From f0c0a376d0fcd4c5579ecf5e95f88387cba85211 Mon Sep 17 00:00:00 2001
From: Mike Christie <michaelc@cs.wisc.edu>
Date: Sun, 17 Aug 2008 15:24:38 -0500
Subject: [SCSI] Add helper code so transport classes/driver can control
 queueing (v3)

SCSI-ml manages the queueing limits for the device and host, but
does not do so at the target level. However something something similar
can come in userful when a driver is transitioning a transport object to
the the blocked state, becuase at that time we do not want to queue
io and we do not want the queuecommand to be called again.

The patch adds code similar to the exisiting SCSI_ML_*BUSY handlers.
You can now return SCSI_MLQUEUE_TARGET_BUSY when we hit
a transport level queueing issue like the hw cannot allocate some
resource at the iscsi session/connection level, or the target has temporarily
closed or shrunk the queueing window, or if we are transitioning
to the blocked state.

bnx2i, when they rework their firmware according to netdev
developers requests, will also need to be able to limit queueing at this
level. bnx2i will hook into libiscsi, but will allocate a scsi host per
netdevice/hba, so unlike pure software iscsi/iser which is allocating
a host per session, it cannot set the scsi_host->can_queue and return
SCSI_MLQUEUE_HOST_BUSY to reflect queueing limits on the transport.

The iscsi class/driver can also set a scsi_target->can_queue value which
reflects the max commands the driver/class can support. For iscsi this
reflects the number of commands we can support for each session due to
session/connection hw limits, driver limits, and to also reflect the
session/targets's queueing window.

Changes:
v1 - initial patch.
v2 - Fix scsi_run_queue handling of multiple blocked targets.
Previously we would break from the main loop if a device was added back on
the starved list. We now run over the list and check if any target is
blocked.
v3 - Rediff for scsi-misc.

Signed-off-by: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
---
 include/scsi/scsi.h        |  1 +
 include/scsi/scsi_device.h | 10 ++++++++++
 2 files changed, 11 insertions(+)

(limited to 'include')

diff --git a/include/scsi/scsi.h b/include/scsi/scsi.h
index 192f8716aa9e..3a5662b2817e 100644
--- a/include/scsi/scsi.h
+++ b/include/scsi/scsi.h
@@ -426,6 +426,7 @@ static inline int scsi_is_wlun(unsigned int lun)
 #define SCSI_MLQUEUE_HOST_BUSY   0x1055
 #define SCSI_MLQUEUE_DEVICE_BUSY 0x1056
 #define SCSI_MLQUEUE_EH_RETRY    0x1057
+#define SCSI_MLQUEUE_TARGET_BUSY 0x1058
 
 /*
  *  Use these to separate status msg and our bytes
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index b49e725be039..a37a8148a310 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -238,6 +238,16 @@ struct scsi_target {
 						 * for the device at a time. */
 	unsigned int		pdt_1f_for_no_lun;	/* PDT = 0x1f */
 						/* means no lun present */
+	/* commands actually active on LLD. protected by host lock. */
+	unsigned int		target_busy;
+	/*
+	 * LLDs should set this in the slave_alloc host template callout.
+	 * If set to zero then there is not limit.
+	 */
+	unsigned int		can_queue;
+	unsigned int		target_blocked;
+	unsigned int		max_target_blocked;
+#define SCSI_DEFAULT_TARGET_BLOCKED	3
 
 	char			scsi_level;
 	struct execute_work	ew;
-- 
cgit v1.2.3-59-g8ed1b


From fff9d40ce0eb4b46f3e186823ceab6bc02c3e5d3 Mon Sep 17 00:00:00 2001
From: Mike Christie <michaelc@cs.wisc.edu>
Date: Tue, 19 Aug 2008 18:45:23 -0500
Subject: [SCSI] fc class: unblock target after calling terminate callback
 (take 2)

When we block a rport and the driver implements the terminate
callback we will fail IO that was running quickly. However
IO that was in the scsi_device/block queue sits there until
the dev_loss_tmo fires, and this can make it look like IO is
lost because new IO will get executed but that IO stuck in
the blocked queue sits there for some time longer.

