diff options
Diffstat (limited to 'fs')
-rw-r--r-- | fs/aio.c | 207 | ||||
-rw-r--r-- | fs/btrfs/extent-tree.c | 3 | ||||
-rw-r--r-- | fs/btrfs/extent_io.c | 8 | ||||
-rw-r--r-- | fs/btrfs/inode.c | 13 | ||||
-rw-r--r-- | fs/btrfs/ioctl.c | 5 | ||||
-rw-r--r-- | fs/btrfs/relocation.c | 9 | ||||
-rw-r--r-- | fs/ceph/file.c | 1 | ||||
-rw-r--r-- | fs/coredump.c | 3 | ||||
-rw-r--r-- | fs/nfs/client.c | 3 | ||||
-rw-r--r-- | fs/nfs/namespace.c | 2 | ||||
-rw-r--r-- | fs/nfs/nfs4session.c | 12 | ||||
-rw-r--r-- | fs/nfs/pnfs.c | 2 | ||||
-rw-r--r-- | fs/nfsd/netns.h | 5 | ||||
-rw-r--r-- | fs/nfsd/nfs4state.c | 38 | ||||
-rw-r--r-- | fs/ntfs/dir.c | 2 | ||||
-rw-r--r-- | fs/ocfs2/dir.c | 2 | ||||
-rw-r--r-- | fs/orangefs/orangefs-debugfs.c | 147 | ||||
-rw-r--r-- | fs/orangefs/orangefs-mod.c | 6 | ||||
-rw-r--r-- | fs/overlayfs/copy_up.c | 2 | ||||
-rw-r--r-- | fs/overlayfs/inode.c | 3 | ||||
-rw-r--r-- | fs/overlayfs/super.c | 15 | ||||
-rw-r--r-- | fs/splice.c | 5 | ||||
-rw-r--r-- | fs/xfs/libxfs/xfs_defer.c | 17 |
23 files changed, 268 insertions, 242 deletions
@@ -1078,6 +1078,17 @@ static void aio_complete(struct kiocb *kiocb, long res, long res2) unsigned tail, pos, head; unsigned long flags; + if (kiocb->ki_flags & IOCB_WRITE) { + struct file *file = kiocb->ki_filp; + + /* + * Tell lockdep we inherited freeze protection from submission + * thread. + */ + __sb_writers_acquired(file_inode(file)->i_sb, SB_FREEZE_WRITE); + file_end_write(file); + } + /* * Special case handling for sync iocbs: * - events go directly into the iocb for fast handling @@ -1392,122 +1403,106 @@ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx) return -EINVAL; } -typedef ssize_t (rw_iter_op)(struct kiocb *, struct iov_iter *); - -static int aio_setup_vectored_rw(int rw, char __user *buf, size_t len, - struct iovec **iovec, - bool compat, - struct iov_iter *iter) +static int aio_setup_rw(int rw, struct iocb *iocb, struct iovec **iovec, + bool vectored, bool compat, struct iov_iter *iter) { + void __user *buf = (void __user *)(uintptr_t)iocb->aio_buf; + size_t len = iocb->aio_nbytes; + + if (!vectored) { + ssize_t ret = import_single_range(rw, buf, len, *iovec, iter); + *iovec = NULL; + return ret; + } #ifdef CONFIG_COMPAT if (compat) - return compat_import_iovec(rw, - (struct compat_iovec __user *)buf, - len, UIO_FASTIOV, iovec, iter); + return compat_import_iovec(rw, buf, len, UIO_FASTIOV, iovec, + iter); #endif - return import_iovec(rw, (struct iovec __user *)buf, - len, UIO_FASTIOV, iovec, iter); + return import_iovec(rw, buf, len, UIO_FASTIOV, iovec, iter); } -/* - * aio_run_iocb: - * Performs the initial checks and io submission. - */ -static ssize_t aio_run_iocb(struct kiocb *req, unsigned opcode, - char __user *buf, size_t len, bool compat) +static inline ssize_t aio_ret(struct kiocb *req, ssize_t ret) +{ + switch (ret) { + case -EIOCBQUEUED: + return ret; + case -ERESTARTSYS: + case -ERESTARTNOINTR: + case -ERESTARTNOHAND: + case -ERESTART_RESTARTBLOCK: + /* + * There's no easy way to restart the syscall since other AIO's + * may be already running. Just fail this IO with EINTR. + */ + ret = -EINTR; + /*FALLTHRU*/ + default: + aio_complete(req, ret, 0); + return 0; + } +} + +static ssize_t aio_read(struct kiocb *req, struct iocb *iocb, bool vectored, + bool compat) { struct file *file = req->ki_filp; - ssize_t ret; - int rw; - fmode_t mode; - rw_iter_op *iter_op; struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; struct iov_iter iter; + ssize_t ret; - switch (opcode) { - case IOCB_CMD_PREAD: - case IOCB_CMD_PREADV: - mode = FMODE_READ; - rw = READ; - iter_op = file->f_op->read_iter; - goto rw_common; - - case IOCB_CMD_PWRITE: - case IOCB_CMD_PWRITEV: - mode = FMODE_WRITE; - rw = WRITE; - iter_op = file->f_op->write_iter; - goto rw_common; -rw_common: - if (unlikely(!