Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

   Currently if a boot instance creation fails, instead of printing out
   the name of the instance that failed, it prints "(null)". That is
   because it prints "cur_str" that had already been processed by
   strsep(). Print the saved name instead.

   While at it, print the error code of the failure.

 - Fix use-after-free for same named historgrams

   Histograms can be named so that they can be used in multiple events.
   But if the named histogram has a variable attached, the second event
   that uses the named histogram which duplicates it and needs to free
   the original after duplication leaves the old variable in place and
   still visible. If another histogram uses than variable, it will use
   the stale one which will try to reference the freed duplicate
   histogram and crash the kernel.

   Free the duplicate variables along with the duplicated histogram
   data.

 - Check return value of kthread_run() in event self test

   The events self tests uses a kthread for testing but does not check
   if it succeeded in creating a kthread. If the kthread creation were
   to fail, the code will still try to call kthread_stop() on the error
   returned.

 - Fix race between reading trace_pipe and updating subbuffer size

   If a user is reading the trace_pipe file at the same time they update
   the ring buffer sub-buffer size, can cause the trace_pipe read to
   read stale data. Add trace_access_lock() around updating the ring
   buffer sub-buffer size.

 - Fix eventfs_inode on failure path in creation of the events directory

   In the creation of the "events" directory, if after allocating the
   eventfs_inode a failure is detected, it calls cleanup_ei() which
   calls free_ei(). The free_ei() will test if eventfs_inode being freed
   has no children. It is a bug if it does. But on the failure case of
   the creation of the "events" directory, the children lists have not
   yet been initialized and the free will trigger a warning because
   list_empty() on an uninitialized list returns false.

   Move the initialization into init_ei() where it makes more sense and
   makes sure that a created eventfs_inode has its lists initialized
   upon creation.

 - Check return value of kthread_run() in ftrace direct sample code

   The sample code that shows how to use the ftrace direct calls does
   not test the return of kthread_run() to see if it succeeds. Return a
   failure if the kthread_run() doesn't succeed.

 - Clear user events state on fork in case of alloc failure

   On fork, the child gets a pointer to the parent's user events state.
   It makes a copy of it then updates the child's pointer to it. But if
   the allocation fails, the duplication function leaves the child with
   a pointer to its parent's descriptor. When the child cleans up its
   data, it will free the parent's descriptor while the parent is still
   using it.

   In the duplication function, set the child's user_event_mm to NULL
   before testing if the allocation succeeded, and when it exits it will
   not free the parent's descriptor.

 - Fix retry exhaustion in simple ring buffer reader swap

   simple_ring_buffer_swap_reader_page() starts with retry set to 8 and
   post-decrements it only after a failed link replacement. On the final
   attempt, a successful replacement leaves retry at zero, while a
   failed replacement leaves it at -1.

   But the check for success expects the retry value to be non-zero and
   exits with an error on zero. This is the opposite result. Fix it.

 - Fail nicely when the remote swap_reader_page() returns an error

   Currently, if the swap_reader_page() of a remote buffer fails, it
   triggers a WARN_ON_ONCE() and continues normally. Instead, have it
   exit with an error and a pr_warn() print instead of a full WARNING.

* tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Stop remote reader update when page swap fails
  tracing: Fix retry exhaustion in simple ring buffer reader swap
  tracing/user_events: Clear copied tracing state before fork duplication
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify
  eventfs: Initialize ei->children and ei->list in init_ei()
  tracing: Fix use-after-free in trace_pipe read on sub-buffer order change
  tracing: Fix crash passing ERR_PTR to kthread_stop()
  tracing: Fix use-after-free with same-name named triggers
  tracing: Fix logged instance name on creation failure