With this patch when the fast io fail tmo fires, we will
fail the blocked IO and any new IO. This patch also allows
all drivers to partially support the fast io fail tmo. If the
terminate io callback is not implemented, we will still fail blocked
IO and any new IO, so multipath can handle that.

This patch also allows the fc and iscsi classes to implement the
same behavior. The timers are just unfornately named differently.

This patch also fixes the problem where drivers were unblocking
the target in their terminate callback, which was needed for
rport removal, but for fast io fail timeout it would cause
IO to bounce arround the scsi/block layer and the LLD queuecommand.
And it for drivers that could have IO stuck but did not have
a terminate callback the unblock calls in the class will fix
them.

v2.
- fix up bit setting style to meet JamesS's pref.
- Broke out new host byte error changes to make it easier to read.
- added JamesS's ack from list.
v1
- initial patch

Signed-off-by: Mike Christie <michaelc@cs.wisc.edu>
Acked-by: James Smart <James.Smart@emulex.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
---
 drivers/scsi/scsi_transport_fc.c | 47 ++++++++++++++++++++++++----------------
 include/scsi/scsi_transport_fc.h |  6 ++++-
 2 files changed, 33 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/scsi_transport_fc.c b/drivers/scsi/scsi_transport_fc.c
index d5f7653bb94b..1e71abf0607a 100644
--- a/drivers/scsi/scsi_transport_fc.c
+++ b/drivers/scsi/scsi_transport_fc.c
@@ -2133,8 +2133,7 @@ fc_attach_transport(struct fc_function_template *ft)
 	SETUP_PRIVATE_RPORT_ATTRIBUTE_RD(roles);
 	SETUP_PRIVATE_RPORT_ATTRIBUTE_RD(port_state);
 	SETUP_PRIVATE_RPORT_ATTRIBUTE_RD(scsi_target_id);
-	if (ft->terminate_rport_io)
-		SETUP_PRIVATE_RPORT_ATTRIBUTE_RW(fast_io_fail_tmo);
+	SETUP_PRIVATE_RPORT_ATTRIBUTE_RW(fast_io_fail_tmo);
 
 	BUG_ON(count > FC_RPORT_NUM_ATTRS);
 
@@ -2328,6 +2327,22 @@ fc_remove_host(struct Scsi_Host *shost)
 }
 EXPORT_SYMBOL(fc_remove_host);
 
+static void fc_terminate_rport_io(struct fc_rport *rport)
+{
+	struct Scsi_Host *shost = rport_to_shost(rport);
+	struct fc_internal *i = to_fc_internal(shost->transportt);
+
+	/* Involve the LLDD if possible to terminate all io on the rport. */
+	if (i->f->terminate_rport_io)
+		i->f->terminate_rport_io(rport);
+
+	/*
+	 * must unblock to flush queued IO. The caller will have set
+	 * the port_state or flags, so that fc_remote_port_chkready will
+	 * fail IO.
+	 */
+	scsi_target_unblock(&rport->dev);
+}
 
 /**
  * fc_starget_delete - called to delete the scsi decendents of an rport
@@ -2340,13 +2355,8 @@ fc_starget_delete(struct work_struct *work)
 {
 	struct fc_rport *rport =
 		container_of(work, struct fc_rport, stgt_delete_work);
-	struct Scsi_Host *shost = rport_to_shost(rport);
-	struct fc_internal *i = to_fc_internal(shost->transportt);
-
-	/* Involve the LLDD if possible to terminate all io on the rport. */
-	if (i->f->terminate_rport_io)
-		i->f->terminate_rport_io(rport);
 
+	fc_terminate_rport_io(rport);
 	scsi_remove_target(&rport->dev);
 }
 
@@ -2372,10 +2382,7 @@ fc_rport_final_delete(struct work_struct *work)
 	if (rport->flags & FC_RPORT_SCAN_PENDING)
 		scsi_flush_work(shost);
 
