diff options
author | James Morris <james.morris@microsoft.com> | 2019-01-22 14:33:10 -0800 |
---|---|---|
committer | James Morris <james.morris@microsoft.com> | 2019-01-22 14:33:10 -0800 |
commit | 9624d5c9c7ff6836bbf9f9b230fd1fcf3d56f91a (patch) | |
tree | e9c1e5d2400ad20c5a9cd633b52a42a00d1d98cb /fs | |
parent | 3e8c73671244af16f1a6042f1c10d13b75cd1156 (diff) | |
parent | 49a57857aeea06ca831043acbb0fa5e0f50602fd (diff) |
Merge tag 'v5.0-rc3' into next-general
Sync to Linux 5.0-rc3 to pull in the VFS changes which impacted a lot
of the LSM code.
Diffstat (limited to 'fs')
-rw-r--r-- | fs/afs/flock.c | 4 | ||||
-rw-r--r-- | fs/afs/inode.c | 3 | ||||
-rw-r--r-- | fs/afs/protocol_yfs.h | 11 | ||||
-rw-r--r-- | fs/afs/rxrpc.c | 53 | ||||
-rw-r--r-- | fs/afs/server_list.c | 4 | ||||
-rw-r--r-- | fs/afs/yfsclient.c | 2 | ||||
-rw-r--r-- | fs/block_dev.c | 28 | ||||
-rw-r--r-- | fs/btrfs/ctree.c | 16 | ||||
-rw-r--r-- | fs/btrfs/ctree.h | 7 | ||||
-rw-r--r-- | fs/btrfs/disk-io.c | 12 | ||||
-rw-r--r-- | fs/btrfs/extent-tree.c | 21 | ||||
-rw-r--r-- | fs/btrfs/inode.c | 5 | ||||
-rw-r--r-- | fs/btrfs/ioctl.c | 49 | ||||
-rw-r--r-- | fs/btrfs/volumes.c | 12 | ||||
-rw-r--r-- | fs/ceph/addr.c | 5 | ||||
-rw-r--r-- | fs/ceph/super.c | 4 | ||||
-rw-r--r-- | fs/cifs/cifsfs.h | 2 | ||||
-rw-r--r-- | fs/cifs/cifsglob.h | 20 | ||||
-rw-r--r-- | fs/cifs/cifssmb.c | 30 | ||||
-rw-r--r-- | fs/cifs/connect.c | 7 | ||||
-rw-r--r-- | fs/cifs/dfs_cache.c | 1 | ||||
-rw-r--r-- | fs/cifs/file.c | 45 | ||||
-rw-r--r-- | fs/cifs/inode.c | 10 | ||||
-rw-r--r-- | fs/cifs/smb2file.c | 8 | ||||
-rw-r--r-- | fs/cifs/smb2pdu.c | 31 | ||||
-rw-r--r-- | fs/cifs/transport.c | 122 | ||||
-rw-r--r-- | fs/hugetlbfs/inode.c | 61 | ||||
-rw-r--r-- | fs/nfs/nfs4file.c | 8 | ||||
-rw-r--r-- | fs/pstore/ram.c | 12 | ||||
-rw-r--r-- | fs/sysfs/dir.c | 3 | ||||
-rw-r--r-- | fs/sysfs/file.c | 6 | ||||
-rw-r--r-- | fs/sysfs/group.c | 3 | ||||
-rw-r--r-- | fs/sysfs/symlink.c | 3 |
33 files changed, 438 insertions, 170 deletions
diff --git a/fs/afs/flock.c b/fs/afs/flock.c index 0568fd986821..e432bd27a2e7 100644 --- a/fs/afs/flock.c +++ b/fs/afs/flock.c @@ -208,7 +208,7 @@ again: /* The new front of the queue now owns the state variables. */ next = list_entry(vnode->pending_locks.next, struct file_lock, fl_u.afs.link); - vnode->lock_key = afs_file_key(next->fl_file); + vnode->lock_key = key_get(afs_file_key(next->fl_file)); vnode->lock_type = (next->fl_type == F_RDLCK) ? AFS_LOCK_READ : AFS_LOCK_WRITE; vnode->lock_state = AFS_VNODE_LOCK_WAITING_FOR_CB; goto again; @@ -413,7 +413,7 @@ static void afs_dequeue_lock(struct afs_vnode *vnode, struct file_lock *fl) /* The new front of the queue now owns the state variables. */ next = list_entry(vnode->pending_locks.next, struct file_lock, fl_u.afs.link); - vnode->lock_key = afs_file_key(next->fl_file); + vnode->lock_key = key_get(afs_file_key(next->fl_file)); vnode->lock_type = (next->fl_type == F_RDLCK) ? AFS_LOCK_READ : AFS_LOCK_WRITE; vnode->lock_state = AFS_VNODE_LOCK_WAITING_FOR_CB; afs_lock_may_be_available(vnode); diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 6b17d3620414..1a4ce07fb406 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -414,7 +414,6 @@ int afs_validate(struct afs_vnode *vnode, struct key *key) } else if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) { valid = true; } else { - vnode->cb_s_break = vnode->cb_interest->server->cb_s_break; vnode->cb_v_break = vnode->volume->cb_v_break; valid = false; } @@ -546,6 +545,8 @@ void afs_evict_inode(struct inode *inode) #endif afs_put_permits(rcu_access_pointer(vnode->permit_cache)); + key_put(vnode->lock_key); + vnode->lock_key = NULL; _leave(""); } diff --git a/fs/afs/protocol_yfs.h b/fs/afs/protocol_yfs.h index 07bc10f076aa..d443e2bfa094 100644 --- a/fs/afs/protocol_yfs.h +++ b/fs/afs/protocol_yfs.h @@ -161,3 +161,14 @@ struct yfs_xdr_YFSStoreVolumeStatus { struct yfs_xdr_u64 max_quota; struct yfs_xdr_u64 file_quota; } __packed; + +enum yfs_lock_type { + yfs_LockNone = -1, + yfs_LockRead = 0, + yfs_LockWrite = 1, + yfs_LockExtend = 2, + yfs_LockRelease = 3, + yfs_LockMandatoryRead = 0x100, + yfs_LockMandatoryWrite = 0x101, + yfs_LockMandatoryExtend = 0x102, +}; diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index a7b44863d502..2c588f9bbbda 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -23,6 +23,7 @@ struct workqueue_struct *afs_async_calls; static void afs_wake_up_call_waiter(struct sock *, struct rxrpc_call *, unsigned long); static long afs_wait_for_call_to_complete(struct afs_call *, struct afs_addr_cursor *); static void afs_wake_up_async_call(struct sock *, struct rxrpc_call *, unsigned long); +static void afs_delete_async_call(struct work_struct *); static void afs_process_async_call(struct work_struct *); static void afs_rx_new_call(struct sock *, struct rxrpc_call *, unsigned long); static void afs_rx_discard_new_call(struct rxrpc_call *, unsigned long); @@ -203,20 +204,26 @@ void afs_put_call(struct afs_call *call) } } +static struct afs_call *afs_get_call(struct afs_call *call, + enum afs_call_trace why) +{ + int u = atomic_inc_return(&call->usage); + + trace_afs_call(call, why, u, + atomic_read(&call->net->nr_outstanding_calls), + __builtin_return_address(0)); + return call; +} + /* * Queue the call for actual work. */ static void afs_queue_call_work(struct afs_call *call) { if (call->type->work) { - int u = atomic_inc_return(&call->usage); - - trace_afs_call(call, afs_call_trace_work, u, - atomic_read(&call->net->nr_outstanding_calls), - __builtin_return_address(0)); - INIT_WORK(&call->work, call->type->work); + afs_get_call(call, afs_call_trace_work); if (!queue_work(afs_wq, &call->work)) afs_put_call(call); } @@ -398,6 +405,12 @@ long afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, } } + /* If the call is going to be asynchronous, we need an extra ref for + * the call to hold itself so the caller need not hang on to its ref. + */ + if (call->async) + afs_get_call(call, afs_call_trace_get); + /* create a call */ rxcall = rxrpc_kernel_begin_call(call->net->socket, srx, call->key, (unsigned long)call, @@ -438,15 +451,17 @@ long afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, goto error_do_abort; } - /* at this point, an async call may no longer exist as it may have - * already completed */ - if (call->async) + /* Note that at this point, we may have received the reply or an abort + * - and an asynchronous call may already have completed. + */ + if (call->async) { + afs_put_call(call); return -EINPROGRESS; + } return afs_wait_for_call_to_complete(call, ac); error_do_abort: - call->state = AFS_CALL_COMPLETE; if (ret != -ECONNABORTED) { rxrpc_kernel_abort_call(call->net->socket, rxcall, RX_USER_ABORT, ret, "KSD"); @@ -463,8 +478,24 @@ error_do_abort: error_kill_call: if (call->type->done) call->type->done(call); - afs_put_call(call); + + /* We need to dispose of the extra ref we grabbed for an async call. + * The call, however, might be queued on afs_async_calls and we need to + * make sure we don't get any more notifications that might requeue it. + */ + if (call->rxcall) { + rxrpc_kernel_end_call(call->net->socket, call->rxcall); + call->rxcall = NULL; + } + if (call->async) { + if (cancel_work_sync(&call->async_work)) + afs_put_call(call); + afs_put_call(call); + } + ac->error = ret; + call->state = AFS_CALL_COMPLETE; + afs_put_call(call); _leave(" = %d", ret); return ret; } diff --git a/fs/afs/server_list.c b/fs/afs/server_list.c index 95d0761cdb34..155dc14caef9 100644 --- a/fs/afs/server_list.c +++ b/fs/afs/server_list.c @@ -42,9 +42,7 @@ struct afs_server_list *afs_alloc_server_list(struct afs_cell *cell, if (vldb->fs_mask[i] & type_mask) nr_servers++; - slist = kzalloc(sizeof(struct afs_server_list) + - sizeof(struct afs_server_entry) * nr_servers, - GFP_KERNEL); + slist = kzalloc(struct_size(slist, servers, nr_servers), GFP_KERNEL); if (!slist) goto error; diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c index 12658c1363ae..5aa57929e8c2 100644 --- a/fs/afs/yfsclient.c +++ b/fs/afs/yfsclient.c @@ -803,7 +803,7 @@ int yfs_fs_create_file(struct afs_fs_cursor *fc, bp = xdr_encode_YFSFid(bp, &vnode->fid); bp = xdr_encode_string(bp, name, namesz); bp = xdr_encode_YFSStoreStatus_mode(bp, mode); - bp = xdr_encode_u32(bp, 0); /* ViceLockType */ + bp = xdr_encode_u32(bp, yfs_LockNone); /* ViceLockType */ yfs_check_req(call, bp); afs_use_fs_server(call, fc->cbi); diff --git a/fs/block_dev.c b/fs/block_dev.c index c546cdce77e6..58a4c1217fa8 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -104,6 +104,20 @@ void invalidate_bdev(struct block_device *bdev) } EXPORT_SYMBOL(invalidate_bdev); +static void set_init_blocksize(struct block_device *bdev) +{ + unsigned bsize = bdev_logical_block_size(bdev); + loff_t size = i_size_read(bdev->bd_inode); + + while (bsize < PAGE_SIZE) { + if (size & bsize) + break; + bsize <<= 1; + } + bdev->bd_block_size = bsize; + bdev->bd_inode->i_blkbits = blksize_bits(bsize); +} + int set_blocksize(struct block_device *bdev, int size) { /* Size must be a power of two, and between 512 and PAGE_SIZE */ @@ -1431,18 +1445,9 @@ EXPORT_SYMBOL(check_disk_change); void bd_set_size(struct block_device *bdev, loff_t size) { - unsigned bsize = bdev_logical_block_size(bdev); - inode_lock(bdev->bd_inode); i_size_write(bdev->bd_inode, size); inode_unlock(bdev->bd_inode); - while (bsize < PAGE_SIZE) { - if (size & bsize) - break; - bsize <<= 1; - } - bdev->bd_block_size = bsize; - bdev->bd_inode->i_blkbits = blksize_bits(bsize); } EXPORT_SYMBOL(bd_set_size); @@ -1519,8 +1524,10 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) } } - if (!ret) + if (!ret) { bd_set_size(bdev,(loff_t)get_capacity(disk)<<9); + set_init_blocksize(bdev); + } /* * If the device is invalidated, rescan partition @@ -1555,6 +1562,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) goto out_clear; } bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9); + set_init_blocksize(bdev); } if (bdev->bd_bdi == &noop_backing_dev_info) diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index d92462fe66c8..f64aad613727 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -1016,19 +1016,21 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, parent_start = parent->start; /* - * If we are COWing a node/leaf from the extent, chunk or device trees, - * make sure that we do not finish block group creation of pending block - * groups. We do this to avoid a deadlock. + * If we are COWing a node/leaf from the extent, chunk, device or free + * space trees, make sure that we do not finish block group creation of + * pending block groups. We do this to avoid a deadlock. * COWing can result in allocation of a new chunk, and flushing pending * block groups (btrfs_create_pending_block_groups()) can be triggered * when finishing allocation of a new chunk. Creation of a pending block - * group modifies the extent, chunk and device trees, therefore we could - * deadlock with ourselves since we are holding a lock on an extent - * buffer that btrfs_create_pending_block_groups() may try to COW later. + * group modifies the extent, chunk, device and free space trees, + * therefore we could deadlock with ourselves since we are holding a + * lock on an extent buffer that btrfs_create_pending_block_groups() may + * try to COW later. */ if (root == fs_info->extent_root || root == fs_info->chunk_root || - root == fs_info->dev_root) + root == fs_info->dev_root || + root == fs_info->free_space_root) trans->can_flush_pending_bgs = false; cow = btrfs_alloc_tree_block(trans, root, parent_start, diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 0a68cf7032f5..7a2a2621f0d9 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -35,6 +35,7 @@ struct btrfs_trans_handle; struct btrfs_transaction; struct btrfs_pending_snapshot; +struct btrfs_delayed_ref_root; extern struct kmem_cache *btrfs_trans_handle_cachep; extern struct kmem_cache *btrfs_bit_radix_cachep; extern struct kmem_cache *btrfs_path_cachep; @@ -786,6 +787,9 @@ enum { * main phase. The fs_info::balance_ctl is initialized. */ BTRFS_FS_BALANCE_RUNNING, + + /* Indicate that the cleaner thread is awake and doing something. */ + BTRFS_FS_CLEANER_RUNNING, }; struct btrfs_fs_info { @@ -2661,6 +2665,9 @@ int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, unsigned long count); int btrfs_async_run_delayed_refs(struct btrfs_fs_info *fs_info, unsigned long count, u64 transid, int wait); +void btrfs_cleanup_ref_head_accounting(struct btrfs_fs_info *fs_info, + struct btrfs_delayed_ref_root *delayed_refs, + struct btrfs_delayed_ref_head *head); int btrfs_lookup_data_extent(struct btrfs_fs_info *fs_info, u64 start, u64 len); int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, u64 bytenr, diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 8da2f380d3c0..6a2a2a951705 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1682,6 +1682,8 @@ static int cleaner_kthread(void *arg) while (1) { again = 0; + set_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags); + /* Make the cleaner go to sleep early. */ if (btrfs_need_cleaner_sleep(fs_info)) goto sleep; @@ -1728,6 +1730,7 @@ static int cleaner_kthread(void *arg) */ btrfs_delete_unused_bgs(fs_info); sleep: + clear_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags); if (kthread_should_park()) kthread_parkme(); if (kthread_should_stop()) @@ -4201,6 +4204,14 @@ static void btrfs_destroy_all_ordered_extents(struct btrfs_fs_info *fs_info) spin_lock(&fs_info->ordered_root_lock); } spin_unlock(&fs_info->ordered_root_lock); + + /* + * We need this here because if we've been flipped read-only we won't + * get sync() from the umount, so we need to make sure any ordered + * extents that haven't had their dirty pages IO start writeout yet + * actually get run and error out properly. + */ + btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1); } static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, @@ -4265,6 +4276,7 @@ static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, if (pin_bytes) btrfs_pin_extent(fs_info, head->bytenr, head->num_bytes, 1); + btrfs_cleanup_ref_head_accounting(fs_info, delayed_refs, head); btrfs_put_delayed_ref_head(head); cond_resched(); spin_lock(&delayed_refs->lock); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index b15afeae16df..d81035b7ea7d 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2456,12 +2456,10 @@ static int run_and_cleanup_extent_op(struct btrfs_trans_handle *trans, return ret ? ret : 1; } -static void cleanup_ref_head_accounting(struct btrfs_trans_handle *trans, - struct btrfs_delayed_ref_head *head) +void btrfs_cleanup_ref_head_accounting(struct btrfs_fs_info *fs_info, + struct btrfs_delayed_ref_root *delayed_refs, + struct btrfs_delayed_ref_head *head) { - struct btrfs_fs_info *fs_info = trans->fs_info; - struct btrfs_delayed_ref_root *delayed_refs = - &trans->transaction->delayed_refs; int nr_items = 1; /* Dropping this ref head update. */ if (head->total_ref_mod < 0) { @@ -2544,7 +2542,7 @@ static int cleanup_ref_head(struct btrfs_trans_handle *trans, } } - cleanup_ref_head_accounting(trans, head); + btrfs_cleanup_ref_head_accounting(fs_info, delayed_refs, head); trace_run_delayed_ref_head(fs_info, head, 0); btrfs_delayed_ref_unlock(head); @@ -4954,6 +4952,15 @@ static void flush_space(struct btrfs_fs_info *fs_info, ret = 0; break; case COMMIT_TRANS: + /* + * If we have pending delayed iputs then we could free up a + * bunch of pinned space, so make sure we run the iputs before + * we do our pinned bytes check below. + */ + mutex_lock(&fs_info->cleaner_delayed_iput_mutex); + btrfs_run_delayed_iputs(fs_info); + mutex_unlock(&fs_info->cleaner_delayed_iput_mutex); + ret = may_commit_transaction(fs_info, space_info); break; default: @@ -7188,7 +7195,7 @@ static noinline int check_ref_cleanup(struct btrfs_trans_handle *trans, if (head->must_insert_reserved) ret = 1; - cleanup_ref_head_accounting(trans, head); + btrfs_cleanup_ref_head_accounting(trans->fs_info, delayed_refs, head); mutex_unlock(&head->mutex); btrfs_put_delayed_ref_head(head); return ret; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 43eb4535319d..5c349667c761 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3129,9 +3129,6 @@ out: /* once for the tree */ btrfs_put_ordered_extent(ordered_extent); - /* Try to release some metadata so we don't get an OOM but don't wait */ - btrfs_btree_balance_dirty_nodelay(fs_info); - return ret; } @@ -3254,6 +3251,8 @@ void btrfs_add_delayed_iput(struct inode *inode) ASSERT(list_empty(&binode->delayed_iput)); list_add_tail(&binode->delayed_iput, &fs_info->delayed_iputs); spin_unlock(&fs_info->delayed_iput_lock); + if (!test_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags)) + wake_up_process(fs_info->cleaner_kthread); } void btrfs_run_delayed_iputs(struct btrfs_fs_info *fs_info) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index fab9443f6a42..9c8e1734429c 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3221,6 +3221,26 @@ static void btrfs_double_inode_lock(struct inode *inode1, struct inode *inode2) inode_lock_nested(inode2, I_MUTEX_CHILD); } +static void btrfs_double_extent_unlock(struct inode *inode1, u64 loff1, + struct inode *inode2, u64 loff2, u64 len) +{ + unlock_extent(&BTRFS_I(inode1)->io_tree, loff1, loff1 + len - 1); + unlock_extent(&BTRFS_I(inode2)->io_tree, loff2, loff2 + len - 1); +} + +static void btrfs_double_extent_lock(struct inode *inode1, u64 loff1, + struct inode *inode2, u64 loff2, u64 len) +{ + if (inode1 < inode2) { + swap(inode1, inode2); + swap(loff1, loff2); + } else if (inode1 == inode2 && loff2 < loff1) { + swap(loff1, loff2); + } + lock_extent(&BTRFS_I(inode1)->io_tree, loff1, loff1 + len - 1); + lock_extent(&BTRFS_I(inode2)->io_tree, loff2, loff2 + len - 1); +} + static int btrfs_extent_same_range(struct inode *src, u64 loff, u64 olen, struct inode *dst, u64 dst_loff) { @@ -3242,11 +3262,12 @@ static int btrfs_extent_same_range(struct inode *src, u64 loff, u64 olen, return -EINVAL; /* - * Lock destination range to serialize with concurrent readpages(). + * Lock destination range to serialize with concurrent readpages() and + * source range to serialize with relocation. */ - lock_extent(&BTRFS_I(dst)->io_tree, dst_loff, dst_loff + len - 1); + btrfs_double_extent_lock(src, loff, dst, dst_loff, len); ret = btrfs_clone(src, dst, loff, olen, len, dst_loff, 1); - unlock_extent(&BTRFS_I(dst)->io_tree, dst_loff, dst_loff + len - 1); + btrfs_double_extent_unlock(src, loff, dst, dst_loff, len); return ret; } @@ -3905,17 +3926,33 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src, len = ALIGN(src->i_size, bs) - off; if (destoff > inode->i_size) { + const u64 wb_start = ALIGN_DOWN(inode->i_size, bs); + ret = btrfs_cont_expand(inode, inode->i_size, destoff); if (ret) return ret; + /* + * We may have truncated the last block if the inode's size is + * not sector size aligned, so we need to wait for writeback to + * complete before proceeding further, otherwise we can race + * with cloning and attempt to increment a reference to an + * extent that no longer exists (writeback completed right after + * we found the previous extent covering eof and before we + * attempted to increment its reference count). + */ + ret = btrfs_wait_ordered_range(inode, wb_start, + destoff - wb_start); + if (ret) + return ret; } /* - * Lock destination range to serialize with concurrent readpages(). + * Lock destination range to serialize with concurrent readpages() and + * source range to serialize with relocation. */ - lock_extent(&BTRFS_I(inode)->io_tree, destoff, destoff + len - 1); + btrfs_double_extent_lock(src, off, inode, destoff, len); ret = btrfs_clone(src, inode, off, olen, len, destoff, 0); - unlock_extent(&BTRFS_I(inode)->io_tree, destoff, destoff + len - 1); + btrfs_double_extent_unlock(src, off, inode, destoff, len); /* * Truncate page cache pages so that future reads will see the cloned * data immediately and not the previous data. diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 2576b1a379c9..3e4f8f88353e 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -7825,6 +7825,18 @@ static int verify_one_dev_extent(struct btrfs_fs_info *fs_info, ret = -EUCLEAN; goto out; } + + /* It's possible this device is a dummy for seed device */ + if (dev->disk_total_bytes == 0) { + dev = find_device(fs_info->fs_devices->seed, devid, NULL); + if (!dev) { + btrfs_err(fs_info, "failed to find seed devid %llu", + devid); + ret = -EUCLEAN; + goto out; + } + } + if (physical_offset + physical_len > dev->disk_total_bytes) { btrfs_err(fs_info, "dev extent devid %llu physical offset %llu len %llu is beyond device boundary %llu", diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 5d0c05e288cc..a47c541f8006 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -1494,10 +1494,7 @@ static vm_fault_t ceph_filemap_fault(struct vm_fault *vmf) if (err < 0 || off >= i_size_read(inode)) { unlock_page(page); put_page(page); - if (err == -ENOMEM) - ret = VM_FAULT_OOM; - else - ret = VM_FAULT_SIGBUS; + ret = vmf_error(err); goto out_inline; } if (err < PAGE_SIZE) diff --git a/fs/ceph/super.c b/fs/ceph/super.c index 4e9a7cc488da..da2cd8e89062 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -530,7 +530,7 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root) seq_putc(m, ','); pos = m->count; - ret = ceph_print_client_options(m, fsc->client); + ret = ceph_print_client_options(m, fsc->client, false); if (ret) return ret; @@ -640,7 +640,7 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt, opt = NULL; /* fsc->client now owns this */ fsc->client->extra_mon_dispatch = extra_mon_dispatch; - fsc->client->osdc.abort_on_full = true; + ceph_set_opt(fsc->client, ABORT_ON_FULL); if (!fsopt->mds_namespace) { ceph_monc_want_map(&fsc->client->monc, CEPH_SUB_MDSMAP, diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index 26776eddd85d..d1f9c2f3f575 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -150,5 +150,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg); extern const struct export_operations cifs_export_ops; #endif /* CONFIG_CIFS_NFSD_EXPORT */ -#define CIFS_VERSION "2.15" +#define CIFS_VERSION "2.16" #endif /* _CIFSFS_H */ diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 01ded7038b19..94dbdbe5be34 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -1438,6 +1438,7 @@ struct mid_q_entry { int mid_state; /* wish this were enum but can not pass to wait_event */ unsigned int mid_flags; __le16 command; /* smb command code */ + unsigned int optype; /* operation type */ bool large_buf:1; /* if valid response, is pointer to large buf */ bool multiRsp:1; /* multiple trans2 responses for one request */ bool multiEnd:1; /* both received */ @@ -1574,6 +1575,25 @@ static inline void free_dfs_info_array(struct dfs_info3_param *param, kfree(param); } +static inline bool is_interrupt_error(int error) +{ + switch (error) { + case -EINTR: + case -ERESTARTSYS: + case -ERESTARTNOHAND: + case -ERESTARTNOINTR: + return true; + } + return false; +} + +static inline bool is_retryable_error(int error) +{ + if (is_interrupt_error(error) || error == -EAGAIN) + return true; + return false; +} + #define MID_FREE 0 #define MID_REQUEST_ALLOCATED 1 #define MID_REQUEST_SUBMITTED 2 diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index b1f49c1c543a..e18915415e13 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -128,24 +128,31 @@ static int __cifs_reconnect_tcon(const struct nls_table *nlsc, int rc; struct dfs_cache_tgt_list tl; struct dfs_cache_tgt_iterator *it = NULL; - char tree[MAX_TREE_SIZE + 1]; + char *tree; const char *tcp_host; size_t tcp_host_len; const char *dfs_host; size_t dfs_host_len; + tree = kzalloc(MAX_TREE_SIZE, GFP_KERNEL); + if (!tree) + return -ENOMEM; + if (tcon->ipc) { - snprintf(tree, sizeof(tree), "\\\\%s\\IPC$", + snprintf(tree, MAX_TREE_SIZE, "\\\\%s\\IPC$", tcon->ses->server->hostname); - return CIFSTCon(0, tcon->ses, tree, tcon, nlsc); + rc = CIFSTCon(0, tcon->ses, tree, tcon, nlsc); + goto out; } - if (!tcon->dfs_path) - return CIFSTCon(0, tcon->ses, tcon->treeName, tcon, nlsc); + if (!tcon->dfs_path) { + rc = CIFSTCon(0, tcon->ses, tcon->treeName, tcon, nlsc); + goto out; + } rc = dfs_cache_noreq_find(tcon->dfs_path + 1, NULL, &tl); if (rc) - return rc; + goto out; extract_unc_hostname(tcon->ses->server->hostname, &tcp_host, &tcp_host_len); @@ -165,7 +172,7 @@ static int __cifs_reconnect_tcon(const struct nls_table *nlsc, continue; } - snprintf(tree, sizeof(tree), "\\%s", tgt); + snprintf(tree, MAX_TREE_SIZE, "\\%s", tgt); rc = CIFSTCon(0, tcon->ses, tree, tcon, nlsc); if (!rc) @@ -182,6 +189,8 @@ static int __cifs_reconnect_tcon(const struct nls_table *nlsc, rc = -ENOENT; } dfs_cache_free_tgts(&tl); +out: + kfree(tree); return rc; } #else @@ -2114,7 +2123,7 @@ cifs_writev_requeue(struct cifs_writedata *wdata) for (j = 0; j < nr_pages; j++) { unlock_page(wdata2->pages[j]); - if (rc != 0 && rc != -EAGAIN) { + if (rc != 0 && !is_retryable_error(rc)) { SetPageError(wdata2->pages[j]); end_page_writeback(wdata2->pages[j]); put_page(wdata2->pages[j]); @@ -2123,7 +2132,7 @@ cifs_writev_requeue(struct cifs_writedata *wdata) if (rc) { kref_put(&wdata2->refcount, cifs_writedata_release); - if (rc == -EAGAIN) + if (is_retryable_error(rc)) continue; break; } @@ -2132,7 +2141,8 @@ cifs_writev_requeue(struct cifs_writedata *wdata) i += nr_pages; } while (i < wdata->nr_pages); - mapping_set_error(inode->i_mapping, rc); + if (rc != 0 && !is_retryable_error(rc)) + mapping_set_error(inode->i_mapping, rc); kref_put(&wdata->refcount, cifs_writedata_release); } diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index f66529679ca2..683310f26171 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -433,9 +433,10 @@ static void reconn_inval_dfs_target(struct TCP_Server_Info *server, kfree(server->hostname); server->hostname = extract_hostname(name); - if (!server->hostname) { - cifs_dbg(FYI, "%s: failed to extract hostname from target: %d\n", - __func__, -ENOMEM); + if (IS_ERR(server->hostname)) { + cifs_dbg(FYI, + "%s: failed to extract hostname from target: %ld\n", + __func__, PTR_ERR(server->hostname)); } } diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c index cd63c4a70875..09b7d0d4f6e4 100644 --- a/fs/cifs/dfs_cache.c +++ b/fs/cifs/dfs_cache.c @@ -776,6 +776,7 @@ static int get_tgt_list(const struct dfs_cache_entry *ce, it->it_name = kstrndup(t->t_name, strlen(t->t_name), GFP_KERNEL); if (!it->it_name) { + kfree(it); rc = -ENOMEM; goto err_free_it; } diff --git a/fs/cifs/file.c b/fs/cifs/file.c index e3e3a7550205..2c7689f3998d 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -733,7 +733,8 @@ reopen_success: if (can_flush) { rc = filemap_write_and_wait(inode->i_mapping); - mapping_set_error(inode->i_mapping, rc); + if (!is_interrupt_error(rc)) + mapping_set_error(inode->i_mapping, rc); if (tcon->unix_ext) rc = cifs_get_inode_info_unix(&inode, full_path, @@ -1132,14 +1133,18 @@ cifs_push_mandatory_locks(struct cifsFileInfo *cfile) /* * Accessing maxBuf is racy with cifs_reconnect - need to store value - * and check it for zero before using. + * and check it before using. */ max_buf = tcon->ses->server->maxBuf; - if (!max_buf) { + if (max_buf < (sizeof(struct smb_hdr) + sizeof(LOCKING_ANDX_RANGE))) { free_xid(xid); return -EINVAL; } + BUILD_BUG_ON(sizeof(struct smb_hdr) + sizeof(LOCKING_ANDX_RANGE) > + PAGE_SIZE); + max_buf = min_t(unsigned int, max_buf - sizeof(struct smb_hdr), + PAGE_SIZE); max_num = (max_buf - sizeof(struct smb_hdr)) / sizeof(LOCKING_ANDX_RANGE); buf = kcalloc(max_num, sizeof(LOCKING_ANDX_RANGE), GFP_KERNEL); @@ -1472,12 +1477,16 @@ cifs_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock, /* * Accessing maxBuf is racy with cifs_reconnect - need to store value - * and check it for zero before using. + * and check it before using. */ max_buf = tcon->ses->server->maxBuf; - if (!max_buf) + if (max_buf < (sizeof(struct smb_hdr) + sizeof(LOCKING_ANDX_RANGE))) return -EINVAL; + BUILD_BUG_ON(sizeof(struct smb_hdr) + sizeof(LOCKING_ANDX_RANGE) > + PAGE_SIZE); + max_buf = min_t(unsigned int, max_buf - sizeof(struct smb_hdr), + PAGE_SIZE); max_num = (max_buf - sizeof(struct smb_hdr)) / sizeof(LOCKING_ANDX_RANGE); buf = kcalloc(max_num, sizeof(LOCKING_ANDX_RANGE), GFP_KERNEL); @@ -2110,6 +2119,7 @@ static int cifs_writepages(struct address_space *mapping, pgoff_t end, index; struct cifs_writedata *wdata; int rc = 0; + int saved_rc = 0; unsigned int xid; /* @@ -2138,8 +2148,10 @@ retry: rc = server->ops->wait_mtu_credits(server, cifs_sb->wsize, &wsize, &credits); - if (rc) + if (rc != 0) { + done = true; break; + } tofind = min((wsize / PAGE_SIZE) - 1, end - index) + 1; @@ -2147,6 +2159,7 @@ retry: &found_pages); if (!wdata) { rc = -ENOMEM; + done = true; add_credits_and_wake_if(server, credits, 0); break; } @@ -2175,7 +2188,7 @@ retry: if (rc != 0) { add_credits_and_wake_if(server, wdata->credits, 0); for (i = 0; i < nr_pages; ++i) { - if (rc == -EAGAIN) + if (is_retryable_error(rc)) redirty_page_for_writepage(wbc, wdata->pages[i]); else @@ -2183,7 +2196,7 @@ retry: end_page_writeback(wdata->pages[i]); put_page(wdata->pages[i]); } - if (rc != -EAGAIN) + if (!is_retryable_error(rc)) mapping_set_error(mapping, rc); } kref_put(&wdata->refcount, cifs_writedata_release); @@ -2193,6 +2206,15 @@ retry: continue; } + /* Return immediately if we received a signal during writing */ + if (is_interrupt_error(rc)) { + done = true; + break; + } + + if (rc != 0 && saved_rc == 0) + saved_rc = rc; + wbc->nr_to_write -= nr_pages; if (wbc->nr_to_write <= 0) done = true; @@ -2210,6 +2232,9 @@ retry: goto retry; } + if (saved_rc != 0) + rc = saved_rc; + if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0)) mapping->writeback_index = index; @@ -2242,8 +2267,8 @@ cifs_writepage_locked(struct page *page, struct writeback_control *wbc) set_page_writeback(page); retry_write: rc = cifs_partialpagewrite(page, 0, PAGE_SIZE); - if (rc == -EAGAIN) { - if (wbc->sync_mode == WB_SYNC_ALL) + if (is_retryable_error(rc)) { + if (wbc->sync_mode == WB_SYNC_ALL && rc == -EAGAIN) goto retry_write; redirty_page_for_writepage(wbc, page); } else if (rc != 0) { diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 13fb59aadebc..478003644916 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -2257,6 +2257,11 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs) * the flush returns error? */ rc = filemap_write_and_wait(inode->i_mapping); + if (is_interrupt_error(rc)) { + rc = -ERESTARTSYS; + goto out; + } + mapping_set_error(inode->i_mapping, rc); rc = 0; @@ -2400,6 +2405,11 