1 files changed, 996 insertions, 0 deletions

diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
new file mode 100644
index 000000000..d82916657
--- /dev/null
+++ b/fs/afs/rxrpc.c
@@ -0,0 +1,996 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Maintain an RxRPC server socket to do AFS communications through
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/slab.h>
+#include <linux/sched/signal.h>
+
+#include <net/sock.h>
+#include <net/af_rxrpc.h>
+#include "internal.h"
+#include "afs_cm.h"
+#include "protocol_yfs.h"
+#define RXRPC_TRACE_ONLY_DEFINE_ENUMS
+#include <trace/events/rxrpc.h>
+
+struct workqueue_struct *afs_async_calls;
+
+static void afs_deferred_free_worker(struct work_struct *work);
+static void afs_wake_up_call_waiter(struct sock *, struct rxrpc_call *, unsigned long);
+static void afs_wake_up_async_call(struct sock *, struct rxrpc_call *, unsigned long);
+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);
+static void afs_rx_attach(struct rxrpc_call *rxcall, unsigned long user_call_ID);
+static void afs_rx_notify_oob(struct sock *sk, struct sk_buff *oob);
+static int afs_deliver_cm_op_id(struct afs_call *);
+
+static const struct rxrpc_kernel_ops afs_rxrpc_callback_ops = {
+	.notify_new_call	= afs_rx_new_call,
+	.discard_new_call	= afs_rx_discard_new_call,
+	.user_attach_call	= afs_rx_attach,
+	.notify_oob		= afs_rx_notify_oob,
+};
+
+/* asynchronous incoming call initial processing */
+static const struct afs_call_type afs_RXCMxxxx = {
+	.name		= "CB.xxxx",
+	.deliver	= afs_deliver_cm_op_id,
+};
+
+/*
+ * open an RxRPC socket and bind it to be a server for callback notifications
+ * - the socket is left in blocking mode and non-blocking ops use MSG_DONTWAIT
+ */
+int afs_open_socket(struct afs_net *net)
+{
+	struct sockaddr_rxrpc srx;
+	struct socket *socket;
+	int ret;
+
+	_enter("");
+
+	ret = sock_create_kern(net->net, AF_RXRPC, SOCK_DGRAM, PF_INET6, &socket);
+	if (ret < 0)
+		goto error_1;
+
+	socket->sk->sk_allocation = GFP_NOFS;
+	socket->sk->sk_user_data = net;
+
+	/* bind the callback manager's address to make this a server socket */
+	memset(&srx, 0, sizeof(srx));
+	srx.srx_family			= AF_RXRPC;
+	srx.srx_service			= CM_SERVICE;
+	srx.transport_type		= SOCK_DGRAM;
+	srx.transport_len		= sizeof(srx.transport.sin6);
+	srx.transport.sin6.sin6_family	= AF_INET6;
+	srx.transport.sin6.sin6_port	= htons(AFS_CM_PORT);
+
+	ret = rxrpc_sock_set_min_security_level(socket->sk,
+						RXRPC_SECURITY_ENCRYPT);
+	if (ret < 0)
+		goto error_2;
+
+	ret = rxrpc_sock_set_manage_response(socket->sk, true);
+	if (ret < 0)
+		goto error_2;
+
+	ret = afs_create_token_key(net, socket);
+	if (ret < 0)
+		pr_err("Couldn't create RxGK CM key: %d\n", ret);
+
+	ret = kernel_bind(socket, (struct sockaddr_unsized *) &srx, sizeof(srx));
+	if (ret == -EADDRINUSE) {
+		srx.transport.sin6.sin6_port = 0;
+		ret = kernel_bind(socket, (struct sockaddr_unsized *) &srx, sizeof(srx));
+	}
+	if (ret < 0)
+		goto error_2;
+
+	srx.srx_service = YFS_CM_SERVICE;
+	ret = kernel_bind(socket, (struct sockaddr_unsized *) &srx, sizeof(srx));
+	if (ret < 0)
+		goto error_2;
+
+	/* Ideally, we'd turn on service upgrade here, but we can't because
+	 * OpenAFS is buggy and leaks the userStatus field from packet to
+	 * packet and between FS packets and CB packets - so if we try to do an
+	 * upgrade on an FS packet, OpenAFS will leak that into the CB packet
+	 * it sends back to us.
+	 */
+
+	rxrpc_kernel_set_notifications(socket, &afs_rxrpc_callback_ops);
+
+	ret = kernel_listen(socket, INT_MAX);
+	if (ret < 0)
+		goto error_2;
+
+	net->socket = socket;
+	afs_charge_preallocation(&net->charge_preallocation_work);
+	_leave(" = 0");
+	return 0;
+
+error_2:
+	sock_release(socket);
+error_1:
