[PATCH 0/8] IB SRP initiator patches for kernel 3.12

[PATCH 0/8] IB SRP initiator patches for kernel 3.12

[Bart Van Assche]

The purpose of this InfiniBand SRP initiator patch series is as follows:
- Make the SRP initiator driver better suited for use in a H.A. setup.
   Add fast_io_fail_tmo, dev_loss_tmo and reconnect_delay parameters.
   These can be used either to speed up failover or to avoid device
   removal when e.g. using initiator side mirroring.
- Make the SRP initiator better suited for use on NUMA systems by
   making the HCA completion vector configurable.
- Improve performance by making the queue size configurable.

Changes since the previous patch series are:
- Rewrote the srp_tmo_valid() to improve readability (requested by Dave
   Dillow).
- The combination (reconnect_delay < 0 && fast_io_fail_tmo < 0 &&
   dev_loss_tmo < 0) is now rejected as requested by Dave Dillow.
- Fixed a race between transport layer failure handling and device
   removal. This issue was reported by Vu Pham.

The previous patch series can be found here:
http://thread.gmane.org/gmane.linux.drivers.rdma/16389

The individual patches in this series are:
0001-IB-srp-Keep-rport-as-long-as-the-IB-transport-layer.patch
0002-scsi_transport_srp-Add-transport-layer-error-handlin.patch
0003-IB-srp-Add-srp_terminate_io.patch
0004-IB-srp-Use-SRP-transport-layer-error-recovery.patch
0005-IB-srp-Start-timers-if-a-transport-layer-error-occur.patch
0006-IB-srp-Make-transport-layer-retry-count-configurable.patch
0007-IB-srp-Introduce-srp_alloc_req_data.patch
0008-IB-srp-Make-queue-size-configurable.patch
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH 1/8] IB/srp: Keep rport as long as the IB transport layer

[Bart Van Assche]

Keep the rport data structure around after srp_remove_host() has
finished until cleanup of the IB transport layer has finished
completely. This is necessary because later patches use the rport
pointer inside the queuecommand callback. Without this patch
accessing the rport from inside a queuecommand callback is racy
because srp_remove_host() must be invoked before scsi_remove_host()
and because the queuecommand callback may get invoked after
srp_remove_host() has finished. In other words, without this patch
the queuecommand callback may get invoked after the rport has been
removed.

Signed-off-by: Bart Van Assche <bvanassche-HInyCGIudOg@public.gmane.org>
Cc: Roland Dreier <roland-BHEL68pLQRGGvPXPguhicg@public.gmane.org>
Cc: James Bottomley <JBottomley-MU7nAjRaF3makBO8gow8eQ@public.gmane.org>
Cc: David Dillow <dillowda-1Heg1YXhbW8@public.gmane.org>
Cc: Vu Pham <vu-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Cc: Sebastian Riemer <sebastian.riemer-EIkl63zCoXaH+58JC4qpiA@public.gmane.org>
---
 drivers/infiniband/ulp/srp/ib_srp.c |    3 +++
 drivers/infiniband/ulp/srp/ib_srp.h |    1 +
 drivers/scsi/scsi_transport_srp.c   |   18 ++++++++++++++++++
 include/scsi/scsi_transport_srp.h   |    2 ++
 4 files changed, 24 insertions(+)

diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index f93baf8..de49088 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -528,11 +528,13 @@ static void srp_remove_target(struct srp_target_port *target)
 	WARN_ON_ONCE(target->state != SRP_TARGET_REMOVED);
 
 	srp_del_scsi_host_attr(target->scsi_host);
+	srp_rport_get(target->rport);
 	srp_remove_host(target->scsi_host);
 	scsi_remove_host(target->scsi_host);
 	srp_disconnect_target(target);
 	ib_destroy_cm_id(target->cm_id);
 	srp_free_target_ib(target);
+	srp_rport_put(target->rport);
 	srp_free_req_data(target);
 	scsi_host_put(target->scsi_host);
 }
@@ -1994,6 +1996,7 @@ static int srp_add_target(struct srp_host *host, struct srp_target_port *target)
 	}
 
 	rport->lld_data = target;
+	target->rport = rport;
 
 	spin_lock(&host->target_lock);
 	list_add_tail(&target->list, &host->target_list);
diff --git a/drivers/infiniband/ulp/srp/ib_srp.h b/drivers/infiniband/ulp/srp/ib_srp.h
index e641088..02392f5 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.h
+++ b/drivers/infiniband/ulp/srp/ib_srp.h
@@ -153,6 +153,7 @@ struct srp_target_port {
 	u16			io_class;
 	struct srp_host	       *srp_host;
 	struct Scsi_Host       *scsi_host;
+	struct srp_rport       *rport;
 	char			target_name[32];
 	unsigned int		scsi_id;
 	unsigned int		sg_tablesize;
diff --git a/drivers/scsi/scsi_transport_srp.c b/drivers/scsi/scsi_transport_srp.c
index f379c7f..f7ba94a 100644
--- a/drivers/scsi/scsi_transport_srp.c
+++ b/drivers/scsi/scsi_transport_srp.c
@@ -185,6 +185,24 @@ static int srp_host_match(struct attribute_container *cont, struct device *dev)
 }
 
