diff options
Diffstat (limited to 'fs')
59 files changed, 652 insertions, 290 deletions
diff --git a/fs/afs/callback.c b/fs/afs/callback.c index 1c7955f5cdaf..128f2dbe256a 100644 --- a/fs/afs/callback.c +++ b/fs/afs/callback.c @@ -203,8 +203,7 @@ void afs_put_cb_interest(struct afs_net *net, struct afs_cb_interest *cbi) */ void afs_init_callback_state(struct afs_server *server) { - if (!test_and_clear_bit(AFS_SERVER_FL_NEW, &server->flags)) - server->cb_s_break++; + server->cb_s_break++; } /* diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c index ca08c83168f5..0b37867b5c20 100644 --- a/fs/afs/fsclient.c +++ b/fs/afs/fsclient.c @@ -1515,8 +1515,8 @@ static int afs_fs_setattr_size64(struct afs_fs_cursor *fc, struct iattr *attr) xdr_encode_AFS_StoreStatus(&bp, attr); - *bp++ = 0; /* position of start of write */ - *bp++ = 0; + *bp++ = htonl(attr->ia_size >> 32); /* position of start of write */ + *bp++ = htonl((u32) attr->ia_size); *bp++ = 0; /* size of write */ *bp++ = 0; *bp++ = htonl(attr->ia_size >> 32); /* new file length */ @@ -1564,7 +1564,7 @@ static int afs_fs_setattr_size(struct afs_fs_cursor *fc, struct iattr *attr) xdr_encode_AFS_StoreStatus(&bp, attr); - *bp++ = 0; /* position of start of write */ + *bp++ = htonl(attr->ia_size); /* position of start of write */ *bp++ = 0; /* size of write */ *bp++ = htonl(attr->ia_size); /* new file length */ diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 8871b9e8645f..465526f495b0 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -475,7 +475,6 @@ struct afs_server { time64_t put_time; /* Time at which last put */ time64_t update_at; /* Time at which to next update the record */ unsigned long flags; -#define AFS_SERVER_FL_NEW 0 /* New server, don't inc cb_s_break */ #define AFS_SERVER_FL_NOT_READY 1 /* The record is not ready for use */ #define AFS_SERVER_FL_NOT_FOUND 2 /* VL server says no such server */ #define AFS_SERVER_FL_VL_FAIL 3 /* Failed to access VL server */ @@ -828,7 +827,7 @@ static inline struct afs_cb_interest *afs_get_cb_interest(struct afs_cb_interest static inline unsigned int afs_calc_vnode_cb_break(struct afs_vnode *vnode) { - return vnode->cb_break + vnode->cb_s_break + vnode->cb_v_break; + return vnode->cb_break + vnode->cb_v_break; } static inline bool afs_cb_is_broken(unsigned int cb_break, @@ -836,7 +835,6 @@ static inline bool afs_cb_is_broken(unsigned int cb_break, const struct afs_cb_interest *cbi) { return !cbi || cb_break != (vnode->cb_break + - cbi->server->cb_s_break + vnode->volume->cb_v_break); } diff --git a/fs/afs/server.c b/fs/afs/server.c index 642afa2e9783..65b33b6da48b 100644 --- a/fs/afs/server.c +++ b/fs/afs/server.c @@ -226,7 +226,6 @@ static struct afs_server *afs_alloc_server(struct afs_net *net, RCU_INIT_POINTER(server->addresses, alist); server->addr_version = alist->version; server->uuid = *uuid; - server->flags = (1UL << AFS_SERVER_FL_NEW); server->update_at = ktime_get_real_seconds() + afs_server_update_delay; rwlock_init(&server->fs_lock); INIT_HLIST_HEAD(&server->cb_volumes); diff --git a/fs/afs/write.c b/fs/afs/write.c index 72efcfcf9f95..0122d7445fba 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -264,6 +264,7 @@ static void afs_kill_pages(struct address_space *mapping, first = page->index + 1; lock_page(page); generic_error_remove_page(mapping, page); + unlock_page(page); } __pagevec_release(&pv); diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c index 5aa57929e8c2..6e97a42d24d1 100644 --- a/fs/afs/yfsclient.c +++ b/fs/afs/yfsclient.c @@ -1514,7 +1514,7 @@ static int yfs_fs_setattr_size(struct afs_fs_cursor *fc, struct iattr *attr) bp = xdr_encode_u32(bp, 0); /* RPC flags */ bp = xdr_encode_YFSFid(bp, &vnode->fid); bp = xdr_encode_YFS_StoreStatus(bp, attr); - bp = xdr_encode_u64(bp, 0); /* position of start of write */ + bp = xdr_encode_u64(bp, attr->ia_size); /* position of start of write */ bp = xdr_encode_u64(bp, 0); /* size of write */ bp = xdr_encode_u64(bp, attr->ia_size); /* new file length */ yfs_check_req(call, bp); @@ -181,7 +181,7 @@ struct poll_iocb { struct file *file; struct wait_queue_head *head; __poll_t events; - bool woken; + bool done; bool cancelled; struct wait_queue_entry wait; struct work_struct work; @@ -204,8 +204,7 @@ struct aio_kiocb { struct kioctx *ki_ctx; kiocb_cancel_fn *ki_cancel; - struct iocb __user *ki_user_iocb; /* user's aiocb */ - __u64 ki_user_data; /* user's data for completion */ + struct io_event ki_res; struct list_head ki_list; /* the aio core uses this * for cancellation */ @@ -1022,6 +1021,9 @@ static bool get_reqs_available(struct kioctx *ctx) /* aio_get_req * Allocate a slot for an aio request. * Returns NULL if no requests are free. + * + * The refcount is initialized to 2 - one for the async op completion, + * one for the synchronous code that does this. */ static inline struct aio_kiocb *aio_get_req(struct kioctx *ctx) { @@ -1034,7 +1036,7 @@ static inline struct aio_kiocb *aio_get_req(struct kioctx *ctx) percpu_ref_get(&ctx->reqs); req->ki_ctx = ctx; INIT_LIST_HEAD(&req->ki_list); - refcount_set(&req->ki_refcnt, 0); + refcount_set(&req->ki_refcnt, 2); req->ki_eventfd = NULL; return req; } @@ -1067,30 +1069,18 @@ out: return ret; } -static inline void iocb_put(struct aio_kiocb *iocb) +static inline void iocb_destroy(struct aio_kiocb *iocb) { - if (refcount_read(&iocb->ki_refcnt) == 0 || - refcount_dec_and_test(&iocb->ki_refcnt)) { - if (iocb->ki_filp) - fput(iocb->ki_filp); - percpu_ref_put(&iocb->ki_ctx->reqs); - kmem_cache_free(kiocb_cachep, iocb); - } -} - -static void aio_fill_event(struct io_event *ev, struct aio_kiocb *iocb, - long res, long res2) -{ - ev->obj = (u64)(unsigned long)iocb->ki_user_iocb; - ev->data = iocb->ki_user_data; - ev->res = res; - ev->res2 = res2; + if (iocb->ki_filp) + fput(iocb->ki_filp); + percpu_ref_put(&iocb->ki_ctx->reqs); + kmem_cache_free(kiocb_cachep, iocb); } /* aio_complete * Called when the io request on the given iocb is complete. */ -static void aio_complete(struct aio_kiocb *iocb, long res, long res2) +static void aio_complete(struct aio_kiocb *iocb) { struct kioctx *ctx = iocb->ki_ctx; struct aio_ring *ring; @@ -1114,14 +1104,14 @@ static void aio_complete(struct aio_kiocb *iocb, long res, long res2) ev_page = kmap_atomic(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]); event = ev_page + pos % AIO_EVENTS_PER_PAGE; - aio_fill_event(event, iocb, res, res2); + *event = iocb->ki_res; kunmap_atomic(ev_page); flush_dcache_page(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]); - pr_debug("%p[%u]: %p: %p %Lx %lx %lx\n", - ctx, tail, iocb, iocb->ki_user_iocb, iocb->ki_user_data, - res, res2); + pr_debug("%p[%u]: %p: %p %Lx %Lx %Lx\n", ctx, tail, iocb, + (void __user *)(unsigned long)iocb->ki_res.obj, + iocb->ki_res.data, iocb->ki_res.res, iocb->ki_res.res2); /* after flagging the request as done, we * must never even look at it again @@ -1163,7 +1153,14 @@ static void aio_complete(struct aio_kiocb *iocb, long res, long res2) if (waitqueue_active(&ctx->wait)) wake_up(&ctx->wait); - iocb_put(iocb); +} + +static inline void iocb_put(struct aio_kiocb *iocb) +{ + if (refcount_dec_and_test(&iocb->ki_refcnt)) { + aio_complete(iocb); + iocb_destroy(iocb); + } } /* aio_read_events_ring @@ -1437,7 +1434,9 @@ static void aio_complete_rw(struct kiocb *kiocb, long res, long res2) file_end_write(kiocb->ki_filp); } - aio_complete(iocb, res, res2); + iocb->ki_res.res = res; + iocb->ki_res.res2 = res2; + iocb_put(iocb); } static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb) @@ -1585,11 +1584,10 @@ static ssize_t aio_write(struct kiocb *req, const struct iocb *iocb, static void aio_fsync_work(struct work_struct *work) { - struct fsync_iocb *req = container_of(work, struct fsync_iocb, work); - int ret; + struct aio_kiocb *iocb = container_of(work, struct aio_kiocb, fsync.work); - ret = vfs_fsync(req->file, req->datasync); - aio_complete(container_of(req, struct aio_kiocb, fsync), ret, 0); + iocb->ki_res.res = vfs_fsync(iocb->fsync.file, iocb->fsync.datasync); + iocb_put(iocb); } static int aio_fsync(struct fsync_iocb *req, const struct iocb *iocb, @@ -1608,11 +1606,6 @@ static int aio_fsync(struct fsync_iocb *req, const struct iocb *iocb, return 0; } -static inline void aio_poll_complete(struct aio_kiocb *iocb, __poll_t mask) -{ - aio_complete(iocb, mangle_poll(mask), 0); -} - static void aio_poll_complete_work(struct work_struct *work) { struct poll_iocb *req = container_of(work, struct poll_iocb, work); @@ -1638,9 +1631,11 @@ static void aio_poll_complete_work(struct work_struct *work) return; } list_del_init(&iocb->ki_list); + iocb->ki_res.res = mangle_poll(mask); + req->done = true; spin_unlock_irq(&ctx->ctx_lock); - aio_poll_complete(iocb, mask); + iocb_put(iocb); } /* assumes we are called with irqs disabled */ @@ -1668,31 +1663,27 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, __poll_t mask = key_to_poll(key); unsigned long flags; - req->woken = true; - /* for instances that support it check for an event match first: */ - if (mask) { - if (!