-	/* involve the LLDD to terminate all pending i/o */
-	if (i->f->terminate_rport_io)
-		i->f->terminate_rport_io(rport);
-
+	fc_terminate_rport_io(rport);
 	/*
 	 * Cancel any outstanding timers. These should really exist
 	 * only when rmmod'ing the LLDD and we're asking for
@@ -2639,7 +2646,8 @@ fc_remote_port_add(struct Scsi_Host *shost, int channel,
 
 				spin_lock_irqsave(shost->host_lock, flags);
 
-				rport->flags &= ~FC_RPORT_DEVLOSS_PENDING;
+				rport->flags &= ~(FC_RPORT_FAST_FAIL_TIMEDOUT |
+						  FC_RPORT_DEVLOSS_PENDING);
 
 				/* if target, initiate a scan */
 				if (rport->scsi_target_id != -1) {
@@ -2702,6 +2710,7 @@ fc_remote_port_add(struct Scsi_Host *shost, int channel,
 			rport->port_id = ids->port_id;
 			rport->roles = ids->roles;
 			rport->port_state = FC_PORTSTATE_ONLINE;
+			rport->flags &= ~FC_RPORT_FAST_FAIL_TIMEDOUT;
 
 			if (fci->f->dd_fcrport_size)
 				memset(rport->dd_data, 0,
@@ -2784,7 +2793,6 @@ void
 fc_remote_port_delete(struct fc_rport  *rport)
 {
 	struct Scsi_Host *shost = rport_to_shost(rport);
-	struct fc_internal *i = to_fc_internal(shost->transportt);
 	int timeout = rport->dev_loss_tmo;
 	unsigned long flags;
 
@@ -2830,7 +2838,7 @@ fc_remote_port_delete(struct fc_rport  *rport)
 
 	/* see if we need to kill io faster than waiting for device loss */
 	if ((rport->fast_io_fail_tmo != -1) &&
-	    (rport->fast_io_fail_tmo < timeout) && (i->f->terminate_rport_io))
+	    (rport->fast_io_fail_tmo < timeout))
 		fc_queue_devloss_work(shost, &rport->fail_io_work,
 					rport->fast_io_fail_tmo * HZ);
 
@@ -2906,7 +2914,8 @@ fc_remote_port_rolechg(struct fc_rport  *rport, u32 roles)
 			fc_flush_devloss(shost);
 
 		spin_lock_irqsave(shost->host_lock, flags);
-		rport->flags &= ~FC_RPORT_DEVLOSS_PENDING;
+		rport->flags &= ~(FC_RPORT_FAST_FAIL_TIMEDOUT |
+				  FC_RPORT_DEVLOSS_PENDING);
 		spin_unlock_irqrestore(shost->host_lock, flags);
 
 		/* ensure any stgt delete functions are done */
@@ -3001,6 +3010,7 @@ fc_timeout_deleted_rport(struct work_struct *work)
 	rport->supported_classes = FC_COS_UNSPECIFIED;
 	rport->roles = FC_PORT_ROLE_UNKNOWN;
 	rport->port_state = FC_PORTSTATE_NOTPRESENT;
+	rport->flags &= ~FC_RPORT_FAST_FAIL_TIMEDOUT;
 
 	/* remove the identifiers that aren't used in the consisting binding */
 	switch (fc_host->tgtid_bind_type) {
@@ -3043,13 +3053,12 @@ fc_timeout_fail_rport_io(struct work_struct *work)
 {
 	struct fc_rport *rport =
 		container_of(work, struct fc_rport, fail_io_work.work);
-	struct Scsi_Host *shost = rport_to_shost(rport);
-	struct fc_internal *i = to_fc_internal(shost->transportt);
 
 	if (rport->port_state != FC_PORTSTATE_BLOCKED)
 		return;
 
-	i->f->terminate_rport_io(rport);
+	rport->flags |= FC_RPORT_FAST_FAIL_TIMEDOUT;
+	fc_terminate_rport_io(rport);
 }
 