(file->f_mode & mode))) - return -EBADF; - - if (!iter_op) - return -EINVAL; - - if (opcode == IOCB_CMD_PREADV || opcode == IOCB_CMD_PWRITEV) - ret = aio_setup_vectored_rw(rw, buf, len, - &iovec, compat, &iter); - else { - ret = import_single_range(rw, buf, len, iovec, &iter); - iovec = NULL; - } - if (!ret) - ret = rw_verify_area(rw, file, &req->ki_pos, - iov_iter_count(&iter)); - if (ret < 0) { - kfree(iovec); - return ret; - } - - if (rw == WRITE) - file_start_write(file); - - ret = iter_op(req, &iter); - - if (rw == WRITE) - file_end_write(file); - kfree(iovec); - break; - - case IOCB_CMD_FDSYNC: - if (!file->f_op->aio_fsync) - return -EINVAL; - - ret = file->f_op->aio_fsync(req, 1); - break; + if (unlikely(!(file->f_mode & FMODE_READ))) + return -EBADF; + if (unlikely(!file->f_op->read_iter)) + return -EINVAL; - case IOCB_CMD_FSYNC: - if (!file->f_op->aio_fsync) - return -EINVAL; + ret = aio_setup_rw(READ, iocb, &iovec, vectored, compat, &iter); + if (ret) + return ret; + ret = rw_verify_area(READ, file, &req->ki_pos, iov_iter_count(&iter)); + if (!ret) + ret = aio_ret(req, file->f_op->read_iter(req, &iter)); + kfree(iovec); + return ret; +} - ret = file->f_op->aio_fsync(req, 0); - break; +static ssize_t aio_write(struct kiocb *req, struct iocb *iocb, bool vectored, + bool compat) +{ + struct file *file = req->ki_filp; + struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; + struct iov_iter iter; + ssize_t ret; - default: - pr_debug("EINVAL: no operation provided\n"); + if (unlikely(!(file->f_mode & FMODE_WRITE))) + return -EBADF; + if (unlikely(!file->f_op->write_iter)) return -EINVAL; - } - if (ret != -EIOCBQUEUED) { + ret = aio_setup_rw(WRITE, iocb, &iovec, vectored, compat, &iter); + if (ret) + return ret; + ret = rw_verify_area(WRITE, file, &req->ki_pos, iov_iter_count(&iter)); + if (!ret) { + req->ki_flags |= IOCB_WRITE; + file_start_write(file); + ret = aio_ret(req, file->f_op->write_iter(req, &iter)); /* - * There's no easy way to restart the syscall since other AIO's - * may be already running. Just fail this IO with EINTR. + * We release freeze protection in aio_complete(). Fool lockdep + * by telling it the lock got released so that it doesn't + * complain about held lock when we return to userspace. */ - if (unlikely(ret == -ERESTARTSYS || ret == -ERESTARTNOINTR || - ret == -ERESTARTNOHAND || - ret == -ERESTART_RESTARTBLOCK)) - ret = -EINTR; - aio_complete(req, ret, 0); + __sb_writers_release(file_inode(file)->i_sb, SB_FREEZE_WRITE); } - - return 0; + kfree(iovec); + return ret; } static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, struct iocb *iocb, bool compat) { struct aio_kiocb *req; + struct file *file; ssize_t ret; /* enforce forwards compatibility on users */ @@ -1530,7 +1525,7 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, if (unlikely(!req)) return -EAGAIN; - req->common.ki_filp = fget(iocb->aio_fildes); + req->common.ki_filp = file = fget(iocb->aio_fildes); if (unlikely(!req->common.ki_filp)) { ret = -EBADF; goto out_put_req; @@ -1565,13 +1560,29 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, req->ki_user_iocb = user_iocb; req->ki_user_data = iocb->aio_data; - ret = aio_run_iocb(&req->common, iocb->aio_lio_opcode, - (char __user *)(unsigned long)iocb->aio_buf, - iocb->aio_nbytes, - compat); - if (ret) - goto out_put_req; + get_file(file); + switch (iocb->aio_lio_opcode) { + case IOCB_CMD_PREAD: + ret = aio_read(&req->common, iocb, false, compat); + break; + case IOCB_CMD_PWRITE: + ret = aio_write(&req->common, iocb, false, compat); + break; + case IOCB_CMD_PREADV: + ret = aio_read(&req->common, iocb, true, compat); + break; + case IOCB_CMD_PWRITEV: + ret = aio_write(&req->common, iocb, true, compat); + break; + default: + pr_debug("invalid aio operation %d\n", iocb->aio_lio_opcode); + ret = -EINVAL; + break; + } + fput(file); + if (ret && ret != -EIOCBQUEUED) + goto out_put_req; return 0; out_put_req: put_reqs_available(ctx, 1); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 210c94ac8818..4607af38c72e 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2647,7 +2647,10 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, btrfs_free_delayed_extent_op(extent_op); if (ret) { + spin_lock(&delayed_refs->lock); locked_ref->processing = 0; + delayed_refs->num_heads_ready++; + spin_unlock(&delayed_refs->lock); btrfs_delayed_ref_unlock(locked_ref); btrfs_put_delayed_ref(ref); btrfs_debug(fs_info, "run_one_delayed_ref returned %d", diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 66a755150056..8ed05d95584a 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -5569,7 +5569,7 @@ void le_bitmap_set(u8 *map, unsigned int start, int len) *p |= mask_to_set; len -= bits_to_set; bits_to_set = BITS_PER_BYTE; - mask_to_set = ~(u8)0; + mask_to_set = ~0; p++; } if (len) { @@ -5589,7 +5589,7 @@ void le_bitmap_clear(u8 *map, unsigned int start, int len) *p &= ~mask_to_clear; len -= bits_to_clear; bits_to_clear = BITS_PER_BYTE; - mask_to_clear = ~(u8)0; + mask_to_clear = ~0; p++; } if (len) { @@ -5679,7 +5679,7 @@ void extent_buffer_bitmap_set(struct extent_buffer *eb, unsigned long start, kaddr[offset] |= mask_to_set; len -= bits_to_set; bits_to_set = BITS_PER_BYTE; - mask_to_set = ~(u8)0; + mask_to_set = ~0; if (++offset >= PAGE_SIZE && len > 0) { offset = 0; page = eb->pages[++i]; @@ -5721,7 +5721,7 @@ void extent_buffer_bitmap_clear(struct extent_buffer *eb, unsigned long start, kaddr[offset] &= ~mask_to_clear; len -= bits_to_clear; bits_to_clear = BITS_PER_BYTE; - mask_to_clear = ~(u8)0; + mask_to_clear = ~0; if (++offset >= PAGE_SIZE && len > 0) { offset = 0; page = eb->pages[++i]; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 2b790bda7998..8e3a5a266917 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4605,8 +4605,8 @@ delete: BUG_ON(ret); if (btrfs_should_throttle_delayed_refs(trans, root)) btrfs_async_run_delayed_refs(root, - trans->transid, - trans->delayed_ref_updates * 2, 0); + trans->delayed_ref_updates * 2, + trans->transid, 0); if (be_nice) { if (truncate_space_check(trans, root, extent_num_bytes)) { @@ -8931,9 +8931,14 @@ again: * So even we call qgroup_free_data(), it won't decrease reserved * space. * 2) Not written to disk - * This means the reserved space should be freed here. + * This means the reserved space should be freed here. However, + * if a truncate invalidates the page (by clearing PageDirty) + * and the page is accounted for while allocating extent + * in btrfs_check_data_free_space() we let delayed_ref to + * free the entire extent. */ - btrfs_qgroup_free_data(inode, page_start, PAGE_SIZE); + if (PageDirty(page)) + btrfs_qgroup_free_data(inode, page_start, PAGE_SIZE); if (!inode_evicting) { clear_extent_bit(tree, page_start, page_end, EXTENT_LOCKED | EXTENT_DIRTY | diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 18e1aa0f85f5..7acbd2cf6192 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3814,6 +3814,11 @@ process_slot: } btrfs_release_path(path); key.offset = next_key_min_offset; + + if (fatal_signal_pending(current)) { + ret = -EINTR; + goto out; + } } ret = 0; diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 0ec8ffa37ab0..c4af0cdb783d 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -2728,7 +2728,14 @@ static int do_relocation(struct btrfs_trans_handle *trans, bytenr = btrfs_node_blockptr(upper->eb, slot); if (lowest) { - BUG_ON(bytenr != node->bytenr); + if (bytenr != node->bytenr) { + btrfs_err(root->fs_info, + "lowest leaf/node mismatch: bytenr %llu node->bytenr %llu slot %d upper %llu", + bytenr, node->bytenr, slot, + upper->eb->start); + err = -EIO; + goto next; + } } else { if (node->eb->start == bytenr) goto next; diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 18630e800208..f995e3528a33 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -1770,7 +1770,6 @@ const struct file_operations ceph_file_fops = { .fsync = ceph_fsync, .lock = ceph_lock, .flock = ceph_flock, - .splice_read = generic_file_splice_read, .splice_write = iter_file_splice_write, .unlocked_ioctl = ceph_ioctl, .compat_ioctl = ceph_ioctl, diff --git a/fs/coredump.c b/fs/coredump.c index 281b768000e6..eb9c92c9b20f 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -1,6 +1,7 @@ #include <linux/slab.h> #include <linux/file.h> #include <linux/fdtable.h> +#include <linux/freezer.h> #include <linux/mm.h> #include <linux/stat.h> #include <linux/fcntl.h> @@ -423,7 +424,9 @@ static int coredump_wait(int exit_code, struct core_state *core_state) if (core_waiters > 0) { struct core_thread *ptr; + freezer_do_not_count(); wait_for_completion(&core_state->startup); + freezer_count(); /* * Wait for all the threads to become inactive, so that * all the thread context (extended register state, like diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 7555ba889d1f..ebecfb8fba06 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -314,7 +314,8 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat /* Match the full socket address */ if (!rpc_cmp_addr_port(sap, clap)) /* Match all xprt_switch full socket addresses */ - if (!rpc_clnt_xprt_switch_has_addr(clp->cl_rpcclient, + if (IS_ERR(clp->cl_rpcclient) || + !rpc_clnt_xprt_switch_has_addr(clp->cl_rpcclient, sap)) continue; diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c index c8162c660c44..5551e8ef67fd 100644 --- a/fs/nfs/namespace.c +++ b/fs/nfs/namespace.c @@ -98,7 +98,7 @@ rename_retry: return end; } namelen = strlen(base); - if (flags & NFS_PATH_CANONICAL) { + if (*end == '/') { /* Strip off excess slashes in base string */ while (namelen > 0 && base[namelen - 1] == '/') namelen--; diff --git a/fs/nfs/nfs4session.c b/fs/nfs/nfs4session.c index b62973045a3e..a61350f75c74 100644 --- a/fs/nfs/nfs4session.c +++ b/fs/nfs/nfs4session.c @@ -178,12 +178,14 @@ static int nfs4_slot_get_seqid(struct nfs4_slot_table *tbl, u32 slotid, __must_hold(&tbl->slot_tbl_lock) { struct nfs4_slot *slot; + int ret; slot = nfs4_lookup_slot(tbl, slotid); - if (IS_ERR(slot)) - return PTR_ERR(slot); - *seq_nr = slot->seq_nr; - return 0; + ret = PTR_ERR_OR_ZERO(slot); + if (!ret) + *seq_nr = slot->seq_nr; + + return ret; } /* @@ -196,7 +198,7 @@ static int nfs4_slot_get_seqid(struct nfs4_slot_table *tbl, u32 slotid, static bool nfs4_slot_seqid_in_use(struct nfs4_slot_table *tbl, u32 slotid, u32 seq_nr) { - u32 cur_seq; + u32 cur_seq = 0; bool ret = false; spin_lock(&tbl->slot_tbl_lock); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 56b2d96f9103..259ef85f435a 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -146,6 +146,8 @@ set_pnfs_layoutdriver(struct nfs_server *server, const struct nfs_fh *mntfh, u32 id; int i; + if (fsinfo->nlayouttypes == 0) + goto out_no_driver; if (!(server->nfs_client->cl_exchange_flags & (EXCHGID4_FLAG_USE_NON_PNFS | EXCHGID4_FLAG_USE_PNFS_MDS))) { printk(KERN_ERR "NFS: %s: cl_exchange_flags 0x%x\n", diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h index b10d557f9c9e..ee36efd5aece 100644 --- a/fs/nfsd/netns.h +++ b/fs/nfsd/netns.h @@ -84,6 +84,8 @@ struct nfsd_net { struct list_head client_lru; struct list_head close_lru; struct list_head del_recall_lru; + + /* protected by blocked_locks_lock */ struct list_head blocked_locks_lru; struct delayed_work laundromat_work; @@ -91,6 +93,9 @@ struct nfsd_net { /* client_lock protects the client lru list and session hash table */ spinlock_t client_lock; + /* protects blocked_locks_lru */ + spinlock_t blocked_locks_lock; + struct file *rec_file; bool in_grace; const struct nfsd4_client_tracking_ops *client_tracking_ops; diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 9752beb78659..4b4beaaa4eaa 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -217,7 +217,7 @@ find_blocked_lock(struct nfs4_lockowner *lo, struct knfsd_fh *fh, { struct nfsd4_blocked_lock *cur, *found = NULL; - spin_lock(&nn->client_lock); + spin_lock(&nn->blocked_locks_lock); list_for_each_entry(cur, &lo->lo_blocked, nbl_list) { if (fh_match(fh, &cur->nbl_fh)) { list_del_init(&cur->nbl_list); @@ -226,7 +226,7 @@ find_blocked_lock(struct