(mask & req->events)) - return 0; + if (mask && !(mask & req->events)) + return 0; + + list_del_init(&req->wait.entry); + if (mask && spin_trylock_irqsave(&iocb->ki_ctx->ctx_lock, flags)) { /* * 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. */ - if (spin_trylock_irqsave(&iocb->ki_ctx->ctx_lock, flags)) { - list_del(&iocb->ki_list); - spin_unlock_irqrestore(&iocb->ki_ctx->ctx_lock, flags); - - list_del_init(&req->wait.entry); - aio_poll_complete(iocb, mask); - return 1; - } + list_del(&iocb->ki_list); + iocb->ki_res.res = mangle_poll(mask); + req->done = true; + spin_unlock_irqrestore(&iocb->ki_ctx->ctx_lock, flags); + iocb_put(iocb); + } else { + schedule_work(&req->work); } - - list_del_init(&req->wait.entry); - schedule_work(&req->work); return 1; } @@ -1724,6 +1715,7 @@ static ssize_t aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb) struct kioctx *ctx = aiocb->ki_ctx; struct poll_iocb *req = &aiocb->poll; struct aio_poll_table apt; + bool cancel = false; __poll_t mask; /* reject any unknown events outside the normal event mask. */ @@ -1737,7 +1729,7 @@ 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->woken = false; + req->done = false; req->cancelled = false; apt.pt._qproc = aio_poll_queue_proc; @@ -1749,41 +1741,34 @@ static ssize_t aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb) INIT_LIST_HEAD(&req->wait.entry); init_waitqueue_func_entry(&req->wait, aio_poll_wake); - /* one for removal from waitqueue, one for this function */ - refcount_set(&aiocb->ki_refcnt, 2); - mask = vfs_poll(req->file, &apt.pt) & req->events; - if (unlikely(!req->head)) { - /* we did not manage to set up a waitqueue, done */ - goto out; - } - spin_lock_irq(&ctx->ctx_lock); - spin_lock(&req->head->lock); - if (req->woken) { - /* wake_up context handles the rest */ - mask = 0; + if (likely(req->head)) { + spin_lock(&req->head->lock); + if (unlikely(list_empty(&req->wait.entry))) { + if (apt.error) + cancel = true; + apt.error = 0; + mask = 0; + } + if (mask || apt.error) { + list_del_init(&req->wait.entry); + } else if (cancel) { + WRITE_ONCE(req->cancelled, true); + } else if (!req->done) { /* actually waiting for an event */ + list_add_tail(&aiocb->ki_list, &ctx->active_reqs); + aiocb->ki_cancel = aio_poll_cancel; + } + spin_unlock(&req->head->lock); + } + if (mask) { /* no async, we'd stolen it */ + aiocb->ki_res.res = mangle_poll(mask); apt.error = 0; - } else if (mask || apt.error) { - /* if we get an error or a mask we are done */ - WARN_ON_ONCE(list_empty(&req->wait.entry)); - list_del_init(&req->wait.entry); - } else { - /* actually waiting for an event */ - list_add_tail(&aiocb->ki_list, &ctx->active_reqs); - aiocb->ki_cancel = aio_poll_cancel; } - spin_unlock(&req->head->lock); spin_unlock_irq(&ctx->ctx_lock); - -out: - if (unlikely(apt.error)) - return apt.error; - if (mask) - aio_poll_complete(aiocb, mask); - iocb_put(aiocb); - return 0; + iocb_put(aiocb); + return apt.error; } static int __io_submit_one(struct kioctx *ctx, const struct iocb *iocb, @@ -1842,8 +1827,10 @@ static int __io_submit_one(struct kioctx *ctx, const struct iocb *iocb, goto out_put_req; } - req->ki_user_iocb = user_iocb; - req->ki_user_data = iocb->aio_data; + req->ki_res.obj = (u64)(unsigned long)user_iocb; + req->ki_res.data = iocb->aio_data; + req->ki_res.res = 0; + req->ki_res.res2 = 0; switch (iocb->aio_lio_opcode) { case IOCB_CMD_PREAD: @@ -1873,18 +1860,21 @@ static int __io_submit_one(struct kioctx *ctx, const struct iocb *iocb, break; } + /* Done with the synchronous reference */ + iocb_put(req); + /* * If ret is 0, we'd either done aio_complete() ourselves or have * arranged for that to be done asynchronously. Anything non-zero * means that we need to destroy req ourselves. */ - if (ret) - goto out_put_req; - return 0; + if (!ret) + return 0; + out_put_req: if (req->ki_eventfd) eventfd_ctx_put(req->ki_eventfd); - iocb_put(req); + iocb_destroy(req); out_put_reqs_available: put_reqs_available(ctx, 1); return ret; @@ -1997,24 +1987,6 @@ COMPAT_SYSCALL_DEFINE3(io_submit, compat_aio_context_t, ctx_id, } #endif -/* lookup_kiocb - * Finds a given iocb for cancellation. - */ -static struct aio_kiocb * -lookup_kiocb(struct kioctx *ctx, struct iocb __user *iocb) -{ - struct aio_kiocb *kiocb; - - assert_spin_locked(&ctx->ctx_lock); - - /* TODO: use a hash or array, this sucks. */ - list_for_each_entry(kiocb, &ctx->active_reqs, ki_list) { - if (kiocb->ki_user_iocb == iocb) - return kiocb; - } - return NULL; -} - /* sys_io_cancel: * Attempts to cancel an iocb previously passed to io_submit. If * the operation is successfully cancelled, the resulting event is @@ -2032,6 +2004,7 @@ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb, struct aio_kiocb *kiocb; int ret = -EINVAL; u32 key; + u64 obj = (u64)(unsigned long)iocb; if (unlikely(get_user(key, &iocb->aio_key))) return -EFAULT; @@ -2043,10 +2016,13 @@ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb, return -EINVAL; spin_lock_irq(&ctx->ctx_lock); - kiocb = lookup_kiocb(ctx, iocb); - if (kiocb) { - ret = kiocb->ki_cancel(&kiocb->rw); - list_del_init(&kiocb->ki_list); + /* TODO: use a hash or array, this sucks. */ + list_for_each_entry(kiocb, &ctx->active_reqs, ki_list) { + if (kiocb->ki_res.obj == obj) { + ret = kiocb->ki_cancel(&kiocb->rw); + list_del_init(&kiocb->ki_list); + break; + } } spin_unlock_irq(&ctx->ctx_lock); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 4ec2b660d014..7f3ece91a4d0 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1886,8 +1886,10 @@ static void btrfs_cleanup_pending_block_groups(struct btrfs_trans_handle *trans) } } -static inline int btrfs_start_delalloc_flush(struct btrfs_fs_info *fs_info) +static inline int btrfs_start_delalloc_flush(struct btrfs_trans_handle *trans) { + struct btrfs_fs_info *fs_info = trans->fs_info; + /* * We use writeback_inodes_sb here because if we used * btrfs_start_delalloc_roots we would deadlock with fs freeze. @@ -1897,15 +1899,50 @@ static inline int btrfs_start_delalloc_flush(struct btrfs_fs_info *fs_info) * from already being in a transaction and our join_transaction doesn't * have to re-take the fs freeze lock. */ - if (btrfs_test_opt(fs_info, FLUSHONCOMMIT)) + if (btrfs_test_opt(fs_info, FLUSHONCOMMIT)) { writeback_inodes_sb(fs_info->sb, WB_REASON_SYNC); + } else { + struct btrfs_pending_snapshot *pending; + struct list_head *head = &trans->transaction->pending_snapshots; + + /* + * Flush dellaloc for any root that is going to be snapshotted. + * This is done to avoid a corrupted version of files, in the + * snapshots, that had both buffered and direct IO writes (even + * if they were done sequentially) due to an unordered update of + * the inode's size on disk. + */ + list_for_each_entry(pending, head, list) { + int ret; + + ret = btrfs_start_delalloc_snapshot(pending->root); + if (ret) + return ret; + } + } return 0; } -static inline void btrfs_wait_delalloc_flush(struct btrfs_fs_info *fs_info) +static inline void btrfs_wait_delalloc_flush(struct btrfs_trans_handle *trans) { - if (btrfs_test_opt(fs_info, FLUSHONCOMMIT)) + struct btrfs_fs_info *fs_info = trans->fs_info; + + if (btrfs_test_opt(fs_info, FLUSHONCOMMIT)) { btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1); + } else { + struct btrfs_pending_snapshot *pending; + struct list_head *head = &trans->transaction->pending_snapshots; + + /* + * Wait for any dellaloc that we started previously for the roots + * that are going to be snapshotted. This is to avoid a corrupted + * version of files in the snapshots that had both buffered and + * direct IO writes (even if they were done sequentially). + */ + list_for_each_entry(pending, head, list) + btrfs_wait_ordered_extents(pending->root, + U64_MAX, 0, U64_MAX); + } } int btrfs_commit_transaction(struct btrfs_trans_handle *trans) @@ -2024,7 +2061,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) extwriter_counter_dec(cur_trans, trans->type); - ret = btrfs_start_delalloc_flush(fs_info); + ret = btrfs_start_delalloc_flush(trans); if (ret) goto cleanup_transaction; @@ -2040,7 +2077,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) if (ret) goto cleanup_transaction; - btrfs_wait_delalloc_flush(fs_info); + btrfs_wait_delalloc_flush(trans); btrfs_scrub_pause(fs_info); /* diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 82928cea0209..7f3f64ba464f 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -1470,6 +1470,7 @@ void ceph_dentry_lru_del(struct dentry *dn) unsigned ceph_dentry_hash(struct inode *dir, struct dentry *dn) { struct ceph_inode_info *dci = ceph_inode(dir); + unsigned hash; switch (dci->i_dir_layout.dl_dir_hash) { case 0: /* for backward compat */ @@ -1477,8 +1478,11 @@ unsigned ceph_dentry_hash(struct inode *dir, struct dentry *dn) return dn->d_name.hash; default: - return ceph_str_hash(dci->i_dir_layout.dl_dir_hash, + spin_lock(&dn->d_lock); + hash = ceph_str_hash(dci->i_dir_layout.dl_dir_hash, dn->d_name.name, dn->d_name.len); + spin_unlock(&dn->d_lock); + return