 /**
diff --git a/include/scsi/scsi_transport_fc.h b/include/scsi/scsi_transport_fc.h
index 21018a4df452..fb8d01370663 100644
--- a/include/scsi/scsi_transport_fc.h
+++ b/include/scsi/scsi_transport_fc.h
@@ -357,6 +357,7 @@ struct fc_rport {	/* aka fc_starget_attrs */
 /* bit field values for struct fc_rport "flags" field: */
 #define FC_RPORT_DEVLOSS_PENDING	0x01
 #define FC_RPORT_SCAN_PENDING		0x02
+#define FC_RPORT_FAST_FAIL_TIMEDOUT	0x03
 
 #define	dev_to_rport(d)				\
 	container_of(d, struct fc_rport, dev)
@@ -683,7 +684,10 @@ fc_remote_port_chkready(struct fc_rport *rport)
 			result = DID_NO_CONNECT << 16;
 		break;
 	case FC_PORTSTATE_BLOCKED:
-		result = DID_IMM_RETRY << 16;
+		if (rport->flags & FC_RPORT_FAST_FAIL_TIMEDOUT)
+			result = DID_NO_CONNECT << 16;
+		else
+			result = DID_IMM_RETRY << 16;
 		break;
 	default:
 		result = DID_NO_CONNECT << 16;
-- 
cgit v1.2.3-59-g8ed1b


From a4dfaa6f2e55b736adf2719133996f7e7dc309bc Mon Sep 17 00:00:00 2001
From: Mike Christie <michaelc@cs.wisc.edu>
Date: Tue, 19 Aug 2008 18:45:25 -0500
Subject: [SCSI] scsi: add transport host byte errors (v3)

Currently, if there is a transport problem the iscsi drivers will return
outstanding commands (commands being exeucted by the driver/fw/hw) with
DID_BUS_BUSY and block the session so no new commands can be queued.
Commands that are caught between the failure handling and blocking are
failed with DID_IMM_RETRY or one of the scsi ml queuecommand return values.
When the recovery_timeout fires, the iscsi drivers then fail IO with
DID_NO_CONNECT.

For fcp, some drivers will fail some outstanding IO (disk but possibly not
tape) with DID_BUS_BUSY or DID_ERROR or some other value that causes a retry
and hits the scsi_error.c failfast check, block the rport, and commands
caught in the race are failed with DID_IMM_RETRY. Other drivers, may
hold onto all IO and wait for the terminate_rport_io or dev_loss_tmo_callbk
to be called.

The following patches attempt to unify what upper layers will see drivers
like multipath can make a good guess. This relies on drivers being
hooked into their transport class.

This first patch just defines two new host byte errors so drivers can
return the same value for when a rport/session is blocked and for
when the fast_io_fail_tmo fires.

The idea is that if the LLD/class detects a problem and is going to block
a rport/session, then if the LLD wants or must return the command to scsi-ml,
then it can return it with DID_TRANSPORT_DISRUPTED. This will requeue
the IO into the same scsi queue it came from, until the fast io fail timer
fires and the class decides what to do.

When using multipath and the fast_io_fail_tmo fires then the class
can fail commands with DID_TRANSPORT_FAILFAST or drivers can use
DID_TRANSPORT_FAILFAST in their terminate_rport_io callbacks or
the equivlent in iscsi if we ever implement more advanced recovery methods.
A LLD, like lpfc, could continue to return DID_ERROR and then it will hit
the normal failfast path, so drivers do not have fully be ported to
work better. The point of the patches is that upper layers will
not see a failure that could be recovered from while the rport/session is
blocked until fast_io_fail_tmo/recovery_timeout fires.

V3
Remove some comments.
V2
Fixed patch/diff errors and renamed DID_TRANSPORT_BLOCKED to
DID_TRANSPORT_DISRUPTED.
V1
initial patch.