nfs4_lockowner *lo, struct knfsd_fh *fh, break; } } - spin_unlock(&nn->client_lock); + spin_unlock(&nn->blocked_locks_lock); if (found) posix_unblock_lock(&found->nbl_lock); return found; @@ -1227,9 +1227,7 @@ static void put_ol_stateid_locked(struct nfs4_ol_stateid *stp, static bool unhash_lock_stateid(struct nfs4_ol_stateid *stp) { - struct nfs4_openowner *oo = openowner(stp->st_openstp->st_stateowner); - - lockdep_assert_held(&oo->oo_owner.so_client->cl_lock); + lockdep_assert_held(&stp->st_stid.sc_client->cl_lock); list_del_init(&stp->st_locks); nfs4_unhash_stid(&stp->st_stid); @@ -1238,12 +1236,12 @@ static bool unhash_lock_stateid(struct nfs4_ol_stateid *stp) static void release_lock_stateid(struct nfs4_ol_stateid *stp) { - struct nfs4_openowner *oo = openowner(stp->st_openstp->st_stateowner); + struct nfs4_client *clp = stp->st_stid.sc_client; bool unhashed; - spin_lock(&oo->oo_owner.so_client->cl_lock); + spin_lock(&clp->cl_lock); unhashed = unhash_lock_stateid(stp); - spin_unlock(&oo->oo_owner.so_client->cl_lock); + spin_unlock(&clp->cl_lock); if (unhashed) nfs4_put_stid(&stp->st_stid); } @@ -4665,7 +4663,7 @@ nfs4_laundromat(struct nfsd_net *nn) * indefinitely once the lock does become free. */ BUG_ON(!list_empty(&reaplist)); - spin_lock(&nn->client_lock); + spin_lock(&nn->blocked_locks_lock); while (!list_empty(&nn->blocked_locks_lru)) { nbl = list_first_entry(&nn->blocked_locks_lru, struct nfsd4_blocked_lock, nbl_lru); @@ -4678,7 +4676,7 @@ nfs4_laundromat(struct nfsd_net *nn) list_move(&nbl->nbl_lru, &reaplist); list_del_init(&nbl->nbl_list); } - spin_unlock(&nn->client_lock); + spin_unlock(&nn->blocked_locks_lock); while (!list_empty(&reaplist)) { nbl = list_first_entry(&nn->blocked_locks_lru, @@ -5439,13 +5437,13 @@ nfsd4_lm_notify(struct file_lock *fl) bool queue = false; /* An empty list means that something else is going to be using it */ - spin_lock(&nn->client_lock); + spin_lock(&nn->blocked_locks_lock); if (!list_empty(&nbl->nbl_list)) { list_del_init(&nbl->nbl_list); list_del_init(&nbl->nbl_lru); queue = true; } - spin_unlock(&nn->client_lock); + spin_unlock(&nn->blocked_locks_lock); if (queue) nfsd4_run_cb(&nbl->nbl_cb); @@ -5868,10 +5866,10 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (fl_flags & FL_SLEEP) { nbl->nbl_time = jiffies; - spin_lock(&nn->client_lock); + spin_lock(&nn->blocked_locks_lock); list_add_tail(&nbl->nbl_list, &lock_sop->lo_blocked); list_add_tail(&nbl->nbl_lru, &nn->blocked_locks_lru); - spin_unlock(&nn->client_lock); + spin_unlock(&nn->blocked_locks_lock); } err = vfs_lock_file(filp, F_SETLK, file_lock, conflock); @@ -5900,10 +5898,10 @@ out: if (nbl) { /* dequeue it if we queued it before */ if (fl_flags & FL_SLEEP) { - spin_lock(&nn->client_lock); + spin_lock(&nn->blocked_locks_lock); list_del_init(&nbl->nbl_list); list_del_init(&nbl->nbl_lru); - spin_unlock(&nn->client_lock); + spin_unlock(&nn->blocked_locks_lock); } free_blocked_lock(nbl); } @@ -6943,9 +6941,11 @@ static int nfs4_state_create_net(struct net *net) INIT_LIST_HEAD(&nn->client_lru); INIT_LIST_HEAD(&nn->close_lru); INIT_LIST_HEAD(&nn->del_recall_lru); - INIT_LIST_HEAD(&nn->blocked_locks_lru); spin_lock_init(&nn->client_lock); + spin_lock_init(&nn->blocked_locks_lock); + INIT_LIST_HEAD(&nn->blocked_locks_lru); + INIT_DELAYED_WORK(&nn->laundromat_work, laundromat_main); get_net(net); @@ -7063,14 +7063,14 @@ nfs4_state_shutdown_net(struct net *net) } BUG_ON(!list_empty(&reaplist)); - spin_lock(&nn->client_lock); + spin_lock(&nn->blocked_locks_lock); while (!list_empty(&nn->blocked_locks_lru)) { nbl = list_first_entry(&nn->blocked_locks_lru, struct nfsd4_blocked_lock, nbl_lru); list_move(&nbl->nbl_lru, &reaplist); list_del_init(&nbl->nbl_list); } - spin_unlock(&nn->client_lock); + spin_unlock(&nn->blocked_locks_lock); while (!list_empty(&reaplist)) { nbl = list_first_entry(&nn->blocked_locks_lru, diff --git a/fs/ntfs/dir.c b/fs/ntfs/dir.c index a18613579001..0ee19ecc982d 100644 --- a/fs/ntfs/dir.c +++ b/fs/ntfs/dir.c @@ -1544,8 +1544,6 @@ const struct file_operations ntfs_dir_ops = { .iterate = ntfs_readdir, /* Read directory contents. */ #ifdef NTFS_RW .fsync = ntfs_dir_fsync, /* Sync a directory to disk. */ - /*.aio_fsync = ,*/ /* Sync all outstanding async - i/o operations on a kiocb. */ #endif /* NTFS_RW */ /*.ioctl = ,*/ /* Perform function on the mounted filesystem. */ diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index e7054e2ac922..3ecb9f337b7d 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -3699,7 +3699,7 @@ static void ocfs2_dx_dir_transfer_leaf(struct inode *dir, u32 split_hash, static int ocfs2_dx_dir_rebalance_credits(struct ocfs2_super *osb, struct ocfs2_dx_root_block *dx_root) { - int credits = ocfs2_clusters_to_blocks(osb->sb, 2); + int credits = ocfs2_clusters_to_blocks(osb->sb, 3); credits += ocfs2_calc_extend_credits(osb->sb, &dx_root->dr_list); credits += ocfs2_quota_trans_credits(osb->sb); diff --git a/fs/orangefs/orangefs-debugfs.c b/fs/orangefs/orangefs-debugfs.c index eb09aa026723..d484068ca716 100644 --- a/fs/orangefs/orangefs-debugfs.c +++ b/fs/orangefs/orangefs-debugfs.c @@ -141,6 +141,9 @@ static struct client_debug_mask client_debug_mask; */ static DEFINE_MUTEX(orangefs_debug_lock); +/* Used to protect data in ORANGEFS_KMOD_DEBUG_HELP_FILE */ +static DEFINE_MUTEX(orangefs_help_file_lock); + /* * initialize kmod debug operations, create orangefs debugfs dir and * ORANGEFS_KMOD_DEBUG_HELP_FILE. @@ -289,6 +292,8 @@ static void *help_start(struct seq_file *m, loff_t *pos) gossip_debug(GOSSIP_DEBUGFS_DEBUG, "help_start: start\n"); + mutex_lock(&orangefs_help_file_lock); + if (*pos == 0) payload = m->private; @@ -305,6 +310,7 @@ static void *help_next(struct seq_file *m, void *v, loff_t *pos) static void help_stop(struct seq_file *m, void *p) { gossip_debug(GOSSIP_DEBUGFS_DEBUG, "help_stop: start\n"); + mutex_unlock(&orangefs_help_file_lock); } static int help_show(struct seq_file *m, void *v) @@ -610,32 +616,54 @@ out: * /sys/kernel/debug/orangefs/debug-help can be catted to * see all the available kernel and client debug keywords. * - * When the kernel boots, we have no idea what keywords the + * When orangefs.ko initializes, we have no idea what keywords the * client supports, nor their associated masks. * - * We pass through this function once at boot and stamp a + * We pass through this function once at module-load and stamp a * boilerplate "we don't know" message for the client in the * debug-help file. We pass through here again when the client * starts and then we can fill out the debug-help file fully. * * The client might be restarted any number of times between - * reboots, we only build the debug-help file the first time. + * module reloads, we only build the debug-help file the first time. */ int orangefs_prepare_debugfs_help_string(int at_boot) { - int rc = -EINVAL; - int i; - int byte_count = 0; char *client_title = "Client Debug Keywords:\n"; char *kernel_title = "Kernel Debug Keywords:\n"; + size_t string_size = DEBUG_HELP_STRING_SIZE; + size_t result_size; + size_t i; + char *new; + int rc = -EINVAL; gossip_debug(GOSSIP_UTILS_DEBUG, "%s: start\n", __func__); - if (at_boot) { - byte_count += strlen(HELP_STRING_UNINITIALIZED); + if (at_boot) client_title = HELP_STRING_UNINITIALIZED; - } else { - /* + + /* build a new debug_help_string. */ + new = kzalloc(DEBUG_HELP_STRING_SIZE, GFP_KERNEL); + if (!new) { + rc = -ENOMEM; + goto out; + } + + /* + * strlcat(dst, src, size) will append at most + * "size - strlen(dst) - 1" bytes of src onto dst, + * null terminating the result, and return the total + * length of the string it tried to create. + * + * We'll just plow through here building our new debug + * help string and let strlcat take care of assuring that + * dst doesn't overflow. + */ + strlcat(new, client_title, string_size); + + if (!at_boot) { + + /* * fill the client keyword/mask array and remember * how many elements there were. */ @@ -644,64 +672,40 @@ int orangefs_prepare_debugfs_help_string(int at_boot) if (cdm_element_count <= 0) goto out; - /* Count the bytes destined for debug_help_string. */ - byte_count += strlen(client_title); - for (i = 0; i < cdm_element_count; i++) { - byte_count += strlen(cdm_array[i].keyword + 2); - if (byte_count >= DEBUG_HELP_STRING_SIZE) { - pr_info("%s: overflow 1!