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * close the RxRPC socket AFS was using
+ */
+void afs_close_socket(struct afs_net *net)
+{
+	_enter("");
+
+	cancel_work_sync(&net->charge_preallocation_work);
+	cancel_work_sync(&net->rx_oob_work);
+	/* Future work items should now see ->live is false. */
+
+	kernel_listen(net->socket, 0);
+
+	/* Make sure work items are no longer running. */
+	flush_workqueue(afs_async_calls);
+	cancel_work_sync(&net->charge_preallocation_work);
+
+	if (net->spare_incoming_call) {
+		afs_put_call(net->spare_incoming_call);
+		net->spare_incoming_call = NULL;
+	}
+
+	_debug("outstanding %u", atomic_read(&net->nr_outstanding_calls));
+	wait_var_event(&net->nr_outstanding_calls,
+		       !atomic_read(&net->nr_outstanding_calls));
+	_debug("no outstanding calls");
+
+	kernel_sock_shutdown(net->socket, SHUT_RDWR);
+	flush_workqueue(afs_async_calls);
+	cancel_work_sync(&net->rx_oob_work);
+	net->socket->sk->sk_user_data = NULL;
+	sock_release(net->socket);
+	key_put(net->fs_cm_token_key);
+
+	_debug("dework");
+	_leave("");
+}
+
+/*
+ * Allocate a call.
+ */
+static struct afs_call *afs_alloc_call(struct afs_net *net,
+				       const struct afs_call_type *type,
+				       gfp_t gfp)
+{
+	struct afs_call *call;
+	int o;
+
+	call = kzalloc_obj(*call, gfp);
+	if (!call)
+		return NULL;
+
+	call->type = type;
+	call->net = net;
+	call->debug_id = atomic_inc_return(&rxrpc_debug_id);
+	refcount_set(&call->ref, 1);
+	INIT_WORK(&call->async_work, type->async_rx ?: afs_process_async_call);
+	INIT_WORK(&call->work, call->type->work);
+	INIT_WORK(&call->free_work, afs_deferred_free_worker);
+	init_waitqueue_head(&call->waitq);
+	spin_lock_init(&call->state_lock);
+	call->iter = &call->def_iter;
+
+	o = atomic_inc_return(&net->nr_outstanding_calls);
+	trace_afs_call(call->debug_id, afs_call_trace_alloc, 1, o,
+		       __builtin_return_address(0));
+	return call;
+}
+
+static void afs_free_call(struct afs_call *call)
+{
+	struct afs_net *net = call->net;
+	int o;
+
+	ASSERT(!work_pending(&call->async_work));
+
+	rxrpc_kernel_put_peer(call->peer);
+
+	if (call->rxcall) {
+		rxrpc_kernel_shutdown_call(net->socket, call->rxcall);
+		rxrpc_kernel_put_call(net->socket, call->rxcall);
+		call->rxcall = NULL;
+	}
+	if (call->type->destructor)
+		call->type->destructor(call);
+
+	afs_unuse_server_notime(call->net, call->server, afs_server_trace_unuse_call);
+	kfree(call->request);
+
+	o = atomic_read(&net->nr_outstanding_calls);
+	trace_afs_call(call->debug_id, afs_call_trace_free, 0, o,
+		       __builtin_return_address(0));
+	kfree(call);
+
+	o = atomic_dec_return(&net->nr_outstanding_calls);
+	if (o == 0)
+		wake_up_var(&net->nr_outstanding_calls);
+}
+
+/*
+ * Dispose of a reference on a call.
+ */
+void afs_put_call(struct afs_call *call)
+{
+	struct afs_net *net = call->net;
+	unsigned int debug_id = call->debug_id;
+	bool zero;
+	int r, o;
+
+	zero = __refcount_dec_and_test(&call->ref, &r);
+	o = atomic_read(&net->nr_outstanding_calls);
+	trace_afs_call(debug_id, afs_call_trace_put, r - 1, o,
+		       __builtin_return_address(0));
+	if (zero)
+		afs_free_call(call);
+}
+
+static void afs_deferred_free_worker(struct work_struct *work)
+{
+	struct afs_call *call = container_of(work, struct afs_call, free_work);
+
+	afs_free_call(call);
+}
+
+/*
+ * Dispose of a reference on a call, deferring the cleanup to a workqueue
+ * to avoid lock recursion.
+ */
+void afs_deferred_put_call(struct afs_call *call)
+{
+	struct afs_net *net = call->net;
+	unsigned int debug_id = call->debug_id;
+	bool zero;
+	int r, o;
+
+	zero = __refcount_dec_and_test(&call->ref, &r);
+	o = atomic_read(&net->nr_outstanding_calls);
+	trace_afs_call(debug_id, afs_call_trace_put, r - 1, o,