hash; } } diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 9d1f34d46627..fd3db2e112d6 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -524,6 +524,7 @@ static void ceph_i_callback(struct rcu_head *head) struct inode *inode = container_of(head, struct inode, i_rcu); struct ceph_inode_info *ci = ceph_inode(inode); + kfree(ci->i_symlink); kmem_cache_free(ceph_inode_cachep, ci); } @@ -561,7 +562,6 @@ void ceph_destroy_inode(struct inode *inode) ceph_put_snap_realm(mdsc, realm); } - kfree(ci->i_symlink); while ((n = rb_first(&ci->i_fragtree)) != NULL) { frag = rb_entry(n, struct ceph_inode_frag, node); rb_erase(n, &ci->i_fragtree); @@ -1152,6 +1152,19 @@ static int splice_dentry(struct dentry **pdn, struct inode *in) return 0; } +static int d_name_cmp(struct dentry *dentry, const char *name, size_t len) +{ + int ret; + + /* take d_lock to ensure dentry->d_name stability */ + spin_lock(&dentry->d_lock); + ret = dentry->d_name.len - len; + if (!ret) + ret = memcmp(dentry->d_name.name, name, len); + spin_unlock(&dentry->d_lock); + return ret; +} + /* * Incorporate results into the local cache. This is either just * one inode, or a directory, dentry, and possibly linked-to inode (e.g., @@ -1401,7 +1414,8 @@ retry_lookup: err = splice_dentry(&req->r_dentry, in); if (err < 0) goto done; - } else if (rinfo->head->is_dentry) { + } else if (rinfo->head->is_dentry && + !d_name_cmp(req->r_dentry, rinfo->dname, rinfo->dname_len)) { struct ceph_vino *ptvino = NULL; if ((le32_to_cpu(rinfo->diri.in->cap.caps) & CEPH_CAP_FILE_SHARED) || diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 163fc74bf221..5cec784e30f6 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -1286,6 +1286,15 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap, list_add(&ci->i_prealloc_cap_flush->i_list, &to_remove); ci->i_prealloc_cap_flush = NULL; } + + if (drop && + ci->i_wrbuffer_ref_head == 0 && + ci->i_wr_ref == 0 && + ci->i_dirty_caps == 0 && + ci->i_flushing_caps == 0) { + ceph_put_snap_context(ci->i_head_snapc); + ci->i_head_snapc = NULL; + } } spin_unlock(&ci->i_ceph_lock); while (!list_empty(&to_remove)) { @@ -1958,10 +1967,39 @@ retry: return path; } +/* Duplicate the dentry->d_name.name safely */ +static int clone_dentry_name(struct dentry *dentry, const char **ppath, + int *ppathlen) +{ + u32 len; + char *name; + +retry: + len = READ_ONCE(dentry->d_name.len); + name = kmalloc(len + 1, GFP_NOFS); + if (!name) + return -ENOMEM; + + spin_lock(&dentry->d_lock); + if (dentry->d_name.len != len) { + spin_unlock(&dentry->d_lock); + kfree(name); + goto retry; + } + memcpy(name, dentry->d_name.name, len); + spin_unlock(&dentry->d_lock); + + name[len] = '\0'; + *ppath = name; + *ppathlen = len; + return 0; +} + static int build_dentry_path(struct dentry *dentry, struct inode *dir, const char **ppath, int *ppathlen, u64 *pino, - int *pfreepath) + bool *pfreepath, bool parent_locked) { + int ret; char *path; rcu_read_lock(); @@ -1970,8 +2008,15 @@ static int build_dentry_path(struct dentry *dentry, struct inode *dir, if (dir && ceph_snap(dir) == CEPH_NOSNAP) { *pino = ceph_ino(dir); rcu_read_unlock(); - *ppath = dentry->d_name.name; - *ppathlen = dentry->d_name.len; + if (parent_locked) { + *ppath = dentry->d_name.name; + *ppathlen = dentry->d_name.len; + } else { + ret = clone_dentry_name(dentry, ppath, ppathlen); + if (ret) + return ret; + *pfreepath = true; + } return 0; } rcu_read_unlock(); @@ -1979,13 +2024,13 @@ static int build_dentry_path(struct dentry *dentry, struct inode *dir, if (IS_ERR(path)) return PTR_ERR(path); *ppath = path; - *pfreepath = 1; + *pfreepath = true; return 0; } static int build_inode_path(struct inode *inode, const char **ppath, int *ppathlen, u64 *pino, - int *pfreepath) + bool *pfreepath) { struct dentry *dentry; char *path; @@ -2001,7 +2046,7 @@ static int build_inode_path(struct inode *inode, if (IS_ERR(path)) return PTR_ERR(path); *ppath = path; - *pfreepath = 1; + *pfreepath = true; return 0; } @@ -2012,7 +2057,7 @@ static int build_inode_path(struct inode *inode, static int set_request_path_attr(struct inode *rinode, struct dentry *rdentry, struct inode *rdiri, const char *rpath, u64 rino, const char **ppath, int *pathlen, - u64 *ino, int *freepath) + u64 *ino, bool *freepath, bool parent_locked) { int r = 0; @@ -2022,7 +2067,7 @@ static int set_request_path_attr(struct inode *rinode, struct dentry *rdentry, ceph_snap(rinode)); } else if (rdentry) { r = build_dentry_path(rdentry, rdiri, ppath, pathlen, ino, - freepath); + freepath, parent_locked); dout(" dentry %p %llx/%.*s\n", rdentry, *ino, *pathlen, *ppath); } else if (rpath || rino) { @@ -2048,7 +2093,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc, const char *path2 = NULL; u64 ino1 = 0, ino2 = 0; int pathlen1 = 0, pathlen2 = 0; - int freepath1 = 0, freepath2 = 0; + bool freepath1 = false, freepath2 = false; int len; u16 releases; void *p, *end; @@ -2056,16 +2101,19 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc, ret = set_request_path_attr(req->r_inode, req->r_dentry, req->r_parent, req->r_path1, req->r_ino1.ino, - &path1, &pathlen1, &ino1, &freepath1); + &path1, &pathlen1, &ino1, &freepath1, + test_bit(CEPH_MDS_R_PARENT_LOCKED, + &req->r_req_flags)); if (ret < 0) { msg = ERR_PTR(ret); goto out; } + /* If r_old_dentry is set, then assume that its parent is locked */ ret = set_request_path_attr(NULL, req->r_old_dentry, req->r_old_dentry_dir, req->r_path2, req->r_ino2.ino, - &path2, &pathlen2, &ino2, &freepath2); + &path2, &pathlen2, &ino2, &freepath2, true); if (ret < 0) { msg = ERR_PTR(ret); goto out_free1; diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index f74193da0e09..1f46b02f7314 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -568,7 +568,12 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci) old_snapc = NULL; update_snapc: - if (ci->i_head_snapc) { + if (ci->i_wrbuffer_ref_head == 0 && + ci->i_wr_ref == 0 && + ci->i_dirty_caps == 0 && + ci->i_flushing_caps == 0) { + ci->i_head_snapc = NULL; + } else { ci->i_head_snapc = ceph_get_snap_context(new_snapc); dout(" new snapc is %p\n", new_snapc); } diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 07cad54b84f1..e8e125acd712 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -1010,7 +1010,7 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off, unsigned int xid; int rc; - if (remap_flags & ~REMAP_FILE_ADVISORY) + if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY)) return -EINVAL; cifs_dbg(FYI, "clone range\n"); diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 6c934ab3722b..10ead04346ee 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -1303,6 +1303,7 @@ cifsFileInfo_get_locked(struct cifsFileInfo *cifs_file) } struct cifsFileInfo *cifsFileInfo_get(struct cifsFileInfo *cifs_file); +void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_hdlr); void cifsFileInfo_put(struct cifsFileInfo *cifs_file); #define CIFS_CACHE_READ_FLG 1 @@ -1824,6 +1825,7 @@ GLOBAL_EXTERN spinlock_t gidsidlock; #endif /* CONFIG_CIFS_ACL */ void cifs_oplock_break(struct work_struct *work); +void cifs_queue_oplock_break(struct cifsFileInfo *cfile); extern const struct slow_work_ops cifs_oplock_break_ops; extern struct workqueue_struct *cifsiod_wq; diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 8d107587208f..7c3f9d00586e 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -360,13 +360,31 @@ cifsFileInfo_get(struct cifsFileInfo *cifs_file) return cifs_file; } -/* - * Release a reference on the file private data. This may involve closing - * the filehandle out on the server. Must be called without holding - * tcon->open_file_lock and cifs_file->file_info_lock. +/** + * cifsFileInfo_put - release a reference of file priv data + * + * Always potentially wait for oplock handler. See _cifsFileInfo_put(). */ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) { + _cifsFileInfo_put(cifs_file, true); +} + +/** + * _cifsFileInfo_put - release a reference of file priv data + * + * This may involve closing the filehandle @cifs_file out on the + * server. Must be called without holding tcon->open_file_lock and + * cifs_file->file_info_lock. + * + * If @wait_for_oplock_handler is true and we are releasing the last + * reference, wait for any running oplock break handler of the file + * and cancel any pending one. If calling this function from the + * oplock break handler, you need to pass false. + * + */ +void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_handler) +{ struct inode *inode = d_inode(cifs_file->dentry); struct cifs_tcon *tcon = tlink_tcon(cifs_file->tlink); struct TCP_Server_Info *server = tcon->ses->server; @@ -414,7 +432,8 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) spin_unlock(&tcon->open_file_lock); - oplock_break_cancelled = cancel_work_sync(&cifs_file->oplock_break); + oplock_break_cancelled = wait_oplock_handler ? + cancel_work_sync(&cifs_file->oplock_break) : false; if (!tcon->need_reconnect && !cifs_file->invalidHandle) { struct TCP_Server_Info *server = tcon->ses->server; @@ -2777,7 +2796,6 @@ static void collect_uncached_write_data(struct cifs_aio_ctx *ctx) struct cifs_tcon *tcon; struct cifs_sb_info *cifs_sb; struct dentry *dentry = ctx->cfile->dentry; - unsigned int i; int rc; tcon = tlink_tcon(ctx->cfile->tlink); @@ -2841,10 +2859,6 @@ restart_loop: kref_put(&wdata->refcount, cifs_uncached_writedata_release); } - if (!ctx->direct_io) - for (i = 0; i < ctx->npages; i++) - put_page(ctx->bv[i].bv_page); - cifs_stats_bytes_written(tcon, ctx->total_len); set_bit(CIFS_INO_INVALID_MAPPING, &CIFS_I(dentry->d_inode)->flags); @@ -3453,7 +3467,6 @@ collect_uncached_read_data(struct cifs_aio_ctx *ctx) struct iov_iter *to = &ctx->iter; struct cifs_sb_info *cifs_sb; struct cifs_tcon *tcon; - unsigned int i; int rc; tcon = tlink_tcon(ctx->cfile->tlink); @@ -3537,15 +3550,8 @@ again: kref_put(&rdata->refcount, cifs_uncached_readdata_release); } - if (!ctx->direct_io) { - for (i = 0; i < ctx->npages; i++) { - if (ctx->should_dirty) - set_page_dirty(ctx->bv[i].bv_page); - put_page(ctx->bv[i].bv_page); - } - + if (!ctx->direct_io) ctx->total_len = ctx->len - iov_iter_count(to); - } cifs_stats_bytes_read(tcon, ctx->total_len); @@ -4480,6 +4486,7 @@ void cifs_oplock_break(struct work_struct *work) cinode); cifs_dbg(FYI, "Oplock release rc = %d\n", rc); } + _cifsFileInfo_put(cfile, false /* do not wait for ourself */); cifs_done_oplock_break(cinode); } diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 53fdb5df0d2e..538fd7d807e4 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -1735,6 +1735,10 @@ cifs_do_rename(const unsigned int xid, struct dentry *from_dentry, if (rc == 0 || rc != -EBUSY) goto do_rename_exit; + /* Don't fall back to using SMB on SMB 2+ mount */ + if (server->vals->protocol_id != 0) + goto do_rename_exit; + /* open-file renames don't work across directories */ if (to_dentry->d_parent != from_dentry->d_parent) goto do_rename_exit; diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index bee203055b30..0dc6f08020ac 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -501,8 +501,7 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv) CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, &pCifsInode->flags); - queue_work(cifsoplockd_wq, - &netfile->oplock_break); + cifs_queue_oplock_break(netfile); netfile->oplock_break_cancelled = false; spin_unlock(&tcon->open_file_lock); @@ -607,6 +606,28 @@ void cifs_put_writer(struct cifsInodeInfo *cinode) spin_unlock(&cinode->writers_lock); } +/** + * cifs_queue_oplock_break - queue the oplock break handler for cfile + * + * This function is called from the demultiplex thread when it + * receives an oplock break for @cfile. + * + * Assumes the tcon->open_file_lock is held. + * Assumes cfile->file_info_lock is NOT held. + */ +void cifs_queue_oplock_break(struct cifsFileInfo *cfile) +{ + /* + * Bump the handle refcount now while we hold the + * open_file_lock to enforce the validity of it for the oplock + * break handler. The matching put is done at the end of the + * handler. + */ + cifsFileInfo_get(cfile); + + queue_work(cifsoplockd_wq, &cfile->oplock_break); +} + void cifs_done_oplock_break(struct cifsInodeInfo *cinode) { clear_bit(CIFS_INODE_PENDING_OPLOCK_BREAK, &cinode->flags); @@ -768,6 +789,11 @@ cifs_aio_ctx_alloc(void) { struct cifs_aio_ctx *ctx; + /* + * Must use kzalloc to initialize ctx->bv to NULL and ctx->direct_io + * to false so that we know when we have to unreference pages within + * cifs_aio_ctx_release() + */ ctx = kzalloc(sizeof(struct cifs_aio_ctx), GFP_KERNEL); if (!ctx) return NULL; @@ -786,7 +812,23 @@ cifs_aio_ctx_release(struct kref *refcount) struct cifs_aio_ctx, refcount); cifsFileInfo_put(ctx->cfile); - kvfree(ctx->bv); + + /* + * ctx->bv is only set if setup_aio_ctx_iter() was call successfuly + * which means that iov_iter_get_pages() was a success and thus that + * we have taken reference on pages. + */ + if (ctx->bv) { + unsigned i; + + for (i = 0; i < ctx->npages; i++) { + if (ctx->should_dirty) + set_page_dirty(ctx->bv[i].bv_page); + put_page(ctx->bv[i].bv_page); + } + kvfree(ctx->bv); + } + kfree(ctx); } diff --git a/fs/cifs/smb2maperror.c b/fs/cifs/smb2maperror.c index 924269cec135..e32c264e3adb 100644 --- a/fs/cifs/smb2maperror.c +++ b/fs/cifs/smb2maperror.c @@ -1036,7 +1036,8 @@ static const struct status_to_posix_error smb2_error_map_table[] = { {STATUS_UNFINISHED_CONTEXT_DELETED, -EIO, "STATUS_UNFINISHED_CONTEXT_DELETED"}, {STATUS_NO_TGT_REPLY, -EIO, "STATUS_NO_TGT_REPLY"}, - {STATUS_OBJECTID_NOT_FOUND, -EIO, "STATUS_OBJECTID_NOT_FOUND"}, + /* Note that ENOATTTR and ENODATA are the same errno */ + {STATUS_OBJECTID_NOT_FOUND, -ENODATA, "STATUS_OBJECTID_NOT_FOUND"}, {STATUS_NO_IP_ADDRESSES, -EIO, "STATUS_NO_IP_ADDRESSES"}, {STATUS_WRONG_CREDENTIAL_HANDLE, -EIO, "STATUS_WRONG_CREDENTIAL_HANDLE"}, diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index 58700d2ba8cd..0a7ed2e3ad4f 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -555,7 +555,7 @@ smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp, clear_bit(CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, &cinode->flags); - queue_work(cifsoplockd_wq, &cfile->oplock_break); + cifs_queue_oplock_break(cfile); kfree(lw); return true; } @@ -719,8 +719,8 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server) CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, &cinode->flags); spin_unlock(&cfile->file_info_lock); - queue_work(cifsoplockd_wq, - &cfile->oplock_break); + + cifs_queue_oplock_break(cfile); spin_unlock(&tcon->open_file_lock); spin_unlock(&cifs_tcp_ses_lock); diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index b29f711ab965..d5434ac0571b 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -949,6 +949,16 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon, resp_buftype[0] = resp_buftype[1] = resp_buftype[2] = CIFS_NO_BUFFER; memset(rsp_iov, 0, sizeof(rsp_iov)); + if (ses->server->ops->query_all_EAs) { + if (!ea_value) { + rc = ses->server->ops->query_all_EAs(xid, tcon, path, + ea_name, NULL, 0, + cifs_sb); + if (rc == -ENODATA) + goto sea_exit; + } + } + /* Open */ memset(&open_iov, 0, sizeof(open_iov)); rqst[0].rq_iov = open_iov; @@ -2200,6 +2210,8 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon, rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, &err_iov, &resp_buftype); + if (!rc) + SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid); if (!rc || !err_iov.iov_base) { rc = -ENOENT; goto free_path; diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 068febe37fe4..85a3c051e622 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -815,8 +815,11 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses) } else if (rsp->DialectRevision == cpu_to_le16(SMB21_PROT_ID)) { /* ops set to 3.0 by default for default so update */ ses->server->ops = &smb21_operations; - } else if (rsp->DialectRevision == cpu_to_le16(SMB311_PROT_ID)) + ses->server->vals = &smb21_values; + } else if (rsp->DialectRevision == cpu_to_le16(SMB311_PROT_ID)) { ses->server->ops = &smb311_operations; + ses->server->vals = &smb311_values; + } } else if (le16_to_cpu(rsp->DialectRevision) != ses->server->vals->protocol_id) { /* if requested single dialect ensure returned dialect matched */ @@ -3387,8 +3390,6 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms, rqst.rq_nvec = 1; rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov); - cifs_small_buf_release(req); - rsp = (struct smb2_read_rsp *)rsp_iov.iov_base; if (rc) { @@ -3401,12 +3402,15 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms, rc); } free_rsp_buf(resp_buftype, rsp_iov.iov_base); + cifs_small_buf_release(req); return rc == -ENODATA ? 0 : rc; } else trace_smb3_read_done(xid, req->PersistentFileId, io_parms->tcon->tid, ses->Suid, io_parms->offset, io_parms->length); + cifs_small_buf_release(req); + *nbytes = le32_to_cpu(rsp->DataLength); if ((*nbytes > CIFS_MAX_MSGSIZE) || (*nbytes > io_parms->length)) { @@ -3705,7 +3709,6 @@ SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms, rc = cifs_send_recv(xid, io_parms->tcon->ses, &rqst, &resp_buftype, flags, &rsp_iov); - cifs_small_buf_release(req); rsp = (struct smb2_write_rsp *)rsp_iov.iov_base; if (rc) { @@ -3723,6 +3726,7 @@ SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms, io_parms->offset, *nbytes); } + cifs_small_buf_release(req); free_rsp_buf(resp_buftype, rsp); return rc; } diff --git a/fs/cifs/trace.h b/fs/cifs/trace.h index 59be48206932..b49bc925fb4f 100644 --- a/fs/cifs/trace.h +++ b/fs/cifs/trace.h @@ -378,19 +378,19 @@ DECLARE_EVENT_CLASS(smb3_tcon_class, __field(unsigned int, xid) __field(__u32, tid) __field(__u64, sesid) - __field(const char *, unc_name) + __string(name, unc_name) __field(int, rc) ), TP_fast_assign( __entry->xid = xid; __entry->tid = tid; __entry->sesid = sesid; - __entry->unc_name = unc_name; + __assign_str(name, unc_name); __entry->rc = rc; ), TP_printk("xid=%u sid=0x%llx tid=0x%x unc_name=%s rc=%d", __entry->xid, __entry->sesid, __entry->tid, - __entry->unc_name, __entry->rc) + __get_str(name), __entry->rc) ) #define