\n", __func__); - goto out; - } + strlcat(new, "\t", string_size); + strlcat(new, cdm_array[i].keyword, string_size); + strlcat(new, "\n", string_size); } - - gossip_debug(GOSSIP_UTILS_DEBUG, - "%s: cdm_element_count:%d:\n", - __func__, - cdm_element_count); } - byte_count += strlen(kernel_title); + strlcat(new, "\n", string_size); + strlcat(new, kernel_title, string_size); + for (i = 0; i < num_kmod_keyword_mask_map; i++) { - byte_count += - strlen(s_kmod_keyword_mask_map[i].keyword + 2); - if (byte_count >= DEBUG_HELP_STRING_SIZE) { - pr_info("%s: overflow 2!\n", __func__); - goto out; - } + strlcat(new, "\t", string_size); + strlcat(new, s_kmod_keyword_mask_map[i].keyword, string_size); + result_size = strlcat(new, "\n", string_size); } - /* build debug_help_string. */ - debug_help_string = kzalloc(DEBUG_HELP_STRING_SIZE, GFP_KERNEL); - if (!debug_help_string) { - rc = -ENOMEM; + /* See if we tried to put too many bytes into "new"... */ + if (result_size >= string_size) { + kfree(new); goto out; } - strcat(debug_help_string, client_title); - - if (!at_boot) { - for (i = 0; i < cdm_element_count; i++) { - strcat(debug_help_string, "\t"); - strcat(debug_help_string, cdm_array[i].keyword); - strcat(debug_help_string, "\n"); - } - } - - strcat(debug_help_string, "\n"); - strcat(debug_help_string, kernel_title); - - for (i = 0; i < num_kmod_keyword_mask_map; i++) { - strcat(debug_help_string, "\t"); - strcat(debug_help_string, s_kmod_keyword_mask_map[i].keyword); - strcat(debug_help_string, "\n"); + if (at_boot) { + debug_help_string = new; + } else { + mutex_lock(&orangefs_help_file_lock); + memset(debug_help_string, 0, DEBUG_HELP_STRING_SIZE); + strlcat(debug_help_string, new, string_size); + mutex_unlock(&orangefs_help_file_lock); } rc = 0; -out: - - return rc; +out: return rc; } @@ -959,8 +963,12 @@ int orangefs_debugfs_new_client_string(void __user *arg) ret = copy_from_user(&client_debug_array_string, (void __user *)arg, ORANGEFS_MAX_DEBUG_STRING_LEN); - if (ret != 0) + + if (ret != 0) { + pr_info("%s: CLIENT_STRING: copy_from_user failed\n", + __func__); return -EIO; + } /* * The real client-core makes an effort to ensure @@ -975,45 +983,18 @@ int orangefs_debugfs_new_client_string(void __user *arg) client_debug_array_string[ORANGEFS_MAX_DEBUG_STRING_LEN - 1] = '\0'; - if (ret != 0) { - pr_info("%s: CLIENT_STRING: copy_from_user failed\n", - __func__); - return -EIO; - } - pr_info("%s: client debug array string has been received.\n", __func__); if (!help_string_initialized) { - /* Free the "we don't know yet" default string... */ - kfree(debug_help_string); - - /* build a proper debug help string */ + /* Build a proper debug help string. */ if (orangefs_prepare_debugfs_help_string(0)) { gossip_err("%s: no debug help string \n", __func__); return -EIO; } - /* Replace the boilerplate boot-time debug-help file. */ - debugfs_remove(help_file_dentry); - - help_file_dentry = - debugfs_create_file( - ORANGEFS_KMOD_DEBUG_HELP_FILE, - 0444, - debug_dir, - debug_help_string, - &debug_help_fops); - - if (!help_file_dentry) { - gossip_err("%s: debugfs_create_file failed for" - " :%s:!