Signed-off-by: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
---
 drivers/scsi/constants.c  |  3 ++-
 drivers/scsi/scsi_error.c | 15 ++++++++++++++-
 include/scsi/scsi.h       |  5 +++++
 3 files changed, 21 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/constants.c b/drivers/scsi/constants.c
index 9785d7384199..4003deefb7d8 100644
--- a/drivers/scsi/constants.c
+++ b/drivers/scsi/constants.c
@@ -1364,7 +1364,8 @@ EXPORT_SYMBOL(scsi_print_sense);
 static const char * const hostbyte_table[]={
 "DID_OK", "DID_NO_CONNECT", "DID_BUS_BUSY", "DID_TIME_OUT", "DID_BAD_TARGET",
 "DID_ABORT", "DID_PARITY", "DID_ERROR", "DID_RESET", "DID_BAD_INTR",
-"DID_PASSTHROUGH", "DID_SOFT_ERROR", "DID_IMM_RETRY", "DID_REQUEUE"};
+"DID_PASSTHROUGH", "DID_SOFT_ERROR", "DID_IMM_RETRY", "DID_REQUEUE",
+"DID_TRANSPORT_DISRUPTED", "DID_TRANSPORT_FAILFAST" };
 #define NUM_HOSTBYTE_STRS ARRAY_SIZE(hostbyte_table)
 
 static const char * const driverbyte_table[]={
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index fecefa05cb62..5bf8be21a165 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -1290,7 +1290,20 @@ int scsi_decide_disposition(struct scsi_cmnd *scmd)
 
 	case DID_REQUEUE:
 		return ADD_TO_MLQUEUE;
-
+	case DID_TRANSPORT_DISRUPTED:
+		/*
+		 * LLD/transport was disrupted during processing of the IO.
+		 * The transport class is now blocked/blocking,
+		 * and the transport will decide what to do with the IO
+		 * based on its timers and recovery capablilities.
+		 */
+		return ADD_TO_MLQUEUE;
+	case DID_TRANSPORT_FAILFAST:
+		/*
+		 * The transport decided to failfast the IO (most likely
+		 * the fast io fail tmo fired), so send IO directly upwards.
+		 */
+		return SUCCESS;
 	case DID_ERROR:
 		if (msg_byte(scmd->result) == COMMAND_COMPLETE &&
 		    status_byte(scmd->result) == RESERVATION_CONFLICT)
diff --git a/include/scsi/scsi.h b/include/scsi/scsi.h
index 3a5662b2817e..a109165714d6 100644
--- a/include/scsi/scsi.h
+++ b/include/scsi/scsi.h
@@ -381,6 +381,11 @@ static inline int scsi_is_wlun(unsigned int lun)
 #define DID_IMM_RETRY   0x0c	/* Retry without decrementing retry count  */
 #define DID_REQUEUE	0x0d	/* Requeue command (no immediate retry) also
 				 * without decrementing the retry count	   */
+#define DID_TRANSPORT_DISRUPTED 0x0e /* Transport error disrupted execution
+				      * and the driver blocked the port to
+				      * recover the link. Transport class will
+				      * retry or fail IO */
+#define DID_TRANSPORT_FAILFAST	0x0f /* Transport class fastfailed the io */
 #define DRIVER_OK       0x00	/* Driver status                           */
 
 /*
-- 
cgit v1.2.3-59-g8ed1b


From f46e307da925a7b71a0018c0510cdc6e588b87fc Mon Sep 17 00:00:00 2001
From: Mike Christie <michaelc@cs.wisc.edu>
Date: Tue, 19 Aug 2008 18:45:27 -0500
Subject: [SCSI] fc class: Add support for new transport errors

If the target is blocked and fast io fail tmo has not fired
then we requeue with DID_TRANSPORT_DISRUPTED. Once that
tmo fires we fail with DID_TRANSPORT_FAILFAST.

v2
- seperate from
"fc class: unblock target after calling terminate callback"
to make it easier to review.
- Add JamesS's ack from list.
v2
- initial patch