DEFINE_SMB3_TCON_EVENT(name) \ @@ -33,6 +33,7 @@ #include <linux/sizes.h> #include <linux/mmu_notifier.h> #include <linux/iomap.h> +#include <asm/pgalloc.h> #include "internal.h" #define CREATE_TRACE_POINTS @@ -1409,7 +1410,9 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf, { struct address_space *mapping = vmf->vma->vm_file->f_mapping; unsigned long pmd_addr = vmf->address & PMD_MASK; + struct vm_area_struct *vma = vmf->vma; struct inode *inode = mapping->host; + pgtable_t pgtable = NULL; struct page *zero_page; spinlock_t *ptl; pmd_t pmd_entry; @@ -1424,12 +1427,22 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf, *entry = dax_insert_entry(xas, mapping, vmf, *entry, pfn, DAX_PMD | DAX_ZERO_PAGE, false); + if (arch_needs_pgtable_deposit()) { + pgtable = pte_alloc_one(vma->vm_mm); + if (!pgtable) + return VM_FAULT_OOM; + } + ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd); if (!pmd_none(*(vmf->pmd))) { spin_unlock(ptl); goto fallback; } + if (pgtable) { + pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable); + mm_inc_nr_ptes(vma->vm_mm); + } pmd_entry = mk_pmd(zero_page, vmf->vma->vm_page_prot); pmd_entry = pmd_mkhuge(pmd_entry); set_pmd_at(vmf->vma->vm_mm, pmd_addr, vmf->pmd, pmd_entry); @@ -1438,6 +1451,8 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf, return VM_FAULT_NOPAGE; fallback: + if (pgtable) + pte_free(vma->vm_mm, pgtable); trace_dax_pmd_load_hole_fallback(inode, vmf, zero_page, *entry); return VM_FAULT_FALLBACK; } diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 29c68c5d44d5..c4a4fc6f1a95 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -163,19 +163,24 @@ static int debugfs_show_options(struct seq_file *m, struct dentry *root) return 0; } -static void debugfs_evict_inode(struct inode *inode) +static void debugfs_i_callback(struct rcu_head *head) { - truncate_inode_pages_final(&inode->i_data); - clear_inode(inode); + struct inode *inode = container_of(head, struct inode, i_rcu); if (S_ISLNK(inode->i_mode)) kfree(inode->i_link); + free_inode_nonrcu(inode); +} + +static void debugfs_destroy_inode(struct inode *inode) +{ + call_rcu(&inode->i_rcu, debugfs_i_callback); } static const struct super_operations debugfs_super_operations = { .statfs = simple_statfs, .remount_fs = debugfs_remount, .show_options = debugfs_show_options, - .evict_inode = debugfs_evict_inode, + .destroy_inode = debugfs_destroy_inode, }; static void debugfs_release_dentry(struct dentry *dentry) diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 2e76fb55d94a..5f24fdc140ad 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -999,6 +999,13 @@ resizefs_out: if (!blk_queue_discard(q)) return -EOPNOTSUPP; + /* + * We haven't replayed the journal, so we cannot use our + * block-bitmap-guided storage zapping commands. + */ + if (test_opt(sb, NOLOAD) && ext4_has_feature_journal(sb)) + return -EROFS; + if (copy_from_user(&range, (struct fstrim_range __user *)arg, sizeof(range))) return -EFAULT; diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 3d9b18505c0c..e7ae26e36c9c 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -932,11 +932,18 @@ static int add_new_gdb_meta_bg(struct super_block *sb, memcpy(n_group_desc, o_group_desc, EXT4_SB(sb)->s_gdb_count * sizeof(struct buffer_head *)); n_group_desc[gdb_num] = gdb_bh; + + BUFFER_TRACE(gdb_bh, "get_write_access"); + err = ext4_journal_get_write_access(handle, gdb_bh); + if (err) { + kvfree(n_group_desc); + brelse(gdb_bh); + return err; + } + EXT4_SB(sb)->s_group_desc = n_group_desc; EXT4_SB(sb)->s_gdb_count++; kvfree(o_group_desc); - BUFFER_TRACE(gdb_bh, "get_write_access"); - err = ext4_journal_get_write_access(handle, gdb_bh); return err; } @@ -2073,6 +2080,10 @@ out: free_flex_gd(flex_gd); if (resize_inode != NULL) iput(resize_inode); - ext4_msg(sb, KERN_INFO, "resized filesystem to %llu", n_blocks_count); + if (err) + ext4_warning(sb, "error (%d) occurred during " + "file system resize", err); + ext4_msg(sb, KERN_INFO, "resized filesystem to %llu", + ext4_blocks_count(es)); return err; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index fb12d3c17c1b..b9bca7298f96 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -430,6 +430,12 @@ static void ext4_journal_commit_callback(journal_t *journal, transaction_t *txn) spin_unlock(&sbi->s_md_lock); } +static bool system_going_down(void) +{ + return system_state == SYSTEM_HALT || system_state == SYSTEM_POWER_OFF + || system_state == SYSTEM_RESTART; +} + /* Deal with the reporting of failure conditions on a filesystem such as * inconsistencies detected or read IO failures. * @@ -460,7 +466,12 @@ static void ext4_handle_error(struct super_block *sb) if (journal) jbd2_journal_abort(journal, -EIO); } - if (test_opt(sb, ERRORS_RO)) { + /* + * We force ERRORS_RO behavior when system is rebooting. Otherwise we + * could panic during 'reboot -f' as the underlying device got already + * disabled. + */ + if (test_opt(sb, ERRORS_RO) || system_going_down()) { ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only"); /* * Make sure updated value of ->s_mount_flags will be visible @@ -468,8 +479,7 @@ static void ext4_handle_error(struct super_block *sb) */ smp_wmb(); sb->s_flags |= SB_RDONLY; - } - if (test_opt(sb, ERRORS_PANIC)) { + } else if (test_opt(sb, ERRORS_PANIC)) { if (EXT4_SB(sb)->s_journal && !(EXT4_SB(sb)->s_journal->j_flags & JBD2_REC_ERR)) return; diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 86ed9c686249..dc82e7757f67 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -829,6 +829,7 @@ int ext4_get_inode_usage(struct inode *inode, qsize_t *usage) bh = ext4_sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl, REQ_PRIO); if (IS_ERR(bh)) { ret = PTR_ERR(bh); + bh = NULL; goto out; } @@ -2903,6 +2904,7 @@ int ext4_xattr_delete_inode(handle_t *handle, struct inode *inode, if (error == -EIO) EXT4_ERROR_INODE(inode, "block %llu read error", EXT4_I(inode)->i_file_acl); + bh = NULL; goto cleanup; } error = ext4_xattr_check_block(inode, bh); @@ -3059,6 +3061,7 @@ ext4_xattr_block_cache_find(struct inode *inode, if (IS_ERR(bh)) { if (PTR_ERR(bh) == -ENOMEM) return NULL; + bh = NULL; EXT4_ERROR_INODE(inode, "block %lu read error", (unsigned long)ce->e_value); } else if (ext4_xattr_cmp(header, BHDR(bh)) == 0) { diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index f955cd3e0677..7743fa83b895 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -306,8 +306,9 @@ static int f2fs_write_meta_pages(struct address_space *mapping, goto skip_write; /* collect a number of dirty meta pages and write together */ - if (wbc->for_kupdate || - get_pages(sbi, F2FS_DIRTY_META) < nr_pages_to_skip(sbi, META)) + if (wbc->sync_mode != WB_SYNC_ALL && + get_pages(sbi, F2FS_DIRTY_META) < + nr_pages_to_skip(sbi, META)) goto skip_write; /* if locked failed, cp will flush dirty pages instead */ @@ -405,7 +406,7 @@ static int f2fs_set_meta_page_dirty(struct page *page) if (!PageDirty(page)) { __set_page_dirty_nobuffers(page); inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_META); - SetPagePrivate(page); + f2fs_set_page_private(page, 0); f2fs_trace_pid(page); return 1; } @@ -956,7 +957,7 @@ void f2fs_update_dirty_page(struct inode *inode, struct page *page) inode_inc_dirty_pages(inode); spin_unlock(&sbi->inode_lock[type]); - SetPagePrivate(page); + f2fs_set_page_private(page, 0); f2fs_trace_pid(page); } diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index f91d8630c9a2..6e598dd85fb5 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -218,12 +218,14 @@ struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi, struct block_device *bdev = sbi->sb->s_bdev; int i; - for (i = 0; i < sbi->s_ndevs; i++) { - if (FDEV(i).start_blk <= blk_addr && - FDEV(i).end_blk >= blk_addr) { - blk_addr -= FDEV(i).start_blk; - bdev = FDEV(i).bdev; - break; + if (f2fs_is_multi_device(sbi)) { + for (i = 0; i < sbi->s_ndevs; i++) { + if (FDEV(i).start_blk <= blk_addr && + FDEV(i).end_blk >= blk_addr) { + blk_addr -= FDEV(i).start_blk; + bdev = FDEV(i).bdev; + break; + } } } if (bio) { @@ -237,6 +239,9 @@ int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr) { int i; + if (!f2fs_is_multi_device(sbi)) + return 0; + for (i = 0; i < sbi->s_ndevs; i++) if (FDEV(i).start_blk <= blkaddr && FDEV(i).end_blk >= blkaddr) return i; @@ -2711,8 +2716,7 @@ void f2fs_invalidate_page(struct page *page, unsigned int offset, if (IS_ATOMIC_WRITTEN_PAGE(page)) return f2fs_drop_inmem_page(inode, page); - set_page_private(page, 0); - ClearPagePrivate(page); + f2fs_clear_page_private(page); } int f2fs_release_page(struct page *page, gfp_t wait) @@ -2726,8 +2730,7 @@ int f2fs_release_page(struct page *page, gfp_t wait) return 0; clear_cold_data(page); - set_page_private(page, 0); - ClearPagePrivate(page); + f2fs_clear_page_private(page); return 1; } @@ -2795,12 +2798,8 @@ int f2fs_migrate_page(struct address_space *mapping, return -EAGAIN; } - /* - * A reference is expected if PagePrivate set when move mapping, - * however F2FS breaks this for maintaining dirty page counts when - * truncating pages. So here adjusting the 'extra_count' make it work. - */ - extra_count = (atomic_written ? 