afs: Build an abstraction around an "operation" concept

Turn the afs_operation struct into the main way that most fileserver
operations are managed.  Various things are added to the struct, including
the following:

 (1) All the parameters and results of the relevant operations are moved
     into it, removing corresponding fields from the afs_call struct.
     afs_call gets a pointer to the op.

 (2) The target volume is made the main focus of the operation, rather than
     the target vnode(s), and a bunch of op->vnode->volume are made
     op->volume instead.

 (3) Two vnode records are defined (op->file[]) for the vnode(s) involved
     in most operations.  The vnode record (struct afs_vnode_param)
     contains:

	- The vnode pointer.

	- The fid of the vnode to be included in the parameters or that was
          returned in the reply (eg. FS.MakeDir).

	- The status and callback information that may be returned in the
     	  reply about the vnode.

	- Callback break and data version tracking for detecting
          simultaneous third-parth changes.

 (4) Pointers to dentries to be updated with new inodes.

 (5) An operations table pointer.  The table includes pointers to functions
     for issuing AFS and YFS-variant RPCs, handling the success and abort
     of an operation and handling post-I/O-lock local editing of a
     directory.

To make this work, the following function restructuring is made:

 (A) The rotation loop that issues calls to fileservers that can be found
     in each function that wants to issue an RPC (such as afs_mkdir()) is
     extracted out into common code, in a new file called fs_operation.c.

 (B) The rotation loops, such as the one in afs_mkdir(), are replaced with
     a much smaller piece of code that allocates an operation, sets the
     parameters and then calls out to the common code to do the actual
     work.

 (C) The code for handling the success and failure of an operation are
     moved into operation functions (as (5) above) and these are called
     from the core code at appropriate times.

 (D) The pseudo inode getting stuff used by the dynamic root code is moved
     over into dynroot.c.

 (E) struct afs_iget_data is absorbed into the operation struct and
     afs_iget() expects to be given an op pointer and a vnode record.

 (F) Point (E) doesn't work for the root dir of a volume, but we know the
     FID in advance (it's always vnode 1, unique 1), so a separate inode
     getter, afs_root_iget(), is provided to special-case that.

 (G) The inode status init/update functions now also take an op and a vnode
     record.

 (H) The RPC marshalling functions now, for the most part, just take an
     afs_operation struct as their only argument.  All the data they need
     is held there.  The result delivery functions write their answers
     there as well.

 (I) The call is attached to the operation and then the operation core does
     the waiting.

And then the new operation code is, for the moment, made to just initialise
the operation, get the appropriate vnode I/O locks and do the same rotation
loop as before.

This lays the foundation for the following changes in the future:

 (*) Overhauling the rotation (again).

 (*) Support for asynchronous I/O, where the fileserver rotation must be
     done asynchronously also.