 /**
+ * srp_rport_get() - increment rport reference count
+ */
+void srp_rport_get(struct srp_rport *rport)
+{
+	get_device(&rport->dev);
+}
+EXPORT_SYMBOL(srp_rport_get);
+
+/**
+ * srp_rport_put() - decrement rport reference count
+ */
+void srp_rport_put(struct srp_rport *rport)
+{
+	put_device(&rport->dev);
+}
+EXPORT_SYMBOL(srp_rport_put);
+
+/**
  * srp_rport_add - add a SRP remote port to the device hierarchy
  * @shost:	scsi host the remote port is connected to.
  * @ids:	The port id for the remote port.
diff --git a/include/scsi/scsi_transport_srp.h b/include/scsi/scsi_transport_srp.h
index ff0f04a..5a2d2d1 100644
--- a/include/scsi/scsi_transport_srp.h
+++ b/include/scsi/scsi_transport_srp.h
@@ -38,6 +38,8 @@ extern struct scsi_transport_template *
 srp_attach_transport(struct srp_function_template *);
 extern void srp_release_transport(struct scsi_transport_template *);
 
+extern void srp_rport_get(struct srp_rport *rport);
+extern void srp_rport_put(struct srp_rport *rport);
 extern struct srp_rport *srp_rport_add(struct Scsi_Host *,
 				       struct srp_rport_identifiers *);
 extern void srp_rport_del(struct srp_rport *);
-- 
1.7.10.4

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH 2/8] scsi_transport_srp: Add transport layer error handling

[Bart Van Assche]

Add the necessary functions in the SRP transport module to allow
an SRP initiator driver to implement transport layer error handling
similar to the functionality already provided by the FC transport
layer. This includes:
- Support for implementing fast_io_fail_tmo, the time that should
  elapse after having detected a transport layer problem and
  before failing I/O.
- Support for implementing dev_loss_tmo, the time that should
  elapse after having detected a transport layer problem and
  before removing a remote port.
- Support for periodically trying to reconnect to an SRP target
  after connection to a target has been lost.

Signed-off-by: Bart Van Assche <bvanassche-HInyCGIudOg@public.gmane.org>
Cc: Roland Dreier <roland-BHEL68pLQRGGvPXPguhicg@public.gmane.org>
Cc: James Bottomley <JBottomley-MU7nAjRaF3makBO8gow8eQ@public.gmane.org>
Cc: David Dillow <dillowda-1Heg1YXhbW8@public.gmane.org>
Cc: Vu Pham <vu-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Cc: Sebastian Riemer <sebastian.riemer-EIkl63zCoXaH+58JC4qpiA@public.gmane.org>
---
 Documentation/ABI/stable/sysfs-transport-srp |   39 ++
 drivers/scsi/scsi_transport_srp.c            |  504 +++++++++++++++++++++++++-
 include/scsi/scsi_transport_srp.h            |   65 +++-
 3 files changed, 605 insertions(+), 3 deletions(-)

diff --git a/Documentation/ABI/stable/sysfs-transport-srp b/Documentation/ABI/stable/sysfs-transport-srp
index b36fb0d..21bd480 100644
--- a/Documentation/ABI/stable/sysfs-transport-srp
+++ b/Documentation/ABI/stable/sysfs-transport-srp
@@ -5,6 +5,24 @@ Contact:	linux-scsi-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
 Description:	Instructs an SRP initiator to disconnect from a target and to
 		remove all LUNs imported from that target.
 
+What:		/sys/class/srp_remote_ports/port-<h>:<n>/dev_loss_tmo
+Date:		December 1, 2013
+KernelVersion:	3.12
+Contact:	linux-scsi-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
+Description:	Number of seconds the SCSI layer will wait after a transport
+		layer error has been observed before removing a target port.
+		Zero means immediate removal. Setting this attribute to "off"
+		will disable the dev_loss timer.
+
+What:		/sys/class/srp_remote_ports/port-<h>:<n>/fast_io_fail_tmo
+Date:		December 1, 2013
+KernelVersion:	3.12
+Contact:	linux-scsi-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
+Description:	Number of seconds the SCSI layer will wait after a transport
+		layer error has been observed before failing I/O. Zero means
+		failing I/O immediately. Setting this attribute to "off" will
+		disable the fast_io_fail timer.
+
 What:		/sys/class/srp_remote_ports/port-<h>:<n>/port_id
 Date:		June 27, 2007
 KernelVersion:	2.6.24
@@ -12,8 +30,29 @@ Contact:	linux-scsi-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
 Description:	16-byte local SRP port identifier in hexadecimal format. An
 		example: 4c:49:4e:55:58:20:56:49:4f:00:00:00:00:00:00:00.
 