1 : 0) - page_has_private(page); + /* one extra reference was held for atomic_write page */ + extra_count = atomic_written ? 1 : 0; rc = migrate_page_move_mapping(mapping, newpage, page, mode, extra_count); if (rc != MIGRATEPAGE_SUCCESS) { @@ -2821,9 +2820,10 @@ int f2fs_migrate_page(struct address_space *mapping, get_page(newpage); } - if (PagePrivate(page)) - SetPagePrivate(newpage); - set_page_private(newpage, page_private(page)); + if (PagePrivate(page)) { + f2fs_set_page_private(newpage, page_private(page)); + f2fs_clear_page_private(page); + } if (mode != MIGRATE_SYNC_NO_COPY) migrate_page_copy(newpage, page); diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index 50d0d36280fa..99a6063c2327 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -728,7 +728,7 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page, !f2fs_truncate_hole(dir, page->index, page->index + 1)) { f2fs_clear_page_cache_dirty_tag(page); clear_page_dirty_for_io(page); - ClearPagePrivate(page); + f2fs_clear_page_private(page); ClearPageUptodate(page); clear_cold_data(page); inode_dec_dirty_pages(dir); diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 279bc00489cc..48f1bbf3e87e 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1364,6 +1364,17 @@ static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type) } #endif +/* + * Test if the mounted volume is a multi-device volume. + * - For a single regular disk volume, sbi->s_ndevs is 0. + * - For a single zoned disk volume, sbi->s_ndevs is 1. + * - For a multi-device volume, sbi->s_ndevs is always 2 or more. + */ +static inline bool f2fs_is_multi_device(struct f2fs_sb_info *sbi) +{ + return sbi->s_ndevs > 1; +} + /* For write statistics. Suppose sector size is 512 bytes, * and the return value is in kbytes. s is of struct f2fs_sb_info. */ @@ -2825,6 +2836,27 @@ static inline bool is_valid_data_blkaddr(struct f2fs_sb_info *sbi, return true; } +static inline void f2fs_set_page_private(struct page *page, + unsigned long data) +{ + if (PagePrivate(page)) + return; + + get_page(page); + SetPagePrivate(page); + set_page_private(page, data); +} + +static inline void f2fs_clear_page_private(struct page *page) +{ + if (!PagePrivate(page)) + return; + + set_page_private(page, 0); + ClearPagePrivate(page); + f2fs_put_page(page, 0); +} + /* * file.c */ @@ -3591,7 +3623,7 @@ static inline bool f2fs_force_buffered_io(struct inode *inode, if (f2fs_post_read_required(inode)) return true; - if (sbi->s_ndevs) + if (f2fs_is_multi_device(sbi)) return true; /* * for blkzoned device, fallback direct IO to buffered IO, so diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index ae2b45e75847..bc078aea60ae 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -768,7 +768,6 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); int err; - bool size_changed = false; if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) return -EIO; @@ -843,8 +842,6 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) down_write(&F2FS_I(inode)->i_sem); F2FS_I(inode)->last_disk_size = i_size_read(inode); up_write(&F2FS_I(inode)->i_sem); - - size_changed = true; } __setattr_copy(inode, attr); @@ -858,7 +855,7 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) } /* file size may changed here */ - f2fs_mark_inode_dirty_sync(inode, size_changed); + f2fs_mark_inode_dirty_sync(inode, true); /* inode change will produce dirty node pages flushed by checkpoint */ f2fs_balance_fs(F2FS_I_SB(inode), true); @@ -2573,7 +2570,7 @@ static int f2fs_ioc_flush_device(struct file *filp, unsigned long arg) sizeof(range))) return -EFAULT; - if (sbi->s_ndevs <= 1 || sbi->s_ndevs - 1 <= range.dev_num || + if (!f2fs_is_multi_device(sbi) || sbi->s_ndevs - 1 <= range.dev_num || __is_large_section(sbi)) { f2fs_msg(sbi->sb, KERN_WARNING, "Can't flush %u in %d for segs_per_sec %u != 1\n", diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 195cf0f9d9ef..ab764bd106de 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -1346,7 +1346,7 @@ void f2fs_build_gc_manager(struct f2fs_sb_info *sbi) sbi->gc_pin_file_threshold = DEF_GC_FAILED_PINNED_FILES; /* give warm/cold data area from slower device */ - if (sbi->s_ndevs && !__is_large_section(sbi)) + if (f2fs_is_multi_device(sbi) && !__is_large_section(sbi)) SIT_I(sbi)->last_victim[ALLOC_NEXT] = GET_SEGNO(sbi, FDEV(0).end_blk) + 1; } diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 4f450e573312..3f99ab288695 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -1920,7 +1920,9 @@ static int f2fs_write_node_pages(struct address_space *mapping, f2fs_balance_fs_bg(sbi); /* collect a number of dirty node pages and write together */ - if (get_pages(sbi, F2FS_DIRTY_NODES) < nr_pages_to_skip(sbi, NODE)) + if (wbc->sync_mode != WB_SYNC_ALL && + get_pages(sbi, F2FS_DIRTY_NODES) < + nr_pages_to_skip(sbi, NODE)) goto skip_write; if (wbc->sync_mode == WB_SYNC_ALL) @@ -1959,7 +1961,7 @@ static int f2fs_set_node_page_dirty(struct page *page) if (!PageDirty(page)) { __set_page_dirty_nobuffers(page); inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_NODES); - SetPagePrivate(page); + f2fs_set_page_private(page, 0); f2fs_trace_pid(page); return 1; } diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index e1b1d390b329..2b809b54d81b 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -191,8 +191,7 @@ void f2fs_register_inmem_page(struct inode *inode, struct page *page) f2fs_trace_pid(page); - set_page_private(page, (unsigned long)ATOMIC_WRITTEN_PAGE); - SetPagePrivate(page); + f2fs_set_page_private(page, (unsigned long)ATOMIC_WRITTEN_PAGE); new = f2fs_kmem_cache_alloc(inmem_entry_slab, GFP_NOFS); @@ -280,8 +279,7 @@ next: ClearPageUptodate(page); clear_cold_data(page); } - set_page_private(page, 0); - ClearPagePrivate(page); + f2fs_clear_page_private(page); f2fs_put_page(page, 1); list_del(&cur->list); @@ -370,8 +368,7 @@ void f2fs_drop_inmem_page(struct inode *inode, struct page *page) kmem_cache_free(inmem_entry_slab, cur); ClearPageUptodate(page); - set_page_private(page, 0); - ClearPagePrivate(page); + f2fs_clear_page_private(page); f2fs_put_page(page, 0); trace_f2fs_commit_inmem_page(page, INMEM_INVALIDATE); @@ -579,7 +576,7 @@ static int submit_flush_wait(struct f2fs_sb_info *sbi, nid_t ino) int ret = 0; int i; - if (!sbi->s_ndevs) + if (!f2fs_is_multi_device(sbi)) return __submit_flush_wait(sbi, sbi->sb->s_bdev); for (i = 0; i < sbi->s_ndevs; i++) { @@ -647,7 +644,8 @@ int f2fs_issue_flush(struct f2fs_sb_info *sbi, nid_t ino) return ret; } - if (atomic_inc_return(&fcc->queued_flush) == 1 || sbi->s_ndevs > 1) { + if (atomic_inc_return(&fcc->queued_flush) == 1 || + f2fs_is_multi_device(sbi)) { ret = submit_flush_wait(sbi, ino); atomic_dec(&fcc->queued_flush); @@ -753,7 +751,7 @@ int f2fs_flush_device_cache(struct f2fs_sb_info *sbi) { int ret = 0, i; - if (!sbi->s_ndevs) + if (!f2fs_is_multi_device(sbi)) return 0; for (i = 1; i < sbi->s_ndevs; i++) { @@ -1362,7 +1360,7 @@ static int __queue_discard_cmd(struct f2fs_sb_info *sbi, trace_f2fs_queue_discard(bdev, blkstart, blklen); - if (sbi->s_ndevs) { + if (f2fs_is_multi_device(sbi)) { int devi = f2fs_target_device_index(sbi, blkstart); blkstart -= FDEV(devi).start_blk; @@ -1717,7 +1715,7 @@ static int __f2fs_issue_discard_zone(struct f2fs_sb_info *sbi, block_t lblkstart = blkstart; int devi = 0; - if (sbi->s_ndevs) { + if (f2fs_is_multi_device(sbi)) { devi = f2fs_target_device_index(sbi, blkstart); blkstart -= FDEV(devi).start_blk; } @@ -3074,7 +3072,7 @@ static void update_device_state(struct f2fs_io_info *fio) struct f2fs_sb_info *sbi = fio->sbi; unsigned int devidx; - if (!sbi->s_ndevs) + if (!f2fs_is_multi_device(sbi)) return; devidx = f2fs_target_device_index(sbi, fio->new_blkaddr); diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 5892fa3c885f..144ffba3ec5a 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1460,9 +1460,16 @@ static int f2fs_enable_quotas(struct super_block *sb); static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi) { + unsigned int s_flags = sbi->sb->s_flags; struct cp_control cpc; - int err; + int err = 0; + int ret; + if (s_flags & SB_RDONLY) { + f2fs_msg(sbi->sb, KERN_ERR, + "checkpoint=disable on readonly fs"); + return -EINVAL; + } sbi->sb->s_flags |= SB_ACTIVE; f2fs_update_time(sbi, DISABLE_TIME); @@ -1470,18 +1477,24 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi) while (!f2fs_time_over(sbi, DISABLE_TIME)) { mutex_lock(&sbi->gc_mutex); err = f2fs_gc(sbi, true, false, NULL_SEGNO); - if (err == -ENODATA) + if (err == -ENODATA) { + err = 0; break; + } if (err && err != -EAGAIN) - return err; + break; } - err = sync_filesystem(sbi->sb); - if (err) - return err; + ret = sync_filesystem(sbi->sb); + if (ret || err) { + err = ret ? ret: err; + goto restore_flag; + } - if (f2fs_disable_cp_again(sbi)) - return -EAGAIN; + if (f2fs_disable_cp_again(sbi)) { + err = -EAGAIN; + goto restore_flag; + } mutex_lock(&sbi->gc_mutex); cpc.reason = CP_PAUSE; @@ -1490,7 +1503,9 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi) sbi->unusable_block_count = 0; mutex_unlock(&sbi->gc_mutex); - return 0; +restore_flag: + sbi->sb->s_flags = s_flags; /* Restore MS_RDONLY status */ + return err; } static void f2fs_enable_checkpoint(struct f2fs_sb_info *sbi) @@ -3359,7 +3374,7 @@ skip_recovery: if (test_opt(sbi, DISABLE_CHECKPOINT)) { err = f2fs_disable_checkpoint(sbi); if (err) - goto free_meta; + goto sync_free_meta; } else if (is_set_ckpt_flags(sbi, CP_DISABLED_FLAG)) { f2fs_enable_checkpoint(sbi); } @@ -3372,7 +3387,7 @@ skip_recovery: /* After POR, we can run background GC thread.