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs) * the flush returns error? */ rc = filemap_write_and_wait(inode->i_mapping); + if (is_interrupt_error(rc)) { + rc = -ERESTARTSYS; + goto cifs_setattr_exit; + } + mapping_set_error(inode->i_mapping, rc); rc = 0; diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c index 4ed10dd086e6..b204e84b87fb 100644 --- a/fs/cifs/smb2file.c +++ b/fs/cifs/smb2file.c @@ -122,12 +122,14 @@ smb2_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock, /* * Accessing maxBuf is racy with cifs_reconnect - need to store value - * and check it for zero before using. + * and check it before using. */ max_buf = tcon->ses->server->maxBuf; - if (!max_buf) + if (max_buf < sizeof(struct smb2_lock_element)) return -EINVAL; + BUILD_BUG_ON(sizeof(struct smb2_lock_element) > PAGE_SIZE); + max_buf = min_t(unsigned int, max_buf, PAGE_SIZE); max_num = max_buf / sizeof(struct smb2_lock_element); buf = kcalloc(max_num, sizeof(struct smb2_lock_element), GFP_KERNEL); if (!buf) @@ -264,6 +266,8 @@ smb2_push_mandatory_locks(struct cifsFileInfo *cfile) return -EINVAL; } + BUILD_BUG_ON(sizeof(struct smb2_lock_element) > PAGE_SIZE); + max_buf = min_t(unsigned int, max_buf, PAGE_SIZE); max_num = max_buf / sizeof(struct smb2_lock_element); buf = kcalloc(max_num, sizeof(struct smb2_lock_element), GFP_KERNEL); if (!buf) { diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index e57f6aa1d638..50811a7dc0e0 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -162,24 +162,31 @@ static int __smb2_reconnect(const struct nls_table *nlsc, int rc; struct dfs_cache_tgt_list tl; struct dfs_cache_tgt_iterator *it = NULL; - char tree[MAX_TREE_SIZE + 1]; + char *tree; const char *tcp_host; size_t tcp_host_len; const char *dfs_host; size_t dfs_host_len; + tree = kzalloc(MAX_TREE_SIZE, GFP_KERNEL); + if (!tree) + return -ENOMEM; + if (tcon->ipc) { - snprintf(tree, sizeof(tree), "\\\\%s\\IPC$", + snprintf(tree, MAX_TREE_SIZE, "\\\\%s\\IPC$", tcon->ses->server->hostname); - return SMB2_tcon(0, tcon->ses, tree, tcon, nlsc); + rc = SMB2_tcon(0, tcon->ses, tree, tcon, nlsc); + goto out; } - if (!tcon->dfs_path) - return SMB2_tcon(0, tcon->ses, tcon->treeName, tcon, nlsc); + if (!tcon->dfs_path) { + rc = SMB2_tcon(0, tcon->ses, tcon->treeName, tcon, nlsc); + goto out; + } rc = dfs_cache_noreq_find(tcon->dfs_path + 1, NULL, &tl); if (rc) - return rc; + goto out; extract_unc_hostname(tcon->ses->server->hostname, &tcp_host, &tcp_host_len); @@ -199,7 +206,7 @@ static int __smb2_reconnect(const struct nls_table *nlsc, continue; } - snprintf(tree, sizeof(tree), "\\%s", tgt); + snprintf(tree, MAX_TREE_SIZE, "\\%s", tgt); rc = SMB2_tcon(0, tcon->ses, tree, tcon, nlsc); if (!rc) @@ -216,6 +223,8 @@ static int __smb2_reconnect(const struct nls_table *nlsc, rc = -ENOENT; } dfs_cache_free_tgts(&tl); +out: + kfree(tree); return rc; } #else @@ -3278,12 +3287,14 @@ smb2_async_readv(struct cifs_readdata *rdata) if (rdata->credits) { shdr->CreditCharge = cpu_to_le16(DIV_ROUND_UP(rdata->bytes, SMB2_MAX_BUFFER_SIZE)); - shdr->CreditRequest = shdr->CreditCharge; + shdr->CreditRequest = + cpu_to_le16(le16_to_cpu(shdr->CreditCharge) + 1); spin_lock(&server->req_lock); server->credits += rdata->credits - le16_to_cpu(shdr->CreditCharge); spin_unlock(&server->req_lock); wake_up(&server->request_q); + rdata->credits = le16_to_cpu(shdr->CreditCharge); flags |= CIFS_HAS_CREDITS; } @@ -3555,12 +3566,14 @@ smb2_async_writev(struct cifs_writedata *wdata, if (wdata->credits) { shdr->CreditCharge = cpu_to_le16(DIV_ROUND_UP(wdata->bytes, SMB2_MAX_BUFFER_SIZE)); - shdr->CreditRequest = shdr->CreditCharge; + shdr->CreditRequest = + cpu_to_le16(le16_to_cpu(shdr->CreditCharge) + 1); spin_lock(&server->req_lock); server->credits += wdata->credits - le16_to_cpu(shdr->CreditCharge); spin_unlock(&server->req_lock); wake_up(&server->request_q); + wdata->credits = le16_to_cpu(shdr->CreditCharge); flags |= CIFS_HAS_CREDITS; } diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 5be7302853b6..202e0e84efdd 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -387,7 +387,7 @@ smbd_done: if (rc < 0 && rc != -EINTR) cifs_dbg(VFS, "Error %d sending data on socket to server\n", rc); - else + else if (rc > 0) rc = 0; return rc; @@ -783,8 +783,34 @@ cifs_setup_request(struct cifs_ses *ses, struct smb_rqst *rqst) } static void -cifs_noop_callback(struct mid_q_entry *mid) +cifs_compound_callback(struct mid_q_entry *mid) { + struct TCP_Server_Info *server = mid->server; + unsigned int optype = mid->optype; + unsigned int credits_received = 0; + + if (mid->mid_state == MID_RESPONSE_RECEIVED) { + if (mid->resp_buf) + credits_received = server->ops->get_credits(mid); + else + cifs_dbg(FYI, "Bad state for cancelled MID\n"); + } + + add_credits(server, credits_received, optype); +} + +static void +cifs_compound_last_callback(struct mid_q_entry *mid) +{ + cifs_compound_callback(mid); + cifs_wake_up_task(mid); +} + +static void +cifs_cancelled_callback(struct mid_q_entry *mid) +{ + cifs_compound_callback(mid); + DeleteMidQEntry(mid); } int @@ -795,7 +821,8 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, int i, j, rc = 0; int timeout, optype; struct mid_q_entry *midQ[MAX_COMPOUND]; - unsigned int credits = 0; + bool cancelled_mid[MAX_COMPOUND] = {false}; + unsigned int credits[MAX_COMPOUND] = {0}; char *buf; timeout = flags & CIFS_TIMEOUT_MASK; @@ -813,13 +840,31 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, return -ENOENT; /* - * Ensure that we do not send more than 50 overlapping requests - * to the same server. We may make this configurable later or - * use ses->maxReq. + * Ensure we obtain 1 credit per request in the compound chain. + * It can be optimized further by waiting for all the credits + * at once but this can wait long enough if we don't have enough + * credits due to some heavy operations in progress or the server + * not granting us much, so a fallback to the current approach is + * needed anyway. */ - rc = wait_for_free_request(ses->server, timeout, optype); - if (rc) - return rc; + for (i = 0; i < num_rqst; i++) { + rc = wait_for_free_request(ses->server, timeout, optype); + if (rc) { + /* + * We haven't sent an SMB packet to the server yet but + * we already obtained credits for i requests in the + * compound chain - need to return those credits back + * for future use. Note that we need to call add_credits + * multiple times to match the way we obtained credits + * in the first place and to account for in flight + * requests correctly. + */ + for (j = 0; j < i; j++) + add_credits(ses->server, 1, optype); + return rc; + } + credits[i] = 1; + } /* * Make sure that we sign in the same order that we send on this socket @@ -835,18 +880,24 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, for (j = 0; j < i; j++) cifs_delete_mid(midQ[j]); mutex_unlock(&ses->server->srv_mutex); + /* Update # of requests on wire to server */ - add_credits(ses->server, 1, optype); + for (j = 0; j < num_rqst; j++) + add_credits(ses->server, credits[j], optype); return PTR_ERR(midQ[i]); } midQ[i]->mid_state = MID_REQUEST_SUBMITTED; + midQ[i]->optype = optype; /* - * We don't invoke the callback compounds unless it is the last - * request. + * Invoke callback for every part of the compound chain + * to calculate credits properly. Wake up this thread only when + * the last element is received. */ if (i < num_rqst - 1) - midQ[i]->callback = cifs_noop_callback; + midQ[i]->callback = cifs_compound_callback; + else + midQ[i]->callback = cifs_compound_last_callback; } cifs_in_send_inc(ses->server); rc = smb_send_rqst(ses->server, num_rqst, rqst, flags); @@ -860,8 +911,20 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, mutex_unlock(&ses->server->srv_mutex); - if (rc < 0) + if (rc < 0) { + /* Sending failed for some reason - return credits back */ + for (i = 0; i < num_rqst; i++) + add_credits(ses->server, credits[i], optype); goto out; + } + + /* + * At this point the request is passed to the network stack - we assume + * that any credits taken from the server structure on the client have + * been spent and we can't return them back. Once we receive responses + * we will collect credits granted by the server in the mid callbacks + * and add those credits to the server structure. + */ /* * Compounding is never used during session establish. @@ -875,36 +938,34 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, for (i = 0; i < num_rqst; i++) { rc = wait_for_response(ses->server, midQ[i]); - if (rc != 0) { + if (rc != 0) + break; + } + if (rc != 0) { + for (; i < num_rqst; i++) { cifs_dbg(VFS, "Cancelling wait for mid %llu cmd: %d\n", midQ[i]->mid, le16_to_cpu(midQ[i]->command)); send_cancel(ses->server, &rqst[i], midQ[i]); spin_lock(&GlobalMid_Lock); if (midQ[i]->mid_state == MID_REQUEST_SUBMITTED) { midQ[i]->mid_flags |= MID_WAIT_CANCELLED; - midQ[i]->callback = DeleteMidQEntry; - spin_unlock(&GlobalMid_Lock); - add_credits(ses->server, 1, optype); - return rc; + midQ[i]->callback = cifs_cancelled_callback; + cancelled_mid[i] = true; + credits[i] = 0; } spin_unlock(&GlobalMid_Lock); } } - for (i = 0; i < num_rqst; i++) - if (midQ[i]->resp_buf) - credits += ses->server->ops->get_credits(midQ[i]); - if (!credits) - credits = 1; - for (i = 0; i < num_rqst; i++) { if (rc < 0) goto out; rc = cifs_sync_mid_result(midQ[i], ses->server); if (rc != 0) { - add_credits(ses->server, credits, optype); - return rc; + /* mark this mid as cancelled to not free it below */ + cancelled_mid[i] = true; + goto out; } if (!midQ[i]->resp_buf || @@ -951,9 +1012,10 @@ out: * This is prevented above by using a noop callback that will not * wake this thread except for the very last PDU. */ - for (i = 0; i < num_rqst; i++) - cifs_delete_mid(midQ[i]); - add_credits(ses->server, credits, optype); + for (i = 0; i < num_rqst; i++) { + if (!cancelled_mid[i]) + cifs_delete_mid(midQ[i]); + } return rc; } diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index a2fcea5f8225..32920a10100e 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -383,16 +383,17 @@ hugetlb_vmdelete_list(struct rb_root_cached *root, pgoff_t start, pgoff_t end) * truncation is indicated by end of range being LLONG_MAX * In this case, we first scan the range and release found pages. * After releasing pages, hugetlb_unreserve_pages cleans up region/reserv - * maps and global counts. + * maps and global counts. Page faults can not race with truncation + * in this routine. hugetlb_no_page() prevents page faults in the + * truncated range. It checks i_size before allocation, and again after + * with the page table lock for the page held. The same lock must be + * acquired to unmap a page. * hole punch is indicated if end is not LLONG_MAX * In the hole punch case we scan the range and release found pages. * Only when releasing a page is the associated region/reserv map * deleted. The region/reserv map for ranges without associated - * pages are not modified. - * - * Callers of this routine must hold the i_mmap_rwsem in write mode to prevent - * races with page faults. - * + * pages are not modified. Page faults can race with hole punch. + * This is indicated if we find a mapped page. * Note: If the passed end of range value is beyond the end of file, but * not LLONG_MAX this routine still performs a hole punch operation. */ @@ -422,14 +423,32 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, for (i = 0; i < pagevec_count(&pvec); ++i) { struct page *page = pvec.pages[i]; + u32 hash; index = page->index; + hash = hugetlb_fault_mutex_hash(h, current->mm, + &pseudo_vma, + mapping, index, 0); + mutex_lock(&hugetlb_fault_mutex_table[hash]); + /* - * A mapped page is impossible as callers should unmap - * all references before calling. And, i_mmap_rwsem - * prevents the creation of additional mappings. + * If page is mapped, it was faulted in after being + * unmapped in caller. Unmap (again) now after taking + * the fault mutex. The mutex will prevent faults + * until we finish removing the page. + * + * This race can only happen in the hole punch case. + * Getting here in a truncate operation is a bug. */ - VM_BUG_ON(page_mapped(page)); + if (unlikely(page_mapped(page))) { + BUG_ON(truncate_op); + + i_mmap_lock_write(mapping); + hugetlb_vmdelete_list(&mapping->i_mmap, + index * pages_per_huge_page(h), + (index + 1) * pages_per_huge_page(h)); + i_mmap_unlock_write(mapping); + } lock_page(page); /* @@ -451,6 +470,7 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, } unlock_page(page); + mutex_unlock(&hugetlb_fault_mutex_table[hash]); } huge_pagevec_release(&pvec); cond_resched(); @@ -462,20 +482,9 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, static void hugetlbfs_evict_inode(struct inode *inode) { - struct address_space *mapping = inode->i_mapping; struct resv_map *resv_map; - /* - * The vfs layer guarantees that there are no other users of this - * inode. Therefore, it would be safe to call remove_inode_hugepages - * without holding i_mmap_rwsem. We acquire and hold here to be - * consistent with other callers. Since there will be no contention - * on the semaphore, overhead is negligible. - */ - i_mmap_lock_write(mapping); remove_inode_hugepages(inode, 0, LLONG_MAX); - i_mmap_unlock_write(mapping); - resv_map = (struct resv_map *)inode->i_mapping->private_data; /* root inode doesn't have the resv_map, so we should check it */ if (resv_map) @@ -496,8 +505,8 @@ static int hugetlb_vmtruncate(struct inode *inode, loff_t offset) i_mmap_lock_write(mapping); if (!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root)) hugetlb_vmdelete_list(&mapping->i_mmap, pgoff, 0); - remove_inode_hugepages(inode, offset, LLONG_MAX); i_mmap_unlock_write(mapping); + remove_inode_hugepages(inode, offset, LLONG_MAX); return 0; } @@ -531,8 +540,8 @@ static long hugetlbfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) hugetlb_vmdelete_list(&mapping->i_mmap, hole_start >> PAGE_SHIFT, hole_end >> PAGE_SHIFT); - remove_inode_hugepages(inode, hole_start, hole_end); i_mmap_unlock_write(mapping); + remove_inode_hugepages(inode, hole_start, hole_end); inode_unlock(inode); } @@ -615,11 +624,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, /* addr is the offset within the file (zero based) */ addr = index * hpage_size; - /* - * fault mutex taken here, protects against fault path - * and hole punch. inode_lock previously taken protects - * against truncation. - */ + /* mutex taken here, fault path and hole punch */ hash = hugetlb_fault_mutex_hash(h, mm, &pseudo_vma, mapping, index, addr); mutex_lock(&hugetlb_fault_mutex_table[hash]); diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index 46d691ba04bc..45b2322e092d 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -133,15 +133,9 @@ 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) { - ssize_t ret; - if (file_inode(file_in) == file_inode(file_out)) return -EINVAL; -retry: - ret = nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count); - if (ret == -EAGAIN) - goto retry; - return ret; + return nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count); } static loff_t nfs4_file_llseek(struct file *filep, loff_t offset, int whence) diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index 96f7d32cd184..898c8321b343 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -128,7 +128,6 @@ ramoops_get_next_prz(struct persistent_ram_zone *przs[], int id, struct pstore_record *record) { struct persistent_ram_zone *prz; - bool update = (record->type == PSTORE_TYPE_DMESG); /* Give up if we never existed or have hit the end. */ if (!przs) @@ -139,7 +138,7 @@ ramoops_get_next_prz(struct persistent_ram_zone *przs[], int id, return NULL; /* Update old/shadowed buffer. */ - if (update) + if (prz->type == PSTORE_TYPE_DMESG) persistent_ram_save_old(prz); if (!persistent_ram_old_size(prz)) @@ -711,18 +710,15 @@ static int ramoops_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct ramoops_platform_data *pdata = dev->platform_data; + struct ramoops_platform_data pdata_local; struct ramoops_context *cxt = &oops_cxt; size_t dump_mem_sz; phys_addr_t paddr; int err = -EINVAL; if (dev_of_node(dev) && !pdata) { - pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL); - if (!pdata) { - pr_err("cannot allocate platform data buffer\n"); - err = -ENOMEM; - goto fail_out; - } + pdata = &pdata_local; + memset(pdata, 0, sizeof(*pdata)); err = ramoops_parse_dt(pdev, pdata); if (err < 0) diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c index feeae8081c22..aa85f2874a9f 100644 --- a/fs/sysfs/dir.c +++ b/fs/sysfs/dir.c @@ -43,7 +43,8 @@ int sysfs_create_dir_ns(struct kobject *kobj, const void *ns) kuid_t uid; kgid_t gid; - BUG_ON(!kobj); + if (WARN_ON(!kobj)) + return -EINVAL; if (kobj->parent) parent = kobj->parent->sd; diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index bb71db63c99c..51398457fe00 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -325,7 +325,8 @@ int sysfs_create_file_ns(struct kobject *kobj, const struct attribute *attr, kuid_t uid; kgid_t gid; - BUG_ON(!kobj || !kobj->sd || !attr); + if (WARN_ON(!kobj || !kobj->sd || !attr)) + return -EINVAL; kobject_get_ownership(kobj, &uid, &gid); return sysfs_add_file_mode_ns(kobj->sd, attr, false, attr->mode, @@ -537,7 +538,8 @@ int sysfs_create_bin_file(struct kobject *kobj, kuid_t uid; kgid_t gid; - BUG_ON(!kobj || !kobj->sd || !attr); + if (WARN_ON(!kobj || !kobj->sd || !attr)) + return -EINVAL; kobject_get_ownership(kobj, &uid, &gid); return sysfs_add_file_mode_ns(kobj->sd, &attr->attr, true, diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c index 1eb2d6307663..57038604d4a8 100644 --- a/fs/sysfs/group.c +++ b/fs/sysfs/group.c @@ -112,7 +112,8 @@ static int internal_create_group(struct kobject *kobj, int update, kgid_t gid; int error; - BUG_ON(!kobj || (!update && !kobj->sd)); + if (WARN_ON(!kobj || (!update && !kobj->sd))) + return -EINVAL; /* Updates may happen before the object has been instantiated */ if (unlikely(update && !kobj->sd)) diff --git a/fs/sysfs/symlink.c b/fs/sysfs/symlink.c index 215c225b2ca1..c4deecc80f67 100644 --- a/fs/sysfs/symlink.c +++ b/fs/sysfs/symlink.c @@ -23,7 +23,8 @@ static int sysfs_do_create_link_sd(struct kernfs_node *parent, { struct kernfs_node *kn, *target = NULL; - BUG_ON(!name || !parent); + if (WARN_ON(!name || !parent)) + return -EINVAL; /* * We don't own @target_kobj and it may be removed at any time. |