+What:		/sys/class/srp_remote_ports/port-<h>:<n>/reconnect_delay
+Date:		December 1, 2013
+KernelVersion:	3.12
+Contact:	linux-scsi-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
+Description:	Number of seconds the SCSI layer will wait after a reconnect
+		attempt failed before retrying. Setting this attribute to
+		"off" will disable time-based reconnecting.
+
 What:		/sys/class/srp_remote_ports/port-<h>:<n>/roles
 Date:		June 27, 2007
 KernelVersion:	2.6.24
 Contact:	linux-scsi-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
 Description:	Role of the remote port. Either "SRP Initiator" or "SRP Target".
+
+What:		/sys/class/srp_remote_ports/port-<h>:<n>/state
+Date:		December 1, 2013
+KernelVersion:	3.12
+Contact:	linux-scsi-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
+Description:	State of the transport layer used for communication with the
+		remote port. "running" if the transport layer is operational;
+		"blocked" if a transport layer error has been encountered but
+		the fail_io_fast_tmo timer has not yet fired; "fail-fast"
+		after the fail_io_fast_tmo timer has fired and before the
+		"dev_loss_tmo" timer has fired; "lost" after the
+		"dev_loss_tmo" timer has fired and before the port is finally
+		removed.
diff --git a/drivers/scsi/scsi_transport_srp.c b/drivers/scsi/scsi_transport_srp.c
index f7ba94a..ff1baa8 100644
--- a/drivers/scsi/scsi_transport_srp.c
+++ b/drivers/scsi/scsi_transport_srp.c
@@ -24,12 +24,15 @@
 #include <linux/err.h>
 #include <linux/slab.h>
 #include <linux/string.h>
+#include <linux/delay.h>
 
 #include <scsi/scsi.h>
+#include <scsi/scsi_cmnd.h>
 #include <scsi/scsi_device.h>
 #include <scsi/scsi_host.h>
 #include <scsi/scsi_transport.h>
 #include <scsi/scsi_transport_srp.h>
+#include "scsi_priv.h"
 #include "scsi_transport_srp_internal.h"
 
 struct srp_host_attrs {
@@ -38,7 +41,7 @@ struct srp_host_attrs {
 #define to_srp_host_attrs(host)	((struct srp_host_attrs *)(host)->shost_data)
 
 #define SRP_HOST_ATTRS 0
-#define SRP_RPORT_ATTRS 3
+#define SRP_RPORT_ATTRS 8
 
 struct srp_internal {
 	struct scsi_transport_template t;
@@ -54,6 +57,36 @@ struct srp_internal {
 
 #define	dev_to_rport(d)	container_of(d, struct srp_rport, dev)
 #define transport_class_to_srp_rport(dev) dev_to_rport((dev)->parent)
+static inline struct Scsi_Host *rport_to_shost(struct srp_rport *r)
+{
+	return dev_to_shost(r->dev.parent);
+}
+
+/**
+ * srp_tmo_valid() - check timeout combination validity
+ *
+ * The combination of the three timeout parameters must be such that SCSI
+ * commands are finished in a reasonable time. Hence do not allow the fast I/O
+ * fail timeout to exceed SCSI_DEVICE_BLOCK_MAX_TIMEOUT. Furthermore, these
+ * parameters must be such that multipath can detect failed paths timely. Hence
+ * do not allow all three parameters to be disabled simultaneously.
+ */
+int srp_tmo_valid(int reconnect_delay, int fast_io_fail_tmo, int dev_loss_tmo)
+{
+	if (reconnect_delay < 0 && fast_io_fail_tmo < 0 && dev_loss_tmo < 0)
+		return -EINVAL;
+	if (reconnect_delay == 0)
+		return -EINVAL;
+	if (fast_io_fail_tmo > SCSI_DEVICE_BLOCK_MAX_TIMEOUT)
+		return -EINVAL;
+	if (dev_loss_tmo >= LONG_MAX / HZ)
+		return -EINVAL;
+	if (fast_io_fail_tmo >= 0 && dev_loss_tmo >= 0 &&
+	    fast_io_fail_tmo >= dev_loss_tmo)
+		return -EINVAL;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(srp_tmo_valid);
 
 static int srp_host_setup(struct transport_container *tc, struct device *dev,
 			  struct device *cdev)
@@ -134,10 +167,447 @@ static ssize_t store_srp_rport_delete(struct device *dev,
 
 static DEVICE_ATTR(delete, S_IWUSR, NULL, store_srp_rport_delete);
 
