IB/srp: Make HCA completion vector configurable

Several InfiniBand HCAs allow configuring the completion vector per
CQ.  This allows spreading the workload created by IB completion
interrupts over multiple MSI-X vectors and hence over multiple CPU
cores.  In other words, configuring the completion vector properly not
only allows reducing latency on an initiator connected to multiple
SRP targets but also allows improving throughput.

Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Acked-by: David Dillow <dillowda@ornl.gov>
Signed-off-by: Roland Dreier <roland@purestorage.com>

3 files changed, 32 insertions, 2 deletions

diff --git a/Documentation/ABI/stable/sysfs-driver-ib_srp b/Documentation/ABI/stable/sysfs-driver-ib_srp
index 481aae95c7d1..5c53d28f775c 100644
--- a/Documentation/ABI/stable/sysfs-driver-ib_srp
+++ b/Documentation/ABI/stable/sysfs-driver-ib_srp
@@ -54,6 +54,13 @@ Description:	Interface for making ib_srp connect to a new target.
 		  ib_srp. Specifying a value that exceeds cmd_sg_entries is
 		  only safe with partial memory descriptor list support enabled
 		  (allow_ext_sg=1).
+		* comp_vector, a number in the range 0..n-1 specifying the
+		  MSI-X completion vector. Some HCA's allocate multiple (n)
+		  MSI-X vectors per HCA port. If the IRQ affinity masks of
+		  these interrupts have been configured such that each MSI-X
+		  interrupt is handled by a different CPU then the comp_vector
+		  parameter can be used to spread the SRP completion workload
+		  over multiple CPU's.
 
 What:		/sys/class/infiniband_srp/srp-<hca>-<port_number>/ibdev
 Date:		January 2, 2006
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 830ef0037087..9b30366cb017 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -231,14 +231,16 @@ static int srp_create_target_ib(struct srp_target_port *target)
 		return -ENOMEM;
 
 	recv_cq = ib_create_cq(target->srp_host->srp_dev->dev,
-			       srp_recv_completion, NULL, target, SRP_RQ_SIZE, 0);
+			       srp_recv_completion, NULL, target, SRP_RQ_SIZE,
+			       target->comp_vector);
 	if (IS_ERR(recv_cq)) {
 		ret = PTR_ERR(recv_cq);
 		goto err;
 	}
 
 	send_cq = ib_create_cq(target->srp_host->srp_dev->dev,
-			       srp_send_completion, NULL, target, SRP_SQ_SIZE, 0);
+			       srp_send_completion, NULL, target, SRP_SQ_SIZE,
+			       target->comp_vector);
 	if (IS_ERR(send_cq)) {
 		ret = PTR_ERR(send_cq);
 		goto err_recv_cq;
@@ -1898,6 +1900,14 @@ static ssize_t show_local_ib_device(struct device *dev,
 	return sprintf(buf, "%s\n", target->srp_host->srp_dev->dev->name);
 }
 
+static ssize_t show_comp_vector(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct srp_target_port *target = host_to_target(class_to_shost(dev));
+
+	return sprintf(buf, "%d\n", target->comp_vector);
+}
+
 static ssize_t show_cmd_sg_entries(struct device *dev,
 				   struct device_attribute *attr, char *buf)
 {
@@ -1924,6 +1934,7 @@ static DEVICE_ATTR(req_lim,         S_IRUGO, show_req_lim,         NULL);
 static DEVICE_ATTR(zero_req_lim,    S_IRUGO, show_zero_req_lim,	   NULL);
 static DEVICE_ATTR(local_ib_port,   S_IRUGO, show_local_ib_port,   NULL);
 static DEVICE_ATTR(local_ib_device, S_IRUGO, show_local_ib_device, NULL);
+static DEVICE_ATTR(comp_vector,     S_IRUGO, show_comp_vector,     NULL);
 static DEVICE_ATTR(cmd_sg_entries,  S_IRUGO, show_cmd_sg_entries,  NULL);
 static DEVICE_ATTR(allow_ext_sg,    S_IRUGO, show_allow_ext_sg,    NULL);
 
@@ -1938,6 +1949,7 @@ static struct device_attribute *srp_host_attrs[] = {
 	&dev_attr_zero_req_lim,
 	&dev_attr_local_ib_port,
 	&dev_attr_local_ib_device,
+	&dev_attr_comp_vector,
 	&dev_attr_cmd_sg_entries,
 	&dev_attr_allow_ext_sg,
 	NULL
@@ -2061,6 +2073,7 @@ enum {
 	SRP_OPT_CMD_SG_ENTRIES	= 1 << 9,
 	SRP_OPT_ALLOW_EXT_SG	= 1 << 10,
 	SRP_OPT_SG_TABLESIZE	= 1 << 11,
+	SRP_OPT_COMP_VECTOR	= 1 << 12,
 	SRP_OPT_ALL		= (SRP_OPT_ID_EXT	|
 				   SRP_OPT_IOC_GUID	|
 				   SRP_OPT_DGID		|
@@ -2081,6 +2094,7 @@ static const match_table_t srp_opt_tokens = {
 	{ SRP_OPT_CMD_SG_ENTRIES,	"cmd_sg_entries=%u"	},
 	{ SRP_OPT_ALLOW_EXT_SG,		"allow_ext_sg=%u"	},
 	{ SRP_OPT_SG_TABLESIZE,		"sg_tablesize=%u"	},
+	{ SRP_OPT_COMP_VECTOR,		"comp_vector=%u"	},
 	{ SRP_OPT_ERR,			NULL 			}
 };
 
@@ -2236,6 +2250,14 @@ static int srp_parse_options(const char *buf, struct srp_target_port *target)
 			target->sg_tablesize = token;
 			break;
 
+		case SRP_OPT_COMP_VECTOR:
+			if (match_int(args, &token) || token < 0) {
+				pr_warn("bad comp_vector parameter '%s'\n", p);
+				goto out;
+			}
+			target->comp_vector = token;
+			break;
+
 		default:
 			pr_warn("unknown parameter or missing value '%s' in target creation request\n",
 				p);
diff --git a/drivers/infiniband/ulp/srp/ib_srp.h b/drivers/infiniband/ulp/srp/ib_srp.h
index 66fbedda4571..e641088c14dc 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.h
+++ b/drivers/infiniband/ulp/srp/ib_srp.h
@@ -156,6 +156,7 @@ struct srp_target_port {
 	char			target_name[32];
 	unsigned int		scsi_id;
 	unsigned int		sg_tablesize;
+	int			comp_vector;
 
 	struct ib_sa_path_rec	path;
 	__be16			orig_dgid[8];