le32_to_cpu(es->s_log_frag_size), sb->s_blocksize_bits); goto failed_mount; } @@ -1078,15 +1080,10 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) sbi->s_blocks_per_group); goto failed_mount; } - if (sbi->s_frags_per_group > sb->s_blocksize * 8) { - ext2_msg(sb, KERN_ERR, - "error: #fragments per group too big: %lu", - sbi->s_frags_per_group); - goto failed_mount; - } - if (sbi->s_inodes_per_group > sb->s_blocksize * 8) { + if (sbi->s_inodes_per_group < sbi->s_inodes_per_block || + sbi->s_inodes_per_group > sb->s_blocksize * 8) { ext2_msg(sb, KERN_ERR, - "error: #inodes per group too big: %lu", + "error: invalid #inodes per group: %lu", sbi->s_inodes_per_group); goto failed_mount; } @@ -1096,6 +1093,13 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) sbi->s_groups_count = ((le32_to_cpu(es->s_blocks_count) - le32_to_cpu(es->s_first_data_block) - 1) / EXT2_BLOCKS_PER_GROUP(sb)) + 1; + if ((u64)sbi->s_groups_count * sbi->s_inodes_per_group != + le32_to_cpu(es->s_inodes_count)) { + ext2_msg(sb, KERN_ERR, "error: invalid #inodes: %u vs computed %llu", + le32_to_cpu(es->s_inodes_count), + (u64)sbi->s_groups_count * sbi->s_inodes_per_group); + goto failed_mount; + } db_count = (sbi->s_groups_count + EXT2_DESC_PER_BLOCK(sb) - 1) / EXT2_DESC_PER_BLOCK(sb); sbi->s_group_desc = kmalloc_array (db_count, diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c index bd1d68ff3a9f..437175bce22e 100644 --- a/fs/ext2/xattr.c +++ b/fs/ext2/xattr.c @@ -664,10 +664,10 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh, /* We need to allocate a new block */ ext2_fsblk_t goal = ext2_group_first_block_no(sb, EXT2_I(inode)->i_block_group); - int block = ext2_new_block(inode, goal, &error); + ext2_fsblk_t block = ext2_new_block(inode, goal, &error); if (error) goto cleanup; - ea_idebug(inode, "creating block %d", block); + ea_idebug(inode, "creating block %lu", block); new_bh = sb_getblk(sb, block); if (unlikely(!new_bh)) { diff --git a/fs/ext4/acl.h b/fs/ext4/acl.h index 9b63f5416a2f..7f3b25b3fa6d 100644 --- a/fs/ext4/acl.h +++ b/fs/ext4/acl.h @@ -67,6 +67,11 @@ extern int ext4_init_acl(handle_t *, struct inode *, struct inode *); static inline int ext4_init_acl(handle_t *handle, struct inode *inode, struct inode *dir) { + /* usually, the umask is applied by posix_acl_create(), but if + ext4 ACL support is disabled at compile time, we need to do + it here, because posix_acl_create() will never be called */ + inode->i_mode &= ~current_umask(); + return 0; } #endif /* CONFIG_EXT4_FS_POSIX_ACL */ diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index f9645de9d04c..9761aeb4b224 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -303,6 +303,22 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb, return desc; } +static ext4_fsblk_t ext4_valid_block_bitmap_padding(struct super_block *sb, + ext4_group_t block_group, + struct buffer_head *bh) +{ + ext4_grpblk_t next_zero_bit; + unsigned long bitmap_size = sb->s_blocksize * 8; + unsigned int offset = num_clusters_in_group(sb, block_group); + + if (bitmap_size <= offset) + return 0; + + next_zero_bit = ext4_find_next_zero_bit(bh->b_data, bitmap_size, offset); + + return (next_zero_bit < bitmap_size ? next_zero_bit : 0); +} + /* * Return the block number which was discovered to be invalid, or 0 if * the block bitmap is valid. @@ -395,6 +411,15 @@ static int ext4_validate_block_bitmap(struct super_block *sb, EXT4_GROUP_INFO_BBITMAP_CORRUPT); return -EFSCORRUPTED; } + blk = ext4_valid_block_bitmap_padding(sb, block_group, bh); + if (unlikely(blk != 0)) { + ext4_unlock_group(sb, block_group); + ext4_error(sb, "bg %u: block %llu: padding at end of block bitmap is not set", + block_group, blk); + ext4_mark_group_bitmap_corrupted(sb, block_group, + EXT4_GROUP_INFO_BBITMAP_CORRUPT); + return -EFSCORRUPTED; + } set_buffer_verified(bh); verified: ext4_unlock_group(sb, block_group); diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c index f22a89cdb407..1bc65ecd4bd6 100644 --- a/fs/ext4/block_validity.c +++ b/fs/ext4/block_validity.c @@ -24,6 +24,7 @@ struct ext4_system_zone { struct rb_node node; ext4_fsblk_t start_blk; unsigned int count; + u32 ino; }; static struct kmem_cache *ext4_system_zone_cachep; @@ -45,7 +46,8 @@ void ext4_exit_system_zone(void) static inline int can_merge(struct ext4_system_zone *entry1, struct ext4_system_zone *entry2) { - if ((entry1->start_blk + entry1->count) == entry2->start_blk) + if ((entry1->start_blk + entry1->count) == entry2->start_blk && + entry1->ino == entry2->ino) return 1; return 0; } @@ -66,7 +68,7 @@ static void release_system_zone(struct ext4_system_blocks *system_blks) */ static int add_system_zone(struct ext4_system_blocks *system_blks, ext4_fsblk_t start_blk, - unsigned int count) + unsigned int count, u32 ino) { struct ext4_system_zone *new_entry, *entry; struct rb_node **n = &system_blks->root.rb_node, *node; @@ -89,6 +91,7 @@ static int add_system_zone(struct ext4_system_blocks *system_blks, return -ENOMEM; new_entry->start_blk = start_blk; new_entry->count = count; + new_entry->ino = ino; new_node = &new_entry->node; rb_link_node(new_node, parent, n); @@ -145,7 +148,7 @@ static void debug_print_tree(struct ext4_sb_info *sbi) static int ext4_data_block_valid_rcu(struct ext4_sb_info *sbi, struct ext4_system_blocks *system_blks, ext4_fsblk_t start_blk, - unsigned int count) + unsigned int count, ino_t ino) { struct ext4_system_zone *entry; struct rb_node *n; @@ -168,6 +171,8 @@ static int ext4_data_block_valid_rcu(struct ext4_sb_info *sbi, else if (start_blk >= (entry->start_blk + entry->count)) n = n->rb_right; else { + if (entry->ino == ino) + return 1; sbi->s_es->s_last_error_block = cpu_to_le64(start_blk); return 0; } @@ -204,17 +209,16 @@ static int ext4_protect_reserved_inode(struct super_block *sb, if (n == 0) { i++; } else { - if (!ext4_data_block_valid_rcu(sbi, system_blks, - map.m_pblk, n)) { - ext4_error(sb, "blocks %llu-%llu from inode %u " + err = add_system_zone(system_blks, map.m_pblk, n, ino); + if (err < 0) { + if (err == -EFSCORRUPTED) { + ext4_error(sb, + "blocks %llu-%llu from inode %u " "overlap system zone", map.m_pblk, map.m_pblk + map.m_len - 1, ino); - err = -EFSCORRUPTED; + } break; } - err = add_system_zone(system_blks, map.m_pblk, n); - if (err < 0) - break; i += n; } } @@ -259,19 +263,19 @@ int ext4_setup_system_zone(struct super_block *sb) ((i < 5) || ((i % flex_size) == 0))) add_system_zone(system_blks, ext4_group_first_block_no(sb, i), - ext4_bg_num_gdb(sb, i) + 1); + ext4_bg_num_gdb(sb, i) + 1, 0); gdp = ext4_get_group_desc(sb, i, NULL); ret = add_system_zone(system_blks, - ext4_block_bitmap(sb, gdp), 1); + ext4_block_bitmap(sb, gdp), 1, 0); if (ret) goto err; ret = add_system_zone(system_blks, - ext4_inode_bitmap(sb, gdp), 1); + ext4_inode_bitmap(sb, gdp), 1, 0); if (ret) goto err; ret = add_system_zone(system_blks, ext4_inode_table(sb, gdp), - sbi->s_itb_per_group); + sbi->s_itb_per_group, 0); if (ret) goto err; } @@ -320,7 +324,7 @@ void ext4_release_system_zone(struct super_block *sb) call_rcu(&system_blks->rcu, ext4_destroy_system_zone); } -int ext4_data_block_valid(struct ext4_sb_info *sbi, ext4_fsblk_t start_blk, +int ext4_inode_block_valid(struct inode *inode, ext4_fsblk_t start_blk, unsigned int count) { struct ext4_system_blocks *system_blks; @@ -332,9 +336,9 @@ int ext4_data_block_valid(struct ext4_sb_info *sbi, ext4_fsblk_t start_blk, * mount option. */ rcu_read_lock(); - system_blks = rcu_dereference(sbi->system_blks); - ret = ext4_data_block_valid_rcu(sbi, system_blks, start_blk, - count); + system_blks = rcu_dereference(EXT4_SB(inode->i_sb)->system_blks); + ret = ext4_data_block_valid_rcu(EXT4_SB(inode->i_sb), system_blks, + start_blk, count, inode->i_ino); rcu_read_unlock(); return ret; } @@ -354,8 +358,7 @@ int ext4_check_blockref(const char *function, unsigned int line, while (bref < p+max) { blk = le32_to_cpu(*bref++); if (blk && - unlikely(!ext4_data_block_valid(EXT4_SB(inode->i_sb), - blk, 1))) { + unlikely(!ext4_inode_block_valid(inode, blk, 1))) { es->s_last_error_block = cpu_to_le64(blk); ext4_error_inode(inode, function, line, blk, "invalid block"); diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index ae520a726339..aed33af7551e 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -535,7 +535,7 @@ static int ext4_dx_readdir(struct file *file, struct dir_context *ctx) struct dir_private_info *info = file->private_data; struct inode *inode = file_inode(file); struct fname *fname; - int ret; + int ret = 0; if (!info) { info = ext4_htree_create_dir_info(file, ctx->pos); @@ -583,7 +583,7 @@ static int ext4_dx_readdir(struct file *file, struct dir_context *ctx) info->curr_minor_hash, &info->next_hash); if (ret < 0) - return ret; + goto finished; if (ret == 0) { ctx->pos = ext4_get_htree_eof(file); break; @@ -614,7 +614,7 @@ static int ext4_dx_readdir(struct file *file, struct dir_context *ctx) } finished: info->last_pos = ctx->pos; - return 0; + return ret < 0 ? ret : 0; } static int ext4_dir_open(struct inode * inode, struct file * filp) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 0a4461ac4225..fa2579abea7d 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -503,7 +503,7 @@ enum { * * It's not paranoia if the Murphy's Law really *is* out to get you. :-) */ -#define TEST_FLAG_VALUE(FLAG) (EXT4_##FLAG##_FL == (1 << EXT4_INODE_##FLAG)) +#define TEST_FLAG_VALUE(FLAG) (EXT4_##FLAG##_FL == (1U << EXT4_INODE_##FLAG)) #define CHECK_FLAG_VALUE(FLAG) BUILD_BUG_ON(!TEST_FLAG_VALUE(FLAG)) static inline void ext4_check_flag_values(void) @@ -929,11 +929,13 @@ do { \ * where the second inode has larger inode number * than the first * I_DATA_SEM_QUOTA - Used for quota inodes only + * I_DATA_SEM_EA - Used for ea_inodes only */ enum { I_DATA_SEM_NORMAL = 0, I_DATA_SEM_OTHER, I_DATA_SEM_QUOTA, + I_DATA_SEM_EA }; @@ -1410,7 +1412,7 @@ struct ext4_sb_info { unsigned long s_commit_interval; u32 s_max_batch_time; u32 s_min_batch_time; - struct block_device *journal_bdev; + struct block_device *s_journal_bdev; #ifdef CONFIG_QUOTA /* Names of quota files with journalled quota */ char __rcu *s_qf_names[EXT4_MAXQUOTAS]; @@ -1498,7 +1500,7 @@ struct ext4_sb_info { struct task_struct *s_mmp_tsk; /* record the last minlen when FITRIM is called. */ - atomic_t s_last_trim_minblks; + unsigned long s_last_trim_minblks; /* Reference to checksum algorithm driver via cryptoapi */ struct crypto_shash *s_chksum_driver; @@ -2326,23 +2328,47 @@ static inline bool ext4_encrypted_inode(struct inode *inode) } #ifdef CONFIG_EXT4_FS_ENCRYPTION +static inline void ext4_fname_from_fscrypt_name(struct ext4_filename *dst, + const struct fscrypt_name *src) +{ + memset(dst, 0, sizeof(*dst)); + + dst->usr_fname = src->usr_fname; + dst->disk_name = src->disk_name; + dst->hinfo.hash = src->hash; + dst->hinfo.minor_hash = src->minor_hash; + dst->crypto_buf = src->crypto_buf; +} + static inline int ext4_fname_setup_filename(struct inode *dir, - const struct qstr *iname, - int lookup, struct ext4_filename *fname) + const struct qstr *iname, + int lookup, + struct ext4_filename *fname) { struct fscrypt_name name; int err; - memset(fname, 0, sizeof(struct ext4_filename)); - err = fscrypt_setup_filename(dir, iname, lookup, &name); + if (err) + return err; - fname->usr_fname = name.usr_fname; - fname->disk_name = name.disk_name; - fname->hinfo.hash = name.hash; - fname->hinfo.minor_hash = name.minor_hash; - fname->crypto_buf = name.crypto_buf; - return err; + ext4_fname_from_fscrypt_name(fname, &name); + return 0; +} + +static inline int ext4_fname_prepare_lookup(struct inode *dir, + struct dentry *dentry, + struct ext4_filename *fname) +{ + struct fscrypt_name name; + int err; + + err = fscrypt_prepare_lookup(dir, dentry, &name); + if (err) + return err; + + ext4_fname_from_fscrypt_name(fname, &name); + return 0; } static inline void ext4_fname_free_filename(struct ext4_filename *fname) @@ -2356,19 +2382,27 @@ static inline void ext4_fname_free_filename(struct ext4_filename *fname) fname->usr_fname = NULL; fname->disk_name.name = NULL; } -#else +#else /* !CONFIG_EXT4_FS_ENCRYPTION */ static inline int ext4_fname_setup_filename(struct inode *dir, - const struct qstr *iname, - int lookup, struct ext4_filename *fname) + const struct qstr *iname, + int lookup, + struct ext4_filename *fname) { fname->usr_fname = iname; fname->disk_name.name = (unsigned char *) iname->name; fname->disk_name.len = iname->len; return 0; } -static inline void ext4_fname_free_filename(struct ext4_filename *fname) { } -#endif +static inline int ext4_fname_prepare_lookup(struct inode *dir, + struct dentry *dentry, + struct ext4_filename *fname) +{ + return ext4_fname_setup_filename(dir, &dentry->d_name, 1, fname); +} + +static inline void ext4_fname_free_filename(struct ext4_filename *fname) { } +#endif /* !CONFIG_EXT4_FS_ENCRYPTION */ /* dir.c */ extern int __ext4_check_dir_entry(const char *, unsigned int, struct inode *, @@ -2395,7 +2429,8 @@ void ext4_insert_dentry(struct inode *inode, struct ext4_filename *fname); static inline void ext4_update_dx_flag(struct inode *inode) { - if (!ext4_has_feature_dir_index(inode->i_sb)) { + if (!ext4_has_feature_dir_index(inode->i_sb) && + ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) { /* ext4_iget() should have caught this... */ WARN_ON_ONCE(ext4_has_feature_metadata_csum(inode->i_sb)); ext4_clear_inode_flag(inode, EXT4_INODE_INDEX); @@ -3147,9 +3182,9 @@ extern void ext4_release_system_zone(struct super_block *sb); extern int ext4_setup_system_zone(struct super_block *sb); extern int __init ext4_init_system_zone(void); extern void ext4_exit_system_zone(void); -extern int ext4_data_block_valid(struct ext4_sb_info *sbi, - ext4_fsblk_t start_blk, - unsigned int count); +extern int ext4_inode_block_valid(struct inode *inode, + ext4_fsblk_t start_blk, + unsigned int count); extern int ext4_check_blockref(const char *, unsigned int, struct inode *, __le32 *, unsigned int); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 3a4570e37cb0..d931252b7d0d 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -377,7 +377,7 @@ static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext) */ if (lblock + len <= lblock) return 0; - return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len); + return ext4_inode_block_valid(inode, block, len); } static int ext4_valid_extent_idx(struct inode *inode, @@ -385,14 +385,17 @@ static int ext4_valid_extent_idx(struct inode *inode, { ext4_fsblk_t block = ext4_idx_pblock(ext_idx); - return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, 1); + return ext4_inode_block_valid(inode, block, 1); } static int ext4_valid_extent_entries(struct inode *inode, struct ext4_extent_header *eh, - int depth) + ext4_fsblk_t *pblk, int depth) { unsigned short entries; + ext4_lblk_t lblock = 0; + ext4_lblk_t prev = 0; + if (eh->eh_entries == 0) return 1; @@ -403,32 +406,36 @@ static int ext4_valid_extent_entries(struct inode *inode, struct ext4_extent *ext = EXT_FIRST_EXTENT(eh); struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es; ext4_fsblk_t pblock = 0; - ext4_lblk_t lblock = 0; - ext4_lblk_t prev = 0; - int len = 0; while (entries) { if (!ext4_valid_extent(inode, ext)) return 0; /* Check for overlapping extents */ lblock = le32_to_cpu(ext->ee_block); - len = ext4_ext_get_actual_len(ext); if ((lblock <= prev) && prev) { pblock = ext4_ext_pblock(ext); es->s_last_error_block = cpu_to_le64(pblock); return 0; } + prev = lblock + ext4_ext_get_actual_len(ext) - 1; ext++; entries--; - prev = lblock + len - 1; } } else { struct ext4_extent_idx *ext_idx = EXT_FIRST_INDEX(eh); while (entries) { if (!ext4_valid_extent_idx(inode, ext_idx)) return 0; + + /* Check for overlapping index extents */ + lblock = le32_to_cpu(ext_idx->ei_block); + if ((lblock <= prev) && prev) { + *pblk = ext4_idx_pblock(ext_idx); + return 0; + } ext_idx++; entries--; + prev = lblock; } } return 1; @@ -462,7 +469,7 @@ static int __ext4_ext_check(const char *function, unsigned int line, error_msg = "invalid eh_entries"; goto corrupted; } - if (!ext4_valid_extent_entries(inode, eh, depth)) { + if (!ext4_valid_extent_entries(inode, eh, &pblk, depth)) { error_msg = "invalid extent entries"; goto corrupted; } @@ -542,14 +549,10 @@ __read_extent_tree_block(const char *function, unsigned int line, } if (buffer_verified(bh) && !(flags & EXT4_EX_FORCE_CACHE)) return bh; - if (!ext4_has_feature_journal(inode->i_sb) || - (inode->i_ino != - le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_journal_inum))) { - err = __ext4_ext_check(function, line, inode, - ext_block_hdr(bh), depth, pblk); - if (err) - goto errout; - } + err = __ext4_ext_check(function, line, inode, + ext_block_hdr(bh), depth, pblk); + if (err) + goto errout; set_buffer_verified(bh); /* * If this is a leaf block, cache all of its entries @@ -862,6 +865,7 @@ int ext4_ext_tree_init(handle_t *handle, struct inode *inode) eh->eh_entries = 0; eh->eh_magic = EXT4_EXT_MAGIC; eh->eh_max = cpu_to_le16(ext4_ext_space_root(inode, 0)); + eh->eh_generation = 0; ext4_mark_inode_dirty(handle, inode); return 0; } @@ -993,6 +997,11 @@ static int ext4_ext_insert_index(handle_t *handle, struct inode *inode, ix = curp->p_idx; } + if (unlikely(ix > EXT_MAX_INDEX(curp->p_hdr))) { + EXT4_ERROR_INODE(inode, "ix > EXT_MAX_INDEX!"); + return -EFSCORRUPTED; + } + len = EXT_LAST_INDEX(curp->p_hdr) - ix + 1; BUG_ON(len < 0); if (len > 0) { @@ -1002,11 +1011,6 @@ static int ext4_ext_insert_index(handle_t *handle, struct inode *inode, memmove(ix + 1, ix, len * sizeof(struct ext4_extent_idx)); } - if (unlikely(ix > EXT_MAX_INDEX(curp->p_hdr))) { - EXT4_ERROR_INODE(inode, "ix > EXT_MAX_INDEX!"); - return -EFSCORRUPTED; - } - ix->ei_block = cpu_to_le32(logical); ext4_idx_store_pblock(ix, ptr); le16_add_cpu(&curp->p_hdr->eh_entries, 1); @@ -1118,6 +1122,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, neh->eh_max = cpu_to_le16(ext4_ext_space_block(inode, 0)); neh->eh_magic = EXT4_EXT_MAGIC; neh->eh_depth = 0; + neh->eh_generation = 0; /* move remainder of path[depth] to the new leaf */ if (unlikely(path[depth].p_hdr->eh_entries != @@ -1195,6 +1200,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, neh->eh_magic = EXT4_EXT_MAGIC; neh->eh_max = cpu_to_le16(ext4_ext_space_block_idx(inode, 0)); neh->eh_depth = cpu_to_le16(depth - i); + neh->eh_generation = 0; fidx = EXT_FIRST_INDEX(neh); fidx->ei_block = border; ext4_idx_store_pblock(fidx, oldblock); @@ -3267,7 +3273,10 @@ static int ext4_split_extent_at(handle_t *handle, ext4_ext_mark_unwritten(ex2); err = ext4_ext_insert_extent(handle, inode, ppath, &newex, flags); - if (err == -ENOSPC && (EXT4_EXT_MAY_ZEROOUT & split_flag)) { + if (err != -ENOSPC && err != -EDQUOT) + goto out; + + if (EXT4_EXT_MAY_ZEROOUT & split_flag) { if (split_flag & (EXT4_EXT_DATA_VALID1|EXT4_EXT_DATA_VALID2)) { if (split_flag & EXT4_EXT_DATA_VALID1) { err = ext4_ext_zeroout(inode, ex2); @@ -3293,30 +3302,30 @@ static int ext4_split_extent_at(handle_t *handle, ext4_ext_pblock(&orig_ex)); } - if (err) - goto fix_extent_len; - /* update the extent length and mark as initialized */ - ex->ee_len = cpu_to_le16(ee_len); - ext4_ext_try_to_merge(handle, inode, path, ex); - err = ext4_ext_dirty(handle, inode, path + path->p_depth); - if (err) - goto fix_extent_len; - - /* update extent status tree */ - err = ext4_zeroout_es(inode, &zero_ex); - - goto out; - } else if (err) - goto fix_extent_len; - -out: - ext4_ext_show_leaf(inode, path); - return err; + if (!err) { + /* update the extent length and mark as initialized */ + ex->ee_len = cpu_to_le16(ee_len); + ext4_ext_try_to_merge(handle, inode, path, ex); + err = ext4_ext_dirty(handle, inode, path + path->p_depth); + if (!err) + /* update extent status tree */ + err = ext4_zeroout_es(inode, &zero_ex); + /* If we failed at this point, we don't know in which + * state the extent tree exactly is so don't try to fix + * length of the original extent as it may do even more + * damage. + */ + goto out; + } + } fix_extent_len: ex->ee_len = orig_ex.ee_len; ext4_ext_dirty(handle, inode, path + path->p_depth); return err; +out: + ext4_ext_show_leaf(inode, path); + return err; } /* diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c index c4e6fb15101b..027c3e1b9f61 100644 --- a/fs/ext4/extents_status.c +++ b/fs/ext4/extents_status.c @@ -1080,11 +1080,9 @@ static unsigned long ext4_es_scan(struct shrinker *shrink, ret = percpu_counter_read_positive(&sbi->s_es_stats.es_stats_shk_cnt); trace_ext4_es_shrink_scan_enter(sbi->s_sb, nr_to_scan, ret); - if (!nr_to_scan) - return ret; - nr_shrunk = __es_shrink(sbi, nr_to_scan, NULL); + ret = percpu_counter_read_positive(&sbi->s_es_stats.es_stats_shk_cnt); trace_ext4_es_shrink_scan_exit(sbi->s_sb, nr_shrunk, ret); return nr_shrunk; } diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 52d155b4e733..d8b7e97dd450 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -501,6 +501,12 @@ loff_t ext4_llseek(struct file *file, loff_t offset, int whence) inode_unlock_shared(inode); break; } + /* + * Make sure inline data cannot be created anymore since we are going + * to allocate blocks for DIO. We know the inode does not have any + * inline data now because ext4_dio_supported() checked for that. + */ + ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); if (offset < 0) return offset; diff --git a/fs/ext4/fsmap.c b/fs/ext4/fsmap.c index 4b99e2db95b8..69c76327792e 100644 --- a/fs/ext4/fsmap.c +++ b/fs/ext4/fsmap.c @@ -108,6 +108,9 @@ static int ext4_getfsmap_helper(struct super_block *sb, /* Are we just counting mappings? */ if (info->gfi_head->fmh_count == 0) { + if (info->gfi_head->fmh_entries == UINT_MAX) + return EXT4_QUERY_RANGE_ABORT; + if (rec_fsblk > info->gfi_next_fsblk) info->gfi_head->fmh_entries++; @@ -483,6 +486,8 @@ static int ext4_getfsmap_datadev(struct super_block *sb, keys[0].fmr_physical = bofs; if (keys[1].fmr_physical >= eofs) keys[1].fmr_physical = eofs - 1; + if (keys[1].fmr_physical < keys[0].fmr_physical) + return 0; start_fsb = keys[0].fmr_physical; end_fsb = keys[1].fmr_physical; @@ -571,8 +576,8 @@ static bool ext4_getfsmap_is_valid_device(struct super_block *sb, if (fm->fmr_device == 0 || fm->fmr_device == UINT_MAX || fm->fmr_device == new_encode_dev(sb->s_bdev->bd_dev)) return true; - if (EXT4_SB(sb)->journal_bdev && - fm->fmr_device == new_encode_dev(EXT4_SB(sb)->journal_bdev->bd_dev)) + if (EXT4_SB(sb)->s_journal_bdev && + fm->fmr_device == new_encode_dev(EXT4_SB(sb)->s_journal_bdev->bd_dev)) return true; return false; } @@ -642,9 +647,9 @@ int ext4_getfsmap(struct super_block *sb, struct ext4_fsmap_head *head, memset(handlers, 0, sizeof(handlers)); handlers[0].gfd_dev = new_encode_dev(sb->s_bdev->bd_dev); handlers[0].gfd_fn = ext4_getfsmap_datadev; - if (EXT4_SB(sb)->journal_bdev) { + if (EXT4_SB(sb)->s_journal_bdev) { handlers[1].gfd_dev = new_encode_dev( - EXT4_SB(sb)->journal_bdev->bd_dev); + EXT4_SB(sb)->s_journal_bdev->bd_dev); handlers[1].gfd_fn = ext4_getfsmap_logdev; } diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 8876eaad10f6..5dfb34802aed 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -399,7 +399,7 @@ static void get_orlov_stats(struct super_block *sb, ext4_group_t g, * * We always try to spread first-level directories. * - * If there are blockgroups with both free inodes and free blocks counts + * If there are blockgroups with both free inodes and free clusters counts * not worse than average we return one with smallest directory count. * Otherwise we simply return a random group. * @@ -408,7 +408,7 @@ static void get_orlov_stats(struct super_block *sb, ext4_group_t g, * It's OK to put directory into a group unless * it has too many directories already (max_dirs) or * it has too few free inodes left (min_inodes) or - * it has too few free blocks left (min_blocks) or + * it has too few free clusters left (min_clusters) or * Parent's group is preferred, if it doesn't satisfy these * conditions we search cyclically through the rest. If none * of the groups look good we just look for a group with more @@ -424,7 +424,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent, ext4_group_t real_ngroups = ext4_get_groups_count(sb); int inodes_per_group = EXT4_INODES_PER_GROUP(sb); unsigned int freei, avefreei, grp_free; - ext4_fsblk_t freeb, avefreec; + ext4_fsblk_t freec, avefreec; unsigned int ndirs; int max_dirs, min_inodes; ext4_grpblk_t min_clusters; @@ -443,9 +443,8 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent, freei = percpu_counter_read_positive(&sbi->s_freeinodes_counter); avefreei = freei / ngroups; - freeb = EXT4_C2B(sbi, - percpu_counter_read_positive(&sbi->s_freeclusters_counter)); - avefreec = freeb; + freec = percpu_counter_read_positive(&sbi->s_freeclusters_counter); + avefreec = freec; do_div(avefreec, ngroups); ndirs = percpu_counter_read_positive(&sbi->s_dirs_counter); @@ -506,7 +505,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent, goto fallback; } - max_dirs = ndirs / ngroups + inodes_per_group / 16; + max_dirs = ndirs / ngroups + inodes_per_group*flex_size / 16; min_inodes = avefreei - inodes_per_group*flex_size / 4; if (min_inodes < 1) min_inodes = 1; @@ -1358,6 +1357,7 @@ int ext4_init_inode_table(struct super_block *sb, ext4_group_t group, handle_t *handle; ext4_fsblk_t blk; int num, ret = 0, used_blks = 0; + unsigned long used_inos = 0; /* This should not happen, but just to be sure check this */ if (sb_rdonly(sb)) { @@ -1388,22 +1388,37 @@ int ext4_init_inode_table(struct super_block *sb, ext4_group_t group, * used inodes so we need to skip blocks with used inodes in * inode table. */ - if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT))) - used_blks = DIV_ROUND_UP((EXT4_INODES_PER_GROUP(sb) - - ext4_itable_unused_count(sb, gdp)), - sbi->s_inodes_per_block); - - if ((used_blks < 0) || (used_blks > sbi->s_itb_per_group) || - ((group == 0) && ((EXT4_INODES_PER_GROUP(sb) - - ext4_itable_unused_count(sb, gdp)) < - EXT4_FIRST_INO(sb)))) { - ext4_error(sb, "Something is wrong with group %u: " - "used itable blocks: %d; " - "itable unused count: %u", - group, used_blks, - ext4_itable_unused_count(sb, gdp)); - ret = 1; - goto err_out; + if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT))) { + used_inos = EXT4_INODES_PER_GROUP(sb) - + ext4_itable_unused_count(sb, gdp); + used_blks = DIV_ROUND_UP(used_inos, sbi->s_inodes_per_block); + + /* Bogus inode unused count? */ + if (used_blks < 0 || used_blks > sbi->s_itb_per_group) { + ext4_error(sb, "Something is wrong with group %u: " + "used itable blocks: %d; " + "itable unused count: %u", + group, used_blks, + ext4_itable_unused_count(sb, gdp)); + ret = 1; + goto err_out; + } + + used_inos += group * EXT4_INODES_PER_GROUP(sb); + /* + * Are there some uninitialized inodes in the inode table + * before the first normal inode? + */ + if ((used_blks != sbi->s_itb_per_group) && + (used_inos < EXT4_FIRST_INO(sb))) { + ext4_error(sb, "Something is wrong with group %u: " + "itable unused count: %u; " + "itables initialized count: %ld", + group, ext4_itable_unused_count(sb, gdp), + used_inos); + ret = 1; + goto err_out; + } } blk = ext4_inode_table(sb, gdp) + used_blks; diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index e1801b288847..9bf711d63368 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -148,6 +148,7 @@ static Indirect *ext4_get_branch(struct inode *inode, int depth, struct super_block *sb = inode->i_sb; Indirect *p = chain; struct buffer_head *bh; + unsigned int key; int ret = -EIO; *err = 0; @@ -156,7 +157,13 @@ static Indirect *ext4_get_branch(struct inode *inode, int depth, if (!p->key) goto no_block; while (--depth) { - bh = sb_getblk(sb, le32_to_cpu(p->key)); + key = le32_to_cpu(p->key); + if (key > ext4_blocks_count(EXT4_SB(sb)->s_es)) { + /* the block was out of range */ + ret = -EFSCORRUPTED; + goto failure; + } + bh = sb_getblk(sb, key); if (unlikely(!bh)) { ret = -ENOMEM; goto failure; @@ -635,6 +642,14 @@ int ext4_ind_map_blocks(handle_t *handle, struct inode *inode, ext4_update_inode_fsync_trans(handle, inode, 1); count = ar.len; + + /* + * Update reserved blocks/metadata blocks after successful block + * allocation which had been deferred till now. + */ + if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) + ext4_da_update_reserve_space(inode, count, 1); + got_it: map->m_flags |= EXT4_MAP_MAPPED; map->m_pblk = le32_to_cpu(chain[depth-1].key); @@ -842,8 +857,7 @@ static int ext4_clear_blocks(handle_t *handle, struct inode *inode, else if (ext4_should_journal_data(inode)) flags |= EXT4_FREE_BLOCKS_FORGET; - if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), block_to_free, - count)) { + if (!ext4_inode_block_valid(inode, block_to_free, count)) { EXT4_ERROR_INODE(inode, "attempt to clear invalid " "blocks %llu len %lu", (unsigned long long) block_to_free, count); @@ -1005,8 +1019,7 @@ static void ext4_free_branches(handle_t *handle, struct inode *inode, if (!nr) continue; /* A hole */ - if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), - nr, 1)) { + if (!ext4_inode_block_valid(inode, nr, 1)) { EXT4_ERROR_INODE(inode, "invalid indirect mapped " "block %lu (level %d)", diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 4572cb057951..71bb3cfc5933 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -32,8 +32,12 @@ static int get_max_inline_xattr_value_size(struct inode *inode, struct ext4_xattr_ibody_header *header; struct ext4_xattr_entry *entry; struct ext4_inode *raw_inode; + void *end; int free, min_offs; + if (!EXT4_INODE_HAS_XATTR_SPACE(inode)) + return 0; + min_offs = EXT4_SB(inode->i_sb)->s_inode_size - EXT4_GOOD_OLD_INODE_SIZE - EXT4_I(inode)->i_extra_isize - @@ -52,14 +56,23 @@ static int get_max_inline_xattr_value_size(struct inode *inode, raw_inode = ext4_raw_inode(iloc); header = IHDR(inode, raw_inode); entry = IFIRST(header); + end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size; /* Compute min_offs. */ - for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) { + while (!IS_LAST_ENTRY(entry)) { + void *next = EXT4_XATTR_NEXT(entry); + + if (next >= end) { + EXT4_ERROR_INODE(inode, + "corrupt xattr in inline inode"); + return 0; + } if (!entry->e_value_inum && entry->e_value_size) { size_t offs = le16_to_cpu(entry->e_value_offs); if (offs < min_offs) min_offs = offs; } + entry = next; } free = min_offs - ((void *)entry - (void *)IFIRST(header)) - sizeof(__u32); @@ -154,7 +167,6 @@ int ext4_find_inline_data_nolock(struct inode *inode) (void *)ext4_raw_inode(&is.iloc)); EXT4_I(inode)->i_inline_size = EXT4_MIN_INLINE_DATA_SIZE + le32_to_cpu(is.s.here->e_value_size); - ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); } out: brelse(is.iloc.bh); @@ -204,7 +216,7 @@ out: /* * write the buffer to the inline inode. * If 'create' is set, we don't need to do the extra copy in the xattr - * value since it is already handled by ext4_xattr_ibody_inline_set. + * value since it is already handled by ext4_xattr_ibody_set. * That saves us one memcpy. */ static void ext4_write_inline_data(struct inode *inode, struct ext4_iloc *iloc, @@ -286,7 +298,7 @@ static int ext4_create_inline_data(handle_t *handle, BUG_ON(!is.s.not_found); - error = ext4_xattr_ibody_inline_set(handle, inode, &i, &is); + error = ext4_xattr_ibody_set(handle, inode, &i, &is); if (error) { if (error == -ENOSPC) ext4_clear_inode_state(inode, @@ -346,7 +358,7 @@ static int ext4_update_inline_data(handle_t *handle, struct inode *inode, error = ext4_xattr_ibody_get(inode, i.name_index, i.name, value, len); - if (error == -ENODATA) + if (error < 0) goto out; BUFFER_TRACE(is.iloc.bh, "get_write_access"); @@ -358,7 +370,7 @@ static int ext4_update_inline_data(handle_t *handle, struct inode *inode, i.value = value; i.value_len = len; - error = ext4_xattr_ibody_inline_set(handle, inode, &i, &is); + error = ext4_xattr_ibody_set(handle, inode, &i, &is); if (error) goto out; @@ -431,7 +443,7 @@ static int ext4_destroy_inline_data_nolock(handle_t *handle, if (error) goto out; - error = ext4_xattr_ibody_inline_set(handle, inode, &i, &is); + error = ext4_xattr_ibody_set(handle, inode, &i, &is); if (error) goto out; @@ -750,6 +762,12 @@ int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len, ext4_write_lock_xattr(inode, &no_expand); BUG_ON(!ext4_has_inline_data(inode)); + /* + * ei->i_inline_off may have changed since ext4_write_begin() + * called ext4_try_to_write_inline_data() + */ + (void) ext4_find_inline_data_nolock(inode); + kaddr = kmap_atomic(page); ext4_write_inline_data(inode, &iloc, kaddr, pos, len); kunmap_atomic(kaddr); @@ -1119,7 +1137,15 @@ static void ext4_restore_inline_data(handle_t *handle, struct inode *inode, struct ext4_iloc *iloc, void *buf, int inline_size) { - ext4_create_inline_data(handle, inode, inline_size); + int ret; + + ret = ext4_create_inline_data(handle, inode, inline_size); + if (ret) { + ext4_msg(inode->i_sb, KERN_EMERG, + "error restoring inline_data for inode -- potential data loss! (inode %lu, error %d)", + inode->i_ino, ret); + return; + } ext4_write_inline_data(inode, iloc, buf, 0, inline_size); ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); } @@ -1921,6 +1947,7 @@ int ext4_inline_data_truncate(struct inode *inode, int *has_inline) ext4_write_lock_xattr(inode, &no_expand); if (!ext4_has_inline_data(inode)) { + ext4_write_unlock_xattr(inode, &no_expand); *has_inline = 0; ext4_journal_stop(handle); return 0; @@ -1960,8 +1987,7 @@ int ext4_inline_data_truncate(struct inode *inode, int *has_inline) i.value = value; i.value_len = i_size > EXT4_MIN_INLINE_DATA_SIZE ? i_size - EXT4_MIN_INLINE_DATA_SIZE : 0; - err = ext4_xattr_ibody_inline_set(handle, inode, - &i, &is); + err = ext4_xattr_ibody_set(handle, inode, &i, &is); if (err) goto out_error; } @@ -2006,6 +2032,18 @@ int ext4_convert_inline_data(struct inode *inode) if (!ext4_has_inline_data(inode)) { ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); return 0; + } else if (!ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) { + /* + * Inode has inline data but EXT4_STATE_MAY_INLINE_DATA is + * cleared. This means we are in the middle of moving of + * inline data to delay allocated block. Just force writeout + * here to finish conversion. + */ + error = filemap_flush(inode->i_mapping); + if (error) + return error; + if (!ext4_has_inline_data(inode)) + return 0; } needed_blocks = ext4_writepage_trans_blocks(inode); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 52be4c965024..646285fbc9fc 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -203,9 +203,12 @@ void ext4_evict_inode(struct inode *inode) */ int extra_credits = 6; struct ext4_xattr_inode_array *ea_inode_array = NULL; + bool freeze_protected = false; trace_ext4_evict_inode(inode); + if (EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL) + ext4_evict_ea_inode(inode); if (inode->i_nlink) { /* * When journalling data dirty buffers are tracked only in the @@ -250,9 +253,14 @@ void ext4_evict_inode(struct inode *inode) /* * Protect us against freezing - iput() caller didn't have to have any - * protection against it + * protection against it. When we are in a running transaction though, + * we are already protected against freezing and we cannot grab further + * protection due to lock ordering constraints. */ - sb_start_intwrite(inode->i_sb); + if (!ext4_journal_current_handle()) { + sb_start_intwrite(inode->i_sb); + freeze_protected = true; + } if (!IS_NOQUOTA(inode)) extra_credits += EXT4_MAXQUOTAS_DEL_BLOCKS(inode->i_sb); @@ -271,7 +279,8 @@ void ext4_evict_inode(struct inode *inode) * cleaned up. */ ext4_orphan_del(NULL, inode); - sb_end_intwrite(inode->i_sb); + if (freeze_protected) + sb_end_intwrite(inode->i_sb); goto no_delete; } @@ -312,7 +321,8 @@ void ext4_evict_inode(struct inode *inode) stop_handle: ext4_journal_stop(handle); ext4_orphan_del(NULL, inode); - sb_end_intwrite(inode->i_sb); + if (freeze_protected) + sb_end_intwrite(inode->i_sb); ext4_xattr_inode_array_free(ea_inode_array); goto no_delete; } @@ -341,7 +351,8 @@ stop_handle: else ext4_free_inode(handle, inode); ext4_journal_stop(handle); - sb_end_intwrite(inode->i_sb); + if (freeze_protected) + sb_end_intwrite(inode->i_sb); ext4_xattr_inode_array_free(ea_inode_array); return; no_delete: @@ -412,8 +423,7 @@ static int __check_block_validity(struct inode *inode, const char *func, (inode->i_ino == le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_journal_inum))) return 0; - if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), map->m_pblk, - map->m_len)) { + if (!ext4_inode_block_valid(inode, map->m_pblk, map->m_len)) { ext4_error_inode(inode, func, line, map->m_pblk, "lblock %lu mapped to illegal pblock %llu " "(length %d)", (unsigned long) map->m_lblk, @@ -658,16 +668,6 @@ found: */ ext4_clear_inode_state(inode, EXT4_STATE_EXT_MIGRATE); } - - /* - * Update reserved blocks/metadata blocks after successful - * block allocation which had been deferred till now. We don't - * support fallocate for non extent files. So we can update - * reserve space here. - */ - if ((retval > 0) && - (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)) - ext4_da_update_reserve_space(inode, retval, 1); } if (retval > 0) { @@ -1302,6 +1302,13 @@ retry_grab: page = grab_cache_page_write_begin(mapping, index, flags); if (!page) return -ENOMEM; + /* + * The same as page allocation, we prealloc buffer heads before + * starting the handle. + */ + if (!page_has_buffers(page)) + create_empty_buffers(page, inode->i_sb->s_blocksize, 0); + unlock_page(page); retry_journal: @@ -1411,7 +1418,8 @@ static int ext4_write_end(struct file *file, int inline_data = ext4_has_inline_data(inode); trace_ext4_write_end(inode, pos, len, copied); - if (inline_data) { + if (inline_data && + ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) { ret = ext4_write_inline_data_end(inode, pos, len, copied, page); if (ret < 0) { @@ -1747,7 +1755,14 @@ static void mpage_release_unused_pages(struct mpage_da_data *mpd, ext4_lblk_t start, last; start = index << (PAGE_SHIFT - inode->i_blkbits); last = end << (PAGE_SHIFT - inode->i_blkbits); + + /* + * avoid racing with extent status tree scans made by + * ext4_insert_delayed_block() + */ + down_write(&EXT4_I(inode)->i_data_sem); ext4_es_remove_extent(inode, start, last - start + 1); + up_write(&EXT4_I(inode)->i_data_sem); } pagevec_init(&pvec); @@ -2064,13 +2079,13 @@ static int __ext4_journalled_writepage(struct page *page, if (!ret) ret = err; - if (!ext4_has_inline_data(inode)) - ext4_walk_page_buffers(NULL, page_bufs, 0, len, - NULL, bput_one); ext4_set_inode_state(inode, EXT4_STATE_JDATA); out: unlock_page(page); out_no_pagelock: + if (!inline_data && page_bufs) + ext4_walk_page_buffers(NULL, page_bufs, 0, len, + NULL, bput_one); brelse(inode_bh); return ret; } @@ -2140,6 +2155,15 @@ static int ext4_writepage(struct page *page, else len = PAGE_SIZE; + /* Should never happen but for bugs in other kernel subsystems */ + if (!page_has_buffers(page)) { + ext4_warning_inode(inode, + "page %lu does not have buffers attached", page->index); + ClearPageDirty(page); + unlock_page(page); + return 0; + } + page_bufs = page_buffers(page); /* * We cannot do block allocation or other extent handling in this @@ -2689,6 +2713,22 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd) wait_on_page_writeback(page); BUG_ON(PageWriteback(page)); + /* + * Should never happen but for buggy code in + * other subsystems that call + * set_page_dirty() without properly warning + * the file system first. See [1] for more + * information. + * + * [1] https://lore.kernel.org/linux-mm/20180103100430.GE4911@quack2.suse.cz + */ + if (!page_has_buffers(page)) { + ext4_warning_inode(mpd->inode, "page %lu does not have buffers attached", page->index); + ClearPageDirty(page); + unlock_page(page); + continue; + } + if (mpd->map.m_len == 0) mpd->first_page = page->index; mpd->next_page = page->index + 1; @@ -4281,7 +4321,8 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) struct super_block *sb = inode->i_sb; ext4_lblk_t first_block, stop_block; struct address_space *mapping = inode->i_mapping; - loff_t first_block_offset, last_block_offset; + loff_t first_block_offset, last_block_offset, max_length; + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); handle_t *handle; unsigned int credits; int ret = 0; @@ -4327,6 +4368,14 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) offset; } + /* + * For punch hole the length + offset needs to be within one block + * before last range. Adjust the length if it goes beyond that limit. + */ + max_length = sbi->s_bitmap_maxbytes - inode->i_sb->s_blocksize; + if (offset + length > max_length) + length = max_length - offset; + if (offset & (sb->s_blocksize - 1) || (offset + length) & (sb->s_blocksize - 1)) { /* @@ -4493,7 +4542,7 @@ int ext4_truncate(struct inode *inode) trace_ext4_truncate_enter(inode); if (!ext4_can_truncate(inode)) - return 0; + goto out_trace; ext4_clear_inode_flag(inode, EXT4_INODE_EOFBLOCKS); @@ -4504,16 +4553,15 @@ int ext4_truncate(struct inode *inode) int has_inline = 1; err = ext4_inline_data_truncate(inode, &has_inline); - if (err) - return err; - if (has_inline) - return 0; + if (err || has_inline) + goto out_trace; } /* If we zero-out tail of the page, we have to create jinode for jbd2 */ if (inode->i_size & (inode->i_sb->s_blocksize - 1)) { - if (ext4_inode_attach_jinode(inode) < 0) - return 0; + err = ext4_inode_attach_jinode(inode); + if (err) + goto out_trace; } if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) @@ -4522,8 +4570,10 @@ int ext4_truncate(struct inode *inode) credits = ext4_blocks_for_truncate(inode); handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits); - if (IS_ERR(handle)) - return PTR_ERR(handle); + if (IS_ERR(handle)) { + err = PTR_ERR(handle); + goto out_trace; + } if (inode->i_size & (inode->i_sb->s_blocksize - 1)) ext4_block_truncate_page(handle, mapping, inode->i_size); @@ -4572,6 +4622,7 @@ out_stop: ext4_mark_inode_dirty(handle, inode); ext4_journal_stop(handle); +out_trace: trace_ext4_truncate_exit(inode); return err; } @@ -4607,9 +4658,17 @@ static int __ext4_get_inode_loc(struct inode *inode, inodes_per_block = EXT4_SB(sb)->s_inodes_per_block; inode_offset = ((inode->i_ino - 1) % EXT4_INODES_PER_GROUP(sb)); - block = ext4_inode_table(sb, gdp) + (inode_offset / inodes_per_block); iloc->offset = (inode_offset % inodes_per_block) * EXT4_INODE_SIZE(sb); + block = ext4_inode_table(sb, gdp); + if ((block <= le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) || + (block >= ext4_blocks_count(EXT4_SB(sb)->s_es))) { + ext4_error(sb, "Invalid inode table block %llu in " + "block_group %u", block, iloc->block_group); + return -EFSCORRUPTED; + } + block += (inode_offset / inodes_per_block); + bh = sb_getblk(sb, block); if (unlikely(!bh)) return -ENOMEM; @@ -4795,11 +4854,15 @@ static inline int ext4_iget_extra_inode(struct inode *inode, __le32 *magic = (void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize; - if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize + sizeof(__le32) <= - EXT4_INODE_SIZE(inode->i_sb) && + if (EXT4_INODE_HAS_XATTR_SPACE(inode) && *magic == cpu_to_le32(EXT4_XATTR_MAGIC)) { + int err; + ext4_set_inode_state(inode, EXT4_STATE_XATTR); - return ext4_find_inline_data_nolock(inode); + err = ext4_find_inline_data_nolock(inode); + if (!err && ext4_has_inline_data(inode)) + ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); + return err; } else EXT4_I(inode)->i_inline_off = 0; return 0; @@ -4875,13 +4938,6 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, goto bad_inode; raw_inode = ext4_raw_inode(&iloc); - if ((ino == EXT4_ROOT_INO) && (raw_inode->i_links_count == 0)) { - ext4_error_inode(inode, function, line, 0, - "iget: root inode unallocated"); - ret = -EFSCORRUPTED; - goto bad_inode; - } - if ((flags & EXT4_IGET_HANDLE) && (raw_inode->i_links_count == 0) && (raw_inode->i_mode == 0)) { ret = -ESTALE; @@ -4952,11 +5008,16 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, * NeilBrown 1999oct15 */ if (inode->i_nlink == 0) { - if ((inode->i_mode == 0 || + if ((inode->i_mode == 0 || flags & EXT4_IGET_SPECIAL || !(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS)) && ino != EXT4_BOOT_LOADER_INO) { - /* this inode is deleted */ - ret = -ESTALE; + /* this inode is deleted or unallocated */ + if (flags & EXT4_IGET_SPECIAL) { + ext4_error_inode(inode, function, line, 0, + "iget: special inode unallocated"); + ret = -EFSCORRUPTED; + } else + ret = -ESTALE; goto bad_inode; } /* The only unlinked inodes we let through here have @@ -5063,7 +5124,7 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, ret = 0; if (ei->i_file_acl && - !ext4_data_block_valid(EXT4_SB(sb), ei->i_file_acl, 1)) { + !ext4_inode_block_valid(inode, ei->i_file_acl, 1)) { ext4_error_inode(inode, function, line, 0, "iget: bad extended attribute block %llu", ei->i_file_acl); @@ -5200,7 +5261,7 @@ static int other_inode_match(struct inode * inode, unsigned long ino, (inode->i_state & I_DIRTY_TIME)) { struct ext4_inode_info *ei = EXT4_I(inode); - inode->i_state &= ~(I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED); + inode->i_state &= ~I_DIRTY_TIME; spin_unlock(&inode->i_lock); spin_lock(&ei->i_raw_lock); @@ -5258,7 +5319,7 @@ static int ext4_do_update_inode(handle_t *handle, struct ext4_inode_info *ei = EXT4_I(inode); struct buffer_head *bh = iloc->bh; struct super_block *sb = inode->i_sb; - int err = 0, rc, block; + int err = 0, block; int need_datasync = 0, set_large_file = 0; uid_t i_uid; gid_t i_gid; @@ -5271,6 +5332,12 @@ static int ext4_do_update_inode(handle_t *handle, if (ext4_test_inode_state(inode, EXT4_STATE_NEW)) memset(raw_inode, 0, EXT4_SB(inode->i_sb)->s_inode_size); + err = ext4_inode_blocks_set(handle, raw_inode, ei); + if (err) { + spin_unlock(&ei->i_raw_lock); + goto out_brelse; + } + raw_inode->i_mode = cpu_to_le16(inode->i_mode); i_uid = i_uid_read(inode); i_gid = i_gid_read(inode); @@ -5304,11 +5371,6 @@ static int ext4_do_update_inode(handle_t *handle, EXT4_INODE_SET_XTIME(i_atime, inode, raw_inode); EXT4_EINODE_SET_XTIME(i_crtime, ei, raw_inode); - err = ext4_inode_blocks_set(handle, raw_inode, ei); - if (err) { - spin_unlock(&ei->i_raw_lock); - goto out_brelse; - } raw_inode->i_dtime = cpu_to_le32(ei->i_dtime); raw_inode->i_flags = cpu_to_le32(ei->i_flags & 0xFFFFFFFF); if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) @@ -5369,9 +5431,9 @@ static int ext4_do_update_inode(handle_t *handle, bh->b_data); BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata"); - rc = ext4_handle_dirty_metadata(handle, NULL, bh); - if (!err) - err = rc; + err = ext4_handle_dirty_metadata(handle, NULL, bh); + if (err) + goto out_brelse; ext4_clear_inode_state(inode, EXT4_STATE_NEW); if (set_large_file) { BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get write access"); @@ -5977,6 +6039,14 @@ static int __ext4_expand_extra_isize(struct inode *inode, return 0; } + /* + * We may need to allocate external xattr block so we need quotas + * initialized. Here we can be called with various locks held so we + * cannot affort to initialize quotas ourselves. So just bail. + */ + if (dquot_initialize_needed(inode)) + return -EAGAIN; + /* try to expand with EAs present */ error = ext4_expand_extra_isize_ea(inode, new_extra_isize, raw_inode, handle); diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 783c54bb2ce7..43e036f0b661 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -169,7 +169,7 @@ static long swap_inode_boot_loader(struct super_block *sb, /* Protect extent tree against block allocations via delalloc */ ext4_double_down_write_data_sem(inode, inode_bl); - if (inode_bl->i_nlink == 0) { + if (is_bad_inode(inode_bl) || !S_ISREG(inode_bl->i_mode)) { /* this inode has never been used as a BOOT_LOADER */ set_nlink(inode_bl, 1); i_uid_write(inode_bl, 0); @@ -178,6 +178,7 @@ static long swap_inode_boot_loader(struct super_block *sb, ei_bl->i_flags = 0; inode_set_iversion(inode_bl, 1); i_size_write(inode_bl, 0); + EXT4_I(inode_bl)->i_disksize = inode_bl->i_size; inode_bl->i_mode = S_IFREG; if (ext4_has_feature_extents(sb)) { ext4_set_inode_flag(inode_bl, EXT4_INODE_EXTENTS); @@ -449,6 +450,10 @@ static int ext4_ioctl_setproject(struct file *filp, __u32 projid) if (ext4_is_quota_file(inode)) return err; + err = dquot_initialize(inode); + if (err) + return err; + err = ext4_get_inode_loc(inode, &iloc); if (err) return err; @@ -464,10 +469,6 @@ static int ext4_ioctl_setproject(struct file *filp, __u32 projid) brelse(iloc.bh); } - err = dquot_initialize(inode); - if (err) - return err; - handle = ext4_journal_start(inode, EXT4_HT_QUOTA, EXT4_QUOTA_INIT_BLOCKS(sb) + EXT4_QUOTA_DEL_BLOCKS(sb) + 3); @@ -560,6 +561,7 @@ static int ext4_shutdown(struct super_block *sb, unsigned long arg) { struct ext4_sb_info *sbi = EXT4_SB(sb); __u32 flags; + struct super_block *ret; if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -578,7 +580,9 @@ static int ext4_shutdown(struct super_block *sb, unsigned long arg) switch (flags) { case EXT4_GOING_FLAGS_DEFAULT: - freeze_bdev(sb->s_bdev); + ret = freeze_bdev(sb->s_bdev); + if (IS_ERR(ret)) + return PTR_ERR(ret); set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags); thaw_bdev(sb->s_bdev, sb); break; @@ -1052,8 +1056,6 @@ resizefs_out: sizeof(range))) return -EFAULT; - range.minlen = max((unsigned int)range.minlen, - q->limits.discard_granularity); ret = ext4_trim_fs(sb, &range); if (ret < 0) return ret; @@ -1092,7 +1094,10 @@ resizefs_out: err = ext4_journal_get_write_access(handle, sbi->s_sbh); if (err) goto pwsalt_err_journal; + lock_buffer(sbi->s_sbh); generate_random_uuid(sbi->s_es->s_encrypt_pw_salt); + ext4_superblock_csum_set(sb); + unlock_buffer(sbi->s_sbh); err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh); pwsalt_err_journal: diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 054cfdd007d6..8875fac9f958 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -16,6 +16,7 @@ #include <linux/slab.h> #include <linux/nospec.h> #include <linux/backing-dev.h> +#include <linux/freezer.h> #include <trace/events/ext4.h> #ifdef CONFIG_EXT4_DEBUG @@ -1542,10 +1543,11 @@ static int mb_find_extent(struct ext4_buddy *e4b, int block, if (ex->fe_start + ex->fe_len > EXT4_CLUSTERS_PER_GROUP(e4b->bd_sb)) { /* Should never happen! (but apparently sometimes does?!?) */ WARN_ON(1); - ext4_error(e4b->bd_sb, "corruption or bug in mb_find_extent " - "block=%d, order=%d needed=%d ex=%u/%d/%d@%u", - block, order, needed, ex->fe_group, ex->fe_start, - ex->fe_len, ex->fe_logical); + ext4_grp_locked_error(e4b->bd_sb, e4b->bd_group, 0, 0, + "corruption or bug in mb_find_extent " + "block=%d, order=%d needed=%d ex=%u/%d/%d@%u", + block, order, needed, ex->fe_group, ex->fe_start, + ex->fe_len, ex->fe_logical); ex->fe_len = 0; ex->fe_start = 0; ex->fe_group = 0; @@ -2990,7 +2992,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, block = ext4_grp_offs_to_block(sb, &ac->ac_b_ex); len = EXT4_C2B(sbi, ac->ac_b_ex.fe_len); - if (!ext4_data_block_valid(sbi, block, len)) { + if (!ext4_inode_block_valid(ac->ac_inode, block, len)) { ext4_error(sb, "Allocating blocks %llu-%llu which overlap " "fs metadata", block, block+len); /* File system mounted not to panic on error @@ -3088,6 +3090,7 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac, struct ext4_allocation_request *ar) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); + struct ext4_super_block *es = sbi->s_es; int bsbits, max; ext4_lblk_t end; loff_t size, start_off; @@ -3169,6 +3172,19 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac, size = size >> bsbits; start = start_off >> bsbits; + /* + * For tiny groups (smaller than 8MB) the chosen allocation + * alignment may be larger than group size. Make sure the + * alignment does not move allocation to a different group which + * makes mballoc fail assertions later. + */ + start = max(start, rounddown(ac->ac_o_ex.fe_logical, + (ext4_lblk_t)EXT4_BLOCKS_PER_GROUP(ac->ac_sb))); + + /* avoid unnecessary preallocation that may trigger assertions */ + if (start + size > EXT_MAX_BLOCKS) + size = EXT_MAX_BLOCKS - start; + /* don't cover already allocated blocks in selected range */ if (ar->pleft && start <= ar->lleft) { size -= ar->lleft + 1 - start; @@ -3259,18 +3275,21 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac, ac->ac_g_ex.fe_len = EXT4_NUM_B2C(sbi, size); /* define goal start in order to merge */ - if (ar->pright && (ar->lright == (start + size))) { + if (ar->pright && (ar->lright == (start + size)) && + ar->pright >= size && + ar->pright - size >= le32_to_cpu(es->s_first_data_block)) { /* merge to the right */ ext4_get_group_no_and_offset(ac->ac_sb, ar->pright - size, - &ac->ac_f_ex.fe_group, - &ac->ac_f_ex.fe_start); + &ac->ac_g_ex.fe_group, + &ac->ac_g_ex.fe_start); ac->ac_flags |= EXT4_MB_HINT_TRY_GOAL; } - if (ar->pleft && (ar->lleft + 1 == start)) { + if (ar->pleft && (ar->lleft + 1 == start) && + ar->pleft + 1 < ext4_blocks_count(es)) { /* merge to the left */ ext4_get_group_no_and_offset(ac->ac_sb, ar->pleft + 1, - &ac->ac_f_ex.fe_group, - &ac->ac_f_ex.fe_start); + &ac->ac_g_ex.fe_group, + &ac->ac_g_ex.fe_start); ac->ac_flags |= EXT4_MB_HINT_TRY_GOAL; } @@ -3362,6 +3381,7 @@ static void ext4_mb_use_inode_pa(struct ext4_allocation_context *ac, BUG_ON(start < pa->pa_pstart); BUG_ON(end > pa->pa_pstart + EXT4_C2B(sbi, pa->pa_len)); BUG_ON(pa->pa_free < len); + BUG_ON(ac->ac_b_ex.fe_len <= 0); pa->pa_free -= len; mb_debug(1, "use %llu/%u from inode pa %p\n", start, len, pa); @@ -3666,10 +3686,8 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) return -ENOMEM; if (ac->ac_b_ex.fe_len < ac->ac_g_ex.fe_len) { - int winl; - int wins; - int win; - int offs; + int new_bex_start; + int new_bex_end; /* we can't allocate as much as normalizer wants. * so, found space must get proper lstart @@ -3677,26 +3695,40 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) BUG_ON(ac->ac_g_ex.fe_logical > ac->ac_o_ex.fe_logical); BUG_ON(ac->ac_g_ex.fe_len < ac->ac_o_ex.fe_len); - /* we're limited by original request in that - * logical block must be covered any way - * winl is window we can move our chunk within */ - winl = ac->ac_o_ex.fe_logical - ac->ac_g_ex.fe_logical; + /* + * Use the below logic for adjusting best extent as it keeps + * fragmentation in check while ensuring logical range of best + * extent doesn't overflow out of goal extent: + * + * 1. Check if best ex can be kept at end of goal and still + * cover original start + * 2. Else, check if best ex can be kept at start of goal and + * still cover original start + * 3. Else, keep the best ex at start of original request. + */ + new_bex_end = ac->ac_g_ex.fe_logical + + EXT4_C2B(sbi, ac->ac_g_ex.fe_len); + new_bex_start = new_bex_end - EXT4_C2B(sbi, ac->ac_b_ex.fe_len); + if (ac->ac_o_ex.fe_logical >= new_bex_start) + goto adjust_bex; - /* also, we should cover whole original request */ - wins = EXT4_C2B(sbi, ac->ac_b_ex.fe_len - ac->ac_o_ex.fe_len); + new_bex_start = ac->ac_g_ex.fe_logical; + new_bex_end = + new_bex_start + EXT4_C2B(sbi, ac->ac_b_ex.fe_len); + if (ac->ac_o_ex.fe_logical < new_bex_end) + goto adjust_bex; - /* the smallest one defines real window */ - win = min(winl, wins); + new_bex_start = ac->ac_o_ex.fe_logical; + new_bex_end = + new_bex_start + EXT4_C2B(sbi, ac->ac_b_ex.fe_len); - offs = ac->ac_o_ex.fe_logical % - EXT4_C2B(sbi, ac->ac_b_ex.fe_len); - if (offs && offs < win) - win = offs; +adjust_bex: + ac->ac_b_ex.fe_logical = new_bex_start; - ac->ac_b_ex.fe_logical = ac->ac_o_ex.fe_logical - - EXT4_NUM_B2C(sbi, win); BUG_ON(ac->ac_o_ex.fe_logical < ac->ac_b_ex.fe_logical); BUG_ON(ac->ac_o_ex.fe_len > ac->ac_b_ex.fe_len); + BUG_ON(new_bex_end > (ac->ac_g_ex.fe_logical + + EXT4_C2B(sbi, ac->ac_g_ex.fe_len))); } /* preallocation can change ac_b_ex, thus we store actually @@ -3883,7 +3915,11 @@ ext4_mb_release_group_pa(struct ext4_buddy *e4b, trace_ext4_mb_release_group_pa(sb, pa); BUG_ON(pa->pa_deleted == 0); ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, &bit); - BUG_ON(group != e4b->bd_group && pa->pa_len != 0); + if (unlikely(group != e4b->bd_group && pa->pa_len != 0)) { + ext4_warning(sb, "bad group: expected %u, group %u, pa_start %llu", + e4b->bd_group, group, pa->pa_pstart); + return 0; + } mb_free_blocks(pa->pa_inode, e4b, bit, pa->pa_len); atomic_add(pa->pa_len, &EXT4_SB(sb)->s_mb_discarded); trace_ext4_mballoc_discard(sb, NULL, group, bit, pa->pa_len); @@ -4690,6 +4726,7 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b, ext4_group_first_block_no(sb, group) + EXT4_C2B(sbi, cluster), "Block already on to-be-freed list"); + kmem_cache_free(ext4_free_data_cachep, new_entry); return 0; } } @@ -4754,7 +4791,7 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode, sbi = EXT4_SB(sb); if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) && - !ext4_data_block_valid(sbi, block, count)) { + !ext4_inode_block_valid(inode, block, count)) { ext4_error(sb, "Freeing blocks not in datazone - " "block = %llu, count = %lu", block, count); goto error_return; @@ -4916,8 +4953,8 @@ do_more: * them with group lock_held */ if (test_opt(sb, DISCARD)) { - err = ext4_issue_discard(sb, block_group, bit, count, - NULL); + err = ext4_issue_discard(sb, block_group, bit, + count_clusters, NULL); if (err && err != -EOPNOTSUPP) ext4_msg(sb, KERN_WARNING, "discard request in" " group:%d block:%d count:%lu failed" @@ -5117,19 +5154,19 @@ error_return: * @sb: super block for the file system * @start: starting block of the free extent in the alloc. group * @count: number of blocks to TRIM - * @group: alloc. group we are working with * @e4b: ext4 buddy for the group * * Trim "count" blocks starting at "start" in the "group". To assure that no * one will allocate those blocks, mark it as used in buddy bitmap. This must * be called with under the group lock. */ -static int ext4_trim_extent(struct super_block *sb, int start, int count, - ext4_group_t group, struct ext4_buddy *e4b) +static int ext4_trim_extent(struct super_block *sb, + int start, int count, struct ext4_buddy *e4b) __releases(bitlock) __acquires(bitlock) { struct ext4_free_extent ex; + ext4_group_t group = e4b->bd_group; int ret = 0; trace_ext4_trim_extent(sb, group, start, count); @@ -5152,6 +5189,71 @@ __acquires(bitlock) return ret; } +static ext4_grpblk_t ext4_last_grp_cluster(struct super_block *sb, + ext4_group_t grp) +{ + if (grp < ext4_get_groups_count(sb)) + return EXT4_CLUSTERS_PER_GROUP(sb) - 1; + return (ext4_blocks_count(EXT4_SB(sb)->s_es) - + ext4_group_first_block_no(sb, grp) - 1) >> + EXT4_CLUSTER_BITS(sb); +} + +static bool ext4_trim_interrupted(void) +{ + return fatal_signal_pending(current) || freezing(current); +} + +static int ext4_try_to_trim_range(struct super_block *sb, + struct ext4_buddy *e4b, ext4_grpblk_t start, + ext4_grpblk_t max, ext4_grpblk_t minblocks) +{ + ext4_grpblk_t next, count, free_count; + bool set_trimmed = false; + void *bitmap; + + bitmap = e4b->bd_bitmap; + if (start == 0 && max >= ext4_last_grp_cluster(sb, e4b->bd_group)) + set_trimmed = true; + start = max(e4b->bd_info->bb_first_free, start); + count = 0; + free_count = 0; + + while (start <= max) { + start = mb_find_next_zero_bit(bitmap, max + 1, start); + if (start > max) + break; + next = mb_find_next_bit(bitmap, max + 1, start); + + if ((next - start) >= minblocks) { + int ret = ext4_trim_extent(sb, start, next - start, e4b); + + if (ret && ret != -EOPNOTSUPP) + return count; + count += next - start; + } + free_count += next - start; + start = next + 1; + + if (ext4_trim_interrupted()) + return count; + + if (need_resched()) { + ext4_unlock_group(sb, e4b->bd_group); + cond_resched(); + ext4_lock_group(sb, e4b->bd_group); + } + + if ((e4b->bd_info->bb_free - free_count) < minblocks) + break; + } + + if (set_trimmed) + EXT4_MB_GRP_SET_TRIMMED(e4b->bd_info); + + return count; +} + /** * ext4_trim_all_free -- function to trim all free space in alloc. group * @sb: super block for file system @@ -5175,10 +5277,8 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group, ext4_grpblk_t start, ext4_grpblk_t max, ext4_grpblk_t minblocks) { - void *bitmap; - ext4_grpblk_t next, count = 0, free_count = 0; struct ext4_buddy e4b; - int ret = 0; + int ret; trace_ext4_trim_all_free(sb, group, start, max); @@ -5188,58 +5288,20 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group, ret, group); return ret; } - bitmap = e4b.bd_bitmap; ext4_lock_group(sb, group); - if (EXT4_MB_GRP_WAS_TRIMMED(e4b.bd_info) && - minblocks >= atomic_read(&EXT4_SB(sb)->s_last_trim_minblks)) - goto out; - - start = (e4b.bd_info->bb_first_free > start) ? - e4b.bd_info->bb_first_free : start; - - while (start <= max) { - start = mb_find_next_zero_bit(bitmap, max + 1, start); - if (start > max) - break; - next = mb_find_next_bit(bitmap, max + 1, start); - if ((next - start) >= minblocks) { - ret = ext4_trim_extent(sb, start, - next - start, group, &e4b); - if (ret && ret != -EOPNOTSUPP) - break; - ret = 0; - count += next - start; - } - free_count += next - start; - start = next + 1; - - if (fatal_signal_pending(current)) { - count = -ERESTARTSYS; - break; - } - - if (need_resched()) { - ext4_unlock_group(sb, group); - cond_resched(); - ext4_lock_group(sb, group); - } - - if ((e4b.bd_info->bb_free - free_count) < minblocks) - break; - } + if (!EXT4_MB_GRP_WAS_TRIMMED(e4b.bd_info) || + minblocks < EXT4_SB(sb)->s_last_trim_minblks) + ret = ext4_try_to_trim_range(sb, &e4b, start, max, minblocks); + else + ret = 0; - if (!ret) { - ret = count; - EXT4_MB_GRP_SET_TRIMMED(e4b.bd_info); - } -out: ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); ext4_debug("trimmed %d blocks in the group %d\n", - count, group); + ret, group); return ret; } @@ -5258,6 +5320,7 @@ out: */ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) { + struct request_queue *q = bdev_get_queue(sb->s_bdev); struct ext4_group_info *grp; ext4_group_t group, first_group, last_group; ext4_grpblk_t cnt = 0, first_cluster, last_cluster; @@ -5276,7 +5339,14 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) start >= max_blks || range->len < sb->s_blocksize) return -EINVAL; - if (end >= max_blks) + /* No point to try to trim less than discard granularity */ + if (range->minlen < q->limits.discard_granularity) { + minlen = EXT4_NUM_B2C(EXT4_SB(sb), + q->limits.discard_granularity >> sb->s_blocksize_bits); + if (minlen > EXT4_CLUSTERS_PER_GROUP(sb)) + goto out; + } + if (end >= max_blks - 1) end = max_blks - 1; if (end <= first_data_blk) goto out; @@ -5293,6 +5363,8 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) end = EXT4_CLUSTERS_PER_GROUP(sb) - 1; for (group = first_group; group <= last_group; group++) { + if (ext4_trim_interrupted()) + break; grp = ext4_get_group_info(sb, group); /* We only do this if the grp has never been initialized */ if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) { @@ -5309,10 +5381,9 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) */ if (group == last_group) end = last_cluster; - if (grp->bb_free >= minlen) { cnt = ext4_trim_all_free(sb, group, first_cluster, - end, minlen); + end, minlen); if (cnt < 0) { ret = cnt; break; @@ -5328,7 +5399,7 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) } if (!ret) - atomic_set(&EXT4_SB(sb)->s_last_trim_minblks, minlen); + EXT4_SB(sb)->s_last_trim_minblks = minlen; out: range->len = EXT4_C2B(EXT4_SB(sb), trimmed) << sb->s_blocksize_bits; @@ -5357,8 +5428,7 @@ ext4_mballoc_query_range( ext4_lock_group(sb, group); - start = (e4b.bd_info->bb_first_free > start) ? - e4b.bd_info->bb_first_free : start; + start = max(e4b.bd_info->bb_first_free, start); if (end >= EXT4_CLUSTERS_PER_GROUP(sb)) end = EXT4_CLUSTERS_PER_GROUP(sb) - 1; diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index bec4ad787c7d..4a72583c7559 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -435,7 +435,7 @@ int ext4_ext_migrate(struct inode *inode) struct inode *tmp_inode = NULL; struct migrate_struct lb; unsigned long max_entries; - __u32 goal; + __u32 goal, tmp_csum_seed; uid_t owner[2]; /* @@ -443,7 +443,8 @@ int ext4_ext_migrate(struct inode *inode) * already is extent-based, error out. */ if (!ext4_has_feature_extents(inode->i_sb) || - (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) + ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) || + ext4_has_inline_data(inode)) return -EINVAL; if (S_ISLNK(inode->i_mode) && inode->i_blocks == 0) @@ -455,12 +456,12 @@ int ext4_ext_migrate(struct inode *inode) percpu_down_write(&sbi->s_writepages_rwsem); /* - * Worst case we can touch the allocation bitmaps, a bgd - * block, and a block to link in the orphan list. We do need - * need to worry about credits for modifying the quota inode. + * Worst case we can touch the allocation bitmaps and a block + * group descriptor block. We do need need to worry about + * credits for modifying the quota inode. */ handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, - 4 + EXT4_MAXQUOTAS_TRANS_BLOCKS(inode->i_sb)); + 3 + EXT4_MAXQUOTAS_TRANS_BLOCKS(inode->i_sb)); if (IS_ERR(handle)) { retval = PTR_ERR(handle); @@ -477,6 +478,14 @@ int ext4_ext_migrate(struct inode *inode) ext4_journal_stop(handle); goto out_unlock; } + /* + * Use the correct seed for checksum (i.e. the seed from 'inode'). This + * is so that the metadata blocks will have the correct checksum after + * the migration. + */ + ei = EXT4_I(inode); + tmp_csum_seed = EXT4_I(tmp_inode)->i_csum_seed; + EXT4_I(tmp_inode)->i_csum_seed = ei->i_csum_seed; i_size_write(tmp_inode, i_size_read(inode)); /* * Set the i_nlink to zero so it will be deleted later @@ -485,7 +494,6 @@ int ext4_ext_migrate(struct inode *inode) clear_nlink(tmp_inode); ext4_ext_tree_init(handle, tmp_inode); - ext4_orphan_add(handle, tmp_inode); ext4_journal_stop(handle); /* @@ -510,17 +518,10 @@ int ext4_ext_migrate(struct inode *inode) handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1); if (IS_ERR(handle)) { - /* - * It is impossible to update on-disk structures without - * a handle, so just rollback in-core changes and live other - * work to orphan_list_cleanup() - */ - ext4_orphan_del(NULL, tmp_inode); retval = PTR_ERR(handle); goto out_tmp_inode; } - ei = EXT4_I(inode); i_data = ei->i_data; memset(&lb, 0, sizeof(lb)); @@ -594,6 +595,7 @@ err_out: * the inode is not visible to user space. */ tmp_inode->i_blocks = 0; + EXT4_I(tmp_inode)->i_csum_seed = tmp_csum_seed; /* Reset the extent details */ ext4_ext_tree_init(handle, tmp_inode); diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 186a2dd05bd8..93d392576c12 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -53,6 +53,7 @@ static struct buffer_head *ext4_append(handle_t *handle, struct inode *inode, ext4_lblk_t *block) { + struct ext4_map_blocks map; struct buffer_head *bh; int err; @@ -62,6 +63,21 @@ static struct buffer_head *ext4_append(handle_t *handle, return ERR_PTR(-ENOSPC); *block = inode->i_size >> inode->i_sb->s_blocksize_bits; + map.m_lblk = *block; + map.m_len = 1; + + /* + * We're appending new directory block. Make sure the block is not + * allocated yet, otherwise we will end up corrupting the + * directory. + */ + err = ext4_map_blocks(NULL, inode, &map, 0); + if (err < 0) + return ERR_PTR(err); + if (err) { + EXT4_ERROR_INODE(inode, "Logical block already allocated"); + return ERR_PTR(-EFSCORRUPTED); + } bh = ext4_bread(handle, inode, *block, EXT4_GET_BLOCKS_CREATE); if (IS_ERR(bh)) @@ -272,9 +288,9 @@ static struct dx_frame *dx_probe(struct ext4_filename *fname, struct dx_hash_info *hinfo, struct dx_frame *frame); static void dx_release(struct dx_frame *frames); -static int dx_make_map(struct inode *dir, struct ext4_dir_entry_2 *de, - unsigned blocksize, struct dx_hash_info *hinfo, - struct dx_map_entry map[]); +static int dx_make_map(struct inode *dir, struct buffer_head *bh, + struct dx_hash_info *hinfo, + struct dx_map_entry *map_tail); static void dx_sort_map(struct dx_map_entry *map, unsigned count); static struct ext4_dir_entry_2 *dx_move_dirents(char *from, char *to, struct dx_map_entry *offsets, int count, unsigned blocksize); @@ -306,17 +322,17 @@ static struct ext4_dir_entry_tail *get_dirent_tail(struct inode *inode, struct ext4_dir_entry *de) { struct ext4_dir_entry_tail *t; + int blocksize = EXT4_BLOCK_SIZE(inode->i_sb); #ifdef PARANOID struct ext4_dir_entry *d, *top; d = de; top = (struct ext4_dir_entry *)(((void *)de) + - (EXT4_BLOCK_SIZE(inode->i_sb) - - sizeof(struct ext4_dir_entry_tail))); - while (d < top && d->rec_len) + (blocksize - sizeof(struct ext4_dir_entry_tail))); + while (d < top && ext4_rec_len_from_disk(d->rec_len, blocksize)) d = (struct ext4_dir_entry *)(((void *)d) + - le16_to_cpu(d->rec_len)); + ext4_rec_len_from_disk(d->rec_len, blocksize)); if (d != top) return NULL; @@ -327,7 +343,8 @@ static struct ext4_dir_entry_tail *get_dirent_tail(struct inode *inode, #endif if (t->det_reserved_zero1 || - le16_to_cpu(t->det_rec_len) != sizeof(struct ext4_dir_entry_tail) || + (ext4_rec_len_from_disk(t->det_rec_len, blocksize) != + sizeof(struct ext4_dir_entry_tail)) || t->det_reserved_zero2 || t->det_reserved_ft != EXT4_FT_DIR_CSUM) return NULL; @@ -409,13 +426,14 @@ static struct dx_countlimit *get_dx_countlimit(struct inode *inode, struct ext4_dir_entry *dp; struct dx_root_info *root; int count_offset; + int blocksize = EXT4_BLOCK_SIZE(inode->i_sb); + unsigned int rlen = ext4_rec_len_from_disk(dirent->rec_len, blocksize); - if (le16_to_cpu(dirent->rec_len) == EXT4_BLOCK_SIZE(inode->i_sb)) + if (rlen == blocksize) count_offset = 8; - else if (le16_to_cpu(dirent->rec_len) == 12) { + else if (rlen == 12) { dp = (struct ext4_dir_entry *)(((void *)dirent) + 12); - if (le16_to_cpu(dp->rec_len) != - EXT4_BLOCK_SIZE(inode->i_sb) - 12) + if (ext4_rec_len_from_disk(dp->rec_len, blocksize) != blocksize - 12) return NULL; root = (struct dx_root_info *)(((void *)dp + 12)); if (root->reserved_zero || @@ -748,12 +766,14 @@ static struct dx_frame * dx_probe(struct ext4_filename *fname, struct inode *dir, struct dx_hash_info *hinfo, struct dx_frame *frame_in) { - unsigned count, indirect; + unsigned count, indirect, level, i; struct dx_entry *at, *entries, *p, *q, *m; struct dx_root *root; struct dx_frame *frame = frame_in; struct dx_frame *ret_err = ERR_PTR(ERR_BAD_DX_DIR); u32 hash; + ext4_lblk_t block; + ext4_lblk_t blocks[EXT4_HTREE_LEVEL]; memset(frame_in, 0, EXT4_HTREE_LEVEL * sizeof(frame_in[0])); frame->bh = ext4_read_dirblock(dir, 0, INDEX); @@ -809,6 +829,8 @@ dx_probe(struct ext4_filename *fname, struct inode *dir, } dxtrace(printk("Look up %x", hash)); + level = 0; + blocks[0] = 0; while (1) { count = dx_get_count(entries); if (!count || count > dx_get_limit(entries)) { @@ -850,15 +872,27 @@ dx_probe(struct ext4_filename *fname, struct inode *dir, dx_get_block(at))); frame->entries = entries; frame->at = at; - if (!indirect--) + + block = dx_get_block(at); + for (i = 0; i <= level; i++) { + if (blocks[i] == block) { + ext4_warning_inode(dir, + "dx entry: tree cycle block %u points back to block %u", + blocks[level], block); + goto fail; + } + } + if (++level > indirect) return frame; + blocks[level] = block; frame++; - frame->bh = ext4_read_dirblock(dir, dx_get_block(at), INDEX); + frame->bh = ext4_read_dirblock(dir, block, INDEX); if (IS_ERR(frame->bh)) { ret_err = (struct dx_frame *) frame->bh; frame->bh = NULL; goto fail; } + entries = ((struct dx_node *) frame->bh->b_data)->entries; if (dx_get_limit(entries) != dx_node_limit(dir)) { @@ -1203,25 +1237,34 @@ static inline int search_dirblock(struct buffer_head *bh, * Create map of hash values, offsets, and sizes, stored at end of block. * Returns number of entries mapped. */ -static int dx_make_map(struct inode *dir, struct ext4_dir_entry_2 *de, - unsigned blocksize, struct dx_hash_info *hinfo, +static int dx_make_map(struct inode *dir, struct buffer_head *bh, + struct dx_hash_info *hinfo, struct dx_map_entry *map_tail) { int count = 0; - char *base = (char *) de; + struct ext4_dir_entry_2 *de = (struct ext4_dir_entry_2 *)bh->b_data; + unsigned int buflen = bh->b_size; + char *base = bh->b_data; struct dx_hash_info h = *hinfo; + int blocksize = EXT4_BLOCK_SIZE(dir->i_sb); - while ((char *) de < base + blocksize) { + if (ext4_has_metadata_csum(dir->i_sb)) + buflen -= sizeof(struct ext4_dir_entry_tail); + + while ((char *) de < base + buflen) { + if (ext4_check_dir_entry(dir, NULL, de, bh, base, buflen, + ((char *)de) - base)) + return -EFSCORRUPTED; if (de->name_len && de->inode) { ext4fs_dirhash(de->name, de->name_len, &h); map_tail--; map_tail->hash = h.hash; map_tail->offs = ((char *) de - base)>>2; - map_tail->size = le16_to_cpu(de->rec_len); + map_tail->size = ext4_rec_len_from_disk(de->rec_len, + blocksize); count++; cond_resched(); } - /* XXX: do we need to check rec_len == 0 case? -Chris */ de = ext4_next_entry(de, blocksize); } return count; @@ -1343,7 +1386,7 @@ static int is_dx_internal_node(struct inode *dir, ext4_lblk_t block, } /* - * ext4_find_entry() + * __ext4_find_entry() * * finds an entry in the specified directory with the wanted name. It * returns the cache buffer in which the entry was found, and the entry @@ -1353,45 +1396,37 @@ static int is_dx_internal_node(struct inode *dir, ext4_lblk_t block, * The returned buffer_head has ->b_count elevated. The caller is expected * to brelse() it when appropriate. */ -static struct buffer_head * ext4_find_entry (struct inode *dir, - const struct qstr *d_name, - struct ext4_dir_entry_2 **res_dir, - int *inlined) +static struct buffer_head *__ext4_find_entry(struct inode *dir, + struct ext4_filename *fname, + struct ext4_dir_entry_2 **res_dir, + int *inlined) { struct super_block *sb; struct buffer_head *bh_use[NAMEI_RA_SIZE]; struct buffer_head *bh, *ret = NULL; ext4_lblk_t start, block; - const u8 *name = d_name->name; + const u8 *name = fname->usr_fname->name; size_t ra_max = 0; /* Number of bh's in the readahead buffer, bh_use[] */ size_t ra_ptr = 0; /* Current index into readahead buffer */ ext4_lblk_t nblocks; int i, namelen, retval; - struct ext4_filename fname; *res_dir = NULL; sb = dir->i_sb; - namelen = d_name->len; + namelen = fname->usr_fname->len; if (namelen > EXT4_NAME_LEN) return NULL; - retval = ext4_fname_setup_filename(dir, d_name, 1, &fname); - if (retval == -ENOENT) - return NULL; - if (retval) - return ERR_PTR(retval); - if (ext4_has_inline_data(dir)) { int has_inline_data = 1; - ret = ext4_find_inline_entry(dir, &fname, res_dir, + ret = ext4_find_inline_entry(dir, fname, res_dir, &has_inline_data); - if (has_inline_data) { - if (inlined) - *inlined = 1; + if (inlined) + *inlined = has_inline_data; + if (has_inline_data) goto cleanup_and_exit; - } } if ((namelen <= 2) && (name[0] == '.') && @@ -1405,7 +1440,7 @@ static struct buffer_head * ext4_find_entry (struct inode *dir, goto restart; } if (is_dx(dir)) { - ret = ext4_dx_find_entry(dir, &fname, res_dir); + ret = ext4_dx_find_entry(dir, fname, res_dir); /* * On success, or if the error was file not found, * return. Otherwise, fall back to doing a search the @@ -1470,7 +1505,7 @@ restart: goto cleanup_and_exit; } set_buffer_verified(bh); - i = search_dirblock(bh, dir, &fname, + i = search_dirblock(bh, dir, fname, block << EXT4_BLOCK_SIZE_BITS(sb), res_dir); if (i == 1) { EXT4_I(dir)->i_dir_start_lookup = block; @@ -1501,10 +1536,50 @@ cleanup_and_exit: /* Clean up the read-ahead blocks */ for (; ra_ptr < ra_max; ra_ptr++) brelse(bh_use[ra_ptr]); - ext4_fname_free_filename(&fname); return ret; } +static struct buffer_head *ext4_find_entry(struct inode *dir, + const struct qstr *d_name, + struct ext4_dir_entry_2 **res_dir, + int *inlined) +{ + int err; + struct ext4_filename fname; + struct buffer_head *bh; + + err = ext4_fname_setup_filename(dir, d_name, 1, &fname); + if (err == -ENOENT) + return NULL; + if (err) + return ERR_PTR(err); + + bh = __ext4_find_entry(dir, &fname, res_dir, inlined); + + ext4_fname_free_filename(&fname); + return bh; +} + +static struct buffer_head *ext4_lookup_entry(struct inode *dir, + struct dentry *dentry, + struct ext4_dir_entry_2 **res_dir) +{ + int err; + struct ext4_filename fname; + struct buffer_head *bh; + + err = ext4_fname_prepare_lookup(dir, dentry, &fname); + if (err == -ENOENT) + return NULL; + if (err) + return ERR_PTR(err); + + bh = __ext4_find_entry(dir, &fname, res_dir, NULL); + + ext4_fname_free_filename(&fname); + return bh; +} + static struct buffer_head * ext4_dx_find_entry(struct inode *dir, struct ext4_filename *fname, struct ext4_dir_entry_2 **res_dir) @@ -1563,16 +1638,11 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi struct inode *inode; struct ext4_dir_entry_2 *de; struct buffer_head *bh; - int err; - - err = fscrypt_prepare_lookup(dir, dentry, flags); - if (err) - return ERR_PTR(err); if (dentry->d_name.len > EXT4_NAME_LEN) return ERR_PTR(-ENAMETOOLONG); - bh = ext4_find_entry(dir, &dentry->d_name, &de, NULL); + bh = ext4_lookup_entry(dir, dentry, &de); if (IS_ERR(bh)) return (struct dentry *) bh; inode = NULL; @@ -1692,7 +1762,8 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, struct dx_hash_info *hinfo) { unsigned blocksize = dir->i_sb->s_blocksize; - unsigned count, continued; + unsigned continued; + int count; struct buffer_head *bh2; ext4_lblk_t newblock; u32 hash2; @@ -1728,8 +1799,11 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, /* create map in the end of data2 block */ map = (struct dx_map_entry *) (data2 + blocksize); - count = dx_make_map(dir, (struct ext4_dir_entry_2 *) data1, - blocksize, hinfo, map); + count = dx_make_map(dir, *bh, hinfo, map); + if (count < 0) { + err = count; + goto journal_error; + } map -= count; dx_sort_map(map, count); /* Ensure that neither split block is over half full */ @@ -2078,6 +2152,9 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, if (!dentry->d_name.len) return -EINVAL; + if (fscrypt_is_nokey_name(dentry)) + return -ENOKEY; + retval = ext4_fname_setup_filename(dir, &dentry->d_name, 0, &fname); if (retval) return retval; @@ -2284,11 +2361,10 @@ again: (frame - 1)->bh); if (err) goto journal_error; - if (restart) { - err = ext4_handle_dirty_dx_node(handle, dir, - frame->bh); + err = ext4_handle_dirty_dx_node(handle, dir, + frame->bh); + if (restart || err) goto journal_error; - } } else { struct dx_root *dxroot; memcpy((char *) entries2, (char *) entries, @@ -2769,11 +2845,8 @@ bool ext4_empty_dir(struct inode *inode) de = (struct ext4_dir_entry_2 *) (bh->b_data + (offset & (sb->s_blocksize - 1))); if (ext4_check_dir_entry(inode, NULL, de, bh, - bh->b_data, bh->b_size, offset)) { - offset = (offset | (sb->s_blocksize - 1)) + 1; - continue; - } - if (le32_to_cpu(de->inode)) { + bh->b_data, bh->b_size, offset) || + le32_to_cpu(de->inode)) { brelse(bh); return false; } @@ -3303,6 +3376,9 @@ static struct buffer_head *ext4_get_first_dir_block(handle_t *handle, struct buffer_head *bh; if (!ext4_has_inline_data(inode)) { + struct ext4_dir_entry_2 *de; + unsigned int offset; + /* The first directory block must not be a hole, so * treat it as DIRENT_HTREE */ @@ -3311,9 +3387,30 @@ static struct buffer_head *ext4_get_first_dir_block(handle_t *handle, *retval = PTR_ERR(bh); return NULL; } - *parent_de = ext4_next_entry( - (struct ext4_dir_entry_2 *)bh->b_data, - inode->i_sb->s_blocksize); + + de = (struct ext4_dir_entry_2 *) bh->b_data; + if (ext4_check_dir_entry(inode, NULL, de, bh, bh->b_data, + bh->b_size, 0) || + le32_to_cpu(de->inode) != inode->i_ino || + strcmp(".", de->name)) { + EXT4_ERROR_INODE(inode, "directory missing '.'"); + brelse(bh); + *retval = -EFSCORRUPTED; + return NULL; + } + offset = ext4_rec_len_from_disk(de->rec_len, + inode->i_sb->s_blocksize); + de = ext4_next_entry(de, inode->i_sb->s_blocksize); + if (ext4_check_dir_entry(inode, NULL, de, bh, bh->b_data, + bh->b_size, offset) || + le32_to_cpu(de->inode) == 0 || strcmp("..", de->name)) { + EXT4_ERROR_INODE(inode, "directory missing '..'"); + brelse(bh); + *retval = -EFSCORRUPTED; + return NULL; + } + *parent_de = de; + return bh; } @@ -3406,12 +3503,36 @@ static int ext4_setent(handle_t *handle, struct ext4_renament *ent, return retval; } } - brelse(ent->bh); - ent->bh = NULL; return 0; } +static void ext4_resetent(handle_t *handle, struct ext4_renament *ent, + unsigned ino, unsigned file_type) +{ + struct ext4_renament old = *ent; + int retval = 0; + + /* + * old->de could have moved from under us during make indexed dir, + * so the old->de may no longer valid and need to find it again + * before reset old inode info. + */ + old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de, + &old.inlined); + if (IS_ERR(old.bh)) + retval = PTR_ERR(old.bh); + if (!old.bh) + retval = -ENOENT; + if (retval) { + ext4_std_error(old.dir->i_sb, retval); + return; + } + + ext4_setent(handle, &old, ino, file_type); + brelse(old.bh); +} + static int ext4_find_delete_entry(handle_t *handle, struct inode *dir, const struct qstr *d_name) { @@ -3560,7 +3681,8 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, return retval; } - old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de, NULL); + old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de, + &old.inlined); if (IS_ERR(old.bh)) return PTR_ERR(old.bh); /* @@ -3571,14 +3693,14 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, */ retval = -ENOENT; if (!old.bh || le32_to_cpu(old.de->inode) != old.inode->i_ino) - goto end_rename; + goto release_bh; new.bh = ext4_find_entry(new.dir, &new.dentry->d_name, &new.de, &new.inlined); if (IS_ERR(new.bh)) { retval = PTR_ERR(new.bh); new.bh = NULL; - goto end_rename; + goto release_bh; } if (new.bh) { if (!new.inode) { @@ -3595,18 +3717,17 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, handle = ext4_journal_start(old.dir, EXT4_HT_DIR, credits); if (IS_ERR(handle)) { retval = PTR_ERR(handle); - handle = NULL; - goto end_rename; + goto release_bh; } } else { whiteout = ext4_whiteout_for_rename(&old, credits, &handle); if (IS_ERR(whiteout)) { retval = PTR_ERR(whiteout); - whiteout = NULL; - goto end_rename; + goto release_bh; } } + old_file_type = old.de->file_type; if (IS_DIRSYNC(old.dir) || IS_DIRSYNC(new.dir)) ext4_handle_sync(handle); @@ -3634,7 +3755,6 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, force_reread = (new.dir->i_ino == old.dir->i_ino && ext4_test_inode_flag(new.dir, EXT4_INODE_INLINE_DATA)); - old_file_type = old.de->file_type; if (whiteout) { /* * Do this before adding a new entry, so the old entry is sure @@ -3706,17 +3826,23 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, retval = 0; end_rename: - brelse(old.dir_bh); - brelse(old.bh); - brelse(new.bh); if (whiteout) { - if (retval) + if (retval) { + ext4_resetent(handle, &old, + old.inode->i_ino, old_file_type); drop_nlink(whiteout); + ext4_orphan_add(handle, whiteout); + } unlock_new_inode(whiteout); + ext4_journal_stop(handle); iput(whiteout); - } - if (handle) + } else { ext4_journal_stop(handle); + } +release_bh: + brelse(old.dir_bh); + brelse(old.bh); + brelse(new.bh); return retval; } @@ -3749,6 +3875,9 @@ static int ext4_cross_rename(struct inode *old_dir, struct dentry *old_dentry, retval = dquot_initialize(old.dir); if (retval) return retval; + retval = dquot_initialize(old.inode); + if (retval) + return retval; retval = dquot_initialize(new.dir); if (retval) return retval; diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 9cc79b7b0df1..bf910f266469 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -105,8 +105,10 @@ static void ext4_finish_bio(struct bio *bio) continue; } clear_buffer_async_write(bh); - if (bio->bi_status) + if (bio->bi_status) { + set_buffer_write_io_error(bh); buffer_io_error(bh); + } } while ((bh = bh->b_this_page) != head); bit_spin_unlock(BH_Uptodate_Lock, &head->b_state); local_irq_restore(flags); @@ -386,7 +388,8 @@ static int io_submit_init_bio(struct ext4_io_submit *io, static int io_submit_add_bh(struct ext4_io_submit *io, struct inode *inode, - struct page *page, + struct page *pagecache_page, + struct page *bounce_page, struct buffer_head *bh) { int ret; @@ -401,10 +404,11 @@ submit_and_retry: return ret; io->io_bio->bi_write_hint = inode->i_write_hint; } - ret = bio_add_page(io->io_bio, page, bh->b_size, bh_offset(bh)); + ret = bio_add_page(io->io_bio, bounce_page ?: pagecache_page, + bh->b_size, bh_offset(bh)); if (ret != bh->b_size) goto submit_and_retry; - wbc_account_io(io->io_wbc, page, bh->b_size); + wbc_account_io(io->io_wbc, pagecache_page, bh->b_size); io->io_next_block++; return 0; } @@ -512,8 +516,7 @@ int ext4_bio_write_page(struct ext4_io_submit *io, do { if (!buffer_async_write(bh)) continue; - ret = io_submit_add_bh(io, inode, - data_page ? data_page : page, bh); + ret = io_submit_add_bh(io, inode, page, data_page, bh); if (ret) { /* * We only get here on ENOMEM. Not much else diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index ef552d93708e..f4b3d450dead 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -53,6 +53,16 @@ int ext4_resize_begin(struct super_block *sb) return -EPERM; /* + * If the reserved GDT blocks is non-zero, the resize_inode feature + * should always be set. + */ + if (EXT4_SB(sb)->s_es->s_reserved_gdt_blocks && + !ext4_has_feature_resize_inode(sb)) { + ext4_error(sb, "resize_inode disabled but reserved GDT blocks non-zero"); + return -EFSCORRUPTED; + } + + /* * If we are not using the primary superblock/GDT copy don't resize, * because the user tools have no way of handling this. Probably a * bad time to do it anyways. @@ -74,6 +84,11 @@ int ext4_resize_begin(struct super_block *sb) return -EPERM; } + if (ext4_has_feature_sparse_super2(sb)) { + ext4_msg(sb, KERN_ERR, "Online resizing not supported with sparse_super2"); + return -EOPNOTSUPP; + } + if (test_and_set_bit_lock(EXT4_FLAGS_RESIZING, &EXT4_SB(sb)->s_ext4_flags)) ret = -EBUSY; @@ -557,13 +572,8 @@ static int setup_new_flex_group_blocks(struct super_block *sb, if (meta_bg == 0 && !ext4_bg_has_super(sb, group)) goto handle_itb; - if (meta_bg == 1) { - ext4_group_t first_group; - first_group = ext4_meta_bg_first_group(sb, group); - if (first_group != group + 1 && - first_group != group + EXT4_DESC_PER_BLOCK(sb) - 1) - goto handle_itb; - } + if (meta_bg == 1) + goto handle_itb; block = start + ext4_bg_has_super(sb, group); /* Copy all of the GDT blocks into the backup in this group */ @@ -861,8 +871,10 @@ static int add_new_gdb(handle_t *handle, struct inode *inode, BUFFER_TRACE(dind, "get_write_access"); err = ext4_journal_get_write_access(handle, dind); - if (unlikely(err)) + if (unlikely(err)) { ext4_std_error(sb, err); + goto errout; + } /* ext4_reserve_inode_write() gets a reference on the iloc */ err = ext4_reserve_inode_write(handle, inode, &iloc); @@ -1466,6 +1478,7 @@ static void ext4_update_super(struct super_block *sb, * Update the fs overhead information */ ext4_calculate_overhead(sb); + es->s_overhead_clusters = cpu_to_le32(sbi->s_overhead); if (test_opt(sb, DEBUG)) printk(KERN_DEBUG "EXT4-fs: added group %u:" @@ -1547,10 +1560,12 @@ exit_journal: int gdb_num_end = ((group + flex_gd->count - 1) / EXT4_DESC_PER_BLOCK(sb)); int meta_bg = ext4_has_feature_meta_bg(sb); + sector_t padding_blocks = meta_bg ? 