+static ssize_t show_srp_rport_state(struct device *dev,
+				    struct device_attribute *attr,
+				    char *buf)
+{
+	static const char *const state_name[] = {
+		[SRP_RPORT_RUNNING]	= "running",
+		[SRP_RPORT_BLOCKED]	= "blocked",
+		[SRP_RPORT_FAIL_FAST]	= "fail-fast",
+		[SRP_RPORT_LOST]	= "lost",
+	};
+	struct srp_rport *rport = transport_class_to_srp_rport(dev);
+	enum srp_rport_state state = rport->state;
+
+	return sprintf(buf, "%s\n",
+		       (unsigned)state < ARRAY_SIZE(state_name) ?
+		       state_name[state] : "???");
+}
+
+static DEVICE_ATTR(state, S_IRUGO, show_srp_rport_state, NULL);
+
+static ssize_t show_reconnect_delay(struct device *dev,
+				    struct device_attribute *attr, char *buf)
+{
+	struct srp_rport *rport = transport_class_to_srp_rport(dev);
+
+	if (rport->reconnect_delay >= 0)
+		return sprintf(buf, "%d\n", rport->reconnect_delay);
+	else
+		return sprintf(buf, "off\n");
+}
+
+static ssize_t store_reconnect_delay(struct device *dev,
+				     struct device_attribute *attr,
+				     const char *buf, const size_t count)
+{
+	struct srp_rport *rport = transport_class_to_srp_rport(dev);
+	int res, delay;
+
+	if (strncmp(buf, "off", 3) != 0) {
+		res = kstrtoint(buf, 0, &delay);
+		if (res)
+			goto out;
+	} else {
+		delay = -1;
+	}
+	res = srp_tmo_valid(delay, rport->fast_io_fail_tmo,
+			    rport->dev_loss_tmo);
+	if (res)
+		goto out;
+
+	if (rport->reconnect_delay <= 0 && delay > 0 &&
+	    rport->state != SRP_RPORT_RUNNING) {
+		queue_delayed_work(system_long_wq, &rport->reconnect_work,
+				   delay * HZ);
+	} else if (delay <= 0) {
+		cancel_delayed_work(&rport->reconnect_work);
+	}
+	rport->reconnect_delay = delay;
+	res = count;
+
+out:
+	return res;
+}
+
+static DEVICE_ATTR(reconnect_delay, S_IRUGO | S_IWUSR, show_reconnect_delay,
+		   store_reconnect_delay);
+
+static ssize_t show_failed_reconnects(struct device *dev,
+				      struct device_attribute *attr, char *buf)
+{
+	struct srp_rport *rport = transport_class_to_srp_rport(dev);
+
+	return sprintf(buf, "%d\n", rport->failed_reconnects);
+}
+
+static DEVICE_ATTR(failed_reconnects, S_IRUGO, show_failed_reconnects, NULL);
+
+static ssize_t show_srp_rport_fast_io_fail_tmo(struct device *dev,
+					       struct device_attribute *attr,
+					       char *buf)
+{
+	struct srp_rport *rport = transport_class_to_srp_rport(dev);
+
+	if (rport->fast_io_fail_tmo >= 0)
+		return sprintf(buf, "%d\n", rport->fast_io_fail_tmo);
+	else
+		return sprintf(buf, "off\n");
+}
+
+static ssize_t store_srp_rport_fast_io_fail_tmo(struct device *dev,
+						struct device_attribute *attr,
+						const char *buf, size_t count)
+{
+	struct srp_rport *rport = transport_class_to_srp_rport(dev);
+	int res;
+	int fast_io_fail_tmo;
+
+	if (strncmp(buf, "off", 3) != 0) {
+		res = kstrtoint(buf, 0, &fast_io_fail_tmo);
+		if (res)
+			goto out;
+	} else {
+		fast_io_fail_tmo = -1;
+	}
+	res = srp_tmo_valid(rport->reconnect_delay, fast_io_fail_tmo,
+			    rport->dev_loss_tmo);
+	if (res)
+		goto out;
+	rport->fast_io_fail_tmo = fast_io_fail_tmo;
+	res = count;
+
+out:
+	return res;
+}
+
+static DEVICE_ATTR(fast_io_fail_tmo, S_IRUGO | S_IWUSR,
+		   show_srp_rport_fast_io_fail_tmo,
+		   store_srp_rport_fast_io_fail_tmo);
+
+static ssize_t show_srp_rport_dev_loss_tmo(struct device *dev,
+					   struct device_attribute *attr,
+					   char *buf)
+{
+	struct srp_rport *rport = transport_class_to_srp_rport(dev);
+
+	if (rport->dev_loss_tmo >= 0)
+		return sprintf(buf, "%d\n", rport->dev_loss_tmo);
+	else
+		return sprintf(buf, "off\n");
+}
+
+static ssize_t store_srp_rport_dev_loss_tmo(struct device *dev,
+					    struct device_attribute *attr,
+					    const char *buf, size_t count)
+{
+	struct srp_rport *rport = transport_class_to_srp_rport(dev);
+	int res;
+	int dev_loss_tmo;
+
+	if (strncmp(buf, "off", 3) != 0) {
+		res = kstrtoint(buf, 0, &dev_loss_tmo);
+		if (res)
+			goto out;
+	} else {
+		dev_loss_tmo = -1;
+	}
+	res = srp_tmo_valid(rport->reconnect_delay, rport->fast_io_fail_tmo,
+			    dev_loss_tmo);
+	if (res)
+		goto out;
+	rport->dev_loss_tmo = dev_loss_tmo;
+	res = count;
+
+out:
+	return res;
+}
+