Signed-off-by: David Howells <dhowells@redhat.com>

1 files changed, 246 insertions, 0 deletions

diff --git a/fs/afs/fs_operation.c b/fs/afs/fs_operation.c
new file mode 100644
index 000000000000..f7a768d12141
--- /dev/null
+++ b/fs/afs/fs_operation.c
@@ -0,0 +1,246 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Fileserver-directed operation handling.
+ *
+ * Copyright (C) 2020 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include "internal.h"
+
+static atomic_t afs_operation_debug_counter;
+
+/*
+ * Create an operation against a volume.
+ */
+struct afs_operation *afs_alloc_operation(struct key *key, struct afs_volume *volume)
+{
+	struct afs_operation *op;
+
+	_enter("");
+
+	op = kzalloc(sizeof(*op), GFP_KERNEL);
+	if (!op)
+		return ERR_PTR(-ENOMEM);
+
+	if (!key) {
+		key = afs_request_key(volume->cell);
+		if (IS_ERR(key)) {
+			kfree(op);
+			return ERR_CAST(key);
+		}
+	} else {
+		key_get(key);
+	}
+
+	op->key		= key;
+	op->volume	= afs_get_volume(volume);
+	op->net		= volume->cell->net;
+	op->cb_v_break	= volume->cb_v_break;
+	op->debug_id	= atomic_inc_return(&afs_operation_debug_counter);
+	op->error	= -EDESTADDRREQ;
+	op->ac.error	= SHRT_MAX;
+
+	_leave(" = [op=%08x]", op->debug_id);
+	return op;
+}
+
+/*
+ * Lock the vnode(s) being operated upon.
+ */
+static bool afs_get_io_locks(struct afs_operation *op)
+{
+	struct afs_vnode *vnode = op->file[0].vnode;
+	struct afs_vnode *vnode2 = op->file[1].vnode;
+
+	_enter("");
+
+	if (op->flags & AFS_OPERATION_UNINTR) {
+		mutex_lock(&vnode->io_lock);
+		op->flags |= AFS_OPERATION_LOCK_0;
+		_leave(" = t [1]");
+		return true;
+	}
+
+	if (!vnode2 || !op->file[1].need_io_lock || vnode == vnode2)
+		vnode2 = NULL;
+
+	if (vnode2 > vnode)
+		swap(vnode, vnode2);
+
+	if (mutex_lock_interruptible(&vnode->io_lock) < 0) {
+		op->error = -EINTR;
+		op->flags |= AFS_OPERATION_STOP;
+		_leave(" = f [I 0]");
+		return false;
+	}
+	op->flags |= AFS_OPERATION_LOCK_0;
+
+	if (vnode2) {
+		if (mutex_lock_interruptible_nested(&vnode2->io_lock, 1) < 0) {
+			op->error = -EINTR;
+			op->flags |= AFS_OPERATION_STOP;
+			mutex_unlock(&vnode->io_lock);
+			op->flags &= ~AFS_OPERATION_LOCK_0;
+			_leave(" = f [I 1]");
+			return false;
+		}
+		op->flags |= AFS_OPERATION_LOCK_1;
+	}
+
+	_leave(" = t [2]");
+	return true;
+}
+
+static void afs_drop_io_locks(struct afs_operation *op)
+{
+	struct afs_vnode *vnode = op->file[0].vnode;
+	struct afs_vnode *vnode2 = op->file[1].vnode;
+
+	_enter("");
+
+	if (op->flags & AFS_OPERATION_LOCK_1)
+		mutex_unlock(&vnode2->io_lock);
+	if (op->flags & AFS_OPERATION_LOCK_0)
+		mutex_unlock(&vnode->io_lock);
+}
+
+static void afs_prepare_vnode(struct afs_operation *op, struct afs_vnode_param *vp,
+			      unsigned int index)
+{
+	struct afs_vnode *vnode = vp->vnode;
+
+	if (vnode) {
+		vp->fid			= vnode->fid;
+		vp->dv_before		= vnode->status.data_version;
+		vp->cb_break_before	= afs_calc_vnode_cb_break(vnode);
+		if (vnode->lock_state != AFS_VNODE_LOCK_NONE)
+			op->flags	|= AFS_OPERATION_CUR_ONLY;
+	}
+
+	if (vp->fid.vnode)
+		_debug("PREP[%u] {%llx:%llu.%u}",
+		       index, vp->fid.vid, vp->fid.vnode, vp->fid.unique);
+}
+
+/*
+ * Begin an operation on the fileserver.
+ *
+ * Fileserver operations are serialised on the server by vnode, so we serialise
+ * them here also using the io_lock.
+ */
+bool afs_begin_vnode_operation(struct afs_operation *op)
+{
+	struct afs_vnode *vnode = op->file[0].vnode;
+
+	ASSERT(vnode);
+
+	_enter("");
+
+	if (op->file[0].need_io_lock)
+		if (!afs_get_io_locks(op))
+			return false;
+
+	read_seqlock_excl(&vnode->cb_lock);
+	op->cbi = afs_get_cb_interest(
+		rcu_dereference_protected(vnode->cb_interest,
+					  lockdep_is_held(&vnode->cb_lock.lock)));
+	read_sequnlock_excl(&vnode->cb_lock);
+
+	afs_prepare_vnode(op, &op->file[0], 0);
+	afs_prepare_vnode(op, &op->file[1], 1);
+	op->cb_v_break = op->volume->cb_v_break;
+	_leave(" = true");
+	return true;
+}
+
+/*
+ * Tidy up a filesystem cursor and unlock the vnode.
+ */
+static void afs_end_vnode_operation(struct afs_operation *op)
+{
+	_enter("");
+
+	if (op->error == -EDESTADDRREQ ||
+	    op->error == -EADDRNOTAVAIL ||
+	    op->error == -ENETUNREACH ||
+	    op->error == -EHOSTUNREACH)
+		afs_dump_edestaddrreq(op);
+
+	afs_drop_io_locks(op);
+
+	if (op->error == -ECONNABORTED)
+		op->error = afs_abort_to_error(op->ac.abort_code);
+}
+
+/*
+ * Wait for an in-progress operation to complete.
+ */
+void afs_wait_for_operation(struct afs_operation *op)
+{
+	_enter("");
+
+	while (afs_select_fileserver(op)) {
+		op->cb_s_break = op->cbi->server->cb_s_break;
+		if (test_bit(AFS_SERVER_FL_IS_YFS, &op->cbi->server->flags) &&
+		    op->ops->issue_yfs_rpc)
+			op->ops->issue_yfs_rpc(op);
+		else
+			op->ops->issue_afs_rpc(op);
+
+		op->error = afs_wait_for_call_to_complete(op->call, &op->ac);
+	}
+
+	if (op->error == 0) {
+		_debug("success");
+		op->ops->success(op);
+	}
+
+	afs_end_vnode_operation(op);
+
+	if (op->error == 0 && op->ops->edit_dir) {
+		_debug("edit_dir");
+		op->ops->edit_dir(op);
+	}
+	_leave("");
+}
+
+/*
+ * Dispose of an operation.
+ */
+int afs_put_operation(struct afs_operation *op)
+{
+	int i, ret = op->error;
+
+	_enter("op=%08x,%d", op->debug_id, ret);
+
+	if (op->ops && op->ops->put)
+		op->ops->put(op);
+	if (op->file[0].put_vnode)
+		iput(&op->file[0].vnode->vfs_inode);
+	if (op->file[1].put_vnode)
+		iput(&op->file[1].vnode->vfs_inode);
+
+	if (op->more_files) {
+		for (i = 0; i < op->nr_files - 2; i++)
+			if (op->more_files[i].put_vnode)
+				iput(&op->more_files[i].vnode->vfs_inode);
+		kfree(op->more_files);
+	}
+
+	afs_end_cursor(&op->ac);
+	afs_put_cb_interest(op->net, op->cbi);
+	afs_put_serverlist(op->net, op->server_list);
+	afs_put_volume(op->net, op->volume);
+	kfree(op);
+	return ret;
+}
+
+int afs_do_sync_operation(struct afs_operation *op)
+{
+	afs_begin_vnode_operation(op);
+	afs_wait_for_operation(op);
+	return afs_put_operation(op);
+}