0 : sbi->s_sbh->b_blocknr - + ext4_group_first_block_no(sb, 0); sector_t old_gdb = 0; - update_backups(sb, sbi->s_sbh->b_blocknr, (char *)es, - sizeof(struct ext4_super_block), 0); + update_backups(sb, ext4_group_first_block_no(sb, 0), + (char *)es, sizeof(struct ext4_super_block), 0); for (; gdb_num <= gdb_num_end; gdb_num++) { struct buffer_head *gdb_bh; @@ -1558,8 +1573,8 @@ exit_journal: gdb_num); if (old_gdb == gdb_bh->b_blocknr) continue; - update_backups(sb, gdb_bh->b_blocknr, gdb_bh->b_data, - gdb_bh->b_size, meta_bg); + update_backups(sb, gdb_bh->b_blocknr - padding_blocks, + gdb_bh->b_data, gdb_bh->b_size, meta_bg); old_gdb = gdb_bh->b_blocknr; } } @@ -1757,7 +1772,7 @@ errout: if (test_opt(sb, DEBUG)) printk(KERN_DEBUG "EXT4-fs: extended group to %llu " "blocks\n", ext4_blocks_count(es)); - update_backups(sb, EXT4_SB(sb)->s_sbh->b_blocknr, + update_backups(sb, ext4_group_first_block_no(sb, 0), (char *)es, sizeof(struct ext4_super_block), 0); } return err; @@ -1922,9 +1937,7 @@ static int ext4_convert_meta_bg(struct super_block *sb, struct inode *inode) errout: ret = ext4_journal_stop(handle); - if (!err) - err = ret; - return ret; + return err ? err : ret; invalid_resize_inode: ext4_error(sb, "corrupted/inconsistent resize inode"); @@ -1963,6 +1976,16 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count) } brelse(bh); + /* + * For bigalloc, trim the requested size to the nearest cluster + * boundary to avoid creating an unusable filesystem. We do this + * silently, instead of returning an error, to avoid breaking + * callers that blindly resize the filesystem to the full size of + * the underlying block device. + */ + if (ext4_has_feature_bigalloc(sb)) + n_blocks_count &= ~((1 << EXT4_CLUSTER_BITS(sb)) - 1); + retry: o_blocks_count = ext4_blocks_count(es); @@ -2064,7 +2087,7 @@ retry: goto out; } - if (ext4_blocks_count(es) == n_blocks_count) + if (ext4_blocks_count(es) == n_blocks_count && n_blocks_count_retry == 0) goto out; err = ext4_alloc_flex_bg_array(sb, n_group + 1); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 0c15ff19acbd..926063a6d232 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -454,19 +454,17 @@ static bool system_going_down(void) static void ext4_handle_error(struct super_block *sb) { + journal_t *journal = EXT4_SB(sb)->s_journal; + if (test_opt(sb, WARN_ON_ERROR)) WARN_ON_ONCE(1); - if (sb_rdonly(sb)) + if (sb_rdonly(sb) || test_opt(sb, ERRORS_CONT)) return; - if (!test_opt(sb, ERRORS_CONT)) { - journal_t *journal = EXT4_SB(sb)->s_journal; - - EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED; - if (journal) - jbd2_journal_abort(journal, -EIO); - } + EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED; + if (journal) + jbd2_journal_abort(journal, -EIO); /* * We force ERRORS_RO behavior when system is rebooting. Otherwise we * could panic during 'reboot -f' as the underlying device got already @@ -907,10 +905,16 @@ static void ext4_blkdev_put(struct block_device *bdev) static void ext4_blkdev_remove(struct ext4_sb_info *sbi) { struct block_device *bdev; - bdev = sbi->journal_bdev; + bdev = sbi->s_journal_bdev; if (bdev) { + /* + * Invalidate the journal device's buffers. We don't want them + * floating about in memory - the physical journal device may + * hotswapped, and it breaks the `ro-after' testing code. + */ + invalidate_bdev(bdev); ext4_blkdev_put(bdev); - sbi->journal_bdev = NULL; + sbi->s_journal_bdev = NULL; } } @@ -1034,14 +1038,8 @@ static void ext4_put_super(struct super_block *sb) sync_blockdev(sb->s_bdev); invalidate_bdev(sb->s_bdev); - if (sbi->journal_bdev && sbi->journal_bdev != sb->s_bdev) { - /* - * Invalidate the journal device's buffers. We don't want them - * floating about in memory - the physical journal device may - * hotswapped, and it breaks the `ro-after' testing code. - */ - sync_blockdev(sbi->journal_bdev); - invalidate_bdev(sbi->journal_bdev); + if (sbi->s_journal_bdev && sbi->s_journal_bdev != sb->s_bdev) { + sync_blockdev(sbi->s_journal_bdev); ext4_blkdev_remove(sbi); } if (sbi->s_ea_inode_cache) { @@ -1083,6 +1081,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) return NULL; inode_set_iversion(&ei->vfs_inode, 1); + ei->i_flags = 0; spin_lock_init(&ei->i_raw_lock); INIT_LIST_HEAD(&ei->i_prealloc_list); spin_lock_init(&ei->i_prealloc_lock); @@ -1690,6 +1689,7 @@ static const struct mount_opts { MOPT_EXT4_ONLY | MOPT_CLEAR}, {Opt_warn_on_error, EXT4_MOUNT_WARN_ON_ERROR, MOPT_SET}, {Opt_nowarn_on_error, EXT4_MOUNT_WARN_ON_ERROR, MOPT_CLEAR}, + {Opt_commit, 0, MOPT_NO_EXT2}, {Opt_nojournal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM, MOPT_EXT4_ONLY | MOPT_CLEAR}, {Opt_journal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM, @@ -1748,8 +1748,8 @@ static const struct mount_opts { {Opt_noquota, (EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA | EXT4_MOUNT_GRPQUOTA | EXT4_MOUNT_PRJQUOTA), MOPT_CLEAR | MOPT_Q}, - {Opt_usrjquota, 0, MOPT_Q}, - {Opt_grpjquota, 0, MOPT_Q}, + {Opt_usrjquota, 0, MOPT_Q | MOPT_STRING}, + {Opt_grpjquota, 0, MOPT_Q | MOPT_STRING}, {Opt_offusrjquota, 0, MOPT_Q}, {Opt_offgrpjquota, 0, MOPT_Q}, {Opt_jqfmt_vfsold, QFMT_VFS_OLD, MOPT_QFMT}, @@ -2423,11 +2423,9 @@ static __le16 ext4_group_desc_csum(struct super_block *sb, __u32 block_group, crc = crc16(crc, (__u8 *)gdp, offset); offset += sizeof(gdp->bg_checksum); /* skip checksum */ /* for checksum of struct ext4_group_desc do the rest...*/ - if (ext4_has_feature_64bit(sb) && - offset < le16_to_cpu(sbi->s_es->s_desc_size)) + if (ext4_has_feature_64bit(sb) && offset < sbi->s_desc_size) crc = crc16(crc, (__u8 *)gdp + offset, - le16_to_cpu(sbi->s_es->s_desc_size) - - offset); + sbi->s_desc_size - offset); out: return cpu_to_le16(crc); @@ -2631,9 +2629,6 @@ static void ext4_orphan_cleanup(struct super_block *sb, sb->s_flags &= ~SB_RDONLY; } #ifdef CONFIG_QUOTA - /* Needed for iput() to work correctly and not trash data */ - sb->s_flags |= SB_ACTIVE; - /* * Turn on quotas which were not enabled for read-only mounts if * filesystem has quota feature, so that they are updated correctly. @@ -2694,8 +2689,15 @@ static void ext4_orphan_cleanup(struct super_block *sb, inode_lock(inode); truncate_inode_pages(inode->i_mapping, inode->i_size); ret = ext4_truncate(inode); - if (ret) + if (ret) { + /* + * We need to clean up the in-core orphan list + * manually if ext4_truncate() failed to get a + * transaction handle. + */ + ext4_orphan_del(NULL, inode); ext4_std_error(inode->i_sb, ret); + } inode_unlock(inode); nr_truncates++; } else { @@ -3024,8 +3026,8 @@ static int ext4_run_li_request(struct ext4_li_request *elr) struct ext4_group_desc *gdp = NULL; ext4_group_t group, ngroups; struct super_block *sb; - unsigned long timeout = 0; int ret = 0; + u64 start_time; sb = elr->lr_super; ngroups = EXT4_SB(sb)->s_groups_count; @@ -3045,13 +3047,12 @@ static int ext4_run_li_request(struct ext4_li_request *elr) ret = 1; if (!ret) { - timeout = jiffies; + start_time = ktime_get_real_ns(); ret = ext4_init_inode_table(sb, group, elr->lr_timeout ? 0 : 1); if (elr->lr_timeout == 0) { - timeout = (jiffies - timeout) * - elr->lr_sbi->s_li_wait_mult; - elr->lr_timeout = timeout; + elr->lr_timeout = nsecs_to_jiffies((ktime_get_real_ns() - start_time) * + elr->lr_sbi->s_li_wait_mult); } elr->lr_next_sched = jiffies + elr->lr_timeout; elr->lr_next_group = group + 1; @@ -3110,6 +3111,7 @@ static int ext4_lazyinit_thread(void *arg) unsigned long next_wakeup, cur; BUG_ON(NULL == eli); + set_freezable(); cont_thread: while (true) { @@ -3439,9 +3441,11 @@ static int count_overhead(struct super_block *sb, ext4_group_t grp, ext4_fsblk_t first_block, last_block, b; ext4_group_t i, ngroups = ext4_get_groups_count(sb); int s, j, count = 0; + int has_super = ext4_bg_has_super(sb, grp); if (!ext4_has_feature_bigalloc(sb)) - return (ext4_bg_has_super(sb, grp) + ext4_bg_num_gdb(sb, grp) + + return (has_super + ext4_bg_num_gdb(sb, grp) + + (has_super ? le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) : 0) + sbi->s_itb_per_group + 2); first_block = le32_to_cpu(sbi->s_es->s_first_data_block) + @@ -3533,7 +3537,7 @@ int ext4_calculate_overhead(struct super_block *sb) * Add the internal journal blocks whether the journal has been * loaded or not */ - if (sbi->s_journal && !sbi->journal_bdev) + if (sbi->s_journal && !sbi->s_journal_bdev) overhead += EXT4_NUM_B2C(sbi, sbi->s_journal->j_maxlen); else if (ext4_has_feature_journal(sb) && !sbi->s_journal && j_inum) { /* j_inum for internal journal is non-zero */ @@ -4297,30 +4301,31 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) ext4_has_feature_journal_needs_recovery(sb)) { ext4_msg(sb, KERN_ERR, "required journal recovery " "suppressed and not mounted read-only"); - goto failed_mount_wq; + goto failed_mount3a; } else { /* Nojournal mode, all journal mount options are illegal */ - if (test_opt2(sb, EXPLICIT_JOURNAL_CHECKSUM)) { - ext4_msg(sb, KERN_ERR, "can't mount with " - "journal_checksum, fs mounted w/o journal"); - goto failed_mount_wq; - } if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) { ext4_msg(sb, KERN_ERR, "can't mount with " "journal_async_commit, fs mounted w/o journal"); - goto failed_mount_wq; + goto failed_mount3a; + } + + if (test_opt2(sb, EXPLICIT_JOURNAL_CHECKSUM)) { + ext4_msg(sb, KERN_ERR, "can't mount with " + "journal_checksum, fs mounted w/o journal"); + goto failed_mount3a; } if (sbi->s_commit_interval != JBD2_DEFAULT_MAX_COMMIT_AGE*HZ) { ext4_msg(sb, KERN_ERR, "can't mount with " "commit=%lu, fs mounted w/o journal", sbi->s_commit_interval / HZ); - goto failed_mount_wq; + goto failed_mount3a; } if (EXT4_MOUNT_DATA_FLAGS & (sbi->s_mount_opt ^ sbi->s_def_mount_opt)) { ext4_msg(sb, KERN_ERR, "can't mount with " "data=, fs mounted w/o journal"); - goto failed_mount_wq; + goto failed_mount3a; } sbi->s_def_mount_opt &= ~EXT4_MOUNT_JOURNAL_CHECKSUM; clear_opt(sb, JOURNAL_CHECKSUM); @@ -4420,9 +4425,18 @@ no_journal: * Get the # of file system overhead blocks from the * superblock if present. */ - if (es->s_overhead_clusters) - sbi->s_overhead = le32_to_cpu(es->s_overhead_clusters); - else { + sbi->s_overhead = le32_to_cpu(es->s_overhead_clusters); + /* ignore the precalculated value if it is ridiculous */ + if (sbi->s_overhead > ext4_blocks_count(es)) + sbi->s_overhead = 0; + /* + * If the bigalloc feature is not enabled recalculating the + * overhead doesn't take long, so we might as well just redo + * it to make sure we are using the correct value. + */ + if (!ext4_has_feature_bigalloc(sb)) + sbi->s_overhead = 0; + if (sbi->s_overhead == 0) { err = ext4_calculate_overhead(sb); if (err) goto failed_mount_wq; @@ -4522,6 +4536,7 @@ no_journal: ext4_msg(sb, KERN_ERR, "unable to initialize " "flex_bg meta info!"); + ret = -ENOMEM; goto failed_mount6; } @@ -4594,6 +4609,7 @@ cantfind_ext4: failed_mount8: ext4_unregister_sysfs(sb); + kobject_put(&sbi->s_kobj); failed_mount7: ext4_unregister_li_request(sb); failed_mount6: @@ -4657,6 +4673,7 @@ failed_mount: ext4_blkdev_remove(sbi); brelse(bh); out_fail: + invalidate_bdev(sb->s_bdev); sb->s_fs_info = NULL; kfree(sbi->s_blockgroup_lock); out_free_base: @@ -4715,7 +4732,7 @@ static struct inode *ext4_get_journal_inode(struct super_block *sb, jbd_debug(2, "Journal inode found at %p: %lld bytes\n", journal_inode, journal_inode->i_size); - if (!S_ISREG(journal_inode->i_mode)) { + if (!S_ISREG(journal_inode->i_mode) || IS_ENCRYPTED(journal_inode)) { ext4_msg(sb, KERN_ERR, "invalid journal inode"); iput(journal_inode); return NULL; @@ -4832,7 +4849,7 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb, be32_to_cpu(journal->j_superblock->s_nr_users)); goto out_journal; } - EXT4_SB(sb)->journal_bdev = bdev; + EXT4_SB(sb)->s_journal_bdev = bdev; ext4_init_journal_params(sb, journal); return journal; @@ -4963,8 +4980,10 @@ static int ext4_commit_super(struct super_block *sb, int sync) struct buffer_head *sbh = EXT4_SB(sb)->s_sbh; int error = 0; - if (!sbh || block_device_ejected(sb)) - return error; + if (!sbh) + return -EINVAL; + if (block_device_ejected(sb)) + return -ENODEV; /* * If the file system is mounted read-only, don't update the @@ -5483,9 +5502,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) } #ifdef CONFIG_QUOTA - /* Release old quota file names */ - for (i = 0; i < EXT4_MAXQUOTAS; i++) - kfree(old_opts.s_qf_names[i]); if (enable_quota) { if (sb_any_quota_suspended(sb)) dquot_resume(sb, -1); @@ -5495,6 +5511,9 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) goto restore_opts; } } + /* Release old quota file names */ + for (i = 0; i < EXT4_MAXQUOTAS; i++) + kfree(old_opts.s_qf_names[i]); #endif if (!test_opt(sb, BLOCK_VALIDITY) && sbi->system_blks) ext4_release_system_zone(sb); @@ -5511,6 +5530,13 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) return 0; restore_opts: + /* + * If there was a failing r/w to ro transition, we may need to + * re-enable quota + */ + if ((sb->s_flags & SB_RDONLY) && !(old_sb_flags & SB_RDONLY) && + sb_any_quota_suspended(sb)) + dquot_resume(sb, -1); sb->s_flags = old_sb_flags; sbi->s_mount_opt = old_opts.s_mount_opt; sbi->s_mount_opt2 = old_opts.s_mount_opt2; @@ -5704,7 +5730,7 @@ static int ext4_write_info(struct super_block *sb, int type) handle_t *handle; /* Data block + inode block */ - handle = ext4_journal_start(d_inode(sb->s_root), EXT4_HT_QUOTA, 2); + handle = ext4_journal_start_sb(sb, EXT4_HT_QUOTA, 2); if (IS_ERR(handle)) return PTR_ERR(handle); ret = dquot_commit_info(sb, type); @@ -5752,6 +5778,11 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id, /* Quotafile not on the same filesystem? */ if (path->dentry->d_sb != sb) return -EXDEV; + + /* Quota already enabled for this file? */ + if (IS_NOQUOTA(d_inode(path->dentry))) + return -EBUSY; + /* Journaling quota? */ if (EXT4_SB(sb)->s_qf_names[type]) { /* Quotafile not in fs root? */ @@ -5787,10 +5818,7 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id, lockdep_set_quota_inode(path->dentry->d_inode, I_DATA_SEM_QUOTA); err = dquot_quota_on(sb, type, format_id, path); - if (err) { - lockdep_set_quota_inode(path->dentry->d_inode, - I_DATA_SEM_NORMAL); - } else { + if (!err) { struct inode *inode = d_inode(path->dentry); handle_t *handle; @@ -5810,10 +5838,29 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id, ext4_journal_stop(handle); unlock_inode: inode_unlock(inode); + if (err) + dquot_quota_off(sb, type); } + if (err) + lockdep_set_quota_inode(path->dentry->d_inode, + I_DATA_SEM_NORMAL); return err; } +static inline bool ext4_check_quota_inum(int type, unsigned long qf_inum) +{ + switch (type) { + case USRQUOTA: + return qf_inum == EXT4_USR_QUOTA_INO; + case GRPQUOTA: + return qf_inum == EXT4_GRP_QUOTA_INO; + case PRJQUOTA: + return qf_inum >= EXT4_GOOD_OLD_FIRST_INO; + default: + BUG(); + } +} + static int ext4_quota_enable(struct super_block *sb, int type, int format_id, unsigned int flags) { @@ -5830,9 +5877,16 @@ static int ext4_quota_enable(struct super_block *sb, int type, int format_id, if (!qf_inums[type]) return -EPERM; + if (!ext4_check_quota_inum(type, qf_inums[type])) { + ext4_error(sb, "Bad quota inum: %lu, type: %d", + qf_inums[type], type); + return -EUCLEAN; + } + qf_inode = ext4_iget(sb, qf_inums[type], EXT4_IGET_SPECIAL); if (IS_ERR(qf_inode)) { - ext4_error(sb, "Bad quota inode # %lu", qf_inums[type]); + ext4_error(sb, "Bad quota inode: %lu, type: %d", + qf_inums[type], type); return PTR_ERR(qf_inode); } @@ -5871,10 +5925,22 @@ static int ext4_enable_quotas(struct super_block *sb) if (err) { ext4_warning(sb, "Failed to enable quota tracking " - "(type=%d, err=%d). Please run " - "e2fsck to fix.", type, err); - for (type--; type >= 0; type--) + "(type=%d, err=%d, ino=%lu). " + "Please run e2fsck to fix.", type, + err, qf_inums[type]); + for (type--; type >= 0; type--) { + struct inode *inode; + + inode = sb_dqopt(sb)->files[type]; + if (inode) + inode = igrab(inode); dquot_quota_off(sb, type); + if (inode) { + lockdep_set_quota_inode(inode, + I_DATA_SEM_NORMAL); + iput(inode); + } + } return err; } @@ -5976,7 +6042,7 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type, struct buffer_head *bh; handle_t *handle = journal_current_handle(); - if (EXT4_SB(sb)->s_journal && !handle) { + if (!handle) { ext4_msg(sb, KERN_WARNING, "Quota write (off=%llu, len=%llu)" " cancelled because transaction is not started", (unsigned long long)off, (unsigned long long)len); diff --git a/fs/ext4/symlink.c b/fs/ext4/symlink.c index dd05af983092..a9457fed351e 100644 --- a/fs/ext4/symlink.c +++ b/fs/ext4/symlink.c @@ -52,10 +52,19 @@ static const char *ext4_encrypted_get_link(struct dentry *dentry, return paddr; } +static int ext4_encrypted_symlink_getattr(const struct path *path, + struct kstat *stat, u32 request_mask, + unsigned int query_flags) +{ + ext4_getattr(path, stat, request_mask, query_flags); + + return fscrypt_symlink_getattr(path, stat); +} + const struct inode_operations ext4_encrypted_symlink_inode_operations = { .get_link = ext4_encrypted_get_link, .setattr = ext4_setattr, - .getattr = ext4_getattr, + .getattr = ext4_encrypted_symlink_getattr, .listxattr = ext4_listxattr, }; diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c index 9212a026a1f1..74722ce7206c 100644 --- a/fs/ext4/sysfs.c +++ b/fs/ext4/sysfs.c @@ -349,6 +349,11 @@ static void ext4_sb_release(struct kobject *kobj) complete(&sbi->s_kobj_unregister); } +static void ext4_feat_release(struct kobject *kobj) +{ + kfree(kobj); +} + static const struct sysfs_ops ext4_attr_ops = { .show = ext4_attr_show, .store = ext4_attr_store, @@ -363,7 +368,7 @@ static struct kobj_type ext4_sb_ktype = { static struct kobj_type ext4_feat_ktype = { .default_attrs = ext4_feat_attrs, .sysfs_ops = &ext4_attr_ops, - .release = (void (*)(struct kobject *))kfree, + .release = ext4_feat_release, }; static struct kobject *ext4_root; diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 899567d74c2a..88bdb2714e51 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -121,7 +121,11 @@ ext4_expand_inode_array(struct ext4_xattr_inode_array **ea_inode_array, #ifdef CONFIG_LOCKDEP void ext4_xattr_inode_set_class(struct inode *ea_inode) { + struct ext4_inode_info *ei = EXT4_I(ea_inode); + lockdep_set_subclass(&ea_inode->i_rwsem, 1); + (void) ei; /* shut up clang warning if !CONFIG_LOCKDEP */ + lockdep_set_subclass(&ei->i_data_sem, I_DATA_SEM_EA); } #endif @@ -384,6 +388,17 @@ static int ext4_xattr_inode_iget(struct inode *parent, unsigned long ea_ino, struct inode *inode; int err; + /* + * We have to check for this corruption early as otherwise + * iget_locked() could wait indefinitely for the state of our + * parent inode. + */ + if (parent->i_ino == ea_ino) { + ext4_error(parent->i_sb, + "Parent and EA inode have the same ino %lu", ea_ino); + return -EFSCORRUPTED; + } + inode = ext4_iget(parent->i_sb, ea_ino, EXT4_IGET_NORMAL); if (IS_ERR(inode)) { err = PTR_ERR(inode); @@ -434,6 +449,21 @@ error: return err; } +/* Remove entry from mbcache when EA inode is getting evicted */ +void ext4_evict_ea_inode(struct inode *inode) +{ + struct mb_cache_entry *oe; + + if (!EA_INODE_CACHE(inode)) + return; + /* Wait for entry to get unused so that we can remove it */ + while ((oe = mb_cache_entry_delete_or_get(EA_INODE_CACHE(inode), + ext4_xattr_inode_get_hash(inode), inode->i_ino))) { + mb_cache_entry_wait_unused(oe); + mb_cache_entry_put(EA_INODE_CACHE(inode), oe); + } +} + static int ext4_xattr_inode_verify_hashes(struct inode *ea_inode, struct ext4_xattr_entry *entry, void *buffer, @@ -1019,10 +1049,8 @@ static int ext4_xattr_ensure_credits(handle_t *handle, struct inode *inode, static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode, int ref_change) { - struct mb_cache *ea_inode_cache = EA_INODE_CACHE(ea_inode); struct ext4_iloc iloc; s64 ref_count; - u32 hash; int ret; inode_lock(ea_inode); @@ -1047,14 +1075,6 @@ static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode, set_nlink(ea_inode, 1); ext4_orphan_del(handle, ea_inode); - - if (ea_inode_cache) { - hash = ext4_xattr_inode_get_hash(ea_inode); - mb_cache_entry_create(ea_inode_cache, - GFP_NOFS, hash, - ea_inode->i_ino, - true /* reusable */); - } } } else { WARN_ONCE(ref_count < 0, "EA inode %lu ref_count=%lld", @@ -1067,12 +1087,6 @@ static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode, clear_nlink(ea_inode); ext4_orphan_add(handle, ea_inode); - - if (ea_inode_cache) { - hash = ext4_xattr_inode_get_hash(ea_inode); - mb_cache_entry_delete(ea_inode_cache, hash, - ea_inode->i_ino); - } } } @@ -1253,6 +1267,7 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode, if (error) goto out; +retry_ref: lock_buffer(bh); hash = le32_to_cpu(BHDR(bh)->h_hash); ref = le32_to_cpu(BHDR(bh)->h_refcount); @@ -1262,9 +1277,18 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode, * This must happen under buffer lock for * ext4_xattr_block_set() to reliably detect freed block */ - if (ea_block_cache) - mb_cache_entry_delete(ea_block_cache, hash, - bh->b_blocknr); + if (ea_block_cache) { + struct mb_cache_entry *oe; + + oe = mb_cache_entry_delete_or_get(ea_block_cache, hash, + bh->b_blocknr); + if (oe) { + unlock_buffer(bh); + mb_cache_entry_wait_unused(oe); + mb_cache_entry_put(ea_block_cache, oe); + goto retry_ref; + } + } get_bh(bh); unlock_buffer(bh); @@ -1288,7 +1312,7 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode, ce = mb_cache_entry_get(ea_block_cache, hash, bh->b_blocknr); if (ce) { - ce->e_reusable = 1; + set_bit(MBE_REUSABLE_B, &ce->e_flags); mb_cache_entry_put(ea_block_cache, ce); } } @@ -1427,6 +1451,13 @@ static struct inode *ext4_xattr_inode_create(handle_t *handle, uid_t owner[2] = { i_uid_read(inode), i_gid_read(inode) }; int err; + if (inode->i_sb->s_root == NULL) { + ext4_warning(inode->i_sb, + "refuse to create EA inode when umounting"); + WARN_ON(1); + return ERR_PTR(-EINVAL); + } + /* * Let the next inode be the goal, so we try and allocate the EA inode * in the same group, or nearby one. @@ -1446,6 +1477,9 @@ static struct inode *ext4_xattr_inode_create(handle_t *handle, if (!err) err = ext4_inode_attach_jinode(ea_inode); if (err) { + if (ext4_xattr_inode_dec_ref(handle, ea_inode)) + ext4_warning_inode(ea_inode, + "cleanup dec ref error %d", err); iput(ea_inode); return ERR_PTR(err); } @@ -1480,6 +1514,9 @@ ext4_xattr_inode_cache_find(struct inode *inode, const void *value, if (!ce) return NULL; + WARN_ON_ONCE(ext4_handle_valid(journal_current_handle()) && + !(current->flags & PF_MEMALLOC_NOFS)); + ea_data = ext4_kvmalloc(value_len, GFP_NOFS); if (!ea_data) { mb_cache_entry_put(ea_inode_cache, ce); @@ -1730,6 +1767,20 @@ static int ext4_xattr_set_entry(struct ext4_xattr_info *i, memmove(here, (void *)here + size, (void *)last - (void *)here + sizeof(__u32)); memset(last, 0, size); + + /* + * Update i_inline_off - moved ibody region might contain + * system.data attribute. Handling a failure here won't + * cause other complications for setting an xattr. + */ + if (!is_block && ext4_has_inline_data(inode)) { + ret = ext4_find_inline_data_nolock(inode); + if (ret) { + ext4_warning_inode(inode, + "unable to update i_inline_off"); + goto out; + } + } } else if (s->not_found) { /* Insert new name. */ size_t size = EXT4_XATTR_LEN(name_len); @@ -1869,6 +1920,8 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, #define header(x) ((struct ext4_xattr_header *)(x)) if (s->base) { + int offset = (char *)s->here - bs->bh->b_data; + BUFFER_TRACE(bs->bh, "get_write_access"); error = ext4_journal_get_write_access(handle, bs->bh); if (error) @@ -1883,9 +1936,20 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, * ext4_xattr_block_set() to reliably detect modified * block */ - if (ea_block_cache) - mb_cache_entry_delete(ea_block_cache, hash, - bs->bh->b_blocknr); + if (ea_block_cache) { + struct mb_cache_entry *oe; + + oe = mb_cache_entry_delete_or_get(ea_block_cache, + hash, bs->bh->b_blocknr); + if (oe) { + /* + * Xattr block is getting reused. Leave + * it alone. + */ + mb_cache_entry_put(ea_block_cache, oe); + goto clone_block; + } + } ea_bdebug(bs->bh, "modifying in-place"); error = ext4_xattr_set_entry(i, s, handle, inode, true /* is_block */); @@ -1900,50 +1964,47 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, if (error) goto cleanup; goto inserted; - } else { - int offset = (char *)s->here - bs->bh->b_data; + } +clone_block: + unlock_buffer(bs->bh); + ea_bdebug(bs->bh, "cloning"); + s->base = kmemdup(BHDR(bs->bh), bs->bh->b_size, GFP_NOFS); + error = -ENOMEM; + if (s->base == NULL) + goto cleanup; + s->first = ENTRY(header(s->base)+1); + header(s->base)->h_refcount = cpu_to_le32(1); + s->here = ENTRY(s->base + offset); + s->end = s->base + bs->bh->b_size; - unlock_buffer(bs->bh); - ea_bdebug(bs->bh, "cloning"); - s->base = kmalloc(bs->bh->b_size, GFP_NOFS); - error = -ENOMEM; - if (s->base == NULL) + /* + * If existing entry points to an xattr inode, we need + * to prevent ext4_xattr_set_entry() from decrementing + * ref count on it because the reference belongs to the + * original block. In this case, make the entry look + * like it has an empty value. + */ + if (!s->not_found && s->here->e_value_inum) { + ea_ino = le32_to_cpu(s->here->e_value_inum); + error = ext4_xattr_inode_iget(inode, ea_ino, + le32_to_cpu(s->here->e_hash), + &tmp_inode); + if (error) goto cleanup; - memcpy(s->base, BHDR(bs->bh), bs->bh->b_size); - s->first = ENTRY(header(s->base)+1); - header(s->base)->h_refcount = cpu_to_le32(1); - s->here = ENTRY(s->base + offset); - s->end = s->base + bs->bh->b_size; - /* - * If existing entry points to an xattr inode, we need - * to prevent ext4_xattr_set_entry() from decrementing - * ref count on it because the reference belongs to the - * original block. In this case, make the entry look - * like it has an empty value. - */ - if (!s->not_found && s->here->e_value_inum) { - ea_ino = le32_to_cpu(s->here->e_value_inum); - error = ext4_xattr_inode_iget(inode, ea_ino, - le32_to_cpu(s->here->e_hash), - &tmp_inode); - if (error) - goto cleanup; - - if (!ext4_test_inode_state(tmp_inode, - EXT4_STATE_LUSTRE_EA_INODE)) { - /* - * Defer quota free call for previous - * inode until success is guaranteed. - */ - old_ea_inode_quota = le32_to_cpu( - s->here->e_value_size); - } - iput(tmp_inode); - - s->here->e_value_inum = 0; - s->here->e_value_size = 0; + if (!ext4_test_inode_state(tmp_inode, + EXT4_STATE_LUSTRE_EA_INODE)) { + /* + * Defer quota free call for previous + * inode until success is guaranteed. + */ + old_ea_inode_quota = le32_to_cpu( + s->here->e_value_size); } + iput(tmp_inode); + + s->here->e_value_inum = 0; + s->here->e_value_size = 0; } } else { /* Allocate a buffer where we construct the new block. */ @@ -1994,8 +2055,9 @@ inserted: else { u32 ref; +#ifdef EXT4_XATTR_DEBUG WARN_ON_ONCE(dquot_initialize_needed(inode)); - +#endif /* The old block is released after updating the inode. */ error = dquot_alloc_block(inode, @@ -2010,18 +2072,13 @@ inserted: lock_buffer(new_bh); /* * We have to be careful about races with - * freeing, rehashing or adding references to - * xattr block. Once we hold buffer lock xattr - * block's state is stable so we can check - * whether the block got freed / rehashed or - * not. Since we unhash mbcache entry under - * buffer lock when freeing / rehashing xattr - * block, checking whether entry is still - * hashed is reliable. Same rules hold for - * e_reusable handling. + * adding references to xattr block. Once we + * hold buffer lock xattr block's state is + * stable so we can check the additional + * reference fits. */ - if (hlist_bl_unhashed(&ce->e_hash_list) || - !ce->e_reusable) { + ref = le32_to_cpu(BHDR(new_bh)->h_refcount) + 1; + if (ref > EXT4_XATTR_REFCOUNT_MAX) { /* * Undo everything and check mbcache * again. @@ -2036,10 +2093,9 @@ inserted: new_bh = NULL; goto inserted; } - ref = le32_to_cpu(BHDR(new_bh)->h_refcount) + 1; BHDR(new_bh)->h_refcount = cpu_to_le32(ref); - if (ref >= EXT4_XATTR_REFCOUNT_MAX) - ce->e_reusable = 0; + if (ref == EXT4_XATTR_REFCOUNT_MAX) + clear_bit(MBE_REUSABLE_B, &ce->e_flags); ea_bdebug(new_bh, "reusing; refcount now=%d", ref); ext4_xattr_block_csum_set(inode, new_bh); @@ -2063,23 +2119,16 @@ inserted: /* We need to allocate a new block */ ext4_fsblk_t goal, block; +#ifdef EXT4_XATTR_DEBUG WARN_ON_ONCE(dquot_initialize_needed(inode)); - +#endif goal = ext4_group_first_block_no(sb, EXT4_I(inode)->i_block_group); - - /* non-extent files can't have physical blocks past 2^32 */ - if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) - goal = goal & EXT4_MAX_BLOCK_FILE_PHYS; - block = ext4_new_meta_blocks(handle, inode, goal, 0, NULL, &error); if (error) goto cleanup; - if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) - BUG_ON(block > EXT4_MAX_BLOCK_FILE_PHYS); - ea_idebug(inode, "creating block %llu", (unsigned long long)block); @@ -2185,8 +2234,9 @@ int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i, struct ext4_inode *raw_inode; int error; - if (EXT4_I(inode)->i_extra_isize == 0) + if (!EXT4_INODE_HAS_XATTR_SPACE(inode)) return 0; + raw_inode = ext4_raw_inode(&is->iloc); header = IHDR(inode, raw_inode); is->s.base = is->s.first = IFIRST(header); @@ -2206,7 +2256,7 @@ int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i, return 0; } -int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode, +int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode, struct ext4_xattr_info *i, struct ext4_xattr_ibody_find *is) { @@ -2214,32 +2264,9 @@ int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode, struct ext4_xattr_search *s = &is->s; int error; - if (EXT4_I(inode)->i_extra_isize == 0) + if (!EXT4_INODE_HAS_XATTR_SPACE(inode)) return -ENOSPC; - error = ext4_xattr_set_entry(i, s, handle, inode, false /* is_block */); - if (error) - return error; - header = IHDR(inode, ext4_raw_inode(&is->iloc)); - if (!IS_LAST_ENTRY(s->first)) { - header->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC); - ext4_set_inode_state(inode, EXT4_STATE_XATTR); - } else { - header->h_magic = cpu_to_le32(0); - ext4_clear_inode_state(inode, EXT4_STATE_XATTR); - } - return 0; -} -static int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode, - struct ext4_xattr_info *i, - struct ext4_xattr_ibody_find *is) -{ - struct ext4_xattr_ibody_header *header; - struct ext4_xattr_search *s = &is->s; - int error; - - if (EXT4_I(inode)->i_extra_isize == 0) - return -ENOSPC; error = ext4_xattr_set_entry(i, s, handle, inode, false /* is_block */); if (error) return error; @@ -2346,6 +2373,7 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index, error = -ENOSPC; goto cleanup; } + WARN_ON_ONCE(!(current->flags & PF_MEMALLOC_NOFS)); } error = ext4_reserve_inode_write(handle, inode, &is.iloc); @@ -2419,7 +2447,7 @@ retry_inode: * external inode if possible. */ if (ext4_has_feature_ea_inode(inode->i_sb) && - !i.in_inode) { + i.value_len && !i.in_inode) { i.in_inode = 1; goto retry_inode; } @@ -2565,13 +2593,13 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode, .in_inode = !!entry->e_value_inum, }; struct ext4_xattr_ibody_header *header = IHDR(inode, raw_inode); + int needs_kvfree = 0; int error; is = kzalloc(sizeof(struct ext4_xattr_ibody_find), GFP_NOFS); bs = kzalloc(sizeof(struct ext4_xattr_block_find), GFP_NOFS); - buffer = kmalloc(value_size, GFP_NOFS); b_entry_name = kmalloc(entry->e_name_len + 1, GFP_NOFS); - if (!is || !bs || !buffer || !b_entry_name) { + if (!is || !bs || !b_entry_name) { error = -ENOMEM; goto out; } @@ -2583,12 +2611,18 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode, /* Save the entry name and the entry value */ if (entry->e_value_inum) { + buffer = kvmalloc(value_size, GFP_NOFS); + if (!buffer) { + error = -ENOMEM; + goto out; + } + needs_kvfree = 1; error = ext4_xattr_inode_get(inode, entry, buffer, value_size); if (error) goto out; } else { size_t value_offs = le16_to_cpu(entry->e_value_offs); - memcpy(buffer, (void *)IFIRST(header) + value_offs, value_size); + buffer = (void *)IFIRST(header) + value_offs; } memcpy(b_entry_name, entry->e_name, entry->e_name_len); @@ -2603,25 +2637,26 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode, if (error) goto out; - /* Remove the chosen entry from the inode */ - error = ext4_xattr_ibody_set(handle, inode, &i, is); - if (error) - goto out; - i.value = buffer; i.value_len = value_size; error = ext4_xattr_block_find(inode, &i, bs); if (error) goto out; - /* Add entry which was removed from the inode into the block */ + /* Move ea entry from the inode into the block */ error = ext4_xattr_block_set(handle, inode, &i, bs); if (error) goto out; - error = 0; + + /* Remove the chosen entry from the inode */ + i.value = NULL; + i.value_len = 0; + error = ext4_xattr_ibody_set(handle, inode, &i, is); + out: kfree(b_entry_name); - kfree(buffer); + if (needs_kvfree && buffer) + kvfree(buffer); if (is) brelse(is->iloc.bh); if (bs) @@ -2796,6 +2831,9 @@ shift: (void *)header, total_ino); EXT4_I(inode)->i_extra_isize = new_extra_isize; + if (ext4_has_inline_data(inode)) + error = ext4_find_inline_data_nolock(inode); + cleanup: if (error && (mnt_count != le16_to_cpu(sbi->s_es->s_mnt_count))) { ext4_warning(inode->i_sb, "Unable to expand inode %lu. Delete some EAs or run e2fsck.", diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h index f39cad2abe2a..66911f8a11f8 100644 --- a/fs/ext4/xattr.h +++ b/fs/ext4/xattr.h @@ -95,6 +95,19 @@ struct ext4_xattr_entry { #define EXT4_ZERO_XATTR_VALUE ((void *)-1) +/* + * If we want to add an xattr to the inode, we should make sure that + * i_extra_isize is not 0 and that the inode size is not less than + * EXT4_GOOD_OLD_INODE_SIZE + extra_isize + pad. + * EXT4_GOOD_OLD_INODE_SIZE extra_isize header entry pad data + * |--------------------------|------------|------|---------|---|-------| + */ +#define EXT4_INODE_HAS_XATTR_SPACE(inode) \ + ((EXT4_I(inode)->i_extra_isize != 0) && \ + (EXT4_GOOD_OLD_INODE_SIZE + EXT4_I(inode)->i_extra_isize + \ + sizeof(struct ext4_xattr_ibody_header) + EXT4_XATTR_PAD <= \ + EXT4_INODE_SIZE((inode)->i_sb))) + struct ext4_xattr_info { const char *name; const void *value; @@ -177,6 +190,7 @@ extern void ext4_xattr_inode_array_free(struct ext4_xattr_inode_array *array); extern int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize, struct ext4_inode *raw_inode, handle_t *handle); +extern void ext4_evict_ea_inode(struct inode *inode); extern const struct xattr_handler *ext4_xattr_handlers[]; @@ -185,9 +199,9 @@ extern int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i, extern int ext4_xattr_ibody_get(struct inode *inode, int name_index, const char *name, void *buffer, size_t buffer_size); -extern int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode, - struct ext4_xattr_info *i, - struct ext4_xattr_ibody_find *is); +extern int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode, + struct ext4_xattr_info *i, + struct ext4_xattr_ibody_find *is); extern struct mb_cache *ext4_xattr_create_cache(void); extern void ext4_xattr_destroy_cache(struct mb_cache *); diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 388500eec729..621e0d4f1fbf 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -218,6 +218,8 @@ int f2fs_ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, blkno * NAT_ENTRY_PER_BLOCK); break; case META_SIT: + if (unlikely(blkno >= TOTAL_SEGS(sbi))) + goto out; /* get sit block addr */ fio.new_blkaddr = current_sit_addr(sbi, blkno * SIT_ENTRY_PER_BLOCK); @@ -271,8 +273,15 @@ static int __f2fs_write_meta_page(struct page *page, trace_f2fs_writepage(page, META); - if (unlikely(f2fs_cp_error(sbi))) + if (unlikely(f2fs_cp_error(sbi))) { + if (is_sbi_flag_set(sbi, SBI_IS_CLOSE)) { + ClearPageUptodate(page); + dec_page_count(sbi, F2FS_DIRTY_META); + unlock_page(page); + return 0; + } goto redirty_out; + } if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) goto redirty_out; if (wbc->for_reclaim && page->index < GET_SUM_BLOCK(sbi, 0)) @@ -1003,8 +1012,12 @@ int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type) get_pages(sbi, is_dir ? F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA)); retry: - if (unlikely(f2fs_cp_error(sbi))) + if (unlikely(f2fs_cp_error(sbi))) { + trace_f2fs_sync_dirty_inodes_exit(sbi->sb, is_dir, + get_pages(sbi, is_dir ? + F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA)); return -EIO; + } spin_lock(&sbi->inode_lock[type]); @@ -1179,7 +1192,8 @@ void f2fs_wait_on_all_pages_writeback(struct f2fs_sb_info *sbi) if (!get_pages(sbi, F2FS_WB_CP_DATA)) break; - if (unlikely(f2fs_cp_error(sbi))) + if (unlikely(f2fs_cp_error(sbi) && + !is_sbi_flag_set(sbi, SBI_IS_CLOSE))) break; io_schedule_timeout(5*HZ); diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index c63f5e32630e..419586809cef 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -464,7 +464,7 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio) } if (fio->io_wbc && !is_read_io(fio->op)) - wbc_account_io(fio->io_wbc, page, PAGE_SIZE); + wbc_account_io(fio->io_wbc, fio->page, PAGE_SIZE); bio_set_op_attrs(bio, fio->op, fio->op_flags); @@ -533,7 +533,7 @@ alloc_new: } if (fio->io_wbc) - wbc_account_io(fio->io_wbc, bio_page, PAGE_SIZE); + wbc_account_io(fio->io_wbc, fio->page, PAGE_SIZE); io->last_block_in_bio = fio->new_blkaddr; f2fs_trace_ios(fio, 0); @@ -1885,7 +1885,8 @@ static int __write_data_page(struct page *page, bool *submitted, * don't drop any dirty dentry pages for keeping lastest * directory structure. */ - if (S_ISDIR(inode->i_mode)) + if (S_ISDIR(inode->i_mode) && + !is_sbi_flag_set(sbi, SBI_IS_CLOSE)) goto redirty_out; goto out; } diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index ebe19894884b..2cd85ce3e450 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -208,16 +208,15 @@ struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir, unsigned int max_depth; unsigned int level; + *res_page = NULL; + if (f2fs_has_inline_dentry(dir)) { - *res_page = NULL; de = f2fs_find_in_inline_dir(dir, fname, res_page); goto out; } - if (npages == 0) { - *res_page = NULL; + if (npages == 0) goto out; - } max_depth = F2FS_I(dir)->i_current_depth; if (unlikely(max_depth > MAX_DIR_HASH_DEPTH)) { @@ -229,7 +228,6 @@ struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir, } for (level = 0; level < max_depth; level++) { - *res_page = NULL; de = find_in_level(dir, level, fname, res_page); if (de || IS_ERR(*res_page)) break; diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c index a70cd2580eae..e85ed4aa9d46 100644 --- a/fs/f2fs/extent_cache.c +++ b/fs/f2fs/extent_cache.c @@ -375,7 +375,8 @@ static bool f2fs_lookup_extent_tree(struct inode *inode, pgoff_t pgofs, struct extent_node *en; bool ret = false; - f2fs_bug_on(sbi, !et); + if (!et) + return false; trace_f2fs_lookup_extent_tree_start(inode, pgofs); @@ -717,9 +718,8 @@ void f2fs_drop_extent_tree(struct inode *inode) if (!f2fs_may_extent_tree(inode)) return; - set_inode_flag(inode, FI_NO_EXTENT); - write_lock(&et->lock); + set_inode_flag(inode, FI_NO_EXTENT); __free_extent_tree(sbi, et); if (et->largest.len) { et->largest.len = 0; diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 53ffa6fe207a..aacd8e11758c 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -2857,6 +2857,8 @@ bool f2fs_empty_dir(struct inode *dir); static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode) { + if (fscrypt_is_nokey_name(dentry)) + return -ENOKEY; return f2fs_do_add_link(d_inode(dentry->d_parent), &dentry->d_name, inode, inode->i_ino, inode->i_mode); } diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 59b5c0b032bb..043ce96ac127 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -675,6 +675,10 @@ int f2fs_truncate(struct inode *inode) return -EIO; } + err = dquot_initialize(inode); + if (err) + return err; + /* we should check inline_data size */ if (!f2fs_may_inline_data(inode)) { err = f2fs_convert_inline_inode(inode); @@ -756,7 +760,8 @@ static void __setattr_copy(struct inode *inode, const struct iattr *attr) if (ia_valid & ATTR_MODE) { umode_t mode = attr->ia_mode; - if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID)) + if (!in_group_p(inode->i_gid) && + !capable_wrt_inode_uidgid(inode, CAP_FSETID)) mode &= ~S_ISGID; set_acl_inode(inode, mode); } @@ -952,7 +957,6 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len) } if (pg_start < pg_end) { - struct address_space *mapping = inode->i_mapping; loff_t blk_start, blk_end; struct f2fs_sb_info *sbi = F2FS_I_SB(inode); @@ -964,8 +968,7 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len) down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); down_write(&F2FS_I(inode)->i_mmap_sem); - truncate_inode_pages_range(mapping, blk_start, - blk_end - 1); + truncate_pagecache_range(inode, blk_start, blk_end - 1); f2fs_lock_op(sbi); ret = f2fs_truncate_hole(inode, pg_start, pg_end); @@ -2889,6 +2892,7 @@ int f2fs_precache_extents(struct inode *inode) return -EOPNOTSUPP; map.m_lblk = 0; + map.m_pblk = 0; map.m_next_pgofs = NULL; map.m_next_extent = &m_next_extent; map.m_seg_type = NO_CHECK_TYPE; diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 700c39ec99f5..fb4494c54484 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -589,6 +589,11 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, set_sbi_flag(sbi, SBI_NEED_FSCK); } + if (f2fs_check_nid_range(sbi, dni->ino)) { + f2fs_put_page(node_page, 1); + return false; + } + *nofs = ofs_of_node(node_page); source_blkaddr = datablock_addr(NULL, node_page, ofs_in_node); f2fs_put_page(node_page, 1); @@ -953,7 +958,8 @@ next_step: if (phase == 3) { inode = f2fs_iget(sb, dni.ino); - if (IS_ERR(inode) || is_bad_inode(inode)) + if (IS_ERR(inode) || is_bad_inode(inode) || + special_file(inode->i_mode)) continue; if (!down_write_trylock( @@ -998,8 +1004,10 @@ next_step: bool locked = false; if (S_ISREG(inode->i_mode)) { - if (!down_write_trylock(&fi->i_gc_rwsem[READ])) + if (!down_write_trylock(&fi->i_gc_rwsem[READ])) { + sbi->skipped_gc_rwsem++; continue; + } if (!down_write_trylock( &fi->i_gc_rwsem[WRITE])) { sbi->skipped_gc_rwsem++; diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index 2fabeb0bb28f..7ad78aa9c7b8 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -193,6 +193,10 @@ int f2fs_convert_inline_inode(struct inode *inode) if (!f2fs_has_inline_data(inode)) return 0; + err = dquot_initialize(inode); + if (err) + return err; + page = f2fs_grab_cache_page(inode->i_mapping, 0, false); if (!page) return -ENOMEM; @@ -216,7 +220,8 @@ out: f2fs_put_page(page, 1); - f2fs_balance_fs(sbi, dn.node_changed); + if (!err) + f2fs_balance_fs(sbi, dn.node_changed); return err; } @@ -403,18 +408,17 @@ static int f2fs_move_inline_dirents(struct inode *dir, struct page *ipage, dentry_blk = page_address(page); + /* + * Start by zeroing the full block, to ensure that all unused space is + * zeroed and no uninitialized memory is leaked to disk. + */ + memset(dentry_blk, 0, F2FS_BLKSIZE); + make_dentry_ptr_inline(dir, &src, inline_dentry); make_dentry_ptr_block(dir, &dst, dentry_blk); /* copy data from inline dentry block to new dentry block */ memcpy(dst.bitmap, src.bitmap, src.nr_bitmap); - memset(dst.bitmap + src.nr_bitmap, 0, dst.nr_bitmap - src.nr_bitmap); - /* - * we do not need to zero out remainder part of dentry and filename - * field, since we have used bitmap for marking the usage status of - * them, besides, we can also ignore copying/zeroing reserved space - * of dentry block, because them haven't been used so far. - */ memcpy(dst.dentry, src.dentry, SIZE_OF_DIR_ENTRY * src.max); memcpy(dst.filename, src.filename, src.max * F2FS_SLOT_LEN); diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index a01be7d8db86..15ff5d9b8c05 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -454,7 +454,7 @@ make_now: inode->i_op = &f2fs_dir_inode_operations; inode->i_fop = &f2fs_dir_operations; inode->i_mapping->a_ops = &f2fs_dblock_aops; - inode_nohighmem(inode); + mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS); } else if (S_ISLNK(inode->i_mode)) { if (f2fs_encrypted_inode(inode)) inode->i_op = &f2fs_encrypted_symlink_inode_operations; diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index 4f0cc0c79d1e..2eb7b0e2b34a 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -432,19 +432,23 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry, nid_t ino = -1; int err = 0; unsigned int root_ino = F2FS_ROOT_INO(F2FS_I_SB(dir)); + struct fscrypt_name fname; trace_f2fs_lookup_start(dir, dentry, flags); - err = fscrypt_prepare_lookup(dir, dentry, flags); - if (err) - goto out; - if (dentry->d_name.len > F2FS_NAME_LEN) { err = -ENAMETOOLONG; goto out; } - de = f2fs_find_entry(dir, &dentry->d_name, &page); + err = fscrypt_prepare_lookup(dir, dentry, &fname); + if (err == -ENOENT) + goto out_splice; + if (err) + goto out; + de = __f2fs_find_entry(dir, &fname, &page); + fscrypt_free_filename(&fname); + if (!de) { if (IS_ERR(page)) { err = PTR_ERR(page); @@ -484,8 +488,7 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry, } out_splice: new = d_splice_alias(inode, dentry); - if (IS_ERR(new)) - err = PTR_ERR(new); + err = PTR_ERR_OR_ZERO(new); trace_f2fs_lookup_end(dir, dentry, ino, err); return new; out_iput: @@ -653,7 +656,7 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) inode->i_op = &f2fs_dir_inode_operations; inode->i_fop = &f2fs_dir_operations; inode->i_mapping->a_ops = &f2fs_dblock_aops; - inode_nohighmem(inode); + mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS); set_inode_flag(inode, FI_INC_LINK); f2fs_lock_op(sbi); @@ -769,7 +772,11 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry, if (whiteout) { f2fs_i_links_write(inode, false); + + spin_lock(&inode->i_lock); inode->i_state |= I_LINKABLE; + spin_unlock(&inode->i_lock); + *whiteout = inode; } else { d_tmpfile(dentry, inode); @@ -963,12 +970,16 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, err = f2fs_add_link(old_dentry, whiteout); if (err) goto put_out_dir; + + spin_lock(&whiteout->i_lock); whiteout->i_state &= ~I_LINKABLE; + spin_unlock(&whiteout->i_lock); + iput(whiteout); } if (old_dir_entry) { - if (old_dir != new_dir && !whiteout) + if (old_dir != new_dir) f2fs_set_link(old_inode, old_dir_entry, old_dir_page, new_dir); else @@ -1208,9 +1219,18 @@ static const char *f2fs_encrypted_get_link(struct dentry *dentry, return target; } +static int f2fs_encrypted_symlink_getattr(const struct path *path, + struct kstat *stat, u32 request_mask, + unsigned int query_flags) +{ + f2fs_getattr(path, stat, request_mask, query_flags); + + return fscrypt_symlink_getattr(path, stat); +} + const struct inode_operations f2fs_encrypted_symlink_inode_operations = { .get_link = f2fs_encrypted_get_link, - .getattr = f2fs_getattr, + .getattr = f2fs_encrypted_symlink_getattr, .setattr = f2fs_setattr, #ifdef CONFIG_F2FS_FS_XATTR .listxattr = f2fs_listxattr, diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 1934dc6ad1cc..9911f780e013 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -879,8 +879,10 @@ static int truncate_dnode(struct dnode_of_data *dn) dn->ofs_in_node = 0; f2fs_truncate_data_blocks(dn); err = truncate_node(dn); - if (err) + if (err) { + f2fs_put_page(page, 1); return err; + } return 1; } @@ -1232,7 +1234,11 @@ struct page *f2fs_new_node_page(struct dnode_of_data *dn, unsigned int ofs) dec_valid_node_count(sbi, dn->inode, !ofs); goto fail; } - f2fs_bug_on(sbi, new_ni.blk_addr != NULL_ADDR); + if (unlikely(new_ni.blk_addr != NULL_ADDR)) { + err = -EFSCORRUPTED; + set_sbi_flag(sbi, SBI_NEED_FSCK); + goto fail; + } #endif new_ni.nid = dn->nid; new_ni.ino = dn->inode->i_ino; @@ -2654,6 +2660,9 @@ static void remove_nats_in_journal(struct f2fs_sb_info *sbi) struct f2fs_nat_entry raw_ne; nid_t nid = le32_to_cpu(nid_in_journal(journal, i)); + if (f2fs_check_nid_range(sbi, nid)) + continue; + raw_ne = nat_in_journal(journal, i); ne = __lookup_nat_cache(nm_i, nid); diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 0e3e590a250f..7596fce92bef 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -354,16 +354,19 @@ void f2fs_drop_inmem_page(struct inode *inode, struct page *page) struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct list_head *head = &fi->inmem_pages; struct inmem_pages *cur = NULL; + struct inmem_pages *tmp; f2fs_bug_on(sbi, !IS_ATOMIC_WRITTEN_PAGE(page)); mutex_lock(&fi->inmem_lock); - list_for_each_entry(cur, head, list) { - if (cur->page == page) + list_for_each_entry(tmp, head, list) { + if (tmp->page == page) { + cur = tmp; break; + } } - f2fs_bug_on(sbi, list_empty(head) || cur->page != page); + f2fs_bug_on(sbi, !cur); list_del(&cur->list); mutex_unlock(&fi->inmem_lock); @@ -1379,7 +1382,7 @@ static int __issue_discard_cmd(struct f2fs_sb_info *sbi, if (i + 1 < dpolicy->granularity) break; - if (i < DEFAULT_DISCARD_GRANULARITY && dpolicy->ordered) + if (i + 1 < DEFAULT_DISCARD_GRANULARITY && dpolicy->ordered) return __issue_discard_cmd_orderly(sbi, dpolicy); pend_list = &dcc->pend_list[i]; diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index 9c2a55ad61bc..d5f9c928946f 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -91,11 +91,11 @@ #define BLKS_PER_SEC(sbi) \ ((sbi)->segs_per_sec * (sbi)->blocks_per_seg) #define GET_SEC_FROM_SEG(sbi, segno) \ - ((segno) / (sbi)->segs_per_sec) + (((segno) == -1) ? -1: (segno) / (sbi)->segs_per_sec) #define GET_SEG_FROM_SEC(sbi, secno) \ ((secno) * (sbi)->segs_per_sec) #define GET_ZONE_FROM_SEC(sbi, secno) \ - ((secno) / (sbi)->secs_per_zone) + (((secno) == -1) ? -1: (secno) / (sbi)->secs_per_zone) #define GET_ZONE_FROM_SEG(sbi, segno) \ GET_ZONE_FROM_SEC(sbi, GET_SEC_FROM_SEG(sbi, segno)) @@ -534,11 +534,10 @@ static inline int reserved_sections(struct f2fs_sb_info *sbi) return GET_SEC_FROM_SEG(sbi, (unsigned int)reserved_segments(sbi)); } -static inline bool has_curseg_enough_space(struct f2fs_sb_info *sbi) +static inline bool has_curseg_enough_space(struct f2fs_sb_info *sbi, + unsigned int node_blocks, unsigned int dent_blocks) { - unsigned int node_blocks = get_pages(sbi, F2FS_DIRTY_NODES) + - get_pages(sbi, F2FS_DIRTY_DENTS); - unsigned int dent_blocks = get_pages(sbi, F2FS_DIRTY_DENTS); + unsigned int segno, left_blocks; int i; @@ -564,19 +563,28 @@ static inline bool has_curseg_enough_space(struct f2fs_sb_info *sbi) static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi, int freed, int needed) { - int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES); - int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS); - int imeta_secs = get_blocktype_secs(sbi, F2FS_DIRTY_IMETA); + unsigned int total_node_blocks = get_pages(sbi, F2FS_DIRTY_NODES) + + get_pages(sbi, F2FS_DIRTY_DENTS) + + get_pages(sbi, F2FS_DIRTY_IMETA); + unsigned int total_dent_blocks = get_pages(sbi, F2FS_DIRTY_DENTS); + unsigned int node_secs = total_node_blocks / BLKS_PER_SEC(sbi); + unsigned int dent_secs = total_dent_blocks / BLKS_PER_SEC(sbi); + unsigned int node_blocks = total_node_blocks % BLKS_PER_SEC(sbi); + unsigned int dent_blocks = total_dent_blocks % BLKS_PER_SEC(sbi); + unsigned int free, need_lower, need_upper; if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) return false; - if (free_sections(sbi) + freed == reserved_sections(sbi) + needed && - has_curseg_enough_space(sbi)) + free = free_sections(sbi) + freed; + need_lower = node_secs + dent_secs + reserved_sections(sbi) + needed; + need_upper = need_lower + (node_blocks ? 1 : 0) + (dent_blocks ? 1 : 0); + + if (free > need_upper) return false; - return (free_sections(sbi) + freed) <= - (node_secs + 2 * dent_secs + imeta_secs + - reserved_sections(sbi) + needed); + else if (free <= need_lower) + return true; + return !has_curseg_enough_space(sbi, node_blocks, dent_blocks); } static inline bool excess_prefree_segs(struct f2fs_sb_info *sbi) diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 161ce0eb8891..89fc8a4ce149 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -3373,4 +3373,5 @@ module_exit(exit_f2fs_fs) MODULE_AUTHOR("Samsung Electronics's Praesto Team"); MODULE_DESCRIPTION("Flash Friendly File System"); MODULE_LICENSE("GPL"); +MODULE_SOFTDEP("pre: crc32"); diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index 9a59f49ba405..89b6c33ba6a4 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -717,4 +717,5 @@ void f2fs_unregister_sysfs(struct f2fs_sb_info *sbi) } kobject_del(&sbi->s_kobj); kobject_put(&sbi->s_kobj); + wait_for_completion(&sbi->s_kobj_unregister); } diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index 201e9da1692a..db3e76b35607 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -658,8 +658,15 @@ static int __f2fs_setxattr(struct inode *inode, int index, } last = here; - while (!IS_XATTR_LAST_ENTRY(last)) + while (!IS_XATTR_LAST_ENTRY(last)) { + if ((void *)(last) + sizeof(__u32) > last_base_addr || + (void *)XATTR_NEXT_ENTRY(last) > last_base_addr) { + set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_FSCK); + error = -EFSCORRUPTED; + goto exit; + } last = XATTR_NEXT_ENTRY(last); + } newsize = XATTR_ALIGN(sizeof(struct f2fs_xattr_entry) + len + size); @@ -710,6 +717,12 @@ static int __f2fs_setxattr(struct inode *inode, int index, memcpy(pval, value, size); last->e_value_size = cpu_to_le16(size); new_hsize += newsize; + /* + * Explicitly add the null terminator. The unused xattr space + * is supposed to always be zeroed, which would make this + * unnecessary, but don't depend on that. + */ + *(u32 *)((u8 *)last + newsize) = 0; } error = write_all_xattrs(inode, new_hsize, base_addr, ipage); diff --git a/fs/fat/dir.c b/fs/fat/dir.c index 397f95b65881..947fbeb59db1 100644 --- a/fs/fat/dir.c +++ b/fs/fat/dir.c @@ -1302,7 +1302,7 @@ int fat_add_entries(struct inode *dir, void *slots, int nr_slots, struct super_block *sb = dir->i_sb; struct msdos_sb_info *sbi = MSDOS_SB(sb); struct buffer_head *bh, *prev, *bhs[3]; /* 32*slots (672bytes) */ - struct msdos_dir_entry *uninitialized_var(de); + struct msdos_dir_entry *de; int err, free_slots, i, nr_bhs; loff_t pos, i_pos; diff --git a/fs/fat/fatent.c b/fs/fat/fatent.c index 4c6c635bc8aa..5e35307a3d6b 100644 --- a/fs/fat/fatent.c +++ b/fs/fat/fatent.c @@ -93,7 +93,8 @@ static int fat12_ent_bread(struct super_block *sb, struct fat_entry *fatent, err_brelse: brelse(bhs[0]); err: - fat_msg(sb, KERN_ERR, "FAT read failed (blocknr %llu)", (llu)blocknr); + fat_msg_ratelimit(sb, KERN_ERR, "FAT read failed (blocknr %llu)", + (llu)blocknr); return -EIO; } @@ -106,8 +107,8 @@ static int fat_ent_bread(struct super_block *sb, struct fat_entry *fatent, fatent->fat_inode = MSDOS_SB(sb)->fat_inode; fatent->bhs[0] = sb_bread(sb, blocknr); if (!fatent->bhs[0]) { - fat_msg(sb, KERN_ERR, "FAT read failed (blocknr %llu)", - (llu)blocknr); + fat_msg_ratelimit(sb, KERN_ERR, "FAT read failed (blocknr %llu)", + (llu)blocknr); return -EIO; } fatent->nr_bhs = 1; diff --git a/fs/fcntl.c b/fs/fcntl.c index 4137d96534a6..dffb5245ae72 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -779,9 +779,10 @@ void send_sigio(struct fown_struct *fown, int fd, int band) { struct task_struct *p; enum pid_type type; + unsigned long flags; struct pid *pid; - read_lock(&fown->lock); + read_lock_irqsave(&fown->lock, flags); type = fown->pid_type; pid = fown->pid; @@ -802,7 +803,7 @@ void send_sigio(struct fown_struct *fown, int fd, int band) read_unlock(&tasklist_lock); } out_unlock_fown: - read_unlock(&fown->lock); + read_unlock_irqrestore(&fown->lock, flags); } static void send_sigurg_to_task(struct task_struct *p, @@ -817,9 +818,10 @@ int send_sigurg(struct fown_struct *fown) struct task_struct *p; enum pid_type type; struct pid *pid; + unsigned long flags; int ret = 0; - read_lock(&fown->lock); + read_lock_irqsave(&fown->lock, flags); type = fown->pid_type; pid = fown->pid; @@ -842,7 +844,7 @@ int send_sigurg(struct fown_struct *fown) read_unlock(&tasklist_lock); } out_unlock_fown: - read_unlock(&fown->lock); + read_unlock_irqrestore(&fown->lock, flags); return ret; } @@ -991,13 +993,14 @@ static void kill_fasync_rcu(struct fasync_struct *fa, int sig, int band) { while (fa) { struct fown_struct *fown; + unsigned long flags; if (fa->magic != FASYNC_MAGIC) { printk(KERN_ERR "kill_fasync: bad magic number in " "fasync_struct!\n"); return; } - read_lock(&fa->fa_lock); + read_lock_irqsave(&fa->fa_lock, flags); if (fa->fa_file) { fown = &fa->fa_file->f_owner; /* Don't send SIGURG to processes which have not set a @@ -1006,7 +1009,7 @@ static void kill_fasync_rcu(struct fasync_struct *fa, int sig, int band) if (!(sig == SIGURG && fown->signum == 0)) send_sigio(fown, fa->fa_fd, band); } - read_unlock(&fa->fa_lock); + read_unlock_irqrestore(&fa->fa_lock, flags); fa = rcu_dereference(fa->fa_next); } } diff --git a/fs/file.c b/fs/file.c index 3762a3f136fd..928ba7b8df1e 100644 --- a/fs/file.c +++ b/fs/file.c @@ -627,6 +627,7 @@ int __close_fd(struct files_struct *files, unsigned fd) fdt = files_fdtable(files); if (fd >= fdt->max_fds) goto out_unlock; + fd = array_index_nospec(fd, fdt->max_fds); file = fdt->fd[fd]; if (!file) goto out_unlock; @@ -677,38 +678,88 @@ void do_close_on_exec(struct files_struct *files) spin_unlock(&files->file_lock); } -static struct file *__fget(unsigned int fd, fmode_t mask) +static inline struct file *__fget_files_rcu(struct files_struct *files, + unsigned int fd, fmode_t mask, unsigned int refs) +{ + for (;;) { + struct file *file; + struct fdtable *fdt = rcu_dereference_raw(files->fdt); + struct file __rcu **fdentry; + + if (unlikely(fd >= fdt->max_fds)) + return NULL; + + fdentry = fdt->fd + array_index_nospec(fd, fdt->max_fds); + file = rcu_dereference_raw(*fdentry); + if (unlikely(!file)) + return NULL; + + if (unlikely(file->f_mode & mask)) + return NULL; + + /* + * Ok, we have a file pointer. However, because we do + * this all locklessly under RCU, we may be racing with + * that file being closed. + * + * Such a race can take two forms: + * + * (a) the file ref already went down to zero, + * and get_file_rcu_many() fails. Just try + * again: + */ + if (unlikely(!get_file_rcu_many(file, refs))) + continue; + + /* + * (b) the file table entry has changed under us. + * Note that we don't need to re-check the 'fdt->fd' + * pointer having changed, because it always goes + * hand-in-hand with 'fdt'. + * + * If so, we need to put our refs and try again. + */ + if (unlikely(rcu_dereference_raw(files->fdt) != fdt) || + unlikely(rcu_dereference_raw(*fdentry) != file)) { + fput_many(file, refs); + continue; + } + + /* + * Ok, we have a ref to the file, and checked that it + * still exists. + */ + return file; + } +} + + +static struct file *__fget(unsigned int fd, fmode_t mask, unsigned int refs) { struct files_struct *files = current->files; struct file *file; rcu_read_lock(); -loop: - file = fcheck_files(files, fd); - if (file) { - /* File object ref couldn't be taken. - * dup2() atomicity guarantee is the reason - * we loop to catch the new file (or NULL pointer) - */ - if (file->f_mode & mask) - file = NULL; - else if (!get_file_rcu(file)) - goto loop; - } + file = __fget_files_rcu(files, fd, mask, refs); rcu_read_unlock(); return file; } +struct file *fget_many(unsigned int fd, unsigned int refs) +{ + return __fget(fd, FMODE_PATH, refs); +} + struct file *fget(unsigned int fd) { - return __fget(fd, FMODE_PATH); + return __fget(fd, FMODE_PATH, 1); } EXPORT_SYMBOL(fget); struct file *fget_raw(unsigned int fd) { - return __fget(fd, 0); + return __fget(fd, 0, 1); } EXPORT_SYMBOL(fget_raw); @@ -739,7 +790,7 @@ static unsigned long __fget_light(unsigned int fd, fmode_t mask) return 0; return (unsigned long)file; } else { - file = __fget(fd, mask); + file = __fget(fd, mask, 1); if (!file) return 0; return FDPUT_FPUT | (unsigned long)file; diff --git a/fs/file_table.c b/fs/file_table.c index e49af4caf15d..6a715639728d 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -326,9 +326,9 @@ void flush_delayed_fput(void) static DECLARE_DELAYED_WORK(delayed_fput_work, delayed_fput); -void fput(struct file *file) +void fput_many(struct file *file, unsigned int refs) { - if (atomic_long_dec_and_test(&file->f_count)) { + if (atomic_long_sub_and_test(refs, &file->f_count)) { struct task_struct *task = current; if (likely(!in_interrupt() && !(task->flags & PF_KTHREAD))) { @@ -347,6 +347,11 @@ void fput(struct file *file) } } +void fput(struct file *file) +{ + fput_many(file, 1); +} + /* * synchronous analog of fput(); for kernel threads that might be needed * in some umount() (and thus can't use flush_delayed_fput() without diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 15216b440880..61dc0dc139f8 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -512,9 +512,14 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id) /* find and pin the new wb */ rcu_read_lock(); memcg_css = css_from_id(new_wb_id, &memory_cgrp_subsys); - if (memcg_css) - isw->new_wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); + if (memcg_css && !css_tryget(memcg_css)) + memcg_css = NULL; rcu_read_unlock(); + if (!memcg_css) + goto out_free; + + isw->new_wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); + css_put(memcg_css); if (!isw->new_wb) goto out_free; @@ -697,7 +702,7 @@ void wbc_detach_inode(struct writeback_control *wbc) * is okay. The main goal is avoiding keeping an inode on * the wrong wb for an extended period of time. */ - if (hweight32(history) > WB_FRN_HIST_THR_SLOTS) + if (hweight16(history) > WB_FRN_HIST_THR_SLOTS) inode_switch_wbs(inode, max_id); } @@ -1157,7 +1162,7 @@ static bool inode_dirtied_after(struct inode *inode, unsigned long t) */ static int move_expired_inodes(struct list_head *delaying_queue, struct list_head *dispatch_queue, - int flags, unsigned long dirtied_before) + unsigned long dirtied_before) { LIST_HEAD(tmp); struct list_head *pos, *node; @@ -1173,8 +1178,6 @@ static int move_expired_inodes(struct list_head *delaying_queue, list_move(&inode->i_io_list, &tmp); moved++; spin_lock(&inode->i_lock); - if (flags & EXPIRE_DIRTY_ATIME) - inode->i_state |= I_DIRTY_TIME_EXPIRED; inode->i_state |= I_SYNC_QUEUED; spin_unlock(&inode->i_lock); if (sb_is_blkdev_sb(inode->i_sb)) @@ -1222,11 +1225,11 @@ static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work, assert_spin_locked(&wb->list_lock); list_splice_init(&wb->b_more_io, &wb->b_io); - moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, 0, dirtied_before); + moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, dirtied_before); if (!work->for_sync) time_expire_jif = jiffies - dirtytime_expire_interval * HZ; moved += move_expired_inodes(&wb->b_dirty_time, &wb->b_io, - EXPIRE_DIRTY_ATIME, time_expire_jif); + time_expire_jif); if (moved) wb_io_lists_populated(wb); trace_writeback_queue_io(wb, work, dirtied_before, moved); @@ -1395,25 +1398,25 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) } /* + * If the inode has dirty timestamps and we need to write them, call + * mark_inode_dirty_sync() to notify the filesystem about it and to + * change I_DIRTY_TIME into I_DIRTY_SYNC. + */ + if ((inode->i_state & I_DIRTY_TIME) && + (wbc->sync_mode == WB_SYNC_ALL || wbc->for_sync || + time_after(jiffies, inode->dirtied_time_when + + dirtytime_expire_interval * HZ))) { + trace_writeback_lazytime(inode); + mark_inode_dirty_sync(inode); + } + + /* * Some filesystems may redirty the inode during the writeback * due to delalloc, clear dirty metadata flags right before * write_inode() */ spin_lock(&inode->i_lock); - dirty = inode->i_state & I_DIRTY; - if (inode->i_state & I_DIRTY_TIME) { - if ((dirty & I_DIRTY_INODE) || - wbc->sync_mode == WB_SYNC_ALL || - unlikely(inode->i_state & I_DIRTY_TIME_EXPIRED) || - unlikely(time_after(jiffies, - (inode->dirtied_time_when + - dirtytime_expire_interval * HZ)))) { - dirty |= I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED; - trace_writeback_lazytime(inode); - } - } else - inode->i_state &= ~I_DIRTY_TIME_EXPIRED; inode->i_state &= ~dirty; /* @@ -1434,8 +1437,6 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) spin_unlock(&inode->i_lock); - if (dirty & I_DIRTY_TIME) - mark_inode_dirty_sync(inode); /* Don't write the inode if only I_DIRTY_PAGES was set */ if (dirty & ~I_DIRTY_PAGES) { int err = write_inode(inode, wbc); @@ -1567,11 +1568,12 @@ static long writeback_sb_inodes(struct super_block *sb, }; unsigned long start_time = jiffies; long write_chunk; - long wrote = 0; /* count both pages and inodes */ + long total_wrote = 0; /* count both pages and inodes */ while (!list_empty(&wb->b_io)) { struct inode *inode = wb_inode(wb->b_io.prev); struct bdi_writeback *tmp_wb; + long wrote; if (inode->i_sb != sb) { if (work->sb) { @@ -1647,7 +1649,9 @@ static long writeback_sb_inodes(struct super_block *sb, wbc_detach_inode(&wbc); work->nr_pages -= write_chunk - wbc.nr_to_write; - wrote += write_chunk - wbc.nr_to_write; + wrote = write_chunk - wbc.nr_to_write - wbc.pages_skipped; + wrote = wrote < 0 ? 0 : wrote; + total_wrote += wrote; if (need_resched()) { /* @@ -1669,7 +1673,7 @@ static long writeback_sb_inodes(struct super_block *sb, tmp_wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); if (!