+static DEVICE_ATTR(dev_loss_tmo, S_IRUGO | S_IWUSR,
+		   show_srp_rport_dev_loss_tmo,
+		   store_srp_rport_dev_loss_tmo);
+
+static int srp_rport_set_state(struct srp_rport *rport,
+			       enum srp_rport_state new_state)
+{
+	enum srp_rport_state old_state = rport->state;
+
+	lockdep_assert_held(&rport->mutex);
+
+	switch (new_state) {
+	case SRP_RPORT_RUNNING:
+		switch (old_state) {
+		case SRP_RPORT_LOST:
+			goto invalid;
+		default:
+			break;
+		}
+		break;
+	case SRP_RPORT_BLOCKED:
+		switch (old_state) {
+		case SRP_RPORT_RUNNING:
+			break;
+		default:
+			goto invalid;
+		}
+		break;
+	case SRP_RPORT_FAIL_FAST:
+		switch (old_state) {
+		case SRP_RPORT_LOST:
+			goto invalid;
+		default:
+			break;
+		}
+		break;
+	case SRP_RPORT_LOST:
+		break;
+	}
+	rport->state = new_state;
+	return 0;
+
+invalid:
+	return -EINVAL;
+}
+
+/**
+ * scsi_request_fn_active() - number of kernel threads inside scsi_request_fn()
+ */
+static int scsi_request_fn_active(struct Scsi_Host *shost)
+{
+	struct scsi_device *sdev;
+	struct request_queue *q;
+	int request_fn_active = 0;
+
+	shost_for_each_device(sdev, shost) {
+		q = sdev->request_queue;
+
+		spin_lock_irq(q->queue_lock);
+		request_fn_active += q->request_fn_active;
+		spin_unlock_irq(q->queue_lock);
+	}
+
+	return request_fn_active;
+}
+
+/**
+ * srp_reconnect_rport() - reconnect to an SRP target port
+ *
+ * Blocks SCSI command queueing before invoking reconnect() such that
+ * queuecommand() won't be invoked concurrently with reconnect(). This is
+ * important since a reconnect() implementation may reallocate resources
+ * needed by queuecommand(). Please note that this function neither waits
+ * until outstanding requests have finished nor tries to abort these. It is
+ * the responsibility of the reconnect() function to finish outstanding
+ * commands before reconnecting to the target port.
+ */
+int srp_reconnect_rport(struct srp_rport *rport)
+{
+	struct Scsi_Host *shost = rport_to_shost(rport);
+	struct srp_internal *i = to_srp_internal(shost->transportt);
+	struct scsi_device *sdev;
+	int res;
+
+	pr_debug("SCSI host %s\n", dev_name(&shost->shost_gendev));
+
+	res = mutex_lock_interruptible(&rport->mutex);
+	if (res)
+		goto out;
+	scsi_target_block(&shost->shost_gendev);
+	while (scsi_request_fn_active(shost))
+		msleep(20);
+	res = i->f->reconnect(rport);
+	pr_debug("%s (state %d): transport.reconnect() returned %d\n",
+		 dev_name(&shost->shost_gendev), rport->state, res);
+	if (res == 0) {
+		mutex_unlock(&rport->mutex);
+
+		cancel_delayed_work(&rport->fast_io_fail_work);
+		cancel_delayed_work(&rport->dev_loss_work);
+
+		mutex_lock(&rport->mutex);
+		rport->failed_reconnects = 0;
+		srp_rport_set_state(rport, SRP_RPORT_RUNNING);
+		scsi_target_unblock(&shost->shost_gendev, SDEV_RUNNING);
+		/*
+		 * It can occur that after fast_io_fail_tmo expired and before
+		 * dev_loss_tmo expired that the SCSI error handler has
+		 * offlined one or more devices. scsi_target_unblock() doesn't
+		 * change the state of these devices into running, so do that
+		 * explicitly.
+		 */
+		spin_lock_irq(shost->host_lock);
+		__shost_for_each_device(sdev, shost)
+			if (sdev->sdev_state == SDEV_OFFLINE)
+				sdev->sdev_state = SDEV_RUNNING;
+		spin_unlock_irq(shost->host_lock);
+	} else if (rport->state == SRP_RPORT_RUNNING) {
+		srp_rport_set_state(rport, SRP_RPORT_FAIL_FAST);
+		scsi_target_unblock(&shost->shost_gendev,
+				    SDEV_TRANSPORT_OFFLINE);
+	}
+	mutex_unlock(&rport->mutex);
+
+out:
+	return res;
+}
+EXPORT_SYMBOL(srp_reconnect_rport);
+
+/**
+ * srp_reconnect_work() - reconnect and schedule a new attempt if necessary
+ */
+static void srp_reconnect_work(struct work_struct *work)
+{
+	struct srp_rport *rport = container_of(to_delayed_work(work),
+					struct srp_rport, reconnect_work);
+	struct Scsi_Host *shost = rport_to_shost(rport);
+	int delay, res;
+
+	res = srp_reconnect_rport(rport);
+	if (res != 0) {
+		shost_printk(KERN_ERR, shost,
+			     "reconnect attempt %d failed (%d)\n",
+			     ++rport->failed_reconnects, res);
+		delay = rport->reconnect_delay *
+			min(100, max(1, rport->failed_reconnects - 10));
+		if (delay > 0)