+		       __builtin_return_address(0));
+	if (zero)
+		schedule_work(&call->free_work);
+}
+
+/*
+ * Queue the call for actual work.
+ */
+static void afs_queue_call_work(struct afs_call *call)
+{
+	if (call->type->work) {
+		afs_get_call(call, afs_call_trace_work);
+		if (!queue_work(afs_wq, &call->work))
+			afs_put_call(call);
+	}
+}
+
+/*
+ * allocate a call with flat request and reply buffers
+ */
+struct afs_call *afs_alloc_flat_call(struct afs_net *net,
+				     const struct afs_call_type *type,
+				     size_t request_size, size_t reply_max)
+{
+	struct afs_call *call;
+
+	call = afs_alloc_call(net, type, GFP_NOFS);
+	if (!call)
+		goto nomem_call;
+
+	if (request_size) {
+		call->request_size = request_size;
+		call->request = kmalloc(request_size, GFP_NOFS);
+		if (!call->request)
+			goto nomem_free;
+	}
+
+	if (reply_max) {
+		call->reply_max = reply_max;
+		call->buffer = kmalloc(reply_max, GFP_NOFS);
+		if (!call->buffer)
+			goto nomem_free;
+	}
+
+	afs_extract_to_buf(call, call->reply_max);
+	call->operation_ID = type->op;
+	init_waitqueue_head(&call->waitq);
+	return call;
+
+nomem_free:
+	afs_put_call(call);
+nomem_call:
+	return NULL;
+}
+
+/*
+ * clean up a call with flat buffer
+ */
+void afs_flat_call_destructor(struct afs_call *call)
+{
+	_enter("");
+
+	kfree(call->request);
+	call->request = NULL;
+	kfree(call->buffer);
+	call->buffer = NULL;
+}
+
+/*
+ * Advance the AFS call state when the RxRPC call ends the transmit phase.
+ */
+static void afs_notify_end_request_tx(struct sock *sock,
+				      struct rxrpc_call *rxcall,
+				      unsigned long call_user_ID)
+{
+	struct afs_call *call = (struct afs_call *)call_user_ID;
+
+	afs_set_call_state(call, AFS_CALL_CL_REQUESTING, AFS_CALL_CL_AWAIT_REPLY);
+}
+
+/*
+ * Initiate a call and synchronously queue up the parameters for dispatch.  Any
+ * error is stored into the call struct, which the caller must check for.
+ */
+void afs_make_call(struct afs_call *call, gfp_t gfp)
+{
+	struct rxrpc_call *rxcall;
+	struct msghdr msg;
+	struct kvec iov[1];
+	size_t len;
+	s64 tx_total_len;
+	int ret;
+
+	_enter(",{%pISp+%u},", rxrpc_kernel_remote_addr(call->peer), call->service_id);
+
+	ASSERT(call->type != NULL);
+	ASSERT(call->type->name != NULL);
+
+	_debug("____MAKE %p{%s,%x} [%d]____",
+	       call, call->type->name, key_serial(call->key),
+	       atomic_read(&call->net->nr_outstanding_calls));
+
+	trace_afs_make_call(call);
+
+	/* Work out the length we're going to transmit.  This is awkward for
+	 * calls such as FS.StoreData where there's an extra injection of data
+	 * after the initial fixed part.
+	 */
+	tx_total_len = call->request_size;
+	if (call->write_iter)
+		tx_total_len += iov_iter_count(call->write_iter);
+
+	/* 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);
+		call->drop_ref = true;
+	}
+
+	/* create a call */
+	rxcall = rxrpc_kernel_begin_call(call->net->socket, call->peer, call->key,
+					 (unsigned long)call,
+					 tx_total_len,
+					 call->max_lifespan,
+					 gfp,
+					 (call->async ?
+					  afs_wake_up_async_call :
+					  afs_wake_up_call_waiter),
+					 call->service_id,
+					 call->upgrade,
+					 (call->intr ? RXRPC_PREINTERRUPTIBLE :
+					  RXRPC_UNINTERRUPTIBLE),
+					 call->debug_id);
+	if (IS_ERR(rxcall)) {
+		ret = PTR_ERR(rxcall);
+		call->error = ret;
+		goto error_kill_call;
+	}
+
+	call->rxcall = rxcall;
+	call->issue_time = ktime_get_real();
+
+	/* send the request */
+	iov[0].iov_base	= call->request;
+	iov[0].iov_len	= call->request_size;
+
+	msg.msg_name		= NULL;
+	msg.msg_namelen		= 0;
+	iov_iter_kvec(&msg.msg_iter, ITER_SOURCE, iov, 1, call->request_size);
+	msg.msg_control		= NULL;
+	msg.msg_controllen	= 0;
+	msg.msg_flags		= MSG_WAITALL | (call->write_iter ? MSG_MORE : 0);