(inode->i_state & I_DIRTY_ALL)) - wrote++; + total_wrote++; requeue_inode(inode, tmp_wb, &wbc); inode_sync_complete(inode); spin_unlock(&inode->i_lock); @@ -1683,14 +1687,14 @@ static long writeback_sb_inodes(struct super_block *sb, * bail out to wb_writeback() often enough to check * background threshold and other termination conditions. */ - if (wrote) { + if (total_wrote) { if (time_is_before_jiffies(start_time + HZ / 10UL)) break; if (work->nr_pages <= 0) break; } } - return wrote; + return total_wrote; } static long __writeback_inodes_wb(struct bdi_writeback *wb, @@ -1990,7 +1994,7 @@ void wb_workfn(struct work_struct *work) struct bdi_writeback, dwork); long pages_written; - set_worker_desc("flush-%s", dev_name(wb->bdi->dev)); + set_worker_desc("flush-%s", bdi_dev_name(wb->bdi)); current->flags |= PF_SWAPWRITE; if (likely(!current_is_workqueue_rescuer() || @@ -2119,28 +2123,6 @@ int dirtytime_interval_handler(struct ctl_table *table, int write, return ret; } -static noinline void block_dump___mark_inode_dirty(struct inode *inode) -{ - if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev")) { - struct dentry *dentry; - const char *name = "?"; - - dentry = d_find_alias(inode); - if (dentry) { - spin_lock(&dentry->d_lock); - name = (const char *) dentry->d_name.name; - } - printk(KERN_DEBUG - "%s(%d): dirtied inode %lu (%s) on %s\n", - current->comm, task_pid_nr(current), inode->i_ino, - name, inode->i_sb->s_id); - if (dentry) { - spin_unlock(&dentry->d_lock); - dput(dentry); - } - } -} - /** * __mark_inode_dirty - internal function * @@ -2200,9 +2182,6 @@ void __mark_inode_dirty(struct inode *inode, int flags) (dirtytime && (inode->i_state & I_DIRTY_INODE))) return; - if (unlikely(block_dump)) - block_dump___mark_inode_dirty(inode); - spin_lock(&inode->i_lock); if (dirtytime && (inode->i_state & I_DIRTY_INODE)) goto out_unlock_inode; diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index c550512ce335..2ff05adfc22a 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -78,10 +78,8 @@ void fscache_free_cookie(struct fscache_cookie *cookie) static int fscache_set_key(struct fscache_cookie *cookie, const void *index_key, size_t index_key_len) { - unsigned long long h; u32 *buf; int bufs; - int i; bufs = DIV_ROUND_UP(index_key_len, sizeof(*buf)); @@ -95,17 +93,7 @@ static int fscache_set_key(struct fscache_cookie *cookie, } memcpy(buf, index_key, index_key_len); - - /* Calculate a hash and combine this with the length in the first word - * or first half word - */ - h = (unsigned long)cookie->parent; - h += index_key_len + cookie->type; - - for (i = 0; i < bufs; i++) - h += buf[i]; - - cookie->key_hash = h ^ (h >> 32); + cookie->key_hash = fscache_hash(0, buf, bufs); return 0; } diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h index d6209022e965..cc87288a5448 100644 --- a/fs/fscache/internal.h +++ b/fs/fscache/internal.h @@ -101,6 +101,8 @@ extern struct workqueue_struct *fscache_object_wq; extern struct workqueue_struct *fscache_op_wq; DECLARE_PER_CPU(wait_queue_head_t, fscache_object_cong_wait); +extern unsigned int fscache_hash(unsigned int salt, unsigned int *data, unsigned int n); + static inline bool fscache_object_congested(void) { return workqueue_congested(WORK_CPU_UNBOUND, fscache_object_wq); diff --git a/fs/fscache/main.c b/fs/fscache/main.c index 30ad89db1efc..aa49234e9520 100644 --- a/fs/fscache/main.c +++ b/fs/fscache/main.c @@ -99,6 +99,45 @@ static struct ctl_table fscache_sysctls_root[] = { #endif /* + * Mixing scores (in bits) for (7,20): + * Input delta: 1-bit 2-bit + * 1 round: 330.3 9201.6 + * 2 rounds: 1246.4 25475.4 + * 3 rounds: 1907.1 31295.1 + * 4 rounds: 2042.3 31718.6 + * Perfect: 2048 31744 + * (32*64) (32*31/2 * 64) + */ +#define HASH_MIX(x, y, a) \ + ( x ^= (a), \ + y ^= x, x = rol32(x, 7),\ + x += y, y = rol32(y,20),\ + y *= 9 ) + +static inline unsigned int fold_hash(unsigned long x, unsigned long y) +{ + /* Use arch-optimized multiply if one exists */ + return __hash_32(y ^ __hash_32(x)); +} + +/* + * Generate a hash. This is derived from full_name_hash(), but we want to be + * sure it is arch independent and that it doesn't change as bits of the + * computed hash value might appear on disk. The caller also guarantees that + * the hashed data will be a series of aligned 32-bit words. + */ +unsigned int fscache_hash(unsigned int salt, unsigned int *data, unsigned int n) +{ + unsigned int a, x = 0, y = salt; + + for (; n; n--) { + a = *data++; + HASH_MIX(x, y, a); + } + return fold_hash(x, y); +} + +/* * initialise the fs caching module */ static int __init fscache_init(void) diff --git a/fs/fuse/acl.c b/fs/fuse/acl.c index 5a48cee6d7d3..f529075a2ce8 100644 --- a/fs/fuse/acl.c +++ b/fs/fuse/acl.c @@ -19,6 +19,9 @@ struct posix_acl *fuse_get_acl(struct inode *inode, int type) void *value = NULL; struct posix_acl *acl; + if (fuse_is_bad(inode)) + return ERR_PTR(-EIO); + if (!fc->posix_acl || fc->no_getxattr) return NULL; @@ -53,6 +56,9 @@ int fuse_set_acl(struct inode *inode, struct posix_acl *acl, int type) const char *name; int ret; + if (fuse_is_bad(inode)) + return -EIO; + if (!fc->posix_acl || fc->no_setxattr) return -EOPNOTSUPP; diff --git a/fs/fuse/control.c b/fs/fuse/control.c index acc35819aae6..af253127b309 100644 --- a/fs/fuse/control.c +++ b/fs/fuse/control.c @@ -117,7 +117,7 @@ static ssize_t fuse_conn_max_background_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { - unsigned uninitialized_var(val); + unsigned val; ssize_t ret; ret = fuse_conn_limit_write(file, buf, count, ppos, &val, diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c index f057c213c453..acd985aa2cba 100644 --- a/fs/fuse/cuse.c +++ b/fs/fuse/cuse.c @@ -269,7 +269,7 @@ static int cuse_parse_one(char **pp, char *end, char **keyp, char **valp) static int cuse_parse_devinfo(char *p, size_t len, struct cuse_devinfo *devinfo) { char *end = p + len; - char *uninitialized_var(key), *uninitialized_var(val); + char *key, *val; int rc; while (true) { @@ -621,6 +621,8 @@ static int __init cuse_init(void) cuse_channel_fops.owner = THIS_MODULE; cuse_channel_fops.open = cuse_channel_open; cuse_channel_fops.release = cuse_channel_release; + /* CUSE is not prepared for FUSE_DEV_IOC_CLONE */ + cuse_channel_fops.unlocked_ioctl = NULL; cuse_class = class_create(THIS_MODULE, "cuse"); if (IS_ERR(cuse_class)) diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index c51c9a6881e4..a5144ecd5bab 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -853,15 +853,16 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep) struct page *newpage; struct pipe_buffer *buf = cs->pipebufs; + get_page(oldpage); err = unlock_request(cs->req); if (err) - return err; + goto out_put_old; fuse_copy_finish(cs); err = pipe_buf_confirm(cs->pipe, buf); if (err) - return err; + goto out_put_old; BUG_ON(!cs->nr_segs); cs->currbuf = buf; @@ -901,7 +902,7 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep) err = replace_page_cache_page(oldpage, newpage, GFP_KERNEL); if (err) { unlock_page(newpage); - return err; + goto out_put_old; } get_page(newpage); @@ -909,6 +910,12 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep) if (!(buf->flags & PIPE_BUF_FLAG_LRU)) lru_cache_add_file(newpage); + /* + * Release while we have extra ref on stolen page. Otherwise + * anon_pipe_buf_release() might think the page can be reused. + */ + pipe_buf_release(cs->pipe, buf); + err = 0; spin_lock(&cs->req->waitq.lock); if (test_bit(FR_ABORTED, &cs->req->flags)) @@ -920,14 +927,19 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep) if (err) { unlock_page(newpage); put_page(newpage); - return err; + goto out_put_old; } unlock_page(oldpage); + /* Drop ref for ap->pages[] array */ put_page(oldpage); cs->len = 0; - return 0; + err = 0; +out_put_old: + /* Drop ref obtained in this function */ + put_page(oldpage); + return err; out_fallback_unlock: unlock_page(newpage); @@ -936,10 +948,10 @@ out_fallback: cs->offset = buf->offset; err = lock_request(cs->req); - if (err) - return err; + if (!err) + err = 1; - return 1; + goto out_put_old; } static int fuse_ref_page(struct fuse_copy_state *cs, struct page *page, @@ -951,14 +963,16 @@ static int fuse_ref_page(struct fuse_copy_state *cs, struct page *page, if (cs->nr_segs == cs->pipe->buffers) return -EIO; + get_page(page); err = unlock_request(cs->req); - if (err) + if (err) { + put_page(page); return err; + } fuse_copy_finish(cs); buf = cs->pipebufs; - get_page(page); buf->page = page; buf->offset = offset; buf->len = count; @@ -985,7 +999,17 @@ static int fuse_copy_page(struct fuse_copy_state *cs, struct page **pagep, while (count) { if (cs->write && cs->pipebufs && page) { - return fuse_ref_page(cs, page, offset, count); + /* + * Can't control lifetime of pipe buffers, so always + * copy user pages. + */ + if (cs->req->user_pages) { + err = fuse_copy_fill(cs); + if (err) + return err; + } else { + return fuse_ref_page(cs, page, offset, count); + } } else if (!cs->len) { if (cs->move_pages && page && offset == 0 && count == PAGE_SIZE) { @@ -1302,6 +1326,15 @@ static ssize_t fuse_dev_do_read(struct fuse_dev *fud, struct file *file, goto restart; } spin_lock(&fpq->lock); + /* + * Must not put request on fpq->io queue after having been shut down by + * fuse_abort_conn() + */ + if (!fpq->connected) { + req->out.h.error = err = -ECONNABORTED; + goto out_end; + + } list_add(&req->list, &fpq->io); spin_unlock(&fpq->lock); cs->req = req; @@ -1879,7 +1912,7 @@ static ssize_t fuse_dev_do_write(struct fuse_dev *fud, } err = -EINVAL; - if (oh.error <= -1000 || oh.error > 0) + if (oh.error <= -512 || oh.error > 0) goto err_finish; spin_lock(&fpq->lock); @@ -2037,8 +2070,12 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, pipe_lock(pipe); out_free: - for (idx = 0; idx < nbuf; idx++) - pipe_buf_release(pipe, &bufs[idx]); + for (idx = 0; idx < nbuf; idx++) { + struct pipe_buffer *buf = &bufs[idx]; + + if (buf->ops) + pipe_buf_release(pipe, buf); + } pipe_unlock(pipe); kvfree(bufs); diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 6244345a5745..16252727ec2e 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -187,7 +187,7 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags) int ret; inode = d_inode_rcu(entry); - if (inode && is_bad_inode(inode)) + if (inode && fuse_is_bad(inode)) goto invalid; else if (time_before64(fuse_dentry_time(entry), get_jiffies_64()) || (flags & LOOKUP_REVAL)) { @@ -232,7 +232,7 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags) spin_unlock(&fc->lock); } kfree(forget); - if (ret == -ENOMEM) + if (ret == -ENOMEM || ret == -EINTR) goto out; if (ret || fuse_invalid_attr(&outarg.attr) || (outarg.attr.mode ^ inode->i_mode) & S_IFMT) @@ -364,6 +364,9 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry, bool outarg_valid = true; bool locked; + if (fuse_is_bad(dir)) + return ERR_PTR(-EIO); + locked = fuse_lock_inode(dir); err = fuse_lookup_name(dir->i_sb, get_node_id(dir), &entry->d_name, &outarg, &inode); @@ -504,6 +507,9 @@ static int fuse_atomic_open(struct inode *dir, struct dentry *entry, struct fuse_conn *fc = get_fuse_conn(dir); struct dentry *res = NULL; + if (fuse_is_bad(dir)) + return -EIO; + if (d_in_lookup(entry)) { res = fuse_lookup(dir, entry, 0); if (IS_ERR(res)) @@ -552,6 +558,9 @@ static int create_new_entry(struct fuse_conn *fc, struct fuse_args *args, int err; struct fuse_forget_link *forget; + if (fuse_is_bad(dir)) + return -EIO; + forget = fuse_alloc_forget(); if (!forget) return -ENOMEM; @@ -679,6 +688,9 @@ static int fuse_unlink(struct inode *dir, struct dentry *entry) struct fuse_conn *fc = get_fuse_conn(dir); FUSE_ARGS(args); + if (fuse_is_bad(dir)) + return -EIO; + args.in.h.opcode = FUSE_UNLINK; args.in.h.nodeid = get_node_id(dir); args.in.numargs = 1; @@ -715,6 +727,9 @@ static int fuse_rmdir(struct inode *dir, struct dentry *entry) struct fuse_conn *fc = get_fuse_conn(dir); FUSE_ARGS(args); + if (fuse_is_bad(dir)) + return -EIO; + args.in.h.opcode = FUSE_RMDIR; args.in.h.nodeid = get_node_id(dir); args.in.numargs = 1; @@ -793,6 +808,9 @@ static int fuse_rename2(struct inode *olddir, struct dentry *oldent, struct fuse_conn *fc = get_fuse_conn(olddir); int err; + if (fuse_is_bad(olddir)) + return -EIO; + if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE)) return -EINVAL; @@ -928,7 +946,7 @@ static int fuse_do_getattr(struct inode *inode, struct kstat *stat, if (!err) { if (fuse_invalid_attr(&outarg.attr) || (inode->i_mode ^ outarg.attr.mode) & S_IFMT) { - make_bad_inode(inode); + fuse_make_bad(inode); err = -EIO; } else { fuse_change_attributes(inode, &outarg.attr, @@ -984,7 +1002,7 @@ int fuse_reverse_inval_entry(struct super_block *sb, u64 parent_nodeid, if (!parent) return -ENOENT; - inode_lock(parent); + inode_lock_nested(parent, I_MUTEX_PARENT); if (!S_ISDIR(parent->i_mode)) goto unlock; @@ -1125,6 +1143,9 @@ static int fuse_permission(struct inode *inode, int mask) bool refreshed = false; int err = 0; + if (fuse_is_bad(inode)) + return -EIO; + if (!fuse_allow_current_process(fc)) return -EACCES; @@ -1262,7 +1283,7 @@ retry: dput(dentry); goto retry; } - if (is_bad_inode(inode)) { + if (fuse_is_bad(inode)) { dput(dentry); return -EIO; } @@ -1293,8 +1314,16 @@ retry: dput(dentry); dentry = alias; } - if (IS_ERR(dentry)) + if (IS_ERR(dentry)) { + if (!IS_ERR(inode)) { + struct fuse_inode *fi = get_fuse_inode(inode); + + spin_lock(&fc->lock); + fi->nlookup--; + spin_unlock(&fc->lock); + } return PTR_ERR(dentry); + } } if (fc->readdirplus_auto) set_bit(FUSE_I_INIT_RDPLUS, &get_fuse_inode(inode)->state); @@ -1360,7 +1389,7 @@ static int fuse_readdir(struct file *file, struct dir_context *ctx) u64 attr_version = 0; bool locked; - if (is_bad_inode(inode)) + if (fuse_is_bad(inode)) return -EIO; req = fuse_get_req(fc, 1); @@ -1420,6 +1449,9 @@ static const char *fuse_get_link(struct dentry *dentry, if (!dentry) return ERR_PTR(-ECHILD); + if (fuse_is_bad(inode)) + return ERR_PTR(-EIO); + link = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!link) return ERR_PTR(-ENOMEM); @@ -1718,7 +1750,7 @@ int fuse_do_setattr(struct dentry *dentry, struct iattr *attr, if (fuse_invalid_attr(&outarg.attr) || (inode->i_mode ^ outarg.attr.mode) & S_IFMT) { - make_bad_inode(inode); + fuse_make_bad(inode); err = -EIO; goto error; } @@ -1774,6 +1806,9 @@ static int fuse_setattr(struct dentry *entry, struct iattr *attr) struct file *file = (attr->ia_valid & ATTR_FILE) ? attr->ia_file : NULL; int ret; + if (fuse_is_bad(inode)) + return -EIO; + if (!fuse_allow_current_process(get_fuse_conn(inode))) return -EACCES; @@ -1832,6 +1867,9 @@ static int fuse_getattr(const struct path *path, struct kstat *stat, struct inode *inode = d_inode(path->dentry); struct fuse_conn *fc = get_fuse_conn(inode); + if (fuse_is_bad(inode)) + return -EIO; + if (!fuse_allow_current_process(fc)) return -EACCES; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 6a3d89672ff7..c629ccafb2b0 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -178,12 +178,11 @@ void fuse_finish_open(struct inode *inode, struct file *file) if (ff->open_flags & FOPEN_DIRECT_IO) file->f_op = &fuse_direct_io_file_operations; - if (!(ff->open_flags & FOPEN_KEEP_CACHE)) - invalidate_inode_pages2(inode->i_mapping); if (ff->open_flags & FOPEN_STREAM) stream_open(inode, file); else if (ff->open_flags & FOPEN_NONSEEKABLE) nonseekable_open(inode, file); + if (fc->atomic_o_trunc && (file->f_flags & O_TRUNC)) { struct fuse_inode *fi = get_fuse_inode(inode); @@ -191,10 +190,14 @@ void fuse_finish_open(struct inode *inode, struct file *file) fi->attr_version = ++fc->attr_version; i_size_write(inode, 0); spin_unlock(&fc->lock); + truncate_pagecache(inode, 0); fuse_invalidate_attr(inode); if (fc->writeback_cache) file_update_time(file); + } else if (!(ff->open_flags & FOPEN_KEEP_CACHE)) { + invalidate_inode_pages2(inode->i_mapping); } + if ((file->f_mode & FMODE_WRITE) && fc->writeback_cache) fuse_link_write_file(file); } @@ -207,6 +210,9 @@ int fuse_open_common(struct inode *inode, struct file *file, bool isdir) fc->atomic_o_trunc && fc->writeback_cache; + if (fuse_is_bad(inode)) + return -EIO; + err = generic_file_open(inode, file); if (err) return err; @@ -408,7 +414,7 @@ static int fuse_flush(struct file *file, fl_owner_t id) struct fuse_flush_in inarg; int err; - if (is_bad_inode(inode)) + if (fuse_is_bad(inode)) return -EIO; if (fc->no_flush) @@ -456,7 +462,7 @@ int fuse_fsync_common(struct file *file, loff_t start, loff_t end, struct fuse_fsync_in inarg; int err; - if (is_bad_inode(inode)) + if (fuse_is_bad(inode)) return -EIO; inode_lock(inode); @@ -771,7 +777,7 @@ static int fuse_readpage(struct file *file, struct page *page) int err; err = -EIO; - if (is_bad_inode(inode)) + if (fuse_is_bad(inode)) goto out; err = fuse_do_readpage(file, page); @@ -898,7 +904,7 @@ static int fuse_readpages(struct file *file, struct address_space *mapping, int nr_alloc = min_t(unsigned, nr_pages, FUSE_MAX_PAGES_PER_REQ); err = -EIO; - if (is_bad_inode(inode)) + if (fuse_is_bad(inode)) goto out; data.file = file; @@ -928,6 +934,9 @@ static ssize_t fuse_file_read_iter(struct kiocb *iocb, struct iov_iter *to) struct inode *inode = iocb->ki_filp->f_mapping->host; struct fuse_conn *fc = get_fuse_conn(inode); + if (fuse_is_bad(inode)) + return -EIO; + /* * In auto invalidate mode, always update attributes on read. * Otherwise, only update if we attempt to read past EOF (to ensure @@ -1128,7 +1137,7 @@ static ssize_t fuse_perform_write(struct kiocb *iocb, int err = 0; ssize_t res = 0; - if (is_bad_inode(inode)) + if (fuse_is_bad(inode)) return -EIO; if (inode->i_size < pos + iov_iter_count(ii)) @@ -1185,6 +1194,9 @@ static ssize_t fuse_file_write_iter(struct kiocb *iocb, struct iov_iter *from) ssize_t err; loff_t endbyte = 0; + if (fuse_is_bad(inode)) + return -EIO; + if (get_fuse_conn(inode)->writeback_cache) { /* Update size (EOF optimization) and mode (SUID clearing) */ err = fuse_update_attributes(mapping->host, file); @@ -1317,6 +1329,7 @@ static int fuse_get_user_pages(struct fuse_req *req, struct iov_iter *ii, (PAGE_SIZE - ret) & (PAGE_SIZE - 1); } + req->user_pages = true; if (write) req->in.argpages = 1; else @@ -1421,7 +1434,7 @@ static ssize_t __fuse_direct_read(struct fuse_io_priv *io, ssize_t res; struct inode *inode = file_inode(io->iocb->ki_filp); - if (is_bad_inode(inode)) + if (fuse_is_bad(inode)) return -EIO; res = fuse_direct_io(io, iter, ppos, 0); @@ -1443,7 +1456,7 @@ static ssize_t fuse_direct_write_iter(struct kiocb *iocb, struct iov_iter *from) struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(iocb); ssize_t res; - if (is_bad_inode(inode)) + if (fuse_is_bad(inode)) return -EIO; /* Don't allow parallel writes to the same file */ @@ -1917,7 +1930,7 @@ static int fuse_writepages(struct address_space *mapping, int err; err = -EIO; - if (is_bad_inode(inode)) + if (fuse_is_bad(inode)) goto out; data.inode = inode; @@ -2702,7 +2715,7 @@ long fuse_ioctl_common(struct file *file, unsigned int cmd, if (!fuse_allow_current_process(fc)) return -EACCES; - if (is_bad_inode(inode)) + if (fuse_is_bad(inode)) return -EIO; return fuse_do_ioctl(file, cmd, arg, flags); @@ -2761,7 +2774,7 @@ static void fuse_register_polled_file(struct fuse_conn *fc, { spin_lock(&fc->lock); if (RB_EMPTY_NODE(&ff->polled_node)) { - struct rb_node **link, *uninitialized_var(parent); + struct rb_node **link, *parent; link = fuse_find_polled_node(fc, ff->kh, &parent); BUG_ON(*link); diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index dbfc35efbefb..1c754a02fb06 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -118,6 +118,8 @@ enum { FUSE_I_INIT_RDPLUS, /** An operation changing file size is in progress */ FUSE_I_SIZE_UNSTABLE, + /* Bad inode */ + FUSE_I_BAD, }; struct fuse_conn; @@ -311,6 +313,8 @@ struct fuse_req { /** refcount */ refcount_t count; + bool user_pages; + /** Unique ID for the interrupt request */ u64 intr_unique; @@ -700,6 +704,17 @@ static inline u64 get_node_id(struct inode *inode) return get_fuse_inode(inode)->nodeid; } +static inline void fuse_make_bad(struct inode *inode) +{ + remove_inode_hash(inode); + set_bit(FUSE_I_BAD, &get_fuse_inode(inode)->state); +} + +static inline bool fuse_is_bad(struct inode *inode) +{ + return unlikely(test_bit(FUSE_I_BAD, &get_fuse_inode(inode)->state)); +} + /** Device operations */ extern const struct file_operations fuse_dev_operations; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index cb018315ecaf..3b51c881baf8 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -174,6 +174,12 @@ void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr, inode->i_uid = make_kuid(fc->user_ns, attr->uid); inode->i_gid = make_kgid(fc->user_ns, attr->gid); inode->i_blocks = attr->blocks; + + /* Sanitize nsecs */ + attr->atimensec = min_t(u32, attr->atimensec, NSEC_PER_SEC - 1); + attr->mtimensec = min_t(u32, attr->mtimensec, NSEC_PER_SEC - 1); + attr->ctimensec = min_t(u32, attr->ctimensec, NSEC_PER_SEC - 1); + inode->i_atime.tv_sec = attr->atime; inode->i_atime.tv_nsec = attr->atimensec; /* mtime from server may be stale due to local buffered write */ @@ -317,7 +323,7 @@ struct inode *fuse_iget(struct super_block *sb, u64 nodeid, unlock_new_inode(inode); } else if ((inode->i_mode ^ attr->mode) & S_IFMT) { /* Inode has changed type, any I/O on the old should fail */ - make_bad_inode(inode); + fuse_make_bad(inode); iput(inode); goto retry; } diff --git a/fs/fuse/xattr.c b/fs/fuse/xattr.c index 433717640f78..a4b65374bced 100644 --- a/fs/fuse/xattr.c +++ b/fs/fuse/xattr.c @@ -113,6 +113,9 @@ ssize_t fuse_listxattr(struct dentry *entry, char *list, size_t size) struct fuse_getxattr_out outarg; ssize_t ret; + if (fuse_is_bad(inode)) + return -EIO; + if (!fuse_allow_current_process(fc)) return -EACCES; @@ -178,6 +181,9 @@ static int fuse_xattr_get(const struct xattr_handler *handler, struct dentry *dentry, struct inode *inode, const char *name, void *value, size_t size) { + if (fuse_is_bad(inode)) + return -EIO; + return fuse_getxattr(inode, name, value, size); } @@ -186,6 +192,9 @@ static int fuse_xattr_set(const struct xattr_handler *handler, const char *name, const void *value, size_t size, int flags) { + if (fuse_is_bad(inode)) + return -EIO; + if (!value) return fuse_removexattr(inode, name); diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 31e8270d0b26..910bfc39dc4b 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -179,7 +179,6 @@ static int __gfs2_jdata_writepage(struct page *page, struct writeback_control *w { struct inode *inode = page->mapping->host; struct gfs2_inode *ip = GFS2_I(inode); - struct gfs2_sbd *sdp = GFS2_SB(inode); if (PageChecked(page)) { ClearPageChecked(page); @@ -187,7 +186,7 @@ static int __gfs2_jdata_writepage(struct page *page, struct writeback_control *w create_empty_buffers(page, inode->i_sb->s_blocksize, BIT(BH_Dirty)|BIT(BH_Uptodate)); } - gfs2_page_add_databufs(ip, page, 0, sdp->sd_vfs->s_blocksize); + gfs2_page_add_databufs(ip, page, 0, PAGE_SIZE); } return gfs2_write_full_page(page, gfs2_get_block_noalloc, wbc); } @@ -360,7 +359,7 @@ static int gfs2_write_cache_jdata(struct address_space *mapping, int done = 0; struct pagevec pvec; int nr_pages; - pgoff_t uninitialized_var(writeback_index); + pgoff_t writeback_index; pgoff_t index; pgoff_t end; pgoff_t done_index; @@ -481,8 +480,6 @@ int stuffed_readpage(struct gfs2_inode *ip, struct page *page) return error; kaddr = kmap_atomic(page); - if (dsize > gfs2_max_stuffed_size(ip)) - dsize = gfs2_max_stuffed_size(ip); memcpy(kaddr, dibh->b_data + sizeof(struct gfs2_dinode), dsize); memset(kaddr + dsize, 0, PAGE_SIZE - dsize); kunmap_atomic(kaddr); diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 43f53020553b..729f36fdced1 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -72,9 +72,6 @@ static int gfs2_unstuffer_page(struct gfs2_inode *ip, struct buffer_head *dibh, void *kaddr = kmap(page); u64 dsize = i_size_read(inode); - if (dsize > gfs2_max_stuffed_size(ip)) - dsize = gfs2_max_stuffed_size(ip); - memcpy(kaddr, dibh->b_data + sizeof(struct gfs2_dinode), dsize); memset(kaddr + dsize, 0, PAGE_SIZE - dsize); kunmap(page); @@ -943,7 +940,7 @@ do_alloc: else if (height == ip->i_height) ret = gfs2_hole_size(inode, lblock, len, mp, iomap); else - iomap->length = size - pos; + iomap->length = size - iomap->offset; } else if (flags & IOMAP_WRITE) { u64 alloc_size; @@ -1168,13 +1165,12 @@ static int gfs2_iomap_end(struct inode *inode, loff_t pos, loff_t length, if (length != written && (iomap->flags & IOMAP_F_NEW)) { /* Deallocate blocks that were just allocated. */ - loff_t blockmask = i_blocksize(inode) - 1; - loff_t end = (pos + length) & ~blockmask; + loff_t hstart = round_up(pos + written, i_blocksize(inode)); + loff_t hend = iomap->offset + iomap->length; - pos = (pos + written + blockmask) & ~blockmask; - if (pos < end) { - truncate_pagecache_range(inode, pos, end - 1); - punch_hole(ip, pos, end - pos); + if (hstart < hend) { + truncate_pagecache_range(inode, hstart, hend - 1); + punch_hole(ip, hstart, hend - hstart); } } @@ -1758,7 +1754,7 @@ static int punch_hole(struct gfs2_inode *ip, u64 offset, u64 length) u64 lblock = (offset + (1 << bsize_shift) - 1) >> bsize_shift; __u16 start_list[GFS2_MAX_META_HEIGHT]; __u16 __end_list[GFS2_MAX_META_HEIGHT], *end_list = NULL; - unsigned int start_aligned, uninitialized_var(end_aligned); + unsigned int start_aligned, end_aligned; unsigned int strip_h = ip->i_height - 1; u32 btotal = 0; int ret, state; diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 143e7d518c5d..7c69486d556f 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -822,8 +822,11 @@ static ssize_t gfs2_file_write_iter(struct kiocb *iocb, struct iov_iter *from) current->backing_dev_info = inode_to_bdi(inode); buffered = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops); current->backing_dev_info = NULL; - if (unlikely(buffered <= 0)) + if (unlikely(buffered <= 0)) { + if (!ret) + ret = buffered; goto out_unlock; + } /* * We need to ensure that the page cache pages are written to diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index ccdd8c821abd..14d11ccda868 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -870,7 +870,8 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number, out_free: kfree(gl->gl_lksb.sb_lvbptr); kmem_cache_free(cachep, gl); - atomic_dec(&sdp->sd_glock_disposal); + if (atomic_dec_and_test(&sdp->sd_glock_disposal)) + wake_up(&sdp->sd_glock_wait); out: return ret; @@ -1456,6 +1457,7 @@ __acquires(&lru_lock) while(!list_empty(list)) { gl = list_entry(list->next, struct gfs2_glock, gl_lru); list_del_init(&gl->gl_lru); + clear_bit(GLF_LRU, &gl->gl_flags); if (!spin_trylock(&gl->gl_lockref.lock)) { add_back_to_lru: list_add(&gl->gl_lru, &lru_list); @@ -1501,7 +1503,6 @@ static long gfs2_scan_glock_lru(int nr) if (!test_bit(GLF_LOCK, &gl->gl_flags)) { list_move(&gl->gl_lru, &dispose); atomic_dec(&lru_count); - clear_bit(GLF_LRU, &gl->gl_flags); freed++; continue; } diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index 20f08f4391c9..ff35cc365930 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -339,6 +339,7 @@ static int inode_go_demote_ok(const struct gfs2_glock *gl) static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf) { + struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); const struct gfs2_dinode *str = buf; struct timespec64 atime; u16 height, depth; @@ -378,7 +379,7 @@ static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf) /* i_diskflags and i_eattr must be set before gfs2_set_inode_flags() */ gfs2_set_inode_flags(&ip->i_inode); height = be16_to_cpu(str->di_height); - if (unlikely(height > GFS2_MAX_META_HEIGHT)) + if (unlikely(height > sdp->sd_max_height)) goto corrupt; ip->i_height = (u8)height; @@ -388,6 +389,9 @@ static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf) ip->i_depth = (u8)depth; ip->i_entries = be32_to_cpu(str->di_entries); + if (gfs2_is_stuffed(ip) && ip->i_inode.i_size > gfs2_max_stuffed_size(ip)) + goto corrupt; + if (S_ISREG(ip->i_inode.i_mode)) gfs2_set_aops(&ip->i_inode); diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c index 62edf8f5615f..9e90e42c495e 100644 --- a/fs/gfs2/lock_dlm.c +++ b/fs/gfs2/lock_dlm.c @@ -283,7 +283,6 @@ static void gdlm_put_lock(struct gfs2_glock *gl) { struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; struct lm_lockstruct *ls = &sdp->sd_lockstruct; - int lvb_needs_unlock = 0; int error; if (gl->gl_lksb.sb_lkid == 0) { @@ -296,13 +295,15 @@ static void gdlm_put_lock(struct gfs2_glock *gl) gfs2_sbstats_inc(gl, GFS2_LKS_DCOUNT); gfs2_update_request_times(gl); - /* don't want to skip dlm_unlock writing the lvb when lock is ex */ - - if (gl->gl_lksb.sb_lvbptr && (gl->gl_state == LM_ST_EXCLUSIVE)) - lvb_needs_unlock = 1; + /* don't want to call dlm if we've unmounted the lock protocol */ + if (test_bit(DFL_UNMOUNT, &ls->ls_recover_flags)) { + gfs2_glock_free(gl); + return; + } + /* don't want to skip dlm_unlock writing the lvb when lock has one */ if (test_bit(SDF_SKIP_DLM_UNLOCK, &sdp->sd_flags) && - !lvb_needs_unlock) { + !gl->gl_lksb.sb_lvbptr) { gfs2_glock_free(gl); return; } diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 9448c8461e57..e5e7a8101aa6 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -161,15 +161,22 @@ static int gfs2_check_sb(struct gfs2_sbd *sdp, int silent) return -EINVAL; } - /* If format numbers match exactly, we're done. */ - - if (sb->sb_fs_format == GFS2_FORMAT_FS && - sb->sb_multihost_format == GFS2_FORMAT_MULTI) - return 0; - - fs_warn(sdp, "Unknown on-disk format, unable to mount\n"); + if (sb->sb_fs_format != GFS2_FORMAT_FS || + sb->sb_multihost_format != GFS2_FORMAT_MULTI) { + fs_warn(sdp, "Unknown on-disk format, unable to mount\n"); + return -EINVAL; + } - return -EINVAL; + if (sb->sb_bsize < 512 || sb->sb_bsize > PAGE_SIZE || + (sb->sb_bsize & (sb->sb_bsize - 1))) { + pr_warn("Invalid superblock size\n"); + return -EINVAL; + } + if (sb->sb_bsize_shift != ffs(sb->sb_bsize) - 1) { + pr_warn("Invalid block size shift\n"); + return -EINVAL; + } + return 0; } static void end_bio_io_page(struct bio *bio) @@ -365,8 +372,10 @@ static int init_names(struct gfs2_sbd *sdp, int silent) if (!table[0]) table = sdp->sd_vfs->s_id; - strlcpy(sdp->sd_proto_name, proto, GFS2_FSNAME_LEN); - strlcpy(sdp->sd_table_name, table, GFS2_FSNAME_LEN); + BUILD_BUG_ON(GFS2_LOCKNAME_LEN > GFS2_FSNAME_LEN); + + strscpy(sdp->sd_proto_name, proto, GFS2_LOCKNAME_LEN); + strscpy(sdp->sd_table_name, table, GFS2_LOCKNAME_LEN); table = sdp->sd_table_name; while ((table = strchr(table, '/'))) diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index dd0f9bc13164..9f753595d90e 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -434,6 +434,17 @@ static int qd_check_sync(struct gfs2_sbd *sdp, struct gfs2_quota_data *qd, (sync_gen && (qd->qd_sync_gen >= *sync_gen))) return 0; + /* + * If qd_change is 0 it means a pending quota change was negated. + * We should not sync it, but we still have a qd reference and slot + * reference taken by gfs2_quota_change -> do_qc that need to be put. + */ + if (!qd->qd_change && test_and_clear_bit(QDF_CHANGE, &qd->qd_flags)) { + slot_put(qd); + qd_put(qd); + return 0; + } + if (!lockref_get_not_dead(&qd->qd_lockref)) return 0; diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index c94c4ac1ae78..cd2d8d674467 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -739,9 +739,9 @@ void gfs2_clear_rgrpd(struct gfs2_sbd *sdp) } gfs2_free_clones(rgd); + return_all_reservations(rgd); kfree(rgd->rd_bits); rgd->rd_bits = NULL; - return_all_reservations(rgd); kmem_cache_free(gfs2_rgrpd_cachep, rgd); } } @@ -926,15 +926,15 @@ static int read_rindex_entry(struct gfs2_inode *ip) rgd->rd_bitbytes = be32_to_cpu(buf.ri_bitbytes); spin_lock_init(&rgd->rd_rsspin); - error = compute_bitstructs(rgd); - if (error) - goto fail; - error = gfs2_glock_get(sdp, rgd->rd_addr, &gfs2_rgrp_glops, CREATE, &rgd->rd_gl); if (error) goto fail; + error = compute_bitstructs(rgd); + if (error) + goto fail_glock; + rgd->rd_rgl = (struct gfs2_rgrp_lvb *)rgd->rd_gl->gl_lksb.sb_lvbptr; rgd->rd_flags &= ~(GFS2_RDF_UPTODATE | GFS2_RDF_PREFERRED); if (rgd->rd_data > sdp->sd_max_rg_data) @@ -951,6 +951,7 @@ static int read_rindex_entry(struct gfs2_inode *ip) } error = 0; /* someone else read in the rgrp; free it and ignore it */ +fail_glock: gfs2_glock_put(rgd->rd_gl); fail: @@ -1009,6 +1010,10 @@ static int gfs2_ri_update(struct gfs2_inode *ip) if (error < 0) return error; + if (RB_EMPTY_ROOT(&sdp->sd_rindex_tree)) { + fs_err(sdp, "no resource groups found in the file system.\n"); + return -ENOENT; + } set_rgrp_preferences(sdp); sdp->sd_rindex_uptodate = 1; @@ -1387,6 +1392,9 @@ int gfs2_fitrim(struct file *filp, void __user *argp) if (!capable(CAP_SYS_ADMIN)) return -EPERM; + if (!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) + return -EROFS; + if (!blk_queue_discard(q)) return -EOPNOTSUPP; @@ -1399,7 +1407,8 @@ int gfs2_fitrim(struct file *filp, void __user *argp) start = r.start >> bs_shift; end = start + (r.len >> bs_shift); - minlen = max_t(u64, r.minlen, + minlen = max_t(u64, r.minlen, sdp->sd_sb.sb_bsize); + minlen = max_t(u64, minlen, q->limits.discard_granularity) >> bs_shift; if (end <= start || minlen > sdp->sd_max_rg_data) diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index a971862b186e..29157f7d9663 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -934,6 +934,7 @@ restart: gfs2_jindex_free(sdp); /* Take apart glock structures and buffer lists */ gfs2_gl_hash_clear(sdp); + truncate_inode_pages_final(&sdp->sd_aspace); gfs2_delete_debugfs_file(sdp); /* Unmount the locking protocol */ gfs2_lm_unmount(sdp); @@ -999,11 +1000,13 @@ void gfs2_freeze_func(struct work_struct *work) static int gfs2_freeze(struct super_block *sb) { struct gfs2_sbd *sdp = sb->s_fs_info; - int error = 0; + int error; mutex_lock(&sdp->sd_freeze_mutex); - if (atomic_read(&sdp->sd_freeze_state) != SFS_UNFROZEN) + if (atomic_read(&sdp->sd_freeze_state) != SFS_UNFROZEN) { + error = -EBUSY; goto out; + } if (test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) { error = -EINVAL; @@ -1045,10 +1048,10 @@ static int gfs2_unfreeze(struct super_block *sb) struct gfs2_sbd *sdp = sb->s_fs_info; mutex_lock(&sdp->sd_freeze_mutex); - if (atomic_read(&sdp->sd_freeze_state) != SFS_FROZEN || + if (atomic_read(&sdp->sd_freeze_state) != SFS_FROZEN || !gfs2_holder_initialized(&sdp->sd_freeze_gh)) { mutex_unlock(&sdp->sd_freeze_mutex); - return 0; + return -EINVAL; } gfs2_glock_dq_uninit(&sdp->sd_freeze_gh); @@ -1371,7 +1374,14 @@ static int gfs2_show_options(struct seq_file *s, struct dentry *root) { struct gfs2_sbd *sdp = root->d_sb->s_fs_info; struct gfs2_args *args = &sdp->sd_args; - int val; + unsigned int logd_secs, statfs_slow, statfs_quantum, quota_quantum; + + spin_lock(&sdp->sd_tune.gt_spin); + logd_secs = sdp->sd_tune.gt_logd_secs; + quota_quantum = sdp->sd_tune.gt_quota_quantum; + statfs_quantum = sdp->sd_tune.gt_statfs_quantum; + statfs_slow = sdp->sd_tune.gt_statfs_slow; + spin_unlock(&sdp->sd_tune.gt_spin); if (is_ancestor(root, sdp->sd_master_dir)) seq_puts(s, ",meta"); @@ -1426,17 +1436,14 @@ static int gfs2_show_options(struct seq_file *s, struct dentry *root) } if (args->ar_discard) seq_puts(s, ",discard"); - val = sdp->sd_tune.gt_logd_secs; - if (val != 30) - seq_printf(s, ",commit=%d", val); - val = sdp->sd_tune.gt_statfs_quantum; - if (val != 30) - seq_printf(s, ",statfs_quantum=%d", val); - else if (sdp->sd_tune.gt_statfs_slow) + if (logd_secs != 30) + seq_printf(s, ",commit=%d", logd_secs); + if (statfs_quantum != 30) + seq_printf(s, ",statfs_quantum=%d", statfs_quantum); + else if (statfs_slow) seq_puts(s, ",statfs_quantum=0"); - val = sdp->sd_tune.gt_quota_quantum; - if (val != 60) - seq_printf(s, ",quota_quantum=%d", val); + if (quota_quantum != 60) + seq_printf(s, ",quota_quantum=%d", quota_quantum); if (args->ar_statfs_percent) seq_printf(s, ",statfs_percent=%d", args->ar_statfs_percent); if (args->ar_errors != GFS2_ERRORS_DEFAULT) { @@ -1583,6 +1590,14 @@ static void gfs2_evict_inode(struct inode *inode) if (inode->i_nlink || sb_rdonly(sb)) goto out; + /* + * In case of an incomplete mount, gfs2_evict_inode() may be called for + * system files without having an active journal to write to. In that + * case, skip the filesystem evict. + */ + if (!sdp->sd_jdesc) + goto out; + if (test_bit(GIF_ALLOC_FAILED, &ip->i_flags)) { BUG_ON(!gfs2_glock_is_locked_by_me(ip->i_gl)); gfs2_holder_mark_uninitialized(&gh); diff --git a/fs/hfs/bfind.c b/fs/hfs/bfind.c index 4af318fbda77..ef9498a6e88a 100644 --- a/fs/hfs/bfind.c +++ b/fs/hfs/bfind.c @@ -25,7 +25,19 @@ int hfs_find_init(struct hfs_btree *tree, struct hfs_find_data *fd) fd->key = ptr + tree->max_key_len + 2; hfs_dbg(BNODE_REFS, "find_init: %d (%p)\n", tree->cnid, __builtin_return_address(0)); - mutex_lock(&tree->tree_lock); + switch (tree->cnid) { + case HFS_CAT_CNID: + mutex_lock_nested(&tree->tree_lock, CATALOG_BTREE_MUTEX); + break; + case HFS_EXT_CNID: + mutex_lock_nested(&tree->tree_lock, EXTENTS_BTREE_MUTEX); + break; + case HFS_ATTR_CNID: + mutex_lock_nested(&tree->tree_lock, ATTR_BTREE_MUTEX); + break; + default: + return -EINVAL; + } return 0; } diff --git a/fs/hfs/bnode.c b/fs/hfs/bnode.c index b63a4df7327b..397e02a56697 100644 --- a/fs/hfs/bnode.c +++ b/fs/hfs/bnode.c @@ -15,16 +15,31 @@ #include "btree.h" -void hfs_bnode_read(struct hfs_bnode *node, void *buf, - int off, int len) +void hfs_bnode_read(struct hfs_bnode *node, void *buf, int off, int len) { struct page *page; + int pagenum; + int bytes_read; + int bytes_to_read; + void *vaddr; off += node->page_offset; - page = node->page[0]; + pagenum = off >> PAGE_SHIFT; + off &= ~PAGE_MASK; /* compute page offset for the first page */ - memcpy(buf, kmap(page) + off, len); - kunmap(page); + for (bytes_read = 0; bytes_read < len; bytes_read += bytes_to_read) { + if (pagenum >= node->tree->pages_per_bnode) + break; + page = node->page[pagenum]; + bytes_to_read = min_t(int, len - bytes_read, PAGE_SIZE - off); + + vaddr = kmap_atomic(page); + memcpy(buf + bytes_read, vaddr + off, bytes_to_read); + kunmap_atomic(vaddr); + + pagenum++; + off = 0; /* page offset only applies to the first page */ + } } u16 hfs_bnode_read_u16(struct hfs_bnode *node, int off) @@ -266,6 +281,7 @@ static struct hfs_bnode *__hfs_bnode_create(struct hfs_btree *tree, u32 cnid) tree->node_hash[hash] = node; tree->node_hash_cnt++; } else { + hfs_bnode_get(node2); spin_unlock(&tree->hash_lock); kfree(node); wait_event(node2->lock_wq, !test_bit(HFS_BNODE_NEW, &node2->flags)); diff --git a/fs/hfs/btree.h b/fs/hfs/btree.h index dcc2aab1b2c4..25ac9a8bb57a 100644 --- a/fs/hfs/btree.h +++ b/fs/hfs/btree.h @@ -13,6 +13,13 @@ typedef int (*btree_keycmp)(const btree_key *, const btree_key *); #define NODE_HASH_SIZE 256 +/* B-tree mutex nested subclasses */ +enum hfs_btree_mutex_classes { + CATALOG_BTREE_MUTEX, + EXTENTS_BTREE_MUTEX, + ATTR_BTREE_MUTEX, +}; + /* A HFS BTree held in memory */ struct hfs_btree { struct super_block *sb; diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index da243c84e93b..ee2ea5532e69 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -453,14 +453,16 @@ int hfs_write_inode(struct inode *inode, struct writeback_control *wbc) /* panic? */ return -EIO; + res = -EIO; + if (HFS_I(main_inode)->cat_key.CName.len > HFS_NAMELEN) + goto out; fd.search_key->cat = HFS_I(main_inode)->cat_key; if (hfs_brec_find(&fd)) - /* panic? */ goto out; if (S_ISDIR(main_inode->i_mode)) { if (fd.entrylength < sizeof(struct hfs_cat_dir)) - /* panic? */; + goto out; hfs_bnode_read(fd.bnode, &rec, fd.entryoffset, sizeof(struct hfs_cat_dir)); if (rec.type != HFS_CDR_DIR || @@ -473,6 +475,8 @@ int hfs_write_inode(struct inode *inode, struct writeback_control *wbc) hfs_bnode_write(fd.bnode, &rec, fd.entryoffset, sizeof(struct hfs_cat_dir)); } else if (HFS_IS_RSRC(inode)) { + if (fd.entrylength < sizeof(struct hfs_cat_file)) + goto out; hfs_bnode_read(fd.bnode, &rec, fd.entryoffset, sizeof(struct hfs_cat_file)); hfs_inode_write_fork(inode, rec.file.RExtRec, @@ -481,7 +485,7 @@ int hfs_write_inode(struct inode *inode, struct writeback_control *wbc) sizeof(struct hfs_cat_file)); } else { if (fd.entrylength < sizeof(struct hfs_cat_file)) - /* panic? */; + goto out; hfs_bnode_read(fd.bnode, &rec, fd.entryoffset, sizeof(struct hfs_cat_file)); if (rec.type != HFS_CDR_FIL || @@ -498,9 +502,10 @@ int hfs_write_inode(struct inode *inode, struct writeback_control *wbc) hfs_bnode_write(fd.bnode, &rec, fd.entryoffset, sizeof(struct hfs_cat_file)); } + res = 0; out: hfs_find_exit(&fd); - return 0; + return res; } static struct dentry *hfs_file_lookup(struct inode *dir, struct dentry *dentry, diff --git a/fs/hfs/super.c b/fs/hfs/super.c index 173876782f73..77b6f35a4aa9 100644 --- a/fs/hfs/super.c +++ b/fs/hfs/super.c @@ -427,14 +427,12 @@ static int hfs_fill_super(struct super_block *sb, void *data, int silent) if (!res) { if (fd.entrylength > sizeof(rec) || fd.entrylength < 0) { res = -EIO; - goto bail; + goto bail_hfs_find; } hfs_bnode_read(fd.bnode, &rec, fd.entryoffset, fd.entrylength); } - if (res) { - hfs_find_exit(&fd); - goto bail_no_root; - } + if (res) + goto bail_hfs_find; res = -EINVAL; root_inode = hfs_iget(sb, &fd.search_key->cat, &rec); hfs_find_exit(&fd); @@ -450,6 +448,8 @@ static int hfs_fill_super(struct super_block *sb, void *data, int silent) /* everything's okay */ return 0; +bail_hfs_find: + hfs_find_exit(&fd); bail_no_root: pr_err("get root inode failed\n"); bail: diff --git a/fs/hfs/trans.c b/fs/hfs/trans.c index 39f5e343bf4d..fdb0edb8a607 100644 --- a/fs/hfs/trans.c +++ b/fs/hfs/trans.c @@ -109,7 +109,7 @@ void hfs_asc2mac(struct super_block *sb, struct hfs_name *out, const struct qstr if (nls_io) { wchar_t ch; - while (srclen > 0) { + while (srclen > 0 && dstlen > 0) { size = nls_io->char2uni(src, srclen, &ch); if (size < 0) { ch = '?'; diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c index a930ddd15681..7054a542689f 100644 --- a/fs/hfsplus/extents.c +++ b/fs/hfsplus/extents.c @@ -598,13 +598,15 @@ void hfsplus_file_truncate(struct inode *inode) res = __hfsplus_ext_cache_extent(&fd, inode, alloc_cnt); if (res) break; - hfs_brec_remove(&fd); - mutex_unlock(&fd.tree->tree_lock); start = hip->cached_start; + if (blk_cnt <= start) + hfs_brec_remove(&fd); + mutex_unlock(&fd.tree->tree_lock); hfsplus_free_extents(sb, hip->cached_extents, alloc_cnt - start, alloc_cnt - blk_cnt); hfsplus_dump_extent(hip->cached_extents); + mutex_lock(&fd.tree->tree_lock); if (blk_cnt > start) { hip->extent_state |= HFSPLUS_EXT_DIRTY; break; @@ -612,7 +614,6 @@ void hfsplus_file_truncate(struct inode *inode) alloc_cnt = start; hip->cached_start = hip->cached_blocks = 0; hip->extent_state &= ~(HFSPLUS_EXT_DIRTY | HFSPLUS_EXT_NEW); - mutex_lock(&fd.tree->tree_lock); } hfs_find_exit(&fd); diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h index dd7ad9f13e3a..db2e1c750199 100644 --- a/fs/hfsplus/hfsplus_fs.h +++ b/fs/hfsplus/hfsplus_fs.h @@ -198,6 +198,8 @@ struct hfsplus_sb_info { #define HFSPLUS_SB_HFSX 3 #define HFSPLUS_SB_CASEFOLD 4 #define HFSPLUS_SB_NOBARRIER 5 +#define HFSPLUS_SB_UID 6 +#define HFSPLUS_SB_GID 7 static inline struct hfsplus_sb_info *HFSPLUS_SB(struct super_block *sb) { diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index d7ab9d8c4b67..a1d4ad584b10 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -187,11 +187,11 @@ static void hfsplus_get_perms(struct inode *inode, mode = be16_to_cpu(perms->mode); i_uid_write(inode, be32_to_cpu(perms->owner)); - if (!i_uid_read(inode) && !mode) + if ((test_bit(HFSPLUS_SB_UID, &sbi->flags)) || (!i_uid_read(inode) && !mode)) inode->i_uid = sbi->uid; i_gid_write(inode, be32_to_cpu(perms->group)); - if (!i_gid_read(inode) && !mode) + if ((test_bit(HFSPLUS_SB_GID, &sbi->flags)) || (!i_gid_read(inode) && !mode)) inode->i_gid = sbi->gid; if (dir) { @@ -476,8 +476,11 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd) if (type == HFSPLUS_FOLDER) { struct hfsplus_cat_folder *folder = &entry.folder; - if (fd->entrylength < sizeof(struct hfsplus_cat_folder)) - /* panic? */; + if (fd->entrylength < sizeof(struct hfsplus_cat_folder)) { + pr_err("bad catalog folder entry\n"); + res = -EIO; + goto out; + } hfs_bnode_read(fd->bnode, &entry, fd->entryoffset, sizeof(struct hfsplus_cat_folder)); hfsplus_get_perms(inode, &folder->permissions, 1); @@ -497,8 +500,11 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd) } else if (type == HFSPLUS_FILE) { struct hfsplus_cat_file *file = &entry.file; - if (fd->entrylength < sizeof(struct hfsplus_cat_file)) - /* panic? */; + if (fd->entrylength < sizeof(struct hfsplus_cat_file)) { + pr_err("bad catalog file entry\n"); + res = -EIO; + goto out; + } hfs_bnode_read(fd->bnode, &entry, fd->entryoffset, sizeof(struct hfsplus_cat_file)); @@ -529,6 +535,7 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd) pr_err("bad catalog entry used to create inode\n"); res = -EIO; } +out: return res; } @@ -537,6 +544,7 @@ int hfsplus_cat_write_inode(struct inode *inode) struct inode *main_inode = inode; struct hfs_find_data fd; hfsplus_cat_entry entry; + int res = 0; if (HFSPLUS_IS_RSRC(inode)) main_inode = HFSPLUS_I(inode)->rsrc_inode; @@ -555,8 +563,11 @@ int hfsplus_cat_write_inode(struct inode *inode) if (S_ISDIR(main_inode->i_mode)) { struct hfsplus_cat_folder *folder = &entry.folder; - if (fd.entrylength < sizeof(struct hfsplus_cat_folder)) - /* panic? */; + if (fd.entrylength < sizeof(struct hfsplus_cat_folder)) { + pr_err("bad catalog folder entry\n"); + res = -EIO; + goto out; + } hfs_bnode_read(fd.bnode, &entry, fd.entryoffset, sizeof(struct hfsplus_cat_folder)); /* simple node checks? */ @@ -581,8 +592,11 @@ int hfsplus_cat_write_inode(struct inode *inode) } else { struct hfsplus_cat_file *file = &entry.file; - if (fd.entrylength < sizeof(struct hfsplus_cat_file)) - /* panic? */; + if (fd.entrylength < sizeof(struct hfsplus_cat_file)) { + pr_err("bad catalog file entry\n"); + res = -EIO; + goto out; + } hfs_bnode_read(fd.bnode, &entry, fd.entryoffset, sizeof(struct hfsplus_cat_file)); hfsplus_inode_write_fork(inode, &file->data_fork); @@ -603,5 +617,5 @@ int hfsplus_cat_write_inode(struct inode *inode) set_bit(HFSPLUS_I_CAT_DIRTY, &HFSPLUS_I(inode)->flags); out: hfs_find_exit(&fd); - return 0; + return res; } diff --git a/fs/hfsplus/options.c b/fs/hfsplus/options.c index 047e05c57560..c94a58762ad6 100644 --- a/fs/hfsplus/options.c +++ b/fs/hfsplus/options.c @@ -140,6 +140,8 @@ int hfsplus_parse_options(char *input, struct hfsplus_sb_info *sbi) if (!uid_valid(sbi->uid)) { pr_err("invalid uid specified\n"); return 0; + } else { + set_bit(HFSPLUS_SB_UID, &sbi->flags); } break; case opt_gid: @@ -151,6 +153,8 @@ int hfsplus_parse_options(char *input, struct hfsplus_sb_info *sbi) if (!gid_valid(sbi->gid)) { pr_err("invalid gid specified\n"); return 0; + } else { + set_bit(HFSPLUS_SB_GID, &sbi->flags); } break; case opt_part: diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c index eb4535eba95d..3b1356b10a47 100644 --- a/fs/hfsplus/super.c +++ b/fs/hfsplus/super.c @@ -294,11 +294,11 @@ static void hfsplus_put_super(struct super_block *sb) hfsplus_sync_fs(sb, 1); } + iput(sbi->alloc_file); + iput(sbi->hidden_dir); hfs_btree_close(sbi->attr_tree); hfs_btree_close(sbi->cat_tree); hfs_btree_close(sbi->ext_tree); - iput(sbi->alloc_file); - iput(sbi->hidden_dir); kfree(sbi->s_vhdr_buf); kfree(sbi->s_backup_vhdr_buf); unload_nls(sbi->nls); diff --git a/fs/hfsplus/unicode.c b/fs/hfsplus/unicode.c index c8d1b2be7854..73342c925a4b 100644 --- a/fs/hfsplus/unicode.c +++ b/fs/hfsplus/unicode.c @@ -398,7 +398,7 @@ int hfsplus_hash_dentry(const struct dentry *dentry, struct qstr *str) astr = str->name; len = str->len; while (len > 0) { - int uninitialized_var(dsize); + int dsize; size = asc2unichar(sb, astr, len, &c); astr += size; len -= size; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 7a24f91af29e..b313627b1801 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -426,7 +426,7 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, u32 hash; index = page->index; - hash = hugetlb_fault_mutex_hash(h, mapping, index, 0); + hash = hugetlb_fault_mutex_hash(h, mapping, index); mutex_lock(&hugetlb_fault_mutex_table[hash]); /* @@ -623,7 +623,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, addr = index * hpage_size; /* mutex taken here, fault path and hole punch */ - hash = hugetlb_fault_mutex_hash(h, mapping, index, addr); + hash = hugetlb_fault_mutex_hash(h, mapping, index); mutex_lock(&hugetlb_fault_mutex_table[hash]); /* See if already present in mapping to avoid alloc/free */ @@ -654,9 +654,10 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, mutex_unlock(&hugetlb_fault_mutex_table[hash]); + set_page_huge_active(page); /* * unlock_page because locked by add_to_page_cache() - * page_put due to reference from alloc_huge_page() + * put_page() due to reference from alloc_huge_page() */ unlock_page(page); put_page(page); diff --git a/fs/inode.c b/fs/inode.c index c9eb5041ffae..5df2e8ee23ed 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -166,8 +166,6 @@ int inode_init_always(struct super_block *sb, struct inode *inode) inode->i_wb_frn_history = 0; #endif - if (security_inode_alloc(inode)) - goto out; spin_lock_init(&inode->i_lock); lockdep_set_class(&inode->i_lock, &sb->s_type->i_lock_key); @@ -195,11 +193,12 @@ int inode_init_always(struct super_block *sb, struct inode *inode) inode->i_fsnotify_mask = 0; #endif inode->i_flctx = NULL; + + if (unlikely(security_inode_alloc(inode))) + return -ENOMEM; this_cpu_inc(nr_inodes); return 0; -out: - return -ENOMEM; } EXPORT_SYMBOL(inode_init_always); diff --git a/fs/iomap.c b/fs/iomap.c index 03edf62633dc..04e82b6bd9bf 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -109,6 +109,7 @@ static struct iomap_page * iomap_page_create(struct inode *inode, struct page *page) { struct iomap_page *iop = to_iomap_page(page); + unsigned int nr_blocks = PAGE_SIZE / i_blocksize(inode); if (iop || i_blocksize(inode) == PAGE_SIZE) return iop; @@ -116,7 +117,10 @@ iomap_page_create(struct inode *inode, struct page *page) iop = kmalloc(sizeof(*iop), GFP_NOFS | __GFP_NOFAIL); atomic_set(&iop->read_count, 0); atomic_set(&iop->write_count, 0); + spin_lock_init(&iop->uptodate_lock); bitmap_zero(iop->uptodate, PAGE_SIZE / SECTOR_SIZE); + if (PageUptodate(page)) + bitmap_fill(iop->uptodate, nr_blocks); /* * migrate_page_move_mapping() assumes that pages with private data have @@ -204,25 +208,38 @@ iomap_adjust_read_range(struct inode *inode, struct iomap_page *iop, } static void -iomap_set_range_uptodate(struct page *page, unsigned off, unsigned len) +iomap_iop_set_range_uptodate(struct page *page, unsigned off, unsigned len) { struct iomap_page *iop = to_iomap_page(page); struct inode *inode = page->mapping->host; unsigned first = off >> inode->i_blkbits; unsigned last = (off + len - 1) >> inode->i_blkbits; - unsigned int i; bool uptodate = true; + unsigned long flags; + unsigned int i; - if (iop) { - for (i = 0; i < PAGE_SIZE / i_blocksize(inode); i++) { - if (i >= first && i <= last) - set_bit(i, iop->uptodate); - else if (!test_bit(i, iop->uptodate)) - uptodate = false; - } + spin_lock_irqsave(&iop->uptodate_lock, flags); + for (i = 0; i < PAGE_SIZE / i_blocksize(inode); i++) { + if (i >= first && i <= last) + set_bit(i, iop->uptodate); + else if (!test_bit(i, iop->uptodate)) + uptodate = false; } - if (uptodate && !PageError(page)) + if (uptodate) + SetPageUptodate(page); + spin_unlock_irqrestore(&iop->uptodate_lock, flags); +} + +static void +iomap_set_range_uptodate(struct page *page, unsigned off, unsigned len) +{ + if (PageError(page)) + return; + + if (page_has_private(page)) + iomap_iop_set_range_uptodate(page, off, len); + else SetPageUptodate(page); } diff --git a/fs/isofs/dir.c b/fs/isofs/dir.c index 947ce22f5b3c..55df4d80793b 100644 --- a/fs/isofs/dir.c +++ b/fs/isofs/dir.c @@ -152,6 +152,7 @@ static int do_isofs_readdir(struct inode *inode, struct file *file, printk(KERN_NOTICE "iso9660: Corrupted directory entry" " in block %lu of inode %lu\n", block, inode->i_ino); + brelse(bh); return -EIO; } diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index 488a9e7f8f66..6e4e2cfd40b9 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -157,7 +157,6 @@ struct iso9660_options{ unsigned int overriderockperm:1; unsigned int uid_set:1; unsigned int gid_set:1; - unsigned int utf8:1; unsigned char map; unsigned char check; unsigned int blocksize; @@ -357,7 +356,6 @@ static int parse_options(char *options, struct iso9660_options *popt) popt->gid = GLOBAL_ROOT_GID; popt->uid = GLOBAL_ROOT_UID; popt->iocharset = NULL; - popt->utf8 = 0; popt->overriderockperm = 0; popt->session=-1; popt->sbsector=-1; @@ -390,10 +388,13 @@ static int parse_options(char *options, struct iso9660_options *popt) case Opt_cruft: popt->cruft = 1; break; +#ifdef CONFIG_JOLIET case Opt_utf8: - popt->utf8 = 1; + kfree(popt->iocharset); + popt->iocharset = kstrdup("utf8", GFP_KERNEL); + if (!popt->iocharset) + return 0; break; -#ifdef CONFIG_JOLIET case Opt_iocharset: kfree(popt->iocharset); popt->iocharset = match_strdup(&args[0]); @@ -496,7 +497,6 @@ static int isofs_show_options(struct seq_file *m, struct dentry *root) if (sbi->s_nocompress) seq_puts(m, ",nocompress"); if (sbi->s_overriderockperm) seq_puts(m, ",overriderockperm"); if (sbi->s_showassoc) seq_puts(m, ",showassoc"); - if (sbi->s_utf8) seq_puts(m, ",utf8"); if (sbi->s_check) seq_printf(m, ",check=%c", sbi->s_check); if (sbi->s_mapping) seq_printf(m, ",map=%c", sbi->s_mapping); @@ -519,9 +519,10 @@ static int isofs_show_options(struct seq_file *m, struct dentry *root) seq_printf(m, ",fmode=%o", sbi->s_fmode); #ifdef CONFIG_JOLIET - if (sbi->s_nls_iocharset && - strcmp(sbi->s_nls_iocharset->charset, CONFIG_NLS_DEFAULT) != 0) + if (sbi->s_nls_iocharset) seq_printf(m, ",iocharset=%s", sbi->s_nls_iocharset->charset); + else + seq_puts(m, ",iocharset=utf8"); #endif return 0; } @@ -865,14 +866,13 @@ root_found: sbi->s_nls_iocharset = NULL; #ifdef CONFIG_JOLIET - if (joliet_level && opt.utf8 == 0) { + if (joliet_level) { char *p = opt.iocharset ? opt.iocharset : CONFIG_NLS_DEFAULT; - sbi->s_nls_iocharset = load_nls(p); - if (! sbi->s_nls_iocharset) { - /* Fail only if explicit charset specified */ - if (opt.iocharset) + if (strcmp(p, "utf8") != 0) { + sbi->s_nls_iocharset = opt.iocharset ? + load_nls(opt.iocharset) : load_nls_default(); + if (!sbi->s_nls_iocharset) goto out_freesbi; - sbi->s_nls_iocharset = load_nls_default(); } } #endif @@ -888,7 +888,6 @@ root_found: sbi->s_gid = opt.gid; sbi->s_uid_set = opt.uid_set; sbi->s_gid_set = opt.gid_set; - sbi->s_utf8 = opt.utf8; sbi->s_nocompress = opt.nocompress; sbi->s_overriderockperm = opt.overriderockperm; /* @@ -1327,6 +1326,8 @@ static int isofs_read_inode(struct inode *inode, int relocated) de = (struct iso_directory_record *) (bh->b_data + offset); de_len = *(unsigned char *) de; + if (de_len < sizeof(struct iso_directory_record)) + goto fail; if (offset + de_len > bufsize) { int frag1 = bufsize - offset; diff --git a/fs/isofs/isofs.h b/fs/isofs/isofs.h index 055ec6c586f7..dcdc191ed183 100644 --- a/fs/isofs/isofs.h +++ b/fs/isofs/isofs.h @@ -44,7 +44,6 @@ struct isofs_sb_info { unsigned char s_session; unsigned int s_high_sierra:1; unsigned int s_rock:2; - unsigned int s_utf8:1; unsigned int s_cruft:1; /* Broken disks with high byte of length * containing junk */ unsigned int s_nocompress:1; diff --git a/fs/isofs/joliet.c b/fs/isofs/joliet.c index be8b6a9d0b92..c0f04a1e7f69 100644 --- a/fs/isofs/joliet.c +++ b/fs/isofs/joliet.c @@ -41,14 +41,12 @@ uni16_to_x8(unsigned char *ascii, __be16 *uni, int len, struct nls_table *nls) int get_joliet_filename(struct iso_directory_record * de, unsigned char *outname, struct inode * inode) { - unsigned char utf8; struct nls_table *nls; unsigned char len = 0; - utf8 = ISOFS_SB(inode->i_sb)->s_utf8; nls = ISOFS_SB(inode->i_sb)->s_nls_iocharset; - if (utf8) { + if (!nls) { len = utf16s_to_utf8s((const wchar_t *) de->name, de->name_len[0] >> 1, UTF16_BIG_ENDIAN, outname, PAGE_SIZE); diff --git a/fs/isofs/namei.c b/fs/isofs/namei.c index cac468f04820..58f80e1b3ac0 100644 --- a/fs/isofs/namei.c +++ b/fs/isofs/namei.c @@ -102,6 +102,7 @@ isofs_find_entry(struct inode *dir, struct dentry *dentry, printk(KERN_NOTICE "iso9660: Corrupted directory entry" " in block %lu of inode %lu\n", block, dir->i_ino); + brelse(bh); return 0; } @@ -152,8 +153,8 @@ isofs_find_entry(struct inode *dir, struct dentry *dentry, struct dentry *isofs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { int found; - unsigned long uninitialized_var(block); - unsigned long uninitialized_var(offset); + unsigned long block; + unsigned long offset; struct inode *inode; struct page *page; diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 8a50722bca29..629928b19e48 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1375,9 +1375,11 @@ static int jbd2_write_superblock(journal_t *journal, int write_flags) return -EIO; } - trace_jbd2_write_superblock(journal, write_flags); if (!(journal->j_flags & JBD2_BARRIER)) write_flags &= ~(REQ_FUA | REQ_PREFLUSH); + + trace_jbd2_write_superblock(journal, write_flags); + if (buffer_write_io_error(bh)) { /* * Oh, dear. A previous attempt to write the journal diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c index a4967b27ffb6..ed923a9765c2 100644 --- a/fs/jbd2/recovery.c +++ b/fs/jbd2/recovery.c @@ -247,6 +247,8 @@ int jbd2_journal_recover(journal_t *journal) journal_superblock_t * sb; struct recovery_info info; + errseq_t wb_err; + struct address_space *mapping; memset(&info, 0, sizeof(info)); sb = journal->j_superblock; @@ -264,6 +266,9 @@ int jbd2_journal_recover(journal_t *journal) return 0; } + wb_err = 0; + mapping = journal->j_fs_dev->bd_inode->i_mapping; + errseq_check_and_advance(&mapping->wb_err, &wb_err); err = do_one_pass(journal, &info, PASS_SCAN); if (!err) err = do_one_pass(journal, &info, PASS_REVOKE); @@ -284,6 +289,9 @@ int jbd2_journal_recover(journal_t *journal) err2 = sync_blockdev(journal->j_fs_dev); if (!err) err = err2; + err2 = errseq_check_and_advance(&mapping->wb_err, &wb_err); + if (!err) + err = err2; /* Make sure all replayed data is on permanent storage */ if (journal->j_flags & JBD2_BARRIER) { err2 = blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL); diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 8c305593fb51..dbad00c20aa1 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -1339,8 +1339,6 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh) struct journal_head *jh; int ret = 0; - if (is_handle_aborted(handle)) - return -EROFS; if (!buffer_jbd(bh)) return -EUCLEAN; @@ -1387,6 +1385,18 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh) journal = transaction->t_journal; jbd_lock_bh_state(bh); + if (is_handle_aborted(handle)) { + /* + * Check journal aborting with @jh->b_state_lock locked, + * since 'jh->b_transaction' could be replaced with + * 'jh->b_next_transaction' during old transaction + * committing if journal aborted, which may fail + * assertion on 'jh->b_frozen_data == NULL'. + */ + ret = -EROFS; + goto out_unlock_bh; + } + if (jh->b_modified == 0) { /* * This buffer's got modified and becoming part diff --git a/fs/jffs2/build.c b/fs/jffs2/build.c index b288c8ae1236..6ae9d6fefb86 100644 --- a/fs/jffs2/build.c +++ b/fs/jffs2/build.c @@ -211,7 +211,10 @@ static int jffs2_build_filesystem(struct jffs2_sb_info *c) ic->scan_dents = NULL; cond_resched(); } - jffs2_build_xattr_subsystem(c); + ret = jffs2_build_xattr_subsystem(c); + if (ret) + goto exit; + c->flags &= ~JFFS2_SB_FLAG_BUILDING; dbg_fsbuild("FS build complete\n"); @@ -415,13 +418,15 @@ int jffs2_do_mount_fs(struct jffs2_sb_info *c) jffs2_free_ino_caches(c); jffs2_free_raw_node_refs(c); ret = -EIO; - goto out_free; + goto out_sum_exit; } jffs2_calc_trigger_levels(c); return 0; + out_sum_exit: + jffs2_sum_exit(c); out_free: kvfree(c->blocks); diff --git a/fs/jffs2/compr_rtime.c b/fs/jffs2/compr_rtime.c index 406d9cc84ba8..79e771ab624f 100644 --- a/fs/jffs2/compr_rtime.c +++ b/fs/jffs2/compr_rtime.c @@ -37,6 +37,9 @@ static int jffs2_rtime_compress(unsigned char *data_in, int outpos = 0; int pos=0; + if (*dstlen <= 3) + return -1; + memset(positions,0,sizeof(positions)); while (pos < (*sourcelen) && outpos <= (*dstlen)-2) { diff --git a/fs/jffs2/erase.c b/fs/jffs2/erase.c index 83b8f06b4a64..7e9abdb89712 100644 --- a/fs/jffs2/erase.c +++ b/fs/jffs2/erase.c @@ -401,7 +401,7 @@ static void jffs2_mark_erased_block(struct jffs2_sb_info *c, struct jffs2_eraseb { size_t retlen; int ret; - uint32_t uninitialized_var(bad_offset); + uint32_t bad_offset; switch (jffs2_block_check_erase(c, jeb, &bad_offset)) { case -EAGAIN: goto refile; diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c index 7d8654a1472e..bf3d8a4516a5 100644 --- a/fs/jffs2/file.c +++ b/fs/jffs2/file.c @@ -135,31 +135,25 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, struct page *pg; struct inode *inode = mapping->host; struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode); + struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb); pgoff_t index = pos >> PAGE_SHIFT; - uint32_t pageofs = index << PAGE_SHIFT; int ret = 0; - pg = grab_cache_page_write_begin(mapping, index, flags); - if (!pg) - return -ENOMEM; - *pagep = pg; - jffs2_dbg(1, "%s()\n", __func__); - if (pageofs > inode->i_size) { - /* Make new hole frag from old EOF to new page */ - struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb); + if (pos > inode->i_size) { + /* Make new hole frag from old EOF to new position */ struct jffs2_raw_inode ri; struct jffs2_full_dnode *fn; uint32_t alloc_len; - jffs2_dbg(1, "Writing new hole frag 0x%x-0x%x between current EOF and new page\n", - (unsigned int)inode->i_size, pageofs); + jffs2_dbg(1, "Writing new hole frag 0x%x-0x%x between current EOF and new position\n", + (unsigned int)inode->i_size, (uint32_t)pos); ret = jffs2_reserve_space(c, sizeof(ri), &alloc_len, ALLOC_NORMAL, JFFS2_SUMMARY_INODE_SIZE); if (ret) - goto out_page; + goto out_err; mutex_lock(&f->sem); memset(&ri, 0, sizeof(ri)); @@ -174,10 +168,10 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, ri.mode = cpu_to_jemode(inode->i_mode); ri.uid = cpu_to_je16(i_uid_read(inode)); ri.gid = cpu_to_je16(i_gid_read(inode)); - ri.isize = cpu_to_je32(max((uint32_t)inode->i_size, pageofs)); + ri.isize = cpu_to_je32((uint32_t)pos); ri.atime = ri.ctime = ri.mtime = cpu_to_je32(JFFS2_NOW()); ri.offset = cpu_to_je32(inode->i_size); - ri.dsize = cpu_to_je32(pageofs - inode->i_size); + ri.dsize = cpu_to_je32((uint32_t)pos - inode->i_size); ri.csize = cpu_to_je32(0); ri.compr = JFFS2_COMPR_ZERO; ri.node_crc = cpu_to_je32(crc32(0, &ri, sizeof(ri)-8)); @@ -189,7 +183,7 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, ret = PTR_ERR(fn); jffs2_complete_reservation(c); mutex_unlock(&f->sem); - goto out_page; + goto out_err; } ret = jffs2_add_full_dnode_to_inode(c, f, fn); if (f->metadata) { @@ -204,14 +198,27 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, jffs2_free_full_dnode(fn); jffs2_complete_reservation(c); mutex_unlock(&f->sem); - goto out_page; + goto out_err; } jffs2_complete_reservation(c); - inode->i_size = pageofs; + inode->i_size = pos; mutex_unlock(&f->sem); } /* + * While getting a page and reading data in, lock c->alloc_sem until + * the page is Uptodate. Otherwise GC task may attempt to read the same + * page in read_cache_page(), which causes a deadlock. + */ + mutex_lock(&c->alloc_sem); + pg = grab_cache_page_write_begin(mapping, index, flags); + if (!pg) { + ret = -ENOMEM; + goto release_sem; + } + *pagep = pg; + + /* * Read in the page if it wasn't already present. Cannot optimize away * the whole page write case until jffs2_write_end can handle the * case of a short-copy. @@ -220,15 +227,17 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, mutex_lock(&f->sem); ret = jffs2_do_readpage_nolock(inode, pg); mutex_unlock(&f->sem); - if (ret) - goto out_page; + if (ret) { + unlock_page(pg); + put_page(pg); + goto release_sem; + } } jffs2_dbg(1, "end write_begin(). pg->flags %lx\n", pg->flags); - return ret; -out_page: - unlock_page(pg); - put_page(pg); +release_sem: + mutex_unlock(&c->alloc_sem); +out_err: return ret; } diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c index eab04eca95a3..6afaace72f2b 100644 --- a/fs/jffs2/fs.c +++ b/fs/jffs2/fs.c @@ -597,8 +597,9 @@ out_root: jffs2_free_ino_caches(c); jffs2_free_raw_node_refs(c); kvfree(c->blocks); - out_inohash: jffs2_clear_xattr_subsystem(c); + jffs2_sum_exit(c); + out_inohash: kfree(c->inocache_list); out_wbuf: jffs2_flash_cleanup(c); diff --git a/fs/jffs2/readinode.c b/fs/jffs2/readinode.c index bccfc40b3a74..d19483fa1fe8 100644 --- a/fs/jffs2/readinode.c +++ b/fs/jffs2/readinode.c @@ -672,6 +672,22 @@ static inline int read_direntry(struct jffs2_sb_info *c, struct jffs2_raw_node_r jffs2_free_full_dirent(fd); return -EIO; } + +#ifdef CONFIG_JFFS2_SUMMARY + /* + * we use CONFIG_JFFS2_SUMMARY because without it, we + * have checked it while mounting + */ + crc = crc32(0, fd->name, rd->nsize); + if (unlikely(crc != je32_to_cpu(rd->name_crc))) { + JFFS2_NOTICE("name CRC failed on dirent node at" + "%#08x: read %#08x,calculated %#08x\n", + ref_offset(ref), je32_to_cpu(rd->node_crc), crc); + jffs2_mark_node_obsolete(c, ref); + jffs2_free_full_dirent(fd); + return 0; + } +#endif } fd->nhash = full_name_hash(NULL, fd->name, rd->nsize); diff --git a/fs/jffs2/scan.c b/fs/jffs2/scan.c index 90431dd613b8..664384dac6e5 100644 --- a/fs/jffs2/scan.c +++ b/fs/jffs2/scan.c @@ -136,7 +136,7 @@ int jffs2_scan_medium(struct jffs2_sb_info *c) if (!s) { JFFS2_WARNING("Can't allocate memory for summary\n"); ret = -ENOMEM; - goto out; + goto out_buf; } } @@ -274,13 +274,15 @@ int jffs2_scan_medium(struct jffs2_sb_info *c) } ret = 0; out: + jffs2_sum_reset_collected(s); + kfree(s); + out_buf: if (buf_size) kfree(flashbuf); #ifndef __ECOS else mtd_unpoint(c->mtd, 0, c->mtd->size); #endif - kfree(s); return ret; } @@ -1075,7 +1077,7 @@ static int jffs2_scan_dirent_node(struct jffs2_sb_info *c, struct jffs2_eraseblo memcpy(&fd->name, rd->name, checkedlen); fd->name[checkedlen] = 0; - crc = crc32(0, fd->name, rd->nsize); + crc = crc32(0, fd->name, checkedlen); if (crc != je32_to_cpu(rd->name_crc)) { pr_notice("%s(): Name CRC failed on node at 0x%08x: Read 0x%08x, calculated 0x%08x\n", __func__, ofs, je32_to_cpu(rd->name_crc), crc); diff --git a/fs/jffs2/summary.c b/fs/jffs2/summary.c index be7c8a6a5748..4fe64519870f 100644 --- a/fs/jffs2/summary.c +++ b/fs/jffs2/summary.c @@ -783,6 +783,8 @@ static int jffs2_sum_write_data(struct jffs2_sb_info *c, struct jffs2_eraseblock dbg_summary("Writing unknown RWCOMPAT_COPY node type %x\n", je16_to_cpu(temp->u.nodetype)); jffs2_sum_disable_collecting(c->summary); + /* The above call removes the list, nothing more to do */ + goto bail_rwcompat; } else { BUG(); /* unknown node in summary information */ } @@ -794,6 +796,7 @@ static int jffs2_sum_write_data(struct jffs2_sb_info *c, struct jffs2_eraseblock c->summary->sum_num--; } + bail_rwcompat: jffs2_sum_reset_collected(c->summary); diff --git a/fs/jffs2/xattr.c b/fs/jffs2/xattr.c index da3e18503c65..acb4492f5970 100644 --- a/fs/jffs2/xattr.c +++ b/fs/jffs2/xattr.c @@ -772,10 +772,10 @@ void jffs2_clear_xattr_subsystem(struct jffs2_sb_info *c) } #define XREF_TMPHASH_SIZE (128) -void jffs2_build_xattr_subsystem(struct jffs2_sb_info *c) +int jffs2_build_xattr_subsystem(struct jffs2_sb_info *c) { struct jffs2_xattr_ref *ref, *_ref; - struct jffs2_xattr_ref *xref_tmphash[XREF_TMPHASH_SIZE]; + struct jffs2_xattr_ref **xref_tmphash; struct jffs2_xattr_datum *xd, *_xd; struct jffs2_inode_cache *ic; struct jffs2_raw_node_ref *raw; @@ -784,9 +784,12 @@ void jffs2_build_xattr_subsystem(struct jffs2_sb_info *c) BUG_ON(!(c->flags & JFFS2_SB_FLAG_BUILDING)); + xref_tmphash = kcalloc(XREF_TMPHASH_SIZE, + sizeof(struct jffs2_xattr_ref *), GFP_KERNEL); + if (!xref_tmphash) + return -ENOMEM; + /* Phase.1 : Merge same xref */ - for (i=0; i < XREF_TMPHASH_SIZE; i++) - xref_tmphash[i] = NULL; for (ref=c->xref_temp; ref; ref=_ref) { struct jffs2_xattr_ref *tmp; @@ -884,6 +887,8 @@ void jffs2_build_xattr_subsystem(struct jffs2_sb_info *c) "%u of xref (%u dead, %u orphan) found.