+			queue_delayed_work(system_long_wq,
+					   &rport->reconnect_work, delay * HZ);
+	}
+}
+
+static void __rport_fail_io_fast(struct srp_rport *rport)
+{
+	struct Scsi_Host *shost = rport_to_shost(rport);
+	struct srp_internal *i;
+
+	lockdep_assert_held(&rport->mutex);
+
+	if (srp_rport_set_state(rport, SRP_RPORT_FAIL_FAST))
+		return;
+	scsi_target_unblock(rport->dev.parent, SDEV_TRANSPORT_OFFLINE);
+
+	/* Involve the LLD if possible to terminate all I/O on the rport. */
+	i = to_srp_internal(shost->transportt);
+	if (i->f->terminate_rport_io)
+		i->f->terminate_rport_io(rport);
+}
+
+/**
+ * rport_fast_io_fail_timedout() - fast I/O failure timeout handler
+ */
+static void rport_fast_io_fail_timedout(struct work_struct *work)
+{
+	struct srp_rport *rport = container_of(to_delayed_work(work),
+					struct srp_rport, fast_io_fail_work);
+	struct Scsi_Host *shost = rport_to_shost(rport);
+
+	pr_debug("fast_io_fail_tmo expired for %s.\n",
+		 dev_name(&shost->shost_gendev));
+
+	mutex_lock(&rport->mutex);
+	__rport_fail_io_fast(rport);
+	mutex_unlock(&rport->mutex);
+}
+
+/**
+ * rport_dev_loss_timedout() - device loss timeout handler
+ */
+static void rport_dev_loss_timedout(struct work_struct *work)
+{
+	struct srp_rport *rport = container_of(to_delayed_work(work),
+					struct srp_rport, dev_loss_work);
+	struct Scsi_Host *shost = rport_to_shost(rport);
+	struct srp_internal *i = to_srp_internal(shost->transportt);
+
+	pr_err("dev_loss_tmo expired for %s.\n",
+	       dev_name(&shost->shost_gendev));
+
+	mutex_lock(&rport->mutex);
+	WARN_ON(srp_rport_set_state(rport, SRP_RPORT_LOST) != 0);
+	scsi_target_unblock(rport->dev.parent, SDEV_TRANSPORT_OFFLINE);
+	mutex_unlock(&rport->mutex);
+
+	i->f->rport_delete(rport);
+}
+
+/**
+ * srp_start_tl_fail_timers() - start the transport layer failure timers
+ *
+ * Start the transport layer fast I/O failure and device loss timers. Do not
+ * modify a timer that was already started.
+ */
+void srp_start_tl_fail_timers(struct srp_rport *rport)
+{
+	struct Scsi_Host *shost = rport_to_shost(rport);
+	int fast_io_fail_tmo, dev_loss_tmo, delay;
+
+	mutex_lock(&rport->mutex);
+	if (!rport->deleted) {
+		delay = rport->reconnect_delay;
+		fast_io_fail_tmo = rport->fast_io_fail_tmo;
+		dev_loss_tmo = rport->dev_loss_tmo;
+		pr_debug("%s current state: %d\n",
+			 dev_name(&shost->shost_gendev), rport->state);
+
+		if (delay > 0)
+			queue_delayed_work(system_long_wq,
+					   &rport->reconnect_work,
+					   1UL * delay * HZ);
+		if (fast_io_fail_tmo >= 0 &&
+		    srp_rport_set_state(rport, SRP_RPORT_BLOCKED) == 0) {
+			pr_debug("%s new state: %d\n",
+				 dev_name(&shost->shost_gendev),
+				 rport->state);
+			scsi_target_block(&shost->shost_gendev);
+			queue_delayed_work(system_long_wq,
+					   &rport->fast_io_fail_work,
+					   1UL * fast_io_fail_tmo * HZ);
+		}
+		if (dev_loss_tmo >= 0)
+			queue_delayed_work(system_long_wq,
+					   &rport->dev_loss_work,
+					   1UL * dev_loss_tmo * HZ);
+	} else {
+		pr_debug("%s has already been deleted\n",
+			 dev_name(&shost->shost_gendev));
+		srp_rport_set_state(rport, SRP_RPORT_FAIL_FAST);
+		scsi_target_unblock(&shost->shost_gendev,
+				    SDEV_TRANSPORT_OFFLINE);
+	}
+	mutex_unlock(&rport->mutex);
+}
+EXPORT_SYMBOL(srp_start_tl_fail_timers);
+
+/**
+ * srp_timed_out() - SRP transport intercept of the SCSI timeout EH
+ *
+ * If a timeout occurs while an rport is in the blocked state, ask the SCSI
+ * EH to continue waiting (BLK_EH_RESET_TIMER). Otherwise let the SCSI core
+ * handle the timeout (BLK_EH_NOT_HANDLED).
+ *
+ * Note: This function is called from soft-IRQ context and with the request
+ * queue lock held.
+ */
+static enum blk_eh_timer_return srp_timed_out(struct scsi_cmnd *scmd)
+{
+	struct scsi_device *sdev = scmd->device;
+	struct Scsi_Host *shost = sdev->host;
+	struct srp_internal *i = to_srp_internal(shost->transportt);
+
+	pr_debug("timeout for sdev %s\n", dev_name(&sdev->sdev_gendev));
+	return i->f->reset_timer_if_blocked && scsi_device_blocked(sdev) ?
+		BLK_EH_RESET_TIMER : BLK_EH_NOT_HANDLED;
+}
+
 static void srp_rport_release(struct device *dev)
 {
 	struct srp_rport *rport = dev_to_rport(dev);
 
