firewire: fw-sbp2: set single-phase retry_limit

Per the SBP-2 specification, all SBP-2 target devices must have a BUSY_TIMEOUT
register. Per the 1394-1995 specification, the retry_limt portion of the
register should be set to 0x0 initially, and set on the target by a logged in
initiator (i.e., a Linux host w/firewire controller(s)).

Well, as it turns out, lots of devices these days have actually moved on to
starting to implement SBP-3 compliance, which says that retry_limit should
default to 0xf instead (yes, SBP-3 stomps directly on 1394-1995, oops).

Prior to this change, the firewire driver stack didn't touch retry_limit, and
any SBP-3 compliant device worked fine, while SBP-2 compliant ones were unable
to retransmit when the host returned an ack_busy_X, which resulted in stalled
out I/O, eventually causing the SCSI layer to give up and offline the device.

The simple fix is for us to set retry_limit to 0xf in the register for all
devices (which actually matches what the old ieee1394 stack did).

Prior to this change, a hard disk behind an SBP-2 Prolific PL-3507 bridge chip
would routinely encounter buffer I/O errors and wind up offlined by the SCSI
layer. With this change, I've encountered zero I/O failures moving tens of GB
of data around.

Signed-off-by: Jarod Wilson <jwilson@redhat.com>
Signed-off-by: Stefan Richter <stefanr@s5r6.in-berlin.de>

1 files changed, 27 insertions, 4 deletions

diff --git a/drivers/firewire/fw-sbp2.c b/drivers/firewire/fw-sbp2.c
index 03069a4..8bce569 100644
--- a/drivers/firewire/fw-sbp2.c
+++ b/drivers/firewire/fw-sbp2.c
@@ -173,6 +173,7 @@ struct sbp2_target {
 #define SBP2_ORB_TIMEOUT		2000U	/* Timeout in ms */
 #define SBP2_ORB_NULL			0x80000000
 #define SBP2_MAX_SG_ELEMENT_LENGTH	0xf000
+#define SBP2_RETRY_LIMIT		0xf	/* 15 retries */
 
 #define SBP2_DIRECTION_TO_MEDIA		0x0
 #define SBP2_DIRECTION_FROM_MEDIA	0x1
@@ -812,6 +813,30 @@ static void sbp2_target_put(struct sbp2_target *tgt)
 	kref_put(&tgt->kref, sbp2_release_target);
 }
 
+static void
+complete_set_busy_timeout(struct fw_card *card, int rcode,
+			  void *payload, size_t length, void *done)
+{
+	complete(done);
+}
+
+static void sbp2_set_busy_timeout(struct sbp2_logical_unit *lu)
+{
+	struct fw_device *device = fw_device(lu->tgt->unit->device.parent);
+	DECLARE_COMPLETION_ONSTACK(done);
+	struct fw_transaction t;
+	static __be32 busy_timeout;
+
+	/* FIXME: we should try to set dual-phase cycle_limit too */
+	busy_timeout = cpu_to_be32(SBP2_RETRY_LIMIT);
+
+	fw_send_request(device->card, &t, TCODE_WRITE_QUADLET_REQUEST,
+			lu->tgt->node_id, lu->generation, device->max_speed,
+			CSR_REGISTER_BASE + CSR_BUSY_TIMEOUT, &busy_timeout,
+			sizeof(busy_timeout), complete_set_busy_timeout, &done);
+	wait_for_completion(&done);
+}
+
 static void sbp2_reconnect(struct work_struct *work);
 
 static void sbp2_login(struct work_struct *work)
@@ -864,10 +889,8 @@ static void sbp2_login(struct work_struct *work)
 	fw_notify("%s: logged in to LUN %04x (%d retries)\n",
 		  tgt->bus_id, lu->lun, lu->retries);
 
-#if 0
-	/* FIXME: The linux1394 sbp2 does this last step. */
-	sbp2_set_busy_timeout(scsi_id);
-#endif
+	/* set appropriate retry limit(s) in BUSY_TIMEOUT register */
+	sbp2_set_busy_timeout(lu);
 
 	PREPARE_DELAYED_WORK(&lu->work, sbp2_reconnect);
 	sbp2_agent_reset(lu);