\n", xdatum_count, xdatum_unchecked_count, xdatum_orphan_count, xref_count, xref_dead_count, xref_orphan_count); + kfree(xref_tmphash); + return 0; } struct jffs2_xattr_datum *jffs2_setup_xattr_datum(struct jffs2_sb_info *c, diff --git a/fs/jffs2/xattr.h b/fs/jffs2/xattr.h index 720007b2fd65..1b5030a3349d 100644 --- a/fs/jffs2/xattr.h +++ b/fs/jffs2/xattr.h @@ -71,7 +71,7 @@ static inline int is_xattr_ref_dead(struct jffs2_xattr_ref *ref) #ifdef CONFIG_JFFS2_FS_XATTR extern void jffs2_init_xattr_subsystem(struct jffs2_sb_info *c); -extern void jffs2_build_xattr_subsystem(struct jffs2_sb_info *c); +extern int jffs2_build_xattr_subsystem(struct jffs2_sb_info *c); extern void jffs2_clear_xattr_subsystem(struct jffs2_sb_info *c); extern struct jffs2_xattr_datum *jffs2_setup_xattr_datum(struct jffs2_sb_info *c, @@ -103,7 +103,7 @@ extern ssize_t jffs2_listxattr(struct dentry *, char *, size_t); #else #define jffs2_init_xattr_subsystem(c) -#define jffs2_build_xattr_subsystem(c) +#define jffs2_build_xattr_subsystem(c) (0) #define jffs2_clear_xattr_subsystem(c) #define jffs2_xattr_do_crccheck_inode(c, ic) diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c index 054cc761b426..68779cc3609a 100644 --- a/fs/jfs/inode.c +++ b/fs/jfs/inode.c @@ -156,12 +156,14 @@ void jfs_evict_inode(struct inode *inode) dquot_initialize(inode); if (JFS_IP(inode)->fileset == FILESYSTEM_I) { + struct inode *ipimap = JFS_SBI(inode->i_sb)->ipimap; truncate_inode_pages_final(&inode->i_data); if (test_cflag(COMMIT_Freewmap, inode)) jfs_free_zero_link(inode); - diFree(inode); + if (ipimap && JFS_IP(ipimap)->i_imap) + diFree(inode); /* * Free the inode from the quota allocation. diff --git a/fs/jfs/jfs_dmap.c b/fs/jfs/jfs_dmap.c index 49263e220dbc..2f452b5ee731 100644 --- a/fs/jfs/jfs_dmap.c +++ b/fs/jfs/jfs_dmap.c @@ -100,7 +100,7 @@ static int dbAllocCtl(struct bmap * bmp, s64 nblocks, int l2nb, s64 blkno, static int dbExtend(struct inode *ip, s64 blkno, s64 nblocks, s64 addnblocks); static int dbFindBits(u32 word, int l2nb); static int dbFindCtl(struct bmap * bmp, int l2nb, int level, s64 * blkno); -static int dbFindLeaf(dmtree_t * tp, int l2nb, int *leafidx); +static int dbFindLeaf(dmtree_t *tp, int l2nb, int *leafidx, bool is_ctl); static int dbFreeBits(struct bmap * bmp, struct dmap * dp, s64 blkno, int nblocks); static int dbFreeDmap(struct bmap * bmp, struct dmap * dp, s64 blkno, @@ -161,13 +161,14 @@ static const s8 budtab[256] = { * 0 - success * -ENOMEM - insufficient memory * -EIO - i/o error + * -EINVAL - wrong bmap data */ int dbMount(struct inode *ipbmap) { struct bmap *bmp; struct dbmap_disk *dbmp_le; struct metapage *mp; - int i; + int i, err; /* * allocate/initialize the in-memory bmap descriptor @@ -182,24 +183,53 @@ int dbMount(struct inode *ipbmap) BMAPBLKNO << JFS_SBI(ipbmap->i_sb)->l2nbperpage, PSIZE, 0); if (mp == NULL) { - kfree(bmp); - return -EIO; + err = -EIO; + goto err_kfree_bmp; } /* copy the on-disk bmap descriptor to its in-memory version. */ dbmp_le = (struct dbmap_disk *) mp->data; bmp->db_mapsize = le64_to_cpu(dbmp_le->dn_mapsize); bmp->db_nfree = le64_to_cpu(dbmp_le->dn_nfree); + bmp->db_l2nbperpage = le32_to_cpu(dbmp_le->dn_l2nbperpage); + if (bmp->db_l2nbperpage > L2PSIZE - L2MINBLOCKSIZE || + bmp->db_l2nbperpage < 0) { + err = -EINVAL; + goto err_release_metapage; + } + bmp->db_numag = le32_to_cpu(dbmp_le->dn_numag); + if (!bmp->db_numag) { + err = -EINVAL; + goto err_release_metapage; + } + bmp->db_maxlevel = le32_to_cpu(dbmp_le->dn_maxlevel); bmp->db_maxag = le32_to_cpu(dbmp_le->dn_maxag); bmp->db_agpref = le32_to_cpu(dbmp_le->dn_agpref); + if (bmp->db_maxag >= MAXAG || bmp->db_maxag < 0 || + bmp->db_agpref >= MAXAG || bmp->db_agpref < 0) { + err = -EINVAL; + goto err_release_metapage; + } + bmp->db_aglevel = le32_to_cpu(dbmp_le->dn_aglevel); bmp->db_agheight = le32_to_cpu(dbmp_le->dn_agheight); bmp->db_agwidth = le32_to_cpu(dbmp_le->dn_agwidth); bmp->db_agstart = le32_to_cpu(dbmp_le->dn_agstart); bmp->db_agl2size = le32_to_cpu(dbmp_le->dn_agl2size); + if (bmp->db_agl2size > L2MAXL2SIZE - L2MAXAG || + bmp->db_agl2size < 0) { + err = -EINVAL; + goto err_release_metapage; + } + + if (((bmp->db_mapsize - 1) >> bmp->db_agl2size) > MAXAG) { + err = -EINVAL; + goto err_release_metapage; + } + for (i = 0; i < MAXAG; i++) bmp->db_agfree[i] = le64_to_cpu(dbmp_le->dn_agfree[i]); bmp->db_agsize = le64_to_cpu(dbmp_le->dn_agsize); @@ -220,6 +250,12 @@ int dbMount(struct inode *ipbmap) BMAP_LOCK_INIT(bmp); return (0); + +err_release_metapage: + release_metapage(mp); +err_kfree_bmp: + kfree(bmp); + return err; } @@ -253,6 +289,7 @@ int dbUnmount(struct inode *ipbmap, int mounterror) /* free the memory for the in-memory bmap. */ kfree(bmp); + JFS_SBI(ipbmap->i_sb)->bmap = NULL; return (0); } @@ -391,7 +428,8 @@ int dbFree(struct inode *ip, s64 blkno, s64 nblocks) } /* write the last buffer. */ - write_metapage(mp); + if (mp) + write_metapage(mp); IREAD_UNLOCK(ipbmap); @@ -1669,7 +1707,7 @@ s64 dbDiscardAG(struct inode *ip, int agno, s64 minlen) } else if (rc == -ENOSPC) { /* search for next smaller log2 block */ l2nb = BLKSTOL2(nblocks) - 1; - nblocks = 1 << l2nb; + nblocks = 1LL << l2nb; } else { /* Trim any already allocated blocks */ jfs_error(bmp->db_ipbmap->i_sb, "-EIO\n"); @@ -1760,7 +1798,7 @@ static int dbFindCtl(struct bmap * bmp, int l2nb, int level, s64 * blkno) * dbFindLeaf() returns the index of the leaf at which * free space was found. */ - rc = dbFindLeaf((dmtree_t *) dcp, l2nb, &leafidx); + rc = dbFindLeaf((dmtree_t *) dcp, l2nb, &leafidx, true); /* release the buffer. */ @@ -2007,9 +2045,12 @@ dbAllocDmapLev(struct bmap * bmp, * free space. if sufficient free space is found, dbFindLeaf() * returns the index of the leaf at which free space was found. */ - if (dbFindLeaf((dmtree_t *) & dp->tree, l2nb, &leafidx)) + if (dbFindLeaf((dmtree_t *) &dp->tree, l2nb, &leafidx, false)) return -ENOSPC; + if (leafidx < 0) + return -EIO; + /* determine the block number within the file system corresponding * to the leaf at which free space was found. */ @@ -2964,14 +3005,18 @@ static void dbAdjTree(dmtree_t * tp, int leafno, int newval) * leafidx - return pointer to be set to the index of the leaf * describing at least l2nb free blocks if sufficient * free blocks are found. + * is_ctl - determines if the tree is of type ctl * * RETURN VALUES: * 0 - success * -ENOSPC - insufficient free blocks. */ -static int dbFindLeaf(dmtree_t * tp, int l2nb, int *leafidx) +static int dbFindLeaf(dmtree_t *tp, int l2nb, int *leafidx, bool is_ctl) { int ti, n = 0, k, x = 0; + int max_size; + + max_size = is_ctl ? CTLTREESIZE : TREESIZE; /* first check the root of the tree to see if there is * sufficient free space. @@ -2992,6 +3037,8 @@ static int dbFindLeaf(dmtree_t * tp, int l2nb, int *leafidx) /* sufficient free space found. move to the next * level (or quit if this is the last level). */ + if (x + n > max_size) + return -ENOSPC; if (l2nb <= tp->dmt_stree[x + n]) break; } diff --git a/fs/jfs/jfs_dmap.h b/fs/jfs/jfs_dmap.h index 562b9a7e4311..f502a15c6c98 100644 --- a/fs/jfs/jfs_dmap.h +++ b/fs/jfs/jfs_dmap.h @@ -196,7 +196,7 @@ typedef union dmtree { #define dmt_leafidx t1.leafidx #define dmt_height t1.height #define dmt_budmin t1.budmin -#define dmt_stree t1.stree +#define dmt_stree t2.stree /* * on-disk aggregate disk allocation map descriptor. diff --git a/fs/jfs/jfs_extent.c b/fs/jfs/jfs_extent.c index 2ae7d59ab10a..c971e8a6525d 100644 --- a/fs/jfs/jfs_extent.c +++ b/fs/jfs/jfs_extent.c @@ -521,6 +521,11 @@ extBalloc(struct inode *ip, s64 hint, s64 * nblocks, s64 * blkno) * blocks in the map. in that case, we'll start off with the * maximum free. */ + + /* give up if no space left */ + if (bmp->db_maxfreebud == -1) + return -ENOSPC; + max = (s64) 1 << bmp->db_maxfreebud; if (*nblocks >= max && *nblocks > nbperpage) nb = nblks = (max > nbperpage) ? max : nbperpage; diff --git a/fs/jfs/jfs_filsys.h b/fs/jfs/jfs_filsys.h index b67d64671bb4..0c36ce6318d5 100644 --- a/fs/jfs/jfs_filsys.h +++ b/fs/jfs/jfs_filsys.h @@ -135,7 +135,9 @@ #define NUM_INODE_PER_IAG INOSPERIAG #define MINBLOCKSIZE 512 +#define L2MINBLOCKSIZE 9 #define MAXBLOCKSIZE 4096 +#define L2MAXBLOCKSIZE 12 #define MAXFILESIZE ((s64)1 << 52) #define JFS_LINK_MAX 0xffffffff @@ -281,5 +283,6 @@ * fsck() must be run to repair */ #define FM_EXTENDFS 0x00000008 /* file system extendfs() in progress */ +#define FM_STATE_MAX 0x0000000f /* max value of s_state */ #endif /* _H_JFS_FILSYS */ diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c index 93e8c590ff5c..b45cc109e506 100644 --- a/fs/jfs/jfs_imap.c +++ b/fs/jfs/jfs_imap.c @@ -208,6 +208,7 @@ int diUnmount(struct inode *ipimap, int mounterror) * free in-memory control structure */ kfree(imap); + JFS_IP(ipimap)->i_imap = NULL; return (0); } @@ -1334,7 +1335,7 @@ diInitInode(struct inode *ip, int iagno, int ino, int extno, struct iag * iagp) int diAlloc(struct inode *pip, bool dir, struct inode *ip) { int rc, ino, iagno, addext, extno, bitno, sword; - int nwords, rem, i, agno; + int nwords, rem, i, agno, dn_numag; u32 mask, inosmap, extsmap; struct inode *ipimap; struct metapage *mp; @@ -1370,6 +1371,9 @@ int diAlloc(struct inode *pip, bool dir, struct inode *ip) /* get the ag number of this iag */ agno = BLKTOAG(JFS_IP(pip)->agstart, JFS_SBI(pip->i_sb)); + dn_numag = JFS_SBI(pip->i_sb)->bmap->db_numag; + if (agno < 0 || agno > dn_numag) + return -EIO; if (atomic_read(&JFS_SBI(pip->i_sb)->bmap->db_active[agno])) { /* diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c index 6b68df395892..356d1fcf7119 100644 --- a/fs/jfs/jfs_logmgr.c +++ b/fs/jfs/jfs_logmgr.c @@ -1338,6 +1338,7 @@ int lmLogInit(struct jfs_log * log) } else { if (memcmp(logsuper->uuid, log->uuid, 16)) { jfs_warn("wrong uuid on JFS log device"); + rc = -EINVAL; goto errout20; } log->size = le32_to_cpu(logsuper->size); diff --git a/fs/jfs/jfs_mount.c b/fs/jfs/jfs_mount.c index d8658607bf46..f1a705d15904 100644 --- a/fs/jfs/jfs_mount.c +++ b/fs/jfs/jfs_mount.c @@ -49,6 +49,7 @@ #include <linux/fs.h> #include <linux/buffer_head.h> +#include <linux/log2.h> #include "jfs_incore.h" #include "jfs_filsys.h" @@ -92,14 +93,14 @@ int jfs_mount(struct super_block *sb) * (initialize mount inode from the superblock) */ if ((rc = chkSuper(sb))) { - goto errout20; + goto out; } ipaimap = diReadSpecial(sb, AGGREGATE_I, 0); if (ipaimap == NULL) { jfs_err("jfs_mount: Failed to read AGGREGATE_I"); rc = -EIO; - goto errout20; + goto out; } sbi->ipaimap = ipaimap; @@ -110,7 +111,7 @@ int jfs_mount(struct super_block *sb) */ if ((rc = diMount(ipaimap))) { jfs_err("jfs_mount: diMount(ipaimap) failed w/rc = %d", rc); - goto errout21; + goto err_ipaimap; } /* @@ -119,7 +120,7 @@ int jfs_mount(struct super_block *sb) ipbmap = diReadSpecial(sb, BMAP_I, 0); if (ipbmap == NULL) { rc = -EIO; - goto errout22; + goto err_umount_ipaimap; } jfs_info("jfs_mount: ipbmap:0x%p", ipbmap); @@ -131,7 +132,7 @@ int jfs_mount(struct super_block *sb) */ if ((rc = dbMount(ipbmap))) { jfs_err("jfs_mount: dbMount failed w/rc = %d", rc); - goto errout22; + goto err_ipbmap; } /* @@ -150,7 +151,7 @@ int jfs_mount(struct super_block *sb) if (!ipaimap2) { jfs_err("jfs_mount: Failed to read AGGREGATE_I"); rc = -EIO; - goto errout35; + goto err_umount_ipbmap; } sbi->ipaimap2 = ipaimap2; @@ -162,7 +163,7 @@ int jfs_mount(struct super_block *sb) if ((rc = diMount(ipaimap2))) { jfs_err("jfs_mount: diMount(ipaimap2) failed, rc = %d", rc); - goto errout35; + goto err_ipaimap2; } } else /* Secondary aggregate inode table is not valid */ @@ -179,7 +180,7 @@ int jfs_mount(struct super_block *sb) jfs_err("jfs_mount: Failed to read FILESYSTEM_I"); /* open fileset secondary inode allocation map */ rc = -EIO; - goto errout40; + goto err_umount_ipaimap2; } jfs_info("jfs_mount: ipimap:0x%p", ipimap); @@ -189,41 +190,34 @@ int jfs_mount(struct super_block *sb) /* initialize fileset inode allocation map */ if ((rc = diMount(ipimap))) { jfs_err("jfs_mount: diMount failed w/rc = %d", rc); - goto errout41; + goto err_ipimap; } - goto out; + return rc; /* * unwind on error */ - errout41: /* close fileset inode allocation map inode */ +err_ipimap: + /* close fileset inode allocation map inode */ diFreeSpecial(ipimap); - - errout40: /* fileset closed */ - +err_umount_ipaimap2: /* close secondary aggregate inode allocation map */ - if (ipaimap2) { + if (ipaimap2) diUnmount(ipaimap2, 1); +err_ipaimap2: + /* close aggregate inodes */ + if (ipaimap2) diFreeSpecial(ipaimap2); - } - - errout35: - - /* close aggregate block allocation map */ +err_umount_ipbmap: /* close aggregate block allocation map */ dbUnmount(ipbmap, 1); +err_ipbmap: /* close aggregate inodes */ diFreeSpecial(ipbmap); - - errout22: /* close aggregate inode allocation map */ - +err_umount_ipaimap: /* close aggregate inode allocation map */ diUnmount(ipaimap, 1); - - errout21: /* close aggregate inodes */ +err_ipaimap: /* close aggregate inodes */ diFreeSpecial(ipaimap); - errout20: /* aggregate closed */ - - out: - +out: if (rc) jfs_err("Mount JFS Failure: %d", rc); @@ -378,6 +372,15 @@ static int chkSuper(struct super_block *sb) sbi->bsize = bsize; sbi->l2bsize = le16_to_cpu(j_sb->s_l2bsize); + /* check some fields for possible corruption */ + if (sbi->l2bsize != ilog2((u32)bsize) || + j_sb->pad != 0 || + le32_to_cpu(j_sb->s_state) > FM_STATE_MAX) { + rc = -EINVAL; + jfs_err("jfs_mount: Mount Failure: superblock is corrupt!"); + goto out; + } + /* * For now, ignore s_pbsize, l2bfactor. All I/O going through buffer * cache. diff --git a/fs/jfs/jfs_txnmgr.c b/fs/jfs/jfs_txnmgr.c index 78789c5ed36b..e10db01f253b 100644 --- a/fs/jfs/jfs_txnmgr.c +++ b/fs/jfs/jfs_txnmgr.c @@ -367,6 +367,11 @@ tid_t txBegin(struct super_block *sb, int flag) jfs_info("txBegin: flag = 0x%x", flag); log = JFS_SBI(sb)->log; + if (!log) { + jfs_error(sb, "read-only filesystem\n"); + return 0; + } + TXN_LOCK(); INCREMENT(TxStat.txBegin); diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c index 14528c0ffe63..c2c439acbb78 100644 --- a/fs/jfs/namei.c +++ b/fs/jfs/namei.c @@ -811,6 +811,11 @@ static int jfs_link(struct dentry *old_dentry, if (rc) goto out; + if (isReadOnly(ip)) { + jfs_error(ip->i_sb, "read-only filesystem\n"); + return -EROFS; + } + tid = txBegin(ip->i_sb, 0); mutex_lock_nested(&JFS_IP(dir)->commit_mutex, COMMIT_MUTEX_PARENT); diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index a4a538abcaf9..5a4e3aa8baf7 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -20,7 +20,15 @@ DEFINE_MUTEX(kernfs_mutex); static DEFINE_SPINLOCK(kernfs_rename_lock); /* kn->parent and ->name */ -static char kernfs_pr_cont_buf[PATH_MAX]; /* protected by rename_lock */ +/* + * Don't use rename_lock to piggy back on pr_cont_buf. We don't want to + * call pr_cont() while holding rename_lock. Because sometimes pr_cont() + * will perform wakeups when releasing console_sem. Holding rename_lock + * will introduce deadlock if the scheduler reads the kernfs_name in the + * wakeup path. + */ +static DEFINE_SPINLOCK(kernfs_pr_cont_lock); +static char kernfs_pr_cont_buf[PATH_MAX]; /* protected by pr_cont_lock */ static DEFINE_SPINLOCK(kernfs_idr_lock); /* root->ino_idr */ #define rb_to_kn(X) rb_entry((X), struct kernfs_node, rb) @@ -229,12 +237,12 @@ void pr_cont_kernfs_name(struct kernfs_node *kn) { unsigned long flags; - spin_lock_irqsave(&kernfs_rename_lock, flags); + spin_lock_irqsave(&kernfs_pr_cont_lock, flags); - kernfs_name_locked(kn, kernfs_pr_cont_buf, sizeof(kernfs_pr_cont_buf)); + kernfs_name(kn, kernfs_pr_cont_buf, sizeof(kernfs_pr_cont_buf)); pr_cont("%s", kernfs_pr_cont_buf); - spin_unlock_irqrestore(&kernfs_rename_lock, flags); + spin_unlock_irqrestore(&kernfs_pr_cont_lock, flags); } /** @@ -248,10 +256,10 @@ void pr_cont_kernfs_path(struct kernfs_node *kn) unsigned long flags; int sz; - spin_lock_irqsave(&kernfs_rename_lock, flags); + spin_lock_irqsave(&kernfs_pr_cont_lock, flags); - sz = kernfs_path_from_node_locked(kn, NULL, kernfs_pr_cont_buf, - sizeof(kernfs_pr_cont_buf)); + sz = kernfs_path_from_node(kn, NULL, kernfs_pr_cont_buf, + sizeof(kernfs_pr_cont_buf)); if (sz < 0) { pr_cont("(error)"); goto out; @@ -265,7 +273,7 @@ void pr_cont_kernfs_path(struct kernfs_node *kn) pr_cont("%s", kernfs_pr_cont_buf); out: - spin_unlock_irqrestore(&kernfs_rename_lock, flags); + spin_unlock_irqrestore(&kernfs_pr_cont_lock, flags); } /** @@ -867,13 +875,12 @@ static struct kernfs_node *kernfs_walk_ns(struct kernfs_node *parent, lockdep_assert_held(&kernfs_mutex); - /* grab kernfs_rename_lock to piggy back on kernfs_pr_cont_buf */ - spin_lock_irq(&kernfs_rename_lock); + spin_lock_irq(&kernfs_pr_cont_lock); len = strlcpy(kernfs_pr_cont_buf, path, sizeof(kernfs_pr_cont_buf)); if (len >= sizeof(kernfs_pr_cont_buf)) { - spin_unlock_irq(&kernfs_rename_lock); + spin_unlock_irq(&kernfs_pr_cont_lock); return NULL; } @@ -885,7 +892,7 @@ static struct kernfs_node *kernfs_walk_ns(struct kernfs_node *parent, parent = kernfs_find_ns(parent, name, ns); } - spin_unlock_irq(&kernfs_rename_lock); + spin_unlock_irq(&kernfs_pr_cont_lock); return parent; } @@ -1506,8 +1513,11 @@ int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name, mutex_lock(&kernfs_mutex); kn = kernfs_find_ns(parent, name, ns); - if (kn) + if (kn) { + kernfs_get(kn); __kernfs_remove(kn); + kernfs_put(kn); + } mutex_unlock(&kernfs_mutex); diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c index 0b22c39dad47..b2a126a947e3 100644 --- a/fs/kernfs/mount.c +++ b/fs/kernfs/mount.c @@ -212,7 +212,7 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn, dput(dentry); return ERR_PTR(-EINVAL); } - dtmp = lookup_one_len_unlocked(kntmp->name, dentry, + dtmp = lookup_positive_unlocked(kntmp->name, dentry, strlen(kntmp->name)); dput(dentry); if (IS_ERR(dtmp)) diff --git a/fs/libfs.c b/fs/libfs.c index 02158618f4c9..fd5f6c106059 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -864,11 +864,11 @@ out: EXPORT_SYMBOL_GPL(simple_attr_read); /* interpret the buffer as a number to call the set function with */ -ssize_t simple_attr_write(struct file *file, const char __user *buf, - size_t len, loff_t *ppos) +static ssize_t simple_attr_write_xsigned(struct file *file, const char __user *buf, + size_t len, loff_t *ppos, bool is_signed) { struct simple_attr *attr; - u64 val; + unsigned long long val; size_t size; ssize_t ret; @@ -886,7 +886,12 @@ ssize_t simple_attr_write(struct file *file, const char __user *buf, goto out; attr->set_buf[size] = '\0'; - val = simple_strtoll(attr->set_buf, NULL, 0); + if (is_signed) + ret = kstrtoll(attr->set_buf, 0, &val); + else + ret = kstrtoull(attr->set_buf, 0, &val); + if (ret) + goto out; ret = attr->set(attr->data, val); if (ret == 0) ret = len; /* on success, claim we got the whole input */ @@ -894,8 +899,21 @@ out: mutex_unlock(&attr->mutex); return ret; } + +ssize_t simple_attr_write(struct file *file, const char __user *buf, + size_t len, loff_t *ppos) +{ + return simple_attr_write_xsigned(file, buf, len, ppos, false); +} EXPORT_SYMBOL_GPL(simple_attr_write); +ssize_t simple_attr_write_signed(struct file *file, const char __user *buf, + size_t len, loff_t *ppos) +{ + return simple_attr_write_xsigned(file, buf, len, ppos, true); +} +EXPORT_SYMBOL_GPL(simple_attr_write_signed); + /** * generic_fh_to_dentry - generic helper for the fh_to_dentry export operation * @sb: filesystem to do the file handle conversion on diff --git a/fs/lockd/host.c b/fs/lockd/host.c index f0b5c987d6ae..3f6ba0cd2bd9 100644 --- a/fs/lockd/host.c +++ b/fs/lockd/host.c @@ -432,12 +432,7 @@ nlm_bind_host(struct nlm_host *host) * RPC rebind is required */ if ((clnt = host->h_rpcclnt) != NULL) { - if (time_after_eq(jiffies, host->h_nextrebind)) { - rpc_force_rebind(clnt); - host->h_nextrebind = jiffies + NLM_HOST_REBIND; - dprintk("lockd: next rebind in %lu jiffies\n", - host->h_nextrebind - jiffies); - } + nlm_rebind_host(host); } else { unsigned long increment = nlmsvc_timeout; struct rpc_timeout timeparms = { @@ -485,13 +480,20 @@ nlm_bind_host(struct nlm_host *host) return clnt; } -/* - * Force a portmap lookup of the remote lockd port +/** + * nlm_rebind_host - If needed, force a portmap lookup of the peer's lockd port + * @host: NLM host handle for peer + * + * This is not needed when using a connection-oriented protocol, such as TCP. + * The existing autobind mechanism is sufficient to force a rebind when + * required, e.g. on connection state transitions. */ void nlm_rebind_host(struct nlm_host *host) { - dprintk("lockd: rebind host %s\n", host->h_name); + if (host->h_proto != IPPROTO_UDP) + return; + if (host->h_rpcclnt && time_after_eq(jiffies, host->h_nextrebind)) { rpc_force_rebind(host->h_rpcclnt); host->h_nextrebind = jiffies + NLM_HOST_REBIND; diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c index 654594ef4f94..68a2eac548c3 100644 --- a/fs/lockd/mon.c +++ b/fs/lockd/mon.c @@ -275,6 +275,9 @@ static struct nsm_handle *nsm_create_handle(const struct sockaddr *sap, { struct nsm_handle *new; + if (!hostname) + return NULL; + new = kzalloc(sizeof(*new) + hostname_len + 1, GFP_KERNEL); if (unlikely(new == NULL)) return NULL; diff --git a/fs/mbcache.c b/fs/mbcache.c index 081ccf0caee3..2e2d4de4cf87 100644 --- a/fs/mbcache.c +++ b/fs/mbcache.c @@ -10,7 +10,7 @@ /* * Mbcache is a simple key-value store. Keys need not be unique, however * key-value pairs are expected to be unique (we use this fact in - * mb_cache_entry_delete()). + * mb_cache_entry_delete_or_get()). * * Ext2 and ext4 use this cache for deduplication of extended attribute blocks. * Ext4 also uses it for deduplication of xattr values stored in inodes. @@ -89,12 +89,19 @@ int mb_cache_entry_create(struct mb_cache *cache, gfp_t mask, u32 key, return -ENOMEM; INIT_LIST_HEAD(&entry->e_list); - /* One ref for hash, one ref returned */ - atomic_set(&entry->e_refcnt, 1); + /* + * We create entry with two references. One reference is kept by the + * hash table, the other reference is used to protect us from + * mb_cache_entry_delete_or_get() until the entry is fully setup. This + * avoids nesting of cache->c_list_lock into hash table bit locks which + * is problematic for RT. + */ + atomic_set(&entry->e_refcnt, 2); entry->e_key = key; entry->e_value = value; - entry->e_reusable = reusable; - entry->e_referenced = 0; + entry->e_flags = 0; + if (reusable) + set_bit(MBE_REUSABLE_B, &entry->e_flags); head = mb_cache_entry_head(cache, key); hlist_bl_lock(head); hlist_bl_for_each_entry(dup, dup_node, head, e_hash_list) { @@ -106,24 +113,41 @@ int mb_cache_entry_create(struct mb_cache *cache, gfp_t mask, u32 key, } hlist_bl_add_head(&entry->e_hash_list, head); hlist_bl_unlock(head); - spin_lock(&cache->c_list_lock); list_add_tail(&entry->e_list, &cache->c_list); - /* Grab ref for LRU list */ - atomic_inc(&entry->e_refcnt); cache->c_entry_count++; spin_unlock(&cache->c_list_lock); + mb_cache_entry_put(cache, entry); return 0; } EXPORT_SYMBOL(mb_cache_entry_create); -void __mb_cache_entry_free(struct mb_cache_entry *entry) +void __mb_cache_entry_free(struct mb_cache *cache, struct mb_cache_entry *entry) { + struct hlist_bl_head *head; + + head = mb_cache_entry_head(cache, entry->e_key); + hlist_bl_lock(head); + hlist_bl_del(&entry->e_hash_list); + hlist_bl_unlock(head); kmem_cache_free(mb_entry_cache, entry); } EXPORT_SYMBOL(__mb_cache_entry_free); +/* + * mb_cache_entry_wait_unused - wait to be the last user of the entry + * + * @entry - entry to work on + * + * Wait to be the last user of the entry. + */ +void mb_cache_entry_wait_unused(struct mb_cache_entry *entry) +{ + wait_var_event(&entry->e_refcnt, atomic_read(&entry->e_refcnt) <= 2); +} +EXPORT_SYMBOL(mb_cache_entry_wait_unused); + static struct mb_cache_entry *__entry_find(struct mb_cache *cache, struct mb_cache_entry *entry, u32 key) @@ -141,10 +165,10 @@ static struct mb_cache_entry *__entry_find(struct mb_cache *cache, while (node) { entry = hlist_bl_entry(node, struct mb_cache_entry, e_hash_list); - if (entry->e_key == key && entry->e_reusable) { - atomic_inc(&entry->e_refcnt); + if (entry->e_key == key && + test_bit(MBE_REUSABLE_B, &entry->e_flags) && + atomic_inc_not_zero(&entry->e_refcnt)) goto out; - } node = node->next; } entry = NULL; @@ -204,10 +228,9 @@ struct mb_cache_entry *mb_cache_entry_get(struct mb_cache *cache, u32 key, head = mb_cache_entry_head(cache, key); hlist_bl_lock(head); hlist_bl_for_each_entry(entry, node, head, e_hash_list) { - if (entry->e_key == key && entry->e_value == value) { - atomic_inc(&entry->e_refcnt); + if (entry->e_key == key && entry->e_value == value && + atomic_inc_not_zero(&entry->e_refcnt)) goto out; - } } entry = NULL; out: @@ -216,7 +239,7 @@ out: } EXPORT_SYMBOL(mb_cache_entry_get); -/* mb_cache_entry_delete - remove a cache entry +/* mb_cache_entry_delete - try to remove a cache entry * @cache - cache we work with * @key - key * @value - value @@ -253,6 +276,43 @@ void mb_cache_entry_delete(struct mb_cache *cache, u32 key, u64 value) } EXPORT_SYMBOL(mb_cache_entry_delete); +/* mb_cache_entry_delete_or_get - remove a cache entry if it has no users + * @cache - cache we work with + * @key - key + * @value - value + * + * Remove entry from cache @cache with key @key and value @value. The removal + * happens only if the entry is unused. The function returns NULL in case the + * entry was successfully removed or there's no entry in cache. Otherwise the + * function grabs reference of the entry that we failed to delete because it + * still has users and return it. + */ +struct mb_cache_entry *mb_cache_entry_delete_or_get(struct mb_cache *cache, + u32 key, u64 value) +{ + struct mb_cache_entry *entry; + + entry = mb_cache_entry_get(cache, key, value); + if (!entry) + return NULL; + + /* + * Drop the ref we got from mb_cache_entry_get() and the initial hash + * ref if we are the last user + */ + if (atomic_cmpxchg(&entry->e_refcnt, 2, 0) != 2) + return entry; + + spin_lock(&cache->c_list_lock); + if (!list_empty(&entry->e_list)) + list_del_init(&entry->e_list); + cache->c_entry_count--; + spin_unlock(&cache->c_list_lock); + __mb_cache_entry_free(cache, entry); + return NULL; +} +EXPORT_SYMBOL(mb_cache_entry_delete_or_get); + /* mb_cache_entry_touch - cache entry got used * @cache - cache the entry belongs to * @entry - entry that got used @@ -262,7 +322,7 @@ EXPORT_SYMBOL(mb_cache_entry_delete); void mb_cache_entry_touch(struct mb_cache *cache, struct mb_cache_entry *entry) { - entry->e_referenced = 1; + set_bit(MBE_REFERENCED_B, &entry->e_flags); } EXPORT_SYMBOL(mb_cache_entry_touch); @@ -280,34 +340,24 @@ static unsigned long mb_cache_shrink(struct mb_cache *cache, unsigned long nr_to_scan) { struct mb_cache_entry *entry; - struct hlist_bl_head *head; unsigned long shrunk = 0; spin_lock(&cache->c_list_lock); while (nr_to_scan-- && !list_empty(&cache->c_list)) { entry = list_first_entry(&cache->c_list, struct mb_cache_entry, e_list); - if (entry->e_referenced) { - entry->e_referenced = 0; + /* Drop initial hash reference if there is no user */ + if (test_bit(MBE_REFERENCED_B, &entry->e_flags) || + atomic_cmpxchg(&entry->e_refcnt, 1, 0) != 1) { + clear_bit(MBE_REFERENCED_B, &entry->e_flags); list_move_tail(&entry->e_list, &cache->c_list); continue; } list_del_init(&entry->e_list); cache->c_entry_count--; - /* - * We keep LRU list reference so that entry doesn't go away - * from under us. - */ spin_unlock(&cache->c_list_lock); - head = mb_cache_entry_head(cache, entry->e_key); - hlist_bl_lock(head); - if (!hlist_bl_unhashed(&entry->e_hash_list)) { - hlist_bl_del_init(&entry->e_hash_list); - atomic_dec(&entry->e_refcnt); - } - hlist_bl_unlock(head); - if (mb_cache_entry_put(cache, entry)) - shrunk++; + __mb_cache_entry_free(cache, entry); + shrunk++; cond_resched(); spin_lock(&cache->c_list_lock); } @@ -399,11 +449,6 @@ void mb_cache_destroy(struct mb_cache *cache) * point. */ list_for_each_entry_safe(entry, next, &cache->c_list, e_list) { - if (!hlist_bl_unhashed(&entry->e_hash_list)) { - hlist_bl_del_init(&entry->e_hash_list); - atomic_dec(&entry->e_refcnt); - } else - WARN_ON(1); list_del(&entry->e_list); WARN_ON(atomic_read(&entry->e_refcnt) != 1); mb_cache_entry_put(cache, entry); diff --git a/fs/minix/inode.c b/fs/minix/inode.c index 03fe8bac36cf..3ce91ad1ee1b 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -450,7 +450,8 @@ static const struct address_space_operations minix_aops = { .writepage = minix_writepage, .write_begin = minix_write_begin, .write_end = generic_write_end, - .bmap = minix_bmap + .bmap = minix_bmap, + .direct_IO = noop_direct_IO }; static const struct inode_operations minix_symlink_inode_operations = { diff --git a/fs/namei.c b/fs/namei.c index 327844fedf3d..60b57e0bc174 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2575,6 +2575,26 @@ struct dentry *lookup_one_len_unlocked(const char *name, } EXPORT_SYMBOL(lookup_one_len_unlocked); +/* + * Like lookup_one_len_unlocked(), except that it yields ERR_PTR(-ENOENT) + * on negatives. Returns known positive or ERR_PTR(); that's what + * most of the users want. Note that pinned negative with unlocked parent + * _can_ become positive at any time, so callers of lookup_one_len_unlocked() + * need to be very careful; pinned positives have ->d_inode stable, so + * this one avoids such problems. + */ +struct dentry *lookup_positive_unlocked(const char *name, + struct dentry *base, int len) +{ + struct dentry *ret = lookup_one_len_unlocked(name, base, len); + if (!IS_ERR(ret) && d_is_negative(ret)) { + dput(ret); + ret = ERR_PTR(-ENOENT); + } + return ret; +} +EXPORT_SYMBOL(lookup_positive_unlocked); + #ifdef CONFIG_UNIX98_PTYS int path_pts(struct path *path) { @@ -2593,7 +2613,7 @@ int path_pts(struct path *path) this.name = "pts"; this.len = 3; child = d_hash_and_lookup(parent, &this); - if (!child) + if (IS_ERR_OR_NULL(child)) return -ENOENT; path->dentry = child; @@ -3453,6 +3473,8 @@ struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode, int open_flag) child = d_alloc(dentry, &slash_name); if (unlikely(!child)) goto out_err; + if (!IS_POSIXACL(dir)) + mode &= ~current_umask(); error = dir->i_op->tmpfile(dir, child, mode); if (error) goto out_err; @@ -4824,7 +4846,7 @@ int __page_symlink(struct inode *inode, const char *symname, int len, int nofs) { struct address_space *mapping = inode->i_mapping; struct page *page; - void *fsdata; + void *fsdata = NULL; int err; unsigned int flags = 0; if (nofs) diff --git a/fs/namespace.c b/fs/namespace.c index 741f40cd955e..396ff1bcfdad 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1610,13 +1610,22 @@ static inline bool may_mount(void) return ns_capable(current->nsproxy->mnt_ns->user_ns, CAP_SYS_ADMIN); } +#ifdef CONFIG_MANDATORY_FILE_LOCKING +static bool may_mandlock(void) +{ + pr_warn_once("======================================================\n" + "WARNING: the mand mount option is being deprecated and\n" + " will be removed in v5.15!\n" + "======================================================\n"); + return capable(CAP_SYS_ADMIN); +} +#else static inline bool may_mandlock(void) { -#ifndef CONFIG_MANDATORY_FILE_LOCKING + pr_warn("VFS: \"mand\" mount option not supported"); return false; -#endif - return capable(CAP_SYS_ADMIN); } +#endif /* * Now umount can handle mount points as well as block devices. @@ -1799,6 +1808,20 @@ void drop_collected_mounts(struct vfsmount *mnt) namespace_unlock(); } +static bool has_locked_children(struct mount *mnt, struct dentry *dentry) +{ + struct mount *child; + + list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) { + if (!is_subdir(child->mnt_mountpoint, dentry)) + continue; + + if (child->mnt.mnt_flags & MNT_LOCKED) + return true; + } + return false; +} + /** * clone_private_mount - create a private clone of a path * @@ -1813,14 +1836,27 @@ struct vfsmount *clone_private_mount(const struct path *path) struct mount *old_mnt = real_mount(path->mnt); struct mount *new_mnt; + down_read(&namespace_sem); if (IS_MNT_UNBINDABLE(old_mnt)) - return ERR_PTR(-EINVAL); + goto invalid; + + if (!check_mnt(old_mnt)) + goto invalid; + + if (has_locked_children(old_mnt, path->dentry)) + goto invalid; new_mnt = clone_mnt(old_mnt, path->dentry, CL_PRIVATE); + up_read(&namespace_sem); + if (IS_ERR(new_mnt)) return ERR_CAST(new_mnt); return &new_mnt->mnt; + +invalid: + up_read(&namespace_sem); + return ERR_PTR(-EINVAL); } EXPORT_SYMBOL_GPL(clone_private_mount); @@ -2136,19 +2172,6 @@ static int do_change_type(struct path *path, int ms_flags) return err; } -static bool has_locked_children(struct mount *mnt, struct dentry *dentry) -{ - struct mount *child; - list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) { - if (!is_subdir(child->mnt_mountpoint, dentry)) - continue; - - if (child->mnt.mnt_flags & MNT_LOCKED) - return true; - } - return false; -} - /* * do loopback mount. */ @@ -2467,9 +2490,12 @@ static int do_new_mount(struct path *path, const char *fstype, int sb_flags, return -ENODEV; mnt = vfs_kern_mount(type, sb_flags, name, data); - if (!IS_ERR(mnt) && (type->fs_flags & FS_HAS_SUBTYPE) && - !mnt->mnt_sb->s_subtype) - mnt = fs_set_subtype(mnt, fstype); + if (!IS_ERR(mnt) && (type->fs_flags & FS_HAS_SUBTYPE)) { + down_write(&mnt->mnt_sb->s_umount); + if (!mnt->mnt_sb->s_subtype) + mnt = fs_set_subtype(mnt, fstype); + up_write(&mnt->mnt_sb->s_umount); + } put_filesystem(type); if (IS_ERR(mnt)) diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index 7ccc30a757ec..c66916d77b4a 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -140,7 +140,7 @@ config PNFS_BLOCK config PNFS_FLEXFILE_LAYOUT tristate depends on NFS_V4_1 && NFS_V3 - default m + default NFS_V4 config NFS_V4_1_IMPLEMENTATION_ID_DOMAIN string "NFSv4.1 Implementation ID Domain" diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index 06cb0c1d9aee..a2bca78b80ab 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -604,6 +604,8 @@ retry: nfs4_delete_deviceid(node->ld, node->nfs_client, id); goto retry; } + + nfs4_put_deviceid_node(node); return ERR_PTR(-ENODEV); } diff --git a/fs/nfs/blocklayout/dev.c b/fs/nfs/blocklayout/dev.c index dec5880ac6de..6e3a14fdff9c 100644 --- a/fs/nfs/blocklayout/dev.c +++ b/fs/nfs/blocklayout/dev.c @@ -422,7 +422,7 @@ bl_parse_concat(struct nfs_server *server, struct pnfs_block_dev *d, int ret, i; d->children = kcalloc(v->concat.volumes_count, - sizeof(struct pnfs_block_dev), GFP_KERNEL); + sizeof(struct pnfs_block_dev), gfp_mask); if (!d->children) return -ENOMEM; @@ -451,7 +451,7 @@ bl_parse_stripe(struct nfs_server *server, struct pnfs_block_dev *d, int ret, i; d->children = kcalloc(v->stripe.volumes_count, - sizeof(struct pnfs_block_dev), GFP_KERNEL); + sizeof(struct pnfs_block_dev), gfp_mask); if (!d->children) return -ENOMEM; diff --git a/fs/nfs/callback.h b/fs/nfs/callback.h index 8f34daf85f70..5d5227ce4d91 100644 --- a/fs/nfs/callback.h +++ b/fs/nfs/callback.h @@ -168,7 +168,7 @@ struct cb_devicenotifyitem { }; struct cb_devicenotifyargs { - int ndevs; + uint32_t ndevs; struct cb_devicenotifyitem *devs; }; diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c index bcc51f131a49..f2a854805f0e 100644 --- a/fs/nfs/callback_proc.c +++ b/fs/nfs/callback_proc.c @@ -364,12 +364,11 @@ __be32 nfs4_callback_devicenotify(void *argp, void *resp, struct cb_process_state *cps) { struct cb_devicenotifyargs *args = argp; - int i; + const struct pnfs_layoutdriver_type *ld = NULL; + uint32_t i; __be32 res = 0; - struct nfs_client *clp = cps->clp; - struct nfs_server *server = NULL; - if (!clp) { + if (!cps->clp) { res = cpu_to_be32(NFS4ERR_OP_NOT_IN_SESSION); goto out; } @@ -377,23 +376,15 @@ __be32 nfs4_callback_devicenotify(void *argp, void *resp, for (i = 0; i < args->ndevs; i++) { struct cb_devicenotifyitem *dev = &args->devs[i]; - if (!server || - server->pnfs_curr_ld->id != dev->cbd_layout_type) { - rcu_read_lock(); - list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) - if (server->pnfs_curr_ld && - server->pnfs_curr_ld->id == dev->cbd_layout_type) { - rcu_read_unlock(); - goto found; - } - rcu_read_unlock(); - continue; + if (!ld || ld->id != dev->cbd_layout_type) { + pnfs_put_layoutdriver(ld); + ld = pnfs_find_layoutdriver(dev->cbd_layout_type); + if (!ld) + continue; } - - found: - nfs4_delete_deviceid(server->pnfs_curr_ld, clp, &dev->cbd_dev_id); + nfs4_delete_deviceid(ld, cps->clp, &dev->cbd_dev_id); } - + pnfs_put_layoutdriver(ld); out: kfree(args->devs); return res; diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index a87a56273407..2f84c612838c 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -268,11 +268,9 @@ __be32 decode_devicenotify_args(struct svc_rqst *rqstp, void *argp) { struct cb_devicenotifyargs *args = argp; + uint32_t tmp, n, i; __be32 *p; __be32 status = 0; - u32 tmp; - int n, i; - args->ndevs = 0; /* Num of device notifications */ p = read_buf(xdr, sizeof(uint32_t)); @@ -281,12 +279,8 @@ __be32 decode_devicenotify_args(struct svc_rqst *rqstp, goto out; } n = ntohl(*p++); - if (n <= 0) - goto out; - if (n > ULONG_MAX / sizeof(*args->devs)) { - status = htonl(NFS4ERR_BADXDR); + if (n == 0) goto out; - } args->devs = kmalloc_array(n, sizeof(*args->devs), GFP_KERNEL); if (!args->devs) { @@ -339,19 +333,21 @@ __be32 decode_devicenotify_args(struct svc_rqst *rqstp, dev->cbd_immediate = 0; } - args->ndevs++; - dprintk("%s: type %d layout 0x%x immediate %d\n", __func__, dev->cbd_notify_type, dev->cbd_layout_type, dev->cbd_immediate); } + args->ndevs = n; + dprintk("%s: ndevs %d\n", __func__, args->ndevs); + return 0; +err: + kfree(args->devs); out: + args->devs = NULL; + args->ndevs = 0; dprintk("%s: status %d ndevs %d\n", __func__, ntohl(status), args->ndevs); return status; -err: - kfree(args->devs); - goto out; } static __be32 decode_sessionid(struct xdr_stream *xdr, @@ -991,7 +987,7 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp) out_invalidcred: pr_warn_ratelimited("NFS: NFSv4 callback contains invalid cred\n"); - return rpc_autherr_badcred; + return svc_return_autherr(rqstp, rpc_autherr_badcred); } /* diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 8808d2ce6a9c..f3bfc4d8559e 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -180,6 +180,7 @@ struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init) INIT_LIST_HEAD(&clp->cl_superblocks); clp->cl_rpcclient = ERR_PTR(-EINVAL); + clp->cl_flags = cl_init->init_flags; clp->cl_proto = cl_init->proto; clp->cl_net = get_net(cl_init->net); @@ -410,7 +411,7 @@ struct nfs_client *nfs_get_client(const struct nfs_client_initdata *cl_init) if (cl_init->hostname == NULL) { WARN_ON(1); - return NULL; + return ERR_PTR(-EINVAL); } /* see if the client already exists */ @@ -430,7 +431,6 @@ struct nfs_client *nfs_get_client(const struct nfs_client_initdata *cl_init) list_add_tail(&new->cl_share_link, &nn->nfs_client_list); spin_unlock(&nn->nfs_client_lock); - new->cl_flags = cl_init->init_flags; return rpc_ops->init_client(new, cl_init); } diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 733fd9e4f0a1..10bc04af2882 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1626,6 +1626,24 @@ out: no_open: res = nfs_lookup(dir, dentry, lookup_flags); + if (!res) { + inode = d_inode(dentry); + if ((lookup_flags & LOOKUP_DIRECTORY) && inode && + !(S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))) + res = ERR_PTR(-ENOTDIR); + else if (inode && S_ISREG(inode->i_mode)) + res = ERR_PTR(-EOPENSTALE); + } else if (!IS_ERR(res)) { + inode = d_inode(res); + if ((lookup_flags & LOOKUP_DIRECTORY) && inode && + !(S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))) { + dput(res); + res = ERR_PTR(-ENOTDIR); + } else if (inode && S_ISREG(inode->i_mode)) { + dput(res); + res = ERR_PTR(-EOPENSTALE); + } + } if (switched) { d_lookup_done(dentry); if (!res) @@ -2015,6 +2033,8 @@ nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) trace_nfs_link_enter(inode, dir, dentry); d_drop(dentry); + if (S_ISREG(inode->i_mode)) + nfs_sync_inode(inode); error = NFS_PROTO(dir)->link(inode, dir, &dentry->d_name); if (error == 0) { ihold(inode); @@ -2103,6 +2123,8 @@ int nfs_rename(struct inode *old_dir, struct dentry *old_dentry, } } + if (S_ISREG(old_inode->i_mode)) + nfs_sync_inode(old_inode); task = nfs_async_rename(old_dir, new_dir, old_dentry, new_dentry, NULL); if (IS_ERR(task)) { error = PTR_ERR(task); diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index e5da9d7fb69e..6a4083d550c6 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -288,8 +288,8 @@ ssize_t nfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) VM_BUG_ON(iov_iter_count(iter) != PAGE_SIZE); if (iov_iter_rw(iter) == READ) - return nfs_file_direct_read(iocb, iter); - return nfs_file_direct_write(iocb, iter); + return nfs_file_direct_read(iocb, iter, true); + return nfs_file_direct_write(iocb, iter, true); } static void nfs_direct_release_pages(struct page **pages, unsigned int npages) @@ -553,6 +553,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq, * nfs_file_direct_read - file direct read operation for NFS files * @iocb: target I/O control block * @iter: vector of user buffers into which to read data + * @swap: flag indicating this is swap IO, not O_DIRECT IO * * We use this function for direct reads instead of calling * generic_file_aio_read() in order to avoid gfar's check to see if @@ -568,7 +569,8 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq, * client must read the updated atime from the server back into its * cache. */ -ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter) +ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter, + bool swap) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; @@ -610,12 +612,14 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter) if (iter_is_iovec(iter)) dreq->flags = NFS_ODIRECT_SHOULD_DIRTY; - nfs_start_io_direct(inode); + if (!swap) + nfs_start_io_direct(inode); NFS_I(inode)->read_io += count; requested = nfs_direct_read_schedule_iovec(dreq, iter, iocb->ki_pos); - nfs_end_io_direct(inode); + if (!swap) + nfs_end_io_direct(inode); if (requested > 0) { result = nfs_direct_wait(dreq); @@ -884,7 +888,7 @@ static const struct nfs_pgio_completion_ops nfs_direct_write_completion_ops = { */ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, struct iov_iter *iter, - loff_t pos) + loff_t pos, int ioflags) { struct nfs_pageio_descriptor desc; struct inode *inode = dreq->inode; @@ -892,7 +896,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, size_t requested_bytes = 0; size_t wsize = max_t(size_t, NFS_SERVER(inode)->wsize, PAGE_SIZE); - nfs_pageio_init_write(&desc, inode, FLUSH_COND_STABLE, false, + nfs_pageio_init_write(&desc, inode, ioflags, false, &nfs_direct_write_completion_ops); desc.pg_dreq = dreq; get_dreq(dreq); @@ -971,6 +975,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, * nfs_file_direct_write - file direct write operation for NFS files * @iocb: target I/O control block * @iter: vector of user buffers from which to write data + * @swap: flag indicating this is swap IO, not O_DIRECT IO * * We use this function for direct writes instead of calling * generic_file_aio_write() in order to avoid taking the inode @@ -987,7 +992,8 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, * Note that O_APPEND is not supported for NFS direct writes, as there * is no atomic O_APPEND write facility in the NFS protocol. */ -ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter) +ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter, + bool swap) { ssize_t result = -EINVAL, requested; size_t count; @@ -1001,7 +1007,11 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter) dfprintk(FILE, "NFS: direct write(%pD2, %zd@%Ld)\n", file, iov_iter_count(iter), (long long) iocb->ki_pos); - result = generic_write_checks(iocb, iter); + if (swap) + /* bypass generic checks */ + result = iov_iter_count(iter); + else + result = generic_write_checks(iocb, iter); if (result <= 0) return result; count = result; @@ -1031,16 +1041,22 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter) if (!is_sync_kiocb(iocb)) dreq->iocb = iocb; - nfs_start_io_direct(inode); + if (swap) { + requested = nfs_direct_write_schedule_iovec(dreq, iter, pos, + FLUSH_STABLE); + } else { + nfs_start_io_direct(inode); - requested = nfs_direct_write_schedule_iovec(dreq, iter, pos); + requested = nfs_direct_write_schedule_iovec(dreq, iter, pos, + FLUSH_COND_STABLE); - if (mapping->nrpages) { - invalidate_inode_pages2_range(mapping, - pos >> PAGE_SHIFT, end); - } + if (mapping->nrpages) { + invalidate_inode_pages2_range(mapping, + pos >> PAGE_SHIFT, end); + } - nfs_end_io_direct(inode); + nfs_end_io_direct(inode); + } if (requested > 0) { result = nfs_direct_wait(dreq); diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 29553fdba8af..62a86c414391 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -157,7 +157,7 @@ nfs_file_read(struct kiocb *iocb, struct iov_iter *to) ssize_t result; if (iocb->ki_flags & IOCB_DIRECT) - return nfs_file_direct_read(iocb, to); + return nfs_file_direct_read(iocb, to, false); dprintk("NFS: read(%pD2, %zu@%lu)\n", iocb->ki_filp, @@ -606,7 +606,7 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from) return result; if (iocb->ki_flags & IOCB_DIRECT) - return nfs_file_direct_write(iocb, from); + return nfs_file_direct_write(iocb, from, false); dprintk("NFS: write(%pD2, %zu@%Ld)\n", file, iov_iter_count(from), (long long) iocb->ki_pos); diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index 2478a69da0f0..015d39ac2c8f 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -717,7 +717,7 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo, if (unlikely(!p)) goto out_err; fl->fh_array[i]->size = be32_to_cpup(p++); - if (sizeof(struct nfs_fh) < fl->fh_array[i]->size) { + if (fl->fh_array[i]->size > NFS_MAXFHSIZE) { printk(KERN_ERR "NFS: Too big fh %d received %d\n", i, fl->fh_array[i]->size); goto out_err; @@ -837,6 +837,12 @@ filelayout_alloc_lseg(struct pnfs_layout_hdr *layoutid, return &fl->generic_hdr; } +static bool +filelayout_lseg_is_striped(const struct nfs4_filelayout_segment *flseg) +{ + return flseg->num_fh > 1; +} + /* * filelayout_pg_test(). Called by nfs_can_coalesce_requests() * @@ -857,6 +863,8 @@ filelayout_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, size = pnfs_generic_pg_test(pgio, prev, req); if (!size) return 0; + else if (!filelayout_lseg_is_striped(FILELAYOUT_LSEG(pgio->pg_lseg))) + return size; /* see if req and prev are in the same stripe */ if (prev) { diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index d8cba46a9395..bb10f2b21cc1 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -101,7 +101,7 @@ static int decode_nfs_fh(struct xdr_stream *xdr, struct nfs_fh *fh) if (unlikely(!p)) return -ENOBUFS; fh->size = be32_to_cpup(p++); - if (fh->size > sizeof(struct nfs_fh)) { + if (fh->size > NFS_MAXFHSIZE) { printk(KERN_ERR "NFS flexfiles: Too big fh received %d\n", fh->size); return -EOVERFLOW; @@ -1189,6 +1189,7 @@ static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg, case -EPFNOSUPPORT: case -EPROTONOSUPPORT: case -EOPNOTSUPP: + case -EINVAL: case -ECONNREFUSED: case -ECONNRESET: case -EHOSTDOWN: diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c index 8da239b6cc16..f1f0519f1ece 100644 --- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c +++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c @@ -429,10 +429,10 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx, goto out_fail; ds = mirror->mirror_ds->ds; + if (READ_ONCE(ds->ds_clp)) + goto out; /* matching smp_wmb() in _nfs4_pnfs_v3/4_ds_connect */ smp_rmb(); - if (ds->ds_clp) - goto out; /* FIXME: For now we assume the server sent only one version of NFS * to use for the DS. diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index e4cd3a2fe698..592b95ab378b 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -787,12 +787,9 @@ int nfs_getattr(const struct path *path, struct kstat *stat, goto out_no_update; /* Flush out writes to the server in order to update c/mtime. */ - if ((request_mask & (STATX_CTIME|STATX_MTIME)) && - S_ISREG(inode->i_mode)) { - err = filemap_write_and_wait(inode->i_mapping); - if (err) - goto out; - } + if ((request_mask & (STATX_CTIME | STATX_MTIME)) && + S_ISREG(inode->i_mode)) + filemap_write_and_wait(inode->i_mapping); /* * We may force a getattr if the user cares about atime. @@ -1038,6 +1035,7 @@ EXPORT_SYMBOL_GPL(nfs_inode_attach_open_context); void nfs_file_set_open_context(struct file *filp, struct nfs_open_context *ctx) { filp->private_data = get_nfs_open_context(ctx); + set_bit(NFS_CONTEXT_FILE_OPEN, &ctx->flags); if (list_empty(&ctx->list)) nfs_inode_attach_open_context(ctx); } @@ -1057,6 +1055,8 @@ struct nfs_open_context *nfs_find_open_context(struct inode *inode, struct rpc_c continue; if ((pos->mode & (FMODE_READ|FMODE_WRITE)) != mode) continue; + if (!test_bit(NFS_CONTEXT_FILE_OPEN, &pos->flags)) + continue; ctx = get_nfs_open_context(pos); break; } @@ -1071,6 +1071,7 @@ void nfs_file_clear_open_context(struct file *filp) if (ctx) { struct inode *inode = d_inode(ctx->dentry); + clear_bit(NFS_CONTEXT_FILE_OPEN, &ctx->flags); /* * We fatal error on write before. Try to writeback * every page again. @@ -1607,10 +1608,10 @@ EXPORT_SYMBOL_GPL(_nfs_display_fhandle); */ static int nfs_inode_attrs_need_update(const struct inode *inode, const struct nfs_fattr *fattr) { - const struct nfs_inode *nfsi = NFS_I(inode); + unsigned long attr_gencount = NFS_I(inode)->attr_gencount; - return ((long)fattr->gencount - (long)nfsi->attr_gencount) > 0 || - ((long)nfsi->attr_gencount - (long)nfs_read_attr_generation_counter() > 0); + return (long)(fattr->gencount - attr_gencount) > 0 || + (long)(attr_gencount - nfs_read_attr_generation_counter()) > 0; } static int nfs_refresh_inode_locked(struct inode *inode, struct nfs_fattr *fattr) @@ -2034,7 +2035,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) nfsi->attrtimeo_timestamp = now; } /* Set the barrier to be more recent than this fattr */ - if ((long)fattr->gencount - (long)nfsi->attr_gencount > 0) + if ((long)(fattr->gencount - nfsi->attr_gencount) > 0) nfsi->attr_gencount = fattr->gencount; } @@ -2142,7 +2143,7 @@ static int nfsiod_start(void) { struct workqueue_struct *wq; dprintk("RPC: creating workqueue nfsiod\n"); - wq = alloc_workqueue("nfsiod", WQ_MEM_RECLAIM, 0); + wq = alloc_workqueue("nfsiod", WQ_MEM_RECLAIM | WQ_UNBOUND, 0); if (wq == NULL) return -ENOMEM; nfsiod_workqueue = wq; diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index a97b081ab843..de626edc0dde 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -578,12 +578,14 @@ extern int nfs4_test_session_trunk(struct rpc_clnt *, static inline struct inode *nfs_igrab_and_active(struct inode *inode) { - inode = igrab(inode); - if (inode != NULL && !nfs_sb_active(inode->i_sb)) { - iput(inode); - inode = NULL; + struct super_block *sb = inode->i_sb; + + if (sb && nfs_sb_active(sb)) { + if (igrab(inode)) + return inode; + nfs_sb_deactive(sb); } - return inode; + return NULL; } static inline void nfs_iput_and_deactive(struct inode *inode) diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c index e5686be67be8..d57d453aecc2 100644 --- a/fs/nfs/namespace.c +++ b/fs/nfs/namespace.c @@ -30,9 +30,9 @@ int nfs_mountpoint_expiry_timeout = 500 * HZ; /* * nfs_path - reconstruct the path given an arbitrary dentry * @base - used to return pointer to the end of devname part of path - * @dentry - pointer to dentry + * @dentry_in - pointer to dentry * @buffer - result buffer - * @buflen - length of buffer + * @buflen_in - length of buffer * @flags - options (see below) * * Helper function for constructing the server pathname @@ -47,15 +47,19 @@ int nfs_mountpoint_expiry_timeout = 500 * HZ; * the original device (export) name * (if unset, the original name is returned verbatim) */ -char *nfs_path(char **p, struct dentry *dentry, char *buffer, ssize_t buflen, - unsigned flags) +char *nfs_path(char **p, struct dentry *dentry_in, char *buffer, + ssize_t buflen_in, unsigned flags) { char *end; int namelen; unsigned seq; const char *base; + struct dentry *dentry; + ssize_t buflen; rename_retry: + buflen = buflen_in; + dentry = dentry_in; end = buffer+buflen; *--end = '\0'; buflen--; diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index ec8a9efa268f..e302f8370b9b 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -346,7 +346,7 @@ nfs3_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr, break; case NFS3_CREATE_UNCHECKED: - goto out; + goto out_release_acls; } nfs_fattr_init(data->res.dir_attr); nfs_fattr_init(data->res.fattr); @@ -695,7 +695,7 @@ nfs3_proc_mknod(struct inode *dir, struct dentry *dentry, struct iattr *sattr, break; default: status = -EINVAL; - goto out; + goto out_release_acls; } status = nfs3_do_create(dir, dentry, data); diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index 9956453aa6ff..0ed419bb02b0 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -34,6 +34,7 @@ */ #define NFS3_fhandle_sz (1+16) #define NFS3_fh_sz (NFS3_fhandle_sz) /* shorthand */ +#define NFS3_post_op_fh_sz (1+NFS3_fh_sz) #define NFS3_sattr_sz (15) #define NFS3_filename_sz (1+(NFS3_MAXNAMLEN>>2)) #define NFS3_path_sz (1+(NFS3_MAXPATHLEN>>2)) @@ -71,7 +72,7 @@ #define NFS3_readlinkres_sz (1+NFS3_post_op_attr_sz+1) #define NFS3_readres_sz (1+NFS3_post_op_attr_sz+3) #define NFS3_writeres_sz (1+NFS3_wcc_data_sz+4) -#define NFS3_createres_sz (1+NFS3_fh_sz+NFS3_post_op_attr_sz+NFS3_wcc_data_sz) +#define NFS3_createres_sz (1+NFS3_post_op_fh_sz+NFS3_post_op_attr_sz+NFS3_wcc_data_sz) #define NFS3_renameres_sz (1+(2 * NFS3_wcc_data_sz)) #define NFS3_linkres_sz (1+NFS3_post_op_attr_sz+NFS3_wcc_data_sz) #define NFS3_readdirres_sz (1+NFS3_post_op_attr_sz+2) diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 526441de89c1..5b1d452e640b 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -59,7 +59,8 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, static int nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, loff_t offset, loff_t len) { - struct nfs_server *server = NFS_SERVER(file_inode(filep)); + struct inode *inode = file_inode(filep); + struct nfs_server *server = NFS_SERVER(inode); struct nfs4_exception exception = { }; struct nfs_lock_context *lock; int err; @@ -68,9 +69,13 @@ static int nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, if (IS_ERR(lock)) return PTR_ERR(lock); - exception.inode = file_inode(filep); + exception.inode = inode; exception.state = lock->open_context->state; + err = nfs_sync_inode(inode); + if (err) + goto out; + do { err = _nfs42_proc_fallocate(msg, filep, lock, offset, len); if (err == -ENOTSUPP) { @@ -79,7 +84,7 @@ static int nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, } err = nfs4_handle_exception(server, err, &exception); } while (exception.retry); - +out: nfs_put_lock_context(lock); return err; } @@ -117,16 +122,13 @@ int nfs42_proc_deallocate(struct file *filep, loff_t offset, loff_t len) return -EOPNOTSUPP; inode_lock(inode); - err = nfs_sync_inode(inode); - if (err) - goto out_unlock; err = nfs42_proc_fallocate(&msg, filep, offset, len); if (err == 0) truncate_pagecache_range(inode, offset, (offset + len) -1); if (err == -EOPNOTSUPP) NFS_SERVER(inode)->caps &= ~NFS_CAP_DEALLOCATE; -out_unlock: + inode_unlock(inode); return err; } @@ -293,8 +295,9 @@ static ssize_t _nfs42_proc_copy(struct file *src, goto out; } - truncate_pagecache_range(dst_inode, pos_dst, - pos_dst + res->write_res.count); + WARN_ON_ONCE(invalidate_inode_pages2_range(dst_inode->i_mapping, + pos_dst >> PAGE_SHIFT, + (pos_dst + res->write_res.count - 1) >> PAGE_SHIFT)); status = res->write_res.count; out: @@ -498,7 +501,10 @@ static loff_t _nfs42_proc_llseek(struct file *filep, if (status) return status; - return vfs_setpos(filep, res.sr_offset, inode->i_sb->s_maxbytes); + if (whence == SEEK_DATA && res.sr_eof) + return -NFS4ERR_NXIO; + else + return vfs_setpos(filep, res.sr_offset, inode->i_sb->s_maxbytes); } loff_t nfs42_proc_llseek(struct file *filep, loff_t offset, int whence) diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c index ec9803088f6b..eee011de3f58 100644 --- a/fs/nfs/nfs42xdr.c +++ b/fs/nfs/nfs42xdr.c @@ -707,8 +707,7 @@ static int nfs4_xdr_dec_clone(struct rpc_rqst *rqstp, status = decode_clone(xdr); if (status) goto out; - status = decode_getfattr(xdr, res->dst_fattr, res->server); - + decode_getfattr(xdr, res->dst_fattr, res->server); out: res->rpc_status = status; return status; diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 5b61520dce88..2d438318681a 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -190,7 +190,7 @@ struct nfs4_state { unsigned int n_wronly; /* Number of write-only references */ unsigned int n_rdwr; /* Number of read/write references */ fmode_t state; /* State on the server (R,W, or RW) */ - atomic_t count; + refcount_t count; wait_queue_head_t waitq; }; @@ -201,6 +201,7 @@ struct nfs4_exception { struct inode *inode; nfs4_stateid *stateid; long timeout; + unsigned char task_is_privileged : 1; unsigned char delay : 1, recovering : 1, retry : 1; @@ -275,7 +276,8 @@ struct vfsmount *nfs4_submount(struct nfs_server *, struct dentry *, struct nfs_fh *, struct nfs_fattr *); int nfs4_replace_transport(struct nfs_server *server, const struct nfs4_fs_locations *locations); - +size_t nfs_parse_server_name(char *string, size_t len, struct sockaddr *sa, + size_t salen, struct net *net); /* nfs4proc.c */ extern int nfs4_handle_exception(struct nfs_server *, int, struct nfs4_exception *); extern int nfs4_async_handle_error(struct rpc_task *task, diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index faaabbedc891..50d352011ea6 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -191,8 +191,11 @@ void nfs40_shutdown_client(struct nfs_client *clp) struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *cl_init) { - int err; + char buf[INET6_ADDRSTRLEN + 1]; + const char *ip_addr = cl_init->ip_addr; struct nfs_client *clp = nfs_alloc_client(cl_init); + int err; + if (IS_ERR(clp)) return clp; @@ -216,6 +219,44 @@ struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *cl_init) init_waitqueue_head(&clp->cl_lock_waitq); #endif INIT_LIST_HEAD(&clp->pending_cb_stateids); + + if (cl_init->minorversion != 0) + __set_bit(NFS_CS_INFINITE_SLOTS, &clp->cl_flags); + __set_bit(NFS_CS_DISCRTRY, &clp->cl_flags); + __set_bit(NFS_CS_NO_RETRANS_TIMEOUT, &clp->cl_flags); + + /* + * Set up the connection to the server before we add add to the + * global list. + */ + err = nfs_create_rpc_client(clp, cl_init, RPC_AUTH_GSS_KRB5I); + if (err == -EINVAL) + err = nfs_create_rpc_client(clp, cl_init, RPC_AUTH_UNIX); + if (err < 0) + goto error; + + /* If no clientaddr= option was specified, find a usable cb address */ + if (ip_addr == NULL) { + struct sockaddr_storage cb_addr; + struct sockaddr *sap = (struct sockaddr *)&cb_addr; + + err = rpc_localaddr(clp->cl_rpcclient, sap, sizeof(cb_addr)); + if (err < 0) + goto error; + err = rpc_ntop(sap, buf, sizeof(buf)); + if (err < 0) + goto error; + ip_addr = (const char *)buf; + } + strlcpy(clp->cl_ipaddr, ip_addr, sizeof(clp->cl_ipaddr)); + + err = nfs_idmap_new(clp); + if (err < 0) { + dprintk("%s: failed to create idmapper. Error = %d\n", + __func__, err); + goto error; + } + __set_bit(NFS_CS_IDMAP, &clp->cl_res_state); return clp; error: @@ -299,6 +340,7 @@ int nfs40_init_client(struct nfs_client *clp) ret = nfs4_setup_slot_table(tbl, NFS4_MAX_SLOT_TABLE, "NFSv4.0 transport Slot table"); if (ret) { + nfs4_shutdown_slot_table(tbl); kfree(tbl); return ret; } @@ -368,8 +410,6 @@ static int nfs4_init_client_minor_version(struct nfs_client *clp) struct nfs_client *nfs4_init_client(struct nfs_client *clp, const struct nfs_client_initdata *cl_init) { - char buf[INET6_ADDRSTRLEN + 1]; - const char *ip_addr = cl_init->ip_addr; struct nfs_client *old; int error; @@ -377,43 +417,6 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp, /* the client is initialised already */ return clp; - /* Check NFS protocol revision and initialize RPC op vector */ - clp->rpc_ops = &nfs_v4_clientops; - - if (clp->cl_minorversion != 0) - __set_bit(NFS_CS_INFINITE_SLOTS, &clp->cl_flags); - __set_bit(NFS_CS_DISCRTRY, &clp->cl_flags); - __set_bit(NFS_CS_NO_RETRANS_TIMEOUT, &clp->cl_flags); - - error = nfs_create_rpc_client(clp, cl_init, RPC_AUTH_GSS_KRB5I); - if (error == -EINVAL) - error = nfs_create_rpc_client(clp, cl_init, RPC_AUTH_UNIX); - if (error < 0) - goto error; - - /* If no clientaddr= option was specified, find a usable cb address */ - if (ip_addr == NULL) { - struct sockaddr_storage cb_addr; - struct sockaddr *sap = (struct sockaddr *)&cb_addr; - - error = rpc_localaddr(clp->cl_rpcclient, sap, sizeof(cb_addr)); - if (error < 0) - goto error; - error = rpc_ntop(sap, buf, sizeof(buf)); - if (error < 0) - goto error; - ip_addr = (const char *)buf; - } - strlcpy(clp->cl_ipaddr, ip_addr, sizeof(clp->cl_ipaddr)); - - error = nfs_idmap_new(clp); - if (error < 0) { - dprintk("%s: failed to create idmapper. Error = %d\n", - __func__, error); - goto error; - } - __set_bit(NFS_CS_IDMAP, &clp->cl_res_state); - error = nfs4_init_client_minor_version(clp); if (error < 0) goto error; @@ -431,8 +434,8 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp, */ nfs_mark_client_ready(clp, -EPERM); } - nfs_put_client(clp); clear_bit(NFS_CS_TSM_POSSIBLE, &clp->cl_flags); + nfs_put_client(clp); return old; error: @@ -1271,8 +1274,11 @@ int nfs4_update_server(struct nfs_server *server, const char *hostname, } nfs_put_client(clp); - if (server->nfs_client->cl_hostname == NULL) + if (server->nfs_client->cl_hostname == NULL) { server->nfs_client->cl_hostname = kstrdup(hostname, GFP_KERNEL); + if (server->nfs_client->cl_hostname == NULL) + return -ENOMEM; + } nfs_server_insert_lists(server); return nfs_probe_destination(server); diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index 75d3cf86f172..e053a883d08d 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -148,7 +148,7 @@ static loff_t nfs4_file_llseek(struct file *filep, loff_t offset, int whence) case SEEK_HOLE: case SEEK_DATA: ret = nfs42_proc_llseek(filep, offset, whence); - if (ret != -ENOTSUPP) + if (ret != -EOPNOTSUPP) return ret; /* Fall through */ default: diff --git a/fs/nfs/nfs4idmap.c b/fs/nfs/nfs4idmap.c index bf34ddaa2ad7..c1c26b06764f 100644 --- a/fs/nfs/nfs4idmap.c +++ b/fs/nfs/nfs4idmap.c @@ -547,22 +547,20 @@ nfs_idmap_prepare_pipe_upcall(struct idmap *idmap, return true; } -static void -nfs_idmap_complete_pipe_upcall_locked(struct idmap *idmap, int ret) +static void nfs_idmap_complete_pipe_upcall(struct idmap_legacy_upcalldata *data, + int ret) { - struct key *authkey = idmap->idmap_upcall_data->authkey; - - kfree(idmap->idmap_upcall_data); - idmap->idmap_upcall_data = NULL; - complete_request_key(authkey, ret); - key_put(authkey); + complete_request_key(data->authkey, ret); + key_put(data->authkey); + kfree(data); } -static void -nfs_idmap_abort_pipe_upcall(struct idmap *idmap, int ret) +static void nfs_idmap_abort_pipe_upcall(struct idmap *idmap, + struct idmap_legacy_upcalldata *data, + int ret) { - if (idmap->idmap_upcall_data != NULL) - nfs_idmap_complete_pipe_upcall_locked(idmap, ret); + if (cmpxchg(&idmap->idmap_upcall_data, data, NULL) == data) + nfs_idmap_complete_pipe_upcall(data, ret); } static int nfs_idmap_legacy_upcall(struct key *authkey, void *aux) @@ -599,7 +597,7 @@ static int nfs_idmap_legacy_upcall(struct key *authkey, void *aux) ret = rpc_queue_upcall(idmap->idmap_pipe, msg); if (ret < 0) - nfs_idmap_abort_pipe_upcall(idmap, ret); + nfs_idmap_abort_pipe_upcall(idmap, data, ret); return ret; out2: @@ -655,6 +653,7 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) struct request_key_auth *rka; struct rpc_inode *rpci = RPC_I(file_inode(filp)); struct idmap *idmap = (struct idmap *)rpci->private; + struct idmap_legacy_upcalldata *data; struct key *authkey; struct idmap_msg im; size_t namelen_in; @@ -664,10 +663,11 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) * will have been woken up and someone else may now have used * idmap_key_cons - so after this point we may no longer touch it. */ - if (idmap->idmap_upcall_data == NULL) + data = xchg(&idmap->idmap_upcall_data, NULL); + if (data == NULL) goto out_noupcall; - authkey = idmap->idmap_upcall_data->authkey; + authkey = data->authkey; rka = get_request_key_auth(authkey); if (mlen != sizeof(im)) { @@ -689,18 +689,17 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) if (namelen_in == 0 || namelen_in == IDMAP_NAMESZ) { ret = -EINVAL; goto out; -} + } - ret = nfs_idmap_read_and_verify_message(&im, - &idmap->idmap_upcall_data->idmap_msg, - rka->target_key, authkey); + ret = nfs_idmap_read_and_verify_message(&im, &data->idmap_msg, + rka->target_key, authkey); if (ret >= 0) { key_set_timeout(rka->target_key, nfs_idmap_cache_timeout); ret = mlen; } out: - nfs_idmap_complete_pipe_upcall_locked(idmap, ret); + nfs_idmap_complete_pipe_upcall(data, ret); out_noupcall: return ret; } @@ -714,7 +713,7 @@ idmap_pipe_destroy_msg(struct rpc_pipe_msg *msg) struct idmap *idmap = data->idmap; if (msg->errno) - nfs_idmap_abort_pipe_upcall(idmap, msg->errno); + nfs_idmap_abort_pipe_upcall(idmap, data, msg->errno); } static void @@ -722,8 +721,11 @@ idmap_release_pipe(struct inode *inode) { struct rpc_inode *rpci = RPC_I(inode); struct idmap *idmap = (struct idmap *)rpci->private; + struct idmap_legacy_upcalldata *data; - nfs_idmap_abort_pipe_upcall(idmap, -EPIPE); + data = xchg(&idmap->idmap_upcall_data, NULL); + if (data) + nfs_idmap_complete_pipe_upcall(data, -EPIPE); } int nfs_map_name_to_uid(const struct nfs_server *server, const char *name, size_t namelen, kuid_t *uid) diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c index 24f06dcc2b08..936c412be28e 100644 --- a/fs/nfs/nfs4namespace.c +++ b/fs/nfs/nfs4namespace.c @@ -121,8 +121,8 @@ static int nfs4_validate_fspath(struct dentry *dentry, return 0; } -static size_t nfs_parse_server_name(char *string, size_t len, - struct sockaddr *sa, size_t salen, struct net *net) +size_t nfs_parse_server_name(char *string, size_t len, struct sockaddr *sa, + size_t salen, struct net *net) { ssize_t ret; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index b2a2ff3f22a4..c9db9a0fc733 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -163,6 +163,7 @@ static int nfs4_map_errors(int err) case -NFS4ERR_RESOURCE: case -NFS4ERR_LAYOUTTRYLATER: case -NFS4ERR_RECALLCONFLICT: + case -NFS4ERR_RETURNCONFLICT: return -EREMOTEIO; case -NFS4ERR_WRONGSEC: case -NFS4ERR_WRONG_CRED: @@ -509,6 +510,7 @@ static int nfs4_do_handle_exception(struct nfs_server *server, case -NFS4ERR_GRACE: case -NFS4ERR_LAYOUTTRYLATER: case -NFS4ERR_RECALLCONFLICT: + case -NFS4ERR_RETURNCONFLICT: exception->delay = 1; return 0; @@ -550,6 +552,8 @@ int nfs4_handle_exception(struct nfs_server *server, int errorcode, struct nfs4_ goto out_retry; } if (exception->recovering) { + if (exception->task_is_privileged) + return -EDEADLOCK; ret = nfs4_wait_clnt_recover(clp); if (test_bit(NFS_MIG_FAILED, &server->mig_status)) return -EIO; @@ -575,6 +579,8 @@ nfs4_async_handle_exception(struct rpc_task *task, struct nfs_server *server, goto out_retry; } if (exception->recovering) { + if (exception->task_is_privileged) + return -EDEADLOCK; rpc_sleep_on(&clp->cl_rpcwaitq, task, NULL); if (test_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) == 0) rpc_wake_up_queued_task(&clp->cl_rpcwaitq, task); @@ -1788,7 +1794,7 @@ static struct nfs4_state *nfs4_try_open_cached(struct nfs4_opendata *opendata) out: return ERR_PTR(ret); out_return_state: - atomic_inc(&state->count); + refcount_inc(&state->count); return state; } @@ -1847,8 +1853,7 @@ _nfs4_opendata_reclaim_to_nfs4_state(struct nfs4_opendata *data) if (!data->rpc_done) { if (data->rpc_status) return ERR_PTR(data->rpc_status); - /* cached opens have already been processed */ - goto update; + return nfs4_try_open_cached(data); } ret = nfs_refresh_inode(inode, &data->f_attr); @@ -1857,10 +1862,11 @@ _nfs4_opendata_reclaim_to_nfs4_state(struct nfs4_opendata *data) if (data->o_res.delegation_type != 0) nfs4_opendata_check_deleg(data, state); -update: - update_open_stateid(state, &data->o_res.stateid, NULL, - data->o_arg.fmode); - atomic_inc(&state->count); + + if (!update_open_stateid(state, &data->o_res.stateid, + NULL, data->o_arg.fmode)) + return ERR_PTR(-EAGAIN); + refcount_inc(&state->count); return state; } @@ -1898,7 +1904,7 @@ nfs4_opendata_find_nfs4_state(struct nfs4_opendata *data) return ERR_CAST(inode); if (data->state != NULL && data->state->inode == inode) { state = data->state; - atomic_inc(&state->count); + refcount_inc(&state->count); } else state = nfs4_get_open_state(inode, data->owner); iput(inode); @@ -1924,8 +1930,11 @@ _nfs4_opendata_to_nfs4_state(struct nfs4_opendata *data) if (data->o_res.delegation_type != 0) nfs4_opendata_check_deleg(data, state); - update_open_stateid(state, &data->o_res.stateid, NULL, - data->o_arg.fmode); + if (!update_open_stateid(state, &data->o_res.stateid, + NULL, data->o_arg.fmode)) { + nfs4_put_open_state(state); + state = ERR_PTR(-EAGAIN); + } out: nfs_release_seqid(data->o_arg.seqid); return state; @@ -1971,23 +1980,23 @@ static struct nfs4_opendata *nfs4_open_recoverdata_alloc(struct nfs_open_context if (opendata == NULL) return ERR_PTR(-ENOMEM); opendata->state = state; - atomic_inc(&state->count); + refcount_inc(&state->count); return opendata; } static int nfs4_open_recover_helper(struct nfs4_opendata *opendata, - fmode_t fmode) + fmode_t fmode) { struct nfs4_state *newstate; + struct nfs_server *server = NFS_SB(opendata->dentry->d_sb); + int openflags = opendata->o_arg.open_flags; int ret; if (!nfs4_mode_match_open_stateid(opendata->state, fmode)) return 0; - opendata->o_arg.open_flags = 0; opendata->o_arg.fmode = fmode; - opendata->o_arg.share_access = nfs4_map_atomic_open_share( - NFS_SB(opendata->dentry->d_sb), - fmode, 0); + opendata->o_arg.share_access = + nfs4_map_atomic_open_share(server, fmode, openflags); memset(&opendata->o_res, 0, sizeof(opendata->o_res)); memset(&opendata->c_res, 0, sizeof(opendata->c_res)); nfs4_init_opendata_res(opendata); @@ -2565,10 +2574,15 @@ static int _nfs4_open_expired(struct nfs_open_context *ctx, struct nfs4_state *s struct nfs4_opendata *opendata; int ret; - opendata = nfs4_open_recoverdata_alloc(ctx, state, - NFS4_OPEN_CLAIM_FH); + opendata = nfs4_open_recoverdata_alloc(ctx, state, NFS4_OPEN_CLAIM_FH); if (IS_ERR(opendata)) return PTR_ERR(opendata); + /* + * We're not recovering a delegation, so ask for no delegation. + * Otherwise the recovery thread could deadlock with an outstanding + * delegation return. + */ + opendata->o_arg.open_flags = O_DIRECT; ret = nfs4_open_recover(opendata, state); if (ret == -ESTALE) d_drop(ctx->dentry); @@ -2916,8 +2930,13 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata, } out: - if (!opendata->cancelled) + if (!opendata->cancelled) { + if (opendata->lgp) { + nfs4_lgopen_release(opendata->lgp); + opendata->lgp = NULL; + } nfs4_sequence_free_slot(&opendata->o_res.seq_res); + } return ret; } @@ -4687,12 +4706,12 @@ static int _nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred, u64 cookie, struct page **pages, unsigned int count, bool plus) { struct inode *dir = d_inode(dentry); + struct nfs_server *server = NFS_SERVER(dir); struct nfs4_readdir_arg args = { .fh = NFS_FH(dir), .pages = pages, .pgbase = 0, .count = count, - .bitmask = NFS_SERVER(d_inode(dentry))->attr_bitmask, .plus = plus, }; struct nfs4_readdir_res res; @@ -4707,9 +4726,15 @@ static int _nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred, dprintk("%s: dentry = %pd2, cookie = %Lu\n", __func__, dentry, (unsigned long long)cookie); + if (!(server->caps & NFS_CAP_SECURITY_LABEL)) + args.bitmask = server->attr_bitmask_nl; + else + args.bitmask = server->attr_bitmask; + nfs4_setup_readdir(cookie, NFS_I(dir)->cookieverf, dentry, &args); res.pgbase = args.pgbase; - status = nfs4_call_sync(NFS_SERVER(dir)->client, NFS_SERVER(dir), &msg, &args.seq_args, &res.seq_res, 0); + status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, + &res.seq_res, 0); if (status >= 0) { memcpy(NFS_I(dir)->cookieverf, res.verifier.data, NFS4_VERIFIER_SIZE); status += args.pgbase; @@ -5120,7 +5145,7 @@ static void nfs4_proc_write_setup(struct nfs_pgio_header *hdr, msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_WRITE]; nfs4_init_sequence(&hdr->args.seq_args, &hdr->res.seq_res, 0, 0); - nfs4_state_protect_write(server->nfs_client, clnt, msg, hdr); + nfs4_state_protect_write(hdr->ds_clp ? hdr->ds_clp : server->nfs_client, clnt, msg, hdr); } static void nfs4_proc_commit_rpc_prepare(struct rpc_task *task, struct nfs_commit_data *data) @@ -5161,7 +5186,8 @@ static void nfs4_proc_commit_setup(struct nfs_commit_data *data, struct rpc_mess data->res.server = server; msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_COMMIT]; nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1, 0); - nfs4_state_protect(server->nfs_client, NFS_SP4_MACH_CRED_COMMIT, clnt, msg); + nfs4_state_protect(data->ds_clp ? data->ds_clp : server->nfs_client, + NFS_SP4_MACH_CRED_COMMIT, clnt, msg); } static int _nfs4_proc_commit(struct file *dst, struct nfs_commitargs *args, @@ -5529,6 +5555,9 @@ static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t bufl unsigned int npages = DIV_ROUND_UP(buflen, PAGE_SIZE); int ret, i; + /* You can't remove system.nfs4_acl: */ + if (buflen == 0) + return -EINVAL; if (!nfs4_server_supports_acls(server)) return -EOPNOTSUPP; if (npages > ARRAY_SIZE(pages)) @@ -5567,6 +5596,14 @@ static int nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t buflen do { err = __nfs4_proc_set_acl(inode, buf, buflen); trace_nfs4_set_acl(inode, err); + if (err == -NFS4ERR_BADOWNER || err == -NFS4ERR_BADNAME) { + /* + * no need to retry since the kernel + * isn't involved in encoding the ACEs. + */ + err = -EINVAL; + break; + } err = nfs4_handle_exception(NFS_SERVER(inode), err, &exception); } while (exception.retry); @@ -5605,7 +5642,7 @@ static int _nfs4_get_security_label(struct inode *inode, void *buf, return ret; if (!(fattr.valid & NFS_ATTR_FATTR_V4_SECURITY_LABEL)) return -ENOENT; - return 0; + return label.len; } static int nfs4_get_security_label(struct inode *inode, void *buf, @@ -6008,6 +6045,7 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata) struct nfs4_exception exception = { .inode = data->inode, .stateid = &data->stateid, + .task_is_privileged = data->args.seq_args.sa_privileged, }; if (!nfs4_sequence_done(task, &data->res.seq_res)) @@ -6151,7 +6189,6 @@ static int _nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, co data = kzalloc(sizeof(*data), GFP_NOFS); if (data == NULL) return -ENOMEM; - nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1, 0); nfs4_state_protect(server->nfs_client, NFS_SP4_MACH_CRED_CLEANUP, @@ -6181,6 +6218,12 @@ static int _nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, co data->lr.roc = false; } + if (!data->inode) + nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1, + 1); + else + nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1, + 0); task_setup_data.callback_data = data; msg.rpc_argp = &data->args; msg.rpc_resp = &data->res; @@ -6581,6 +6624,7 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata) { struct nfs4_lockdata *data = calldata; struct nfs4_lock_state *lsp = data->lsp; + struct nfs_server *server = NFS_SERVER(d_inode(data->ctx->dentry)); dprintk("%s: begin!\n", __func__); @@ -6590,8 +6634,7 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata) data->rpc_status = task->tk_status; switch (task->tk_status) { case 0: - renew_lease(NFS_SERVER(d_inode(data->ctx->dentry)), - data->timestamp); + renew_lease(server, data->timestamp); if (data->arg.new_lock && !data->cancelled) { data->fl.fl_flags &= ~(FL_SLEEP | FL_ACCESS); if (locks_lock_inode_wait(lsp->ls_state->inode, &data->fl) < 0) @@ -6612,6 +6655,8 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata) if (!nfs4_stateid_match(&data->arg.open_stateid, &lsp->ls_state->open_stateid)) goto out_restart; + else if (nfs4_async_handle_error(task, server, lsp->ls_state, NULL) == -EAGAIN) + goto out_restart; } else if (!nfs4_stateid_match(&data->arg.lock_stateid, &lsp->ls_stateid)) goto out_restart; @@ -6715,9 +6760,9 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *f data->arg.new_lock_owner, ret); } else data->cancelled = true; + trace_nfs4_set_lock(fl, state, &data->res.stateid, cmd, ret); rpc_put_task(task); dprintk("%s: done, ret = %d!\n", __func__, ret); - trace_nfs4_set_lock(fl, state, &data->res.stateid, cmd, ret); return ret; } @@ -7600,9 +7645,11 @@ int nfs4_proc_secinfo(struct inode *dir, const struct qstr *name, * both PNFS and NON_PNFS flags set, and not having one of NON_PNFS, PNFS, or * DS flags set. */ -static int nfs4_check_cl_exchange_flags(u32 flags) +static int nfs4_check_cl_exchange_flags(u32 flags, u32 version) { - if (flags & ~EXCHGID4_FLAG_MASK_R) + if (version >= 2 && (flags & ~EXCHGID4_2_FLAG_MASK_R)) + goto out_inval; + else if (version < 2 && (flags & ~EXCHGID4_FLAG_MASK_R)) goto out_inval; if ((flags & EXCHGID4_FLAG_USE_PNFS_MDS) && (flags & EXCHGID4_FLAG_USE_NON_PNFS)) @@ -7997,7 +8044,8 @@ static int _nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred, if (status != 0) goto out; - status = nfs4_check_cl_exchange_flags(resp->flags); + status = nfs4_check_cl_exchange_flags(resp->flags, + clp->cl_mvops->minor_version); if (status != 0) goto out; @@ -8667,6 +8715,9 @@ static int nfs41_reclaim_complete_handle_errors(struct rpc_task *task, struct nf rpc_delay(task, NFS4_POLL_RETRY_MAX); /* fall through */ case -NFS4ERR_RETRY_UNCACHED_REP: + case -EACCES: + dprintk("%s: failed to reclaim complete error %d for server %s, retrying\n", + __func__, task->tk_status, clp->cl_hostname); return -EAGAIN; case -NFS4ERR_BADSESSION: case -NFS4ERR_DEADSESSION: @@ -8827,6 +8878,7 @@ nfs4_layoutget_handle_exception(struct rpc_task *task, status = -EBUSY; break; case -NFS4ERR_RECALLCONFLICT: + case -NFS4ERR_RETURNCONFLICT: status = -ERECALLCONFLICT; break; case -NFS4ERR_DELEG_REVOKED: @@ -9045,15 +9097,20 @@ int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp, bool sync) &task_setup_data.rpc_client, &msg); dprintk("--> %s\n", __func__); + lrp->inode = nfs_igrab_and_active(lrp->args.inode); if (!sync) { - lrp->inode = nfs_igrab_and_active(lrp->args.inode); if (!lrp->inode) { nfs4_layoutreturn_release(lrp); return -EAGAIN; } task_setup_data.flags |= RPC_TASK_ASYNC; } - nfs4_init_sequence(&lrp->args.seq_args, &lrp->res.seq_res, 1, 0); + if (!lrp->inode) + nfs4_init_sequence(&lrp->args.seq_args, &lrp->res.seq_res, 1, + 1); + else + nfs4_init_sequence(&lrp->args.seq_args, &lrp->res.seq_res, 1, + 0); task = rpc_run_task(&task_setup_data); if (IS_ERR(task)) return PTR_ERR(task); diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index b3086e99420c..f0f0fb7499e3 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -49,6 +49,7 @@ #include <linux/workqueue.h> #include <linux/bitops.h> #include <linux/jiffies.h> +#include <linux/sched/mm.h> #include <linux/sunrpc/clnt.h> @@ -65,6 +66,8 @@ #define OPENOWNER_POOL_SIZE 8 +static void nfs4_state_start_reclaim_reboot(struct nfs_client *clp); + const nfs4_stateid zero_stateid = { { .data = { 0 } }, .type = NFS4_SPECIAL_STATEID_TYPE, @@ -337,6 +340,8 @@ do_confirm: status = nfs4_proc_create_session(clp, cred); if (status != 0) goto out; + if (!(clp->cl_exchange_flags & EXCHGID4_FLAG_CONFIRMED_R)) + nfs4_state_start_reclaim_reboot(clp); nfs41_finish_session_reset(clp); nfs_mark_client_ready(clp, NFS_CS_READY); out: @@ -674,7 +679,7 @@ nfs4_alloc_open_state(void) state = kzalloc(sizeof(*state), GFP_NOFS); if (!state) return NULL; - atomic_set(&state->count, 1); + refcount_set(&state->count, 1); INIT_LIST_HEAD(&state->lock_states); spin_lock_init(&state->state_lock); seqlock_init(&state->seqlock); @@ -708,7 +713,7 @@ __nfs4_find_state_byowner(struct inode *inode, struct nfs4_state_owner *owner) continue; if (!nfs4_valid_open_stateid(state)) continue; - if (atomic_inc_not_zero(&state->count)) + if (refcount_inc_not_zero(&state->count)) return state; } return NULL; @@ -762,7 +767,7 @@ void nfs4_put_open_state(struct nfs4_state *state) struct inode *inode = state->inode; struct nfs4_state_owner *owner = state->owner; - if (!atomic_dec_and_lock(&state->count, &owner->so_lock)) + if (!refcount_dec_and_lock(&state->count, &owner->so_lock)) return; spin_lock(&inode->i_lock); list_del(&state->inode_states); @@ -1246,6 +1251,8 @@ void nfs4_schedule_state_manager(struct nfs_client *clp) if (IS_ERR(task)) { printk(KERN_ERR "%s: kthread_run: %ld\n", __func__, PTR_ERR(task)); + if (!nfs_client_init_is_complete(clp)) + nfs_mark_client_ready(clp, PTR_ERR(task)); nfs4_clear_state_manager_bit(clp); nfs_put_client(clp); module_put(THIS_MODULE); @@ -1593,7 +1600,7 @@ restart: continue; if (state->state == 0) continue; - atomic_inc(&state->count); + refcount_inc(&state->count); spin_unlock(&sp->so_lock); status = ops->recover_open(sp, state); if (status >= 0) { @@ -1735,6 +1742,7 @@ static void nfs4_state_mark_reclaim_helper(struct nfs_client *clp, static void nfs4_state_start_reclaim_reboot(struct nfs_client *clp) { + set_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state); /* Mark all delegations for reclaim */ nfs_delegation_mark_reclaim(clp); nfs4_state_mark_reclaim_helper(clp, nfs4_state_mark_reclaim_reboot); @@ -2066,6 +2074,9 @@ static int nfs4_try_migration(struct nfs_server *server, struct rpc_cred *cred) } result = -NFS4ERR_NXIO; + if (!locations->nlocations) + goto out; + if (!(locations->fattr.valid & NFS_ATTR_FATTR_V4_LOCATIONS)) { dprintk("<-- %s: No fs_locations data, migration skipped\n", __func__); @@ -2502,9 +2513,17 @@ static int nfs4_bind_conn_to_session(struct nfs_client *clp) static void nfs4_state_manager(struct nfs_client *clp) { + unsigned int memflags; int status = 0; const char *section = "", *section_sep = ""; + /* + * State recovery can deadlock if the direct reclaim code tries + * start NFS writeback. So ensure memory allocations are all + * GFP_NOFS. + */ + memflags = memalloc_nofs_save(); + /* Ensure exclusive access to NFSv4 state */ do { clear_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state); @@ -2577,6 +2596,7 @@ static void nfs4_state_manager(struct nfs_client *clp) if (status < 0) goto out_error; nfs4_state_end_reclaim_reboot(clp); + continue; } /* Detect expired delegations... */ @@ -2597,6 +2617,7 @@ static void nfs4_state_manager(struct nfs_client *clp) goto out_error; } + memalloc_nofs_restore(memflags); nfs4_end_drain_session(clp); nfs4_clear_state_manager_bit(clp); @@ -2613,6 +2634,7 @@ static void nfs4_state_manager(struct nfs_client *clp) return; if (test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) != 0) return; + memflags = memalloc_nofs_save(); } while (refcount_read(&clp->cl_count) > 1 && !signalled()); goto out_drain; @@ -2624,6 +2646,7 @@ out_error: clp->cl_hostname, -status); ssleep(1); out_drain: + memalloc_nofs_restore(memflags); nfs4_end_drain_session(clp); nfs4_clear_state_manager_bit(clp); } diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c index 6fb7cb6b3f4b..e7a10f5f5405 100644 --- a/fs/nfs/nfs4super.c +++ b/fs/nfs/nfs4super.c @@ -95,7 +95,7 @@ static void nfs4_evict_inode(struct inode *inode) nfs_inode_return_delegation_noreclaim(inode); /* Note that above delegreturn would trigger pnfs return-on-close */ pnfs_return_layout(inode); - pnfs_destroy_layout(NFS_I(inode)); + pnfs_destroy_layout_final(NFS_I(inode)); /* First call standard NFS clear_inode() code */ nfs_clear_inode(inode); } diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 0a5cae8f8aff..f0021e3b8efd 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -3747,8 +3747,6 @@ static int decode_attr_fs_locations(struct xdr_stream *xdr, uint32_t *bitmap, st if (unlikely(!p)) goto out_overflow; n = be32_to_cpup(p); - if (n <= 0) - goto out_eio; for (res->nlocations = 0; res->nlocations < n; res->nlocations++) { u32 m; struct nfs4_fs_location *loc; @@ -4279,12 +4277,10 @@ static int decode_attr_security_label(struct xdr_stream *xdr, uint32_t *bitmap, if (unlikely(!p)) goto out_overflow; if (len < NFS4_MAXLABELLEN) { - if (label) { - if (label->len) { - if (label->len < len) - return -ERANGE; - memcpy(label->label, p, len); - } + if (label && label->len) { + if (label->len < len) + return -ERANGE; + memcpy(label->label, p, len); label->len = len; label->pi = pi; label->lfs = lfs; @@ -4294,10 +4290,11 @@ static int decode_attr_security_label(struct xdr_stream *xdr, uint32_t *bitmap, } else printk(KERN_WARNING "%s: label too long (%u)!\n", __func__, len); + if (label && label->label) + dprintk("%s: label=%.*s, len=%d, PI=%d, LFS=%d\n", + __func__, label->len, (char *)label->label, + label->len, label->pi, label->lfs); } - if (label && label->label) - dprintk("%s: label=%s, len=%d, PI=%d, LFS=%d\n", __func__, - (char *)label->label, label->len, label->pi, label->lfs); return status; out_overflow: diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 2c7d76b4c5e1..a9e1bcdd9394 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -987,17 +987,16 @@ static void nfs_pageio_doio(struct nfs_pageio_descriptor *desc) { struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc); - if (!list_empty(&mirror->pg_list)) { int error = desc->pg_ops->pg_doio(desc); if (error < 0) desc->pg_error = error; - else + if (list_empty(&mirror->pg_list)) { mirror->pg_bytes_written += mirror->pg_count; - } - if (list_empty(&mirror->pg_list)) { - mirror->pg_count = 0; - mirror->pg_base = 0; + mirror->pg_count = 0; + mirror->pg_base = 0; + mirror->pg_recoalesce = 0; + } } } @@ -1095,7 +1094,6 @@ static int nfs_do_recoalesce(struct nfs_pageio_descriptor *desc) do { list_splice_init(&mirror->pg_list, &head); - mirror->pg_bytes_written -= mirror->pg_count; mirror->pg_count = 0; mirror->pg_base = 0; mirror->pg_recoalesce = 0; diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 2b9e139a2997..cfb1fe5dfb1e 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -92,6 +92,17 @@ find_pnfs_driver(u32 id) return local; } +const struct pnfs_layoutdriver_type *pnfs_find_layoutdriver(u32 id) +{ + return find_pnfs_driver(id); +} + +void pnfs_put_layoutdriver(const struct pnfs_layoutdriver_type *ld) +{ + if (ld) + module_put(ld->owner); +} + void unset_pnfs_layoutdriver(struct nfs_server *nfss) { @@ -294,6 +305,7 @@ void pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo) { struct inode *inode; + unsigned long i_state; if (!lo) return; @@ -304,8 +316,12 @@ pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo) if (!list_empty(&lo->plh_segs)) WARN_ONCE(1, "NFS: BUG unfreed layout segments.