*/ err = f2fs_start_gc_thread(sbi); if (err) - goto free_meta; + goto sync_free_meta; } kvfree(options); @@ -3394,6 +3409,11 @@ skip_recovery: f2fs_update_time(sbi, REQ_TIME); return 0; +sync_free_meta: + /* safe to flush all the data */ + sync_filesystem(sbi->sb); + retry = false; + free_meta: #ifdef CONFIG_QUOTA f2fs_truncate_quota_inode_pages(sb); @@ -3407,6 +3427,8 @@ free_meta: * falls into an infinite loop in f2fs_sync_meta_pages(). */ truncate_inode_pages_final(META_MAPPING(sbi)); + /* evict some inodes being cached by GC */ + evict_inodes(sb); f2fs_unregister_sysfs(sbi); free_root_inode: dput(sb->s_root); diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index 73b92985198b..6b6fe6431a64 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -347,7 +347,7 @@ check: *base_addr = txattr_addr; return 0; out: - kzfree(txattr_addr); + kvfree(txattr_addr); return err; } @@ -390,7 +390,7 @@ static int read_all_xattrs(struct inode *inode, struct page *ipage, *base_addr = txattr_addr; return 0; fail: - kzfree(txattr_addr); + kvfree(txattr_addr); return err; } @@ -517,7 +517,7 @@ int f2fs_getxattr(struct inode *inode, int index, const char *name, } error = size; out: - kzfree(base_addr); + kvfree(base_addr); return error; } @@ -563,7 +563,7 @@ ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) } error = buffer_size - rest; cleanup: - kzfree(base_addr); + kvfree(base_addr); return error; } @@ -694,7 +694,7 @@ static int __f2fs_setxattr(struct inode *inode, int index, if (!error && S_ISDIR(inode->i_mode)) set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_CP); exit: - kzfree(base_addr); + kvfree(base_addr); return error; } diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 809c0f2f9942..64f4de983468 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -2034,10 +2034,8 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, rem += pipe->bufs[(pipe->curbuf + idx) & (pipe->buffers - 1)].len; ret = -EINVAL; - if (rem < len) { - pipe_unlock(pipe); - goto out; - } + if (rem < len) + goto out_free; rem = len; while (rem) { @@ -2055,7 +2053,9 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, pipe->curbuf = (pipe->curbuf + 1) & (pipe->buffers - 1); pipe->nrbufs--; } else { - pipe_buf_get(pipe, ibuf); + if (!pipe_buf_get(pipe, ibuf)) + goto out_free; + *obuf = *ibuf; obuf->flags &= ~PIPE_BUF_FLAG_GIFT; obuf->len = rem; @@ -2078,11 +2078,11 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, ret = fuse_dev_do_write(fud, &cs, len); pipe_lock(pipe); +out_free: for (idx = 0; idx < nbuf; idx++) pipe_buf_release(pipe, &bufs[idx]); pipe_unlock(pipe); -out: kvfree(bufs); return ret; } diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index a7fa037b876b..a3a3d256fb0e 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -741,11 +741,17 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, umode_t mode, dev_t dev) { struct inode *inode; - struct resv_map *resv_map; + struct resv_map *resv_map = NULL; - resv_map = resv_map_alloc(); - if (!resv_map) - return NULL; + /* + * Reserve maps are only needed for inodes that can have associated + * page allocations. + */ + if (S_ISREG(mode) || S_ISLNK(mode)) { + resv_map = resv_map_alloc(); + if (!resv_map) + return NULL; + } inode = new_inode(sb); if (inode) { @@ -780,8 +786,10 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, break; } lockdep_annotate_inode_mutex_key(inode); - } else - kref_put(&resv_map->refs, resv_map_release); + } else { + if (resv_map) + kref_put(&resv_map->refs, resv_map_release); + } return inode; } diff --git a/fs/jffs2/readinode.c b/fs/jffs2/readinode.c index 389ea53ea487..bccfc40b3a74 100644 --- a/fs/jffs2/readinode.c +++ b/fs/jffs2/readinode.c @@ -1414,11 +1414,6 @@ void jffs2_do_clear_inode(struct jffs2_sb_info *c, struct jffs2_inode_info *f) jffs2_kill_fragtree(&f->fragtree, deleted?c:NULL); - if (f->target) { - kfree(f->target); - f->target = NULL; - } - fds = f->dents; while(fds) { fd = fds; diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c index bb6ae387469f..05d892c79339 100644 --- a/fs/jffs2/super.c +++ b/fs/jffs2/super.c @@ -47,7 +47,10 @@ static struct inode *jffs2_alloc_inode(struct super_block *sb) static void jffs2_i_callback(struct rcu_head *head) { struct inode *inode = container_of(head, struct inode, i_rcu); - kmem_cache_free(jffs2_inode_cachep, JFFS2_INODE_INFO(inode)); + struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode); + + kfree(f->target); + kmem_cache_free(jffs2_inode_cachep, f); } static void jffs2_destroy_inode(struct inode *inode) diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 4ca0b5c18192..853a69e493f5 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -650,11 +650,10 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root, kn->id.generation = gen; /* - * set ino first. This barrier is paired with atomic_inc_not_zero in + * set ino first. This RELEASE is paired with atomic_inc_not_zero in * kernfs_find_and_get_node_by_ino */ - smp_mb__before_atomic(); - atomic_set(&kn->count, 1); + atomic_set_release(&kn->count, 1); atomic_set(&kn->active, KN_DEACTIVATED_BIAS); RB_CLEAR_NODE(&kn->rb); diff --git a/fs/nfs/client.c b/fs/nfs/client.c index fb1cf1a4bda2..90d71fda65ce 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -453,7 +453,7 @@ void nfs_init_timeout_values(struct rpc_timeout *to, int proto, case XPRT_TRANSPORT_RDMA: if (retrans == NFS_UNSPEC_RETRANS) to->to_retries = NFS_DEF_TCP_RETRANS; - if (timeo == NFS_UNSPEC_TIMEO || to->to_retries == 0) + if (timeo == NFS_UNSPEC_TIMEO || to->to_initval == 0) to->to_initval = NFS_DEF_TCP_TIMEO * HZ / 10; if (to->to_initval > NFS_MAX_TCP_TIMEOUT) to->to_initval = NFS_MAX_TCP_TIMEOUT; diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index fed06fd9998d..94f98e190e63 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -329,9 +329,6 @@ ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src, }; ssize_t err, err2; - if (!nfs_server_capable(file_inode(dst), NFS_CAP_COPY)) - return -EOPNOTSUPP; - src_lock = nfs_get_lock_context(nfs_file_open_context(src)); if (IS_ERR(src_lock)) return PTR_ERR(src_lock); diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index 45b2322e092d..00d17198ee12 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -133,8 +133,10 @@ static ssize_t nfs4_copy_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, size_t count, unsigned int flags) { + if (!nfs_server_capable(file_inode(file_out), NFS_CAP_COPY)) + return -EOPNOTSUPP; if (file_inode(file_in) == file_inode(file_out)) - return -EINVAL; + return -EOPNOTSUPP; return nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count); } diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 0570391eaa16..15c025c1a305 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -2041,7 +2041,8 @@ static int nfs23_validate_mount_data(void *options, memcpy(sap, &data->addr, sizeof(data->addr)); args->nfs_server.addrlen = sizeof(data->addr); args->nfs_server.port = ntohs(data->addr.sin_port); - if (!nfs_verify_server_address(sap)) + if (sap->sa_family != AF_INET || + !nfs_verify_server_address(sap)) goto out_no_address; if (!