+
+	ret = rxrpc_kernel_send_data(call->net->socket, rxcall,
+				     &msg, call->request_size,
+				     afs_notify_end_request_tx);
+	if (ret < 0)
+		goto error_do_abort;
+
+	if (call->write_iter) {
+		msg.msg_iter = *call->write_iter;
+		msg.msg_flags &= ~MSG_MORE;
+		trace_afs_send_data(call, &msg);
+
+		ret = rxrpc_kernel_send_data(call->net->socket,
+					     call->rxcall, &msg,
+					     iov_iter_count(&msg.msg_iter),
+					     afs_notify_end_request_tx);
+		*call->write_iter = msg.msg_iter;
+
+		trace_afs_sent_data(call, &msg, ret);
+		if (ret < 0)
+			goto error_do_abort;
+	}
+
+	/* Note that at this point, we may have received the reply or an abort
+	 * - and an asynchronous call may already have completed.
+	 *
+	 * afs_wait_for_call_to_complete(call)
+	 * must be called to synchronously clean up.
+	 */
+	return;
+
+error_do_abort:
+	if (ret != -ECONNABORTED)
+		rxrpc_kernel_abort_call(call->net->socket, rxcall,
+					RX_USER_ABORT, ret,
+					afs_abort_send_data_error);
+	if (call->async) {
+		afs_see_call(call, afs_call_trace_async_abort);
+		return;
+	}
+
+	if (ret == -ECONNABORTED) {
+		len = 0;
+		iov_iter_kvec(&msg.msg_iter, ITER_DEST, NULL, 0, 0);
+		rxrpc_kernel_recv_data(call->net->socket, rxcall,
+				       &msg.msg_iter, &len, false,
+				       &call->abort_code, &call->service_id);
+		call->responded = true;
+	}
+	call->error = ret;
+	trace_afs_call_done(call);
+error_kill_call:
+	if (call->async)
+		afs_see_call(call, afs_call_trace_async_kill);
+	if (call->type->immediate_cancel)
+		call->type->immediate_cancel(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_shutdown_call(call->net->socket, call->rxcall);
+	if (call->async) {
+		if (cancel_work_sync(&call->async_work))
+			afs_put_call(call);
+		afs_set_call_complete(call, ret, 0);
+	}
+
+	call->error = ret;
+	call->state = AFS_CALL_COMPLETE;
+	_leave(" = %d", ret);
+}
+
+/*
+ * Log remote abort codes that indicate that we have a protocol disagreement
+ * with the server.
+ */
+static void afs_log_error(struct afs_call *call, s32 remote_abort)
+{
+	static int max = 0;
+	const char *msg;
+	int m;
+
+	switch (remote_abort) {
+	case RX_EOF:		 msg = "unexpected EOF";	break;
+	case RXGEN_CC_MARSHAL:	 msg = "client marshalling";	break;
+	case RXGEN_CC_UNMARSHAL: msg = "client unmarshalling";	break;
+	case RXGEN_SS_MARSHAL:	 msg = "server marshalling";	break;
+	case RXGEN_SS_UNMARSHAL: msg = "server unmarshalling";	break;
+	case RXGEN_DECODE:	 msg = "opcode decode";		break;
+	case RXGEN_SS_XDRFREE:	 msg = "server XDR cleanup";	break;
+	case RXGEN_CC_XDRFREE:	 msg = "client XDR cleanup";	break;
+	case -32:		 msg = "insufficient data";	break;
+	default:
+		return;
+	}
+
+	m = max;
+	if (m < 3) {
+		max = m + 1;
+		pr_notice("kAFS: Peer reported %s failure on %s [%pISp]\n",
+			  msg, call->type->name,
+			  rxrpc_kernel_remote_addr(call->peer));
+	}
+}
+
+/*
+ * deliver messages to a call
+ */
+void afs_deliver_to_call(struct afs_call *call)
+{
+	enum afs_call_state state;
+	size_t len;
+	u32 abort_code, remote_abort = 0;
+	int ret;
+
+	_enter("%s", call->type->name);
+
+	while (state = READ_ONCE(call->state),
+	       state == AFS_CALL_CL_AWAIT_REPLY ||
+	       state == AFS_CALL_SV_AWAIT_OP_ID ||
+	       state == AFS_CALL_SV_AWAIT_REQUEST ||
+	       state == AFS_CALL_SV_AWAIT_ACK
+	       ) {
+		if (state == AFS_CALL_SV_AWAIT_ACK) {
+			len = 0;
+			iov_iter_kvec(&call->def_iter, ITER_DEST, NULL, 0, 0);
+			ret = rxrpc_kernel_recv_data(call->net->socket,
+						     call->rxcall, &call->def_iter,
+						     &len, false, &remote_abort,
+						     &call->service_id);
+			trace_afs_receive_data(call, &call->def_iter, false, ret);
+
+			if (ret == -EINPROGRESS || ret == -EAGAIN)
+				return;