\n"); pnfs_detach_layout_hdr(lo); + i_state = inode->i_state; spin_unlock(&inode->i_lock); pnfs_free_layout_hdr(lo); + /* Notify pnfs_destroy_layout_final() that we're done */ + if (i_state & (I_FREEING | I_CLEAR)) + wake_up_var(lo); } } @@ -713,8 +729,7 @@ pnfs_free_lseg_list(struct list_head *free_me) } } -void -pnfs_destroy_layout(struct nfs_inode *nfsi) +static struct pnfs_layout_hdr *__pnfs_destroy_layout(struct nfs_inode *nfsi) { struct pnfs_layout_hdr *lo; LIST_HEAD(tmp_list); @@ -732,9 +747,34 @@ pnfs_destroy_layout(struct nfs_inode *nfsi) pnfs_put_layout_hdr(lo); } else spin_unlock(&nfsi->vfs_inode.i_lock); + return lo; +} + +void pnfs_destroy_layout(struct nfs_inode *nfsi) +{ + __pnfs_destroy_layout(nfsi); } EXPORT_SYMBOL_GPL(pnfs_destroy_layout); +static bool pnfs_layout_removed(struct nfs_inode *nfsi, + struct pnfs_layout_hdr *lo) +{ + bool ret; + + spin_lock(&nfsi->vfs_inode.i_lock); + ret = nfsi->layout != lo; + spin_unlock(&nfsi->vfs_inode.i_lock); + return ret; +} + +void pnfs_destroy_layout_final(struct nfs_inode *nfsi) +{ + struct pnfs_layout_hdr *lo = __pnfs_destroy_layout(nfsi); + + if (lo) + wait_var_event(lo, pnfs_layout_removed(nfsi, lo)); +} + static bool pnfs_layout_add_bulk_destroy_list(struct inode *inode, struct list_head *layout_list) @@ -1239,6 +1279,11 @@ _pnfs_return_layout(struct inode *ino) { struct pnfs_layout_hdr *lo = NULL; struct nfs_inode *nfsi = NFS_I(ino); + struct pnfs_layout_range range = { + .iomode = IOMODE_ANY, + .offset = 0, + .length = NFS4_MAX_UINT64, + }; LIST_HEAD(tmp_list); nfs4_stateid stateid; int status = 0; @@ -1265,16 +1310,10 @@ _pnfs_return_layout(struct inode *ino) } valid_layout = pnfs_layout_is_valid(lo); pnfs_clear_layoutcommit(ino, &tmp_list); - pnfs_mark_matching_lsegs_invalid(lo, &tmp_list, NULL, 0); + pnfs_mark_matching_lsegs_return(lo, &tmp_list, &range, 0); - if (NFS_SERVER(ino)->pnfs_curr_ld->return_range) { - struct pnfs_layout_range range = { - .iomode = IOMODE_ANY, - .offset = 0, - .length = NFS4_MAX_UINT64, - }; + if (NFS_SERVER(ino)->pnfs_curr_ld->return_range) NFS_SERVER(ino)->pnfs_curr_ld->return_range(lo, &range); - } /* Don't send a LAYOUTRETURN if list was initially empty */ if (!test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags) || @@ -1431,12 +1470,18 @@ void pnfs_roc_release(struct nfs4_layoutreturn_args *args, int ret) { struct pnfs_layout_hdr *lo = args->layout; + struct inode *inode = args->inode; const nfs4_stateid *arg_stateid = NULL; const nfs4_stateid *res_stateid = NULL; struct nfs4_xdr_opaque_data *ld_private = args->ld_private; switch (ret) { case -NFS4ERR_NOMATCHING_LAYOUT: + spin_lock(&inode->i_lock); + if (pnfs_layout_is_valid(lo) && + nfs4_stateid_match_other(&args->stateid, &lo->plh_stateid)) + pnfs_set_plh_return_info(lo, args->range.iomode, 0); + spin_unlock(&inode->i_lock); break; case 0: if (res->lrs_present) @@ -1852,6 +1897,7 @@ lookup_again: lo = pnfs_find_alloc_layout(ino, ctx, gfp_flags); if (lo == NULL) { spin_unlock(&ino->i_lock); + lseg = ERR_PTR(-ENOMEM); trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg, PNFS_UPDATE_LAYOUT_NOMEM); goto out; @@ -1979,6 +2025,7 @@ lookup_again: lgp = pnfs_alloc_init_layoutget_args(ino, ctx, &stateid, &arg, gfp_flags); if (!lgp) { + lseg = ERR_PTR(-ENOMEM); trace_pnfs_update_layout(ino, pos, count, iomode, lo, NULL, PNFS_UPDATE_LAYOUT_NOMEM); nfs_layoutget_end(lo); @@ -1998,6 +2045,12 @@ lookup_again: case -ERECALLCONFLICT: case -EAGAIN: break; + case -ENODATA: + /* The server returned NFS4ERR_LAYOUTUNAVAILABLE */ + pnfs_layout_set_fail_bit( + lo, pnfs_iomode_to_fail_bit(iomode)); + lseg = NULL; + goto out_put_layout_hdr; default: if (!nfs_error_is_fatal(PTR_ERR(lseg))) { pnfs_layout_clear_fail_bit(lo, pnfs_iomode_to_fail_bit(iomode)); @@ -2112,6 +2165,7 @@ static void _lgopen_prepare_attached(struct nfs4_opendata *data, &rng, GFP_KERNEL); if (!lgp) { pnfs_clear_first_layoutget(lo); + nfs_layoutget_end(lo); pnfs_put_layout_hdr(lo); return; } @@ -2265,7 +2319,13 @@ pnfs_layout_process(struct nfs4_layoutget *lgp) * We got an entirely new state ID. Mark all segments for the * inode invalid, and retry the layoutget */ - pnfs_mark_layout_stateid_invalid(lo, &free_me); + struct pnfs_layout_range range = { + .iomode = IOMODE_ANY, + .length = NFS4_MAX_UINT64, + }; + pnfs_set_plh_return_info(lo, IOMODE_ANY, 0); + pnfs_mark_matching_lsegs_return(lo, &lo->plh_return_segs, + &range, 0); goto out_forget; } @@ -2284,6 +2344,7 @@ out_forget: spin_unlock(&ino->i_lock); lseg->pls_layout = lo; NFS_SERVER(ino)->pnfs_curr_ld->free_lseg(lseg); + pnfs_free_lseg_list(&free_me); return ERR_PTR(-EAGAIN); } @@ -2316,6 +2377,9 @@ pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo, assert_spin_locked(&lo->plh_inode->i_lock); + if (test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags)) + tmp_list = &lo->plh_return_segs; + list_for_each_entry_safe(lseg, next, &lo->plh_segs, pls_list) if (pnfs_match_lseg_recall(lseg, return_range, seq)) { dprintk("%s: marking lseg %p iomode %d " @@ -2323,6 +2387,8 @@ pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo, lseg, lseg->pls_range.iomode, lseg->pls_range.offset, lseg->pls_range.length); + if (test_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags)) + tmp_list = &lo->plh_return_segs; if (mark_lseg_invalid(lseg, tmp_list)) continue; remaining++; diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 3ba44819a88a..d5d818b1ac9d 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -225,6 +225,8 @@ struct pnfs_devicelist { extern int pnfs_register_layoutdriver(struct pnfs_layoutdriver_type *); extern void pnfs_unregister_layoutdriver(struct pnfs_layoutdriver_type *); +extern const struct pnfs_layoutdriver_type *pnfs_find_layoutdriver(u32 id); +extern void pnfs_put_layoutdriver(const struct pnfs_layoutdriver_type *ld); /* nfs4proc.c */ extern size_t max_response_pages(struct nfs_server *server); @@ -254,6 +256,7 @@ struct pnfs_layout_segment *pnfs_layout_process(struct nfs4_layoutget *lgp); void pnfs_layoutget_free(struct nfs4_layoutget *lgp); void pnfs_free_lseg_list(struct list_head *tmp_list); void pnfs_destroy_layout(struct nfs_inode *); +void pnfs_destroy_layout_final(struct nfs_inode *); void pnfs_destroy_all_layouts(struct nfs_client *); int pnfs_destroy_layouts_byfsid(struct nfs_client *clp, struct nfs_fsid *fsid, @@ -645,6 +648,10 @@ static inline void pnfs_destroy_layout(struct nfs_inode *nfsi) { } +static inline void pnfs_destroy_layout_final(struct nfs_inode *nfsi) +{ +} + static inline struct pnfs_layout_segment * pnfs_get_lseg(struct pnfs_layout_segment *lseg) { diff --git a/fs/nfs/pnfs_dev.c b/fs/nfs/pnfs_dev.c index e8a07b3f9aaa..ba67906d6b2c 100644 --- a/fs/nfs/pnfs_dev.c +++ b/fs/nfs/pnfs_dev.c @@ -152,7 +152,7 @@ nfs4_get_device_info(struct nfs_server *server, set_bit(NFS_DEVICEID_NOCACHE, &d->flags); out_free_pages: - for (i = 0; i < max_pages; i++) + while (--i >= 0) __free_page(pages[i]); kfree(pages); out_free_pdev: diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index acfb52bc0007..bd6190d794c4 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -555,19 +555,16 @@ out: } EXPORT_SYMBOL_GPL(nfs4_pnfs_ds_add); -static void nfs4_wait_ds_connect(struct nfs4_pnfs_ds *ds) +static int nfs4_wait_ds_connect(struct nfs4_pnfs_ds *ds) { might_sleep(); - wait_on_bit(&ds->ds_state, NFS4DS_CONNECTING, - TASK_KILLABLE); + return wait_on_bit(&ds->ds_state, NFS4DS_CONNECTING, TASK_KILLABLE); } static void nfs4_clear_ds_conn_bit(struct nfs4_pnfs_ds *ds) { smp_mb__before_atomic(); - clear_bit(NFS4DS_CONNECTING, &ds->ds_state); - smp_mb__after_atomic(); - wake_up_bit(&ds->ds_state, NFS4DS_CONNECTING); + clear_and_wake_up_bit(NFS4DS_CONNECTING, &ds->ds_state); } static struct nfs_client *(*get_v3_ds_connect)( @@ -638,7 +635,7 @@ static int _nfs4_pnfs_v3_ds_connect(struct nfs_server *mds_srv, } smp_wmb(); - ds->ds_clp = clp; + WRITE_ONCE(ds->ds_clp, clp); dprintk("%s [new] addr: %s\n", __func__, ds->ds_remotestr); out: return status; @@ -711,7 +708,7 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv, } smp_wmb(); - ds->ds_clp = clp; + WRITE_ONCE(ds->ds_clp, clp); dprintk("%s [new] addr: %s\n", __func__, ds->ds_remotestr); out: return status; @@ -728,30 +725,33 @@ int nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds, { int err; -again: - err = 0; - if (test_and_set_bit(NFS4DS_CONNECTING, &ds->ds_state) == 0) { - if (version == 3) { - err = _nfs4_pnfs_v3_ds_connect(mds_srv, ds, timeo, - retrans); - } else if (version == 4) { - err = _nfs4_pnfs_v4_ds_connect(mds_srv, ds, timeo, - retrans, minor_version); - } else { - dprintk("%s: unsupported DS version %d\n", __func__, - version); - err = -EPROTONOSUPPORT; - } + do { + err = nfs4_wait_ds_connect(ds); + if (err || ds->ds_clp) + goto out; + if (nfs4_test_deviceid_unavailable(devid)) + return -ENODEV; + } while (test_and_set_bit(NFS4DS_CONNECTING, &ds->ds_state) != 0); - nfs4_clear_ds_conn_bit(ds); - } else { - nfs4_wait_ds_connect(ds); + if (ds->ds_clp) + goto connect_done; - /* what was waited on didn't connect AND didn't mark unavail */ - if (!ds->ds_clp && !nfs4_test_deviceid_unavailable(devid)) - goto again; + switch (version) { + case 3: + err = _nfs4_pnfs_v3_ds_connect(mds_srv, ds, timeo, retrans); + break; + case 4: + err = _nfs4_pnfs_v4_ds_connect(mds_srv, ds, timeo, retrans, + minor_version); + break; + default: + dprintk("%s: unsupported DS version %d\n", __func__, version); + err = -EPROTONOSUPPORT; } +connect_done: + nfs4_clear_ds_conn_bit(ds); +out: /* * At this point the ds->ds_clp should be ready, but it might have * hit an error. diff --git a/fs/nfs/write.c b/fs/nfs/write.c index d419d89b91f7..65aaa6eaad2c 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -598,9 +598,8 @@ release_request: static void nfs_write_error_remove_page(struct nfs_page *req) { + SetPageError(req->wb_page); nfs_end_page_writeback(req); - generic_error_remove_page(page_file_mapping(req->wb_page), - req->wb_page); nfs_release_request(req); } @@ -1045,25 +1044,11 @@ nfs_scan_commit_list(struct list_head *src, struct list_head *dst, struct nfs_page *req, *tmp; int ret = 0; -restart: list_for_each_entry_safe(req, tmp, src, wb_list) { kref_get(&req->wb_kref); if (!nfs_lock_request(req)) { - int status; - - /* Prevent deadlock with nfs_lock_and_join_requests */ - if (!list_empty(dst)) { - nfs_release_request(req); - continue; - } - /* Ensure we make progress to prevent livelock */ - mutex_unlock(&NFS_I(cinfo->inode)->commit_mutex); - status = nfs_wait_on_request(req); nfs_release_request(req); - mutex_lock(&NFS_I(cinfo->inode)->commit_mutex); - if (status < 0) - break; - goto restart; + continue; } nfs_request_remove_commit_list(req, cinfo); clear_bit(PG_COMMIT_TO_DS, &req->wb_flags); @@ -1911,6 +1896,7 @@ static int __nfs_commit_inode(struct inode *inode, int how, int may_wait = how & FLUSH_SYNC; int ret, nscan; + how &= ~FLUSH_SYNC; nfs_init_cinfo_from_inode(&cinfo, inode); nfs_commit_begin(cinfo.mds); for (;;) { diff --git a/fs/nfs_common/grace.c b/fs/nfs_common/grace.c index 5be08f02a76b..4f90c444907f 100644 --- a/fs/nfs_common/grace.c +++ b/fs/nfs_common/grace.c @@ -68,10 +68,14 @@ __state_in_grace(struct net *net, bool open) if (!open) return !list_empty(grace_list); + spin_lock(&grace_lock); list_for_each_entry(lm, grace_list, list) { - if (lm->block_opens) + if (lm->block_opens) { + spin_unlock(&grace_lock); return true; + } } + spin_unlock(&grace_lock); return false; } diff --git a/fs/nfsd/blocklayoutxdr.c b/fs/nfsd/blocklayoutxdr.c index 442543304930..2455dc8be18a 100644 --- a/fs/nfsd/blocklayoutxdr.c +++ b/fs/nfsd/blocklayoutxdr.c @@ -82,6 +82,15 @@ nfsd4_block_encode_getdeviceinfo(struct xdr_stream *xdr, int len = sizeof(__be32), ret, i; __be32 *p; + /* + * See paragraph 5 of RFC 8881 S18.40.3. + */ + if (!gdp->gd_maxcount) { + if (xdr_stream_encode_u32(xdr, 0) != XDR_UNIT) + return nfserr_resource; + return nfs_ok; + } + p = xdr_reserve_space(xdr, len + sizeof(__be32)); if (!p) return nfserr_resource; diff --git a/fs/nfsd/flexfilelayoutxdr.c b/fs/nfsd/flexfilelayoutxdr.c index e81d2a5cf381..bb205328e043 100644 --- a/fs/nfsd/flexfilelayoutxdr.c +++ b/fs/nfsd/flexfilelayoutxdr.c @@ -85,6 +85,15 @@ nfsd4_ff_encode_getdeviceinfo(struct xdr_stream *xdr, int addr_len; __be32 *p; + /* + * See paragraph 5 of RFC 8881 S18.40.3. + */ + if (!gdp->gd_maxcount) { + if (xdr_stream_encode_u32(xdr, 0) != XDR_UNIT) + return nfserr_resource; + return nfs_ok; + } + /* len + padding for two strings */ addr_len = 16 + da->netaddr.netid_len + da->netaddr.addr_len; ver_len = 20; diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index c9cf46e0c040..335c95a03c01 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -200,6 +200,11 @@ nfsd3_proc_write(struct svc_rqst *rqstp) (unsigned long long) argp->offset, argp->stable? " stable" : ""); + resp->status = nfserr_fbig; + if (argp->offset > (u64)OFFSET_MAX || + argp->offset + argp->len > (u64)OFFSET_MAX) + return rpc_success; + fh_copy(&resp->fh, &argp->fh); resp->committed = argp->stable; nvecs = svc_fill_write_vector(rqstp, rqstp->rq_arg.pages, diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 83919116d5cb..9f537decdd9c 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -844,19 +844,22 @@ compose_entry_fh(struct nfsd3_readdirres *cd, struct svc_fh *fhp, if (isdotent(name, namlen)) { if (namlen == 2) { dchild = dget_parent(dparent); - /* filesystem root - cannot return filehandle for ".." */ + /* + * Don't return filehandle for ".." if we're at + * the filesystem or export root: + */ if (dchild == dparent) goto out; + if (dparent == exp->ex_path.dentry) + goto out; } else dchild = dget(dparent); } else - dchild = lookup_one_len_unlocked(name, dparent, namlen); + dchild = lookup_positive_unlocked(name, dparent, namlen); if (IS_ERR(dchild)) return rv; if (d_mountpoint(dchild)) goto out; - if (d_really_is_negative(dchild)) - goto out; if (dchild->d_inode->i_ino != ino) goto out; rv = fh_compose(fhp, exp, dchild, &cd->fh); diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 7ee417b685e9..519d994c0c4c 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -800,7 +800,6 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c } else { if (!conn->cb_xprt) return -EINVAL; - clp->cl_cb_conn.cb_xprt = conn->cb_xprt; clp->cl_cb_session = ses; args.bc_xprt = conn->cb_xprt; args.prognumber = clp->cl_cb_session->se_cb_prog; @@ -820,6 +819,9 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c rpc_shutdown_client(client); return PTR_ERR(cred); } + + if (clp->cl_minorversion != 0) + clp->cl_cb_conn.cb_xprt = conn->cb_xprt; clp->cl_cb_client = client; clp->cl_cb_cred = cred; return 0; diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index f4cf1c0793c6..cf81b5bc3e15 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -322,11 +322,11 @@ nfsd4_recall_file_layout(struct nfs4_layout_stateid *ls) if (ls->ls_recalled) goto out_unlock; - ls->ls_recalled = true; - atomic_inc(&ls->ls_stid.sc_file->fi_lo_recalls); if (list_empty(&ls->ls_layouts)) goto out_unlock; + ls->ls_recalled = true; + atomic_inc(&ls->ls_stid.sc_file->fi_lo_recalls); trace_nfsd_layout_recall(&ls->ls_stid.sc_stateid); refcount_inc(&ls->ls_stid.sc_count); diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index f35aa9f88b5e..5ec90b252b6a 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -870,8 +870,8 @@ nfsd4_rename(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, rename->rn_tname, rename->rn_tnamelen); if (status) return status; - set_change_info(&rename->rn_sinfo, &cstate->current_fh); - set_change_info(&rename->rn_tinfo, &cstate->save_fh); + set_change_info(&rename->rn_sinfo, &cstate->save_fh); + set_change_info(&rename->rn_tinfo, &cstate->current_fh); return nfs_ok; } @@ -997,8 +997,9 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, unsigned long cnt; int nvecs; - if (write->wr_offset >= OFFSET_MAX) - return nfserr_inval; + if (write->wr_offset > (u64)OFFSET_MAX || + write->wr_offset + write->wr_buflen > (u64)OFFSET_MAX) + return nfserr_fbig; cnt = write->wr_buflen; trace_nfsd_write_start(rqstp, &cstate->current_fh, diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 655079ae1dd1..5c241e510888 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -975,6 +975,11 @@ hash_delegation_locked(struct nfs4_delegation *dp, struct nfs4_file *fp) return 0; } +static bool delegation_hashed(struct nfs4_delegation *dp) +{ + return !(list_empty(&dp->dl_perfile)); +} + static bool unhash_delegation_locked(struct nfs4_delegation *dp) { @@ -982,7 +987,7 @@ unhash_delegation_locked(struct nfs4_delegation *dp) lockdep_assert_held(&state_lock); - if (list_empty(&dp->dl_perfile)) + if (!delegation_hashed(dp)) return false; dp->dl_stid.sc_type = NFS4_CLOSED_DELEG_STID; @@ -1014,9 +1019,9 @@ static void revoke_delegation(struct nfs4_delegation *dp) WARN_ON(!list_empty(&dp->dl_recall_lru)); if (clp->cl_minorversion) { + spin_lock(&clp->cl_lock); dp->dl_stid.sc_type = NFS4_REVOKED_DELEG_STID; refcount_inc(&dp->dl_stid.sc_count); - spin_lock(&clp->cl_lock); list_add(&dp->dl_recall_lru, &clp->cl_revoked); spin_unlock(&clp->cl_lock); } @@ -3441,8 +3446,10 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp, status = nfserr_clid_inuse; if (client_has_state(old) && !same_creds(&unconf->cl_cred, - &old->cl_cred)) + &old->cl_cred)) { + old = NULL; goto out; + } status = mark_client_expired_locked(old); if (status) { old = NULL; @@ -3912,7 +3919,7 @@ static void nfsd4_cb_recall_prepare(struct nfsd4_callback *cb) * queued for a lease break. Don't queue it again. */ spin_lock(&state_lock); - if (dp->dl_time == 0) { + if (delegation_hashed(dp) && dp->dl_time == 0) { dp->dl_time = get_seconds(); list_add_tail(&dp->dl_recall_lru, &nn->del_recall_lru); } @@ -4991,15 +4998,6 @@ static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid) if (ZERO_STATEID(stateid) || ONE_STATEID(stateid) || CLOSE_STATEID(stateid)) return status; - /* Client debugging aid. */ - if (!same_clid(&stateid->si_opaque.so_clid, &cl->cl_clientid)) { - char addr_str[INET6_ADDRSTRLEN]; - rpc_ntop((struct sockaddr *)&cl->cl_addr, addr_str, - sizeof(addr_str)); - pr_warn_ratelimited("NFSD: client %s testing state ID " - "with incorrect client ID\n", addr_str); - return status; - } spin_lock(&cl->cl_lock); s = find_stateid_locked(cl, stateid); if (!s) diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index db0beefe65ec..33827cdd8066 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -2984,18 +2984,9 @@ nfsd4_encode_dirent_fattr(struct xdr_stream *xdr, struct nfsd4_readdir *cd, __be32 nfserr; int ignore_crossmnt = 0; - dentry = lookup_one_len_unlocked(name, cd->rd_fhp->fh_dentry, namlen); + dentry = lookup_positive_unlocked(name, cd->rd_fhp->fh_dentry, namlen); if (IS_ERR(dentry)) return nfserrno(PTR_ERR(dentry)); - if (d_really_is_negative(dentry)) { - /* - * we're not holding the i_mutex here, so there's - * a window where this directory entry could have gone - * away. - */ - dput(dentry); - return nfserr_noent; - } exp_get(exp); /* @@ -3102,6 +3093,17 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen, case nfserr_noent: xdr_truncate_encode(xdr, start_offset); goto skip_entry; + case nfserr_jukebox: + /* + * The pseudoroot should only display dentries that lead to + * exports. If we get EJUKEBOX here, then we can't tell whether + * this entry should be included. Just fail the whole READDIR + * with NFS4ERR_DELAY in that case, and hope that the situation + * will resolve itself by the client's next attempt. + */ + if (cd->rd_fhp->fh_export->ex_flags & NFSEXP_V4ROOT) + goto fail; + /* fallthrough */ default: /* * If the client requested the RDATTR_ERROR attribute, @@ -3124,15 +3126,18 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen, goto fail; cd->rd_maxcount -= entry_bytes; /* - * RFC 3530 14.2.24 describes rd_dircount as only a "hint", so - * let's always let through the first entry, at least: + * RFC 3530 14.2.24 describes rd_dircount as only a "hint", and + * notes that it could be zero. If it is zero, then the server + * should enforce only the rd_maxcount value. */ - if (!cd->rd_dircount) - goto fail; - name_and_cookie = 4 + 4 * XDR_QUADLEN(namlen) + 8; - if (name_and_cookie > cd->rd_dircount && cd->cookie_offset) - goto fail; - cd->rd_dircount -= min(cd->rd_dircount, name_and_cookie); + if (cd->rd_dircount) { + name_and_cookie = 4 + 4 * XDR_QUADLEN(namlen) + 8; + if (name_and_cookie > cd->rd_dircount && cd->cookie_offset) + goto fail; + cd->rd_dircount -= min(cd->rd_dircount, name_and_cookie); + if (!cd->rd_dircount) + cd->rd_maxcount = 0; + } cd->cookie_offset = cookie_offset; skip_entry: @@ -3389,7 +3394,7 @@ nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_op p = xdr_reserve_space(xdr, 32); if (!p) return nfserr_resource; - *p++ = cpu_to_be32(0); + *p++ = cpu_to_be32(open->op_recall); /* * TODO: space_limit's in delegations @@ -3591,7 +3596,7 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr, if (resp->xdr.buf->page_len && test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags)) { WARN_ON_ONCE(1); - return nfserr_resource; + return nfserr_serverfault; } xdr_commit_encode(xdr); @@ -4121,20 +4126,17 @@ nfsd4_encode_getdeviceinfo(struct nfsd4_compoundres *resp, __be32 nfserr, *p++ = cpu_to_be32(gdev->gd_layout_type); - /* If maxcount is 0 then just update notifications */ - if (gdev->gd_maxcount != 0) { - ops = nfsd4_layout_ops[gdev->gd_layout_type]; - nfserr = ops->encode_getdeviceinfo(xdr, gdev); - if (nfserr) { - /* - * We don't bother to burden the layout drivers with - * enforcing gd_maxcount, just tell the client to - * come back with a bigger buffer if it's not enough. - */ - if (xdr->buf->len + 4 > gdev->gd_maxcount) - goto toosmall; - return nfserr; - } + ops = nfsd4_layout_ops[gdev->gd_layout_type]; + nfserr = ops->encode_getdeviceinfo(xdr, gdev); + if (nfserr) { + /* + * We don't bother to burden the layout drivers with + * enforcing gd_maxcount, just tell the client to + * come back with a bigger buffer if it's not enough. + */ + if (xdr->buf->len + 4 > gdev->gd_maxcount) + goto toosmall; + return nfserr; } if (gdev->gd_notify_types) { diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index cb69660d0779..7af48d306f20 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -347,7 +347,7 @@ static ssize_t write_unlock_fs(struct file *file, char *buf, size_t size) static ssize_t write_filehandle(struct file *file, char *buf, size_t size) { char *dname, *path; - int uninitialized_var(maxsize); + int maxsize; char *mesg = buf; int len; struct auth_domain *dom; @@ -788,7 +788,10 @@ out_close: svc_xprt_put(xprt); } out_err: - nfsd_destroy(net); + if (!list_empty(&nn->nfsd_serv->sv_permsocks)) + nn->nfsd_serv->sv_nrthreads--; + else + nfsd_destroy(net); return err; } diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index 0d20fd161225..bce1cc686eb5 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -118,6 +118,13 @@ done: return nfsd_return_attrs(nfserr, resp); } +/* Obsolete, replaced by MNTPROC_MNT. */ +static __be32 +nfsd_proc_root(struct svc_rqst *rqstp) +{ + return nfs_ok; +} + /* * Look up a path name component * Note: the dentry in the resp->fh may be negative if the file @@ -201,6 +208,13 @@ nfsd_proc_read(struct svc_rqst *rqstp) return fh_getattr(&resp->fh, &resp->stat); } +/* Reserved */ +static __be32 +nfsd_proc_writecache(struct svc_rqst *rqstp) +{ + return nfs_ok; +} + /* * Write data to a file * N.B. After this call resp->fh needs an fh_put @@ -214,7 +228,7 @@ nfsd_proc_write(struct svc_rqst *rqstp) unsigned long cnt = argp->len; unsigned int nvecs; - dprintk("nfsd: WRITE %s %d bytes at %d\n", + dprintk("nfsd: WRITE %s %u bytes at %d\n", SVCFH_fmt(&argp->fh), argp->len, argp->offset); @@ -615,6 +629,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_xdrressize = ST+AT, }, [NFSPROC_ROOT] = { + .pc_func = nfsd_proc_root, .pc_decode = nfssvc_decode_void, .pc_encode = nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_void), @@ -652,6 +667,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_xdrressize = ST+AT+1+NFSSVC_MAXBLKSIZE_V2/4, }, [NFSPROC_WRITECACHE] = { + .pc_func = nfsd_proc_writecache, .pc_decode = nfssvc_decode_void, .pc_encode = nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_void), diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 89cb484f1cfb..ad38633392a0 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -417,8 +417,7 @@ static void nfsd_last_thread(struct svc_serv *serv, struct net *net) return; nfsd_shutdown_net(net); - printk(KERN_WARNING "nfsd: last server has exited, flushing export " - "cache\n"); + pr_info("nfsd: last server has exited, flushing export cache\n"); nfsd_export_flush(net); } diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h index 80933e4334d8..5b2ef30a8ac0 100644 --- a/fs/nfsd/trace.h +++ b/fs/nfsd/trace.h @@ -53,14 +53,14 @@ TRACE_EVENT(nfsd_compound_status, DECLARE_EVENT_CLASS(nfsd_io_class, TP_PROTO(struct svc_rqst *rqstp, struct svc_fh *fhp, - loff_t offset, - unsigned long len), + u64 offset, + u32 len), TP_ARGS(rqstp, fhp, offset, len), TP_STRUCT__entry( __field(u32, xid) __field(u32, fh_hash) - __field(loff_t, offset) - __field(unsigned long, len) + __field(u64, offset) + __field(u32, len) ), TP_fast_assign( __entry->xid = be32_to_cpu(rqstp->rq_xid); @@ -68,7 +68,7 @@ DECLARE_EVENT_CLASS(nfsd_io_class, __entry->offset = offset; __entry->len = len; ), - TP_printk("xid=0x%08x fh_hash=0x%08x offset=%lld len=%lu", + TP_printk("xid=0x%08x fh_hash=0x%08x offset=%llu len=%u", __entry->xid, __entry->fh_hash, __entry->offset, __entry->len) ) @@ -77,8 +77,8 @@ DECLARE_EVENT_CLASS(nfsd_io_class, DEFINE_EVENT(nfsd_io_class, nfsd_##name, \ TP_PROTO(struct svc_rqst *rqstp, \ struct svc_fh *fhp, \ - loff_t offset, \ - unsigned long len), \ + u64 offset, \ + u32 len), \ TP_ARGS(rqstp, fhp, offset, len)) DEFINE_NFSD_IO_EVENT(read_start); diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 28e7f86c8c94..a7231d17e359 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -1691,6 +1691,12 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen, if (!flen || isdotent(fname, flen) || !tlen || isdotent(tname, tlen)) goto out; + err = (rqstp->rq_vers == 2) ? nfserr_acces : nfserr_xdev; + if (ffhp->fh_export->ex_path.mnt != tfhp->fh_export->ex_path.mnt) + goto out; + if (ffhp->fh_export->ex_path.dentry != tfhp->fh_export->ex_path.dentry) + goto out; + host_err = fh_want_write(ffhp); if (host_err) { err = nfserrno(host_err); @@ -1724,12 +1730,6 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen, if (ndentry == trap) goto out_dput_new; - host_err = -EXDEV; - if (ffhp->fh_export->ex_path.mnt != tfhp->fh_export->ex_path.mnt) - goto out_dput_new; - if (ffhp->fh_export->ex_path.dentry != tfhp->fh_export->ex_path.dentry) - goto out_dput_new; - host_err = vfs_rename(fdir, odentry, tdir, ndentry, NULL, 0); if (!host_err) { host_err = commit_metadata(tfhp); diff --git a/fs/nfsd/xdr.h b/fs/nfsd/xdr.h index ea7cca3a64b7..6251d8754c82 100644 --- a/fs/nfsd/xdr.h +++ b/fs/nfsd/xdr.h @@ -33,7 +33,7 @@ struct nfsd_readargs { struct nfsd_writeargs { svc_fh fh; __u32 offset; - int len; + __u32 len; struct kvec first; }; diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c index 235b959fc2b3..bbd82f650e93 100644 --- a/fs/nilfs2/alloc.c +++ b/fs/nilfs2/alloc.c @@ -205,7 +205,8 @@ static int nilfs_palloc_get_block(struct inode *inode, unsigned long blkoff, int ret; spin_lock(lock); - if (prev->bh && blkoff == prev->blkoff) { + if (prev->bh && blkoff == prev->blkoff && + likely(buffer_uptodate(prev->bh))) { get_bh(prev->bh); *bhp = prev->bh; spin_unlock(lock); diff --git a/fs/nilfs2/bmap.c b/fs/nilfs2/bmap.c index fb5a9a8a13cf..2ba57e4b4f0a 100644 --- a/fs/nilfs2/bmap.c +++ b/fs/nilfs2/bmap.c @@ -67,20 +67,28 @@ int nilfs_bmap_lookup_at_level(struct nilfs_bmap *bmap, __u64 key, int level, down_read(&bmap->b_sem); ret = bmap->b_ops->bop_lookup(bmap, key, level, ptrp); - if (ret < 0) { - ret = nilfs_bmap_convert_error(bmap, __func__, ret); + if (ret < 0) goto out; - } + if (NILFS_BMAP_USE_VBN(bmap)) { ret = nilfs_dat_translate(nilfs_bmap_get_dat(bmap), *ptrp, &blocknr); if (!ret) *ptrp = blocknr; + else if (ret == -ENOENT) { + /* + * If there was no valid entry in DAT for the block + * address obtained by b_ops->bop_lookup, then pass + * internal code -EINVAL to nilfs_bmap_convert_error + * to treat it as metadata corruption. + */ + ret = -EINVAL; + } } out: up_read(&bmap->b_sem); - return ret; + return nilfs_bmap_convert_error(bmap, __func__, ret); } int nilfs_bmap_lookup_contig(struct nilfs_bmap *bmap, __u64 key, __u64 *ptrp, diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c index ebb24a314f43..677ff78d54fb 100644 --- a/fs/nilfs2/btnode.c +++ b/fs/nilfs2/btnode.c @@ -20,6 +20,23 @@ #include "page.h" #include "btnode.h" + +/** + * nilfs_init_btnc_inode - initialize B-tree node cache inode + * @btnc_inode: inode to be initialized + * + * nilfs_init_btnc_inode() sets up an inode for B-tree node cache. + */ +void nilfs_init_btnc_inode(struct inode *btnc_inode) +{ + struct nilfs_inode_info *ii = NILFS_I(btnc_inode); + + btnc_inode->i_mode = S_IFREG; + ii->i_flags = 0; + memset(&ii->i_bmap_data, 0, sizeof(struct nilfs_bmap)); + mapping_set_gfp_mask(btnc_inode->i_mapping, GFP_NOFS); +} + void nilfs_btnode_cache_clear(struct address_space *btnc) { invalidate_mapping_pages(btnc, 0, -1); @@ -29,7 +46,7 @@ void nilfs_btnode_cache_clear(struct address_space *btnc) struct buffer_head * nilfs_btnode_create_block(struct address_space *btnc, __u64 blocknr) { - struct inode *inode = NILFS_BTNC_I(btnc); + struct inode *inode = btnc->host; struct buffer_head *bh; bh = nilfs_grab_buffer(inode, btnc, blocknr, BIT(BH_NILFS_Node)); @@ -57,7 +74,7 @@ int nilfs_btnode_submit_block(struct address_space *btnc, __u64 blocknr, struct buffer_head **pbh, sector_t *submit_ptr) { struct buffer_head *bh; - struct inode *inode = NILFS_BTNC_I(btnc); + struct inode *inode = btnc->host; struct page *page; int err; @@ -157,7 +174,7 @@ int nilfs_btnode_prepare_change_key(struct address_space *btnc, struct nilfs_btnode_chkey_ctxt *ctxt) { struct buffer_head *obh, *nbh; - struct inode *inode = NILFS_BTNC_I(btnc); + struct inode *inode = btnc->host; __u64 oldkey = ctxt->oldkey, newkey = ctxt->newkey; int err; @@ -278,6 +295,14 @@ void nilfs_btnode_abort_change_key(struct address_space *btnc, radix_tree_delete(&btnc->i_pages, newkey); xa_unlock_irq(&btnc->i_pages); unlock_page(ctxt->bh->b_page); - } else - brelse(nbh); + } else { + /* + * When canceling a buffer that a prepare operation has + * allocated to copy a node block to another location, use + * nilfs_btnode_delete() to initialize and release the buffer + * so that the buffer flags will not be in an inconsistent + * state when it is reallocated. + */ + nilfs_btnode_delete(nbh); + } } diff --git a/fs/nilfs2/btnode.h b/fs/nilfs2/btnode.h index 0f88dbc9bcb3..05ab64d354dc 100644 --- a/fs/nilfs2/btnode.h +++ b/fs/nilfs2/btnode.h @@ -30,6 +30,7 @@ struct nilfs_btnode_chkey_ctxt { struct buffer_head *newbh; }; +void nilfs_init_btnc_inode(struct inode *btnc_inode); void nilfs_btnode_cache_clear(struct address_space *); struct buffer_head *nilfs_btnode_create_block(struct address_space *btnc, __u64 blocknr); diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index 23e043eca237..a0e37530dcf3 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -58,7 +58,8 @@ static void nilfs_btree_free_path(struct nilfs_btree_path *path) static int nilfs_btree_get_new_block(const struct nilfs_bmap *btree, __u64 ptr, struct buffer_head **bhp) { - struct address_space *btnc = &NILFS_BMAP_I(btree)->i_btnode_cache; + struct inode *btnc_inode = NILFS_BMAP_I(btree)->i_assoc_inode; + struct address_space *btnc = btnc_inode->i_mapping; struct buffer_head *bh; bh = nilfs_btnode_create_block(btnc, ptr); @@ -470,7 +471,8 @@ static int __nilfs_btree_get_block(const struct nilfs_bmap *btree, __u64 ptr, struct buffer_head **bhp, const struct nilfs_btree_readahead_info *ra) { - struct address_space *btnc = &NILFS_BMAP_I(btree)->i_btnode_cache; + struct inode *btnc_inode = NILFS_BMAP_I(btree)->i_assoc_inode; + struct address_space *btnc = btnc_inode->i_mapping; struct buffer_head *bh, *ra_bh; sector_t submit_ptr = 0; int ret; @@ -478,9 +480,18 @@ static int __nilfs_btree_get_block(const struct nilfs_bmap *btree, __u64 ptr, ret = nilfs_btnode_submit_block(btnc, ptr, 0, REQ_OP_READ, 0, &bh, &submit_ptr); if (ret) { - if (ret != -EEXIST) - return ret; - goto out_check; + if (likely(ret == -EEXIST)) + goto out_check; + if (ret == -ENOENT) { + /* + * Block address translation failed due to invalid + * value of 'ptr'. In this case, return internal code + * -EINVAL (broken bmap) to notify bmap layer of fatal + * metadata corruption. + */ + ret = -EINVAL; + } + return ret; } if (ra) { @@ -1742,6 +1753,10 @@ nilfs_btree_prepare_convert_and_insert(struct nilfs_bmap *btree, __u64 key, dat = nilfs_bmap_get_dat(btree); } + ret = nilfs_attach_btree_node_cache(&NILFS_BMAP_I(btree)->vfs_inode); + if (ret < 0) + return ret; + ret = nilfs_bmap_prepare_alloc_ptr(btree, dreq, dat); if (ret < 0) return ret; @@ -1914,7 +1929,7 @@ static int nilfs_btree_prepare_update_v(struct nilfs_bmap *btree, path[level].bp_ctxt.newkey = path[level].bp_newreq.bpr_ptr; path[level].bp_ctxt.bh = path[level].bp_bh; ret = nilfs_btnode_prepare_change_key( - &NILFS_BMAP_I(btree)->i_btnode_cache, + NILFS_BMAP_I(btree)->i_assoc_inode->i_mapping, &path[level].bp_ctxt); if (ret < 0) { nilfs_dat_abort_update(dat, @@ -1940,7 +1955,7 @@ static void nilfs_btree_commit_update_v(struct nilfs_bmap *btree, if (buffer_nilfs_node(path[level].bp_bh)) { nilfs_btnode_commit_change_key( - &NILFS_BMAP_I(btree)->i_btnode_cache, + NILFS_BMAP_I(btree)->i_assoc_inode->i_mapping, &path[level].bp_ctxt); path[level].bp_bh = path[level].bp_ctxt.bh; } @@ -1959,7 +1974,7 @@ static void nilfs_btree_abort_update_v(struct nilfs_bmap *btree, &path[level].bp_newreq.bpr_req); if (buffer_nilfs_node(path[level].bp_bh)) nilfs_btnode_abort_change_key( - &NILFS_BMAP_I(btree)->i_btnode_cache, + NILFS_BMAP_I(btree)->i_assoc_inode->i_mapping, &path[level].bp_ctxt); } @@ -2135,7 +2150,8 @@ static void nilfs_btree_add_dirty_buffer(struct nilfs_bmap *btree, static void nilfs_btree_lookup_dirty_buffers(struct nilfs_bmap *btree, struct list_head *listp) { - struct address_space *btcache = &NILFS_BMAP_I(btree)->i_btnode_cache; + struct inode *btnc_inode = NILFS_BMAP_I(btree)->i_assoc_inode; + struct address_space *btcache = btnc_inode->i_mapping; struct list_head lists[NILFS_BTREE_LEVEL_MAX]; struct pagevec pvec; struct buffer_head *bh, *head; @@ -2189,12 +2205,12 @@ static int nilfs_btree_assign_p(struct nilfs_bmap *btree, path[level].bp_ctxt.newkey = blocknr; path[level].bp_ctxt.bh = *bh; ret = nilfs_btnode_prepare_change_key( - &NILFS_BMAP_I(btree)->i_btnode_cache, + NILFS_BMAP_I(btree)->i_assoc_inode->i_mapping, &path[level].bp_ctxt); if (ret < 0) return ret; nilfs_btnode_commit_change_key( - &NILFS_BMAP_I(btree)->i_btnode_cache, + NILFS_BMAP_I(btree)->i_assoc_inode->i_mapping, &path[level].bp_ctxt); *bh = path[level].bp_ctxt.bh; } @@ -2399,6 +2415,10 @@ int nilfs_btree_init(struct nilfs_bmap *bmap) if (nilfs_btree_root_broken(nilfs_btree_get_root(bmap), bmap->b_inode)) ret = -EIO; + else + ret = nilfs_attach_btree_node_cache( + &NILFS_BMAP_I(bmap)->vfs_inode); + return ret; } diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c index 6f4066636be9..e2a5320f2718 100644 --- a/fs/nilfs2/dat.c +++ b/fs/nilfs2/dat.c @@ -111,6 +111,13 @@ static void nilfs_dat_commit_free(struct inode *dat, kunmap_atomic(kaddr); nilfs_dat_commit_entry(dat, req); + + if (unlikely(req->pr_desc_bh == NULL || req->pr_bitmap_bh == NULL)) { + nilfs_error(dat->i_sb, + "state inconsistency probably due to duplicate use of vblocknr = %llu", + (unsigned long long)req->pr_entry_nr); + return; + } nilfs_palloc_commit_free_entry(dat, req); } @@ -497,7 +504,9 @@ int nilfs_dat_read(struct super_block *sb, size_t entry_size, di = NILFS_DAT_I(dat); lockdep_set_class(&di->mi.mi_sem, &dat_lock_key); nilfs_palloc_setup_cache(dat, &di->palloc_cache); - nilfs_mdt_setup_shadow_map(dat, &di->shadow); + err = nilfs_mdt_setup_shadow_map(dat, &di->shadow); + if (err) + goto failed; err = nilfs_read_inode_common(dat, raw_inode); if (err) diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c index aa3c328ee189..cef46650102e 100644 --- a/fs/nilfs2/gcinode.c +++ b/fs/nilfs2/gcinode.c @@ -73,10 +73,8 @@ int nilfs_gccache_submit_read_data(struct inode *inode, sector_t blkoff, struct the_nilfs *nilfs = inode->i_sb->s_fs_info; err = nilfs_dat_translate(nilfs->ns_dat, vbn, &pbn); - if (unlikely(err)) { /* -EIO, -ENOMEM, -ENOENT */ - brelse(bh); + if (unlikely(err)) /* -EIO, -ENOMEM, -ENOENT */ goto failed; - } } lock_buffer(bh); @@ -102,6 +100,8 @@ int nilfs_gccache_submit_read_data(struct inode *inode, sector_t blkoff, failed: unlock_page(bh->b_page); put_page(bh->b_page); + if (unlikely(err)) + brelse(bh); return err; } @@ -126,9 +126,10 @@ int nilfs_gccache_submit_read_data(struct inode *inode, sector_t blkoff, int nilfs_gccache_submit_read_node(struct inode *inode, sector_t pbn, __u64 vbn, struct buffer_head **out_bh) { + struct inode *btnc_inode = NILFS_I(inode)->i_assoc_inode; int ret; - ret = nilfs_btnode_submit_block(&NILFS_I(inode)->i_btnode_cache, + ret = nilfs_btnode_submit_block(btnc_inode->i_mapping, vbn ? : pbn, pbn, REQ_OP_READ, 0, out_bh, &pbn); if (ret == -EEXIST) /* internal code (cache hit) */ @@ -170,7 +171,7 @@ int nilfs_init_gcinode(struct inode *inode) ii->i_flags = 0; nilfs_bmap_init_gc(ii->i_bmap); - return 0; + return nilfs_attach_btree_node_cache(inode); } /** @@ -185,7 +186,7 @@ void nilfs_remove_all_gcinodes(struct the_nilfs *nilfs) ii = list_first_entry(head, struct nilfs_inode_info, i_dirty); list_del_init(&ii->i_dirty); truncate_inode_pages(&ii->vfs_inode.i_data, 0); - nilfs_btnode_cache_clear(&ii->i_btnode_cache); + nilfs_btnode_cache_clear(ii->i_assoc_inode->i_mapping); iput(&ii->vfs_inode); } } diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 671085512e0f..ea94dc21af0c 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -28,12 +28,16 @@ * @cno: checkpoint number * @root: pointer on NILFS root object (mounted checkpoint) * @for_gc: inode for GC flag + * @for_btnc: inode for B-tree node cache flag + * @for_shadow: inode for shadowed page cache flag */ struct nilfs_iget_args { u64 ino; __u64 cno; struct nilfs_root *root; - int for_gc; + bool for_gc; + bool for_btnc; + bool for_shadow; }; static int nilfs_iget_test(struct inode *inode, void *opaque); @@ -322,7 +326,8 @@ static int nilfs_insert_inode_locked(struct inode *inode, unsigned long ino) { struct nilfs_iget_args args = { - .ino = ino, .root = root, .cno = 0, .for_gc = 0 + .ino = ino, .root = root, .cno = 0, .for_gc = false, + .for_btnc = false, .for_shadow = false }; return insert_inode_locked4(inode, ino, nilfs_iget_test, &args); @@ -335,6 +340,7 @@ struct inode *nilfs_new_inode(struct inode *dir, umode_t mode) struct inode *inode; struct nilfs_inode_info *ii; struct nilfs_root *root; + struct buffer_head *bh; int err = -ENOMEM; ino_t ino; @@ -350,11 +356,26 @@ struct inode *nilfs_new_inode(struct inode *dir, umode_t mode) ii->i_state = BIT(NILFS_I_NEW); ii->i_root = root; - err = nilfs_ifile_create_inode(root->ifile, &ino, &ii->i_bh); + err = nilfs_ifile_create_inode(root->ifile, &ino, &bh); if (unlikely(err)) goto failed_ifile_create_inode; /* reference count of i_bh inherits from nilfs_mdt_read_block() */ + if (unlikely(ino < NILFS_USER_INO)) { + nilfs_msg(sb, KERN_WARNING, + "inode bitmap is inconsistent for reserved inodes"); + do { + brelse(bh); + err = nilfs_ifile_create_inode(root->ifile, &ino, &bh); + if (unlikely(err)) + goto failed_ifile_create_inode; + } while (ino < NILFS_USER_INO); + + nilfs_msg(sb, KERN_INFO, + "repaired inode bitmap for reserved inodes"); + } + ii->i_bh = bh; + atomic64_inc(&root->inodes_count); inode_init_owner(inode, dir, mode); inode->i_ino = ino; @@ -446,6 +467,8 @@ int nilfs_read_inode_common(struct inode *inode, inode->i_atime.tv_nsec = le32_to_cpu(raw_inode->i_mtime_nsec); inode->i_ctime.tv_nsec = le32_to_cpu(raw_inode->i_ctime_nsec); inode->i_mtime.tv_nsec = le32_to_cpu(raw_inode->i_mtime_nsec); + if (nilfs_is_metadata_file_inode(inode) && !S_ISREG(inode->i_mode)) + return -EIO; /* this inode is for metadata and corrupted */ if (inode->i_nlink == 0) return -ESTALE; /* this inode is deleted */ @@ -534,6 +557,19 @@ static int nilfs_iget_test(struct inode *inode, void *opaque) return 0; ii = NILFS_I(inode); + if (test_bit(NILFS_I_BTNC, &ii->i_state)) { + if (!args->for_btnc) + return 0; + } else if (args->for_btnc) { + return 0; + } + if (test_bit(NILFS_I_SHADOW, &ii->i_state)) { + if (!args->for_shadow) + return 0; + } else if (args->for_shadow) { + return 0; + } + if (!test_bit(NILFS_I_GCINODE, &ii->i_state)) return !args->for_gc; @@ -545,15 +581,17 @@ static int nilfs_iget_set(struct inode *inode, void *opaque) struct nilfs_iget_args *args = opaque; inode->i_ino = args->ino; - if (args->for_gc) { + NILFS_I(inode)->i_cno = args->cno; + NILFS_I(inode)->i_root = args->root; + if (args->root && args->ino == NILFS_ROOT_INO) + nilfs_get_root(args->root); + + if (args->for_gc) NILFS_I(inode)->i_state = BIT(NILFS_I_GCINODE); - NILFS_I(inode)->i_cno = args->cno; - NILFS_I(inode)->i_root = NULL; - } else { - if (args->root && args->ino == NILFS_ROOT_INO) - nilfs_get_root(args->root); - NILFS_I(inode)->i_root = args->root; - } + if (args->for_btnc) + NILFS_I(inode)->i_state |= BIT(NILFS_I_BTNC); + if (args->for_shadow) + NILFS_I(inode)->i_state |= BIT(NILFS_I_SHADOW); return 0; } @@ -561,7 +599,8 @@ struct inode *nilfs_ilookup(struct super_block *sb, struct nilfs_root *root, unsigned long ino) { struct nilfs_iget_args args = { - .ino = ino, .root = root, .cno = 0, .for_gc = 0 + .ino = ino, .root = root, .cno = 0, .for_gc = false, + .for_btnc = false, .for_shadow = false }; return ilookup5(sb, ino, nilfs_iget_test, &args); @@ -571,7 +610,8 @@ struct inode *nilfs_iget_locked(struct super_block *sb, struct nilfs_root *root, unsigned long ino) { struct nilfs_iget_args args = { - .ino = ino, .root = root, .cno = 0, .for_gc = 0 + .ino = ino, .root = root, .cno = 0, .for_gc = false, + .for_btnc = false, .for_shadow = false }; return iget5_locked(sb, ino, nilfs_iget_test, nilfs_iget_set, &args); @@ -602,7 +642,8 @@ struct inode *nilfs_iget_for_gc(struct super_block *sb, unsigned long ino, __u64 cno) { struct nilfs_iget_args args = { - .ino = ino, .root = NULL, .cno = cno, .for_gc = 1 + .ino = ino, .root = NULL, .cno = cno, .for_gc = true, + .for_btnc = false, .for_shadow = false }; struct inode *inode; int err; @@ -622,6 +663,113 @@ struct inode *nilfs_iget_for_gc(struct super_block *sb, unsigned long ino, return inode; } +/** + * nilfs_attach_btree_node_cache - attach a B-tree node cache to the inode + * @inode: inode object + * + * nilfs_attach_btree_node_cache() attaches a B-tree node cache to @inode, + * or does nothing if the inode already has it. This function allocates + * an additional inode to maintain page cache of B-tree nodes one-on-one. + * + * Return Value: On success, 0 is returned. On errors, one of the following + * negative error code is returned. + * + * %-ENOMEM - Insufficient memory available. + */ +int nilfs_attach_btree_node_cache(struct inode *inode) +{ + struct nilfs_inode_info *ii = NILFS_I(inode); + struct inode *btnc_inode; + struct nilfs_iget_args args; + + if (ii->i_assoc_inode) + return 0; + + args.ino = inode->i_ino; + args.root = ii->i_root; + args.cno = ii->i_cno; + args.for_gc = test_bit(NILFS_I_GCINODE, &ii->i_state) != 0; + args.for_btnc = true; + args.for_shadow = test_bit(NILFS_I_SHADOW, &ii->i_state) != 0; + + btnc_inode = iget5_locked(inode->i_sb, inode->i_ino, nilfs_iget_test, + nilfs_iget_set, &args); + if (unlikely(!btnc_inode)) + return -ENOMEM; + if (btnc_inode->i_state & I_NEW) { + nilfs_init_btnc_inode(btnc_inode); + unlock_new_inode(btnc_inode); + } + NILFS_I(btnc_inode)->i_assoc_inode = inode; + NILFS_I(btnc_inode)->i_bmap = ii->i_bmap; + ii->i_assoc_inode = btnc_inode; + + return 0; +} + +/** + * nilfs_detach_btree_node_cache - detach the B-tree node cache from the inode + * @inode: inode object + * + * nilfs_detach_btree_node_cache() detaches the B-tree node cache and its + * holder inode bound to @inode, or does nothing if @inode doesn't have it. + */ +void nilfs_detach_btree_node_cache(struct inode *inode) +{ + struct nilfs_inode_info *ii = NILFS_I(inode); + struct inode *btnc_inode = ii->i_assoc_inode; + + if (btnc_inode) { + NILFS_I(btnc_inode)->i_assoc_inode = NULL; + ii->i_assoc_inode = NULL; + iput(btnc_inode); + } +} + +/** + * nilfs_iget_for_shadow - obtain inode for shadow mapping + * @inode: inode object that uses shadow mapping + * + * nilfs_iget_for_shadow() allocates a pair of inodes that holds page + * caches for shadow mapping. The page cache for data pages is set up + * in one inode and the one for b-tree node pages is set up in the + * other inode, which is attached to the former inode. + * + * Return Value: On success, a pointer to the inode for data pages is + * returned. On errors, one of the following negative error code is returned + * in a pointer type. + * + * %-ENOMEM - Insufficient memory available. + */ +struct inode *nilfs_iget_for_shadow(struct inode *inode) +{ + struct nilfs_iget_args args = { + .ino = inode->i_ino, .root = NULL, .cno = 0, .for_gc = false, + .for_btnc = false, .for_shadow = true + }; + struct inode *s_inode; + int err; + + s_inode = iget5_locked(inode->i_sb, inode->i_ino, nilfs_iget_test, + nilfs_iget_set, &args); + if (unlikely(!s_inode)) + return ERR_PTR(-ENOMEM); + if (!(s_inode->i_state & I_NEW)) + return inode; + + NILFS_I(s_inode)->i_flags = 0; + memset(NILFS_I(s_inode)->i_bmap, 0, sizeof(struct nilfs_bmap)); + mapping_set_gfp_mask(s_inode->i_mapping, GFP_NOFS); + + err = nilfs_attach_btree_node_cache(s_inode); + if (unlikely(err)) { + iget_failed(s_inode); + return ERR_PTR(err); + } + unlock_new_inode(s_inode); + return s_inode; +} + void nilfs_write_inode_common(struct inode *inode, struct nilfs_inode *raw_inode, int has_bmap) { @@ -770,7 +918,8 @@ static void nilfs_clear_inode(struct inode *inode) if (test_bit(NILFS_I_BMAP, &ii->i_state)) nilfs_bmap_clear(ii->i_bmap); - nilfs_btnode_cache_clear(&ii->i_btnode_cache); + if (!test_bit(NILFS_I_BTNC, &ii->i_state)) + nilfs_detach_btree_node_cache(inode); if (ii->i_root && inode->i_ino == NILFS_ROOT_INO) nilfs_put_root(ii->i_root); @@ -781,6 +930,7 @@ void nilfs_evict_inode(struct inode *inode) struct nilfs_transaction_info ti; struct super_block *sb = inode->i_sb; struct nilfs_inode_info *ii = NILFS_I(inode); + struct the_nilfs *nilfs; int ret; if (inode->i_nlink || !ii->i_root || unlikely(is_bad_inode(inode))) { @@ -793,6 +943,23 @@ void nilfs_evict_inode(struct inode *inode) truncate_inode_pages_final(&inode->i_data); + nilfs = sb->s_fs_info; + if (unlikely(sb_rdonly(sb) || !nilfs->ns_writer)) { + /* + * If this inode is about to be disposed after the file system + * has been degraded to read-only due to file system corruption + * or after the writer has been detached, do not make any + * changes that cause writes, just clear it. + * Do this check after read-locking ns_segctor_sem by + * nilfs_transaction_begin() in order to avoid a race with + * the writer detach operation. + */ + clear_inode(inode); + nilfs_clear_inode(inode); + nilfs_transaction_abort(sb); + return; + } + /* TODO: some of the following operations may fail. */ nilfs_truncate_bmap(ii, 0); nilfs_mark_inode_dirty(inode); @@ -869,7 +1036,7 @@ int nilfs_load_inode_block(struct inode *inode, struct buffer_head **pbh) int err; spin_lock(&nilfs->ns_inode_lock); - if (ii->i_bh == NULL) { + if (ii->i_bh == NULL || unlikely(!buffer_uptodate(ii->i_bh))) { spin_unlock(&nilfs->ns_inode_lock); err = nilfs_ifile_get_inode_block(ii->i_root->ifile, inode->i_ino, pbh); @@ -878,7 +1045,10 @@ int nilfs_load_inode_block(struct inode *inode, struct buffer_head **pbh) spin_lock(&nilfs->ns_inode_lock); if (ii->i_bh == NULL) ii->i_bh = *pbh; - else { + else if (unlikely(!buffer_uptodate(ii->i_bh))) { + __brelse(ii->i_bh); + ii->i_bh = *pbh; + } else { brelse(*pbh); *pbh = ii->i_bh; } @@ -945,9 +1115,17 @@ int nilfs_set_file_dirty(struct inode *inode, unsigned int nr_dirty) int __nilfs_mark_inode_dirty(struct inode *inode, int flags) { + struct the_nilfs *nilfs = inode->i_sb->s_fs_info; struct buffer_head *ibh; int err; + /* + * Do not dirty inodes after the log writer has been detached + * and its nilfs_root struct has been freed. + */ + if (unlikely(nilfs_purging(nilfs))) + return 0; + err = nilfs_load_inode_block(inode, &ibh); if (unlikely(err)) { nilfs_msg(inode->i_sb, KERN_WARNING, diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c index 9b96d79eea6c..dfb2083b8ce1 100644 --- a/fs/nilfs2/ioctl.c +++ b/fs/nilfs2/ioctl.c @@ -70,7 +70,7 @@ static int nilfs_ioctl_wrap_copy(struct the_nilfs *nilfs, if (argv->v_index > ~(__u64)0 - argv->v_nmembs) return -EINVAL; - buf = (void *)__get_free_pages(GFP_NOFS, 0); + buf = (void *)get_zeroed_page(GFP_NOFS); if (unlikely(!buf)) return -ENOMEM; maxmembs = PAGE_SIZE / argv->v_size; @@ -1135,7 +1135,14 @@ static int nilfs_ioctl_set_alloc_range(struct inode *inode, void __user *argp) minseg = range[0] + segbytes - 1; do_div(minseg, segbytes); + + if (range[1] < 4096) + goto out; + maxseg = NILFS_SB2_OFFSET_BYTES(range[1]); + if (maxseg < segbytes) + goto out; + do_div(maxseg, segbytes); maxseg--; diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c index 700870a92bc4..7c9055d767d1 100644 --- a/fs/nilfs2/mdt.c +++ b/fs/nilfs2/mdt.c @@ -469,9 +469,18 @@ int nilfs_mdt_init(struct inode *inode, gfp_t gfp_mask, size_t objsz) void nilfs_mdt_clear(struct inode *inode) { struct nilfs_mdt_info *mdi = NILFS_MDT(inode); + struct nilfs_shadow_map *shadow = mdi->mi_shadow; if (mdi->mi_palloc_cache) nilfs_palloc_destroy_cache(inode); + + if (shadow) { + struct inode *s_inode = shadow->inode; + + shadow->inode = NULL; + iput(s_inode); + mdi->mi_shadow = NULL; + } } /** @@ -505,12 +514,15 @@ int nilfs_mdt_setup_shadow_map(struct inode *inode, struct nilfs_shadow_map *shadow) { struct nilfs_mdt_info *mi = NILFS_MDT(inode); + struct inode *s_inode; INIT_LIST_HEAD(&shadow->frozen_buffers); - address_space_init_once(&shadow->frozen_data); - nilfs_mapping_init(&shadow->frozen_data, inode); - address_space_init_once(&shadow->frozen_btnodes); - nilfs_mapping_init(&shadow->frozen_btnodes, inode); + + s_inode = nilfs_iget_for_shadow(inode); + if (IS_ERR(s_inode)) + return PTR_ERR(s_inode); + + shadow->inode = s_inode; mi->mi_shadow = shadow; return 0; } @@ -524,14 +536,15 @@ int nilfs_mdt_save_to_shadow_map(struct inode *inode) struct nilfs_mdt_info *mi = NILFS_MDT(inode); struct nilfs_inode_info *ii = NILFS_I(inode); struct nilfs_shadow_map *shadow = mi->mi_shadow; + struct inode *s_inode = shadow->inode; int ret; - ret = nilfs_copy_dirty_pages(&shadow->frozen_data, inode->i_mapping); + ret = nilfs_copy_dirty_pages(s_inode->i_mapping, inode->i_mapping); if (ret) goto out; - ret = nilfs_copy_dirty_pages(&shadow->frozen_btnodes, - &ii->i_btnode_cache); + ret = nilfs_copy_dirty_pages(NILFS_I(s_inode)->i_assoc_inode->i_mapping, + ii->i_assoc_inode->i_mapping); if (ret) goto out; @@ -547,7 +560,7 @@ int nilfs_mdt_freeze_buffer(struct inode *inode, struct buffer_head *bh) struct page *page; int blkbits = inode->i_blkbits; - page = grab_cache_page(&shadow->frozen_data, bh->b_page->index); + page = grab_cache_page(shadow->inode->i_mapping, bh->b_page->index); if (!page) return -ENOMEM; @@ -579,7 +592,7 @@ nilfs_mdt_get_frozen_buffer(struct inode *inode, struct buffer_head *bh) struct page *page; int n; - page = find_lock_page(&shadow->frozen_data, bh->b_page->index); + page = find_lock_page(shadow->inode->i_mapping, bh->b_page->index); if (page) { if (page_has_buffers(page)) { n = bh_offset(bh) >> inode->i_blkbits; @@ -620,10 +633,11 @@ void nilfs_mdt_restore_from_shadow_map(struct inode *inode) nilfs_palloc_clear_cache(inode); nilfs_clear_dirty_pages(inode->i_mapping, true); - nilfs_copy_back_pages(inode->i_mapping, &shadow->frozen_data); + nilfs_copy_back_pages(inode->i_mapping, shadow->inode->i_mapping); - nilfs_clear_dirty_pages(&ii->i_btnode_cache, true); - nilfs_copy_back_pages(&ii->i_btnode_cache, &shadow->frozen_btnodes); + nilfs_clear_dirty_pages(ii->i_assoc_inode->i_mapping, true); + nilfs_copy_back_pages(ii->i_assoc_inode->i_mapping, + NILFS_I(shadow->inode)->i_assoc_inode->i_mapping); nilfs_bmap_restore(ii->i_bmap, &shadow->bmap_store); @@ -638,10 +652,11 @@ void nilfs_mdt_clear_shadow_map(struct inode *inode) { struct nilfs_mdt_info *mi = NILFS_MDT(inode); struct nilfs_shadow_map *shadow = mi->mi_shadow; + struct inode *shadow_btnc_inode = NILFS_I(shadow->inode)->i_assoc_inode; down_write(&mi->mi_sem); nilfs_release_frozen_buffers(shadow); - truncate_inode_pages(&shadow->frozen_data, 0); - truncate_inode_pages(&shadow->frozen_btnodes, 0); + truncate_inode_pages(shadow->inode->i_mapping, 0); + truncate_inode_pages(shadow_btnc_inode->i_mapping, 0); up_write(&mi->mi_sem); } diff --git a/fs/nilfs2/mdt.h b/fs/nilfs2/mdt.h index e77aea4bb921..9d8ac0d27c16 100644 --- a/fs/nilfs2/mdt.h +++ b/fs/nilfs2/mdt.h @@ -18,14 +18,12 @@ /** * struct nilfs_shadow_map - shadow mapping of meta data file * @bmap_store: shadow copy of bmap state - * @frozen_data: shadowed dirty data pages - * @frozen_btnodes: shadowed dirty b-tree nodes' pages + * @inode: holder of page caches used in shadow mapping * @frozen_buffers: list of frozen buffers */ struct nilfs_shadow_map { struct nilfs_bmap_store bmap_store; - struct address_space frozen_data; - struct address_space frozen_btnodes; + struct inode *inode; struct list_head frozen_buffers; }; diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h index a2f247b6a209..cca30f0f965c 100644 --- a/fs/nilfs2/nilfs.h +++ b/fs/nilfs2/nilfs.h @@ -28,7 +28,7 @@ * @i_xattr: <TODO> * @i_dir_start_lookup: page index of last successful search * @i_cno: checkpoint number for GC inode - * @i_btnode_cache: cached pages of b-tree nodes + * @i_assoc_inode: associated inode (B-tree node cache holder or back pointer) * @i_dirty: list for connecting dirty files * @xattr_sem: semaphore for extended attributes processing * @i_bh: buffer contains disk inode @@ -43,7 +43,7 @@ struct nilfs_inode_info { __u64 i_xattr; /* sector_t ??? */ __u32 i_dir_start_lookup; __u64 i_cno; /* check point number for GC inode */ - struct address_space i_btnode_cache; + struct inode *i_assoc_inode; struct list_head i_dirty; /* List for connecting dirty files */ #ifdef CONFIG_NILFS_XATTR @@ -75,13 +75,6 @@ NILFS_BMAP_I(const struct nilfs_bmap *bmap) return container_of(bmap, struct nilfs_inode_info, i_bmap_data); } -static inline struct inode *NILFS_BTNC_I(struct address_space *btnc) -{ - struct nilfs_inode_info *ii = - container_of(btnc, struct nilfs_inode_info, i_btnode_cache); - return &ii->vfs_inode; -} - /* * Dynamic state flags of NILFS on-memory inode (i_state) */ @@ -98,6 +91,8 @@ enum { NILFS_I_INODE_SYNC, /* dsync is not allowed for inode */ NILFS_I_BMAP, /* has bmap and btnode_cache */ NILFS_I_GCINODE, /* inode for GC, on memory only */ + NILFS_I_BTNC, /* inode for btree node cache */ + NILFS_I_SHADOW, /* inode for shadowed page cache */ }; /* @@ -203,6 +198,9 @@ static inline int nilfs_acl_chmod(struct inode *inode) static inline int nilfs_init_acl(struct inode *inode, struct inode *dir) { + if (S_ISLNK(inode->i_mode)) + return 0; + inode->i_mode &= ~current_umask(); return 0; } @@ -265,6 +263,9 @@ struct inode *nilfs_iget(struct super_block *sb, struct nilfs_root *root, unsigned long ino); extern struct inode *nilfs_iget_for_gc(struct super_block *sb, unsigned long ino, __u64 cno); +int nilfs_attach_btree_node_cache(struct inode *inode); +void nilfs_detach_btree_node_cache(struct inode *inode); +struct inode *nilfs_iget_for_shadow(struct inode *inode); extern void nilfs_update_inode(struct inode *, struct buffer_head *, int); extern void nilfs_truncate(struct inode *); extern void nilfs_evict_inode(struct inode *); diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c index 329a056b73b1..e5fee7fac915 100644 --- a/fs/nilfs2/page.c +++ b/fs/nilfs2/page.c @@ -372,7 +372,15 @@ void nilfs_clear_dirty_pages(struct address_space *mapping, bool silent) struct page *page = pvec.pages[i]; lock_page(page); - nilfs_clear_dirty_page(page, silent); + + /* + * This page may have been removed from the address + * space by truncation or invalidation when the lock + * was acquired. Skip processing in that case. + */ + if (likely(page->mapping == mapping)) + nilfs_clear_dirty_page(page, silent); + unlock_page(page); } pagevec_release(&pvec); @@ -452,10 +460,9 @@ void nilfs_mapping_init(struct address_space *mapping, struct inode *inode) /* * NILFS2 needs clear_page_dirty() in the following two cases: * - * 1) For B-tree node pages and data pages of the dat/gcdat, NILFS2 clears - * page dirty flags when it copies back pages from the shadow cache - * (gcdat->{i_mapping,i_btnode_cache}) to its original cache - * (dat->{i_mapping,i_btnode_cache}). + * 1) For B-tree node pages and data pages of DAT file, NILFS2 clears dirty + * flag of pages when it copies back pages from shadow cache to the + * original cache. * * 2) Some B-tree operations like insertion or deletion may dispose buffers * in dirty state, and this needs to cancel the dirty state of their pages. diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c index 20c479b5e41b..e72466fc8ca9 100644 --- a/fs/nilfs2/segbuf.c +++ b/fs/nilfs2/segbuf.c @@ -101,6 +101,12 @@ int nilfs_segbuf_extend_segsum(struct nilfs_segment_buffer *segbuf) if (unlikely(!bh)) return -ENOMEM; + lock_buffer(bh); + if (!buffer_uptodate(bh)) { + memset(bh->b_data, 0, bh->b_size); + set_buffer_uptodate(bh); + } + unlock_buffer(bh); nilfs_segbuf_add_segsum_buffer(segbuf, bh); return 0; } diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 91b58c897f92..fdcbed6ee832 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -322,7 +322,7 @@ void nilfs_relax_pressure_in_lock(struct super_block *sb) struct the_nilfs *nilfs = sb->s_fs_info; struct nilfs_sc_info *sci = nilfs->ns_writer; - if (!sci || !sci->sc_flush_request) + if (sb_rdonly(sb) || unlikely(!sci) || !sci->sc_flush_request) return; set_bit(NILFS_SC_PRIOR_FLUSH, &sci->sc_flags); @@ -435,6 +435,23 @@ static int nilfs_segctor_reset_segment_buffer(struct nilfs_sc_info *sci) return 0; } +/** + * nilfs_segctor_zeropad_segsum - zero pad the rest of the segment summary area + * @sci: segment constructor object + * + * nilfs_segctor_zeropad_segsum() zero-fills unallocated space at the end of + * the current segment summary block. + */ +static void nilfs_segctor_zeropad_segsum(struct nilfs_sc_info *sci) +{ + struct nilfs_segsum_pointer *ssp; + + ssp = sci->sc_blk_cnt > 0 ? &sci->sc_binfo_ptr : &sci->sc_finfo_ptr; + if (ssp->offset < ssp->bh->b_size) + memset(ssp->bh->b_data + ssp->offset, 0, + ssp->bh->b_size - ssp->offset); +} + static int nilfs_segctor_feed_segment(struct nilfs_sc_info *sci) { sci->sc_nblk_this_inc += sci->sc_curseg->sb_sum.nblocks; @@ -443,6 +460,7 @@ static int nilfs_segctor_feed_segment(struct nilfs_sc_info *sci) * The current segment is filled up * (internal code) */ + nilfs_segctor_zeropad_segsum(sci); sci->sc_curseg = NILFS_NEXT_SEGBUF(sci->sc_curseg); return nilfs_segctor_reset_segment_buffer(sci); } @@ -547,6 +565,7 @@ static int nilfs_segctor_add_file_block(struct nilfs_sc_info *sci, goto retry; } if (unlikely(required)) { + nilfs_segctor_zeropad_segsum(sci); err = nilfs_segbuf_extend_segsum(segbuf); if (unlikely(err)) goto failed; @@ -711,6 +730,11 @@ static size_t nilfs_lookup_dirty_data_buffers(struct inode *inode, struct page *page = pvec.pages[i]; lock_page(page); + if (unlikely(page->mapping != mapping)) { + /* Exclude pages removed from the address space */ + unlock_page(page); + continue; + } if (!page_has_buffers(page)) create_empty_buffers(page, i_blocksize(inode), 0); unlock_page(page); @@ -738,15 +762,18 @@ static void nilfs_lookup_dirty_node_buffers(struct inode *inode, struct list_head *listp) { struct nilfs_inode_info *ii = NILFS_I(inode); - struct address_space *mapping = &ii->i_btnode_cache; + struct inode *btnc_inode = ii->i_assoc_inode; struct pagevec pvec; struct buffer_head *bh, *head; unsigned int i; pgoff_t index = 0; + if (!btnc_inode) + return; + pagevec_init(&pvec); - while (pagevec_lookup_tag(&pvec, mapping, &index, + while (pagevec_lookup_tag(&pvec, btnc_inode->i_mapping, &index, PAGECACHE_TAG_DIRTY)) { for (i = 0; i < pagevec_count(&pvec); i++) { bh = head = page_buffers(pvec.pages[i]); @@ -877,9 +904,11 @@ static int nilfs_segctor_create_checkpoint(struct nilfs_sc_info *sci) nilfs_mdt_mark_dirty(nilfs->ns_cpfile); nilfs_cpfile_put_checkpoint( nilfs->ns_cpfile, nilfs->ns_cno, bh_cp); - } else - WARN_ON(err == -EINVAL || err == -ENOENT); - + } else if (err == -EINVAL || err == -ENOENT) { + nilfs_error(sci->sc_super, + "checkpoint creation failed due to metadata corruption."); + err = -EIO; + } return err; } @@ -893,7 +922,11 @@ static int nilfs_segctor_fill_in_checkpoint(struct nilfs_sc_info *sci) err = nilfs_cpfile_get_checkpoint(nilfs->ns_cpfile, nilfs->ns_cno, 0, &raw_cp, &bh_cp); if (unlikely(err)) { - WARN_ON(err == -EINVAL || err == -ENOENT); + if (err == -EINVAL || err == -ENOENT) { + nilfs_error(sci->sc_super, + "checkpoint finalization failed due to metadata corruption."); + err = -EIO; + } goto failed_ibh; } raw_cp->cp_snapshot_list.ssl_next = 0; @@ -956,10 +989,13 @@ static void nilfs_segctor_fill_in_super_root(struct nilfs_sc_info *sci, unsigned int isz, srsz; bh_sr = NILFS_LAST_SEGBUF(&sci->sc_segbufs)->sb_super_root; + + lock_buffer(bh_sr); raw_sr = (struct nilfs_super_root *)bh_sr->b_data; isz = nilfs->ns_inode_size; srsz = NILFS_SR_BYTES(isz); + raw_sr->sr_sum = 0; /* Ensure initialization within this update */ raw_sr->sr_bytes = cpu_to_le16(srsz); raw_sr->sr_nongc_ctime = cpu_to_le64(nilfs_doing_gc() ? @@ -973,6 +1009,8 @@ static void nilfs_segctor_fill_in_super_root(struct nilfs_sc_info *sci, nilfs_write_inode_common(nilfs->ns_sufile, (void *)raw_sr + NILFS_SR_SUFILE_OFFSET(isz), 1); memset((void *)raw_sr + srsz, 0, nilfs->ns_blocksize - srsz); + set_buffer_uptodate(bh_sr); + unlock_buffer(bh_sr); } static void nilfs_redirty_inodes(struct list_head *head) @@ -1522,6 +1560,7 @@ static int nilfs_segctor_collect(struct nilfs_sc_info *sci, nadd = min_t(int, nadd << 1, SC_MAX_SEGDELTA); sci->sc_stage = prev_stage; } + nilfs_segctor_zeropad_segsum(sci); nilfs_segctor_truncate_segments(sci, sci->sc_curseg, nilfs->ns_sufile); return 0; @@ -1749,6 +1788,7 @@ static void nilfs_abort_logs(struct list_head *logs, int err) list_for_each_entry(segbuf, logs, sb_list) { list_for_each_entry(bh, &segbuf->sb_segsum_buffers, b_assoc_buffers) { + clear_buffer_uptodate(bh); if (bh->b_page != bd_page) { if (bd_page) end_page_writeback(bd_page); @@ -1760,6 +1800,7 @@ static void nilfs_abort_logs(struct list_head *logs, int err) b_assoc_buffers) { clear_buffer_async_write(bh); if (bh == segbuf->sb_super_root) { + clear_buffer_uptodate(bh); if (bh->b_page != bd_page) { end_page_writeback(bd_page); bd_page = bh->b_page; @@ -2010,6 +2051,9 @@ static int nilfs_segctor_do_construct(struct nilfs_sc_info *sci, int mode) struct the_nilfs *nilfs = sci->sc_super->s_fs_info; int err; + if (sb_rdonly(sci->sc_super)) + return -EROFS; + nilfs_sc_cstage_set(sci, NILFS_ST_INIT); sci->sc_cno = nilfs->ns_cno; @@ -2234,7 +2278,7 @@ int nilfs_construct_segment(struct super_block *sb) struct nilfs_transaction_info *ti; int err; - if (!sci) + if (sb_rdonly(sb) || unlikely(!sci)) return -EROFS; /* A call inside transactions causes a deadlock. */ @@ -2273,7 +2317,7 @@ int nilfs_construct_dsync_segment(struct super_block *sb, struct inode *inode, struct nilfs_transaction_info ti; int err = 0; - if (!sci) + if (sb_rdonly(sb) || unlikely(!sci)) return -EROFS; nilfs_transaction_lock(sb, &ti, 0); @@ -2410,7 +2454,7 @@ nilfs_remove_written_gcinodes(struct the_nilfs *nilfs, struct list_head *head) continue; list_del_init(&ii->i_dirty); truncate_inode_pages(&ii->vfs_inode.i_data, 0); - nilfs_btnode_cache_clear(&ii->i_btnode_cache); + nilfs_btnode_cache_clear(ii->i_assoc_inode->i_mapping); iput(&ii->vfs_inode); } } @@ -2600,11 +2644,10 @@ static int nilfs_segctor_thread(void *arg) goto loop; end_thread: - spin_unlock(&sci->sc_state_lock); - /* end sync. */ sci->sc_task = NULL; wake_up(&sci->sc_wait_task); /* for nilfs_segctor_kill_thread() */ + spin_unlock(&sci->sc_state_lock); return 0; } @@ -2696,7 +2739,7 @@ static void nilfs_segctor_write_out(struct nilfs_sc_info *sci) flush_work(&sci->sc_iput_work); - } while (ret && retrycount-- > 0); + } while (ret && ret != -EROFS && retrycount-- > 0); } /** @@ -2769,11 +2812,12 @@ int nilfs_attach_log_writer(struct super_block *sb, struct nilfs_root *root) if (nilfs->ns_writer) { /* - * This happens if the filesystem was remounted - * read/write after nilfs_error degenerated it into a - * read-only mount. + * This happens if the filesystem is made read-only by + * __nilfs_error or nilfs_remount and then remounted + * read/write. In these cases, reuse the existing + * writer. */ - nilfs_detach_log_writer(sb); + return 0; } nilfs->ns_writer = nilfs_segctor_new(sb, root); @@ -2783,10 +2827,9 @@ int nilfs_attach_log_writer(struct super_block *sb, struct nilfs_root *root) inode_attach_wb(nilfs->ns_bdev->bd_inode, NULL); err = nilfs_segctor_start_thread(nilfs->ns_writer); - if (err) { - kfree(nilfs->ns_writer); - nilfs->ns_writer = NULL; - } + if (unlikely(err)) + nilfs_detach_log_writer(sb); + return err; } @@ -2807,6 +2850,7 @@ void nilfs_detach_log_writer(struct super_block *sb) nilfs_segctor_destroy(nilfs->ns_writer); nilfs->ns_writer = NULL; } + set_nilfs_purging(nilfs); /* Force to free the list of dirty files */ spin_lock(&nilfs->ns_inode_lock); @@ -2819,4 +2863,5 @@ void nilfs_detach_log_writer(struct super_block *sb) up_write(&nilfs->ns_segctor_sem); nilfs_dispose_list(nilfs, &garbage_list, 1); + clear_nilfs_purging(nilfs); } diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c index bf3f8f05c89b..4626540008c1 100644 --- a/fs/nilfs2/sufile.c +++ b/fs/nilfs2/sufile.c @@ -498,14 +498,45 @@ void nilfs_sufile_do_free(struct inode *sufile, __u64 segnum, int nilfs_sufile_mark_dirty(struct inode *sufile, __u64 segnum) { struct buffer_head *bh; + void *kaddr; + struct nilfs_segment_usage *su; int ret; + down_write(&NILFS_MDT(sufile)->mi_sem); ret = nilfs_sufile_get_segment_usage_block(sufile, segnum, 0, &bh); - if (!ret) { + if (ret) + goto out_sem; + + kaddr = kmap_atomic(bh->b_page); + su = nilfs_sufile_block_get_segment_usage(sufile, segnum, bh, kaddr); + if (unlikely(nilfs_segment_usage_error(su))) { + struct the_nilfs *nilfs = sufile->i_sb->s_fs_info; + + kunmap_atomic(kaddr); + brelse(bh); + if (nilfs_segment_is_active(nilfs, segnum)) { + nilfs_error(sufile->i_sb, + "active segment %llu is erroneous", + (unsigned long long)segnum); + } else { + /* + * Segments marked erroneous are never allocated by + * nilfs_sufile_alloc(); only active segments, ie, + * the segments indexed by ns_segnum or ns_nextnum, + * can be erroneous here. + */ + WARN_ON_ONCE(1); + } + ret = -EIO; + } else { + nilfs_segment_usage_set_dirty(su); + kunmap_atomic(kaddr); mark_buffer_dirty(bh); nilfs_mdt_mark_dirty(sufile); brelse(bh); } +out_sem: + up_write(&NILFS_MDT(sufile)->mi_sem); return ret; } @@ -531,9 +562,14 @@ int nilfs_sufile_set_segment_usage(struct inode *sufile, __u64 segnum, kaddr = kmap_atomic(bh->b_page); su = nilfs_sufile_block_get_segment_usage(sufile, segnum, bh, kaddr); - WARN_ON(nilfs_segment_usage_error(su)); - if (modtime) + if (modtime) { + /* + * Check segusage error and set su_lastmod only when updating + * this entry with a valid timestamp, not for cancellation. + */ + WARN_ON_ONCE(nilfs_segment_usage_error(su)); su->su_lastmod = cpu_to_le64(modtime); + } su->su_nblocks = cpu_to_le32(nblocks); kunmap_atomic(kaddr); @@ -774,6 +810,15 @@ int nilfs_sufile_resize(struct inode *sufile, __u64 newnsegs) goto out_header; sui->ncleansegs -= nsegs - newnsegs; + + /* + * If the sufile is successfully truncated, immediately adjust + * the segment allocation space while locking the semaphore + * "mi_sem" so that nilfs_sufile_alloc() never allocates + * segments in the truncated space. + */ + sui->allocmax = newnsegs - 1; + sui->allocmin = 0; } kaddr = kmap_atomic(header_bh->b_page); diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 26290aa1023f..99bcb4ab47a6 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -151,7 +151,8 @@ struct inode *nilfs_alloc_inode(struct super_block *sb) ii->i_bh = NULL; ii->i_state = 0; ii->i_cno = 0; - nilfs_mapping_init(&ii->i_btnode_cache, &ii->vfs_inode); + ii->i_assoc_inode = NULL; + ii->i_bmap = &ii->i_bmap_data; return &ii->vfs_inode; } @@ -373,10 +374,31 @@ static int nilfs_move_2nd_super(struct super_block *sb, loff_t sb2off) goto out; } nsbp = (void *)nsbh->b_data + offset; - memset(nsbp, 0, nilfs->ns_blocksize); + lock_buffer(nsbh); if (sb2i >= 0) { + /* + * The position of the second superblock only changes by 4KiB, + * which is larger than the maximum superblock data size + * (= 1KiB), so there is no need to use memmove() to allow + * overlap between source and destination. + */ memcpy(nsbp, nilfs->ns_sbp[sb2i], nilfs->ns_sbsize); + + /* + * Zero fill after copy to avoid overwriting in case of move + * within the same block. + */ + memset(nsbh->b_data, 0, offset); + memset((void *)nsbp + nilfs->ns_sbsize, 0, + nsbh->b_size - offset - nilfs->ns_sbsize); + } else { + memset(nsbh->b_data, 0, nsbh->b_size); + } + set_buffer_uptodate(nsbh); + unlock_buffer(nsbh); + + if (sb2i >= 0) { brelse(nilfs->ns_sbh[sb2i]); nilfs->ns_sbh[sb2i] = nsbh; nilfs->ns_sbp[sb2i] = nsbp; @@ -410,6 +432,15 @@ int nilfs_resize_fs(struct super_block *sb, __u64 newsize) goto out; /* + * Prevent underflow in second superblock position calculation. + * The exact minimum size check is done in nilfs_sufile_resize(). + */ + if (newsize < 4096) { + ret = -ENOSPC; + goto out; + } + + /* * Write lock is required to protect some functions depending * on the number of segments, the number of reserved segments, * and so forth. @@ -474,6 +505,7 @@ static void nilfs_put_super(struct super_block *sb) up_write(&nilfs->ns_sem); } + nilfs_sysfs_delete_device_group(nilfs); iput(nilfs->ns_sufile); iput(nilfs->ns_cpfile); iput(nilfs->ns_dat); @@ -1100,6 +1132,7 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent) nilfs_put_root(fsroot); failed_unload: + nilfs_sysfs_delete_device_group(nilfs); iput(nilfs->ns_sufile); iput(nilfs->ns_cpfile); iput(nilfs->ns_dat); @@ -1137,8 +1170,6 @@ static int nilfs_remount(struct super_block *sb, int *flags, char *data) if ((bool)(*flags & SB_RDONLY) == sb_rdonly(sb)) goto out; if (*flags & SB_RDONLY) { - /* Shutting down log writer */ - nilfs_detach_log_writer(sb); sb->s_flags |= SB_RDONLY; /* @@ -1382,8 +1413,6 @@ static void nilfs_inode_init_once(void *obj) #ifdef CONFIG_NILFS_XATTR init_rwsem(&ii->xattr_sem); #endif - address_space_init_once(&ii->i_btnode_cache); - ii->i_bmap = &ii->i_bmap_data; inode_init_once(&ii->vfs_inode); } diff --git a/fs/nilfs2/sysfs.c b/fs/nilfs2/sysfs.c index e60be7bb55b0..28a2db3b1787 100644 --- a/fs/nilfs2/sysfs.c +++ b/fs/nilfs2/sysfs.c @@ -64,11 +64,9 @@ static const struct sysfs_ops nilfs_##name##_attr_ops = { \ #define NILFS_DEV_INT_GROUP_TYPE(name, parent_name) \ static void nilfs_##name##_attr_release(struct kobject *kobj) \ { \ - struct nilfs_sysfs_##parent_name##_subgroups *subgroups; \ - struct the_nilfs *nilfs = container_of(kobj->parent, \ - struct the_nilfs, \ - ns_##parent_name##_kobj); \ - subgroups = nilfs->ns_##parent_name##_subgroups; \ + struct nilfs_sysfs_##parent_name##_subgroups *subgroups = container_of(kobj, \ + struct nilfs_sysfs_##parent_name##_subgroups, \ + sg_##name##_kobj); \ complete(&subgroups->sg_##name##_kobj_unregister); \ } \ static struct kobj_type nilfs_##name##_ktype = { \ @@ -94,12 +92,12 @@ static int nilfs_sysfs_create_##name##_group(struct the_nilfs *nilfs) \ err = kobject_init_and_add(kobj, &nilfs_##name##_ktype, parent, \ #name); \ if (err) \ - return err; \ - return 0; \ + kobject_put(kobj); \ + return err; \ } \ static void nilfs_sysfs_delete_##name##_group(struct the_nilfs *nilfs) \ { \ - kobject_del(&nilfs->ns_##parent_name##_subgroups->sg_##name##_kobj); \ + kobject_put(&nilfs->ns_##parent_name##_subgroups->sg_##name##_kobj); \ } /************************************************************************ @@ -210,14 +208,14 @@ int nilfs_sysfs_create_snapshot_group(struct nilfs_root *root) } if (err) - return err; + kobject_put(&root->snapshot_kobj); - return 0; + return err; } void nilfs_sysfs_delete_snapshot_group(struct nilfs_root *root) { - kobject_del(&root->snapshot_kobj); + kobject_put(&root->snapshot_kobj); } /************************************************************************ @@ -1000,7 +998,7 @@ int nilfs_sysfs_create_device_group(struct super_block *sb) err = kobject_init_and_add(&nilfs->ns_dev_kobj, &nilfs_dev_ktype, NULL, "%s", sb->s_id); if (err) - goto free_dev_subgroups; + goto cleanup_dev_kobject; err = nilfs_sysfs_create_mounted_snapshots_group(nilfs); if (err) @@ -1037,9 +1035,7 @@ delete_mounted_snapshots_group: nilfs_sysfs_delete_mounted_snapshots_group(nilfs); cleanup_dev_kobject: - kobject_del(&nilfs->ns_dev_kobj); - -free_dev_subgroups: + kobject_put(&nilfs->ns_dev_kobj); kfree(nilfs->ns_dev_subgroups); failed_create_device_group: @@ -1054,6 +1050,7 @@ void nilfs_sysfs_delete_device_group(struct the_nilfs *nilfs) nilfs_sysfs_delete_superblock_group(nilfs); nilfs_sysfs_delete_segctor_group(nilfs); kobject_del(&nilfs->ns_dev_kobj); + kobject_put(&nilfs->ns_dev_kobj); kfree(nilfs->ns_dev_subgroups); } diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index 484785cdf96e..c8d869bc25b0 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -13,6 +13,7 @@ #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/random.h> +#include <linux/log2.h> #include <linux/crc32.h> #include "nilfs.h" #include "segment.h" @@ -86,7 +87,6 @@ void destroy_nilfs(struct the_nilfs *nilfs) { might_sleep(); if (nilfs_init(nilfs)) { - nilfs_sysfs_delete_device_group(nilfs); brelse(nilfs->ns_sbh[0]); brelse(nilfs->ns_sbh[1]); } @@ -274,6 +274,10 @@ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb) goto failed; } + err = nilfs_sysfs_create_device_group(sb); + if (unlikely(err)) + goto sysfs_error; + if (valid_fs) goto skip_recovery; @@ -335,6 +339,9 @@ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb) goto failed; failed_unload: + nilfs_sysfs_delete_device_group(nilfs); + + sysfs_error: iput(nilfs->ns_cpfile); iput(nilfs->ns_sufile); iput(nilfs->ns_dat); @@ -368,6 +375,18 @@ unsigned long nilfs_nrsvsegs(struct the_nilfs *nilfs, unsigned long nsegs) 100)); } +/** + * nilfs_max_segment_count - calculate the maximum number of segments + * @nilfs: nilfs object + */ +static u64 nilfs_max_segment_count(struct the_nilfs *nilfs) +{ + u64 max_count = U64_MAX; + + do_div(max_count, nilfs->ns_blocks_per_segment); + return min_t(u64, max_count, ULONG_MAX); +} + void nilfs_set_nsegments(struct the_nilfs *nilfs, unsigned long nsegs) { nilfs->ns_nsegments = nsegs; @@ -377,6 +396,8 @@ void nilfs_set_nsegments(struct the_nilfs *nilfs, unsigned long nsegs) static int nilfs_store_disk_layout(struct the_nilfs *nilfs, struct nilfs_super_block *sbp) { + u64 nsegments, nblocks; + if (le32_to_cpu(sbp->s_rev_level) < NILFS_MIN_SUPP_REV) { nilfs_msg(nilfs->ns_sb, KERN_ERR, "unsupported revision (superblock rev.