whiterose

linux unikernel
Log | Files | Refs | README | LICENSE | git clone https://git.ne02ptzero.me/git/whiterose

commit a3a80255d58d0f0d304ba877ae0313a264973a70
parent 6d060fa39035d5ff6bb3e720a8119aeb50453e3b
Author: Linus Torvalds <torvalds@linux-foundation.org>
Date:   Fri, 18 Jan 2019 06:27:24 +1200

Merge tag 'afs-fixes-20190117' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs

Pull AFS fixes from David Howells:
 "Here's a set of fixes for AFS:

   - Use struct_size() for kzalloc() size calculation.

   - When calling YFS.CreateFile rather than AFS.CreateFile, it is
     possible to create a file with a file lock already held. The
     default value indicating no lock required is actually -1, not 0.

   - Fix an oops in inode/vnode validation if the target inode doesn't
     have a server interest assigned (ie. a server that will notify us
     of changes by third parties).

   - Fix refcounting of keys in file locking.

   - Fix a race in refcounting asynchronous operations in the event of
     an error during request transmission. The provision of a dedicated
     function to get an extra ref on a call is split into a separate
     commit"

* tag 'afs-fixes-20190117' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs:
  afs: Fix race in async call refcounting
  afs: Provide a function to get a ref on a call
  afs: Fix key refcounting in file locking code
  afs: Don't set vnode->cb_s_break in afs_validate()
  afs: Set correct lock type for the yfs CreateFile
  afs: Use struct_size() in kzalloc()

Diffstat:
Mfs/afs/flock.c | 4++--
Mfs/afs/inode.c | 3++-
Mfs/afs/protocol_yfs.h | 11+++++++++++
Mfs/afs/rxrpc.c | 53++++++++++++++++++++++++++++++++++++++++++-----------
Mfs/afs/server_list.c | 4+---
Mfs/afs/yfsclient.c | 2+-
Minclude/trace/events/afs.h | 2++
7 files changed, 61 insertions(+), 18 deletions(-)

diff --git 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 @@ -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 @@ -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 @@ -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 @@ -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 @@ -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/include/trace/events/afs.h b/include/trace/events/afs.h @@ -25,6 +25,7 @@ enum afs_call_trace { afs_call_trace_alloc, afs_call_trace_free, + afs_call_trace_get, afs_call_trace_put, afs_call_trace_wake, afs_call_trace_work, @@ -159,6 +160,7 @@ enum afs_file_error { #define afs_call_traces \ EM(afs_call_trace_alloc, "ALLOC") \ EM(afs_call_trace_free, "FREE ") \ + EM(afs_call_trace_get, "GET ") \ EM(afs_call_trace_put, "PUT ") \ EM(afs_call_trace_wake, "WAKE ") \ E_(afs_call_trace_work, "WORK ")