+			if (ret < 0 || ret == 1) {
+				if (ret == 1)
+					ret = 0;
+				goto call_complete;
+			}
+			return;
+		}
+
+		ret = call->type->deliver(call);
+		state = READ_ONCE(call->state);
+		if (ret == 0 && call->unmarshalling_error)
+			ret = -EBADMSG;
+		switch (ret) {
+		case 0:
+			call->responded = true;
+			afs_queue_call_work(call);
+			if (state == AFS_CALL_CL_PROC_REPLY) {
+				if (call->op)
+					set_bit(AFS_SERVER_FL_MAY_HAVE_CB,
+						&call->op->server->flags);
+				goto call_complete;
+			}
+			ASSERTCMP(state, >, AFS_CALL_CL_PROC_REPLY);
+			goto done;
+		case -EINPROGRESS:
+		case -EAGAIN:
+			goto out;
+		case -ECONNABORTED:
+			ASSERTCMP(state, ==, AFS_CALL_COMPLETE);
+			call->responded = true;
+			afs_log_error(call, call->abort_code);
+			goto done;
+		case -ENOTSUPP:
+			call->responded = true;
+			abort_code = RXGEN_OPCODE;
+			rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
+						abort_code, ret,
+						afs_abort_op_not_supported);
+			goto local_abort;
+		case -EIO:
+			pr_err("kAFS: Call %u in bad state %u\n",
+			       call->debug_id, state);
+			fallthrough;
+		case -ENODATA:
+		case -EBADMSG:
+		case -EMSGSIZE:
+		case -ENOMEM:
+		case -EFAULT:
+			abort_code = RXGEN_CC_UNMARSHAL;
+			if (state != AFS_CALL_CL_AWAIT_REPLY)
+				abort_code = RXGEN_SS_UNMARSHAL;
+			rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
+						abort_code, ret,
+						afs_abort_unmarshal_error);
+			goto local_abort;
+		default:
+			abort_code = RX_CALL_DEAD;
+			rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
+						abort_code, ret,
+						afs_abort_general_error);
+			goto local_abort;
+		}
+	}
+
+done:
+	if (call->type->done)
+		call->type->done(call);
+out:
+	_leave("");
+	return;
+
+local_abort:
+	abort_code = 0;
+call_complete:
+	afs_set_call_complete(call, ret, remote_abort);
+	goto done;
+}
+
+/*
+ * Wait synchronously for a call to complete.
+ */
+void afs_wait_for_call_to_complete(struct afs_call *call)
+{
+	bool rxrpc_complete = false;
+
+	_enter("");
+
+	if (!afs_check_call_state(call, AFS_CALL_COMPLETE)) {
+		DECLARE_WAITQUEUE(myself, current);
+
+		add_wait_queue(&call->waitq, &myself);
+		for (;;) {
+			set_current_state(TASK_UNINTERRUPTIBLE);
+
+			/* deliver any messages that are in the queue */
+			if (!afs_check_call_state(call, AFS_CALL_COMPLETE) &&
+			    call->need_attention) {
+				call->need_attention = false;
+				__set_current_state(TASK_RUNNING);
+				afs_deliver_to_call(call);
+				continue;
+			}
+
+			if (afs_check_call_state(call, AFS_CALL_COMPLETE))
+				break;
+
+			if (!rxrpc_kernel_check_life(call->net->socket, call->rxcall)) {
+				/* rxrpc terminated the call. */
+				rxrpc_complete = true;
+				break;
+			}
+
+			schedule();
+		}
+
+		remove_wait_queue(&call->waitq, &myself);
+		__set_current_state(TASK_RUNNING);
+	}
+
+	if (!afs_check_call_state(call, AFS_CALL_COMPLETE)) {
+		if (rxrpc_complete) {
+			afs_set_call_complete(call, call->error, call->abort_code);
+		} else {
+			/* Kill off the call if it's still live. */
+			_debug("call interrupted");
+			if (rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
+						    RX_USER_ABORT, -EINTR,
+						    afs_abort_interrupted))
+				afs_set_call_complete(call, -EINTR, 0);
+		}
+	}
+}
+
+/*
+ * wake up a waiting call
+ */
+static void afs_wake_up_call_waiter(struct sock *sk, struct rxrpc_call *rxcall,
+				    unsigned long call_user_ID)
+{
+	struct afs_call *call = (struct afs_call *)call_user_ID;
+
+	call->need_attention = true;
+	wake_up(&call->waitq);
+}
+
+/*
+ * Wake up an asynchronous call.  The caller is holding the call notify
+ * spinlock around this, so we can't call afs_put_call().
+ */
+static void afs_wake_up_async_call(struct sock *sk, struct rxrpc_call *rxcall,