=%d.%d, current rev.=%d.%d). Please check the version of mkfs.nilfs(2).", @@ -423,7 +444,35 @@ static int nilfs_store_disk_layout(struct the_nilfs *nilfs, return -EINVAL; } - nilfs_set_nsegments(nilfs, le64_to_cpu(sbp->s_nsegments)); + nsegments = le64_to_cpu(sbp->s_nsegments); + if (nsegments > nilfs_max_segment_count(nilfs)) { + nilfs_msg(nilfs->ns_sb, KERN_ERR, + "segment count %llu exceeds upper limit (%llu segments)", + (unsigned long long)nsegments, + (unsigned long long)nilfs_max_segment_count(nilfs)); + return -EINVAL; + } + + nblocks = (u64)i_size_read(nilfs->ns_sb->s_bdev->bd_inode) >> + nilfs->ns_sb->s_blocksize_bits; + if (nblocks) { + u64 min_block_count = nsegments * nilfs->ns_blocks_per_segment; + /* + * To avoid failing to mount early device images without a + * second superblock, exclude that block count from the + * "min_block_count" calculation. + */ + + if (nblocks < min_block_count) { + nilfs_msg(nilfs->ns_sb, KERN_ERR, + "total number of segment blocks %llu exceeds device size (%llu blocks)", + (unsigned long long)min_block_count, + (unsigned long long)nblocks); + return -EINVAL; + } + } + + nilfs_set_nsegments(nilfs, nsegments); nilfs->ns_crc_seed = le32_to_cpu(sbp->s_crc_seed); return 0; } @@ -448,11 +497,33 @@ static int nilfs_valid_sb(struct nilfs_super_block *sbp) return crc == le32_to_cpu(sbp->s_sum); } -static int nilfs_sb2_bad_offset(struct nilfs_super_block *sbp, u64 offset) +/** + * nilfs_sb2_bad_offset - check the location of the second superblock + * @sbp: superblock raw data buffer + * @offset: byte offset of second superblock calculated from device size + * + * nilfs_sb2_bad_offset() checks if the position on the second + * superblock is valid or not based on the filesystem parameters + * stored in @sbp. If @offset points to a location within the segment + * area, or if the parameters themselves are not normal, it is + * determined to be invalid. + * + * Return Value: true if invalid, false if valid. + */ +static bool nilfs_sb2_bad_offset(struct nilfs_super_block *sbp, u64 offset) { - return offset < ((le64_to_cpu(sbp->s_nsegments) * - le32_to_cpu(sbp->s_blocks_per_segment)) << - (le32_to_cpu(sbp->s_log_block_size) + 10)); + unsigned int shift_bits = le32_to_cpu(sbp->s_log_block_size); + u32 blocks_per_segment = le32_to_cpu(sbp->s_blocks_per_segment); + u64 nsegments = le64_to_cpu(sbp->s_nsegments); + u64 index; + + if (blocks_per_segment < NILFS_SEG_MIN_BLOCKS || + shift_bits > ilog2(NILFS_MAX_BLOCK_SIZE) - BLOCK_SIZE_BITS) + return true; + + index = offset >> (shift_bits + BLOCK_SIZE_BITS); + do_div(index, blocks_per_segment); + return index < nsegments; } static void nilfs_release_super_block(struct the_nilfs *nilfs) @@ -494,9 +565,15 @@ static int nilfs_load_super_block(struct the_nilfs *nilfs, { struct nilfs_super_block **sbp = nilfs->ns_sbp; struct buffer_head **sbh = nilfs->ns_sbh; - u64 sb2off = NILFS_SB2_OFFSET_BYTES(nilfs->ns_bdev->bd_inode->i_size); + u64 sb2off, devsize = nilfs->ns_bdev->bd_inode->i_size; int valid[2], swp = 0; + if (devsize < NILFS_SEG_MIN_BLOCKS * NILFS_MIN_BLOCK_SIZE + 4096) { + nilfs_msg(sb, KERN_ERR, "device size too small"); + return -EINVAL; + } + sb2off = NILFS_SB2_OFFSET_BYTES(devsize); + sbp[0] = nilfs_read_super_block(sb, NILFS_SB_OFFSET_BYTES, blocksize, &sbh[0]); sbp[1] = nilfs_read_super_block(sb, sb2off, blocksize, &sbh[1]); @@ -611,7 +688,11 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb, char *data) goto failed_sbh; } nilfs_release_super_block(nilfs); - sb_set_blocksize(sb, blocksize); + if (!sb_set_blocksize(sb, blocksize)) { + nilfs_msg(sb, KERN_ERR, "bad blocksize %d", blocksize); + err = -EINVAL; + goto out; + } err = nilfs_load_super_block(nilfs, sb, blocksize, &sbp); if (err) @@ -639,10 +720,6 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb, char *data) if (err) goto failed_sbh; - err = nilfs_sysfs_create_device_group(sb); - if (err) - goto failed_sbh; - set_nilfs_init(nilfs); err = 0; out: @@ -695,9 +772,7 @@ int nilfs_count_free_blocks(struct the_nilfs *nilfs, sector_t *nblocks) { unsigned long ncleansegs; - down_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem); ncleansegs = nilfs_sufile_get_ncleansegs(nilfs->ns_sufile); - up_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem); *nblocks = (sector_t)ncleansegs * nilfs->ns_blocks_per_segment; return 0; } @@ -797,14 +872,13 @@ nilfs_find_or_create_root(struct the_nilfs *nilfs, __u64 cno) void nilfs_put_root(struct nilfs_root *root) { - if (refcount_dec_and_test(&root->count)) { - struct the_nilfs *nilfs = root->nilfs; - - nilfs_sysfs_delete_snapshot_group(root); + struct the_nilfs *nilfs = root->nilfs; - spin_lock(&nilfs->ns_cptree_lock); + if (refcount_dec_and_lock(&root->count, &nilfs->ns_cptree_lock)) { rb_erase(&root->rb_node, &nilfs->ns_cptree); spin_unlock(&nilfs->ns_cptree_lock); + + nilfs_sysfs_delete_snapshot_group(root); iput(root->ifile); kfree(root); diff --git a/fs/nilfs2/the_nilfs.h b/fs/nilfs2/the_nilfs.h index 380a543c5b19..de6e24d80eb6 100644 --- a/fs/nilfs2/the_nilfs.h +++ b/fs/nilfs2/the_nilfs.h @@ -29,6 +29,7 @@ enum { THE_NILFS_DISCONTINUED, /* 'next' pointer chain has broken */ THE_NILFS_GC_RUNNING, /* gc process is running */ THE_NILFS_SB_DIRTY, /* super block is dirty */ + THE_NILFS_PURGING, /* disposing dirty files for cleanup */ }; /** @@ -208,6 +209,7 @@ THE_NILFS_FNS(INIT, init) THE_NILFS_FNS(DISCONTINUED, discontinued) THE_NILFS_FNS(GC_RUNNING, gc_running) THE_NILFS_FNS(SB_DIRTY, sb_dirty) +THE_NILFS_FNS(PURGING, purging) /* * Mount option operations diff --git a/fs/nls/nls_base.c b/fs/nls/nls_base.c index 52ccd34b1e79..a026dbd3593f 100644 --- a/fs/nls/nls_base.c +++ b/fs/nls/nls_base.c @@ -272,7 +272,7 @@ int unregister_nls(struct nls_table * nls) return -EINVAL; } -static struct nls_table *find_nls(char *charset) +static struct nls_table *find_nls(const char *charset) { struct nls_table *nls; spin_lock(&nls_lock); @@ -288,7 +288,7 @@ static struct nls_table *find_nls(char *charset) return nls; } -struct nls_table *load_nls(char *charset) +struct nls_table *load_nls(const char *charset) { return try_then_request_module(find_nls(charset), "nls_%s", charset); } diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c index 86fcf5814279..74aeabbf0ea4 100644 --- a/fs/notify/fdinfo.c +++ b/fs/notify/fdinfo.c @@ -83,16 +83,9 @@ static void inotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark) inode_mark = container_of(mark, struct inotify_inode_mark, fsn_mark); inode = igrab(fsnotify_conn_inode(mark->connector)); if (inode) { - /* - * IN_ALL_EVENTS represents all of the mask bits - * that we expose to userspace. There is at - * least one bit (FS_EVENT_ON_CHILD) which is - * used only internally to the kernel. - */ - u32 mask = mark->mask & IN_ALL_EVENTS; - seq_printf(m, "inotify wd:%x ino:%lx sdev:%x mask:%x ignored_mask:%x ", + seq_printf(m, "inotify wd:%x ino:%lx sdev:%x mask:%x ignored_mask:0 ", inode_mark->wd, inode->i_ino, inode->i_sb->s_dev, - mask, mark->ignored_mask); + inotify_mark_user_mask(mark)); show_mark_fhandle(m, inode); seq_putc(m, '\n'); iput(inode); diff --git a/fs/notify/inotify/inotify.h b/fs/notify/inotify/inotify.h index 7e4578d35b61..5d94c00b1233 100644 --- a/fs/notify/inotify/inotify.h +++ b/fs/notify/inotify/inotify.h @@ -21,6 +21,18 @@ static inline struct inotify_event_info *INOTIFY_E(struct fsnotify_event *fse) return container_of(fse, struct inotify_event_info, fse); } +/* + * INOTIFY_USER_FLAGS represents all of the mask bits that we expose to + * userspace. There is at least one bit (FS_EVENT_ON_CHILD) which is + * used only internally to the kernel. + */ +#define INOTIFY_USER_MASK (IN_ALL_EVENTS | IN_ONESHOT | IN_EXCL_UNLINK) + +static inline __u32 inotify_mark_user_mask(struct fsnotify_mark *fsn_mark) +{ + return fsn_mark->mask & INOTIFY_USER_MASK; +} + extern void inotify_ignored_and_remove_idr(struct fsnotify_mark *fsn_mark, struct fsnotify_group *group); extern int inotify_handle_event(struct fsnotify_group *group, diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index 97a51690338e..83d0b9356844 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -96,7 +96,7 @@ static inline __u32 inotify_arg_to_mask(u32 arg) mask = (FS_IN_IGNORED | FS_EVENT_ON_CHILD | FS_UNMOUNT); /* mask off the flags used to open the fd */ - mask |= (arg & (IN_ALL_EVENTS | IN_ONESHOT | IN_EXCL_UNLINK)); + mask |= (arg & INOTIFY_USER_MASK); return mask; } diff --git a/fs/notify/mark.c b/fs/notify/mark.c index 09535f6423fc..3afd58170984 100644 --- a/fs/notify/mark.c +++ b/fs/notify/mark.c @@ -434,7 +434,7 @@ void fsnotify_free_mark(struct fsnotify_mark *mark) void fsnotify_destroy_mark(struct fsnotify_mark *mark, struct fsnotify_group *group) { - mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING); + mutex_lock(&group->mark_mutex); fsnotify_detach_mark(mark); mutex_unlock(&group->mark_mutex); fsnotify_free_mark(mark); @@ -703,7 +703,7 @@ void fsnotify_clear_marks_by_group(struct fsnotify_group *group, * move marks to free to to_free list in one go and then free marks in * to_free list one by one. */ - mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING); + mutex_lock(&group->mark_mutex); list_for_each_entry_safe(mark, lmark, &group->marks_list, g_list) { if ((1U << mark->connector->type) & type_mask) list_move(&mark->g_list, &to_free); @@ -712,7 +712,7 @@ void fsnotify_clear_marks_by_group(struct fsnotify_group *group, clear: while (1) { - mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING); + mutex_lock(&group->mark_mutex); if (list_empty(head)) { mutex_unlock(&group->mark_mutex); break; diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c index 44a39a099b54..0a7efbe2adb3 100644 --- a/fs/ntfs/attrib.c +++ b/fs/ntfs/attrib.c @@ -606,15 +606,39 @@ static int ntfs_attr_find(const ATTR_TYPE type, const ntfschar *name, a = (ATTR_RECORD*)((u8*)ctx->attr + le32_to_cpu(ctx->attr->length)); for (;; a = (ATTR_RECORD*)((u8*)a + le32_to_cpu(a->length))) { - if ((u8*)a < (u8*)ctx->mrec || (u8*)a > (u8*)ctx->mrec + - le32_to_cpu(ctx->mrec->bytes_allocated)) + u8 *mrec_end = (u8 *)ctx->mrec + + le32_to_cpu(ctx->mrec->bytes_allocated); + u8 *name_end; + + /* check whether ATTR_RECORD wrap */ + if ((u8 *)a < (u8 *)ctx->mrec) + break; + + /* check whether Attribute Record Header is within bounds */ + if ((u8 *)a > mrec_end || + (u8 *)a + sizeof(ATTR_RECORD) > mrec_end) + break; + + /* check whether ATTR_RECORD's name is within bounds */ + name_end = (u8 *)a + le16_to_cpu(a->name_offset) + + a->name_length * sizeof(ntfschar); + if (name_end > mrec_end) break; + ctx->attr = a; if (unlikely(le32_to_cpu(a->type) > le32_to_cpu(type) || a->type == AT_END)) return -ENOENT; if (unlikely(!a->length)) break; + + /* check whether ATTR_RECORD's length wrap */ + if ((u8 *)a + le32_to_cpu(a->length) < (u8 *)a) + break; + /* check whether ATTR_RECORD's length is within bounds */ + if ((u8 *)a + le32_to_cpu(a->length) > mrec_end) + break; + if (a->type != type) continue; /* diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c index bd3221cbdd95..97d34de2a8f3 100644 --- a/fs/ntfs/inode.c +++ b/fs/ntfs/inode.c @@ -502,7 +502,7 @@ err_corrupt_attr: } file_name_attr = (FILE_NAME_ATTR*)((u8*)attr + le16_to_cpu(attr->data.resident.value_offset)); - p2 = (u8*)attr + le32_to_cpu(attr->data.resident.value_length); + p2 = (u8 *)file_name_attr + le32_to_cpu(attr->data.resident.value_length); if (p2 < (u8*)attr || p2 > p) goto err_corrupt_attr; /* This attribute is ok, but is it in the $Extend directory? */ @@ -654,6 +654,12 @@ static int ntfs_read_locked_inode(struct inode *vi) } a = ctx->attr; /* Get the standard information attribute value. */ + if ((u8 *)a + le16_to_cpu(a->data.resident.value_offset) + + le32_to_cpu(a->data.resident.value_length) > + (u8 *)ctx->mrec + vol->mft_record_size) { + ntfs_error(vi->i_sb, "Corrupt standard information attribute in inode."); + goto unm_err_out; + } si = (STANDARD_INFORMATION*)((u8*)a + le16_to_cpu(a->data.resident.value_offset)); @@ -1835,6 +1841,12 @@ int ntfs_read_inode_mount(struct inode *vi) brelse(bh); } + if (le32_to_cpu(m->bytes_allocated) != vol->mft_record_size) { + ntfs_error(sb, "Incorrect mft record size %u in superblock, should be %u.", + le32_to_cpu(m->bytes_allocated), vol->mft_record_size); + goto err_out; + } + /* Apply the mst fixups. */ if (post_read_mst_fixup((NTFS_RECORD*)m, vol->mft_record_size)) { /* FIXME: Try to use the $MFTMirr now. */ @@ -1842,6 +1854,13 @@ int ntfs_read_inode_mount(struct inode *vi) goto err_out; } + /* Sanity check offset to the first attribute */ + if (le16_to_cpu(m->attrs_offset) >= le32_to_cpu(m->bytes_allocated)) { + ntfs_error(sb, "Incorrect mft offset to the first attribute %u in superblock.", + le16_to_cpu(m->attrs_offset)); + goto err_out; + } + /* Need this to sanity check attribute list references to $MFT. */ vi->i_generation = ni->seq_no = le16_to_cpu(m->sequence_number); @@ -1894,6 +1913,10 @@ int ntfs_read_inode_mount(struct inode *vi) } /* Now allocate memory for the attribute list. */ ni->attr_list_size = (u32)ntfs_attr_size(a); + if (!ni->attr_list_size) { + ntfs_error(sb, "Attr_list_size is zero"); + goto put_err_out; + } ni->attr_list = ntfs_malloc_nofs(ni->attr_list_size); if (!ni->attr_list) { ntfs_error(sb, "Not enough memory to allocate buffer " diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c index bb7159f697f2..f47a3390118f 100644 --- a/fs/ntfs/super.c +++ b/fs/ntfs/super.c @@ -2106,7 +2106,8 @@ get_ctx_vol_failed: // TODO: Initialize security. /* Get the extended system files' directory inode. */ vol->extend_ino = ntfs_iget(sb, FILE_Extend); - if (IS_ERR(vol->extend_ino) || is_bad_inode(vol->extend_ino)) { + if (IS_ERR(vol->extend_ino) || is_bad_inode(vol->extend_ino) || + !S_ISDIR(vol->extend_ino->i_mode)) { if (!IS_ERR(vol->extend_ino)) iput(vol->extend_ino); ntfs_error(sb, "Failed to load $Extend."); diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index ff0e083ce2a1..c7cf0913229c 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -4722,7 +4722,7 @@ int ocfs2_insert_extent(handle_t *handle, struct ocfs2_alloc_context *meta_ac) { int status; - int uninitialized_var(free_records); + int free_records; struct buffer_head *last_eb_bh = NULL; struct ocfs2_insert_type insert = {0, }; struct ocfs2_extent_rec rec; @@ -7048,35 +7048,26 @@ void ocfs2_set_inode_data_inline(struct inode *inode, struct ocfs2_dinode *di) int ocfs2_convert_inline_data_to_extents(struct inode *inode, struct buffer_head *di_bh) { - int ret, i, has_data, num_pages = 0; + int ret, has_data, num_pages = 0; int need_free = 0; u32 bit_off, num; handle_t *handle; - u64 uninitialized_var(block); + u64 block; struct ocfs2_inode_info *oi = OCFS2_I(inode); struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; struct ocfs2_alloc_context *data_ac = NULL; - struct page **pages = NULL; - loff_t end = osb->s_clustersize; + struct page *page = NULL; struct ocfs2_extent_tree et; int did_quota = 0; has_data = i_size_read(inode) ? 1 : 0; if (has_data) { - pages = kcalloc(ocfs2_pages_per_cluster(osb->sb), - sizeof(struct page *), GFP_NOFS); - if (pages == NULL) { - ret = -ENOMEM; - mlog_errno(ret); - return ret; - } - ret = ocfs2_reserve_clusters(osb, 1, &data_ac); if (ret) { mlog_errno(ret); - goto free_pages; + goto out; } } @@ -7096,7 +7087,8 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode, } if (has_data) { - unsigned int page_end; + unsigned int page_end = min_t(unsigned, PAGE_SIZE, + osb->s_clustersize); u64 phys; ret = dquot_alloc_space_nodirty(inode, @@ -7120,15 +7112,8 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode, */ block = phys = ocfs2_clusters_to_blocks(inode->i_sb, bit_off); - /* - * Non sparse file systems zero on extend, so no need - * to do that now. - */ - if (!ocfs2_sparse_alloc(osb) && - PAGE_SIZE < osb->s_clustersize) - end = PAGE_SIZE; - - ret = ocfs2_grab_eof_pages(inode, 0, end, pages, &num_pages); + ret = ocfs2_grab_eof_pages(inode, 0, page_end, &page, + &num_pages); if (ret) { mlog_errno(ret); need_free = 1; @@ -7139,20 +7124,15 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode, * This should populate the 1st page for us and mark * it up to date. */ - ret = ocfs2_read_inline_data(inode, pages[0], di_bh); + ret = ocfs2_read_inline_data(inode, page, di_bh); if (ret) { mlog_errno(ret); need_free = 1; goto out_unlock; } - page_end = PAGE_SIZE; - if (PAGE_SIZE > osb->s_clustersize) - page_end = osb->s_clustersize; - - for (i = 0; i < num_pages; i++) - ocfs2_map_and_dirty_page(inode, handle, 0, page_end, - pages[i], i > 0, &phys); + ocfs2_map_and_dirty_page(inode, handle, 0, page_end, page, 0, + &phys); } spin_lock(&oi->ip_lock); @@ -7183,8 +7163,8 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode, } out_unlock: - if (pages) - ocfs2_unlock_and_free_pages(pages, num_pages); + if (page) + ocfs2_unlock_and_free_pages(&page, num_pages); out_commit: if (ret < 0 && did_quota) @@ -7208,8 +7188,6 @@ out_commit: out: if (data_ac) ocfs2_free_alloc_context(data_ac); -free_pages: - kfree(pages); return ret; } diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 543efa3e5655..1353db3f7f48 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -2003,11 +2003,25 @@ int ocfs2_write_end_nolock(struct address_space *mapping, } if (unlikely(copied < len) && wc->w_target_page) { + loff_t new_isize; + if (!PageUptodate(wc->w_target_page)) copied = 0; - ocfs2_zero_new_buffers(wc->w_target_page, start+copied, - start+len); + new_isize = max_t(loff_t, i_size_read(inode), pos + copied); + if (new_isize > page_offset(wc->w_target_page)) + ocfs2_zero_new_buffers(wc->w_target_page, start+copied, + start+len); + else { + /* + * When page is fully beyond new isize (data copy + * failed), do not bother zeroing the page. Invalidate + * it instead so that writeback does not get confused + * put page & buffer dirty bits into inconsistent + * state. + */ + block_invalidatepage(wc->w_target_page, 0, PAGE_SIZE); + } } if (wc->w_target_page) flush_dcache_page(wc->w_target_page); @@ -2311,7 +2325,7 @@ static int ocfs2_dio_end_io_write(struct inode *inode, struct ocfs2_alloc_context *meta_ac = NULL; handle_t *handle = NULL; loff_t end = offset + bytes; - int ret = 0, credits = 0, locked = 0; + int ret = 0, credits = 0; ocfs2_init_dealloc_ctxt(&dealloc); @@ -2322,13 +2336,6 @@ static int ocfs2_dio_end_io_write(struct inode *inode, !dwc->dw_orphaned) goto out; - /* ocfs2_file_write_iter will get i_mutex, so we need not lock if we - * are in that context. */ - if (dwc->dw_writer_pid != task_pid_nr(current)) { - inode_lock(inode); - locked = 1; - } - ret = ocfs2_inode_lock(inode, &di_bh, 1); if (ret < 0) { mlog_errno(ret); @@ -2409,8 +2416,6 @@ out: if (meta_ac) ocfs2_free_alloc_context(meta_ac); ocfs2_run_deallocs(osb, &dealloc); - if (locked) - inode_unlock(inode); ocfs2_dio_free_write_ctx(inode, dwc); return ret; diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index 9b2ed62dd638..19b0d358a0d6 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -2154,7 +2154,7 @@ static struct config_item *o2hb_heartbeat_group_make_item(struct config_group *g o2hb_nego_timeout_handler, reg, NULL, ®->hr_handler_list); if (ret) - goto free; + goto remove_item; ret = o2net_register_handler(O2HB_NEGO_APPROVE_MSG, reg->hr_key, sizeof(struct o2hb_nego_msg), @@ -2173,6 +2173,12 @@ static struct config_item *o2hb_heartbeat_group_make_item(struct config_group *g unregister_handler: o2net_unregister_handler_list(®->hr_handler_list); +remove_item: + spin_lock(&o2hb_live_lock); + list_del(®->hr_all_item); + if (o2hb_global_heartbeat_active()) + clear_bit(reg->hr_region_num, o2hb_region_bitmap); + spin_unlock(&o2hb_live_lock); free: kfree(reg); return ERR_PTR(ret); diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index c121abbdfc7d..13f4bb4e174c 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -866,9 +866,9 @@ static int ocfs2_dx_dir_lookup(struct inode *inode, u64 *ret_phys_blkno) { int ret = 0; - unsigned int cend, uninitialized_var(clen); - u32 uninitialized_var(cpos); - u64 uninitialized_var(blkno); + unsigned int cend, clen; + u32 cpos; + u64 blkno; u32 name_hash = hinfo->major_hash; ret = ocfs2_dx_dir_lookup_rec(inode, el, name_hash, &cpos, &blkno, @@ -912,7 +912,7 @@ static int ocfs2_dx_dir_search(const char *name, int namelen, struct ocfs2_dir_lookup_result *res) { int ret, i, found; - u64 uninitialized_var(phys); + u64 phys; struct buffer_head *dx_leaf_bh = NULL; struct ocfs2_dx_leaf *dx_leaf; struct ocfs2_dx_entry *dx_entry = NULL; @@ -4420,9 +4420,9 @@ out: int ocfs2_dx_dir_truncate(struct inode *dir, struct buffer_head *di_bh) { int ret; - unsigned int uninitialized_var(clen); - u32 major_hash = UINT_MAX, p_cpos, uninitialized_var(cpos); - u64 uninitialized_var(blkno); + unsigned int clen; + u32 major_hash = UINT_MAX, p_cpos, cpos; + u64 blkno; struct ocfs2_super *osb = OCFS2_SB(dir->i_sb); struct buffer_head *dx_root_bh = NULL; struct ocfs2_dx_root_block *dx_root; diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h index d06e27ec4be4..fb181f6d6c06 100644 --- a/fs/ocfs2/dlm/dlmcommon.h +++ b/fs/ocfs2/dlm/dlmcommon.h @@ -704,10 +704,6 @@ struct dlm_begin_reco __be32 pad2; }; - -#define BITS_PER_BYTE 8 -#define BITS_TO_BYTES(bits) (((bits)+BITS_PER_BYTE-1)/BITS_PER_BYTE) - struct dlm_query_join_request { u8 node_idx; diff --git a/fs/ocfs2/dlmfs/userdlm.c b/fs/ocfs2/dlmfs/userdlm.c index 9cecf4857195..24dbbbf13827 100644 --- a/fs/ocfs2/dlmfs/userdlm.c +++ b/fs/ocfs2/dlmfs/userdlm.c @@ -449,6 +449,11 @@ again: } spin_lock(&lockres->l_lock); + if (lockres->l_flags & USER_LOCK_IN_TEARDOWN) { + spin_unlock(&lockres->l_lock); + status = -EAGAIN; + goto bail; + } /* We only compare against the currently granted level * here. If the lock is blocked waiting on a downconvert, @@ -615,7 +620,7 @@ int user_dlm_destroy_lock(struct user_lock_res *lockres) spin_lock(&lockres->l_lock); if (lockres->l_flags & USER_LOCK_IN_TEARDOWN) { spin_unlock(&lockres->l_lock); - return 0; + goto bail; } lockres->l_flags |= USER_LOCK_IN_TEARDOWN; @@ -629,12 +634,17 @@ int user_dlm_destroy_lock(struct user_lock_res *lockres) } if (lockres->l_ro_holders || lockres->l_ex_holders) { + lockres->l_flags &= ~USER_LOCK_IN_TEARDOWN; spin_unlock(&lockres->l_lock); goto bail; } status = 0; if (!(lockres->l_flags & USER_LOCK_ATTACHED)) { + /* + * lock is never requested, leave USER_LOCK_IN_TEARDOWN set + * to avoid new lock request coming in. + */ spin_unlock(&lockres->l_lock); goto bail; } @@ -645,6 +655,10 @@ int user_dlm_destroy_lock(struct user_lock_res *lockres) status = ocfs2_dlm_unlock(conn, &lockres->l_lksb, DLM_LKF_VALBLK); if (status) { + spin_lock(&lockres->l_lock); + lockres->l_flags &= ~USER_LOCK_IN_TEARDOWN; + lockres->l_flags &= ~USER_LOCK_BUSY; + spin_unlock(&lockres->l_lock); user_log_dlm_error("ocfs2_dlm_unlock", status, lockres); goto bail; } diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 8149fb6f1f0d..a906f47ce1ba 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -3907,7 +3907,7 @@ static int ocfs2_data_convert_worker(struct ocfs2_lock_res *lockres, oi = OCFS2_I(inode); oi->ip_dir_lock_gen++; mlog(0, "generation: %u\n", oi->ip_dir_lock_gen); - goto out; + goto out_forget; } if (!S_ISREG(inode->i_mode)) @@ -3938,6 +3938,7 @@ static int ocfs2_data_convert_worker(struct ocfs2_lock_res *lockres, filemap_fdatawait(mapping); } +out_forget: forget_all_cached_acls(inode); out: diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c index 06cb96462bf9..1f41171c1468 100644 --- a/fs/ocfs2/extent_map.c +++ b/fs/ocfs2/extent_map.c @@ -416,7 +416,7 @@ static int ocfs2_get_clusters_nocache(struct inode *inode, { int i, ret, tree_height, len; struct ocfs2_dinode *di; - struct ocfs2_extent_block *uninitialized_var(eb); + struct ocfs2_extent_block *eb; struct ocfs2_extent_list *el; struct ocfs2_extent_rec *rec; struct buffer_head *eb_bh = NULL; @@ -613,7 +613,7 @@ int ocfs2_get_clusters(struct inode *inode, u32 v_cluster, unsigned int *extent_flags) { int ret; - unsigned int uninitialized_var(hole_len), flags = 0; + unsigned int hole_len, flags = 0; struct buffer_head *di_bh = NULL; struct ocfs2_extent_rec rec; diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index fbd70111a2f1..c1780b14d23d 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -492,10 +492,11 @@ int ocfs2_truncate_file(struct inode *inode, * greater than page size, so we have to truncate them * anyway. */ - unmap_mapping_range(inode->i_mapping, new_i_size + PAGE_SIZE - 1, 0, 1); - truncate_inode_pages(inode->i_mapping, new_i_size); if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) { + unmap_mapping_range(inode->i_mapping, + new_i_size + PAGE_SIZE - 1, 0, 1); + truncate_inode_pages(inode->i_mapping, new_i_size); status = ocfs2_truncate_inline(inode, di_bh, new_i_size, i_size_read(inode), 1); if (status) @@ -514,6 +515,9 @@ int ocfs2_truncate_file(struct inode *inode, goto bail_unlock_sem; } + unmap_mapping_range(inode->i_mapping, new_i_size + PAGE_SIZE - 1, 0, 1); + truncate_inode_pages(inode->i_mapping, new_i_size); + status = ocfs2_commit_truncate(osb, inode, di_bh); if (status < 0) { mlog_errno(status); @@ -1252,22 +1256,24 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr) goto bail_unlock; } } + down_write(&OCFS2_I(inode)->ip_alloc_sem); handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS + 2 * ocfs2_quota_trans_credits(sb)); if (IS_ERR(handle)) { status = PTR_ERR(handle); mlog_errno(status); - goto bail_unlock; + goto bail_unlock_alloc; } status = __dquot_transfer(inode, transfer_to); if (status < 0) goto bail_commit; } else { + down_write(&OCFS2_I(inode)->ip_alloc_sem); handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS); if (IS_ERR(handle)) { status = PTR_ERR(handle); mlog_errno(status); - goto bail_unlock; + goto bail_unlock_alloc; } } @@ -1280,6 +1286,8 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr) bail_commit: ocfs2_commit_trans(osb, handle); +bail_unlock_alloc: + up_write(&OCFS2_I(inode)->ip_alloc_sem); bail_unlock: if (status && inode_locked) { ocfs2_inode_unlock_tracker(inode, 1, &oh, had_lock); @@ -1533,6 +1541,45 @@ static void ocfs2_truncate_cluster_pages(struct inode *inode, u64 byte_start, } } +/* + * zero out partial blocks of one cluster. + * + * start: file offset where zero starts, will be made upper block aligned. + * len: it will be trimmed to the end of current cluster if "start + len" + * is bigger than it. + */ +static int ocfs2_zeroout_partial_cluster(struct inode *inode, + u64 start, u64 len) +{ + int ret; + u64 start_block, end_block, nr_blocks; + u64 p_block, offset; + u32 cluster, p_cluster, nr_clusters; + struct super_block *sb = inode->i_sb; + u64 end = ocfs2_align_bytes_to_clusters(sb, start); + + if (start + len < end) + end = start + len; + + start_block = ocfs2_blocks_for_bytes(sb, start); + end_block = ocfs2_blocks_for_bytes(sb, end); + nr_blocks = end_block - start_block; + if (!nr_blocks) + return 0; + + cluster = ocfs2_bytes_to_clusters(sb, start); + ret = ocfs2_get_clusters(inode, cluster, &p_cluster, + &nr_clusters, NULL); + if (ret) + return ret; + if (!p_cluster) + return 0; + + offset = start_block - ocfs2_clusters_to_blocks(sb, cluster); + p_block = ocfs2_clusters_to_blocks(sb, p_cluster) + offset; + return sb_issue_zeroout(sb, p_block, nr_blocks, GFP_NOFS); +} + static int ocfs2_zero_partial_clusters(struct inode *inode, u64 start, u64 len) { @@ -1542,6 +1589,7 @@ static int ocfs2_zero_partial_clusters(struct inode *inode, struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); unsigned int csize = osb->s_clustersize; handle_t *handle; + loff_t isize = i_size_read(inode); /* * The "start" and "end" values are NOT necessarily part of @@ -1562,6 +1610,26 @@ static int ocfs2_zero_partial_clusters(struct inode *inode, if ((start & (csize - 1)) == 0 && (end & (csize - 1)) == 0) goto out; + /* No page cache for EOF blocks, issue zero out to disk. */ + if (end > isize) { + /* + * zeroout eof blocks in last cluster starting from + * "isize" even "start" > "isize" because it is + * complicated to zeroout just at "start" as "start" + * may be not aligned with block size, buffer write + * would be required to do that, but out of eof buffer + * write is not supported. + */ + ret = ocfs2_zeroout_partial_cluster(inode, isize, + end - isize); + if (ret) { + mlog_errno(ret); + goto out; + } + if (start >= isize) + goto out; + end = isize; + } handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS); if (IS_ERR(handle)) { ret = PTR_ERR(handle); @@ -1869,7 +1937,7 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode, { int ret; s64 llen; - loff_t size; + loff_t size, orig_isize; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct buffer_head *di_bh = NULL; handle_t *handle; @@ -1961,6 +2029,15 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode, default: ret = -EINVAL; } + + orig_isize = i_size_read(inode); + /* zeroout eof blocks in the cluster. */ + if (!ret && change_size && orig_isize < size) { + ret = ocfs2_zeroout_partial_cluster(inode, orig_isize, + size - orig_isize); + if (!ret) + i_size_write(inode, size); + } up_write(&OCFS2_I(inode)->ip_alloc_sem); if (ret) { mlog_errno(ret); @@ -1977,9 +2054,6 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode, goto out_inode_unlock; } - if (change_size && i_size_read(inode) < size) - i_size_write(inode, size); - inode->i_ctime = inode->i_mtime = current_time(inode); ret = ocfs2_mark_inode_dirty(handle, inode, di_bh); if (ret < 0) @@ -2037,14 +2111,20 @@ static long ocfs2_fallocate(struct file *file, int mode, loff_t offset, struct ocfs2_space_resv sr; int change_size = 1; int cmd = OCFS2_IOC_RESVSP64; + int ret = 0; if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE)) return -EOPNOTSUPP; if (!ocfs2_writes_unwritten_extents(osb)) return -EOPNOTSUPP; - if (mode & FALLOC_FL_KEEP_SIZE) + if (mode & FALLOC_FL_KEEP_SIZE) { change_size = 0; + } else { + ret = inode_newsize_ok(inode, offset + len); + if (ret) + return ret; + } if (mode & FALLOC_FL_PUNCH_HOLE) cmd = OCFS2_IOC_UNRESVSP64; diff --git a/fs/ocfs2/filecheck.c b/fs/ocfs2/filecheck.c index 1906cc962c4d..345ca9e14028 100644 --- a/fs/ocfs2/filecheck.c +++ b/fs/ocfs2/filecheck.c @@ -336,11 +336,7 @@ static ssize_t ocfs2_filecheck_attr_show(struct kobject *kobj, ret = snprintf(buf + total, remain, "%lu\t\t%u\t%s\n", p->fe_ino, p->fe_done, ocfs2_filecheck_error(p->fe_status)); - if (ret < 0) { - total = ret; - break; - } - if (ret == remain) { + if (ret >= remain) { /* snprintf() didn't fit */ total = -E2BIG; break; diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c index 1565dd8e8856..fbbc30f20173 100644 --- a/fs/ocfs2/move_extents.c +++ b/fs/ocfs2/move_extents.c @@ -115,14 +115,6 @@ static int __ocfs2_move_extent(handle_t *handle, */ replace_rec.e_flags = ext_flags & ~OCFS2_EXT_REFCOUNTED; - ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), - context->et.et_root_bh, - OCFS2_JOURNAL_ACCESS_WRITE); - if (ret) { - mlog_errno(ret); - goto out; - } - ret = ocfs2_split_extent(handle, &context->et, path, index, &replace_rec, context->meta_ac, &context->dealloc); @@ -131,8 +123,6 @@ static int __ocfs2_move_extent(handle_t *handle, goto out; } - ocfs2_journal_dirty(handle, context->et.et_root_bh); - context->new_phys_cpos = new_p_cpos; /* @@ -454,7 +444,7 @@ static int ocfs2_find_victim_alloc_group(struct inode *inode, bg = (struct ocfs2_group_desc *)gd_bh->b_data; if (vict_blkno < (le64_to_cpu(bg->bg_blkno) + - le16_to_cpu(bg->bg_bits))) { + (le16_to_cpu(bg->bg_bits) << bits_per_unit))) { *ret_bh = gd_bh; *vict_bit = (vict_blkno - blkno) >> @@ -569,6 +559,7 @@ static void ocfs2_probe_alloc_group(struct inode *inode, struct buffer_head *bh, last_free_bits++; if (last_free_bits == move_len) { + i -= move_len; *goal_bit = i; *phys_cpos = base_cpos + i; break; @@ -1040,18 +1031,19 @@ int ocfs2_ioctl_move_extents(struct file *filp, void __user *argp) context->range = ⦥ + /* + * ok, the default theshold for the defragmentation + * is 1M, since our maximum clustersize was 1M also. + * any thought? + */ + if (!range.me_threshold) + range.me_threshold = 1024 * 1024; + + if (range.me_threshold > i_size_read(inode)) + range.me_threshold = i_size_read(inode); + if (range.me_flags & OCFS2_MOVE_EXT_FL_AUTO_DEFRAG) { context->auto_defrag = 1; - /* - * ok, the default theshold for the defragmentation - * is 1M, since our maximum clustersize was 1M also. - * any thought? - */ - if (!range.me_threshold) - range.me_threshold = 1024 * 1024; - - if (range.me_threshold > i_size_read(inode)) - range.me_threshold = i_size_read(inode); if (range.me_flags & OCFS2_MOVE_EXT_FL_PART_DEFRAG) context->partial = 1; diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index b7ca84bc3df7..bb8483510327 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -245,6 +245,7 @@ static int ocfs2_mknod(struct inode *dir, handle_t *handle = NULL; struct ocfs2_super *osb; struct ocfs2_dinode *dirfe; + struct ocfs2_dinode *fe = NULL; struct buffer_head *new_fe_bh = NULL; struct inode *inode = NULL; struct ocfs2_alloc_context *inode_ac = NULL; @@ -395,6 +396,7 @@ static int ocfs2_mknod(struct inode *dir, goto leave; } + fe = (struct ocfs2_dinode *) new_fe_bh->b_data; if (S_ISDIR(mode)) { status = ocfs2_fill_new_dir(osb, handle, dir, inode, new_fe_bh, data_ac, meta_ac); @@ -460,8 +462,11 @@ static int ocfs2_mknod(struct inode *dir, leave: if (status < 0 && did_quota_inode) dquot_free_inode(inode); - if (handle) + if (handle) { + if (status < 0 && fe) + ocfs2_set_links_count(fe, 0); ocfs2_commit_trans(osb, handle); + } ocfs2_inode_unlock(dir, 1); if (did_block_signals) @@ -639,18 +644,9 @@ static int ocfs2_mknod_locked(struct ocfs2_super *osb, return status; } - status = __ocfs2_mknod_locked(dir, inode, dev, new_fe_bh, + return __ocfs2_mknod_locked(dir, inode, dev, new_fe_bh, parent_fe_bh, handle, inode_ac, fe_blkno, suballoc_loc, suballoc_bit); - if (status < 0) { - u64 bg_blkno = ocfs2_which_suballoc_group(fe_blkno, suballoc_bit); - int tmp = ocfs2_free_suballoc_bits(handle, inode_ac->ac_inode, - inode_ac->ac_bh, suballoc_bit, bg_blkno, 1); - if (tmp) - mlog_errno(tmp); - } - - return status; } static int ocfs2_mkdir(struct inode *dir, @@ -1542,6 +1538,10 @@ static int ocfs2_rename(struct inode *old_dir, status = ocfs2_add_entry(handle, new_dentry, old_inode, OCFS2_I(old_inode)->ip_blkno, new_dir_bh, &target_insert); + if (status < 0) { + mlog_errno(status); + goto bail; + } } old_inode->i_ctime = current_time(old_inode); @@ -2031,8 +2031,11 @@ bail: ocfs2_clusters_to_bytes(osb->sb, 1)); if (status < 0 && did_quota_inode) dquot_free_inode(inode); - if (handle) + if (handle) { + if (status < 0 && fe) + ocfs2_set_links_count(fe, 0); ocfs2_commit_trans(osb, handle); + } ocfs2_inode_unlock(dir, 1); if (did_block_signals) @@ -2507,7 +2510,7 @@ int ocfs2_create_inode_in_orphan(struct inode *dir, struct buffer_head *new_di_bh = NULL; struct ocfs2_alloc_context *inode_ac = NULL; struct ocfs2_dir_lookup_result orphan_insert = { NULL, }; - u64 uninitialized_var(di_blkno), suballoc_loc; + u64 di_blkno, suballoc_loc; u16 suballoc_bit; status = ocfs2_inode_lock(dir, &parent_di_bh, 1); diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index fc197e599e8c..e184b36f8dd3 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -1069,7 +1069,7 @@ static int ocfs2_get_refcount_rec(struct ocfs2_caching_info *ci, struct buffer_head **ret_bh) { int ret = 0, i, found; - u32 low_cpos, uninitialized_var(cpos_end); + u32 low_cpos, cpos_end; struct ocfs2_extent_list *el; struct ocfs2_extent_rec *rec = NULL; struct ocfs2_extent_block *eb = NULL; diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c index c4b029c43464..10d691530d83 100644 --- a/fs/ocfs2/stackglue.c +++ b/fs/ocfs2/stackglue.c @@ -510,11 +510,7 @@ static ssize_t ocfs2_loaded_cluster_plugins_show(struct kobject *kobj, list_for_each_entry(p, &ocfs2_stack_list, sp_list) { ret = snprintf(buf, remain, "%s\n", p->sp_name); - if (ret < 0) { - total = ret; - break; - } - if (ret == remain) { + if (ret >= remain) { /* snprintf() didn't fit */ total = -E2BIG; break; @@ -541,7 +537,7 @@ static ssize_t ocfs2_active_cluster_plugin_show(struct kobject *kobj, if (active_stack) { ret = snprintf(buf, PAGE_SIZE, "%s\n", active_stack->sp_name); - if (ret == PAGE_SIZE) + if (ret >= PAGE_SIZE) ret = -E2BIG; } spin_unlock(&ocfs2_stack_lock); @@ -719,6 +715,8 @@ static struct ctl_table_header *ocfs2_table_header; static int __init ocfs2_stack_glue_init(void) { + int ret; + strcpy(cluster_stack_name, OCFS2_STACK_PLUGIN_O2CB); ocfs2_table_header = register_sysctl_table(ocfs2_root_table); @@ -728,7 +726,11 @@ static int __init ocfs2_stack_glue_init(void) return -ENOMEM; /* or something. */ } - return ocfs2_sysfs_init(); + ret = ocfs2_sysfs_init(); + if (ret) + unregister_sysctl_table(ocfs2_table_header); + + return ret; } static void __exit ocfs2_stack_glue_exit(void) diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 2658d91c1f7b..4fd99ef7f334 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -985,8 +985,10 @@ static void ocfs2_disable_quotas(struct ocfs2_super *osb) for (type = 0; type < OCFS2_MAXQUOTAS; type++) { if (!sb_has_quota_loaded(sb, type)) continue; - oinfo = sb_dqinfo(sb, type)->dqi_priv; - cancel_delayed_work_sync(&oinfo->dqi_sync_work); + if (!sb_has_quota_suspended(sb, type)) { + oinfo = sb_dqinfo(sb, type)->dqi_priv; + cancel_delayed_work_sync(&oinfo->dqi_sync_work); + } inode = igrab(sb->s_dquot.files[type]); /* Turn off quotas. This will remove all dquot structures from * memory and so they will be automatically synced to global @@ -1150,17 +1152,6 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) goto read_super_error; } - root = d_make_root(inode); - if (!root) { - status = -ENOMEM; - mlog_errno(status); - goto read_super_error; - } - - sb->s_root = root; - - ocfs2_complete_mount_recovery(osb); - osb->osb_dev_kset = kset_create_and_add(sb->s_id, NULL, &ocfs2_kset->kobj); if (!osb->osb_dev_kset) { @@ -1178,6 +1169,17 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) goto read_super_error; } + root = d_make_root(inode); + if (!root) { + status = -ENOMEM; + mlog_errno(status); + goto read_super_error; + } + + sb->s_root = root; + + ocfs2_complete_mount_recovery(osb); + if (ocfs2_mount_local(osb)) snprintf(nodestr, sizeof(nodestr), "local"); else @@ -1747,6 +1749,7 @@ static void ocfs2_inode_init_once(void *data) oi->ip_blkno = 0ULL; oi->ip_clusters = 0; + oi->ip_next_orphan = NULL; ocfs2_resv_init_once(&oi->ip_la_data_resv); @@ -2204,11 +2207,17 @@ static int ocfs2_initialize_super(struct super_block *sb, } if (ocfs2_clusterinfo_valid(osb)) { + /* + * ci_stack and ci_cluster in ocfs2_cluster_info may not be null + * terminated, so make sure no overflow happens here by using + * memcpy. Destination strings will always be null terminated + * because osb is allocated using kzalloc. + */ osb->osb_stackflags = OCFS2_RAW_SB(di)->s_cluster_info.ci_stackflags; - strlcpy(osb->osb_cluster_stack, + memcpy(osb->osb_cluster_stack, OCFS2_RAW_SB(di)->s_cluster_info.ci_stack, - OCFS2_STACK_LABEL_LEN + 1); + OCFS2_STACK_LABEL_LEN); if (strlen(osb->osb_cluster_stack) != OCFS2_STACK_LABEL_LEN) { mlog(ML_ERROR, "couldn't mount because of an invalid " @@ -2217,9 +2226,9 @@ static int ocfs2_initialize_super(struct super_block *sb, status = -EINVAL; goto bail; } - strlcpy(osb->osb_cluster_name, + memcpy(osb->osb_cluster_name, OCFS2_RAW_SB(di)->s_cluster_info.ci_cluster, - OCFS2_CLUSTER_NAME_LEN + 1); + OCFS2_CLUSTER_NAME_LEN); } else { /* The empty string is identical with classic tools that * don't know about s_cluster_info. */ diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index c146e12a8601..54d881c9ac81 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -1219,7 +1219,7 @@ static int ocfs2_xattr_block_get(struct inode *inode, struct ocfs2_xattr_value_root *xv; size_t size; int ret = -ENODATA, name_offset, name_len, i; - int uninitialized_var(block_off); + int block_off; xs->bucket = ocfs2_xattr_bucket_new(inode); if (!xs->bucket) { diff --git a/fs/omfs/file.c b/fs/omfs/file.c index bf83e6644333..ce59b2fb50c7 100644 --- a/fs/omfs/file.c +++ b/fs/omfs/file.c @@ -220,7 +220,7 @@ static int omfs_get_block(struct inode *inode, sector_t block, struct buffer_head *bh; sector_t next, offset; int ret; - u64 uninitialized_var(new_block); + u64 new_block; u32 max_extents; int extent_count; struct omfs_extent *oe; diff --git a/fs/orangefs/dcache.c b/fs/orangefs/dcache.c index fe484cf93e5c..8bbe9486e3a6 100644 --- a/fs/orangefs/dcache.c +++ b/fs/orangefs/dcache.c @@ -26,8 +26,10 @@ static int orangefs_revalidate_lookup(struct dentry *dentry) gossip_debug(GOSSIP_DCACHE_DEBUG, "%s: attempting lookup.\n", __func__); new_op = op_alloc(ORANGEFS_VFS_OP_LOOKUP); - if (!new_op) + if (!new_op) { + ret = -ENOMEM; goto out_put_parent; + } new_op->upcall.req.lookup.sym_follow = ORANGEFS_LOOKUP_LINK_NO_FOLLOW; new_op->upcall.req.lookup.parent_refn = parent->refn; diff --git a/fs/orangefs/orangefs-bufmap.c b/fs/orangefs/orangefs-bufmap.c index c4e98c9c1621..6d20b1b3a581 100644 --- a/fs/orangefs/orangefs-bufmap.c +++ b/fs/orangefs/orangefs-bufmap.c @@ -179,7 +179,7 @@ orangefs_bufmap_free(struct orangefs_bufmap *bufmap) { kfree(bufmap->page_array); kfree(bufmap->desc_array); - kfree(bufmap->buffer_index_array); + bitmap_free(bufmap->buffer_index_array); kfree(bufmap); } @@ -229,8 +229,7 @@ orangefs_bufmap_alloc(struct ORANGEFS_dev_map_desc *user_desc) bufmap->desc_size = user_desc->size; bufmap->desc_shift = ilog2(bufmap->desc_size); - bufmap->buffer_index_array = - kzalloc(DIV_ROUND_UP(bufmap->desc_count, BITS_PER_LONG), GFP_KERNEL); + bufmap->buffer_index_array = bitmap_zalloc(bufmap->desc_count, GFP_KERNEL); if (!bufmap->buffer_index_array) goto out_free_bufmap; @@ -253,7 +252,7 @@ orangefs_bufmap_alloc(struct ORANGEFS_dev_map_desc *user_desc) out_free_desc_array: kfree(bufmap->desc_array); out_free_index_array: - kfree(bufmap->buffer_index_array); + bitmap_free(bufmap->buffer_index_array); out_free_bufmap: kfree(bufmap); out: diff --git a/fs/orangefs/orangefs-debugfs.c b/fs/orangefs/orangefs-debugfs.c index e24738c691f6..f79c015fa7cb 100644 --- a/fs/orangefs/orangefs-debugfs.c +++ b/fs/orangefs/orangefs-debugfs.c @@ -254,6 +254,8 @@ out: void orangefs_debugfs_cleanup(void) { debugfs_remove_recursive(debug_dir); + kfree(debug_help_string); + debug_help_string = NULL; } /* open ORANGEFS_KMOD_DEBUG_HELP_FILE */ @@ -709,6 +711,7 @@ int orangefs_prepare_debugfs_help_string(int at_boot) memset(debug_help_string, 0, DEBUG_HELP_STRING_SIZE); strlcat(debug_help_string, new, string_size); mutex_unlock(&orangefs_help_file_lock); + kfree(new); } rc = 0; diff --git a/fs/orangefs/orangefs-mod.c b/fs/orangefs/orangefs-mod.c index 85ef87245a87..c8818163e392 100644 --- a/fs/orangefs/orangefs-mod.c +++ b/fs/orangefs/orangefs-mod.c @@ -141,7 +141,7 @@ static int __init orangefs_init(void) gossip_err("%s: could not initialize device subsystem %d!\n", __func__, ret); - goto cleanup_device; + goto cleanup_sysfs; } ret = register_filesystem(&orangefs_fs_type); @@ -153,11 +153,11 @@ static int __init orangefs_init(void) goto out; } - orangefs_sysfs_exit(); - -cleanup_device: orangefs_dev_cleanup(); +cleanup_sysfs: + orangefs_sysfs_exit(); + sysfs_init_failed: debugfs_init_failed: diff --git a/fs/orangefs/super.c b/fs/orangefs/super.c index dfaee90d30bd..524fd95173b3 100644 --- a/fs/orangefs/super.c +++ b/fs/orangefs/super.c @@ -195,7 +195,7 @@ static int orangefs_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_bavail = (sector_t) new_op->downcall.resp.statfs.blocks_avail; buf->f_files = (sector_t) new_op->downcall.resp.statfs.files_total; buf->f_ffree = (sector_t) new_op->downcall.resp.statfs.files_avail; - buf->f_frsize = sb->s_blocksize; + buf->f_frsize = 0; out_op_release: op_release(new_op); diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 6eb0b882ad23..debcac35a51d 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -79,6 +79,14 @@ int ovl_copy_xattr(struct dentry *old, struct dentry *new) if (ovl_is_private_xattr(name)) continue; + + error = security_inode_copy_up_xattr(name); + if (error < 0 && error != -EOPNOTSUPP) + break; + if (error == 1) { + error = 0; + continue; /* Discard */ + } retry: size = vfs_getxattr(old, name, value, value_size); if (size == -ERANGE) @@ -102,13 +110,6 @@ retry: goto retry; } - error = security_inode_copy_up_xattr(name); - if (error < 0 && error != -EOPNOTSUPP) - break; - if (error == 1) { - error = 0; - continue; /* Discard */ - } error = vfs_setxattr(new, name, value, size, 0); if (error) break; @@ -194,7 +195,7 @@ static int ovl_set_timestamps(struct dentry *upperdentry, struct kstat *stat) { struct iattr attr = { .ia_valid = - ATTR_ATIME | ATTR_MTIME | ATTR_ATIME_SET | ATTR_MTIME_SET, + ATTR_ATIME | ATTR_MTIME | ATTR_ATIME_SET | ATTR_MTIME_SET | ATTR_CTIME, .ia_atime = stat->atime, .ia_mtime = stat->mtime, }; @@ -712,7 +713,7 @@ static int ovl_copy_up_meta_inode_data(struct ovl_copy_up_ctx *c) struct path upperpath, datapath; int err; char *capability = NULL; - ssize_t uninitialized_var(cap_size); + ssize_t cap_size; ovl_path_upper(c->dentry, &upperpath); if (WARN_ON(upperpath.dentry == NULL)) @@ -823,7 +824,7 @@ static int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry, int ovl_copy_up_flags(struct dentry *dentry, int flags) { int err = 0; - const struct cred *old_cred = ovl_override_creds(dentry->d_sb); + const struct cred *old_cred; bool disconnected = (dentry->d_flags & DCACHE_DISCONNECTED); /* @@ -834,6 +835,7 @@ int ovl_copy_up_flags(struct dentry *dentry, int flags) if (WARN_ON(disconnected && d_is_dir(dentry))) return -EIO; + old_cred = ovl_override_creds(dentry->d_sb); while (!err) { struct dentry *next; struct dentry *parent = NULL; diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 800bcad67325..9fa64dbde97a 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -116,8 +116,7 @@ kill_whiteout: goto out; } -static int ovl_mkdir_real(struct inode *dir, struct dentry **newdentry, - umode_t mode) +int ovl_mkdir_real(struct inode *dir, struct dentry **newdentry, umode_t mode) { int err; struct dentry *d, *dentry = *newdentry; @@ -517,8 +516,10 @@ static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode, goto out_cleanup; } err = ovl_instantiate(dentry, inode, newdentry, hardlink); - if (err) - goto out_cleanup; + if (err) { + ovl_cleanup(udir, newdentry); + dput(newdentry); + } out_dput: dput(upper); out_unlock: @@ -560,28 +561,42 @@ static int ovl_create_or_link(struct dentry *dentry, struct inode *inode, goto out_revert_creds; } - err = -ENOMEM; - override_cred = prepare_creds(); - if (override_cred) { + if (!attr->hardlink) { + err = -ENOMEM; + override_cred = prepare_creds(); + if (!override_cred) + goto out_revert_creds; + /* + * In the creation cases(create, mkdir, mknod, symlink), + * ovl should transfer current's fs{u,g}id to underlying + * fs. Because underlying fs want to initialize its new + * inode owner using current's fs{u,g}id. And in this + * case, the @inode is a new inode that is initialized + * in inode_init_owner() to current's fs{u,g}id. So use + * the inode's i_{u,g}id to override the cred's fs{u,g}id. + * + * But in the other hardlink case, ovl_link() does not + * create a new inode, so just use the ovl mounter's + * fs{u,g}id. + */ override_cred->fsuid = inode->i_uid; override_cred->fsgid = inode->i_gid; - if (!attr->hardlink) { - err = security_dentry_create_files_as(dentry, - attr->mode, &dentry->d_name, old_cred, - override_cred); - if (err) { - put_cred(override_cred); - goto out_revert_creds; - } + err = security_dentry_create_files_as(dentry, + attr->mode, &dentry->d_name, old_cred, + override_cred); + if (err) { + put_cred(override_cred); + goto out_revert_creds; } put_cred(override_creds(override_cred)); put_cred(override_cred); - - if (!ovl_dentry_is_whiteout(dentry)) - err = ovl_create_upper(dentry, inode, attr); - else - err = ovl_create_over_whiteout(dentry, inode, attr); } + + if (!ovl_dentry_is_whiteout(dentry)) + err = ovl_create_upper(dentry, inode, attr); + else + err = ovl_create_over_whiteout(dentry, inode, attr); + out_revert_creds: revert_creds(old_cred); return err; @@ -946,8 +961,8 @@ static char *ovl_get_redirect(struct dentry *dentry, bool abs_redirect) buflen -= thislen; memcpy(&buf[buflen], name, thislen); - tmp = dget_dlock(d->d_parent); spin_unlock(&d->d_lock); + tmp = dget_parent(d); dput(d); d = tmp; @@ -1164,9 +1179,13 @@ static int ovl_rename(struct inode *olddir, struct dentry *old, goto out_dput; } } else { - if (!d_is_negative(newdentry) && - (!new_opaque || !ovl_is_whiteout(newdentry))) - goto out_dput; + if (!d_is_negative(newdentry)) { + if (!new_opaque || !ovl_is_whiteout(newdentry)) + goto out_dput; + } else { + if (flags & RENAME_EXCHANGE) + goto out_dput; + } } if (olddentry == trap) diff --git a/fs/overlayfs/export.c b/fs/overlayfs/export.c index ba6c7c59261a..271f8c9fe253 100644 --- a/fs/overlayfs/export.c +++ b/fs/overlayfs/export.c @@ -277,7 +277,7 @@ static int ovl_encode_fh(struct inode *inode, u32 *fid, int *max_len, return FILEID_INVALID; dentry = d_find_any_alias(inode); - if (WARN_ON(!dentry)) + if (!dentry) return FILEID_INVALID; type = ovl_dentry_to_fh(dentry, fid, max_len); diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 8b3c284ce92e..08e60a6df77c 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -340,7 +340,9 @@ int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char *name, goto out; if (!value && !upperdentry) { + old_cred = ovl_override_creds(dentry->d_sb); err = vfs_getxattr(realdentry, name, NULL, 0); + revert_creds(old_cred); if (err < 0) goto out_drop_write; } diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c index badf039267a2..e51dc7f16596 100644 --- a/fs/overlayfs/namei.c +++ b/fs/overlayfs/namei.c @@ -203,7 +203,7 @@ static int ovl_lookup_single(struct dentry *base, struct ovl_lookup_data *d, int err; bool last_element = !post[0]; - this = lookup_one_len_unlocked(name, base, namelen); + this = lookup_positive_unlocked(name, base, namelen); if (IS_ERR(this)) { err = PTR_ERR(this); this = NULL; @@ -211,8 +211,6 @@ static int ovl_lookup_single(struct dentry *base, struct ovl_lookup_data *d, goto out; goto out_err; } - if (!this->d_inode) - goto put_and_out; if (ovl_dentry_weird(this)) { /* Don't support traversing automounts and other weirdness */ @@ -654,7 +652,7 @@ struct dentry *ovl_get_index_fh(struct ovl_fs *ofs, struct ovl_fh *fh) if (err) return ERR_PTR(err); - index = lookup_one_len_unlocked(name.name, ofs->indexdir, name.len); + index = lookup_positive_unlocked(name.name, ofs->indexdir, name.len); kfree(name.name); if (IS_ERR(index)) { if (PTR_ERR(index) == -ENOENT) @@ -662,9 +660,7 @@ struct dentry *ovl_get_index_fh(struct ovl_fs *ofs, struct ovl_fh *fh) return index; } - if (d_is_negative(index)) - err = 0; - else if (ovl_is_whiteout(index)) + if (ovl_is_whiteout(index)) err = -ESTALE; else if (ovl_dentry_weird(index)) err = -EIO; @@ -688,7 +684,7 @@ struct dentry *ovl_lookup_index(struct ovl_fs *ofs, struct dentry *upper, if (err) return ERR_PTR(err); - index = lookup_one_len_unlocked(name.name, ofs->indexdir, name.len); + index = lookup_positive_unlocked(name.name, ofs->indexdir, name.len); if (IS_ERR(index)) { err = PTR_ERR(index); if (err == -ENOENT) { @@ -703,9 +699,7 @@ struct dentry *ovl_lookup_index(struct ovl_fs *ofs, struct dentry *upper, } inode = d_inode(index); - if (d_is_negative(index)) { - goto out_dput; - } else if (ovl_is_whiteout(index) && !verify) { + if (ovl_is_whiteout(index) && !verify) { /* * When index lookup is called with !verify for decoding an * overlay file handle, a whiteout index implies that decode @@ -1134,7 +1128,7 @@ bool ovl_lower_positive(struct dentry *dentry) struct dentry *this; struct dentry *lowerdir = poe->lowerstack[i].dentry; - this = lookup_one_len_unlocked(name->name, lowerdir, + this = lookup_positive_unlocked(name->name, lowerdir, name->len); if (IS_ERR(this)) { switch (PTR_ERR(this)) { @@ -1151,10 +1145,8 @@ bool ovl_lower_positive(struct dentry *dentry) break; } } else { - if (this->d_inode) { - positive = !ovl_is_whiteout(this); - done = true; - } + positive = !ovl_is_whiteout(this); + done = true; dput(this); } } diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index 265bf9cfde08..8dcede7df2ca 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -402,6 +402,7 @@ struct ovl_cattr { #define OVL_CATTR(m) (&(struct ovl_cattr) { .mode = (m) }) +int ovl_mkdir_real(struct inode *dir, struct dentry **newdentry, umode_t mode); struct dentry *ovl_create_real(struct inode *dir, struct dentry *newdentry, struct ovl_cattr *attr); int ovl_cleanup(struct inode *dir, struct dentry *dentry); diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 246623406db9..1c1eb873e6ec 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -82,7 +82,7 @@ static void ovl_dentry_release(struct dentry *dentry) static struct dentry *ovl_d_real(struct dentry *dentry, const struct inode *inode) { - struct dentry *real; + struct dentry *real = NULL, *lower; /* It's an overlay file */ if (inode && d_inode(dentry) == inode) @@ -101,9 +101,10 @@ static struct dentry *ovl_d_real(struct dentry *dentry, if (real && !inode && ovl_has_upperdata(d_inode(dentry))) return real; - real = ovl_dentry_lowerdata(dentry); - if (!real) + lower = ovl_dentry_lowerdata(dentry); + if (!lower) goto bug; + real = lower; /* Handle recursion */ real = d_real(real, inode); @@ -111,8 +112,10 @@ static struct dentry *ovl_d_real(struct dentry *dentry, if (!inode || inode == d_inode(real)) return real; bug: - WARN(1, "ovl_d_real(%pd4, %s:%lu): real dentry not found\n", dentry, - inode ? inode->i_sb->s_id : "NULL", inode ? inode->i_ino : 0); + WARN(1, "%s(%pd4, %s:%lu): real dentry (%p/%lu) not found\n", + __func__, dentry, inode ? inode->i_sb->s_id : "NULL", + inode ? inode->i_ino : 0, real, + real && d_inode(real) ? d_inode(real)->i_ino : 0); return dentry; } @@ -265,8 +268,8 @@ static int ovl_sync_fs(struct super_block *sb, int wait) return 0; /* - * If this is a sync(2) call or an emergency sync, all the super blocks - * will be iterated, including upper_sb, so no need to do anything. + * Not called for sync(2) call or an emergency sync (SB_I_SKIP_SYNC). + * All the super blocks will be iterated, including upper_sb. * * If this is a syncfs(2) call, then we do need to call * sync_filesystem() on upper_sb, but enough if we do it when being @@ -651,10 +654,14 @@ retry: goto retry; } - work = ovl_create_real(dir, work, OVL_CATTR(attr.ia_mode)); - err = PTR_ERR(work); - if (IS_ERR(work)) - goto out_err; + err = ovl_mkdir_real(dir, &work, attr.ia_mode); + if (err) + goto out_dput; + + /* Weird filesystem returning with hashed negative (kernfs)? */ + err = -EINVAL; + if (d_really_is_negative(work)) + goto out_dput; /* * Try to remove POSIX ACL xattrs from workdir. We are good if: @@ -1476,7 +1483,8 @@ out_err: * - upper/work dir of any overlayfs instance */ static int ovl_check_layer(struct super_block *sb, struct ovl_fs *ofs, - struct dentry *dentry, const char *name) + struct dentry *dentry, const char *name, + bool is_lower) { struct dentry *next = dentry, *parent; int err = 0; @@ -1488,7 +1496,7 @@ static int ovl_check_layer(struct super_block *sb, struct ovl_fs *ofs, /* Walk back ancestors to root (inclusive) looking for traps */ while (!err && parent != next) { - if (ovl_lookup_trap_inode(sb, parent)) { + if (is_lower && ovl_lookup_trap_inode(sb, parent)) { err = -ELOOP; pr_err("overlayfs: overlapping %s path\n", name); } else if (ovl_is_inuse(parent)) { @@ -1514,7 +1522,7 @@ static int ovl_check_overlapping_layers(struct super_block *sb, if (ofs->upper_mnt) { err = ovl_check_layer(sb, ofs, ofs->upper_mnt->mnt_root, - "upperdir"); + "upperdir", false); if (err) return err; @@ -1525,7 +1533,8 @@ static int ovl_check_overlapping_layers(struct super_block *sb, * workbasedir. In that case, we already have their traps in * inode cache and we will catch that case on lookup. */ - err = ovl_check_layer(sb, ofs, ofs->workbasedir, "workdir"); + err = ovl_check_layer(sb, ofs, ofs->workbasedir, "workdir", + false); if (err) return err; } @@ -1533,7 +1542,7 @@ static int ovl_check_overlapping_layers(struct super_block *sb, for (i = 0; i < ofs->numlower; i++) { err = ovl_check_layer(sb, ofs, ofs->lower_layers[i].mnt->mnt_root, - "lowerdir"); + "lowerdir", true); if (err) return err; } @@ -1655,6 +1664,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) sb->s_xattr = ovl_xattr_handlers; sb->s_fs_info = ofs; sb->s_flags |= SB_POSIXACL; + sb->s_iflags |= SB_I_SKIP_SYNC; err = -ENOMEM; root_dentry = d_make_root(ovl_new_inode(sb, S_IFDIR, 0)); diff --git a/fs/pipe.c b/fs/pipe.c index 2a297bce381f..1489257a6c95 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -30,6 +30,21 @@ #include "internal.h" /* + * New pipe buffers will be restricted to this size while the user is exceeding + * their pipe buffer quota. The general pipe use case needs at least two + * buffers: one for data yet to be read, and one for new data. If this is less + * than two, then a write to a non-empty pipe may block even if the pipe is not + * full. This can occur with GNU make jobserver or similar uses of pipes as + * semaphores: multiple processes may be waiting to write tokens back to the + * pipe before reading tokens: https://lore.kernel.org/lkml/1628086770.5rn8p04n6j.none@localhost/. + * + * Users can reduce their pipe buffers with F_SETPIPE_SZ below this at their + * own risk, namely: pipe writes to non-full pipes may block until the pipe is + * emptied. + */ +#define PIPE_MIN_DEF_BUFFERS 2 + +/* * The max size that a non-root user is allowed to grow the pipe. Can * be set by root in /proc/sys/fs/pipe-max-size */ @@ -654,8 +669,8 @@ struct pipe_inode_info *alloc_pipe_info(void) user_bufs = account_pipe_buffers(user, 0, pipe_bufs); if (too_many_pipe_buffers_soft(user_bufs) && is_unprivileged_user()) { - user_bufs = account_pipe_buffers(user, pipe_bufs, 1); - pipe_bufs = 1; + user_bufs = account_pipe_buffers(user, pipe_bufs, PIPE_MIN_DEF_BUFFERS); + pipe_bufs = PIPE_MIN_DEF_BUFFERS; } if (too_many_pipe_buffers_hard(user_bufs) && is_unprivileged_user()) diff --git a/fs/pnode.c b/fs/pnode.c index 7910ae91f17e..d27b7b97c4c1 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -245,7 +245,7 @@ static int propagate_one(struct mount *m) } do { struct mount *parent = last_source->mnt_parent; - if (last_source == first_source) + if (peers(last_source, first_source)) break; done = parent->mnt_master == p; if (done && peers(n, parent)) diff --git a/fs/proc/base.c b/fs/proc/base.c index 3b9b726b1a6c..69f48794b550 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -835,7 +835,7 @@ static ssize_t mem_rw(struct file *file, char __user *buf, flags = FOLL_FORCE | (write ? FOLL_WRITE : 0); while (count > 0) { - int this_len = min_t(int, count, PAGE_SIZE); + size_t this_len = min_t(size_t, count, PAGE_SIZE); if (write && copy_from_user(page, buf, this_len)) { copied = -EFAULT; @@ -1035,7 +1035,6 @@ static ssize_t oom_adj_read(struct file *file, char __user *buf, size_t count, static int __set_oom_adj(struct file *file, int oom_adj, bool legacy) { - static DEFINE_MUTEX(oom_adj_mutex); struct mm_struct *mm = NULL; struct task_struct *task; int err = 0; @@ -1075,7 +1074,7 @@ static int __set_oom_adj(struct file *file, int oom_adj, bool legacy) struct task_struct *p = find_lock_task_mm(task); if (p) { - if (atomic_read(&p->mm->mm_users) > 1) { + if (test_bit(MMF_MULTIPROCESS, &p->mm->flags)) { mm = p->mm; mmgrab(mm); } @@ -2536,6 +2535,13 @@ out: } #ifdef CONFIG_SECURITY +static int proc_pid_attr_open(struct inode *inode, struct file *file) +{ + file->private_data = NULL; + __mem_open(inode, file, PTRACE_MODE_READ_FSCREDS); + return 0; +} + static ssize_t proc_pid_attr_read(struct file * file, char __user * buf, size_t count, loff_t *ppos) { @@ -2565,6 +2571,10 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf, void *page; int rv; + /* A task may only write when it was the opener. */ + if (file->private_data != current->mm) + return -EPERM; + rcu_read_lock(); task = pid_task(proc_pid(inode), PIDTYPE_PID); if (!task) { @@ -2610,9 +2620,11 @@ out: } static const struct file_operations proc_pid_attr_operations = { + .open = proc_pid_attr_open, .read = proc_pid_attr_read, .write = proc_pid_attr_write, .llseek = generic_file_llseek, + .release = mem_release, }; static const struct pid_entry attr_dir_stuff[] = { @@ -3326,7 +3338,8 @@ static int proc_tid_comm_permission(struct inode *inode, int mask) } static const struct inode_operations proc_tid_comm_inode_operations = { - .permission = proc_tid_comm_permission, + .setattr = proc_setattr, + .permission = proc_tid_comm_permission, }; /* diff --git a/fs/proc/generic.c b/fs/proc/generic.c index e39bac94dead..d8b3c6a7173f 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -137,8 +137,12 @@ static int proc_getattr(const struct path *path, struct kstat *stat, { struct inode *inode = d_inode(path->dentry); struct proc_dir_entry *de = PDE(inode); - if (de && de->nlink) - set_nlink(inode, de->nlink); + if (de) { + nlink_t nlink = READ_ONCE(de->nlink); + if (nlink > 0) { + set_nlink(inode, nlink); + } + } generic_fillattr(inode, stat); return 0; @@ -337,6 +341,16 @@ static const struct file_operations proc_dir_operations = { .iterate_shared = proc_readdir, }; +static int proc_net_d_revalidate(struct dentry *dentry, unsigned int flags) +{ + return 0; +} + +const struct dentry_operations proc_net_dentry_ops = { + .d_revalidate = proc_net_d_revalidate, + .d_delete = always_delete_dentry, +}; + /* * proc directories can do almost nothing.. */ @@ -361,6 +375,7 @@ struct proc_dir_entry *proc_register(struct proc_dir_entry *dir, write_unlock(&proc_subdir_lock); goto out_free_inum; } + dir->nlink++; write_unlock(&proc_subdir_lock); return dp; @@ -430,6 +445,9 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent, proc_set_user(ent, (*parent)->uid, (*parent)->gid); ent->proc_dops = &proc_misc_dentry_ops; + /* Revalidate everything under /proc/${pid}/net */ + if ((*parent)->proc_dops == &proc_net_dentry_ops) + pde_force_lookup(ent); out: return ent; @@ -458,8 +476,8 @@ struct proc_dir_entry *proc_symlink(const char *name, } EXPORT_SYMBOL(proc_symlink); -struct proc_dir_entry *proc_mkdir_data(const char *name, umode_t mode, - struct proc_dir_entry *parent, void *data) +struct proc_dir_entry *_proc_mkdir(const char *name, umode_t mode, + struct proc_dir_entry *parent, void *data, bool force_lookup) { struct proc_dir_entry *ent; @@ -471,13 +489,20 @@ struct proc_dir_entry *proc_mkdir_data(const char *name, umode_t mode, ent->data = data; ent->proc_fops = &proc_dir_operations; ent->proc_iops = &proc_dir_inode_operations; - parent->nlink++; + if (force_lookup) { + pde_force_lookup(ent); + } ent = proc_register(parent, ent); - if (!ent) - parent->nlink--; } return ent; } +EXPORT_SYMBOL_GPL(_proc_mkdir); + +struct proc_dir_entry *proc_mkdir_data(const char *name, umode_t mode, + struct proc_dir_entry *parent, void *data) +{ + return _proc_mkdir(name, mode, parent, data, false); +} EXPORT_SYMBOL_GPL(proc_mkdir_data); struct proc_dir_entry *proc_mkdir_mode(const char *name, umode_t mode, @@ -504,10 +529,7 @@ struct proc_dir_entry *proc_create_mount_point(const char *name) ent->data = NULL; ent->proc_fops = NULL; ent->proc_iops = NULL; - parent->nlink++; ent = proc_register(parent, ent); - if (!ent) - parent->nlink--; } return ent; } @@ -665,8 +687,12 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent) len = strlen(fn); de = pde_subdir_find(parent, fn, len); - if (de) + if (de) { rb_erase(&de->subdir_node, &parent->subdir); + if (S_ISDIR(de->mode)) { + parent->nlink--; + } + } write_unlock(&proc_subdir_lock); if (!de) { WARN(1, "name '%s'\n", name); @@ -675,9 +701,6 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent) proc_entry_rundown(de); - if (S_ISDIR(de->mode)) - parent->nlink--; - de->nlink = 0; WARN(pde_subdir_first(de), "%s: removing non-empty directory '%s/%s', leaking at least '%s'\n", __func__, de->parent->name, de->name, pde_subdir_first(de)->name); @@ -713,13 +736,12 @@ int remove_proc_subtree(const char *name, struct proc_dir_entry *parent) de = next; continue; } - write_unlock(&proc_subdir_lock); - - proc_entry_rundown(de); next = de->parent; if (S_ISDIR(de->mode)) next->nlink--; - de->nlink = 0; + write_unlock(&proc_subdir_lock); + + proc_entry_rundown(de); if (de == root) break; pde_put(de); diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 95b14196f284..4f14906ef16b 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -305,3 +305,10 @@ extern unsigned long task_statm(struct mm_struct *, unsigned long *, unsigned long *, unsigned long *, unsigned long *); extern void task_mem(struct seq_file *, struct mm_struct *); + +extern const struct dentry_operations proc_net_dentry_ops; +static inline void pde_force_lookup(struct proc_dir_entry *pde) +{ + /* /proc/net/ entries can be changed under us by setns(CLONE_NEWNET) */ + pde->proc_dops = &proc_net_dentry_ops; +} diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c index a7b12435519e..68ce173d5590 100644 --- a/fs/proc/proc_net.c +++ b/fs/proc/proc_net.c @@ -38,22 +38,6 @@ static struct net *get_proc_net(const struct inode *inode) return maybe_get_net(PDE_NET(PDE(inode))); } -static int proc_net_d_revalidate(struct dentry *dentry, unsigned int flags) -{ - return 0; -} - -static const struct dentry_operations proc_net_dentry_ops = { - .d_revalidate = proc_net_d_revalidate, - .d_delete = always_delete_dentry, -}; - -static void pde_force_lookup(struct proc_dir_entry *pde) -{ - /* /proc/net/ entries can be changed under us by setns(CLONE_NEWNET) */ - pde->proc_dops = &proc_net_dentry_ops; -} - static int seq_open_net(struct inode *inode, struct file *file) { unsigned int state_size = PDE(inode)->state_size; @@ -358,6 +342,9 @@ static __net_init int proc_net_ns_init(struct net *net) proc_set_user(netd, uid, gid); + /* Seed dentry revalidation for /proc/${pid}/net */ + pde_force_lookup(netd); + err = -EEXIST; net_statd = proc_net_mkdir(net, "stat", netd); if (!net_statd) diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index c95f32b83a94..7c62a526506c 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -13,6 +13,7 @@ #include <linux/namei.h> #include <linux/mm.h> #include <linux/module.h> +#include <linux/kmemleak.h> #include "internal.h" static const struct dentry_operations proc_sys_dentry_operations; @@ -1376,6 +1377,38 @@ struct ctl_table_header *register_sysctl(const char *path, struct ctl_table *tab } EXPORT_SYMBOL(register_sysctl); +/** + * __register_sysctl_init() - register sysctl table to path + * @path: path name for sysctl base + * @table: This is the sysctl table that needs to be registered to the path + * @table_name: The name of sysctl table, only used for log printing when + * registration fails + * + * The sysctl interface is used by userspace to query or modify at runtime + * a predefined value set on a variable. These variables however have default + * values pre-set. Code which depends on these variables will always work even + * if register_sysctl() fails. If register_sysctl() fails you'd just loose the + * ability to query or modify the sysctls dynamically at run time. Chances of + * register_sysctl() failing on init are extremely low, and so for both reasons + * this function does not return any error as it is used by initialization code. + * + * Context: Can only be called after your respective sysctl base path has been + * registered. So for instance, most base directories are registered early on + * init before init levels are processed through proc_sys_init() and + * sysctl_init(). + */ +void __init __register_sysctl_init(const char *path, struct ctl_table *table, + const char *table_name) +{ + struct ctl_table_header *hdr = register_sysctl(path, table); + + if (unlikely(!hdr)) { + pr_err("failed when register_sysctl %s to %s\n", table_name, path); + return; + } + kmemleak_not_leak(hdr); +} + static char *append_path(const char *path, char *pos, const char *name) { int namelen; diff --git a/fs/proc/self.c b/fs/proc/self.c index cc6d4253399d..7922edf70ce1 100644 --- a/fs/proc/self.c +++ b/fs/proc/self.c @@ -16,6 +16,13 @@ static const char *proc_self_get_link(struct dentry *dentry, pid_t tgid = task_tgid_nr_ns(current, ns); char *name; + /* + * Not currently supported. Once we can inherit all of struct pid, + * we can allow this. + */ + if (current->flags & PF_KTHREAD) + return ERR_PTR(-EOPNOTSUPP); + if (!tgid) return ERR_PTR(-ENOENT); /* max length of unsigned int in decimal + NULL term */ diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index efa6273c0006..2f2afc3c6fc6 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -701,9 +701,7 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask, page = device_private_entry_to_page(swpent); } if (page) { - int mapcount = page_mapcount(page); - - if (mapcount >= 2) + if (page_mapcount(page) >= 2 || hugetlb_pmd_shared(pte)) mss->shared_hugetlb += huge_page_size(hstate_vma(vma)); else mss->private_hugetlb += huge_page_size(hstate_vma(vma)); @@ -843,7 +841,7 @@ static int show_smaps_rollup(struct seq_file *m, void *v) last_vma_end = vma->vm_end; } - show_vma_header_prefix(m, priv->mm->mmap->vm_start, + show_vma_header_prefix(m, priv->mm->mmap ? priv->mm->mmap->vm_start : 0, last_vma_end, 0, 0, 0, 0); seq_pad(m, ' '); seq_puts(m, "[rollup]\n"); diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index c4147e50af98..f5dfedc01552 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -117,14 +117,19 @@ static ssize_t read_from_oldmem(char *buf, size_t count, nr_bytes = count; /* If pfn is not ram, return zeros for sparse dump files */ - if (pfn_is_ram(pfn) == 0) - memset(buf, 0, nr_bytes); - else { + if (pfn_is_ram(pfn) == 0) { + tmp = 0; + if (!userbuf) + memset(buf, 0, nr_bytes); + else if (clear_user(buf, nr_bytes)) + tmp = -EFAULT; + } else { tmp = copy_oldmem_page(pfn, buf, nr_bytes, offset, userbuf); - if (tmp < 0) - return tmp; } + if (tmp < 0) + return tmp; + *ppos += nr_bytes; count -= nr_bytes; buf += nr_bytes; diff --git a/fs/pstore/Kconfig b/fs/pstore/Kconfig index 503086f7f7c1..d5fb6d95d4d4 100644 --- a/fs/pstore/Kconfig +++ b/fs/pstore/Kconfig @@ -117,6 +117,7 @@ config PSTORE_CONSOLE config PSTORE_PMSG bool "Log user space messages" depends on PSTORE + select RT_MUTEXES help When the option is enabled, pstore will export a character interface /dev/pmsg0 to log user space messages. On reboot diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index 2197bf68f278..904c2a60f5ba 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -250,7 +250,7 @@ static int pstore_compress(const void *in, void *out, { int ret; - if (!IS_ENABLED(CONFIG_PSTORE_COMPRESSION)) + if (!IS_ENABLED(CONFIG_PSTORE_COMPRESS)) return -EINVAL; ret = crypto_comp_compress(tfm, in, inlen, out, &outlen); @@ -650,7 +650,7 @@ static void decompress_record(struct pstore_record *record) int unzipped_len; char *decompressed; - if (!IS_ENABLED(CONFIG_PSTORE_COMPRESSION) || !record->compressed) + if (!IS_ENABLED(CONFIG_PSTORE_COMPRESS) || !record->compressed) return; /* Only PSTORE_TYPE_DMESG support compression. */ diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index bafbab2dd039..33294dee7d7f 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -753,6 +753,7 @@ static int ramoops_probe(struct platform_device *pdev) /* Make sure we didn't get bogus platform data pointer. */ if (!pdata) { pr_err("NULL platform data\n"); + err = -EINVAL; goto fail_out; } @@ -760,6 +761,7 @@ static int ramoops_probe(struct platform_device *pdev) !pdata->ftrace_size && !pdata->pmsg_size)) { pr_err("The memory size and the record/console size must be " "non-zero\n"); + err = -EINVAL; goto fail_out; } diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c index 3c777ec80d47..a6e5022469ab 100644 --- a/fs/pstore/ram_core.c +++ b/fs/pstore/ram_core.c @@ -189,7 +189,7 @@ static int persistent_ram_init_ecc(struct persistent_ram_zone *prz, { int numerr; struct persistent_ram_buffer *buffer = prz->buffer; - int ecc_blocks; + size_t ecc_blocks; size_t ecc_total; if (!ecc_info || !ecc_info->ecc_size) @@ -426,7 +426,11 @@ static void *persistent_ram_vmap(phys_addr_t start, size_t size, phys_addr_t addr = page_start + i * PAGE_SIZE; pages[i] = pfn_to_page(addr >> PAGE_SHIFT); } - vaddr = vmap(pages, page_count, VM_MAP, prot); + /* + * VM_IOREMAP used here to bypass this region during vread() + * and kmap_atomic() (i.e. kcore) to avoid __va() failures. + */ + vaddr = vmap(pages, page_count, VM_MAP | VM_IOREMAP, prot); kfree(pages); /* @@ -496,7 +500,7 @@ static int persistent_ram_post_init(struct persistent_ram_zone *prz, u32 sig, sig ^= PERSISTENT_RAM_SIG; if (prz->buffer->sig == sig) { - if (buffer_size(prz) == 0) { + if (buffer_size(prz) == 0 && buffer_start(prz) == 0) { pr_debug("found existing empty buffer\n"); return 0; } diff --git a/fs/qnx4/dir.c b/fs/qnx4/dir.c index a6ee23aadd28..66645a5a35f3 100644 --- a/fs/qnx4/dir.c +++ b/fs/qnx4/dir.c @@ -15,13 +15,48 @@ #include <linux/buffer_head.h> #include "qnx4.h" +/* + * A qnx4 directory entry is an inode entry or link info + * depending on the status field in the last byte. The + * first byte is where the name start either way, and a + * zero means it's empty. + * + * Also, due to a bug in gcc, we don't want to use the + * real (differently sized) name arrays in the inode and + * link entries, but always the 'de_name[]' one in the + * fake struct entry. + * + * See + * + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=99578#c6 + * + * for details, but basically gcc will take the size of the + * 'name' array from one of the used union entries randomly. + * + * This use of 'de_name[]' (48 bytes) avoids the false positive + * warnings that would happen if gcc decides to use 'inode.di_name' + * (16 bytes) even when the pointer and size were to come from + * 'link.dl_name' (48 bytes). + * + * In all cases the actual name pointer itself is the same, it's + * only the gcc internal 'what is the size of this field' logic + * that can get confused. + */ +union qnx4_directory_entry { + struct { + const char de_name[48]; + u8 de_pad[15]; + u8 de_status; + }; + struct qnx4_inode_entry inode; + struct qnx4_link_info link; +}; + static int qnx4_readdir(struct file *file, struct dir_context *ctx) { struct inode *inode = file_inode(file); unsigned int offset; struct buffer_head *bh; - struct qnx4_inode_entry *de; - struct qnx4_link_info *le; unsigned long blknum; int ix, ino; int size; @@ -38,27 +73,27 @@ static int qnx4_readdir(struct file *file, struct dir_context *ctx) } ix = (ctx->pos >> QNX4_DIR_ENTRY_SIZE_BITS) % QNX4_INODES_PER_BLOCK; for (; ix < QNX4_INODES_PER_BLOCK; ix++, ctx->pos += QNX4_DIR_ENTRY_SIZE) { + union qnx4_directory_entry *de; + offset = ix * QNX4_DIR_ENTRY_SIZE; - de = (struct qnx4_inode_entry *) (bh->b_data + offset); - if (!de->di_fname[0]) + de = (union qnx4_directory_entry *) (bh->b_data + offset); + + if (!de->de_name[0]) continue; - if (!(de->di_status & (QNX4_FILE_USED|QNX4_FILE_LINK))) + if (!(de->de_status & (QNX4_FILE_USED|QNX4_FILE_LINK))) continue; - if (!(de->di_status & QNX4_FILE_LINK)) - size = QNX4_SHORT_NAME_MAX; - else - size = QNX4_NAME_MAX; - size = strnlen(de->di_fname, size); - QNX4DEBUG((KERN_INFO "qnx4_readdir:%.*s\n", size, de->di_fname)); - if (!(de->di_status & QNX4_FILE_LINK)) + if (!(de->de_status & QNX4_FILE_LINK)) { + size = sizeof(de->inode.di_fname); ino = blknum * QNX4_INODES_PER_BLOCK + ix - 1; - else { - le = (struct qnx4_link_info*)de; - ino = ( le32_to_cpu(le->dl_inode_blk) - 1 ) * + } else { + size = sizeof(de->link.dl_fname); + ino = ( le32_to_cpu(de->link.dl_inode_blk) - 1 ) * QNX4_INODES_PER_BLOCK + - le->dl_inode_ndx; + de->link.dl_inode_ndx; } - if (!dir_emit(ctx, de->di_fname, size, ino, DT_UNKNOWN)) { + size = strnlen(de->de_name, size); + QNX4DEBUG((KERN_INFO "qnx4_readdir:%.