+	cancel_delayed_work_sync(&rport->reconnect_work);
+	cancel_delayed_work_sync(&rport->fast_io_fail_work);
+	cancel_delayed_work_sync(&rport->dev_loss_work);
+
 	put_device(dev->parent);
 	kfree(rport);
 }
@@ -214,12 +684,15 @@ struct srp_rport *srp_rport_add(struct Scsi_Host *shost,
 {
 	struct srp_rport *rport;
 	struct device *parent = &shost->shost_gendev;
+	struct srp_internal *i = to_srp_internal(shost->transportt);
 	int id, ret;
 
 	rport = kzalloc(sizeof(*rport), GFP_KERNEL);
 	if (!rport)
 		return ERR_PTR(-ENOMEM);
 
+	mutex_init(&rport->mutex);
+
 	device_initialize(&rport->dev);
 
 	rport->dev.parent = get_device(parent);
@@ -228,6 +701,17 @@ struct srp_rport *srp_rport_add(struct Scsi_Host *shost,
 	memcpy(rport->port_id, ids->port_id, sizeof(rport->port_id));
 	rport->roles = ids->roles;
 
+	if (i->f->reconnect)
+		rport->reconnect_delay = i->f->reconnect_delay ?
+			*i->f->reconnect_delay : 10;
+	INIT_DELAYED_WORK(&rport->reconnect_work, srp_reconnect_work);
+	rport->fast_io_fail_tmo = i->f->fast_io_fail_tmo ?
+		*i->f->fast_io_fail_tmo : 15;
+	rport->dev_loss_tmo = i->f->dev_loss_tmo ? *i->f->dev_loss_tmo : 600;
+	INIT_DELAYED_WORK(&rport->fast_io_fail_work,
+			  rport_fast_io_fail_timedout);
+	INIT_DELAYED_WORK(&rport->dev_loss_work, rport_dev_loss_timedout);
+
 	id = atomic_inc_return(&to_srp_host_attrs(shost)->next_port_id);
 	dev_set_name(&rport->dev, "port-%d:%d", shost->host_no, id);
 
@@ -277,6 +761,13 @@ void srp_rport_del(struct srp_rport *rport)
 	transport_remove_device(dev);
 	device_del(dev);
 	transport_destroy_device(dev);
+
+	mutex_lock(&rport->mutex);
+	if (rport->state == SRP_RPORT_BLOCKED)
+		__rport_fail_io_fast(rport);
+	rport->deleted = true;
+	mutex_unlock(&rport->mutex);
+
 	put_device(dev);
 }
 EXPORT_SYMBOL_GPL(srp_rport_del);
@@ -328,6 +819,8 @@ srp_attach_transport(struct srp_function_template *ft)
 	if (!i)
 		return NULL;
 
+	i->t.eh_timed_out = srp_timed_out;
+
 	i->t.tsk_mgmt_response = srp_tsk_mgmt_response;
 	i->t.it_nexus_response = srp_it_nexus_response;
 
