[V3] SA Busy Handling

Commit Message

Michael Heinz Dec. 2, 2010, 8:28 p.m. UTC

None

Patch

diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c
index 64e660c..2e103ed 100644
--- a/drivers/infiniband/core/mad.c
+++ b/drivers/infiniband/core/mad.c
@@ -54,6 +54,10 @@  MODULE_PARM_DESC(send_queue_size, "Size of send queue in number of work requests
 module_param_named(recv_queue_size, mad_recvq_size, int, 0444);
 MODULE_PARM_DESC(recv_queue_size, "Size of receive queue in number of work requests");
 
+int mad_wait_on_busy = 0;
+module_param_named(treat_busy_as_timeout, mad_wait_on_busy, int, 0444);
+MODULE_PARM_DESC(treat_busy_as_timeout, "When true, treat BUSY responses as if they were timeouts.");
+
 static struct kmem_cache *ib_mad_cache;
 
 static struct list_head ib_mad_port_list;
@@ -1120,6 +1124,7 @@  int ib_post_send_mad(struct ib_mad_send_buf *send_buf,
 		mad_send_wr->timeout = msecs_to_jiffies(send_buf->timeout_ms);
 		mad_send_wr->max_retries = send_buf->retries;
 		mad_send_wr->retries_left = send_buf->retries;
+		mad_send_wr->wait_on_busy = send_buf->wait_on_busy || mad_wait_on_busy;
 		send_buf->retries = 0;
 		/* Reference for work request to QP + response */
 		mad_send_wr->refcount = 1 + (mad_send_wr->timeout > 0);
@@ -1828,6 +1833,9 @@  static void ib_mad_complete_recv(struct ib_mad_agent_private *mad_agent_priv,
 
 	/* Complete corresponding request */
 	if (ib_response_mad(mad_recv_wc->recv_buf.mad)) {
+		u16 busy = be16_to_cpu(mad_recv_wc->recv_buf.mad->mad_hdr.status) &
+							   IB_MGMT_MAD_STATUS_BUSY;
+
 		spin_lock_irqsave(&mad_agent_priv->lock, flags);
 		mad_send_wr = ib_find_send_mad(mad_agent_priv, mad_recv_wc);
 		if (!mad_send_wr) {
@@ -1836,6 +1844,20 @@  static void ib_mad_complete_recv(struct ib_mad_agent_private *mad_agent_priv,
 			deref_mad_agent(mad_agent_priv);
 			return;
 		}
+
+		printk(KERN_DEBUG PFX "Completing recv %p: busy = %d, retries_left = %d, wait_on_busy = %d\n",
+			   mad_send_wr, busy, mad_send_wr->retries_left, mad_send_wr->wait_on_busy);
+
+		if (busy && mad_send_wr->retries_left && mad_send_wr->wait_on_busy &&
+		   (mad_recv_wc->recv_buf.mad->mad_hdr.method != IB_MGMT_METHOD_TRAP_REPRESS)) {
+			/* Just let the query timeout and have it requeued later */
+			spin_unlock_irqrestore(&mad_agent_priv->lock, flags);
+			ib_free_recv_mad(mad_recv_wc);
+			deref_mad_agent(mad_agent_priv);
+			printk(KERN_INFO PFX "SA/SM responded MAD_STATUS_BUSY. Allowing request to time out.\n");
+			return;
+		}
+
 		ib_mark_mad_done(mad_send_wr);
 		spin_unlock_irqrestore(&mad_agent_priv->lock, flags);
 
diff --git a/drivers/infiniband/core/mad_priv.h b/drivers/infiniband/core/mad_priv.h
index 8b4df0a..b6477cf 100644
--- a/drivers/infiniband/core/mad_priv.h
+++ b/drivers/infiniband/core/mad_priv.h
@@ -135,6 +135,7 @@  struct ib_mad_send_wr_private {
 	unsigned long timeout;
 	int max_retries;
 	int retries_left;
+	int wait_on_busy;
 	int retry;
 	int refcount;
 	enum ib_wc_status status;
diff --git a/include/rdma/ib_mad.h b/include/rdma/ib_mad.h
index d3b9401..fadc2c3 100644
--- a/include/rdma/ib_mad.h
+++ b/include/rdma/ib_mad.h
@@ -77,6 +77,15 @@ 
 
 #define IB_MGMT_MAX_METHODS			128
 
+/* MAD Status field bit masks */
+#define IB_MGMT_MAD_STATUS_SUCCESS                      0x0000
+#define IB_MGMT_MAD_STATUS_BUSY                         0x0001
+#define IB_MGMT_MAD_STATUS_REDIRECT_REQD                0x0002
+#define IB_MGMT_MAD_STATUS_BAD_VERERSION                0x0004
+#define IB_MGMT_MAD_STATUS_UNSUPPORTED_METHOD           0x0008
+#define IB_MGMT_MAD_STATUS_UNSUPPORTED_METHOD_ATTRIB    0x000c
+#define IB_MGMT_MAD_STATUS_INVALID_ATTRIB_VALUE         0x001c
+
 /* RMPP information */
 #define IB_MGMT_RMPP_VERSION			1
 
@@ -246,6 +255,7 @@  struct ib_mad_send_buf {
 	int			seg_count;
 	int			seg_size;
 	int			timeout_ms;
+	int			wait_on_busy;
 	int			retries;
 };