*s\n", size, name)); + if (!dir_emit(ctx, de->de_name, size, ino, DT_UNKNOWN)) { brelse(bh); return 0; } diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 1d1d393f4208..868936076f41 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -223,18 +223,31 @@ static void put_quota_format(struct quota_format_type *fmt) /* * Dquot List Management: - * The quota code uses three lists for dquot management: the inuse_list, - * free_dquots, and dquot_hash[] array. A single dquot structure may be - * on all three lists, depending on its current state. + * The quota code uses five lists for dquot management: the inuse_list, + * releasing_dquots, free_dquots, dqi_dirty_list, and dquot_hash[] array. + * A single dquot structure may be on some of those lists, depending on + * its current state. * * All dquots are placed to the end of inuse_list when first created, and this * list is used for invalidate operation, which must look at every dquot. * - * Unused dquots (dq_count == 0) are added to the free_dquots list when freed, - * and this list is searched whenever we need an available dquot. Dquots are - * removed from the list as soon as they are used again, and - * dqstats.free_dquots gives the number of dquots on the list. When - * dquot is invalidated it's completely released from memory. + * When the last reference of a dquot is dropped, the dquot is added to + * releasing_dquots. We'll then queue work item which will call + * synchronize_srcu() and after that perform the final cleanup of all the + * dquots on the list. Each cleaned up dquot is moved to free_dquots list. + * Both releasing_dquots and free_dquots use the dq_free list_head in the dquot + * struct. + * + * Unused and cleaned up dquots are in the free_dquots list and this list is + * searched whenever we need an available dquot. Dquots are removed from the + * list as soon as they are used again and dqstats.free_dquots gives the number + * of dquots on the list. When dquot is invalidated it's completely released + * from memory. + * + * Dirty dquots are added to the dqi_dirty_list of quota_info when mark + * dirtied, and this list is searched when writing dirty dquots back to + * quota file. Note that some filesystems do dirty dquot tracking on their + * own (e.g. in a journal) and thus don't use dqi_dirty_list. * * Dquots with a specific identity (device, type and id) are placed on * one of the dquot_hash[] hash chains. The provides an efficient search @@ -243,6 +256,7 @@ static void put_quota_format(struct quota_format_type *fmt) static LIST_HEAD(inuse_list); static LIST_HEAD(free_dquots); +static LIST_HEAD(releasing_dquots); static unsigned int dq_hash_bits, dq_hash_mask; static struct hlist_head *dquot_hash; @@ -253,6 +267,9 @@ static qsize_t inode_get_rsv_space(struct inode *inode); static qsize_t __inode_get_rsv_space(struct inode *inode); static int __dquot_initialize(struct inode *inode, int type); +static void quota_release_workfn(struct work_struct *work); +static DECLARE_DELAYED_WORK(quota_release_work, quota_release_workfn); + static inline unsigned int hashfn(const struct super_block *sb, struct kqid qid) { @@ -300,12 +317,21 @@ static inline void put_dquot_last(struct dquot *dquot) dqstats_inc(DQST_FREE_DQUOTS); } +static inline void put_releasing_dquots(struct dquot *dquot) +{ + list_add_tail(&dquot->dq_free, &releasing_dquots); + set_bit(DQ_RELEASING_B, &dquot->dq_flags); +} + static inline void remove_free_dquot(struct dquot *dquot) { if (list_empty(&dquot->dq_free)) return; list_del_init(&dquot->dq_free); - dqstats_dec(DQST_FREE_DQUOTS); + if (!test_bit(DQ_RELEASING_B, &dquot->dq_flags)) + dqstats_dec(DQST_FREE_DQUOTS); + else + clear_bit(DQ_RELEASING_B, &dquot->dq_flags); } static inline void put_inuse(struct dquot *dquot) @@ -331,6 +357,11 @@ static void wait_on_dquot(struct dquot *dquot) mutex_unlock(&dquot->dq_lock); } +static inline int dquot_active(struct dquot *dquot) +{ + return test_bit(DQ_ACTIVE_B, &dquot->dq_flags); +} + static inline int dquot_dirty(struct dquot *dquot) { return test_bit(DQ_MOD_B, &dquot->dq_flags); @@ -346,14 +377,14 @@ int dquot_mark_dquot_dirty(struct dquot *dquot) { int ret = 1; - if (!test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) + if (!dquot_active(dquot)) return 0; if (sb_dqopt(dquot->dq_sb)->flags & DQUOT_NOLIST_DIRTY) return test_and_set_bit(DQ_MOD_B, &dquot->dq_flags); /* If quota is dirty already, we don't have to acquire dq_list_lock */ - if (test_bit(DQ_MOD_B, &dquot->dq_flags)) + if (dquot_dirty(dquot)) return 1; spin_lock(&dq_list_lock); @@ -432,7 +463,7 @@ int dquot_acquire(struct dquot *dquot) smp_mb__before_atomic(); set_bit(DQ_READ_B, &dquot->dq_flags); /* Instantiate dquot if needed */ - if (!test_bit(DQ_ACTIVE_B, &dquot->dq_flags) && !dquot->dq_off) { + if (!dquot_active(dquot) && !dquot->dq_off) { ret = dqopt->ops[dquot->dq_id.type]->commit_dqblk(dquot); /* Write the info if needed */ if (info_dirty(&dqopt->info[dquot->dq_id.type])) { @@ -471,7 +502,7 @@ int dquot_commit(struct dquot *dquot) goto out_lock; /* Inactive dquot can be only if there was error during read/init * => we have better not writing it */ - if (test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) + if (dquot_active(dquot)) ret = dqopt->ops[dquot->dq_id.type]->commit_dqblk(dquot); else ret = -EIO; @@ -532,6 +563,8 @@ static void invalidate_dquots(struct super_block *sb, int type) struct dquot *dquot, *tmp; restart: + flush_delayed_work("a_release_work); + spin_lock(&dq_list_lock); list_for_each_entry_safe(dquot, tmp, &inuse_list, dq_inuse) { if (dquot->dq_sb != sb) @@ -540,7 +573,7 @@ restart: continue; /* Wait for dquot users */ if (atomic_read(&dquot->dq_count)) { - dqgrab(dquot); + atomic_inc(&dquot->dq_count); spin_unlock(&dq_list_lock); /* * Once dqput() wakes us up, we know it's time to free @@ -559,6 +592,15 @@ restart: goto restart; } /* + * The last user already dropped its reference but dquot didn't + * get fully cleaned up yet. Restart the scan which flushes the + * work cleaning up released dquots. + */ + if (test_bit(DQ_RELEASING_B, &dquot->dq_flags)) { + spin_unlock(&dq_list_lock); + goto restart; + } + /* * Quota now has no users and it has been written on last * dqput() */ @@ -582,14 +624,13 @@ int dquot_scan_active(struct super_block *sb, spin_lock(&dq_list_lock); list_for_each_entry(dquot, &inuse_list, dq_inuse) { - if (!test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) + if (!dquot_active(dquot)) continue; if (dquot->dq_sb != sb) continue; /* Now we have active dquot so we can just increase use count */ atomic_inc(&dquot->dq_count); spin_unlock(&dq_list_lock); - dqstats_inc(DQST_LOOKUPS); dqput(old_dquot); old_dquot = dquot; /* @@ -598,7 +639,7 @@ int dquot_scan_active(struct super_block *sb, * outstanding call and recheck the DQ_ACTIVE_B after that. */ wait_on_dquot(dquot); - if (test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) { + if (dquot_active(dquot)) { ret = fn(dquot, priv); if (ret < 0) goto out; @@ -614,6 +655,18 @@ out: } EXPORT_SYMBOL(dquot_scan_active); +static inline int dquot_write_dquot(struct dquot *dquot) +{ + int ret = dquot->dq_sb->dq_op->write_dquot(dquot); + if (ret < 0) { + quota_error(dquot->dq_sb, "Can't write quota structure " + "(error %d). Quota may get out of sync!", ret); + /* Clear dirty bit anyway to avoid infinite loop. */ + clear_dquot_dirty(dquot); + } + return ret; +} + /* Write all dquot structures to quota files */ int dquot_writeback_dquots(struct super_block *sb, int type) { @@ -637,24 +690,23 @@ int dquot_writeback_dquots(struct super_block *sb, int type) dquot = list_first_entry(&dirty, struct dquot, dq_dirty); - WARN_ON(!test_bit(DQ_ACTIVE_B, &dquot->dq_flags)); + WARN_ON(!dquot_active(dquot)); + /* If the dquot is releasing we should not touch it */ + if (test_bit(DQ_RELEASING_B, &dquot->dq_flags)) { + spin_unlock(&dq_list_lock); + flush_delayed_work("a_release_work); + spin_lock(&dq_list_lock); + continue; + } /* Now we have active dquot from which someone is * holding reference so we can safely just increase * use count */ dqgrab(dquot); spin_unlock(&dq_list_lock); - dqstats_inc(DQST_LOOKUPS); - err = sb->dq_op->write_dquot(dquot); - if (err) { - /* - * Clear dirty bit anyway to avoid infinite - * loop here. - */ - clear_dquot_dirty(dquot); - if (!ret) - ret = err; - } + err = dquot_write_dquot(dquot); + if (err && !ret) + ret = err; dqput(dquot); spin_lock(&dq_list_lock); } @@ -687,9 +739,14 @@ int dquot_quota_sync(struct super_block *sb, int type) /* This is not very clever (and fast) but currently I don't know about * any other simple way of getting quota data to disk and we must get * them there for userspace to be visible... */ - if (sb->s_op->sync_fs) - sb->s_op->sync_fs(sb, 1); - sync_blockdev(sb->s_bdev); + if (sb->s_op->sync_fs) { + ret = sb->s_op->sync_fs(sb, 1); + if (ret) + return ret; + } + ret = sync_blockdev(sb->s_bdev); + if (ret) + return ret; /* * Now when everything is written we can discard the pagecache so @@ -743,12 +800,52 @@ static struct shrinker dqcache_shrinker = { }; /* + * Safely release dquot and put reference to dquot. + */ +static void quota_release_workfn(struct work_struct *work) +{ + struct dquot *dquot; + struct list_head rls_head; + + spin_lock(&dq_list_lock); + /* Exchange the list head to avoid livelock. */ + list_replace_init(&releasing_dquots, &rls_head); + spin_unlock(&dq_list_lock); + synchronize_srcu(&dquot_srcu); + +restart: + spin_lock(&dq_list_lock); + while (!list_empty(&rls_head)) { + dquot = list_first_entry(&rls_head, struct dquot, dq_free); + WARN_ON_ONCE(atomic_read(&dquot->dq_count)); + /* + * Note that DQ_RELEASING_B protects us from racing with + * invalidate_dquots() calls so we are safe to work with the + * dquot even after we drop dq_list_lock. + */ + if (dquot_dirty(dquot)) { + spin_unlock(&dq_list_lock); + /* Commit dquot before releasing */ + dquot_write_dquot(dquot); + goto restart; + } + if (dquot_active(dquot)) { + spin_unlock(&dq_list_lock); + dquot->dq_sb->dq_op->release_dquot(dquot); + goto restart; + } + /* Dquot is inactive and clean, now move it to free list */ + remove_free_dquot(dquot); + put_dquot_last(dquot); + } + spin_unlock(&dq_list_lock); +} + +/* * Put reference to dquot */ void dqput(struct dquot *dquot) { - int ret; - if (!dquot) return; #ifdef CONFIG_QUOTA_DEBUG @@ -760,7 +857,7 @@ void dqput(struct dquot *dquot) } #endif dqstats_inc(DQST_DROPS); -we_slept: + spin_lock(&dq_list_lock); if (atomic_read(&dquot->dq_count) > 1) { /* We have more than one user... nothing to do */ @@ -772,35 +869,16 @@ we_slept: spin_unlock(&dq_list_lock); return; } + /* Need to release dquot? */ - if (dquot_dirty(dquot)) { - spin_unlock(&dq_list_lock); - /* Commit dquot before releasing */ - ret = dquot->dq_sb->dq_op->write_dquot(dquot); - if (ret < 0) { - quota_error(dquot->dq_sb, "Can't write quota structure" - " (error %d). Quota may get out of sync!", - ret); - /* - * We clear dirty bit anyway, so that we avoid - * infinite loop here - */ - clear_dquot_dirty(dquot); - } - goto we_slept; - } - if (test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) { - spin_unlock(&dq_list_lock); - dquot->dq_sb->dq_op->release_dquot(dquot); - goto we_slept; - } - atomic_dec(&dquot->dq_count); #ifdef CONFIG_QUOTA_DEBUG /* sanity check */ BUG_ON(!list_empty(&dquot->dq_free)); #endif - put_dquot_last(dquot); + put_releasing_dquots(dquot); + atomic_dec(&dquot->dq_count); spin_unlock(&dq_list_lock); + queue_delayed_work(system_unbound_wq, "a_release_work, 1); } EXPORT_SYMBOL(dqput); @@ -887,10 +965,10 @@ we_slept: dqstats_inc(DQST_LOOKUPS); } /* Wait for dq_lock - after this we know that either dquot_release() is - * already finished or it will be canceled due to dq_count > 1 test */ + * already finished or it will be canceled due to dq_count > 0 test */ wait_on_dquot(dquot); /* Read the dquot / allocate space in quota file */ - if (!test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) { + if (!dquot_active(dquot)) { int err; err = sb->dq_op->acquire_dquot(dquot); @@ -1403,7 +1481,7 @@ static int info_bdq_free(struct dquot *dquot, qsize_t space) return QUOTA_NL_NOWARN; } -static int dquot_active(const struct inode *inode) +static int inode_quota_active(const struct inode *inode) { struct super_block *sb = inode->i_sb; @@ -1426,7 +1504,7 @@ static int __dquot_initialize(struct inode *inode, int type) qsize_t rsv; int ret = 0; - if (!dquot_active(inode)) + if (!inode_quota_active(inode)) return 0; dquots = i_dquot(inode); @@ -1534,7 +1612,7 @@ bool dquot_initialize_needed(struct inode *inode) struct dquot **dquots; int i; - if (!dquot_active(inode)) + if (!inode_quota_active(inode)) return false; dquots = i_dquot(inode); @@ -1645,7 +1723,7 @@ int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags) int reserve = flags & DQUOT_SPACE_RESERVE; struct dquot **dquots; - if (!dquot_active(inode)) { + if (!inode_quota_active(inode)) { if (reserve) { spin_lock(&inode->i_lock); *inode_reserved_space(inode) += number; @@ -1717,7 +1795,7 @@ int dquot_alloc_inode(struct inode *inode) struct dquot_warn warn[MAXQUOTAS]; struct dquot * const *dquots; - if (!dquot_active(inode)) + if (!inode_quota_active(inode)) return 0; for (cnt = 0; cnt < MAXQUOTAS; cnt++) warn[cnt].w_type = QUOTA_NL_NOWARN; @@ -1760,7 +1838,7 @@ int dquot_claim_space_nodirty(struct inode *inode, qsize_t number) struct dquot **dquots; int cnt, index; - if (!dquot_active(inode)) { + if (!inode_quota_active(inode)) { spin_lock(&inode->i_lock); *inode_reserved_space(inode) -= number; __inode_add_bytes(inode, number); @@ -1802,7 +1880,7 @@ void dquot_reclaim_space_nodirty(struct inode *inode, qsize_t number) struct dquot **dquots; int cnt, index; - if (!dquot_active(inode)) { + if (!inode_quota_active(inode)) { spin_lock(&inode->i_lock); *inode_reserved_space(inode) += number; __inode_sub_bytes(inode, number); @@ -1846,7 +1924,7 @@ void __dquot_free_space(struct inode *inode, qsize_t number, int flags) struct dquot **dquots; int reserve = flags & DQUOT_SPACE_RESERVE, index; - if (!dquot_active(inode)) { + if (!inode_quota_active(inode)) { if (reserve) { spin_lock(&inode->i_lock); *inode_reserved_space(inode) -= number; @@ -1901,7 +1979,7 @@ void dquot_free_inode(struct inode *inode) struct dquot * const *dquots; int index; - if (!dquot_active(inode)) + if (!inode_quota_active(inode)) return; dquots = i_dquot(inode); @@ -2072,7 +2150,7 @@ int dquot_transfer(struct inode *inode, struct iattr *iattr) struct super_block *sb = inode->i_sb; int ret; - if (!dquot_active(inode)) + if (!inode_quota_active(inode)) return 0; if (iattr->ia_valid & ATTR_UID && !uid_eq(iattr->ia_uid, inode->i_uid)){ @@ -2293,28 +2371,76 @@ EXPORT_SYMBOL(dquot_quota_off); * Turn quotas on on a device */ -/* - * Helper function to turn quotas on when we already have the inode of - * quota file and no quota information is loaded. - */ -static int vfs_load_quota_inode(struct inode *inode, int type, int format_id, +static int vfs_setup_quota_inode(struct inode *inode, int type) +{ + struct super_block *sb = inode->i_sb; + struct quota_info *dqopt = sb_dqopt(sb); + + if (is_bad_inode(inode)) + return -EUCLEAN; + if (!S_ISREG(inode->i_mode)) + return -EACCES; + if (IS_RDONLY(inode)) + return -EROFS; + if (sb_has_quota_loaded(sb, type)) + return -EBUSY; + + /* + * Quota files should never be encrypted. They should be thought of as + * filesystem metadata, not user data. New-style internal quota files + * cannot be encrypted by users anyway, but old-style external quota + * files could potentially be incorrectly created in an encrypted + * directory, hence this explicit check. Some reasons why encrypted + * quota files don't work include: (1) some filesystems that support + * encryption don't handle it in their quota_read and quota_write, and + * (2) cleaning up encrypted quota files at unmount would need special + * consideration, as quota files are cleaned up later than user files. + */ + if (IS_ENCRYPTED(inode)) + return -EINVAL; + + dqopt->files[type] = igrab(inode); + if (!dqopt->files[type]) + return -EIO; + if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE)) { + /* We don't want quota and atime on quota files (deadlocks + * possible) Also nobody should write to the file - we use + * special IO operations which ignore the immutable bit. */ + inode_lock(inode); + inode->i_flags |= S_NOQUOTA; + inode_unlock(inode); + /* + * When S_NOQUOTA is set, remove dquot references as no more + * references can be added + */ + __dquot_drop(inode); + } + return 0; +} + +static void vfs_cleanup_quota_inode(struct super_block *sb, int type) +{ + struct quota_info *dqopt = sb_dqopt(sb); + struct inode *inode = dqopt->files[type]; + + if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE)) { + inode_lock(inode); + inode->i_flags &= ~S_NOQUOTA; + inode_unlock(inode); + } + dqopt->files[type] = NULL; + iput(inode); +} + +int dquot_load_quota_sb(struct super_block *sb, int type, int format_id, unsigned int flags) { struct quota_format_type *fmt = find_quota_format(format_id); - struct super_block *sb = inode->i_sb; struct quota_info *dqopt = sb_dqopt(sb); int error; if (!fmt) return -ESRCH; - if (!S_ISREG(inode->i_mode)) { - error = -EACCES; - goto out_fmt; - } - if (IS_RDONLY(inode)) { - error = -EROFS; - goto out_fmt; - } if (!sb->s_op->quota_write || !sb->s_op->quota_read || (type == PRJQUOTA && sb->dq_op->get_projid == NULL)) { error = -EINVAL; @@ -2346,27 +2472,9 @@ static int vfs_load_quota_inode(struct inode *inode, int type, int format_id, invalidate_bdev(sb->s_bdev); } - if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE)) { - /* We don't want quota and atime on quota files (deadlocks - * possible) Also nobody should write to the file - we use - * special IO operations which ignore the immutable bit. */ - inode_lock(inode); - inode->i_flags |= S_NOQUOTA; - inode_unlock(inode); - /* - * When S_NOQUOTA is set, remove dquot references as no more - * references can be added - */ - __dquot_drop(inode); - } - - error = -EIO; - dqopt->files[type] = igrab(inode); - if (!dqopt->files[type]) - goto out_file_flags; error = -EINVAL; if (!fmt->qf_ops->check_quota_file(sb, type)) - goto out_file_init; + goto out_fmt; dqopt->ops[type] = fmt->qf_ops; dqopt->info[type].dqi_format = fmt; @@ -2374,7 +2482,7 @@ static int vfs_load_quota_inode(struct inode *inode, int type, int format_id, INIT_LIST_HEAD(&dqopt->info[type].dqi_dirty_list); error = dqopt->ops[type]->read_file_info(sb, type); if (error < 0) - goto out_file_init; + goto out_fmt; if (dqopt->flags & DQUOT_QUOTA_SYS_FILE) { spin_lock(&dq_data_lock); dqopt->info[type].dqi_flags |= DQF_SYS_FILE; @@ -2386,21 +2494,34 @@ static int vfs_load_quota_inode(struct inode *inode, int type, int format_id, error = add_dquot_ref(sb, type); if (error) - dquot_disable(sb, type, flags); + dquot_disable(sb, type, + DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED); return error; -out_file_init: - dqopt->files[type] = NULL; - iput(inode); -out_file_flags: - inode_lock(inode); - inode->i_flags &= ~S_NOQUOTA; - inode_unlock(inode); out_fmt: put_quota_format(fmt); return error; } +EXPORT_SYMBOL(dquot_load_quota_sb); + +/* + * Helper function to turn quotas on when we already have the inode of + * quota file and no quota information is loaded. + */ +static int vfs_load_quota_inode(struct inode *inode, int type, int format_id, + unsigned int flags) +{ + int err; + + err = vfs_setup_quota_inode(inode, type); + if (err < 0) + return err; + err = dquot_load_quota_sb(inode->i_sb, type, format_id, flags); + if (err < 0) + vfs_cleanup_quota_inode(inode->i_sb, type); + return err; +} /* Reenable quotas on remount RW */ int dquot_resume(struct super_block *sb, int type) @@ -2501,21 +2622,15 @@ int dquot_quota_on_mount(struct super_block *sb, char *qf_name, struct dentry *dentry; int error; - dentry = lookup_one_len_unlocked(qf_name, sb->s_root, strlen(qf_name)); + dentry = lookup_positive_unlocked(qf_name, sb->s_root, strlen(qf_name)); if (IS_ERR(dentry)) return PTR_ERR(dentry); - if (d_really_is_negative(dentry)) { - error = -ENOENT; - goto out; - } - error = security_quota_on(dentry); if (!error) error = vfs_load_quota_inode(d_inode(dentry), type, format_id, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED); -out: dput(dentry); return error; } diff --git a/fs/quota/quota_tree.c b/fs/quota/quota_tree.c index bb3f59bcfcf5..ae2ed96d4847 100644 --- a/fs/quota/quota_tree.c +++ b/fs/quota/quota_tree.c @@ -61,7 +61,7 @@ static ssize_t read_blk(struct qtree_mem_dqinfo *info, uint blk, char *buf) memset(buf, 0, info->dqi_usable_bs); return sb->s_op->quota_read(sb, info->dqi_type, buf, - info->dqi_usable_bs, blk << info->dqi_blocksize_bits); + info->dqi_usable_bs, (loff_t)blk << info->dqi_blocksize_bits); } static ssize_t write_blk(struct qtree_mem_dqinfo *info, uint blk, char *buf) @@ -70,7 +70,7 @@ static ssize_t write_blk(struct qtree_mem_dqinfo *info, uint blk, char *buf) ssize_t ret; ret = sb->s_op->quota_write(sb, info->dqi_type, buf, - info->dqi_usable_bs, blk << info->dqi_blocksize_bits); + info->dqi_usable_bs, (loff_t)blk << info->dqi_blocksize_bits); if (ret != info->dqi_usable_bs) { quota_error(sb, "dquota write failed"); if (ret >= 0) @@ -79,6 +79,35 @@ static ssize_t write_blk(struct qtree_mem_dqinfo *info, uint blk, char *buf) return ret; } +static inline int do_check_range(struct super_block *sb, const char *val_name, + uint val, uint min_val, uint max_val) +{ + if (val < min_val || val > max_val) { + quota_error(sb, "Getting %s %u out of range %u-%u", + val_name, val, min_val, max_val); + return -EUCLEAN; + } + + return 0; +} + +static int check_dquot_block_header(struct qtree_mem_dqinfo *info, + struct qt_disk_dqdbheader *dh) +{ + int err = 0; + + err = do_check_range(info->dqi_sb, "dqdh_next_free", + le32_to_cpu(dh->dqdh_next_free), 0, + info->dqi_blocks - 1); + if (err) + return err; + err = do_check_range(info->dqi_sb, "dqdh_prev_free", + le32_to_cpu(dh->dqdh_prev_free), 0, + info->dqi_blocks - 1); + + return err; +} + /* Remove empty block from list and return it */ static int get_free_dqblk(struct qtree_mem_dqinfo *info) { @@ -93,6 +122,9 @@ static int get_free_dqblk(struct qtree_mem_dqinfo *info) ret = read_blk(info, blk, buf); if (ret < 0) goto out_buf; + ret = check_dquot_block_header(info, dh); + if (ret) + goto out_buf; info->dqi_free_blk = le32_to_cpu(dh->dqdh_next_free); } else { @@ -240,6 +272,9 @@ static uint find_free_dqentry(struct qtree_mem_dqinfo *info, *err = read_blk(info, blk, buf); if (*err < 0) goto out_buf; + *err = check_dquot_block_header(info, dh); + if (*err) + goto out_buf; } else { blk = get_free_dqblk(info); if ((int)blk < 0) { @@ -283,7 +318,7 @@ static uint find_free_dqentry(struct qtree_mem_dqinfo *info, blk); goto out_buf; } - dquot->dq_off = (blk << info->dqi_blocksize_bits) + + dquot->dq_off = ((loff_t)blk << info->dqi_blocksize_bits) + sizeof(struct qt_disk_dqdbheader) + i * info->dqi_entry_size; kfree(buf); @@ -422,6 +457,7 @@ static int free_dqentry(struct qtree_mem_dqinfo *info, struct dquot *dquot, quota_error(dquot->dq_sb, "Quota structure has offset to " "other block (%u) than it should (%u)", blk, (uint)(dquot->dq_off >> info->dqi_blocksize_bits)); + ret = -EIO; goto out_buf; } ret = read_blk(info, blk, buf); @@ -431,6 +467,9 @@ static int free_dqentry(struct qtree_mem_dqinfo *info, struct dquot *dquot, goto out_buf; } dh = (struct qt_disk_dqdbheader *)buf; + ret = check_dquot_block_header(info, dh); + if (ret) + goto out_buf; le16_add_cpu(&dh->dqdh_entries, -1); if (!le16_to_cpu(dh->dqdh_entries)) { /* Block got free? */ ret = remove_free_dqentry(info, buf, blk); @@ -487,6 +526,13 @@ static int remove_tree(struct qtree_mem_dqinfo *info, struct dquot *dquot, goto out_buf; } newblk = le32_to_cpu(ref[get_index(info, dquot->dq_id, depth)]); + if (newblk < QT_TREEOFF || newblk >= info->dqi_blocks) { + quota_error(dquot->dq_sb, "Getting block too big (%u >= %u)", + newblk, info->dqi_blocks); + ret = -EUCLEAN; + goto out_buf; + } + if (depth == info->dqi_qtree_depth - 1) { ret = free_dqentry(info, dquot, newblk); newblk = 0; @@ -558,7 +604,7 @@ static loff_t find_block_dqentry(struct qtree_mem_dqinfo *info, ret = -EIO; goto out_buf; } else { - ret = (blk << info->dqi_blocksize_bits) + sizeof(struct + ret = ((loff_t)blk << info->dqi_blocksize_bits) + sizeof(struct qt_disk_dqdbheader) + i * info->dqi_entry_size; } out_buf: @@ -586,6 +632,13 @@ static loff_t find_tree_dqentry(struct qtree_mem_dqinfo *info, blk = le32_to_cpu(ref[get_index(info, dquot->dq_id, depth)]); if (!blk) /* No reference? */ goto out_buf; + if (blk < QT_TREEOFF || blk >= info->dqi_blocks) { + quota_error(dquot->dq_sb, "Getting block too big (%u >= %u)", + blk, info->dqi_blocks); + ret = -EUCLEAN; + goto out_buf; + } + if (depth < info->dqi_qtree_depth - 1) ret = find_tree_dqentry(info, dquot, blk, depth+1); else diff --git a/fs/quota/quota_v2.c b/fs/quota/quota_v2.c index a73e5b34db41..addfaae8decf 100644 --- a/fs/quota/quota_v2.c +++ b/fs/quota/quota_v2.c @@ -158,7 +158,31 @@ static int v2_read_file_info(struct super_block *sb, int type) qinfo->dqi_entry_size = sizeof(struct v2r1_disk_dqblk); qinfo->dqi_ops = &v2r1_qtree_ops; } + ret = -EUCLEAN; + /* Some sanity checks of the read headers... */ + if ((loff_t)qinfo->dqi_blocks << qinfo->dqi_blocksize_bits > + i_size_read(sb_dqopt(sb)->files[type])) { + quota_error(sb, "Number of blocks too big for quota file size (%llu > %llu).", + (loff_t)qinfo->dqi_blocks << qinfo->dqi_blocksize_bits, + i_size_read(sb_dqopt(sb)->files[type])); + goto out_free; + } + if (qinfo->dqi_free_blk >= qinfo->dqi_blocks) { + quota_error(sb, "Free block number too big (%u >= %u).", + qinfo->dqi_free_blk, qinfo->dqi_blocks); + goto out_free; + } + if (qinfo->dqi_free_entry >= qinfo->dqi_blocks) { + quota_error(sb, "Block with free entry too big (%u >= %u).", + qinfo->dqi_free_entry, qinfo->dqi_blocks); + goto out_free; + } ret = 0; +out_free: + if (ret) { + kfree(info->dqi_priv); + info->dqi_priv = NULL; + } out: up_read(&dqopt->dqio_sem); return ret; @@ -283,6 +307,7 @@ static void v2r1_mem2diskdqb(void *dp, struct dquot *dquot) d->dqb_curspace = cpu_to_le64(m->dqb_curspace); d->dqb_btime = cpu_to_le64(m->dqb_btime); d->dqb_id = cpu_to_le32(from_kqid(&init_user_ns, dquot->dq_id)); + d->dqb_pad = 0; if (qtree_entry_unused(info, dp)) d->dqb_itime = cpu_to_le64(1); } diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c index 3ac1f2387083..5e1ebbe639eb 100644 --- a/fs/ramfs/file-nommu.c +++ b/fs/ramfs/file-nommu.c @@ -228,7 +228,7 @@ static unsigned long ramfs_nommu_get_unmapped_area(struct file *file, if (!pages) goto out_free; - nr = find_get_pages(inode->i_mapping, &pgoff, lpages, pages); + nr = find_get_pages_contig(inode->i_mapping, pgoff, lpages, pages); if (nr != lpages) goto out_free_pages; /* leave if some pages were missing */ diff --git a/fs/readdir.c b/fs/readdir.c index 443270f635f4..3c5ce8a0ddc9 100644 --- a/fs/readdir.c +++ b/fs/readdir.c @@ -132,6 +132,9 @@ static int fillonedir(struct dir_context *ctx, const char *name, int namlen, if (buf->result) return -EINVAL; + buf->result = verify_dirent_name(name, namlen); + if (buf->result < 0) + return buf->result; d_ino = ino; if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) { buf->result = -EOVERFLOW; @@ -398,6 +401,9 @@ static int compat_fillonedir(struct dir_context *ctx, const char *name, if (buf->result) return -EINVAL; + buf->result = verify_dirent_name(name, namlen); + if (buf->result < 0) + return buf->result; d_ino = ino; if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) { buf->result = -EOVERFLOW; diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index 6419e6dacc39..ac35ddf0dd60 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -1553,11 +1553,7 @@ void reiserfs_read_locked_inode(struct inode *inode, * set version 1, version 2 could be used too, because stat data * key is the same in both versions */ - key.version = KEY_FORMAT_3_5; - key.on_disk_key.k_dir_id = dirino; - key.on_disk_key.k_objectid = inode->i_ino; - key.on_disk_key.k_offset = 0; - key.on_disk_key.k_type = 0; + _make_cpu_key(&key, KEY_FORMAT_3_5, dirino, inode->i_ino, 0, 0, 3); /* look for the object's stat data */ retval = search_item(inode->i_sb, &key, &path_to_sd); @@ -2165,7 +2161,8 @@ out_end_trans: out_inserted_sd: clear_nlink(inode); th->t_trans_id = 0; /* so the caller can't use this handle later */ - unlock_new_inode(inode); /* OK to do even if we hadn't locked it */ + if (inode->i_state & I_NEW) + unlock_new_inode(inode); iput(inode); return err; } diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c index 8a76f9d14bc6..3425a04bc8a0 100644 --- a/fs/reiserfs/journal.c +++ b/fs/reiserfs/journal.c @@ -2336,7 +2336,7 @@ static struct buffer_head *reiserfs_breada(struct block_device *dev, int i, j; bh = __getblk(dev, block, bufsize); - if (buffer_uptodate(bh)) + if (!bh || buffer_uptodate(bh)) return (bh); if (block + BUFNR > max_block) { @@ -2346,6 +2346,8 @@ static struct buffer_head *reiserfs_breada(struct block_device *dev, j = 1; for (i = 1; i < blocks; i++) { bh = __getblk(dev, block + i, bufsize); + if (!bh) + break; if (buffer_uptodate(bh)) { brelse(bh); break; @@ -2772,6 +2774,20 @@ int journal_init(struct super_block *sb, const char *j_dev_name, goto free_and_return; } + /* + * Sanity check to see if journal first block is correct. + * If journal first block is invalid it can cause + * zeroing important superblock members. + */ + if (!SB_ONDISK_JOURNAL_DEVICE(sb) && + SB_ONDISK_JOURNAL_1st_BLOCK(sb) < SB_JOURNAL_1st_RESERVED_BLOCK(sb)) { + reiserfs_warning(sb, "journal-1393", + "journal 1st super block is invalid: 1st reserved block %d, but actual 1st block is %d", + SB_JOURNAL_1st_RESERVED_BLOCK(sb), + SB_ONDISK_JOURNAL_1st_BLOCK(sb)); + goto free_and_return; + } + if (journal_init_dev(sb, journal, j_dev_name) != 0) { reiserfs_warning(sb, "sh-462", "unable to initialize journal device"); diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c index 959a066b7bb0..2843b7cf4d7a 100644 --- a/fs/reiserfs/namei.c +++ b/fs/reiserfs/namei.c @@ -695,6 +695,7 @@ static int reiserfs_create(struct inode *dir, struct dentry *dentry, umode_t mod out_failed: reiserfs_write_unlock(dir->i_sb); + reiserfs_security_free(&security); return retval; } @@ -778,6 +779,7 @@ static int reiserfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode out_failed: reiserfs_write_unlock(dir->i_sb); + reiserfs_security_free(&security); return retval; } @@ -876,6 +878,7 @@ static int reiserfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode retval = journal_end(&th); out_failed: reiserfs_write_unlock(dir->i_sb); + reiserfs_security_free(&security); return retval; } @@ -1191,6 +1194,7 @@ static int reiserfs_symlink(struct inode *parent_dir, retval = journal_end(&th); out_failed: reiserfs_write_unlock(parent_dir->i_sb); + reiserfs_security_free(&security); return retval; } diff --git a/fs/reiserfs/stree.c b/fs/reiserfs/stree.c index 2946713cb00d..4ebad6781b0e 100644 --- a/fs/reiserfs/stree.c +++ b/fs/reiserfs/stree.c @@ -387,6 +387,24 @@ void pathrelse(struct treepath *search_path) search_path->path_length = ILLEGAL_PATH_ELEMENT_OFFSET; } +static int has_valid_deh_location(struct buffer_head *bh, struct item_head *ih) +{ + struct reiserfs_de_head *deh; + int i; + + deh = B_I_DEH(bh, ih); + for (i = 0; i < ih_entry_count(ih); i++) { + if (deh_location(&deh[i]) > ih_item_len(ih)) { + reiserfs_warning(NULL, "reiserfs-5094", + "directory entry location seems wrong %h", + &deh[i]); + return 0; + } + } + + return 1; +} + static int is_leaf(char *buf, int blocksize, struct buffer_head *bh) { struct block_head *blkh; @@ -454,6 +472,15 @@ static int is_leaf(char *buf, int blocksize, struct buffer_head *bh) "(second one): %h", ih); return 0; } + if (is_direntry_le_ih(ih)) { + if (ih_item_len(ih) < (ih_entry_count(ih) * IH_SIZE)) { + reiserfs_warning(NULL, "reiserfs-5093", + "item entry count seems wrong %h", + ih); + return 0; + } + return has_valid_deh_location(bh, ih); + } prev_location = ih_location(ih); } diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index de5eda33c92a..e5be1d747c03 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -1264,6 +1264,10 @@ static int reiserfs_parse_options(struct super_block *s, "turned on."); return 0; } + if (qf_names[qtype] != + REISERFS_SB(s)->s_qf_names[qtype]) + kfree(qf_names[qtype]); + qf_names[qtype] = NULL; if (*arg) { /* Some filename specified? */ if (REISERFS_SB(s)->s_qf_names[qtype] && strcmp(REISERFS_SB(s)->s_qf_names[qtype], @@ -1293,10 +1297,6 @@ static int reiserfs_parse_options(struct super_block *s, else *mount_options |= 1 << REISERFS_GRPQUOTA; } else { - if (qf_names[qtype] != - REISERFS_SB(s)->s_qf_names[qtype]) - kfree(qf_names[qtype]); - qf_names[qtype] = NULL; if (qtype == USRQUOTA) *mount_options &= ~(1 << REISERFS_USRQUOTA); else @@ -1443,7 +1443,6 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) unsigned long safe_mask = 0; unsigned int commit_max_age = (unsigned int)-1; struct reiserfs_journal *journal = SB_JOURNAL(s); - char *new_opts; int err; char *qf_names[REISERFS_MAXQUOTAS]; unsigned int qfmt = 0; @@ -1451,10 +1450,6 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) int i; #endif - new_opts = kstrdup(arg, GFP_KERNEL); - if (arg && !new_opts) - return -ENOMEM; - sync_filesystem(s); reiserfs_write_lock(s); @@ -1605,7 +1600,6 @@ out_ok_unlocked: out_err_unlock: reiserfs_write_unlock(s); out_err: - kfree(new_opts); return err; } @@ -2085,6 +2079,14 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent) unlock_new_inode(root_inode); } + if (!S_ISDIR(root_inode->i_mode) || !inode_get_bytes(root_inode) || + !root_inode->i_size) { + SWARN(silent, s, "", "corrupt root inode, run fsck"); + iput(root_inode); + errval = -EUCLEAN; + goto error; + } + s->s_root = d_make_root(root_inode); if (!s->s_root) goto error; diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index ee216925a709..0a397f179fd6 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -665,6 +665,13 @@ reiserfs_xattr_get(struct inode *inode, const char *name, void *buffer, if (get_inode_sd_version(inode) == STAT_DATA_V1) return -EOPNOTSUPP; + /* + * priv_root needn't be initialized during mount so allow initial + * lookups to succeed. + */ + if (!REISERFS_SB(inode->i_sb)->priv_root) + return 0; + dentry = xattr_lookup(inode, name, XATTR_REPLACE); if (IS_ERR(dentry)) { err = PTR_ERR(dentry); diff --git a/fs/reiserfs/xattr.h b/fs/reiserfs/xattr.h index c764352447ba..81bec2c80b25 100644 --- a/fs/reiserfs/xattr.h +++ b/fs/reiserfs/xattr.h @@ -43,7 +43,7 @@ void reiserfs_security_free(struct reiserfs_security_handle *sec); static inline int reiserfs_xattrs_initialized(struct super_block *sb) { - return REISERFS_SB(sb)->priv_root != NULL; + return REISERFS_SB(sb)->priv_root && REISERFS_SB(sb)->xattr_root; } #define xattr_size(size) ((size) + sizeof(struct reiserfs_xattr_header)) diff --git a/fs/reiserfs/xattr_security.c b/fs/reiserfs/xattr_security.c index 20be9a0e5870..159af6c26f4b 100644 --- a/fs/reiserfs/xattr_security.c +++ b/fs/reiserfs/xattr_security.c @@ -49,6 +49,7 @@ int reiserfs_security_init(struct inode *dir, struct inode *inode, int error; sec->name = NULL; + sec->value = NULL; /* Don't add selinux attributes on xattrs - they'll never get used */ if (IS_PRIVATE(dir)) @@ -80,11 +81,15 @@ int reiserfs_security_write(struct reiserfs_transaction_handle *th, struct inode *inode, struct reiserfs_security_handle *sec) { + char xattr_name[XATTR_NAME_MAX + 1] = XATTR_SECURITY_PREFIX; int error; - if (strlen(sec->name) < sizeof(XATTR_SECURITY_PREFIX)) + + if (XATTR_SECURITY_PREFIX_LEN + strlen(sec->name) > XATTR_NAME_MAX) return -EINVAL; - error = reiserfs_xattr_set_handle(th, inode, sec->name, sec->value, + strlcat(xattr_name, sec->name, sizeof(xattr_name)); + + error = reiserfs_xattr_set_handle(th, inode, xattr_name, sec->value, sec->length, XATTR_CREATE); if (error == -ENODATA || error == -EOPNOTSUPP) error = 0; @@ -94,7 +99,6 @@ int reiserfs_security_write(struct reiserfs_transaction_handle *th, void reiserfs_security_free(struct reiserfs_security_handle *sec) { - kfree(sec->name); kfree(sec->value); sec->name = NULL; sec->value = NULL; diff --git a/fs/select.c b/fs/select.c index 4a6b6e4b21cb..1c3985d0bcc3 100644 --- a/fs/select.c +++ b/fs/select.c @@ -431,9 +431,11 @@ get_max: return max; } -#define POLLIN_SET (EPOLLRDNORM | EPOLLRDBAND | EPOLLIN | EPOLLHUP | EPOLLERR) -#define POLLOUT_SET (EPOLLWRBAND | EPOLLWRNORM | EPOLLOUT | EPOLLERR) -#define POLLEX_SET (EPOLLPRI) +#define POLLIN_SET (EPOLLRDNORM | EPOLLRDBAND | EPOLLIN | EPOLLHUP | EPOLLERR |\ + EPOLLNVAL) +#define POLLOUT_SET (EPOLLWRBAND | EPOLLWRNORM | EPOLLOUT | EPOLLERR |\ + EPOLLNVAL) +#define POLLEX_SET (EPOLLPRI | EPOLLNVAL) static inline void wait_key_set(poll_table *wait, unsigned long in, unsigned long out, unsigned long bit, @@ -500,6 +502,7 @@ static int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time) break; if (!(bit & all_bits)) continue; + mask = EPOLLNVAL; f = fdget(i); if (f.file) { wait_key_set(wait, in, out, bit, @@ -507,34 +510,34 @@ static int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time) mask = vfs_poll(f.file, wait); fdput(f); - if ((mask & POLLIN_SET) && (in & bit)) { - res_in |= bit; - retval++; - wait->_qproc = NULL; - } - if ((mask & POLLOUT_SET) && (out & bit)) { - res_out |= bit; - retval++; - wait->_qproc = NULL; - } - if ((mask & POLLEX_SET) && (ex & bit)) { - res_ex |= bit; - retval++; - wait->_qproc = NULL; - } - /* got something, stop busy polling */ - if (retval) { - can_busy_loop = false; - busy_flag = 0; - - /* - * only remember a returned - * POLL_BUSY_LOOP if we asked for it - */ - } else if (busy_flag & mask) - can_busy_loop = true; - } + if ((mask & POLLIN_SET) && (in & bit)) { + res_in |= bit; + retval++; + wait->_qproc = NULL; + } + if ((mask & POLLOUT_SET) && (out & bit)) { + res_out |= bit; + retval++; + wait->_qproc = NULL; + } + if ((mask & POLLEX_SET) && (ex & bit)) { + res_ex |= bit; + retval++; + wait->_qproc = NULL; + } + /* got something, stop busy polling */ + if (retval) { + can_busy_loop = false; + busy_flag = 0; + + /* + * only remember a returned + * POLL_BUSY_LOOP if we asked for it + */ + } else if (busy_flag & mask) + can_busy_loop = true; + } if (res_in) *rinp = res_in; @@ -1003,10 +1006,9 @@ static long do_restart_poll(struct restart_block *restart_block) ret = do_sys_poll(ufds, nfds, to); - if (ret == -EINTR) { - restart_block->fn = do_restart_poll; - ret = -ERESTART_RESTARTBLOCK; - } + if (ret == -EINTR) + ret = set_restart_fn(restart_block, do_restart_poll); + return ret; } @@ -1028,7 +1030,6 @@ SYSCALL_DEFINE3(poll, struct pollfd __user *, ufds, unsigned int, nfds, struct restart_block *restart_block; restart_block = ¤t->restart_block; - restart_block->fn = do_restart_poll; restart_block->poll.ufds = ufds; restart_block->poll.nfds = nfds; @@ -1039,7 +1040,7 @@ SYSCALL_DEFINE3(poll, struct pollfd __user *, ufds, unsigned int, nfds, } else restart_block->poll.has_timeout = 0; - ret = -ERESTART_RESTARTBLOCK; + ret = set_restart_fn(restart_block, do_restart_poll); } return ret; } diff --git a/fs/seq_file.c b/fs/seq_file.c index 05e58b56f620..e11f62b29be8 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -29,6 +29,9 @@ static void seq_set_overflow(struct seq_file *m) static void *seq_buf_alloc(unsigned long size) { + if (unlikely(size > MAX_RW_COUNT)) + return NULL; + return kvmalloc(size, GFP_KERNEL_ACCOUNT); } diff --git a/fs/signalfd.c b/fs/signalfd.c index 3c40a3bf772c..94e0ae01db5c 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -35,17 +35,7 @@ void signalfd_cleanup(struct sighand_struct *sighand) { - wait_queue_head_t *wqh = &sighand->signalfd_wqh; - /* - * The lockless check can race with remove_wait_queue() in progress, - * but in this case its caller should run under rcu_read_lock() and - * sighand_cachep is SLAB_TYPESAFE_BY_RCU, we can safely return. - */ - if (likely(!waitqueue_active(wqh))) - return; - - /* wait_queue_entry_t->func(POLLFREE) should do remove_wait_queue() */ - wake_up_poll(wqh, EPOLLHUP | POLLFREE); + wake_up_pollfree(&sighand->signalfd_wqh); } struct signalfd_ctx { diff --git a/fs/squashfs/export.c b/fs/squashfs/export.c index 8073b6532cf0..1d406a2094a5 100644 --- a/fs/squashfs/export.c +++ b/fs/squashfs/export.c @@ -54,12 +54,17 @@ static long long squashfs_inode_lookup(struct super_block *sb, int ino_num) struct squashfs_sb_info *msblk = sb->s_fs_info; int blk = SQUASHFS_LOOKUP_BLOCK(ino_num - 1); int offset = SQUASHFS_LOOKUP_BLOCK_OFFSET(ino_num - 1); - u64 start = le64_to_cpu(msblk->inode_lookup_table[blk]); + u64 start; __le64 ino; int err; TRACE("Entered squashfs_inode_lookup, inode_number = %d\n", ino_num); + if (ino_num == 0 || (ino_num - 1) >= msblk->inodes) + return -EINVAL; + + start = le64_to_cpu(msblk->inode_lookup_table[blk]); + err = squashfs_read_metadata(sb, &ino, &start, &offset, sizeof(ino)); if (err < 0) return err; @@ -124,7 +129,10 @@ __le64 *squashfs_read_inode_lookup_table(struct super_block *sb, u64 lookup_table_start, u64 next_table, unsigned int inodes) { unsigned int length = SQUASHFS_LOOKUP_BLOCK_BYTES(inodes); + unsigned int indexes = SQUASHFS_LOOKUP_BLOCKS(inodes); + int n; __le64 *table; + u64 start, end; TRACE("In read_inode_lookup_table, length %d\n", length); @@ -134,20 +142,41 @@ __le64 *squashfs_read_inode_lookup_table(struct super_block *sb, if (inodes == 0) return ERR_PTR(-EINVAL); - /* length bytes should not extend into the next table - this check - * also traps instances where lookup_table_start is incorrectly larger - * than the next table start + /* + * The computed size of the lookup table (length bytes) should exactly + * match the table start and end points */ - if (lookup_table_start + length > next_table) + if (length != (next_table - lookup_table_start)) return ERR_PTR(-EINVAL); table = squashfs_read_table(sb, lookup_table_start, length); + if (IS_ERR(table)) + return table; /* - * table[0] points to the first inode lookup table metadata block, - * this should be less than lookup_table_start + * table0], table[1], ... table[indexes - 1] store the locations + * of the compressed inode lookup blocks. Each entry should be + * less than the next (i.e. table[0] < table[1]), and the difference + * between them should be SQUASHFS_METADATA_SIZE or less. + * table[indexes - 1] should be less than lookup_table_start, and + * again the difference should be SQUASHFS_METADATA_SIZE or less */ - if (!IS_ERR(table) && le64_to_cpu(table[0]) >= lookup_table_start) { + for (n = 0; n < (indexes - 1); n++) { + start = le64_to_cpu(table[n]); + end = le64_to_cpu(table[n + 1]); + + if (start >= end + || (end - start) > + (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { + kfree(table); + return ERR_PTR(-EINVAL); + } + } + + start = le64_to_cpu(table[indexes - 1]); + if (start >= lookup_table_start || + (lookup_table_start - start) > + (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { kfree(table); return ERR_PTR(-EINVAL); } diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c index f1c1430ae721..0bcb83479fcb 100644 --- a/fs/squashfs/file.c +++ b/fs/squashfs/file.c @@ -224,11 +224,11 @@ failure: * If the skip factor is limited in this way then the file will use multiple * slots. */ -static inline int calculate_skip(int blocks) +static inline int calculate_skip(u64 blocks) { - int skip = blocks / ((SQUASHFS_META_ENTRIES + 1) + u64 skip = blocks / ((SQUASHFS_META_ENTRIES + 1) * SQUASHFS_META_INDEXES); - return min(SQUASHFS_CACHED_BLKS - 1, skip + 1); + return min((u64) SQUASHFS_CACHED_BLKS - 1, skip + 1); } diff --git a/fs/squashfs/id.c b/fs/squashfs/id.c index d38ea3dab951..d2e15baab537 100644 --- a/fs/squashfs/id.c +++ b/fs/squashfs/id.c @@ -48,10 +48,15 @@ int squashfs_get_id(struct super_block *sb, unsigned int index, struct squashfs_sb_info *msblk = sb->s_fs_info; int block = SQUASHFS_ID_BLOCK(index); int offset = SQUASHFS_ID_BLOCK_OFFSET(index); - u64 start_block = le64_to_cpu(msblk->id_table[block]); + u64 start_block; __le32 disk_id; int err; + if (index >= msblk->ids) + return -EINVAL; + + start_block = le64_to_cpu(msblk->id_table[block]); + err = squashfs_read_metadata(sb, &disk_id, &start_block, &offset, sizeof(disk_id)); if (err < 0) @@ -69,7 +74,10 @@ __le64 *squashfs_read_id_index_table(struct super_block *sb, u64 id_table_start, u64 next_table, unsigned short no_ids) { unsigned int length = SQUASHFS_ID_BLOCK_BYTES(no_ids); + unsigned int indexes = SQUASHFS_ID_BLOCKS(no_ids); + int n; __le64 *table; + u64 start, end; TRACE("In read_id_index_table, length %d\n", length); @@ -80,20 +88,38 @@ __le64 *squashfs_read_id_index_table(struct super_block *sb, return ERR_PTR(-EINVAL); /* - * length bytes should not extend into the next table - this check - * also traps instances where id_table_start is incorrectly larger - * than the next table start + * The computed size of the index table (length bytes) should exactly + * match the table start and end points */ - if (id_table_start + length > next_table) + if (length != (next_table - id_table_start)) return ERR_PTR(-EINVAL); table = squashfs_read_table(sb, id_table_start, length); + if (IS_ERR(table)) + return table; /* - * table[0] points to the first id lookup table metadata block, this - * should be less than id_table_start + * table[0], table[1], ... table[indexes - 1] store the locations + * of the compressed id blocks. Each entry should be less than + * the next (i.e. table[0] < table[1]), and the difference between them + * should be SQUASHFS_METADATA_SIZE or less. table[indexes - 1] + * should be less than id_table_start, and again the difference + * should be SQUASHFS_METADATA_SIZE or less */ - if (!IS_ERR(table) && le64_to_cpu(table[0]) >= id_table_start) { + for (n = 0; n < (indexes - 1); n++) { + start = le64_to_cpu(table[n]); + end = le64_to_cpu(table[n + 1]); + + if (start >= end || (end - start) > + (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { + kfree(table); + return ERR_PTR(-EINVAL); + } + } + + start = le64_to_cpu(table[indexes - 1]); + if (start >= id_table_start || (id_table_start - start) > + (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { kfree(table); return ERR_PTR(-EINVAL); } diff --git a/fs/squashfs/squashfs_fs.h b/fs/squashfs/squashfs_fs.h index 4e6853f084d0..75886e6d9c97 100644 --- a/fs/squashfs/squashfs_fs.h +++ b/fs/squashfs/squashfs_fs.h @@ -30,6 +30,7 @@ /* size of metadata (inode and directory) blocks */ #define SQUASHFS_METADATA_SIZE 8192 +#define SQUASHFS_BLOCK_OFFSET 2 /* default size of block device I/O */ #ifdef CONFIG_SQUASHFS_4K_DEVBLK_SIZE @@ -195,7 +196,7 @@ static inline int squashfs_block_size(__le32 raw) #define SQUASHFS_ID_BLOCK_BYTES(A) (SQUASHFS_ID_BLOCKS(A) *\ sizeof(u64)) /* xattr id lookup table defines */ -#define SQUASHFS_XATTR_BYTES(A) ((A) * sizeof(struct squashfs_xattr_id)) +#define SQUASHFS_XATTR_BYTES(A) (((u64) (A)) * sizeof(struct squashfs_xattr_id)) #define SQUASHFS_XATTR_BLOCK(A) (SQUASHFS_XATTR_BYTES(A) / \ SQUASHFS_METADATA_SIZE) diff --git a/fs/squashfs/squashfs_fs_sb.h b/fs/squashfs/squashfs_fs_sb.h index ef69c31947bf..7ec30a11273e 100644 --- a/fs/squashfs/squashfs_fs_sb.h +++ b/fs/squashfs/squashfs_fs_sb.h @@ -76,6 +76,7 @@ struct squashfs_sb_info { long long bytes_used; unsigned int inodes; unsigned int fragments; - int xattr_ids; + unsigned int xattr_ids; + unsigned int ids; }; #endif diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c index 40e657386fa5..728b2d72f3f0 100644 --- a/fs/squashfs/super.c +++ b/fs/squashfs/super.c @@ -176,6 +176,7 @@ static int squashfs_fill_super(struct super_block *sb, void *data, int silent) msblk->directory_table = le64_to_cpu(sblk->directory_table_start); msblk->inodes = le32_to_cpu(sblk->inodes); msblk->fragments = le32_to_cpu(sblk->fragments); + msblk->ids = le16_to_cpu(sblk->no_ids); flags = le16_to_cpu(sblk->flags); TRACE("Found valid superblock on %pg\n", sb->s_bdev); @@ -187,7 +188,7 @@ static int squashfs_fill_super(struct super_block *sb, void *data, int silent) TRACE("Block size %d\n", msblk->block_size); TRACE("Number of inodes %d\n", msblk->inodes); TRACE("Number of fragments %d\n", msblk->fragments); - TRACE("Number of ids %d\n", le16_to_cpu(sblk->no_ids)); + TRACE("Number of ids %d\n", msblk->ids); TRACE("sblk->inode_table_start %llx\n", msblk->inode_table); TRACE("sblk->directory_table_start %llx\n", msblk->directory_table); TRACE("sblk->fragment_table_start %llx\n", @@ -244,8 +245,7 @@ static int squashfs_fill_super(struct super_block *sb, void *data, int silent) allocate_id_index_table: /* Allocate and read id index table */ msblk->id_table = squashfs_read_id_index_table(sb, - le64_to_cpu(sblk->id_table_start), next_table, - le16_to_cpu(sblk->no_ids)); + le64_to_cpu(sblk->id_table_start), next_table, msblk->ids); if (IS_ERR(msblk->id_table)) { ERROR("unable to read id index table\n"); err = PTR_ERR(msblk->id_table); diff --git a/fs/squashfs/xattr.h b/fs/squashfs/xattr.h index afe70f815e3d..f360f27e38f3 100644 --- a/fs/squashfs/xattr.h +++ b/fs/squashfs/xattr.h @@ -23,15 +23,23 @@ #ifdef CONFIG_SQUASHFS_XATTR extern __le64 *squashfs_read_xattr_id_table(struct super_block *, u64, - u64 *, int *); + u64 *, unsigned int *); extern int squashfs_xattr_lookup(struct super_block *, unsigned int, int *, unsigned int *, unsigned long long *); #else static inline __le64 *squashfs_read_xattr_id_table(struct super_block *sb, - u64 start, u64 *xattr_table_start, int *xattr_ids) + u64 start, u64 *xattr_table_start, unsigned int *xattr_ids) { + struct squashfs_xattr_id_table *id_table; + + id_table = squashfs_read_table(sb, start, sizeof(*id_table)); + if (IS_ERR(id_table)) + return (__le64 *) id_table; + + *xattr_table_start = le64_to_cpu(id_table->xattr_table_start); + kfree(id_table); + ERROR("Xattrs in filesystem, these will be ignored\n"); - *xattr_table_start = start; return ERR_PTR(-ENOTSUPP); } diff --git a/fs/squashfs/xattr_id.c b/fs/squashfs/xattr_id.c index c89607d690c4..fe266b3e95f8 100644 --- a/fs/squashfs/xattr_id.c +++ b/fs/squashfs/xattr_id.c @@ -44,10 +44,15 @@ int squashfs_xattr_lookup(struct super_block *sb, unsigned int index, struct squashfs_sb_info *msblk = sb->s_fs_info; int block = SQUASHFS_XATTR_BLOCK(index); int offset = SQUASHFS_XATTR_BLOCK_OFFSET(index); - u64 start_block = le64_to_cpu(msblk->xattr_id_table[block]); + u64 start_block; struct squashfs_xattr_id id; int err; + if (index >= msblk->xattr_ids) + return -EINVAL; + + start_block = le64_to_cpu(msblk->xattr_id_table[block]); + err = squashfs_read_metadata(sb, &id, &start_block, &offset, sizeof(id)); if (err < 0) @@ -63,13 +68,17 @@ int squashfs_xattr_lookup(struct super_block *sb, unsigned int index, /* * Read uncompressed xattr id lookup table indexes from disk into memory */ -__le64 *squashfs_read_xattr_id_table(struct super_block *sb, u64 start, - u64 *xattr_table_start, int *xattr_ids) +__le64 *squashfs_read_xattr_id_table(struct super_block *sb, u64 table_start, + u64 *xattr_table_start, unsigned int *xattr_ids) { - unsigned int len; + struct squashfs_sb_info *msblk = sb->s_fs_info; + unsigned int len, indexes; struct squashfs_xattr_id_table *id_table; + __le64 *table; + u64 start, end; + int n; - id_table = squashfs_read_table(sb, start, sizeof(*id_table)); + id_table = squashfs_read_table(sb, table_start, sizeof(*id_table)); if (IS_ERR(id_table)) return (__le64 *) id_table; @@ -83,13 +92,54 @@ __le64 *squashfs_read_xattr_id_table(struct super_block *sb, u64 start, if (*xattr_ids == 0) return ERR_PTR(-EINVAL); - /* xattr_table should be less than start */ - if (*xattr_table_start >= start) + len = SQUASHFS_XATTR_BLOCK_BYTES(*xattr_ids); + indexes = SQUASHFS_XATTR_BLOCKS(*xattr_ids); + + /* + * The computed size of the index table (len bytes) should exactly + * match the table start and end points + */ + start = table_start + sizeof(*id_table); + end = msblk->bytes_used; + + if (len != (end - start)) return ERR_PTR(-EINVAL); - len = SQUASHFS_XATTR_BLOCK_BYTES(*xattr_ids); + table = squashfs_read_table(sb, start, len); + if (IS_ERR(table)) + return table; + + /* table[0], table[1], ... table[indexes - 1] store the locations + * of the compressed xattr id blocks. Each entry should be less than + * the next (i.e. table[0] < table[1]), and the difference between them + * should be SQUASHFS_METADATA_SIZE or less. table[indexes - 1] + * should be less than table_start, and again the difference + * shouls be SQUASHFS_METADATA_SIZE or less. + * + * Finally xattr_table_start should be less than table[0]. + */ + for (n = 0; n < (indexes - 1); n++) { + start = le64_to_cpu(table[n]); + end = le64_to_cpu(table[n + 1]); + + if (start >= end || (end - start) > + (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { + kfree(table); + return ERR_PTR(-EINVAL); + } + } + + start = le64_to_cpu(table[indexes - 1]); + if (start >= table_start || (table_start - start) > + (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { + kfree(table); + return ERR_PTR(-EINVAL); + } - TRACE("In read_xattr_index_table, length %d\n", len); + if (*xattr_table_start >= le64_to_cpu(table[0])) { + kfree(table); + return ERR_PTR(-EINVAL); + } - return squashfs_read_table(sb, start + sizeof(*id_table), len); + return table; } diff --git a/fs/stat.c b/fs/stat.c index f8e6fb2c3657..376543199b5a 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -286,9 +286,6 @@ SYSCALL_DEFINE2(fstat, unsigned int, fd, struct __old_kernel_stat __user *, stat # define choose_32_64(a,b) b #endif -#define valid_dev(x) choose_32_64(old_valid_dev(x),true) -#define encode_dev(x) choose_32_64(old_encode_dev,new_encode_dev)(x) - #ifndef INIT_STRUCT_STAT_PADDING # define INIT_STRUCT_STAT_PADDING(st) memset(&st, 0, sizeof(st)) #endif @@ -297,7 +294,9 @@ static int cp_new_stat(struct kstat *stat, struct stat __user *statbuf) { struct stat tmp; - if (!valid_dev(stat->dev) || !valid_dev(stat->rdev)) + if (sizeof(tmp.st_dev) < 4 && !old_valid_dev(stat->dev)) + return -EOVERFLOW; + if (sizeof(tmp.st_rdev) < 4 && !old_valid_dev(stat->rdev)) return -EOVERFLOW; #if BITS_PER_LONG == 32 if (stat->size > MAX_NON_LFS) @@ -305,7 +304,7 @@ static int cp_new_stat(struct kstat *stat, struct stat __user *statbuf) #endif INIT_STRUCT_STAT_PADDING(tmp); - tmp.st_dev = encode_dev(stat->dev); + tmp.st_dev = new_encode_dev(stat->dev); tmp.st_ino = stat->ino; if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino) return -EOVERFLOW; @@ -315,7 +314,7 @@ static int cp_new_stat(struct kstat *stat, struct stat __user *statbuf) return -EOVERFLOW; SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid)); SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid)); - tmp.st_rdev = encode_dev(stat->rdev); + tmp.st_rdev = new_encode_dev(stat->rdev); tmp.st_size = stat->size; tmp.st_atime = stat->atime.tv_sec; tmp.st_mtime = stat->mtime.tv_sec; @@ -588,11 +587,13 @@ static int cp_compat_stat(struct kstat *stat, struct compat_stat __user *ubuf) { struct compat_stat tmp; - if (!old_valid_dev(stat->dev) || !old_valid_dev(stat->rdev)) + if (sizeof(tmp.st_dev) < 4 && !old_valid_dev(stat->dev)) + return -EOVERFLOW; + if (sizeof(tmp.st_rdev) < 4 && !old_valid_dev(stat->rdev)) return -EOVERFLOW; memset(&tmp, 0, sizeof(tmp)); - tmp.st_dev = old_encode_dev(stat->dev); + tmp.st_dev = new_encode_dev(stat->dev); tmp.st_ino = stat->ino; if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino) return -EOVERFLOW; @@ -602,7 +603,7 @@ static int cp_compat_stat(struct kstat *stat, struct compat_stat __user *ubuf) return -EOVERFLOW; SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid)); SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid)); - tmp.st_rdev = old_encode_dev(stat->rdev); + tmp.st_rdev = new_encode_dev(stat->rdev); if ((u64) stat->size > MAX_NON_LFS) return -EOVERFLOW; tmp.st_size = stat->size; diff --git a/fs/statfs.c b/fs/statfs.c index 56f655f757ff..29786598c2b5 100644 --- a/fs/statfs.c +++ b/fs/statfs.c @@ -114,6 +114,7 @@ static int do_statfs_native(struct kstatfs *st, struct statfs __user *p) if (sizeof(buf) == sizeof(*st)) memcpy(&buf, st, sizeof(*st)); else { + memset(&buf, 0, sizeof(buf)); if (sizeof buf.f_blocks == 4) { if ((st->f_blocks | st->f_bfree | st->f_bavail | st->f_bsize | st->f_frsize) & @@ -142,7 +143,6 @@ static int do_statfs_native(struct kstatfs *st, struct statfs __user *p) buf.f_namelen = st->f_namelen; buf.f_frsize = st->f_frsize; buf.f_flags = st->f_flags; - memset(buf.f_spare, 0, sizeof(buf.f_spare)); } if (copy_to_user(p, &buf, sizeof(buf))) return -EFAULT; @@ -155,6 +155,7 @@ static int do_statfs64(struct kstatfs *st, struct statfs64 __user *p) if (sizeof(buf) == sizeof(*st)) memcpy(&buf, st, sizeof(*st)); else { + memset(&buf, 0, sizeof(buf)); buf.f_type = st->f_type; buf.f_bsize = st->f_bsize; buf.f_blocks = st->f_blocks; @@ -166,7 +167,6 @@ static int do_statfs64(struct kstatfs *st, struct statfs64 __user *p) buf.f_namelen = st->f_namelen; buf.f_frsize = st->f_frsize; buf.f_flags = st->f_flags; - memset(buf.f_spare, 0, sizeof(buf.f_spare)); } if (copy_to_user(p, &buf, sizeof(buf))) return -EFAULT; diff --git a/fs/super.c b/fs/super.c index f3a8c008e164..8dc26e23f1a3 100644 --- a/fs/super.c +++ b/fs/super.c @@ -1360,36 +1360,11 @@ EXPORT_SYMBOL(__sb_end_write); */ int __sb_start_write(struct super_block *sb, int level, bool wait) { - bool force_trylock = false; - int ret = 1; + if (!wait) + return percpu_down_read_trylock(sb->s_writers.rw_sem + level-1); -#ifdef CONFIG_LOCKDEP - /* - * We want lockdep to tell us about possible deadlocks with freezing - * but it's it bit tricky to properly instrument it. Getting a freeze - * protection works as getting a read lock but there are subtle - * problems. XFS for example gets freeze protection on internal level - * twice in some cases, which is OK only because we already hold a - * freeze protection also on higher level. Due to these cases we have - * to use wait == F (trylock mode) which must not fail. - */ - if (wait) { - int i; - - for (i = 0; i < level - 1; i++) - if (percpu_rwsem_is_held(sb->s_writers.rw_sem + i)) { - force_trylock = true; - break; - } - } -#endif - if (wait && !force_trylock) - percpu_down_read(sb->s_writers.rw_sem + level-1); - else - ret = percpu_down_read_trylock(sb->s_writers.rw_sem + level-1); - - WARN_ON(force_trylock && !ret); - return ret; + percpu_down_read(sb->s_writers.rw_sem + level-1); + return 1; } EXPORT_SYMBOL(__sb_start_write); @@ -1429,11 +1404,9 @@ static void lockdep_sb_freeze_acquire(struct super_block *sb) percpu_rwsem_acquire(sb->s_writers.rw_sem + level, 0, _THIS_IP_); } -static void sb_freeze_unlock(struct super_block *sb) +static void sb_freeze_unlock(struct super_block *sb, int level) { - int level; - - for (level = SB_FREEZE_LEVELS - 1; level >= 0; level--) + for (level--; level >= 0; level--) percpu_up_write(sb->s_writers.rw_sem + level); } @@ -1504,7 +1477,14 @@ int freeze_super(struct super_block *sb) sb_wait_write(sb, SB_FREEZE_PAGEFAULT); /* All writers are done so after syncing there won't be dirty data */ - sync_filesystem(sb); + ret = sync_filesystem(sb); + if (ret) { + sb->s_writers.frozen = SB_UNFROZEN; + sb_freeze_unlock(sb, SB_FREEZE_PAGEFAULT); + wake_up(&sb->s_writers.wait_unfrozen); + deactivate_locked_super(sb); + return ret; + } /* Now wait for internal filesystem counter */ sb->s_writers.frozen = SB_FREEZE_FS; @@ -1516,7 +1496,7 @@ int freeze_super(struct super_block *sb) printk(KERN_ERR "VFS:Filesystem freeze failed\n"); sb->s_writers.frozen = SB_UNFROZEN; - sb_freeze_unlock(sb); + sb_freeze_unlock(sb, SB_FREEZE_FS); wake_up(&sb->s_writers.wait_unfrozen); deactivate_locked_super(sb); return ret; @@ -1567,7 +1547,7 @@ static int thaw_super_locked(struct super_block *sb) } sb->s_writers.frozen = SB_UNFROZEN; - sb_freeze_unlock(sb); + sb_freeze_unlock(sb, SB_FREEZE_FS); out: wake_up(&sb->s_writers.wait_unfrozen); deactivate_locked_super(sb); diff --git a/fs/sync.c b/fs/sync.c index b54e0541ad89..917ebd12c251 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -76,7 +76,8 @@ static void sync_inodes_one_sb(struct super_block *sb, void *arg) static void sync_fs_one_sb(struct super_block *sb, void *arg) { - if (!sb_rdonly(sb) && sb->s_op->sync_fs) + if (!sb_rdonly(sb) && !(sb->s_iflags & SB_I_SKIP_SYNC) && + sb->s_op->sync_fs) sb->s_op->sync_fs(sb, *(int *)arg); } diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 0a7252aecfa5..cd70dbeeab22 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -15,6 +15,7 @@ #include <linux/list.h> #include <linux/mutex.h> #include <linux/seq_file.h> +#include <linux/mm.h> #include "sysfs.h" #include "../kernfs/kernfs-internal.h" @@ -556,3 +557,56 @@ void sysfs_remove_bin_file(struct kobject *kobj, kernfs_remove_by_name(kobj->sd, attr->attr.name); } EXPORT_SYMBOL_GPL(sysfs_remove_bin_file); + +/** + * sysfs_emit - scnprintf equivalent, aware of PAGE_SIZE buffer. + * @buf: start of PAGE_SIZE buffer. + * @fmt: format + * @...: optional arguments to @format + * + * + * Returns number of characters written to @buf. + */ +int sysfs_emit(char *buf, const char *fmt, ...) +{ + va_list args; + int len; + + if (WARN(!buf, "invalid sysfs_emit: buf:%p\n", buf)) + return 0; + + va_start(args, fmt); + len = vscnprintf(buf, PAGE_SIZE, fmt, args); + va_end(args); + + return len; +} +EXPORT_SYMBOL_GPL(sysfs_emit); + +/** + * sysfs_emit_at - scnprintf equivalent, aware of PAGE_SIZE buffer. + * @buf: start of PAGE_SIZE buffer. + * @at: offset in @buf to start write in bytes + * @at must be >= 0 && < PAGE_SIZE + * @fmt: format + * @...: optional arguments to @fmt + * + * + * Returns number of characters written starting at &@buf[@at]. + */ +int sysfs_emit_at(char *buf, int at, const char *fmt, ...) +{ + va_list args; + int len; + + if (WARN(!buf || at < 0 || at >= PAGE_SIZE, + "invalid sysfs_emit_at: buf:%p at:%d\n", buf, at)) + return 0; + + va_start(args, fmt); + len = vscnprintf(buf + at, PAGE_SIZE - at, fmt, args); + va_end(args); + + return len; +} +EXPORT_SYMBOL_GPL(sysfs_emit_at); diff --git a/fs/sysv/itree.c b/fs/sysv/itree.c index bcb67b0cabe7..e3d1673b8ec9 100644 --- a/fs/sysv/itree.c +++ b/fs/sysv/itree.c @@ -145,6 +145,10 @@ static int alloc_branch(struct inode *inode, */ parent = block_to_cpu(SYSV_SB(inode->i_sb), branch[n-1].key); bh = sb_getblk(inode->i_sb, parent); + if (!bh) { + sysv_free_block(inode->i_sb, branch[n].key); + break; + } lock_buffer(bh); memset(bh->b_data, 0, blocksize); branch[n].bh = bh; @@ -438,7 +442,7 @@ static unsigned sysv_nblocks(struct super_block *s, loff_t size) res += blocks; direct = 1; } - return blocks; + return res; } int sysv_getattr(const struct path *path, struct kstat *stat, diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index 7098c49f3693..4ad24d0371c8 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -142,6 +142,8 @@ struct tracefs_mount_opts { kuid_t uid; kgid_t gid; umode_t mode; + /* Opt_* bitfield. */ + unsigned int opts; }; enum { @@ -162,6 +164,77 @@ struct tracefs_fs_info { struct tracefs_mount_opts mount_opts; }; +static void change_gid(struct dentry *dentry, kgid_t gid) +{ + if (!dentry->d_inode) + return; + dentry->d_inode->i_gid = gid; +} + +/* + * Taken from d_walk, but without he need for handling renames. + * Nothing can be renamed while walking the list, as tracefs + * does not support renames. This is only called when mounting + * or remounting the file system, to set all the files to + * the given gid. + */ +static void set_gid(struct dentry *parent, kgid_t gid) +{ + struct dentry *this_parent; + struct list_head *next; + + this_parent = parent; + spin_lock(&this_parent->d_lock); + + change_gid(this_parent, gid); +repeat: + next = this_parent->d_subdirs.next; +resume: + while (next != &this_parent->d_subdirs) { + struct list_head *tmp = next; + struct dentry *dentry = list_entry(tmp, struct dentry, d_child); + next = tmp->next; + + spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); + + change_gid(dentry, gid); + + if (!list_empty(&dentry->d_subdirs)) { + spin_unlock(&this_parent->d_lock); + spin_release(&dentry->d_lock.dep_map, 1, _RET_IP_); + this_parent = dentry; + spin_acquire(&this_parent->d_lock.dep_map, 0, 1, _RET_IP_); + goto repeat; + } + spin_unlock(&dentry->d_lock); + } + /* + * All done at this level ... ascend and resume the search. + */ + rcu_read_lock(); +ascend: + if (this_parent != parent) { + struct dentry *child = this_parent; + this_parent = child->d_parent; + + spin_unlock(&child->d_lock); + spin_lock(&this_parent->d_lock); + + /* go into the first sibling still alive */ + do { + next = child->d_child.next; + if (next == &this_parent->d_subdirs) + goto ascend; + child = list_entry(next, struct dentry, d_child); + } while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED)); + rcu_read_unlock(); + goto resume; + } + rcu_read_unlock(); + spin_unlock(&this_parent->d_lock); + return; +} + static int tracefs_parse_options(char *data, struct tracefs_mount_opts *opts) { substring_t args[MAX_OPT_ARGS]; @@ -171,6 +244,7 @@ static int tracefs_parse_options(char *data, struct tracefs_mount_opts *opts) kgid_t gid; char *p; + opts->opts = 0; opts->mode = TRACEFS_DEFAULT_MODE; while ((p = strsep(&data, ",")) != NULL) { @@ -205,22 +279,36 @@ static int tracefs_parse_options(char *data, struct tracefs_mount_opts *opts) * but traditionally tracefs has ignored all mount options */ } + + opts->opts |= BIT(token); } return 0; } -static int tracefs_apply_options(struct super_block *sb) +static int tracefs_apply_options(struct super_block *sb, bool remount) { struct tracefs_fs_info *fsi = sb->s_fs_info; struct inode *inode = sb->s_root->d_inode; struct tracefs_mount_opts *opts = &fsi->mount_opts; - inode->i_mode &= ~S_IALLUGO; - inode->i_mode |= opts->mode; + /* + * On remount, only reset mode/uid/gid if they were provided as mount + * options. + */ + + if (!remount || opts->opts & BIT(Opt_mode)) { + inode->i_mode &= ~S_IALLUGO; + inode->i_mode |= opts->mode; + } - inode->i_uid = opts->uid; - inode->i_gid = opts->gid; + if (!remount || opts->opts & BIT(Opt_uid)) + inode->i_uid = opts->uid; + + if (!remount || opts->opts & BIT(Opt_gid)) { + /* Set all the group ids to the mount option */ + set_gid(sb->s_root, opts->gid); + } return 0; } @@ -235,7 +323,7 @@ static int tracefs_remount(struct super_block *sb, int *flags, char *data) if (err) goto fail; - tracefs_apply_options(sb); + tracefs_apply_options(sb, true); fail: return err; @@ -287,7 +375,7 @@ static int trace_fill_super(struct super_block *sb, void *data, int silent) sb->s_op = &tracefs_super_operations; - tracefs_apply_options(sb); + tracefs_apply_options(sb, false); return 0; @@ -409,6 +497,8 @@ struct dentry *tracefs_create_file(const char *name, umode_t mode, inode->i_mode = mode; inode->i_fop = fops ? fops : &tracefs_file_operations; inode->i_private = data; + inode->i_uid = d_inode(dentry->d_parent)->i_uid; + inode->i_gid = d_inode(dentry->d_parent)->i_gid; d_instantiate(dentry, inode); fsnotify_create(dentry->d_parent->d_inode, dentry); return end_creating(dentry); @@ -427,9 +517,12 @@ static struct dentry *__create_dir(const char *name, struct dentry *parent, if (unlikely(!inode)) return failed_creating(dentry); - inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO; + /* Do not set bits for OTH */ + inode->i_mode = S_IFDIR | S_IRWXU | S_IRUSR| S_IRGRP | S_IXUSR | S_IXGRP; inode->i_op = ops; inode->i_fop = &simple_dir_operations; + inode->i_uid = d_inode(dentry->d_parent)->i_uid; + inode->i_gid = d_inode(dentry->d_parent)->i_gid; /* directory inodes start off with i_nlink == 2 (for "." entry) */ inc_nlink(inode); diff --git a/fs/ubifs/budget.c b/fs/ubifs/budget.c index 7ef22baf9d15..30c7bd63c2ad 100644 --- a/fs/ubifs/budget.c +++ b/fs/ubifs/budget.c @@ -224,11 +224,10 @@ long long ubifs_calc_available(const struct ubifs_info *c, int min_idx_lebs) subtract_lebs += 1; /* - * The GC journal head LEB is not really accessible. And since - * different write types go to different heads, we may count only on - * one head's space. + * Since different write types go to different heads, we should + * reserve one leb for each head. */ - subtract_lebs += c->jhead_cnt - 1; + subtract_lebs += c->jhead_cnt; /* We also reserve one LEB for deletions, which bypass budgeting */ subtract_lebs += 1; @@ -415,7 +414,7 @@ static int calc_dd_growth(const struct ubifs_info *c, dd_growth = req->dirtied_page ? c->bi.page_budget : 0; if (req->dirtied_ino) - dd_growth += c->bi.inode_budget << (req->dirtied_ino - 1); + dd_growth += c->bi.inode_budget * req->dirtied_ino; if (req->mod_dent) dd_growth += c->bi.dent_budget; dd_growth += req->dirtied_ino_d; diff --git a/fs/ubifs/commit.c b/fs/ubifs/commit.c index 591f2c7a48f0..583e20787689 100644 --- a/fs/ubifs/commit.c +++ b/fs/ubifs/commit.c @@ -564,11 +564,11 @@ out: */ int dbg_check_old_index(struct ubifs_info *c, struct ubifs_zbranch *zroot) { - int lnum, offs, len, err = 0, uninitialized_var(last_level), child_cnt; + int lnum, offs, len, err = 0, last_level, child_cnt; int first = 1, iip; struct ubifs_debug_info *d = c->dbg; - union ubifs_key uninitialized_var(lower_key), upper_key, l_key, u_key; - unsigned long long uninitialized_var(last_sqnum); + union ubifs_key lower_key, upper_key, l_key, u_key; + unsigned long long last_sqnum; struct ubifs_idx_node *idx; struct list_head list; struct idx_node *i; diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c index 564e330d05b1..24bbecd4752b 100644 --- a/fs/ubifs/debug.c +++ b/fs/ubifs/debug.c @@ -1129,6 +1129,7 @@ int dbg_check_dir(struct ubifs_info *c, const struct inode *dir) err = PTR_ERR(dent); if (err == -ENOENT) break; + kfree(pdent); return err; } diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index d7c0aa0626cd..39296e801242 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -220,11 +220,9 @@ static struct dentry *ubifs_lookup(struct inode *dir, struct dentry *dentry, dbg_gen("'%pd' in dir ino %lu", dentry, dir->i_ino); - err = fscrypt_prepare_lookup(dir, dentry, flags); - if (err) - return ERR_PTR(err); - - err = fscrypt_setup_filename(dir, &dentry->d_name, 1, &nm); + err = fscrypt_prepare_lookup(dir, dentry, &nm); + if (err == -ENOENT) + return d_splice_alias(NULL, dentry); if (err) return ERR_PTR(err); @@ -292,6 +290,15 @@ done: return d_splice_alias(inode, dentry); } +static int ubifs_prepare_create(struct inode *dir, struct dentry *dentry, + struct fscrypt_name *nm) +{ + if (fscrypt_is_nokey_name(dentry)) + return -ENOKEY; + + return fscrypt_setup_filename(dir, &dentry->d_name, 0, nm); +} + static int ubifs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { @@ -315,7 +322,7 @@ static int ubifs_create(struct inode *dir, struct dentry *dentry, umode_t mode, if (err) return err; - err = fscrypt_setup_filename(dir, &dentry->d_name, 0, &nm); + err = ubifs_prepare_create(dir, dentry, &nm); if (err) goto out_budg; @@ -366,15 +373,18 @@ static int do_tmpfile(struct inode *dir, struct dentry *dentry, { struct inode *inode; struct ubifs_info *c = dir->i_sb->s_fs_info; - struct ubifs_budget_req req = { .new_ino = 1, .new_dent = 1}; + struct ubifs_budget_req req = { .new_ino = 1, .new_dent = 1, + .dirtied_ino = 1}; struct ubifs_budget_req ino_req = { .dirtied_ino = 1 }; struct ubifs_inode *ui, *dir_ui = ubifs_inode(dir); int err, instantiated = 0; struct fscrypt_name nm; /* - * Budget request settings: new dirty inode, new direntry, - * budget for dirtied inode will be released via writeback. + * Budget request settings: new inode, new direntry, changing the + * parent directory inode. + * Allocate budget separately for new dirtied inode, the budget will + * be released via writeback. */ dbg_gen("dent '%pd', mode %#hx in dir ino %lu", @@ -435,6 +445,7 @@ static int do_tmpfile(struct inode *dir, struct dentry *dentry, mutex_unlock(&dir_ui->ui_mutex); ubifs_release_budget(c, &req); + fscrypt_free_filename(&nm); return 0; @@ -444,6 +455,8 @@ out_inode: make_bad_inode(inode); if (!instantiated) iput(inode); + else if (whiteout) + iput(*whiteout); out_budg: ubifs_release_budget(c, &req); if (!instantiated) @@ -964,7 +977,8 @@ static int ubifs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) struct ubifs_inode *dir_ui = ubifs_inode(dir); struct ubifs_info *c = dir->i_sb->s_fs_info; int err, sz_change; - struct ubifs_budget_req req = { .new_ino = 1, .new_dent = 1 }; + struct ubifs_budget_req req = { .new_ino = 1, .new_dent = 1, + .dirtied_ino = 1}; struct fscrypt_name nm; /* @@ -979,7 +993,7 @@ static int ubifs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) if (err) return err; - err = fscrypt_setup_filename(dir, &dentry->d_name, 0, &nm); + err = ubifs_prepare_create(dir, dentry, &nm); if (err) goto out_budg; @@ -1064,7 +1078,7 @@ static int ubifs_mknod(struct inode *dir, struct dentry *dentry, return err; } - err = fscrypt_setup_filename(dir, &dentry->d_name, 0, &nm); + err = ubifs_prepare_create(dir, dentry, &nm); if (err) { kfree(dev); goto out_budg; @@ -1128,7 +1142,6 @@ static int ubifs_symlink(struct inode *dir, struct dentry *dentry, int err, sz_change, len = strlen(symname); struct fscrypt_str disk_link; struct ubifs_budget_req req = { .new_ino = 1, .new_dent = 1, - .new_ino_d = ALIGN(len, 8), .dirtied_ino = 1 }; struct fscrypt_name nm; @@ -1144,11 +1157,12 @@ static int ubifs_symlink(struct inode *dir, struct dentry *dentry, * Budget request settings: new inode, new direntry and changing parent * directory inode. */ + req.new_ino_d = ALIGN(disk_link.len - 1, 8); err = ubifs_budget_space(c, &req); if (err) return err; - err = fscrypt_setup_filename(dir, &dentry->d_name, 0, &nm); + err = ubifs_prepare_create(dir, dentry, &nm); if (err) goto out_budg; @@ -1280,7 +1294,7 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry, struct ubifs_budget_req ino_req = { .dirtied_ino = 1, .dirtied_ino_d = ALIGN(old_inode_ui->data_len, 8) }; struct timespec64 time; - unsigned int uninitialized_var(saved_nlink); + unsigned int saved_nlink; struct fscrypt_name old_nm, new_nm; /* @@ -1296,9 +1310,13 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry, old_dentry, old_inode->i_ino, old_dir->i_ino, new_dentry, new_dir->i_ino, flags); - if (unlink) + if (unlink) { ubifs_assert(c, inode_is_locked(new_inode)); + /* Budget for old inode's data when its nlink > 1. */ + req.dirtied_ino_d = ALIGN(ubifs_inode(new_inode)->data_len, 8); + } + if (unlink && is_dir) { err = ubifs_check_dir_empty(new_inode); if (err) @@ -1334,6 +1352,7 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry, if (flags & RENAME_WHITEOUT) { union ubifs_dev_desc *dev = NULL; + struct ubifs_budget_req wht_req; dev = kmalloc(sizeof(union ubifs_dev_desc), GFP_NOFS); if (!dev) { @@ -1347,11 +1366,31 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry, goto out_release; } + spin_lock(&whiteout->i_lock); whiteout->i_state |= I_LINKABLE; + spin_unlock(&whiteout->i_lock); + whiteout_ui = ubifs_inode(whiteout); whiteout_ui->data = dev; whiteout_ui->data_len = ubifs_encode_dev(dev, MKDEV(0, 0)); ubifs_assert(c, !whiteout_ui->dirty); + + memset(&wht_req, 0, sizeof(struct ubifs_budget_req)); + wht_req.dirtied_ino = 1; + wht_req.dirtied_ino_d = ALIGN(whiteout_ui->data_len, 8); + /* + * To avoid deadlock between space budget (holds ui_mutex and + * waits wb work) and writeback work(waits ui_mutex), do space + * budget before ubifs inodes locked. + */ + err = ubifs_budget_space(c, &wht_req); + if (err) { + iput(whiteout); + goto out_release; + } + + /* Add the old_dentry size to the old_dir size. */ + old_sz -= CALC_DENT_SIZE(fname_len(&old_nm)); } lock_4_inodes(old_dir, new_dir, new_inode, whiteout); @@ -1426,21 +1465,13 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry, } if (whiteout) { - struct ubifs_budget_req wht_req = { .dirtied_ino = 1, - .dirtied_ino_d = \ - ALIGN(ubifs_inode(whiteout)->data_len, 8) }; - - err = ubifs_budget_space(c, &wht_req); - if (err) { - kfree(whiteout_ui->data); - whiteout_ui->data_len = 0; - iput(whiteout); - goto out_release; - } - inc_nlink(whiteout); mark_inode_dirty(whiteout); + + spin_lock(&whiteout->i_lock); whiteout->i_state &= ~I_LINKABLE; + spin_unlock(&whiteout->i_lock); + iput(whiteout); } @@ -1523,6 +1554,10 @@ static int ubifs_xrename(struct inode *old_dir, struct dentry *old_dentry, return err; } + err = ubifs_budget_space(c, &req); + if (err) + goto out; + lock_4_inodes(old_dir, new_dir, NULL, NULL); time = current_time(old_dir); @@ -1548,6 +1583,7 @@ static int ubifs_xrename(struct inode *old_dir, struct dentry *old_dentry, unlock_4_inodes(old_dir, new_dir, NULL, NULL); ubifs_release_budget(c, &req); +out: fscrypt_free_filename(&fst_nm); fscrypt_free_filename(&snd_nm); return err; diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index d7d2fdda4bbd..fca3b7f483c7 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -234,7 +234,7 @@ static int write_begin_slow(struct address_space *mapping, struct ubifs_info *c = inode->i_sb->s_fs_info; pgoff_t index = pos >> PAGE_SHIFT; struct ubifs_budget_req req = { .new_page = 1 }; - int uninitialized_var(err), appending = !!