thunderbolt: Rework control channel to be more reliable

If a request times out the response might arrive right after the request
is failed. This response is pushed to the kfifo and next request will
read it instead. Since it most likely will not pass our validation
checks in parse_header() the next request will fail as well, and
response to that request will be pushed to the kfifo, ad infinitum.

We end up in a situation where all requests fail and no devices can be
added anymore until the driver is unloaded and reloaded again.

To overcome this, rework the control channel so that we will have a
queue of outstanding requests. Each request will be handled in turn and
the response is validated against what is expected. Unexpected packets
(for example responses for requests that have been timed out) are
dropped. This model is copied from Greybus implementation with small
changes here and there to get it cope with Thunderbolt control packets.

In addition the configuration packets support sequence number which the
switch is supposed to copy from the request to response. We use this to
drop responses that are already timed out. Taking advantage of the
sequence number, we automatically retry configuration read/write 4 times
before giving up.

Also timeout is not a programming error so there is no need to trigger a
scary backtrace (WARN), instead we just log a warning.  After all
Thunderbolt devices are hot-pluggable by definition which means user can
unplug a device any time and that is totally acceptable.

With this change there is no need to take the global domain lock when
sending configuration packets anymore. This is useful when we add
support for cross-domain (XDomain) communication later on.

Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Reviewed-by: Yehezkel Bernat <yehezkel.bernat@intel.com>
Reviewed-by: Michael Jamet <michael.jamet@intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Andreas Noever <andreas.noever@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

1 files changed, 65 insertions, 0 deletions

diff --git a/drivers/thunderbolt/ctl.h b/drivers/thunderbolt/ctl.h
index 2b23e030a85b..36fd28b1c1c5 100644
--- a/drivers/thunderbolt/ctl.h
+++ b/drivers/thunderbolt/ctl.h
@@ -7,6 +7,8 @@
 #ifndef _TB_CFG
 #define _TB_CFG
 
+#include <linux/kref.h>
+
 #include "nhi.h"
 #include "tb_msgs.h"
 
@@ -39,6 +41,69 @@ struct tb_cfg_result {
 	enum tb_cfg_error tb_error; /* valid if err == 1 */
 };
 
+struct ctl_pkg {
+	struct tb_ctl *ctl;
+	void *buffer;
+	struct ring_frame frame;
+};
+
+/**
+ * struct tb_cfg_request - Control channel request
+ * @kref: Reference count
+ * @ctl: Pointer to the control channel structure. Only set when the
+ *	 request is queued.
+ * @request_size: Size of the request packet (in bytes)
+ * @request_type: Type of the request packet
+ * @response: Response is stored here
+ * @response_size: Maximum size of one response packet
+ * @response_type: Expected type of the response packet
+ * @npackets: Number of packets expected to be returned with this request
+ * @match: Function used to match the incoming packet
+ * @copy: Function used to copy the incoming packet to @response
+ * @callback: Callback called when the request is finished successfully
+ * @callback_data: Data to be passed to @callback
+ * @flags: Flags for the request
+ * @work: Work item used to complete the request
+ * @result: Result after the request has been completed
+ * @list: Requests are queued using this field
+ *
+ * An arbitrary request over Thunderbolt control channel. For standard
+ * control channel message, one should use tb_cfg_read/write() and
+ * friends if possible.
+ */
+struct tb_cfg_request {
+	struct kref kref;
+	struct tb_ctl *ctl;
+	const void *request;
+	size_t request_size;
+	enum tb_cfg_pkg_type request_type;
+	void *response;
+	size_t response_size;
+	enum tb_cfg_pkg_type response_type;
+	size_t npackets;
+	bool (*match)(const struct tb_cfg_request *req,
+		      const struct ctl_pkg *pkg);
+	bool (*copy)(struct tb_cfg_request *req, const struct ctl_pkg *pkg);
+	void (*callback)(void *callback_data);
+	void *callback_data;
+	unsigned long flags;
+	struct work_struct work;
+	struct tb_cfg_result result;
+	struct list_head list;
+};
+
+#define TB_CFG_REQUEST_ACTIVE		0
+#define TB_CFG_REQUEST_CANCELED		1
+
+struct tb_cfg_request *tb_cfg_request_alloc(void);
+void tb_cfg_request_get(struct tb_cfg_request *req);
+void tb_cfg_request_put(struct tb_cfg_request *req);
+int tb_cfg_request(struct tb_ctl *ctl, struct tb_cfg_request *req,
+		   void (*callback)(void *), void *callback_data);
+void tb_cfg_request_cancel(struct tb_cfg_request *req, int err);
+struct tb_cfg_result tb_cfg_request_sync(struct tb_ctl *ctl,
+			struct tb_cfg_request *req, int timeout_msec);
+
 static inline u64 tb_cfg_get_route(const struct tb_cfg_header *header)
 {
 	return (u64) header->route_hi << 32 | header->route_lo;