+				   unsigned long call_user_ID)
+{
+	struct afs_call *call = (struct afs_call *)call_user_ID;
+	int r;
+
+	trace_afs_notify_call(rxcall, call);
+	call->need_attention = true;
+
+	if (__refcount_inc_not_zero(&call->ref, &r)) {
+		trace_afs_call(call->debug_id, afs_call_trace_wake, r + 1,
+			       atomic_read(&call->net->nr_outstanding_calls),
+			       __builtin_return_address(0));
+
+		if (!queue_work(afs_async_calls, &call->async_work))
+			afs_deferred_put_call(call);
+	}
+}
+
+/*
+ * Perform I/O processing on an asynchronous call.  The work item carries a ref
+ * to the call struct that we either need to release or to pass on.
+ */
+static void afs_process_async_call(struct work_struct *work)
+{
+	struct afs_call *call = container_of(work, struct afs_call, async_work);
+
+	_enter("");
+
+	if (call->state < AFS_CALL_COMPLETE && call->need_attention) {
+		call->need_attention = false;
+		afs_deliver_to_call(call);
+	}
+
+	afs_put_call(call);
+	_leave("");
+}
+
+static void afs_rx_attach(struct rxrpc_call *rxcall, unsigned long user_call_ID)
+{
+	struct afs_call *call = (struct afs_call *)user_call_ID;
+
+	call->rxcall = rxcall;
+}
+
+/*
+ * Charge the incoming call preallocation.
+ */
+void afs_charge_preallocation(struct work_struct *work)
+{
+	struct afs_net *net =
+		container_of(work, struct afs_net, charge_preallocation_work);
+	struct afs_call *call = net->spare_incoming_call;
+
+	while (READ_ONCE(net->live)) {
+		if (!call) {
+			call = afs_alloc_call(net, &afs_RXCMxxxx, GFP_KERNEL);
+			if (!call)
+				break;
+
+			call->drop_ref = true;
+			call->async = true;
+			call->state = AFS_CALL_SV_AWAIT_OP_ID;
+			init_waitqueue_head(&call->waitq);
+			afs_extract_to_tmp(call);
+		}
+
+		if (rxrpc_kernel_charge_accept(net->socket,
+					       afs_wake_up_async_call,
+					       (unsigned long)call,
+					       GFP_KERNEL,
+					       call->debug_id) < 0)
+			break;
+		call = NULL;
+	}
+	net->spare_incoming_call = call;
+}
+
+/*
+ * Discard a preallocated call when a socket is shut down.
+ */
+static void afs_rx_discard_new_call(struct rxrpc_call *rxcall,
+				    unsigned long user_call_ID)
+{
+	struct afs_call *call = (struct afs_call *)user_call_ID;
+
+	call->rxcall = NULL;
+	afs_put_call(call);
+}
+
+/*
+ * Notification of an incoming call.
+ */
+static void afs_rx_new_call(struct sock *sk, struct rxrpc_call *rxcall,
+			    unsigned long user_call_ID)
+{
+	struct afs_call *call = (struct afs_call *)user_call_ID;
+	struct afs_net *net = afs_sock2net(sk);
+
+	call->peer = rxrpc_kernel_get_call_peer(sk->sk_socket, call->rxcall);
+	call->server = afs_find_server(call->peer);
+	if (!call->server)
+		trace_afs_cm_no_server(call, rxrpc_kernel_remote_srx(call->peer));
+
+	if (net->live)
+		queue_work(afs_wq, &net->charge_preallocation_work);
+}
+
+/*
+ * Grab the operation ID from an incoming cache manager call.  The socket
+ * buffer is discarded on error or if we don't yet have sufficient data.
+ */
+static int afs_deliver_cm_op_id(struct afs_call *call)
+{
+	int ret;
+
+	_enter("{%zu}", iov_iter_count(call->iter));
+
+	/* the operation ID forms the first four bytes of the request data */
+	ret = afs_extract_data(call, true);
+	if (ret < 0)
+		return ret;
+
+	call->operation_ID = ntohl(call->tmp);
+	afs_set_call_state(call, AFS_CALL_SV_AWAIT_OP_ID, AFS_CALL_SV_AWAIT_REQUEST);
+
+	/* ask the cache manager to route the call (it'll change the call type
+	 * if successful) */
+	if (!afs_cm_incoming_call(call))
+		return -ENOTSUPP;
+
+	call->security_ix = rxrpc_kernel_query_call_security(call->rxcall,
+							     &call->service_id,
+							     &call->enctype);
+
+	trace_afs_cb_call(call);
+	call->work.func = call->type->work;
+
+	/* pass responsibility for the remainder of this message off to the