(pos + len > inode->i_size); + int err, appending = !!(pos + len > inode->i_size); struct page *page; dbg_gen("ino %lu, pos %llu, len %u, i_size %lld", @@ -438,7 +438,7 @@ static int ubifs_write_begin(struct file *file, struct address_space *mapping, struct ubifs_info *c = inode->i_sb->s_fs_info; struct ubifs_inode *ui = ubifs_inode(inode); pgoff_t index = pos >> PAGE_SHIFT; - int uninitialized_var(err), appending = !!(pos + len > inode->i_size); + int err, appending = !!(pos + len > inode->i_size); int skipped_read = 0; struct page *page; @@ -1043,7 +1043,7 @@ static int ubifs_writepage(struct page *page, struct writeback_control *wbc) if (page->index >= synced_i_size >> PAGE_SHIFT) { err = inode->i_sb->s_op->write_inode(inode, NULL); if (err) - goto out_unlock; + goto out_redirty; /* * The inode has been written, but the write-buffer has * not been synchronized, so in case of an unclean @@ -1071,11 +1071,17 @@ static int ubifs_writepage(struct page *page, struct writeback_control *wbc) if (i_size > synced_i_size) { err = inode->i_sb->s_op->write_inode(inode, NULL); if (err) - goto out_unlock; + goto out_redirty; } return do_writepage(page, len); - +out_redirty: + /* + * redirty_page_for_writepage() won't call ubifs_dirty_inode() because + * it passes I_DIRTY_PAGES flag while calling __mark_inode_dirty(), so + * there is no need to do space budget for dirty inode. + */ + redirty_page_for_writepage(wbc, page); out_unlock: unlock_page(page); return err; @@ -1642,6 +1648,16 @@ static const char *ubifs_get_link(struct dentry *dentry, return fscrypt_get_symlink(inode, ui->data, ui->data_len, done); } +static int ubifs_symlink_getattr(const struct path *path, struct kstat *stat, + u32 request_mask, unsigned int query_flags) +{ + ubifs_getattr(path, stat, request_mask, query_flags); + + if (IS_ENCRYPTED(d_inode(path->dentry))) + return fscrypt_symlink_getattr(path, stat); + return 0; +} + const struct address_space_operations ubifs_file_address_operations = { .readpage = ubifs_readpage, .writepage = ubifs_writepage, @@ -1669,7 +1685,7 @@ const struct inode_operations ubifs_file_inode_operations = { const struct inode_operations ubifs_symlink_inode_operations = { .get_link = ubifs_get_link, .setattr = ubifs_setattr, - .getattr = ubifs_getattr, + .getattr = ubifs_symlink_getattr, #ifdef CONFIG_UBIFS_FS_XATTR .listxattr = ubifs_listxattr, #endif diff --git a/fs/ubifs/io.c b/fs/ubifs/io.c index fab29f899f91..0ad819c904df 100644 --- a/fs/ubifs/io.c +++ b/fs/ubifs/io.c @@ -331,7 +331,7 @@ void ubifs_pad(const struct ubifs_info *c, void *buf, int pad) { uint32_t crc; - ubifs_assert(c, pad >= 0 && !(pad & 7)); + ubifs_assert(c, pad >= 0); if (pad >= UBIFS_PAD_NODE_SZ) { struct ubifs_ch *ch = buf; @@ -728,6 +728,10 @@ int ubifs_wbuf_write_nolock(struct ubifs_wbuf *wbuf, void *buf, int len) * write-buffer. */ memcpy(wbuf->buf + wbuf->used, buf, len); + if (aligned_len > len) { + ubifs_assert(c, aligned_len - len < 8); + ubifs_pad(c, wbuf->buf + wbuf->used + len, aligned_len - len); + } if (aligned_len == wbuf->avail) { dbg_io("flush jhead %s wbuf to LEB %d:%d", @@ -806,27 +810,58 @@ int ubifs_wbuf_write_nolock(struct ubifs_wbuf *wbuf, void *buf, int len) */ n = aligned_len >> c->max_write_shift; if (n) { - n <<= c->max_write_shift; + int m = n - 1; + dbg_io("write %d bytes to LEB %d:%d", n, wbuf->lnum, wbuf->offs); - err = ubifs_leb_write(c, wbuf->lnum, buf + written, - wbuf->offs, n); + + if (m) { + /* '(n-1)<<c->max_write_shift < len' is always true. */ + m <<= c->max_write_shift; + err = ubifs_leb_write(c, wbuf->lnum, buf + written, + wbuf->offs, m); + if (err) + goto out; + wbuf->offs += m; + aligned_len -= m; + len -= m; + written += m; + } + + /* + * The non-written len of buf may be less than 'n' because + * parameter 'len' is not 8 bytes aligned, so here we read + * min(len, n) bytes from buf. + */ + n = 1 << c->max_write_shift; + memcpy(wbuf->buf, buf + written, min(len, n)); + if (n > len) { + ubifs_assert(c, n - len < 8); + ubifs_pad(c, wbuf->buf + len, n - len); + } + + err = ubifs_leb_write(c, wbuf->lnum, wbuf->buf, wbuf->offs, n); if (err) goto out; wbuf->offs += n; aligned_len -= n; - len -= n; + len -= min(len, n); written += n; } spin_lock(&wbuf->lock); - if (aligned_len) + if (aligned_len) { /* * And now we have what's left and what does not take whole * max. write unit, so write it to the write-buffer and we are * done. */ memcpy(wbuf->buf, buf + written, len); + if (aligned_len > len) { + ubifs_assert(c, aligned_len - len < 8); + ubifs_pad(c, wbuf->buf + len, aligned_len - len); + } + } if (c->leb_size - wbuf->offs >= c->max_write_size) wbuf->size = c->max_write_size; diff --git a/fs/ubifs/ioctl.c b/fs/ubifs/ioctl.c index e666459f63c7..3fca4f741412 100644 --- a/fs/ubifs/ioctl.c +++ b/fs/ubifs/ioctl.c @@ -113,7 +113,7 @@ static int setflags(struct inode *inode, int flags) struct ubifs_inode *ui = ubifs_inode(inode); struct ubifs_info *c = inode->i_sb->s_fs_info; struct ubifs_budget_req req = { .dirtied_ino = 1, - .dirtied_ino_d = ui->data_len }; + .dirtied_ino_d = ALIGN(ui->data_len, 8) }; err = ubifs_budget_space(c, &req); if (err) diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c index 802565a17733..0a60a065c7e8 100644 --- a/fs/ubifs/journal.c +++ b/fs/ubifs/journal.c @@ -1355,7 +1355,7 @@ int ubifs_jnl_truncate(struct ubifs_info *c, const struct inode *inode, union ubifs_key key, to_key; struct ubifs_ino_node *ino; struct ubifs_trun_node *trun; - struct ubifs_data_node *uninitialized_var(dn); + struct ubifs_data_node *dn; int err, dlen, len, lnum, offs, bit, sz, sync = IS_SYNC(inode); struct ubifs_inode *ui = ubifs_inode(inode); ino_t inum = inode->i_ino; diff --git a/fs/ubifs/lpt.c b/fs/ubifs/lpt.c index 31393370e334..433bfcddc497 100644 --- a/fs/ubifs/lpt.c +++ b/fs/ubifs/lpt.c @@ -287,7 +287,7 @@ uint32_t ubifs_unpack_bits(const struct ubifs_info *c, uint8_t **addr, int *pos, const int k = 32 - nrbits; uint8_t *p = *addr; int b = *pos; - uint32_t uninitialized_var(val); + uint32_t val; const int bytes = (nrbits + b + 7) >> 3; ubifs_assert(c, nrbits > 0); diff --git a/fs/ubifs/replay.c b/fs/ubifs/replay.c index c6f9b2225387..673d1f08b9a4 100644 --- a/fs/ubifs/replay.c +++ b/fs/ubifs/replay.c @@ -232,7 +232,8 @@ static bool inode_still_linked(struct ubifs_info *c, struct replay_entry *rino) */ list_for_each_entry_reverse(r, &c->replay_list, list) { ubifs_assert(c, r->sqnum >= rino->sqnum); - if (key_inum(c, &r->key) == key_inum(c, &rino->key)) + if (key_inum(c, &r->key) == key_inum(c, &rino->key) && + key_type(c, &r->key) == UBIFS_INO_KEY) return r->deletion == 0; } diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index fec62e9dfbe6..f5b663d70826 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -1730,7 +1730,6 @@ out: kthread_stop(c->bgt); c->bgt = NULL; } - free_wbufs(c); kfree(c->write_reserve_buf); c->write_reserve_buf = NULL; vfree(c->ileb_buf); diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c index f15ac37956e7..330ccf72745b 100644 --- a/fs/ubifs/tnc.c +++ b/fs/ubifs/tnc.c @@ -56,6 +56,33 @@ enum { NOT_ON_MEDIA = 3, }; +static void do_insert_old_idx(struct ubifs_info *c, + struct ubifs_old_idx *old_idx) +{ + struct ubifs_old_idx *o; + struct rb_node **p, *parent = NULL; + + p = &c->old_idx.rb_node; + while (*p) { + parent = *p; + o = rb_entry(parent, struct ubifs_old_idx, rb); + if (old_idx->lnum < o->lnum) + p = &(*p)->rb_left; + else if (old_idx->lnum > o->lnum) + p = &(*p)->rb_right; + else if (old_idx->offs < o->offs) + p = &(*p)->rb_left; + else if (old_idx->offs > o->offs) + p = &(*p)->rb_right; + else { + ubifs_err(c, "old idx added twice!"); + kfree(old_idx); + } + } + rb_link_node(&old_idx->rb, parent, p); + rb_insert_color(&old_idx->rb, &c->old_idx); +} + /** * insert_old_idx - record an index node obsoleted since the last commit start. * @c: UBIFS file-system description object @@ -81,35 +108,15 @@ enum { */ static int insert_old_idx(struct ubifs_info *c, int lnum, int offs) { - struct ubifs_old_idx *old_idx, *o; - struct rb_node **p, *parent = NULL; + struct ubifs_old_idx *old_idx; old_idx = kmalloc(sizeof(struct ubifs_old_idx), GFP_NOFS); if (unlikely(!old_idx)) return -ENOMEM; old_idx->lnum = lnum; old_idx->offs = offs; + do_insert_old_idx(c, old_idx); - p = &c->old_idx.rb_node; - while (*p) { - parent = *p; - o = rb_entry(parent, struct ubifs_old_idx, rb); - if (lnum < o->lnum) - p = &(*p)->rb_left; - else if (lnum > o->lnum) - p = &(*p)->rb_right; - else if (offs < o->offs) - p = &(*p)->rb_left; - else if (offs > o->offs) - p = &(*p)->rb_right; - else { - ubifs_err(c, "old idx added twice!"); - kfree(old_idx); - return 0; - } - } - rb_link_node(&old_idx->rb, parent, p); - rb_insert_color(&old_idx->rb, &c->old_idx); return 0; } @@ -211,23 +218,6 @@ static struct ubifs_znode *copy_znode(struct ubifs_info *c, __set_bit(DIRTY_ZNODE, &zn->flags); __clear_bit(COW_ZNODE, &zn->flags); - ubifs_assert(c, !ubifs_zn_obsolete(znode)); - __set_bit(OBSOLETE_ZNODE, &znode->flags); - - if (znode->level != 0) { - int i; - const int n = zn->child_cnt; - - /* The children now have new parent */ - for (i = 0; i < n; i++) { - struct ubifs_zbranch *zbr = &zn->zbranch[i]; - - if (zbr->znode) - zbr->znode->parent = zn; - } - } - - atomic_long_inc(&c->dirty_zn_cnt); return zn; } @@ -246,6 +236,42 @@ static int add_idx_dirt(struct ubifs_info *c, int lnum, int dirt) } /** + * replace_znode - replace old znode with new znode. + * @c: UBIFS file-system description object + * @new_zn: new znode + * @old_zn: old znode + * @zbr: the branch of parent znode + * + * Replace old znode with new znode in TNC. + */ +static void replace_znode(struct ubifs_info *c, struct ubifs_znode *new_zn, + struct ubifs_znode *old_zn, struct ubifs_zbranch *zbr) +{ + ubifs_assert(c, !ubifs_zn_obsolete(old_zn)); + __set_bit(OBSOLETE_ZNODE, &old_zn->flags); + + if (old_zn->level != 0) { + int i; + const int n = new_zn->child_cnt; + + /* The children now have new parent */ + for (i = 0; i < n; i++) { + struct ubifs_zbranch *child = &new_zn->zbranch[i]; + + if (child->znode) + child->znode->parent = new_zn; + } + } + + zbr->znode = new_zn; + zbr->lnum = 0; + zbr->offs = 0; + zbr->len = 0; + + atomic_long_inc(&c->dirty_zn_cnt); +} + +/** * dirty_cow_znode - ensure a znode is not being committed. * @c: UBIFS file-system description object * @zbr: branch of znode to check @@ -277,21 +303,32 @@ static struct ubifs_znode *dirty_cow_znode(struct ubifs_info *c, return zn; if (zbr->len) { - err = insert_old_idx(c, zbr->lnum, zbr->offs); - if (unlikely(err)) - return ERR_PTR(err); + struct ubifs_old_idx *old_idx; + + old_idx = kmalloc(sizeof(struct ubifs_old_idx), GFP_NOFS); + if (unlikely(!old_idx)) { + err = -ENOMEM; + goto out; + } + old_idx->lnum = zbr->lnum; + old_idx->offs = zbr->offs; + err = add_idx_dirt(c, zbr->lnum, zbr->len); - } else - err = 0; + if (err) { + kfree(old_idx); + goto out; + } - zbr->znode = zn; - zbr->lnum = 0; - zbr->offs = 0; - zbr->len = 0; + do_insert_old_idx(c, old_idx); + } + + replace_znode(c, zn, znode, zbr); - if (unlikely(err)) - return ERR_PTR(err); return zn; + +out: + kfree(zn); + return ERR_PTR(err); } /** @@ -899,7 +936,7 @@ static int fallible_resolve_collision(struct ubifs_info *c, int adding) { struct ubifs_znode *o_znode = NULL, *znode = *zn; - int uninitialized_var(o_n), err, cmp, unsure = 0, nn = *n; + int o_n, err, cmp, unsure = 0, nn = *n; cmp = fallible_matches_name(c, &znode->zbranch[nn], nm); if (unlikely(cmp < 0)) @@ -1521,8 +1558,8 @@ out: */ int ubifs_tnc_get_bu_keys(struct ubifs_info *c, struct bu_info *bu) { - int n, err = 0, lnum = -1, uninitialized_var(offs); - int uninitialized_var(len); + int n, err = 0, lnum = -1, offs; + int len; unsigned int block = key_block(c, &bu->key); struct ubifs_znode *znode; @@ -3046,6 +3083,21 @@ static void tnc_destroy_cnext(struct ubifs_info *c) cnext = cnext->cnext; if (ubifs_zn_obsolete(znode)) kfree(znode); + else if (!ubifs_zn_cow(znode)) { + /* + * Don't forget to update clean znode count after + * committing failed, because ubifs will check this + * count while closing tnc. Non-obsolete znode could + * be re-dirtied during committing process, so dirty + * flag is untrustable. The flag 'COW_ZNODE' is set + * for each dirty znode before committing, and it is + * cleared as long as the znode become clean, so we + * can statistic clean znode count according to this + * flag. + */ + atomic_long_inc(&c->clean_zn_cnt); + atomic_long_inc(&ubifs_clean_zn_cnt); + } } while (cnext && cnext != c->cnext); } diff --git a/fs/ubifs/tnc_misc.c b/fs/ubifs/tnc_misc.c index d90ee01076a9..fe3b52d2749b 100644 --- a/fs/ubifs/tnc_misc.c +++ b/fs/ubifs/tnc_misc.c @@ -138,8 +138,8 @@ int ubifs_search_zbranch(const struct ubifs_info *c, const struct ubifs_znode *znode, const union ubifs_key *key, int *n) { - int beg = 0, end = znode->child_cnt, uninitialized_var(mid); - int uninitialized_var(cmp); + int beg = 0, end = znode->child_cnt, mid; + int cmp; const struct ubifs_zbranch *zbr = &znode->zbranch[0]; ubifs_assert(c, end > beg); diff --git a/fs/udf/balloc.c b/fs/udf/balloc.c index fcda0fc97b90..0dc98bbad9c4 100644 --- a/fs/udf/balloc.c +++ b/fs/udf/balloc.c @@ -36,18 +36,41 @@ static int read_block_bitmap(struct super_block *sb, unsigned long bitmap_nr) { struct buffer_head *bh = NULL; - int retval = 0; + int i; + int max_bits, off, count; struct kernel_lb_addr loc; loc.logicalBlockNum = bitmap->s_extPosition; loc.partitionReferenceNum = UDF_SB(sb)->s_partition; bh = udf_tread(sb, udf_get_lb_pblock(sb, &loc, block)); + bitmap->s_block_bitmap[bitmap_nr] = bh; if (!bh) - retval = -EIO; + return -EIO; - bitmap->s_block_bitmap[bitmap_nr] = bh; - return retval; + /* Check consistency of Space Bitmap buffer. */ + max_bits = sb->s_blocksize * 8; + if (!bitmap_nr) { + off = sizeof(struct spaceBitmapDesc) << 3; + count = min(max_bits - off, bitmap->s_nr_groups); + } else { + /* + * Rough check if bitmap number is too big to have any bitmap + * blocks reserved. + */ + if (bitmap_nr > + (bitmap->s_nr_groups >> (sb->s_blocksize_bits + 3)) + 2) + return 0; + off = 0; + count = bitmap->s_nr_groups - bitmap_nr * max_bits + + (sizeof(struct spaceBitmapDesc) << 3); + count = min(count, max_bits); + } + + for (i = 0; i < count; i++) + if (udf_test_bit(i + off, bh->b_data)) + return -EFSCORRUPTED; + return 0; } static int __load_block_bitmap(struct super_block *sb, @@ -555,7 +578,7 @@ static udf_pblk_t udf_table_new_block(struct super_block *sb, udf_pblk_t newblock = 0; uint32_t adsize; uint32_t elen, goal_elen = 0; - struct kernel_lb_addr eloc, uninitialized_var(goal_eloc); + struct kernel_lb_addr eloc, goal_eloc; struct extent_position epos, goal_epos; int8_t etype; struct udf_inode_info *iinfo = UDF_I(table); diff --git a/fs/udf/dir.c b/fs/udf/dir.c index c19dba45aa20..d0f92a52e3ba 100644 --- a/fs/udf/dir.c +++ b/fs/udf/dir.c @@ -31,6 +31,7 @@ #include <linux/mm.h> #include <linux/slab.h> #include <linux/bio.h> +#include <linux/iversion.h> #include "udf_i.h" #include "udf_sb.h" @@ -44,7 +45,7 @@ static int udf_readdir(struct file *file, struct dir_context *ctx) struct fileIdentDesc *fi = NULL; struct fileIdentDesc cfi; udf_pblk_t block, iblock; - loff_t nf_pos; + loff_t nf_pos, emit_pos = 0; int flen; unsigned char *fname = NULL, *copy_name = NULL; unsigned char *nameptr; @@ -58,6 +59,7 @@ static int udf_readdir(struct file *file, struct dir_context *ctx) int i, num, ret = 0; struct extent_position epos = { NULL, 0, {0, 0} }; struct super_block *sb = dir->i_sb; + bool pos_valid = false; if (ctx->pos == 0) { if (!dir_emit_dot(file, ctx)) @@ -68,6 +70,21 @@ static int udf_readdir(struct file *file, struct dir_context *ctx) if (nf_pos >= size) goto out; + /* + * Something changed since last readdir (either lseek was called or dir + * changed)? We need to verify the position correctly points at the + * beginning of some dir entry so that the directory parsing code does + * not get confused. Since UDF does not have any reliable way of + * identifying beginning of dir entry (names are under user control), + * we need to scan the directory from the beginning. + */ + if (!inode_eq_iversion(dir, file->f_version)) { + emit_pos = nf_pos; + nf_pos = 0; + } else { + pos_valid = true; + } + fname = kmalloc(UDF_NAME_LEN, GFP_NOFS); if (!fname) { ret = -ENOMEM; @@ -123,13 +140,21 @@ static int udf_readdir(struct file *file, struct dir_context *ctx) while (nf_pos < size) { struct kernel_lb_addr tloc; + loff_t cur_pos = nf_pos; - ctx->pos = (nf_pos >> 2) + 1; + /* Update file position only if we got past the current one */ + if (nf_pos >= emit_pos) { + ctx->pos = (nf_pos >> 2) + 1; + pos_valid = true; + } fi = udf_fileident_read(dir, &nf_pos, &fibh, &cfi, &epos, &eloc, &elen, &offset); if (!fi) goto out; + /* Still not at offset where user asked us to read from? */ + if (cur_pos < emit_pos) + continue; liu = le16_to_cpu(cfi.lengthOfImpUse); lfi = cfi.lengthFileIdent; @@ -187,8 +212,11 @@ static int udf_readdir(struct file *file, struct dir_context *ctx) } /* end while */ ctx->pos = (nf_pos >> 2) + 1; + pos_valid = true; out: + if (pos_valid) + file->f_version = inode_query_iversion(dir); if (fibh.sbh != fibh.ebh) brelse(fibh.ebh); brelse(fibh.sbh); diff --git a/fs/udf/directory.c b/fs/udf/directory.c index d9523013096f..73720320f0ab 100644 --- a/fs/udf/directory.c +++ b/fs/udf/directory.c @@ -34,7 +34,7 @@ struct fileIdentDesc *udf_fileident_read(struct inode *dir, loff_t *nf_pos, fibh->soffset = fibh->eoffset; if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { - fi = udf_get_fileident(iinfo->i_ext.i_data - + fi = udf_get_fileident(iinfo->i_data - (iinfo->i_efe ? sizeof(struct extendedFileEntry) : sizeof(struct fileEntry)), diff --git a/fs/udf/file.c b/fs/udf/file.c index cd31e4f6d6da..8fff7ffc33a8 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -50,7 +50,7 @@ static void __udf_adinicb_readpage(struct page *page) * So just sample it once and use the same value everywhere. */ kaddr = kmap_atomic(page); - memcpy(kaddr, iinfo->i_ext.i_data + iinfo->i_lenEAttr, isize); + memcpy(kaddr, iinfo->i_data + iinfo->i_lenEAttr, isize); memset(kaddr + isize, 0, PAGE_SIZE - isize); flush_dcache_page(page); SetPageUptodate(page); @@ -76,8 +76,7 @@ static int udf_adinicb_writepage(struct page *page, BUG_ON(!PageLocked(page)); kaddr = kmap_atomic(page); - memcpy(iinfo->i_ext.i_data + iinfo->i_lenEAttr, kaddr, - i_size_read(inode)); + memcpy(iinfo->i_data + iinfo->i_lenEAttr, kaddr, i_size_read(inode)); SetPageUptodate(page); kunmap_atomic(kaddr); mark_inode_dirty(inode); @@ -148,26 +147,24 @@ static ssize_t udf_file_write_iter(struct kiocb *iocb, struct iov_iter *from) goto out; down_write(&iinfo->i_data_sem); - if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { - loff_t end = iocb->ki_pos + iov_iter_count(from); - - if (inode->i_sb->s_blocksize < - (udf_file_entry_alloc_offset(inode) + end)) { - err = udf_expand_file_adinicb(inode); - if (err) { - inode_unlock(inode); - udf_debug("udf_expand_adinicb: err=%d\n", err); - return err; - } - } else { - iinfo->i_lenAlloc = max(end, inode->i_size); - up_write(&iinfo->i_data_sem); + if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB && + inode->i_sb->s_blocksize < (udf_file_entry_alloc_offset(inode) + + iocb->ki_pos + iov_iter_count(from))) { + err = udf_expand_file_adinicb(inode); + if (err) { + inode_unlock(inode); + udf_debug("udf_expand_adinicb: err=%d\n", err); + return err; } } else up_write(&iinfo->i_data_sem); retval = __generic_file_write_iter(iocb, from); out: + down_write(&iinfo->i_data_sem); + if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB && retval > 0) + iinfo->i_lenAlloc = inode->i_size; + up_write(&iinfo->i_data_sem); inode_unlock(inode); if (retval > 0) { @@ -215,7 +212,7 @@ long udf_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return put_user(UDF_I(inode)->i_lenEAttr, (int __user *)arg); case UDF_GETEABLOCK: return copy_to_user((char __user *)arg, - UDF_I(inode)->i_ext.i_data, + UDF_I(inode)->i_data, UDF_I(inode)->i_lenEAttr) ? -EFAULT : 0; default: return -ENOIOCTLCMD; diff --git a/fs/udf/ialloc.c b/fs/udf/ialloc.c index f8e5872f7cc2..cdaa86e077b2 100644 --- a/fs/udf/ialloc.c +++ b/fs/udf/ialloc.c @@ -67,16 +67,16 @@ struct inode *udf_new_inode(struct inode *dir, umode_t mode) iinfo->i_efe = 1; if (UDF_VERS_USE_EXTENDED_FE > sbi->s_udfrev) sbi->s_udfrev = UDF_VERS_USE_EXTENDED_FE; - iinfo->i_ext.i_data = kzalloc(inode->i_sb->s_blocksize - - sizeof(struct extendedFileEntry), - GFP_KERNEL); + iinfo->i_data = kzalloc(inode->i_sb->s_blocksize - + sizeof(struct extendedFileEntry), + GFP_KERNEL); } else { iinfo->i_efe = 0; - iinfo->i_ext.i_data = kzalloc(inode->i_sb->s_blocksize - - sizeof(struct fileEntry), - GFP_KERNEL); + iinfo->i_data = kzalloc(inode->i_sb->s_blocksize - + sizeof(struct fileEntry), + GFP_KERNEL); } - if (!iinfo->i_ext.i_data) { + if (!iinfo->i_data) { iput(inode); return ERR_PTR(-ENOMEM); } diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 4c46ebf0e773..08d7208eb7b7 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -50,15 +50,15 @@ static int udf_update_inode(struct inode *, int); static int udf_sync_inode(struct inode *inode); static int udf_alloc_i_data(struct inode *inode, size_t size); static sector_t inode_getblk(struct inode *, sector_t, int *, int *); -static int8_t udf_insert_aext(struct inode *, struct extent_position, - struct kernel_lb_addr, uint32_t); +static int udf_insert_aext(struct inode *, struct extent_position, + struct kernel_lb_addr, uint32_t); static void udf_split_extents(struct inode *, int *, int, udf_pblk_t, struct kernel_long_ad *, int *); static void udf_prealloc_extents(struct inode *, int, int, struct kernel_long_ad *, int *); static void udf_merge_extents(struct inode *, struct kernel_long_ad *, int *); -static void udf_update_extents(struct inode *, struct kernel_long_ad *, int, - int, struct extent_position *); +static int udf_update_extents(struct inode *, struct kernel_long_ad *, int, + int, struct extent_position *); static int udf_get_block(struct inode *, sector_t, struct buffer_head *, int); static void __udf_clear_extent_cache(struct inode *inode) @@ -132,23 +132,26 @@ void udf_evict_inode(struct inode *inode) struct udf_inode_info *iinfo = UDF_I(inode); int want_delete = 0; - if (!inode->i_nlink && !is_bad_inode(inode)) { - want_delete = 1; - udf_setsize(inode, 0); - udf_update_inode(inode, IS_SYNC(inode)); + if (!is_bad_inode(inode)) { + if (!inode->i_nlink) { + want_delete = 1; + udf_setsize(inode, 0); + udf_update_inode(inode, IS_SYNC(inode)); + } + if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB && + inode->i_size != iinfo->i_lenExtents) { + udf_warn(inode->i_sb, + "Inode %lu (mode %o) has inode size %llu different from extent length %llu. Filesystem need not be standards compliant.\n", + inode->i_ino, inode->i_mode, + (unsigned long long)inode->i_size, + (unsigned long long)iinfo->i_lenExtents); + } } truncate_inode_pages_final(&inode->i_data); invalidate_inode_buffers(inode); clear_inode(inode); - if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB && - inode->i_size != iinfo->i_lenExtents) { - udf_warn(inode->i_sb, "Inode %lu (mode %o) has inode size %llu different from extent length %llu. Filesystem need not be standards compliant.\n", - inode->i_ino, inode->i_mode, - (unsigned long long)inode->i_size, - (unsigned long long)iinfo->i_lenExtents); - } - kfree(iinfo->i_ext.i_data); - iinfo->i_ext.i_data = NULL; + kfree(iinfo->i_data); + iinfo->i_data = NULL; udf_clear_extent_cache(inode); if (want_delete) { udf_free_inode(inode); @@ -248,10 +251,6 @@ int udf_expand_file_adinicb(struct inode *inode) char *kaddr; struct udf_inode_info *iinfo = UDF_I(inode); int err; - struct writeback_control udf_wbc = { - .sync_mode = WB_SYNC_NONE, - .nr_to_write = 1, - }; WARN_ON_ONCE(!inode_is_locked(inode)); if (!iinfo->i_lenAlloc) { @@ -279,14 +278,14 @@ int udf_expand_file_adinicb(struct inode *inode) kaddr = kmap_atomic(page); memset(kaddr + iinfo->i_lenAlloc, 0x00, PAGE_SIZE - iinfo->i_lenAlloc); - memcpy(kaddr, iinfo->i_ext.i_data + iinfo->i_lenEAttr, + memcpy(kaddr, iinfo->i_data + iinfo->i_lenEAttr, iinfo->i_lenAlloc); flush_dcache_page(page); SetPageUptodate(page); kunmap_atomic(kaddr); } down_write(&iinfo->i_data_sem); - memset(iinfo->i_ext.i_data + iinfo->i_lenEAttr, 0x00, + memset(iinfo->i_data + iinfo->i_lenEAttr, 0x00, iinfo->i_lenAlloc); iinfo->i_lenAlloc = 0; if (UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_USE_SHORT_AD)) @@ -295,19 +294,21 @@ int udf_expand_file_adinicb(struct inode *inode) iinfo->i_alloc_type = ICBTAG_FLAG_AD_LONG; /* from now on we have normal address_space methods */ inode->i_data.a_ops = &udf_aops; + set_page_dirty(page); + unlock_page(page); up_write(&iinfo->i_data_sem); - err = inode->i_data.a_ops->writepage(page, &udf_wbc); + err = filemap_fdatawrite(inode->i_mapping); if (err) { /* Restore everything back so that we don't lose data... */ lock_page(page); down_write(&iinfo->i_data_sem); kaddr = kmap_atomic(page); - memcpy(iinfo->i_ext.i_data + iinfo->i_lenEAttr, kaddr, - inode->i_size); + memcpy(iinfo->i_data + iinfo->i_lenEAttr, kaddr, inode->i_size); kunmap_atomic(kaddr); unlock_page(page); iinfo->i_alloc_type = ICBTAG_FLAG_AD_IN_ICB; inode->i_data.a_ops = &udf_adinicb_aops; + iinfo->i_lenAlloc = inode->i_size; up_write(&iinfo->i_data_sem); } put_page(page); @@ -390,8 +391,7 @@ struct buffer_head *udf_expand_dir_adinicb(struct inode *inode, } mark_buffer_dirty_inode(dbh, inode); - memset(iinfo->i_ext.i_data + iinfo->i_lenEAttr, 0, - iinfo->i_lenAlloc); + memset(iinfo->i_data + iinfo->i_lenEAttr, 0, iinfo->i_lenAlloc); iinfo->i_lenAlloc = 0; eloc.logicalBlockNum = *block; eloc.partitionReferenceNum = @@ -432,6 +432,12 @@ static int udf_get_block(struct inode *inode, sector_t block, iinfo->i_next_alloc_goal++; } + /* + * Block beyond EOF and prealloc extents? Just discard preallocation + * as it is not useful and complicates things. + */ + if (((loff_t)block) << inode->i_blkbits > iinfo->i_lenExtents) + udf_discard_prealloc(inode); udf_clear_extent_cache(inode); phys = inode_getblk(inode, block, &err, &new); if (!phys) @@ -481,8 +487,6 @@ static int udf_do_extend_file(struct inode *inode, uint32_t add; int count = 0, fake = !(last_ext->extLength & UDF_EXTENT_LENGTH_MASK); struct super_block *sb = inode->i_sb; - struct kernel_lb_addr prealloc_loc = {}; - uint32_t prealloc_len = 0; struct udf_inode_info *iinfo; int err; @@ -503,19 +507,6 @@ static int udf_do_extend_file(struct inode *inode, ~(sb->s_blocksize - 1); } - /* Last extent are just preallocated blocks? */ - if ((last_ext->extLength & UDF_EXTENT_FLAG_MASK) == - EXT_NOT_RECORDED_ALLOCATED) { - /* Save the extent so that we can reattach it to the end */ - prealloc_loc = last_ext->extLocation; - prealloc_len = last_ext->extLength; - /* Mark the extent as a hole */ - last_ext->extLength = EXT_NOT_RECORDED_NOT_ALLOCATED | - (last_ext->extLength & UDF_EXTENT_LENGTH_MASK); - last_ext->extLocation.logicalBlockNum = 0; - last_ext->extLocation.partitionReferenceNum = 0; - } - /* Can we merge with the previous extent? */ if ((last_ext->extLength & UDF_EXTENT_FLAG_MASK) == EXT_NOT_RECORDED_NOT_ALLOCATED) { @@ -528,8 +519,10 @@ static int udf_do_extend_file(struct inode *inode, } if (fake) { - udf_add_aext(inode, last_pos, &last_ext->extLocation, - last_ext->extLength, 1); + err = udf_add_aext(inode, last_pos, &last_ext->extLocation, + last_ext->extLength, 1); + if (err < 0) + goto out_err; count++; } else { struct kernel_lb_addr tmploc; @@ -537,11 +530,14 @@ static int udf_do_extend_file(struct inode *inode, udf_write_aext(inode, last_pos, &last_ext->extLocation, last_ext->extLength, 1); + /* - * We've rewritten the last extent but there may be empty - * indirect extent after it - enter it. + * We've rewritten the last extent. If we are going to add + * more extents, we may need to enter possible following + * empty indirect extent. */ - udf_next_aext(inode, last_pos, &tmploc, &tmplen, 0); + if (new_block_bytes) + udf_next_aext(inode, last_pos, &tmploc, &tmplen, 0); } /* Managed to do everything necessary? */ @@ -560,7 +556,7 @@ static int udf_do_extend_file(struct inode *inode, err = udf_add_aext(inode, last_pos, &last_ext->extLocation, last_ext->extLength, 1); if (err) - return err; + goto out_err; count++; } if (new_block_bytes) { @@ -569,22 +565,11 @@ static int udf_do_extend_file(struct inode *inode, err = udf_add_aext(inode, last_pos, &last_ext->extLocation, last_ext->extLength, 1); if (err) - return err; + goto out_err; count++; } out: - /* Do we have some preallocated blocks saved? */ - if (prealloc_len) { - err = udf_add_aext(inode, last_pos, &prealloc_loc, - prealloc_len, 1); - if (err) - return err; - last_ext->extLocation = prealloc_loc; - last_ext->extLength = prealloc_len; - count++; - } - /* last_pos should point to the last written extent... */ if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT) last_pos->offset -= sizeof(struct short_ad); @@ -594,19 +579,28 @@ out: return -EIO; return count; +out_err: + /* Remove extents we've created so far */ + udf_clear_extent_cache(inode); + udf_truncate_extents(inode); + return err; } /* Extend the final block of the file to final_block_len bytes */ static void udf_do_extend_final_block(struct inode *inode, struct extent_position *last_pos, struct kernel_long_ad *last_ext, - uint32_t final_block_len) + uint32_t new_elen) { - struct super_block *sb = inode->i_sb; uint32_t added_bytes; - added_bytes = final_block_len - - (last_ext->extLength & (sb->s_blocksize - 1)); + /* + * Extent already large enough? It may be already rounded up to block + * size... + */ + if (new_elen <= (last_ext->extLength & UDF_EXTENT_LENGTH_MASK)) + return; + added_bytes = new_elen - (last_ext->extLength & UDF_EXTENT_LENGTH_MASK); last_ext->extLength += added_bytes; UDF_I(inode)->i_lenExtents += added_bytes; @@ -623,12 +617,12 @@ static int udf_extend_file(struct inode *inode, loff_t newsize) int8_t etype; struct super_block *sb = inode->i_sb; sector_t first_block = newsize >> sb->s_blocksize_bits, offset; - unsigned long partial_final_block; + loff_t new_elen; int adsize; struct udf_inode_info *iinfo = UDF_I(inode); struct kernel_long_ad extent; int err = 0; - int within_final_block; + bool within_last_ext; if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT) adsize = sizeof(struct short_ad); @@ -637,8 +631,17 @@ static int udf_extend_file(struct inode *inode, loff_t newsize) else BUG(); + /* + * When creating hole in file, just don't bother with preserving + * preallocation. It likely won't be very useful anyway. + */ + udf_discard_prealloc(inode); + etype = inode_bmap(inode, first_block, &epos, &eloc, &elen, &offset); - within_final_block = (etype != -1); + within_last_ext = (etype != -1); + /* We don't expect extents past EOF... */ + WARN_ON_ONCE(within_last_ext && + elen > ((loff_t)offset + 1) << inode->i_blkbits); if ((!epos.bh && epos.offset == udf_file_entry_alloc_offset(inode)) || (epos.bh && epos.offset == sizeof(struct allocExtDesc))) { @@ -654,19 +657,17 @@ static int udf_extend_file(struct inode *inode, loff_t newsize) extent.extLength |= etype << 30; } - partial_final_block = newsize & (sb->s_blocksize - 1); + new_elen = ((loff_t)offset << inode->i_blkbits) | + (newsize & (sb->s_blocksize - 1)); /* File has extent covering the new size (could happen when extending * inside a block)? */ - if (within_final_block) { + if (within_last_ext) { /* Extending file within the last file block */ - udf_do_extend_final_block(inode, &epos, &extent, - partial_final_block); + udf_do_extend_final_block(inode, &epos, &extent, new_elen); } else { - loff_t add = ((loff_t)offset << sb->s_blocksize_bits) | - partial_final_block; - err = udf_do_extend_file(inode, &epos, &extent, add); + err = udf_do_extend_file(inode, &epos, &extent, new_elen); } if (err < 0) @@ -688,7 +689,7 @@ static sector_t inode_getblk(struct inode *inode, sector_t block, struct kernel_lb_addr eloc, tmpeloc; int c = 1; loff_t lbcount = 0, b_off = 0; - udf_pblk_t newblocknum, newblock; + udf_pblk_t newblocknum, newblock = 0; sector_t offset = 0; int8_t etype; struct udf_inode_info *iinfo = UDF_I(inode); @@ -767,10 +768,11 @@ static sector_t inode_getblk(struct inode *inode, sector_t block, goto out_free; } - /* Are we beyond EOF? */ + /* Are we beyond EOF and preallocated extent? */ if (etype == -1) { int ret; loff_t hole_len; + isBeyondEOF = true; if (count) { if (c) @@ -790,25 +792,22 @@ static sector_t inode_getblk(struct inode *inode, sector_t block, ret = udf_do_extend_file(inode, &prev_epos, laarr, hole_len); if (ret < 0) { *err = ret; - newblock = 0; goto out_free; } c = 0; offset = 0; count += ret; - /* We are not covered by a preallocated extent? */ - if ((laarr[0].extLength & UDF_EXTENT_FLAG_MASK) != - EXT_NOT_RECORDED_ALLOCATED) { - /* Is there any real extent? - otherwise we overwrite - * the fake one... */ - if (count) - c = !c; - laarr[c].extLength = EXT_NOT_RECORDED_NOT_ALLOCATED | - inode->i_sb->s_blocksize; - memset(&laarr[c].extLocation, 0x00, - sizeof(struct kernel_lb_addr)); - count++; - } + /* + * Is there any real extent? - otherwise we overwrite the fake + * one... + */ + if (count) + c = !c; + laarr[c].extLength = EXT_NOT_RECORDED_NOT_ALLOCATED | + inode->i_sb->s_blocksize; + memset(&laarr[c].extLocation, 0x00, + sizeof(struct kernel_lb_addr)); + count++; endnum = c + 1; lastblock = 1; } else { @@ -855,7 +854,6 @@ static sector_t inode_getblk(struct inode *inode, sector_t block, goal, err); if (!newblocknum) { *err = -ENOSPC; - newblock = 0; goto out_free; } if (isBeyondEOF) @@ -881,7 +879,9 @@ static sector_t inode_getblk(struct inode *inode, sector_t block, /* write back the new extents, inserting new extents if the new number * of extents is greater than the old number, and deleting extents if * the new number of extents is less than the old number */ - udf_update_extents(inode, laarr, startnum, endnum, &prev_epos); + *err = udf_update_extents(inode, laarr, startnum, endnum, &prev_epos); + if (*err < 0) + goto out_free; newblock = udf_get_pblock(inode->i_sb, newblocknum, iinfo->i_location.partitionReferenceNum, 0); @@ -1085,23 +1085,8 @@ static void udf_merge_extents(struct inode *inode, struct kernel_long_ad *laarr, blocksize - 1) >> blocksize_bits)))) { if (((li->extLength & UDF_EXTENT_LENGTH_MASK) + - (lip1->extLength & UDF_EXTENT_LENGTH_MASK) + - blocksize - 1) & ~UDF_EXTENT_LENGTH_MASK) { - lip1->extLength = (lip1->extLength - - (li->extLength & - UDF_EXTENT_LENGTH_MASK) + - UDF_EXTENT_LENGTH_MASK) & - ~(blocksize - 1); - li->extLength = (li->extLength & - UDF_EXTENT_FLAG_MASK) + - (UDF_EXTENT_LENGTH_MASK + 1) - - blocksize; - lip1->extLocation.logicalBlockNum = - li->extLocation.logicalBlockNum + - ((li->extLength & - UDF_EXTENT_LENGTH_MASK) >> - blocksize_bits); - } else { + (lip1->extLength & UDF_EXTENT_LENGTH_MASK) + + blocksize - 1) <= UDF_EXTENT_LENGTH_MASK) { li->extLength = lip1->extLength + (((li->extLength & UDF_EXTENT_LENGTH_MASK) + @@ -1164,21 +1149,30 @@ static void udf_merge_extents(struct inode *inode, struct kernel_long_ad *laarr, } } -static void udf_update_extents(struct inode *inode, struct kernel_long_ad *laarr, - int startnum, int endnum, - struct extent_position *epos) +static int udf_update_extents(struct inode *inode, struct kernel_long_ad *laarr, + int startnum, int endnum, + struct extent_position *epos) { int start = 0, i; struct kernel_lb_addr tmploc; uint32_t tmplen; + int err; if (startnum > endnum) { for (i = 0; i < (startnum - endnum); i++) udf_delete_aext(inode, *epos); } else if (startnum < endnum) { for (i = 0; i < (endnum - startnum); i++) { - udf_insert_aext(inode, *epos, laarr[i].extLocation, - laarr[i].extLength); + err = udf_insert_aext(inode, *epos, + laarr[i].extLocation, + laarr[i].extLength); + /* + * If we fail here, we are likely corrupting the extent + * list and leaking blocks. At least stop early to + * limit the damage. + */ + if (err < 0) + return err; udf_next_aext(inode, epos, &laarr[i].extLocation, &laarr[i].extLength, 1); start++; @@ -1190,6 +1184,7 @@ static void udf_update_extents(struct inode *inode, struct kernel_long_ad *laarr udf_write_aext(inode, epos, &laarr[i].extLocation, laarr[i].extLength, 1); } + return 0; } struct buffer_head *udf_bread(struct inode *inode, udf_pblk_t block, @@ -1254,7 +1249,7 @@ set_size: if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { down_write(&iinfo->i_data_sem); udf_clear_extent_cache(inode); - memset(iinfo->i_ext.i_data + iinfo->i_lenEAttr + newsize, + memset(iinfo->i_data + iinfo->i_lenEAttr + newsize, 0x00, bsize - newsize - udf_file_entry_alloc_offset(inode)); iinfo->i_lenAlloc = newsize; @@ -1390,6 +1385,7 @@ reread: ret = -EIO; goto out; } + iinfo->i_hidden = hidden_inode; iinfo->i_unique = 0; iinfo->i_lenEAttr = 0; iinfo->i_lenExtents = 0; @@ -1403,7 +1399,7 @@ reread: sizeof(struct extendedFileEntry)); if (ret) goto out; - memcpy(iinfo->i_ext.i_data, + memcpy(iinfo->i_data, bh->b_data + sizeof(struct extendedFileEntry), bs - sizeof(struct extendedFileEntry)); } else if (fe->descTag.tagIdent == cpu_to_le16(TAG_IDENT_FE)) { @@ -1412,7 +1408,7 @@ reread: ret = udf_alloc_i_data(inode, bs - sizeof(struct fileEntry)); if (ret) goto out; - memcpy(iinfo->i_ext.i_data, + memcpy(iinfo->i_data, bh->b_data + sizeof(struct fileEntry), bs - sizeof(struct fileEntry)); } else if (fe->descTag.tagIdent == cpu_to_le16(TAG_IDENT_USE)) { @@ -1425,7 +1421,7 @@ reread: sizeof(struct unallocSpaceEntry)); if (ret) goto out; - memcpy(iinfo->i_ext.i_data, + memcpy(iinfo->i_data, bh->b_data + sizeof(struct unallocSpaceEntry), bs - sizeof(struct unallocSpaceEntry)); return 0; @@ -1483,6 +1479,8 @@ reread: iinfo->i_lenEAttr = le32_to_cpu(fe->lengthExtendedAttr); iinfo->i_lenAlloc = le32_to_cpu(fe->lengthAllocDescs); iinfo->i_checkpoint = le32_to_cpu(fe->checkpoint); + iinfo->i_streamdir = 0; + iinfo->i_lenStreams = 0; } else { inode->i_blocks = le64_to_cpu(efe->logicalBlocksRecorded) << (inode->i_sb->s_blocksize_bits - 9); @@ -1496,6 +1494,16 @@ reread: iinfo->i_lenEAttr = le32_to_cpu(efe->lengthExtendedAttr); iinfo->i_lenAlloc = le32_to_cpu(efe->lengthAllocDescs); iinfo->i_checkpoint = le32_to_cpu(efe->checkpoint); + + /* Named streams */ + iinfo->i_streamdir = (efe->streamDirectoryICB.extLength != 0); + iinfo->i_locStreamdir = + lelb_to_cpu(efe->streamDirectoryICB.extLocation); + iinfo->i_lenStreams = le64_to_cpu(efe->objectSize); + if (iinfo->i_lenStreams >= inode->i_size) + iinfo->i_lenStreams -= inode->i_size; + else + iinfo->i_lenStreams = 0; } inode->i_generation = iinfo->i_unique; @@ -1592,8 +1600,8 @@ out: static int udf_alloc_i_data(struct inode *inode, size_t size) { struct udf_inode_info *iinfo = UDF_I(inode); - iinfo->i_ext.i_data = kmalloc(size, GFP_KERNEL); - if (!iinfo->i_ext.i_data) + iinfo->i_data = kmalloc(size, GFP_KERNEL); + if (!iinfo->i_data) return -ENOMEM; return 0; } @@ -1667,7 +1675,7 @@ static int udf_update_inode(struct inode *inode, int do_sync) use->lengthAllocDescs = cpu_to_le32(iinfo->i_lenAlloc); memcpy(bh->b_data + sizeof(struct unallocSpaceEntry), - iinfo->i_ext.i_data, inode->i_sb->s_blocksize - + iinfo->i_data, inode->i_sb->s_blocksize - sizeof(struct unallocSpaceEntry)); use->descTag.tagIdent = cpu_to_le16(TAG_IDENT_USE); crclen = sizeof(struct unallocSpaceEntry); @@ -1697,8 +1705,12 @@ static int udf_update_inode(struct inode *inode, int do_sync) if (S_ISDIR(inode->i_mode) && inode->i_nlink > 0) fe->fileLinkCount = cpu_to_le16(inode->i_nlink - 1); - else - fe->fileLinkCount = cpu_to_le16(inode->i_nlink); + else { + if (iinfo->i_hidden) + fe->fileLinkCount = cpu_to_le16(0); + else + fe->fileLinkCount = cpu_to_le16(inode->i_nlink); + } fe->informationLength = cpu_to_le64(inode->i_size); @@ -1736,7 +1748,7 @@ static int udf_update_inode(struct inode *inode, int do_sync) if (iinfo->i_efe == 0) { memcpy(bh->b_data + sizeof(struct fileEntry), - iinfo->i_ext.i_data, + iinfo->i_data, inode->i_sb->s_blocksize - sizeof(struct fileEntry)); fe->logicalBlocksRecorded = cpu_to_le64(lb_recorded); @@ -1755,12 +1767,22 @@ static int udf_update_inode(struct inode *inode, int do_sync) crclen = sizeof(struct fileEntry); } else { memcpy(bh->b_data + sizeof(struct extendedFileEntry), - iinfo->i_ext.i_data, + iinfo->i_data, inode->i_sb->s_blocksize - sizeof(struct extendedFileEntry)); - efe->objectSize = cpu_to_le64(inode->i_size); + efe->objectSize = + cpu_to_le64(inode->i_size + iinfo->i_lenStreams); efe->logicalBlocksRecorded = cpu_to_le64(lb_recorded); + if (iinfo->i_streamdir) { + struct long_ad *icb_lad = &efe->streamDirectoryICB; + + icb_lad->extLocation = + cpu_to_lelb(iinfo->i_locStreamdir); + icb_lad->extLength = + cpu_to_le32(inode->i_sb->s_blocksize); + } + udf_adjust_time(iinfo, inode->i_atime); udf_adjust_time(iinfo, inode->i_mtime); udf_adjust_time(iinfo, inode->i_ctime); @@ -1859,8 +1881,13 @@ struct inode *__udf_iget(struct super_block *sb, struct kernel_lb_addr *ino, if (!inode) return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) + if (!(inode->i_state & I_NEW)) { + if (UDF_I(inode)->i_hidden != hidden_inode) { + iput(inode); + return ERR_PTR(-EFSCORRUPTED); + } return inode; + } memcpy(&UDF_I(inode)->i_location, ino, sizeof(struct kernel_lb_addr)); err = udf_read_inode(inode, hidden_inode); @@ -2041,7 +2068,7 @@ void udf_write_aext(struct inode *inode, struct extent_position *epos, struct udf_inode_info *iinfo = UDF_I(inode); if (!epos->bh) - ptr = iinfo->i_ext.i_data + epos->offset - + ptr = iinfo->i_data + epos->offset - udf_file_entry_alloc_offset(inode) + iinfo->i_lenEAttr; else @@ -2133,7 +2160,7 @@ int8_t udf_current_aext(struct inode *inode, struct extent_position *epos, if (!epos->bh) { if (!epos->offset) epos->offset = udf_file_entry_alloc_offset(inode); - ptr = iinfo->i_ext.i_data + epos->offset - + ptr = iinfo->i_data + epos->offset - udf_file_entry_alloc_offset(inode) + iinfo->i_lenEAttr; alen = udf_file_entry_alloc_offset(inode) + @@ -2174,12 +2201,13 @@ int8_t udf_current_aext(struct inode *inode, struct extent_position *epos, return etype; } -static int8_t udf_insert_aext(struct inode *inode, struct extent_position epos, - struct kernel_lb_addr neloc, uint32_t nelen) +static int udf_insert_aext(struct inode *inode, struct extent_position epos, + struct kernel_lb_addr neloc, uint32_t nelen) { struct kernel_lb_addr oeloc; uint32_t oelen; int8_t etype; + int err; if (epos.bh) get_bh(epos.bh); @@ -2189,10 +2217,10 @@ static int8_t udf_insert_aext(struct inode *inode, struct extent_position epos, neloc = oeloc; nelen = (etype << 30) | oelen; } - udf_add_aext(inode, &epos, &neloc, nelen, 1); + err = udf_add_aext(inode, &epos, &neloc, nelen, 1); brelse(epos.bh); - return (nelen >> 30); + return err; } int8_t udf_delete_aext(struct inode *inode, struct extent_position epos) diff --git a/fs/udf/misc.c b/fs/udf/misc.c index 401e64cde1be..1614d308d0f0 100644 --- a/fs/udf/misc.c +++ b/fs/udf/misc.c @@ -52,9 +52,9 @@ struct genericFormat *udf_add_extendedattr(struct inode *inode, uint32_t size, uint16_t crclen; struct udf_inode_info *iinfo = UDF_I(inode); - ea = iinfo->i_ext.i_data; + ea = iinfo->i_data; if (iinfo->i_lenEAttr) { - ad = iinfo->i_ext.i_data + iinfo->i_lenEAttr; + ad = iinfo->i_data + iinfo->i_lenEAttr; } else { ad = ea; size += sizeof(struct extendedAttrHeaderDesc); @@ -153,7 +153,7 @@ struct genericFormat *udf_get_extendedattr(struct inode *inode, uint32_t type, uint32_t offset; struct udf_inode_info *iinfo = UDF_I(inode); - ea = iinfo->i_ext.i_data; + ea = iinfo->i_data; if (iinfo->i_lenEAttr) { struct extendedAttrHeaderDesc *eahd; @@ -173,13 +173,22 @@ struct genericFormat *udf_get_extendedattr(struct inode *inode, uint32_t type, else offset = le32_to_cpu(eahd->appAttrLocation); - while (offset < iinfo->i_lenEAttr) { + while (offset + sizeof(*gaf) < iinfo->i_lenEAttr) { + uint32_t attrLength; + gaf = (struct genericFormat *)&ea[offset]; + attrLength = le32_to_cpu(gaf->attrLength); + + /* Detect undersized elements and buffer overflows */ + if ((attrLength < sizeof(*gaf)) || + (attrLength > (iinfo->i_lenEAttr - offset))) + break; + if (le32_to_cpu(gaf->attrType) == type && gaf->attrSubtype == subtype) return gaf; else - offset += le32_to_cpu(gaf->attrLength); + offset += attrLength; } } diff --git a/fs/udf/namei.c b/fs/udf/namei.c index 58cc2414992b..05dd1f45ba90 100644 --- a/fs/udf/namei.c +++ b/fs/udf/namei.c @@ -30,6 +30,7 @@ #include <linux/sched.h> #include <linux/crc-itu-t.h> #include <linux/exportfs.h> +#include <linux/iversion.h> static inline int udf_match(int len1, const unsigned char *name1, int len2, const unsigned char *name2) @@ -135,6 +136,8 @@ int udf_write_fi(struct inode *inode, struct fileIdentDesc *cfi, mark_buffer_dirty_inode(fibh->ebh, inode); mark_buffer_dirty_inode(fibh->sbh, inode); } + inode_inc_iversion(inode); + return 0; } @@ -238,7 +241,7 @@ static struct fileIdentDesc *udf_find_entry(struct inode *dir, poffset - lfi); else { if (!copy_name) { - copy_name = kmalloc(UDF_NAME_LEN, + copy_name = kmalloc(UDF_NAME_LEN_CS0, GFP_NOFS); if (!copy_name) { fi = ERR_PTR(-ENOMEM); @@ -475,8 +478,7 @@ add: if (dinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { block = dinfo->i_location.logicalBlockNum; fi = (struct fileIdentDesc *) - (dinfo->i_ext.i_data + - fibh->soffset - + (dinfo->i_data + fibh->soffset - udf_ext0_offset(dir) + dinfo->i_lenEAttr); } else { @@ -948,6 +950,10 @@ static int udf_symlink(struct inode *dir, struct dentry *dentry, iinfo->i_location.partitionReferenceNum, 0); epos.bh = udf_tgetblk(sb, block); + if (unlikely(!epos.bh)) { + err = -ENOMEM; + goto out_no_entry; + } lock_buffer(epos.bh); memset(epos.bh->b_data, 0x00, bsize); set_buffer_uptodate(epos.bh); @@ -955,7 +961,7 @@ static int udf_symlink(struct inode *dir, struct dentry *dentry, mark_buffer_dirty_inode(epos.bh, inode); ea = epos.bh->b_data + udf_ext0_offset(inode); } else - ea = iinfo->i_ext.i_data + iinfo->i_lenEAttr; + ea = iinfo->i_data + iinfo->i_lenEAttr; eoffset = sb->s_blocksize - udf_ext0_offset(inode); pc = (struct pathComponent *)ea; @@ -1099,8 +1105,9 @@ static int udf_rename(struct inode *old_dir, struct dentry *old_dentry, return -EINVAL; ofi = udf_find_entry(old_dir, &old_dentry->d_name, &ofibh, &ocfi); - if (IS_ERR(ofi)) { - retval = PTR_ERR(ofi); + if (!ofi || IS_ERR(ofi)) { + if (IS_ERR(ofi)) + retval = PTR_ERR(ofi); goto end_rename; } @@ -1109,8 +1116,7 @@ static int udf_rename(struct inode *old_dir, struct dentry *old_dentry, brelse(ofibh.sbh); tloc = lelb_to_cpu(ocfi.icb.extLocation); - if (!ofi || udf_get_lb_pblock(old_dir->i_sb, &tloc, 0) - != old_inode->i_ino) + if (udf_get_lb_pblock(old_dir->i_sb, &tloc, 0) != old_inode->i_ino) goto end_rename; nfi = udf_find_entry(new_dir, &new_dentry->d_name, &nfibh, &ncfi); @@ -1135,7 +1141,7 @@ static int udf_rename(struct inode *old_dir, struct dentry *old_dentry, retval = -EIO; if (old_iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { dir_fi = udf_get_fileident( - old_iinfo->i_ext.i_data - + old_iinfo->i_data - (old_iinfo->i_efe ? sizeof(struct extendedFileEntry) : sizeof(struct fileEntry)), diff --git a/fs/udf/partition.c b/fs/udf/partition.c index 090baff83990..4cbf40575965 100644 --- a/fs/udf/partition.c +++ b/fs/udf/partition.c @@ -65,7 +65,7 @@ uint32_t udf_get_pblock_virt15(struct super_block *sb, uint32_t block, } if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { - loc = le32_to_cpu(((__le32 *)(iinfo->i_ext.i_data + + loc = le32_to_cpu(((__le32 *)(iinfo->i_data + vdata->s_start_offset))[block]); goto translate; } diff --git a/fs/udf/super.c b/fs/udf/super.c index 1676a175cd7a..bce48a07790c 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -57,6 +57,7 @@ #include <linux/crc-itu-t.h> #include <linux/log2.h> #include <asm/byteorder.h> +#include <linux/iversion.h> #include "udf_sb.h" #include "udf_i.h" @@ -112,16 +113,10 @@ struct logicalVolIntegrityDescImpUse *udf_sb_lvidiu(struct super_block *sb) return NULL; lvid = (struct logicalVolIntegrityDesc *)UDF_SB(sb)->s_lvid_bh->b_data; partnum = le32_to_cpu(lvid->numOfPartitions); - if ((sb->s_blocksize - sizeof(struct logicalVolIntegrityDescImpUse) - - offsetof(struct logicalVolIntegrityDesc, impUse)) / - (2 * sizeof(uint32_t)) < partnum) { - udf_err(sb, "Logical volume integrity descriptor corrupted " - "(numOfPartitions = %u)!\n", partnum); - return NULL; - } /* The offset is to skip freeSpaceTable and sizeTable arrays */ offset = partnum * 2 * sizeof(uint32_t); - return (struct logicalVolIntegrityDescImpUse *)&(lvid->impUse[offset]); + return (struct logicalVolIntegrityDescImpUse *) + (((uint8_t *)(lvid + 1)) + offset); } /* UDF filesystem type */ @@ -151,12 +146,16 @@ static struct inode *udf_alloc_inode(struct super_block *sb) ei->i_unique = 0; ei->i_lenExtents = 0; + ei->i_lenStreams = 0; ei->i_next_alloc_block = 0; ei->i_next_alloc_goal = 0; ei->i_strat4096 = 0; + ei->i_streamdir = 0; + ei->i_hidden = 0; init_rwsem(&ei->i_data_sem); ei->cached_extent.lstart = -1; spin_lock_init(&ei->i_extent_cache_lock); + inode_set_iversion(&ei->vfs_inode, 1); return &ei->vfs_inode; } @@ -176,7 +175,7 @@ static void init_once(void *foo) { struct udf_inode_info *ei = (struct udf_inode_info *)foo; - ei->i_ext.i_data = NULL; + ei->i_data = NULL; inode_init_once(&ei->vfs_inode); } @@ -576,6 +575,11 @@ static int udf_parse_options(char *options, struct udf_options *uopt, if (!remount) { if (uopt->nls_map) unload_nls(uopt->nls_map); + /* + * load_nls() failure is handled later in + * udf_fill_super() after all options are + * parsed. + */ uopt->nls_map = load_nls(args[0].from); uopt->flags |= (1 << UDF_FLAG_NLS_MAP); } @@ -1204,7 +1208,7 @@ static int udf_load_vat(struct super_block *sb, int p_index, int type1_index) vat20 = (struct virtualAllocationTable20 *)bh->b_data; } else { vat20 = (struct virtualAllocationTable20 *) - vati->i_ext.i_data; + vati->i_data; } map->s_type_specific.s_virtual.s_start_offset = @@ -1349,6 +1353,12 @@ static int udf_load_sparable_map(struct super_block *sb, (int)spm->numSparingTables); return -EIO; } + if (le32_to_cpu(spm->sizeSparingTable) > sb->s_blocksize) { + udf_err(sb, "error loading logical volume descriptor: " + "Too big sparing table size (%u)\n", + le32_to_cpu(spm->sizeSparingTable)); + return -EIO; + } for (i = 0; i < spm->numSparingTables; i++) { loc = le32_to_cpu(spm->locSparingTable[i]); @@ -1523,6 +1533,7 @@ static void udf_load_logicalvolint(struct super_block *sb, struct kernel_extent_ struct udf_sb_info *sbi = UDF_SB(sb); struct logicalVolIntegrityDesc *lvid; int indirections = 0; + u32 parts, impuselen; while (++indirections <= UDF_MAX_LVID_NESTING) { final_bh = NULL; @@ -1549,15 +1560,27 @@ static void udf_load_logicalvolint(struct super_block *sb, struct kernel_extent_ lvid = (struct logicalVolIntegrityDesc *)final_bh->b_data; if (lvid->nextIntegrityExt.extLength == 0) - return; + goto check; loc = leea_to_cpu(lvid->nextIntegrityExt); } udf_warn(sb, "Too many LVID indirections (max %u), ignoring.\n", UDF_MAX_LVID_NESTING); +out_err: brelse(sbi->s_lvid_bh); sbi->s_lvid_bh = NULL; + return; +check: + parts = le32_to_cpu(lvid->numOfPartitions); + impuselen = le32_to_cpu(lvid->lengthOfImpUse); + if (parts >= sb->s_blocksize || impuselen >= sb->s_blocksize || + sizeof(struct logicalVolIntegrityDesc) + impuselen + + 2 * parts * sizeof(u32) > sb->s_blocksize) { + udf_warn(sb, "Corrupted LVID (parts=%u, impuselen=%u), " + "ignoring.\n", parts, impuselen); + goto out_err; + } } /* @@ -1679,7 +1702,8 @@ static noinline int udf_process_sequence( "Pointers (max %u supported)\n", UDF_MAX_TD_NESTING); brelse(bh); - return -EIO; + ret = -EIO; + goto out; } vdp = (struct volDescPtr *)bh->b_data; @@ -1699,7 +1723,8 @@ static noinline int udf_process_sequence( curr = get_volume_descriptor_record(ident, bh, &data); if (IS_ERR(curr)) { brelse(bh); - return PTR_ERR(curr); + ret = PTR_ERR(curr); + goto out; } /* Descriptor we don't care about? */ if (!curr) @@ -1721,28 +1746,31 @@ static noinline int udf_process_sequence( */ if (!data.vds[VDS_POS_PRIMARY_VOL_DESC].block) { udf_err(sb, "Primary Volume Descriptor not found!\n"); - return -EAGAIN; + ret = -EAGAIN; + goto out; } ret = udf_load_pvoldesc(sb, data.vds[VDS_POS_PRIMARY_VOL_DESC].block); if (ret < 0) - return ret; + goto out; if (data.vds[VDS_POS_LOGICAL_VOL_DESC].block) { ret = udf_load_logicalvol(sb, data.vds[VDS_POS_LOGICAL_VOL_DESC].block, fileset); if (ret < 0) - return ret; + goto out; } /* Now handle prevailing Partition Descriptors */ for (i = 0; i < data.num_part_descs; i++) { ret = udf_load_partdesc(sb, data.part_descs_loc[i].rec.block); if (ret < 0) - return ret; + goto out; } - - return 0; + ret = 0; +out: + kfree(data.part_descs_loc); + return ret; } /* diff --git a/fs/udf/symlink.c b/fs/udf/symlink.c index 6023c97c6da2..aef3e4d9014d 100644 --- a/fs/udf/symlink.c +++ b/fs/udf/symlink.c @@ -122,7 +122,7 @@ static int udf_symlink_filler(struct file *file, struct page *page) down_read(&iinfo->i_data_sem); if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { - symlink = iinfo->i_ext.i_data + iinfo->i_lenEAttr; + symlink = iinfo->i_data + iinfo->i_lenEAttr; } else { bh = sb_bread(inode->i_sb, pos); diff --git a/fs/udf/truncate.c b/fs/udf/truncate.c index 94220ba85628..b0c71edc83f7 100644 --- a/fs/udf/truncate.c +++ b/fs/udf/truncate.c @@ -120,60 +120,42 @@ void udf_truncate_tail_extent(struct inode *inode) void udf_discard_prealloc(struct inode *inode) { - struct extent_position epos = { NULL, 0, {0, 0} }; + struct extent_position epos = {}; + struct extent_position prev_epos = {}; struct kernel_lb_addr eloc; uint32_t elen; uint64_t lbcount = 0; int8_t etype = -1, netype; - int adsize; struct udf_inode_info *iinfo = UDF_I(inode); + int bsize = 1 << inode->i_blkbits; if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB || - inode->i_size == iinfo->i_lenExtents) + ALIGN(inode->i_size, bsize) == ALIGN(iinfo->i_lenExtents, bsize)) return; - if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT) - adsize = sizeof(struct short_ad); - else if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_LONG) - adsize = sizeof(struct long_ad); - else - adsize = 0; - epos.block = iinfo->i_location; /* Find the last extent in the file */ - while ((netype = udf_next_aext(inode, &epos, &eloc, &elen, 1)) != -1) { - etype = netype; + while ((netype = udf_next_aext(inode, &epos, &eloc, &elen, 0)) != -1) { + brelse(prev_epos.bh); + prev_epos = epos; + if (prev_epos.bh) + get_bh(prev_epos.bh); + + etype = udf_next_aext(inode, &epos, &eloc, &elen, 1); lbcount += elen; } if (etype == (EXT_NOT_RECORDED_ALLOCATED >> 30)) { - epos.offset -= adsize; lbcount -= elen; - extent_trunc(inode, &epos, &eloc, etype, elen, 0); - if (!epos.bh) { - iinfo->i_lenAlloc = - epos.offset - - udf_file_entry_alloc_offset(inode); - mark_inode_dirty(inode); - } else { - struct allocExtDesc *aed = - (struct allocExtDesc *)(epos.bh->b_data); - aed->lengthAllocDescs = - cpu_to_le32(epos.offset - - sizeof(struct allocExtDesc)); - if (!UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_STRICT) || - UDF_SB(inode->i_sb)->s_udfrev >= 0x0201) - udf_update_tag(epos.bh->b_data, epos.offset); - else - udf_update_tag(epos.bh->b_data, - sizeof(struct allocExtDesc)); - mark_buffer_dirty_inode(epos.bh, inode); - } + udf_delete_aext(inode, prev_epos); + udf_free_blocks(inode->i_sb, inode, &eloc, 0, + DIV_ROUND_UP(elen, 1 << inode->i_blkbits)); } /* This inode entry is in-memory only and thus we don't have to mark * the inode dirty */ iinfo->i_lenExtents = lbcount; brelse(epos.bh); + brelse(prev_epos.bh); } static void udf_update_alloc_ext_desc(struct inode *inode, diff --git a/fs/udf/udf_i.h b/fs/udf/udf_i.h index 2ef0e212f08a..b77bf713a1b6 100644 --- a/fs/udf/udf_i.h +++ b/fs/udf/udf_i.h @@ -42,12 +42,12 @@ struct udf_inode_info { unsigned i_efe : 1; /* extendedFileEntry */ unsigned i_use : 1; /* unallocSpaceEntry */ unsigned i_strat4096 : 1; - unsigned reserved : 26; - union { - struct short_ad *i_sad; - struct long_ad *i_lad; - __u8 *i_data; - } i_ext; + unsigned i_streamdir : 1; + unsigned i_hidden : 1; /* hidden system inode */ + unsigned reserved : 24; + __u8 *i_data; + struct kernel_lb_addr i_locStreamdir; + __u64 i_lenStreams; struct rw_semaphore i_data_sem; struct udf_ext_cache cached_extent; /* Spinlock for protecting extent cache */ diff --git a/fs/udf/udf_sb.h b/fs/udf/udf_sb.h index d12e507e9eb2..aa58173b468f 100644 --- a/fs/udf/udf_sb.h +++ b/fs/udf/udf_sb.h @@ -57,6 +57,8 @@ #define MF_DUPLICATE_MD 0x01 #define MF_MIRROR_FE_LOADED 0x02 +#define EFSCORRUPTED EUCLEAN + struct udf_meta_data { __u32 s_meta_file_loc; __u32 s_mirror_file_loc; diff --git a/fs/udf/unicode.c b/fs/udf/unicode.c index 5fcfa96463eb..85521d6b0237 100644 --- a/fs/udf/unicode.c +++ b/fs/udf/unicode.c @@ -247,7 +247,7 @@ static int udf_name_from_CS0(struct super_block *sb, } if (translate) { - if (str_o_len <= 2 && str_o[0] == '.' && + if (str_o_len > 0 && str_o_len <= 2 && str_o[0] == '.' && (str_o_len == 1 || str_o[1] == '.')) needsCRC = 1; if (needsCRC) { diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index d269d1139f7f..23c8efc967af 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -32,11 +32,6 @@ static struct kmem_cache *userfaultfd_ctx_cachep __read_mostly; -enum userfaultfd_state { - UFFD_STATE_WAIT_API, - UFFD_STATE_RUNNING, -}; - /* * Start with fault_pending_wqh and fault_wqh so they're more likely * to be in the same cacheline. @@ -68,8 +63,6 @@ struct userfaultfd_ctx { unsigned int flags; /* features requested from the userspace */ unsigned int features; - /* state machine */ - enum userfaultfd_state state; /* released */ bool released; /* memory mappings are changing because of non-cooperative event */ @@ -103,6 +96,14 @@ struct userfaultfd_wake_range { unsigned long len; }; +/* internal indication that UFFD_API ioctl was successfully executed */ +#define UFFD_FEATURE_INITIALIZED (1u << 31) + +static bool userfaultfd_is_initialized(struct userfaultfd_ctx *ctx) +{ + return ctx->features & UFFD_FEATURE_INITIALIZED; +} + static int userfaultfd_wake_function(wait_queue_entry_t *wq, unsigned mode, int wake_flags, void *key) { @@ -700,7 +701,6 @@ int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs) atomic_set(&ctx->refcount, 1); ctx->flags = octx->flags; - ctx->state = UFFD_STATE_RUNNING; ctx->features = octx->features; ctx->released = false; ctx->mmap_changing = false; @@ -981,38 +981,33 @@ static __poll_t userfaultfd_poll(struct file *file, poll_table *wait) poll_wait(file, &ctx->fd_wqh, wait); - switch (ctx->state) { - case UFFD_STATE_WAIT_API: + if (!userfaultfd_is_initialized(ctx)) return EPOLLERR; - case UFFD_STATE_RUNNING: - /* - * poll() never guarantees that read won't block. - * userfaults can be waken before they're read(). - */ - if (unlikely(!(file->f_flags & O_NONBLOCK))) - return EPOLLERR; - /* - * lockless access to see if there are pending faults - * __pollwait last action is the add_wait_queue but - * the spin_unlock would allow the waitqueue_active to - * pass above the actual list_add inside - * add_wait_queue critical section. So use a full - * memory barrier to serialize the list_add write of - * add_wait_queue() with the waitqueue_active read - * below. - */ - ret = 0; - smp_mb(); - if (waitqueue_active(&ctx->fault_pending_wqh)) - ret = EPOLLIN; - else if (waitqueue_active(&ctx->event_wqh)) - ret = EPOLLIN; - - return ret; - default: - WARN_ON_ONCE(1); + + /* + * poll() never guarantees that read won't block. + * userfaults can be waken before they're read(). + */ + if (unlikely(!(file->f_flags & O_NONBLOCK))) return EPOLLERR; - } + /* + * lockless access to see if there are pending faults + * __pollwait last action is the add_wait_queue but + * the spin_unlock would allow the waitqueue_active to + * pass above the actual list_add inside + * add_wait_queue critical section. So use a full + * memory barrier to serialize the list_add write of + * add_wait_queue() with the waitqueue_active read + * below. + */ + ret = 0; + smp_mb(); + if (waitqueue_active(&ctx->fault_pending_wqh)) + ret = EPOLLIN; + else if (waitqueue_active(&ctx->event_wqh)) + ret = EPOLLIN; + + return ret; } static const struct file_operations userfaultfd_fops; @@ -1206,7 +1201,7 @@ static ssize_t userfaultfd_read(struct file *file, char __user *buf, struct uffd_msg msg; int no_wait = file->f_flags & O_NONBLOCK; - if (ctx->state == UFFD_STATE_WAIT_API) + if (!userfaultfd_is_initialized(ctx)) return -EINVAL; for (;;) { @@ -1808,9 +1803,10 @@ out: static inline unsigned int uffd_ctx_features(__u64 user_features) { /* - * For the current set of features the bits just coincide + * For the current set of features the bits just coincide. Set + * UFFD_FEATURE_INITIALIZED to mark the features as enabled. */ - return (unsigned int)user_features; + return (unsigned int)user_features | UFFD_FEATURE_INITIALIZED; } /* @@ -1823,12 +1819,10 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx, { struct uffdio_api uffdio_api; void __user *buf = (void __user *)arg; + unsigned int ctx_features; int ret; __u64 features; - ret = -EINVAL; - if (ctx->state != UFFD_STATE_WAIT_API) - goto out; ret = -EFAULT; if (copy_from_user(&uffdio_api, buf, sizeof(uffdio_api))) goto out; @@ -1845,9 +1839,13 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx, ret = -EFAULT; if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api))) goto out; - ctx->state = UFFD_STATE_RUNNING; + /* only enable the requested features for this uffd context */ - ctx->features = uffd_ctx_features(features); + ctx_features = uffd_ctx_features(features); + ret = -EINVAL; + if (cmpxchg(&ctx->features, 0, ctx_features) != 0) + goto err_out; + ret = 0; out: return ret; @@ -1864,7 +1862,7 @@ static long userfaultfd_ioctl(struct file *file, unsigned cmd, int ret = -EINVAL; struct userfaultfd_ctx *ctx = file->private_data; - if (cmd != UFFDIO_API && ctx->state == UFFD_STATE_WAIT_API) + if (cmd != UFFDIO_API && !userfaultfd_is_initialized(ctx)) return -EINVAL; switch(cmd) { @@ -1962,7 +1960,6 @@ SYSCALL_DEFINE1(userfaultfd, int, flags) atomic_set(&ctx->refcount, 1); ctx->flags = flags; ctx->features = 0; - ctx->state = UFFD_STATE_WAIT_API; ctx->released = false; ctx->mmap_changing = false; ctx->mm = current->mm; diff --git a/fs/xattr.c b/fs/xattr.c index 470ee0af3200..5c3407e18e15 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -1012,7 +1012,7 @@ static int xattr_list_one(char **buffer, ssize_t *remaining_size, ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs, char *buffer, size_t size) { - bool trusted = capable(CAP_SYS_ADMIN); + bool trusted = ns_capable_noaudit(&init_user_ns, CAP_SYS_ADMIN); struct simple_xattr *xattr; ssize_t remaining_size = size; int err = 0; diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index 1eb7933dac83..b3a9043b0c9e 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -2213,6 +2213,7 @@ xfs_defer_agfl_block( new->xefi_startblock = XFS_AGB_TO_FSB(mp, agno, agbno); new->xefi_blockcount = 1; new->xefi_oinfo = *oinfo; + new->xefi_skip_discard = false; trace_xfs_agfl_free_defer(mp, agno, 0, agbno, 1); diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index f35e1801f1c9..fc9950a505e6 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -4920,20 +4920,25 @@ xfs_bmap_del_extent_real( flags = XFS_ILOG_CORE; if (whichfork == XFS_DATA_FORK && XFS_IS_REALTIME_INODE(ip)) { - xfs_fsblock_t bno; xfs_filblks_t len; xfs_extlen_t mod; - bno = div_u64_rem(del->br_startblock, mp->m_sb.sb_rextsize, - &mod); - ASSERT(mod == 0); len = div_u64_rem(del->br_blockcount, mp->m_sb.sb_rextsize, &mod); ASSERT(mod == 0); - error = xfs_rtfree_extent(tp, bno, (xfs_extlen_t)len); - if (error) - goto done; + if (!(bflags & XFS_BMAPI_REMAP)) { + xfs_fsblock_t bno; + + bno = div_u64_rem(del->br_startblock, + mp->m_sb.sb_rextsize, &mod); + ASSERT(mod == 0); + + error = xfs_rtfree_extent(tp, bno, (xfs_extlen_t)len); + if (error) + goto done; + } + do_fx = 0; nblks = len * mp->m_sb.sb_rextsize; qfield = XFS_TRANS_DQ_RTBCOUNT; diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h index 488dc8860fd7..50242ba3cdb7 100644 --- a/fs/xfs/libxfs/xfs_bmap.h +++ b/fs/xfs/libxfs/xfs_bmap.h @@ -52,9 +52,9 @@ struct xfs_extent_free_item { xfs_fsblock_t xefi_startblock;/* starting fs block number */ xfs_extlen_t xefi_blockcount;/* number of blocks in extent */ + bool xefi_skip_discard; struct list_head xefi_list; struct xfs_owner_info xefi_oinfo; /* extent owner */ - bool xefi_skip_discard; }; #define XFS_BMAP_MAX_NMAP 4 diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c index 245af452840e..ab3e72e702f0 100644 --- a/fs/xfs/libxfs/xfs_rmap.c +++ b/fs/xfs/libxfs/xfs_rmap.c @@ -1387,7 +1387,7 @@ xfs_rmap_convert_shared( * record for our insertion point. This will also give us the record for * start block contiguity tests. */ - error = xfs_rmap_lookup_le_range(cur, bno, owner, offset, flags, + error = xfs_rmap_lookup_le_range(cur, bno, owner, offset, oldext, &PREV, &i); if (error) goto done; diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c index b228c821bae6..fe7323032e78 100644 --- a/fs/xfs/libxfs/xfs_rtbitmap.c +++ b/fs/xfs/libxfs/xfs_rtbitmap.c @@ -1020,7 +1020,6 @@ xfs_rtalloc_query_range( struct xfs_mount *mp = tp->t_mountp; xfs_rtblock_t rtstart; xfs_rtblock_t rtend; - xfs_rtblock_t rem; int is_free; int error = 0; @@ -1029,13 +1028,12 @@ xfs_rtalloc_query_range( if (low_rec->ar_startext >= mp->m_sb.sb_rextents || low_rec->ar_startext == high_rec->ar_startext) return 0; - if (high_rec->ar_startext > mp->m_sb.sb_rextents) - high_rec->ar_startext = mp->m_sb.sb_rextents; + high_rec->ar_startext = min(high_rec->ar_startext, + mp->m_sb.sb_rextents - 1); /* Iterate the bitmap, looking for discrepancies. */ rtstart = low_rec->ar_startext; - rem = high_rec->ar_startext - rtstart; - while (rem) { + while (rtstart <= high_rec->ar_startext) { /* Is the first block free? */ error = xfs_rtcheck_range(mp, tp, rtstart, 1, 1, &rtend, &is_free); @@ -1044,7 +1042,7 @@ xfs_rtalloc_query_range( /* How long does the extent go for? */ error = xfs_rtfind_forw(mp, tp, rtstart, - high_rec->ar_startext - 1, &rtend); + high_rec->ar_startext, &rtend); if (error) break; @@ -1057,7 +1055,6 @@ xfs_rtalloc_query_range( break; } - rem -= rtend - rtstart + 1; rtstart = rtend + 1; } diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c index f84a58e523bc..cf005e18d618 100644 --- a/fs/xfs/scrub/bmap.c +++ b/fs/xfs/scrub/bmap.c @@ -120,6 +120,8 @@ xchk_bmap_get_rmap( if (info->whichfork == XFS_ATTR_FORK) rflags |= XFS_RMAP_ATTR_FORK; + if (irec->br_state == XFS_EXT_UNWRITTEN) + rflags |= XFS_RMAP_UNWRITTEN; /* * CoW staging extents are owned (on disk) by the refcountbt, so @@ -223,13 +225,13 @@ xchk_bmap_xref_rmap( * which doesn't track unwritten state. */ if (owner != XFS_RMAP_OWN_COW && - irec->br_state == XFS_EXT_UNWRITTEN && - !(rmap.rm_flags & XFS_RMAP_UNWRITTEN)) + !!(irec->br_state == XFS_EXT_UNWRITTEN) != + !!(rmap.rm_flags & XFS_RMAP_UNWRITTEN)) xchk_fblock_xref_set_corrupt(info->sc, info->whichfork, irec->br_startoff); - if (info->whichfork == XFS_ATTR_FORK && - !(rmap.rm_flags & XFS_RMAP_ATTR_FORK)) + if (!!(info->whichfork == XFS_ATTR_FORK) != + !!(rmap.rm_flags & XFS_RMAP_ATTR_FORK)) xchk_fblock_xref_set_corrupt(info->sc, info->whichfork, irec->br_startoff); if (rmap.rm_flags & XFS_RMAP_BMBT_BLOCK) diff --git a/fs/xfs/scrub/btree.c b/fs/xfs/scrub/btree.c index 4ae959f7ad2c..c924fe3cdad6 100644 --- a/fs/xfs/scrub/btree.c +++ b/fs/xfs/scrub/btree.c @@ -450,32 +450,41 @@ xchk_btree_check_minrecs( int level, struct xfs_btree_block *block) { - unsigned int numrecs; - int ok_level; - - numrecs = be16_to_cpu(block->bb_numrecs); + struct xfs_btree_cur *cur = bs->cur; + unsigned int root_level = cur->bc_nlevels - 1; + unsigned int numrecs = be16_to_cpu(block->bb_numrecs); /* More records than minrecs means the block is ok. */ - if (numrecs >= bs->cur->bc_ops->get_minrecs(bs->cur, level)) + if (numrecs >= cur->bc_ops->get_minrecs(cur, level)) return; /* - * Certain btree blocks /can/ have fewer than minrecs records. Any - * level greater than or equal to the level of the highest dedicated - * btree block are allowed to violate this constraint. - * - * For a btree rooted in a block, the btree root can have fewer than - * minrecs records. If the btree is rooted in an inode and does not - * store records in the root, the direct children of the root and the - * root itself can have fewer than minrecs records. + * For btrees rooted in the inode, it's possible that the root block + * contents spilled into a regular ondisk block because there wasn't + * enough space in the inode root. The number of records in that + * child block might be less than the standard minrecs, but that's ok + * provided that there's only one direct child of the root. */ - ok_level = bs->cur->bc_nlevels - 1; - if (bs->cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) - ok_level--; - if (level >= ok_level) + if ((cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) && + level == cur->bc_nlevels - 2) { + struct xfs_btree_block *root_block; + struct xfs_buf *root_bp; + int root_maxrecs; + + root_block = xfs_btree_get_block(cur, root_level, &root_bp); + root_maxrecs = cur->bc_ops->get_dmaxrecs(cur, root_level); + if (be16_to_cpu(root_block->bb_numrecs) != 1 || + numrecs <= root_maxrecs) + xchk_btree_set_corrupt(bs->sc, cur, level); return; + } - xchk_btree_set_corrupt(bs->sc, bs->cur, level); + /* + * Otherwise, only the root level is allowed to have fewer than minrecs + * records or keyptrs. + */ + if (level < root_level) + xchk_btree_set_corrupt(bs->sc, cur, level); } /* diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c index e386c9b0b4ab..8d45d60832db 100644 --- a/fs/xfs/scrub/inode.c +++ b/fs/xfs/scrub/inode.c @@ -131,8 +131,7 @@ xchk_inode_flags( goto bad; /* rt flags require rt device */ - if ((flags & (XFS_DIFLAG_REALTIME | XFS_DIFLAG_RTINHERIT)) && - !mp->m_rtdev_targp) + if ((flags & XFS_DIFLAG_REALTIME) && !mp->m_rtdev_targp) goto bad; /* new rt bitmap flag only valid for rbmino */ diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c index e8c82b026083..76e4f16a9fab 100644 --- a/fs/xfs/scrub/refcount.c +++ b/fs/xfs/scrub/refcount.c @@ -180,7 +180,6 @@ xchk_refcountbt_process_rmap_fragments( */ INIT_LIST_HEAD(&worklist); rbno = NULLAGBLOCK; - nr = 1; /* Make sure the fragments actually /are/ in agbno order. */ bno = 0; @@ -194,15 +193,14 @@ xchk_refcountbt_process_rmap_fragments( * Find all the rmaps that start at or before the refc extent, * and put them on the worklist. */ + nr = 0; list_for_each_entry_safe(frag, n, &refchk->fragments, list) { - if (frag->rm.rm_startblock > refchk->bno) - goto done; + if (frag->rm.rm_startblock > refchk->bno || nr > target_nr) + break; bno = frag->rm.rm_startblock + frag->rm.rm_blockcount; if (bno < rbno) rbno = bno; list_move_tail(&frag->list, &worklist); - if (nr == target_nr) - break; nr++; } diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 3e1dd66bd676..734b80a4220c 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -130,7 +130,7 @@ xfs_bmap_rtalloc( * pick an extent that will space things out in the rt area. */ if (ap->eof && ap->offset == 0) { - xfs_rtblock_t uninitialized_var(rtx); /* realtime extent no */ + xfs_rtblock_t rtx; /* realtime extent no */ error = xfs_rtpick_extent(mp, ap->tp, ralen, &rtx); if (error) diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c index 3d76a9e35870..75b57b683d3e 100644 --- a/fs/xfs/xfs_fsmap.c +++ b/fs/xfs/xfs_fsmap.c @@ -259,6 +259,9 @@ xfs_getfsmap_helper( /* Are we just counting mappings? */ if (info->head->fmh_count == 0) { + if (info->head->fmh_entries == UINT_MAX) + return -ECANCELED; + if (rec_daddr > info->next_daddr) info->head->fmh_entries++; diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index cd81d6d9848d..0370ee34b71c 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -2899,7 +2899,6 @@ xfs_rename( * appropriately. */ if (flags & RENAME_WHITEOUT) { - ASSERT(!(flags & (RENAME_NOREPLACE | RENAME_EXCHANGE))); error = xfs_rename_alloc_whiteout(target_dp, &wip); if (error) return error; diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 6ffb53edf1b4..f12308981608 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -701,7 +701,8 @@ xfs_ioc_space( flags |= XFS_PREALLOC_CLEAR; if (bf->l_start > XFS_ISIZE(ip)) { error = xfs_alloc_file_space(ip, XFS_ISIZE(ip), - bf->l_start - XFS_ISIZE(ip), 0); + bf->l_start - XFS_ISIZE(ip), + XFS_BMAPI_PREALLOC); if (error) goto out_unlock; } diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index e427ad097e2e..6011086b51de 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -849,7 +849,7 @@ xfs_setattr_size( ASSERT(xfs_isilocked(ip, XFS_MMAPLOCK_EXCL)); ASSERT(S_ISREG(inode->i_mode)); ASSERT((iattr->ia_valid & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET| - ATTR_MTIME_SET|ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0); + ATTR_MTIME_SET|ATTR_TIMES_SET)) == 0); oldsize = inode->i_size; newsize = iattr->ia_size; @@ -895,6 +895,16 @@ xfs_setattr_size( error = iomap_zero_range(inode, oldsize, newsize - oldsize, &did_zeroing, &xfs_iomap_ops); } else { + /* + * iomap won't detect a dirty page over an unwritten block (or a + * cow block over a hole) and subsequently skips zeroing the + * newly post-EOF portion of the page. Flush the new EOF to + * convert the block before the pagecache truncate. + */ + error = filemap_write_and_wait_range(inode->i_mapping, newsize, + newsize); + if (error) + return error; error = iomap_truncate_page(inode, newsize, &did_zeroing, &xfs_iomap_ops); } diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c index f44c3599527d..1c9bced3e860 100644 --- a/fs/xfs/xfs_pnfs.c +++ b/fs/xfs/xfs_pnfs.c @@ -141,7 +141,7 @@ xfs_fs_map_blocks( goto out_unlock; error = invalidate_inode_pages2(inode->i_mapping); if (WARN_ON_ONCE(error)) - return error; + goto out_unlock; end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + length); offset_fsb = XFS_B_TO_FSBT(mp, offset); diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index 484eb0adcefb..280965fc9bbd 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -245,6 +245,9 @@ xfs_rtallocate_extent_block( end = XFS_BLOCKTOBIT(mp, bbno + 1) - 1; i <= end; i++) { + /* Make sure we don't scan off the end of the rt volume. */ + maxlen = min(mp->m_sb.sb_rextents, i + maxlen) - i; + /* * See if there's a free extent of maxlen starting at i. * If it's not so then next will contain the first non-free. @@ -440,6 +443,14 @@ xfs_rtallocate_extent_near( */ if (bno >= mp->m_sb.sb_rextents) bno = mp->m_sb.sb_rextents - 1; + + /* Make sure we don't run off the end of the rt volume. */ + maxlen = min(mp->m_sb.sb_rextents, bno + maxlen) - bno; + if (maxlen < minlen) { + *rtblock = NULLRTBLOCK; + return 0; + } + /* * Try the exact allocation first. */ @@ -987,10 +998,13 @@ xfs_growfs_rt( xfs_ilock(mp->m_rbmip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, mp->m_rbmip, XFS_ILOCK_EXCL); /* - * Update the bitmap inode's size. + * Update the bitmap inode's size ondisk and incore. We need + * to update the incore size so that inode inactivation won't + * punch what it thinks are "posteof" blocks. */ mp->m_rbmip->i_d.di_size = nsbp->sb_rbmblocks * nsbp->sb_blocksize; + i_size_write(VFS_I(mp->m_rbmip), mp->m_rbmip->i_d.di_size); xfs_trans_log_inode(tp, mp->m_rbmip, XFS_ILOG_CORE); /* * Get the summary inode into the transaction. @@ -998,9 +1012,12 @@ xfs_growfs_rt( xfs_ilock(mp->m_rsumip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, mp->m_rsumip, XFS_ILOCK_EXCL); /* - * Update the summary inode's size. + * Update the summary inode's size. We need to update the + * incore size so that inode inactivation won't punch what it + * thinks are "posteof" blocks. */ mp->m_rsumip->i_d.di_size = nmp->m_rsumsize; + i_size_write(VFS_I(mp->m_rsumip), mp->m_rsumip->i_d.di_size); xfs_trans_log_inode(tp, mp->m_rsumip, XFS_ILOG_CORE); /* * Copy summary data from old to new sizes. diff --git a/fs/xfs/xfs_trans_inode.c b/fs/xfs/xfs_trans_inode.c index ae453dd236a6..6fcdf7e449fe 100644 --- a/fs/xfs/xfs_trans_inode.c +++ b/fs/xfs/xfs_trans_inode.c @@ -99,9 +99,9 @@ xfs_trans_log_inode( * to log the timestamps, or will clear already cleared fields in the * worst case. */ - if (inode->i_state & (I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED)) { + if (inode->i_state & I_DIRTY_TIME) { spin_lock(&inode->i_lock); - inode->i_state &= ~(I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED); + inode->i_state &= ~I_DIRTY_TIME; spin_unlock(&inode->i_lock); } |