(data->flags & NFS_MOUNT_TCP)) diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index c74e4538d0eb..258f741d6a21 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -1023,8 +1023,9 @@ static void nfsd4_cb_prepare(struct rpc_task *task, void *calldata) cb->cb_seq_status = 1; cb->cb_status = 0; if (minorversion) { - if (!nfsd41_cb_get_slot(clp, task)) + if (!cb->cb_holds_slot && !nfsd41_cb_get_slot(clp, task)) return; + cb->cb_holds_slot = true; } rpc_call_start(task); } @@ -1051,6 +1052,9 @@ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback return true; } + if (!cb->cb_holds_slot) + goto need_restart; + switch (cb->cb_seq_status) { case 0: /* @@ -1089,6 +1093,7 @@ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback cb->cb_seq_status); } + cb->cb_holds_slot = false; clear_bit(0, &clp->cl_cb_slot_busy); rpc_wake_up_next(&clp->cl_cb_waitq); dprintk("%s: freed slot, new seqid=%d\n", __func__, @@ -1296,6 +1301,7 @@ void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp, cb->cb_seq_status = 1; cb->cb_status = 0; cb->cb_need_restart = false; + cb->cb_holds_slot = false; } void nfsd4_run_cb(struct nfsd4_callback *cb) diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 6a45fb00c5fc..f056b1d3fecd 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -265,6 +265,7 @@ find_or_allocate_block(struct nfs4_lockowner *lo, struct knfsd_fh *fh, static void free_blocked_lock(struct nfsd4_blocked_lock *nbl) { + locks_delete_block(&nbl->nbl_lock); locks_release_private(&nbl->nbl_lock); kfree(nbl); } @@ -293,11 +294,18 @@ remove_blocked_locks(struct nfs4_lockowner *lo) nbl = list_first_entry(&reaplist, struct nfsd4_blocked_lock, nbl_lru); list_del_init(&nbl->nbl_lru); - locks_delete_block(&nbl->nbl_lock); free_blocked_lock(nbl); } } +static void +nfsd4_cb_notify_lock_prepare(struct nfsd4_callback *cb) +{ + struct nfsd4_blocked_lock *nbl = container_of(cb, + struct nfsd4_blocked_lock, nbl_cb); + locks_delete_block(&nbl->nbl_lock); +} + static int nfsd4_cb_notify_lock_done(struct nfsd4_callback *cb, struct rpc_task *task) { @@ -325,6 +333,7 @@ nfsd4_cb_notify_lock_release(struct nfsd4_callback *cb) } static const struct nfsd4_callback_ops nfsd4_cb_notify_lock_ops = { + .prepare = nfsd4_cb_notify_lock_prepare, .done = nfsd4_cb_notify_lock_done, .release = nfsd4_cb_notify_lock_release, }; @@ -4863,7 +4872,6 @@ nfs4_laundromat(struct nfsd_net *nn) nbl = list_first_entry(&reaplist, struct nfsd4_blocked_lock, nbl_lru); list_del_init(&nbl->nbl_lru); - locks_delete_block(&nbl->nbl_lock); free_blocked_lock(nbl); } out: diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 396c76755b03..9d6cb246c6c5 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -70,6 +70,7 @@ struct nfsd4_callback { int cb_seq_status; int cb_status; bool cb_need_restart; + bool cb_holds_slot; }; struct nfsd4_callback_ops { diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index 798f1253141a..3b7b8e95c98a 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -519,8 +519,10 @@ static int inotify_update_existing_watch(struct fsnotify_group *group, fsn_mark = fsnotify_find_mark(&inode->i_fsnotify_marks, group); if (!fsn_mark) return -ENOENT; - else if (create) - return -EEXIST; + else if (create) { + ret = -EEXIST; + goto out; + } i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark); @@ -548,6 +550,7 @@ static int inotify_update_existing_watch(struct fsnotify_group *group, /* return the wd */ ret = i_mark->wd; +out: /* match the get from fsnotify_find_mark() */ fsnotify_put_mark(fsn_mark); diff --git a/fs/open.c b/fs/open.c index f1c2f855fd43..a00350018a47 100644 --- a/fs/open.c +++ b/fs/open.c @@ -1215,3 +1215,21 @@ int nonseekable_open(struct inode *inode, struct file *filp) } EXPORT_SYMBOL(nonseekable_open); + +/* + * stream_open is used by subsystems that want stream-like file descriptors. + * Such file descriptors are not seekable and don't have notion of position + * (file.f_pos is always 0). Contrary to file descriptors of other regular + * files, .read() and .write() can run simultaneously. + * + * stream_open never fails and is marked to return int so that it could be + * directly used as file_operations.open . + */ +int stream_open(struct inode *inode, struct file *filp) +{ + filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE | FMODE_ATOMIC_POS); + filp->f_mode |= FMODE_STREAM; + return 0; +} + +EXPORT_SYMBOL(stream_open); diff --git a/fs/pipe.c b/fs/pipe.c index c51750ed4011..2a297bce381f 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -189,9 +189,9 @@ EXPORT_SYMBOL(generic_pipe_buf_steal); * in the tee() system call, when we duplicate the buffers in one * pipe into another. */ -void generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) +bool generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { - get_page(buf->page); + return try_get_page(buf->page); } EXPORT_SYMBOL(generic_pipe_buf_get); diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index bbcc185062bb..d29d869abec1 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -54,6 +54,28 @@ static LIST_HEAD(kclist_head); static DECLARE_RWSEM(kclist_lock); static int kcore_need_update = 1; +/* + * Returns > 0 for RAM pages, 0 for non-RAM pages, < 0 on error + * Same as oldmem_pfn_is_ram in vmcore + */ +static int (*mem_pfn_is_ram)(unsigned long pfn); + +int __init register_mem_pfn_is_ram(int (*fn)(unsigned long pfn)) +{ + if (mem_pfn_is_ram) + return -EBUSY; + mem_pfn_is_ram = fn; + return 0; +} + +static int pfn_is_ram(unsigned long pfn) +{ + if (mem_pfn_is_ram) + return mem_pfn_is_ram(pfn); + else + return 1; +} + /* This doesn't grab kclist_lock, so it should only be used at init time. */ void __init kclist_add(struct kcore_list *new, void *addr, size_t size, int type) @@ -465,6 +487,11 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) goto out; } m = NULL; /* skip the list anchor */ + } else if (!pfn_is_ram(__pa(start) >> PAGE_SHIFT)) { + if (clear_user(buffer, tsz)) { + ret = -EFAULT; + goto out; + } } else if (m->type == KCORE_VMALLOC) { vread(buf, (char *)start, tsz); /* we have to zero-fill user buffer even if no read */ diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index d65390727541..7325baa8f9d4 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -1626,9 +1626,11 @@ static void drop_sysctl_table(struct ctl_table_header *header) if (--header->nreg) return; - if (parent) + if (parent) { put_links(header); - start_unregistering(header); + start_unregistering(header); + } + if (!--header->count) kfree_rcu(header, rcu); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 85b0ef890b28..91bd2ff0c62c 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1141,6 +1141,24 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, count = -EINTR; goto out_mm; } + /* + * Avoid to modify vma->vm_flags + * without locked ops while the + * coredump reads the vm_flags. + */ + if (!mmget_still_valid(mm)) { + /* + * Silently return "count" + * like if get_task_mm() + * failed. FIXME: should this + * function have returned + * -ESRCH if get_task_mm() + * failed like if + * get_proc_task() fails? + */ + up_write(&mm->mmap_sem); + goto out_mm; + } for (vma = mm->mmap; vma; vma = vma->vm_next) { vma->vm_flags &= ~VM_SOFTDIRTY; vma_set_page_prot(vma); diff --git a/fs/read_write.c b/fs/read_write.c index 27b69b85d49f..3d3194e32201 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -560,12 +560,13 @@ ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_ static inline loff_t file_pos_read(struct file *file) { - return file->f_pos; + return file->f_mode & FMODE_STREAM ? 0 : file->f_pos; } static inline void file_pos_write(struct file *file, loff_t pos) { - file->f_pos = pos; + if ((file->f_mode & FMODE_STREAM) == 0) + file->f_pos = pos; } ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count) diff --git a/fs/splice.c b/fs/splice.c index 90c29675d573..c38c7e7a49c9 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -333,8 +333,8 @@ const struct pipe_buf_operations default_pipe_buf_ops = { .get = generic_pipe_buf_get, }; -static int generic_pipe_buf_nosteal(struct pipe_inode_info *pipe, - struct pipe_buffer *buf) +int generic_pipe_buf_nosteal(struct pipe_inode_info *pipe, + struct pipe_buffer *buf) { return 1; } @@ -1588,7 +1588,11 @@ retry: * Get a reference to this pipe buffer, * so we can copy the contents over. */ - pipe_buf_get(ipipe, ibuf); + if (!pipe_buf_get(ipipe, ibuf)) { + if (ret == 0) + ret = -EFAULT; + break; + } *obuf = *ibuf; /* @@ -1662,7 +1666,11 @@ static int link_pipe(struct pipe_inode_info *ipipe, * Get a reference to this pipe buffer, * so we can copy the contents over. */ - pipe_buf_get(ipipe, ibuf); + if (!pipe_buf_get(ipipe, ibuf)) { + if (ret == 0) + ret = -EFAULT; + break; + } obuf = opipe->bufs + nbuf; *obuf = *ibuf; diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 89800fc7dc9d..f5de1e726356 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -629,6 +629,8 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, /* the various vma->vm_userfaultfd_ctx still points to it */ down_write(&mm->mmap_sem); + /* no task can run (and in turn coredump) yet */ + VM_WARN_ON(!mmget_still_valid(mm)); for (vma = mm->mmap; vma; vma = vma->vm_next) if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) { vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; @@ -883,6 +885,8 @@ static int userfaultfd_release(struct inode *inode, struct file *file) * taking the mmap_sem for writing. */ down_write(&mm->mmap_sem); + if (!mmget_still_valid(mm)) + goto skip_mm; prev = NULL; for (vma = mm->mmap; vma; vma = vma->vm_next) { cond_resched(); @@ -905,6 +909,7 @@ static int userfaultfd_release(struct inode *inode, struct file *file) vma->vm_flags = new_flags; vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; } +skip_mm: up_write(&mm->mmap_sem); mmput(mm); wakeup: @@ -1333,6 +1338,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, goto out; down_write(&mm->mmap_sem); + if (!mmget_still_valid(mm)) + goto out_unlock; vma = find_vma_prev(mm, start, &prev); if (!vma) goto out_unlock; @@ -1520,6 +1527,8 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, goto out; down_write(&mm->mmap_sem); + if (!mmget_still_valid(mm)) + goto out_unlock; vma = find_vma_prev(mm, start, &prev); if (!vma) goto out_unlock; |