+	 * cache manager op */
+	return call->type->deliver(call);
+}
+
+/*
+ * Advance the AFS call state when an RxRPC service call ends the transmit
+ * phase.
+ */
+static void afs_notify_end_reply_tx(struct sock *sock,
+				    struct rxrpc_call *rxcall,
+				    unsigned long call_user_ID)
+{
+	struct afs_call *call = (struct afs_call *)call_user_ID;
+
+	afs_set_call_state(call, AFS_CALL_SV_REPLYING, AFS_CALL_SV_AWAIT_ACK);
+}
+
+/*
+ * send an empty reply
+ */
+void afs_send_empty_reply(struct afs_call *call)
+{
+	struct afs_net *net = call->net;
+	struct msghdr msg;
+
+	_enter("");
+
+	rxrpc_kernel_set_tx_length(net->socket, call->rxcall, 0);
+
+	msg.msg_name		= NULL;
+	msg.msg_namelen		= 0;
+	iov_iter_kvec(&msg.msg_iter, ITER_SOURCE, NULL, 0, 0);
+	msg.msg_control		= NULL;
+	msg.msg_controllen	= 0;
+	msg.msg_flags		= 0;
+
+	switch (rxrpc_kernel_send_data(net->socket, call->rxcall, &msg, 0,
+				       afs_notify_end_reply_tx)) {
+	case 0:
+		_leave(" [replied]");
+		return;
+
+	case -ENOMEM:
+		_debug("oom");
+		rxrpc_kernel_abort_call(net->socket, call->rxcall,
+					RXGEN_SS_MARSHAL, -ENOMEM,
+					afs_abort_oom);
+		fallthrough;
+	default:
+		_leave(" [error]");
+		return;
+	}
+}
+
+/*
+ * send a simple reply
+ */
+void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len)
+{
+	struct afs_net *net = call->net;
+	struct msghdr msg;
+	struct kvec iov[1];
+	int n;
+
+	_enter("");
+
+	rxrpc_kernel_set_tx_length(net->socket, call->rxcall, len);
+
+	iov[0].iov_base		= (void *) buf;
+	iov[0].iov_len		= len;
+	msg.msg_name		= NULL;
+	msg.msg_namelen		= 0;
+	iov_iter_kvec(&msg.msg_iter, ITER_SOURCE, iov, 1, len);
+	msg.msg_control		= NULL;
+	msg.msg_controllen	= 0;
+	msg.msg_flags		= 0;
+
+	n = rxrpc_kernel_send_data(net->socket, call->rxcall, &msg, len,
+				   afs_notify_end_reply_tx);
+	if (n >= 0) {
+		/* Success */
+		_leave(" [replied]");
+		return;
+	}
+
+	if (n == -ENOMEM) {
+		_debug("oom");
+		rxrpc_kernel_abort_call(net->socket, call->rxcall,
+					RXGEN_SS_MARSHAL, -ENOMEM,
+					afs_abort_oom);
+	}
+	_leave(" [error]");
+}
+
+/*
+ * Extract a piece of data from the received data socket buffers.
+ */
+int afs_extract_data(struct afs_call *call, bool want_more)
+{
+	struct afs_net *net = call->net;
+	struct iov_iter *iter = call->iter;
+	enum afs_call_state state;
+	u32 remote_abort = 0;
+	int ret;
+
+	_enter("{%s,%zu,%zu},%d",
+	       call->type->name, call->iov_len, iov_iter_count(iter), want_more);
+
+	ret = rxrpc_kernel_recv_data(net->socket, call->rxcall, iter,
+				     &call->iov_len, want_more, &remote_abort,
+				     &call->service_id);
+	trace_afs_receive_data(call, call->iter, want_more, ret);
+	if (ret == 0 || ret == -EAGAIN)
+		return ret;
+
+	state = READ_ONCE(call->state);
+	if (ret == 1) {
+		switch (state) {
+		case AFS_CALL_CL_AWAIT_REPLY:
+			afs_set_call_state(call, state, AFS_CALL_CL_PROC_REPLY);
+			break;
+		case AFS_CALL_SV_AWAIT_REQUEST:
+			afs_set_call_state(call, state, AFS_CALL_SV_REPLYING);
+			break;
+		case AFS_CALL_COMPLETE:
+			kdebug("prem complete %d", call->error);
+			return afs_io_error(call, afs_io_error_extract);
+		default:
+			break;
+		}
+		return 0;
+	}
+
+	afs_set_call_complete(call, ret, remote_abort);
+	return ret;
+}
+
+/*
+ * Log protocol error production.
+ */
+noinline int afs_protocol_error(struct afs_call *call,
+				enum afs_eproto_cause cause)
+{
+	trace_afs_protocol_error(call, cause);
+	if (call)
+		call->unmarshalling_error = true;
+	return -EBADMSG;
+}
+
+/*
+ * Wake up OOB notification processing.
+ */
+static void afs_rx_notify_oob(struct sock *sk, struct sk_buff *oob)
+{
+	struct afs_net *net = sk->sk_user_data;
+
+	if (READ_ONCE(net->live))
+		queue_work(afs_wq, &net->rx_oob_work);
+}