\n", - __func__, - ORANGEFS_KMOD_DEBUG_HELP_FILE); - return -EIO; - } } debug_mask_to_string(&client_debug_mask, 1); diff --git a/fs/orangefs/orangefs-mod.c b/fs/orangefs/orangefs-mod.c index 2e5b03065f34..4113eb0495bf 100644 --- a/fs/orangefs/orangefs-mod.c +++ b/fs/orangefs/orangefs-mod.c @@ -124,7 +124,7 @@ static int __init orangefs_init(void) * unknown at boot time. * * orangefs_prepare_debugfs_help_string will be used again - * later to rebuild the debug-help file after the client starts + * later to rebuild the debug-help-string after the client starts * and passes along the needed info. The argument signifies * which time orangefs_prepare_debugfs_help_string is being * called. @@ -152,7 +152,9 @@ static int __init orangefs_init(void) ret = register_filesystem(&orangefs_fs_type); if (ret == 0) { - pr_info("orangefs: module version %s loaded\n", ORANGEFS_VERSION); + pr_info("%s: module version %s loaded\n", + __func__, + ORANGEFS_VERSION); ret = 0; goto out; } diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index aeb60f791418..36795eed40b0 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -178,6 +178,8 @@ static int ovl_copy_up_data(struct path *old, struct path *new, loff_t len) len -= bytes; } + if (!error) + error = vfs_fsync(new_file, 0); fput(new_file); out_fput: fput(old_file); diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index c58f01babf30..7fb53d055537 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -270,9 +270,6 @@ struct posix_acl *ovl_get_acl(struct inode *inode, int type) if (!IS_ENABLED(CONFIG_FS_POSIX_ACL) || !IS_POSIXACL(realinode)) return NULL; - if (!realinode->i_op->get_acl) - return NULL; - old_cred = ovl_override_creds(inode->i_sb); acl = get_acl(realinode, type); revert_creds(old_cred); diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index bcf3965be819..edd46a0e951d 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -1037,6 +1037,21 @@ ovl_posix_acl_xattr_set(const struct xattr_handler *handler, posix_acl_release(acl); + /* + * Check if sgid bit needs to be cleared (actual setacl operation will + * be done with mounter's capabilities and so that won't do it for us). + */ + if (unlikely(inode->i_mode & S_ISGID) && + handler->flags == ACL_TYPE_ACCESS && + !in_group_p(inode->i_gid) && + !capable_wrt_inode_uidgid(inode, CAP_FSETID)) { + struct iattr iattr = { .ia_valid = ATTR_KILL_SGID }; + + err = ovl_setattr(dentry, &iattr); + if (err) + return err; + } + err = ovl_xattr_set(dentry, handler->name, value, size, flags); if (!err) ovl_copyattr(ovl_inode_real(inode, NULL), inode); diff --git a/fs/splice.c b/fs/splice.c index 153d4f3bd441..dcaf185a5731 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -299,13 +299,8 @@ ssize_t generic_file_splice_read(struct file *in, loff_t *ppos, { struct iov_iter to; struct kiocb kiocb; - loff_t isize; int idx, ret; - isize = i_size_read(in->f_mapping->host); - if (unlikely(*ppos >= isize)) - return 0; - iov_iter_pipe(&to, ITER_PIPE | READ, pipe, len); idx = to.idx; init_sync_kiocb(&kiocb, in); diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c index 613c5cf19436..5c2929f94bd3 100644 --- a/fs/xfs/libxfs/xfs_defer.c +++ b/fs/xfs/libxfs/xfs_defer.c @@ -199,9 +199,9 @@ xfs_defer_intake_work( struct xfs_defer_pending *dfp; list_for_each_entry(dfp, &dop->dop_intake, dfp_list) { - trace_xfs_defer_intake_work(tp->t_mountp, dfp); dfp->dfp_intent = dfp->dfp_type->create_intent(tp, dfp->dfp_count); + trace_xfs_defer_intake_work(tp->t_mountp, dfp); list_sort(tp->t_mountp, &dfp->dfp_work, dfp->dfp_type->diff_items); list_for_each(li, &dfp->dfp_work) @@ -221,21 +221,14 @@ xfs_defer_trans_abort( struct xfs_defer_pending *dfp; trace_xfs_defer_trans_abort(tp->t_mountp, dop); - /* - * If the transaction was committed, drop the intent reference - * since we're bailing out of here. The other reference is - * dropped when the intent hits the AIL. If the transaction - * was not committed, the intent is freed by the intent item - * unlock handler on abort. - */ - if (!dop->dop_committed) - return; - /* Abort intent items. */ + /* Abort intent items that don't have a done item. */ list_for_each_entry(dfp, &dop->dop_pending, dfp_list) { trace_xfs_defer_pending_abort(tp->t_mountp, dfp); - if (!dfp->dfp_done) + if (dfp->dfp_intent && !dfp->dfp_done) { dfp->dfp_type->abort_intent(dfp->dfp_intent); + dfp->dfp_intent = NULL; + } } /* Shut down FS. */ |