@@ -345,6 +838,15 @@ srp_attach_transport(struct srp_function_template *ft)
 	count = 0;
 	i->rport_attrs[count++] = &dev_attr_port_id;
 	i->rport_attrs[count++] = &dev_attr_roles;
+	if (ft->has_rport_state) {
+		i->rport_attrs[count++] = &dev_attr_state;
+		i->rport_attrs[count++] = &dev_attr_fast_io_fail_tmo;
+		i->rport_attrs[count++] = &dev_attr_dev_loss_tmo;
+	}
+	if (ft->reconnect) {
+		i->rport_attrs[count++] = &dev_attr_reconnect_delay;
+		i->rport_attrs[count++] = &dev_attr_failed_reconnects;
+	}
 	if (ft->rport_delete)
 		i->rport_attrs[count++] = &dev_attr_delete;
 	i->rport_attrs[count++] = NULL;
diff --git a/include/scsi/scsi_transport_srp.h b/include/scsi/scsi_transport_srp.h
index 5a2d2d1..4795dec 100644
--- a/include/scsi/scsi_transport_srp.h
+++ b/include/scsi/scsi_transport_srp.h
@@ -13,6 +13,26 @@ struct srp_rport_identifiers {
 	u8 roles;
 };
 
+/**
+ * enum srp_rport_state - SRP transport layer state
+ * @SRP_RPORT_RUNNING:   Transport layer operational.
+ * @SRP_RPORT_BLOCKED:   Transport layer not operational; fast I/O fail timer
+ *                       is running and I/O has been blocked.
+ * @SRP_RPORT_FAIL_FAST: Fast I/O fail timer has expired; fail I/O fast.
+ * @SRP_RPORT_LOST:      Device loss timer has expired; port is being removed.
+ */
+enum srp_rport_state {
+	SRP_RPORT_RUNNING,
+	SRP_RPORT_BLOCKED,
+	SRP_RPORT_FAIL_FAST,
+	SRP_RPORT_LOST,
+};
+
+/**
+ * struct srp_rport
+ * @mutex:   Protects against concurrent rport fast_io_fail / dev_loss_tmo /
+ *   reconnect activity.
+ */
 struct srp_rport {
 	/* for initiator and target drivers */
 
@@ -23,11 +43,29 @@ struct srp_rport {
 
 	/* for initiator drivers */
 
-	void *lld_data;	/* LLD private data */
+	void			*lld_data;	/* LLD private data */
+
+	struct mutex		mutex;
+	enum srp_rport_state	state;
+	bool			deleted;
+	int			reconnect_delay;
+	int			failed_reconnects;
+	struct delayed_work	reconnect_work;
+	int			fast_io_fail_tmo;
+	int			dev_loss_tmo;
+	struct delayed_work	fast_io_fail_work;
+	struct delayed_work	dev_loss_work;
 };
 
 struct srp_function_template {
 	/* for initiator drivers */
+	bool has_rport_state;
+	bool reset_timer_if_blocked;
+	int *reconnect_delay;
+	int *fast_io_fail_tmo;
+	int *dev_loss_tmo;
+	int (*reconnect)(struct srp_rport *rport);
+	void (*terminate_rport_io)(struct srp_rport *rport);
 	void (*rport_delete)(struct srp_rport *rport);
 	/* for target drivers */
 	int (* tsk_mgmt_response)(struct Scsi_Host *, u64, u64, int);
@@ -43,7 +81,30 @@ extern void srp_rport_put(struct srp_rport *rport);
 extern struct srp_rport *srp_rport_add(struct Scsi_Host *,
 				       struct srp_rport_identifiers *);
 extern void srp_rport_del(struct srp_rport *);
-
+extern int srp_tmo_valid(int reconnect_delay, int fast_io_fail_tmo,
+			 int dev_loss_tmo);
+extern int srp_reconnect_rport(struct srp_rport *rport);
+extern void srp_start_tl_fail_timers(struct srp_rport *rport);
 extern void srp_remove_host(struct Scsi_Host *);
 
+/**
+ * srp_chkready() - evaluate the transport layer state before I/O
+ *
+ * Returns a SCSI result code that can be returned by the LLD. The role of
+ * this function is similar to that of fc_remote_port_chkready().
+ */
+static inline int srp_chkready(struct srp_rport *rport)
+{
+	switch (rport->state) {
+	case SRP_RPORT_RUNNING:
+	case SRP_RPORT_BLOCKED:
+	default:
+		return 0;
+	case SRP_RPORT_FAIL_FAST:
+		return DID_TRANSPORT_FAILFAST << 16;
+	case SRP_RPORT_LOST:
+		return DID_NO_CONNECT << 16;
+	}
+}
+
 #endif
-- 
1.7.10.4

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: [PATCH 0/8] IB SRP initiator patches for kernel 3.12

[David Dillow]

On Tue, 2013-08-20 at 14:41 +0200, Bart Van Assche wrote:
> Changes since the previous patch series are:
> - Rewrote the srp_tmo_valid() to improve readability (requested by Dave
>    Dillow).
> - The combination (reconnect_delay < 0 && fast_io_fail_tmo < 0 &&
>    dev_loss_tmo < 0) is now rejected as requested by Dave Dillow.
> - Fixed a race between transport layer failure handling and device
>    removal. This issue was reported by Vu Pham.

For patches 1-6,

Acked-by: David Dillow <dillowda-1Heg1YXhbW8@public.gmane.org>
-- 
Dave Dillow
National Center for Computational Science
Oak Ridge National Laboratory
(865) 241-6602 office


--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html