Signed-off-by: Mike Christie <michaelc@cs.wisc.edu>
Acked-by: James Smart <James.Smart@emulex.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
---
 include/scsi/scsi_transport_fc.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/scsi/scsi_transport_fc.h b/include/scsi/scsi_transport_fc.h
index fb8d01370663..49d8913c4f86 100644
--- a/include/scsi/scsi_transport_fc.h
+++ b/include/scsi/scsi_transport_fc.h
@@ -679,15 +679,15 @@ fc_remote_port_chkready(struct fc_rport *rport)
 		if (rport->roles & FC_PORT_ROLE_FCP_TARGET)
 			result = 0;
 		else if (rport->flags & FC_RPORT_DEVLOSS_PENDING)
-			result = DID_IMM_RETRY << 16;
+			result = DID_TRANSPORT_DISRUPTED << 16;
 		else
 			result = DID_NO_CONNECT << 16;
 		break;
 	case FC_PORTSTATE_BLOCKED:
 		if (rport->flags & FC_RPORT_FAST_FAIL_TIMEDOUT)
-			result = DID_NO_CONNECT << 16;
+			result = DID_TRANSPORT_FAILFAST << 16;
 		else
-			result = DID_IMM_RETRY << 16;
+			result = DID_TRANSPORT_DISRUPTED << 16;
 		break;
 	default:
 		result = DID_NO_CONNECT << 16;
-- 
cgit v1.2.3-59-g8ed1b


From 6000a368cd8e6da1caf101411bdb494cd6fb8b09 Mon Sep 17 00:00:00 2001
From: Mike Christie <michaelc@cs.wisc.edu>
Date: Tue, 19 Aug 2008 18:45:30 -0500
Subject: [SCSI] block: separate failfast into multiple bits.

Multipath is best at handling transport errors. If it gets a device
error then there is not much the multipath layer can do. It will just
access the same device but from a different path.

This patch breaks up failfast into device, transport and driver errors.
The multipath layers (md and dm mutlipath) only ask the lower levels to
fast fail transport errors. The user of failfast, read ahead, will ask
to fast fail on all errors.

Note that blk_noretry_request will return true if any failfast bit
is set. This allows drivers that do not support the multipath failfast
bits to continue to fail on any failfast error like before. Drivers
like scsi that are able to fail fast specific errors can check
for the specific fail fast type. In the next patch I will convert
scsi.

Signed-off-by: Mike Christie <michaelc@cs.wisc.edu>
Cc: Jens Axboe <jens.axboe@oracle.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
---
 block/blk-core.c                            | 11 +++++++++--
 drivers/md/dm-mpath.c                       |  2 +-
 drivers/md/multipath.c                      |  4 ++--
 drivers/s390/block/dasd_diag.c              |  2 +-
 drivers/s390/block/dasd_eckd.c              |  2 +-
 drivers/s390/block/dasd_fba.c               |  2 +-
 drivers/scsi/device_handler/scsi_dh_alua.c  |  3 ++-
 drivers/scsi/device_handler/scsi_dh_emc.c   |  3 ++-
 drivers/scsi/device_handler/scsi_dh_hp_sw.c |  6 ++++--
 drivers/scsi/device_handler/scsi_dh_rdac.c  |  3 ++-
 drivers/scsi/scsi_transport_spi.c           |  4 +++-
 include/linux/bio.h                         | 26 +++++++++++++++++---------
 include/linux/blkdev.h                      | 15 ++++++++++++---
 13 files changed, 57 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/block/blk-core.c b/block/blk-core.c
index 2d053b584410..9e79a485e4f3 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1075,8 +1075,15 @@ void init_request_from_bio(struct request *req, struct bio *bio)
 	/*
 	 * inherit FAILFAST from bio (for read-ahead, and explicit FAILFAST)
 	 */
-	if (bio_rw_ahead(bio) || bio_failfast(bio))
-		req->cmd_flags |= REQ_FAILFAST;
+	if (bio_rw_ahead(bio))
+		req->cmd_flags |= (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
+				   REQ_FAILFAST_DRIVER);
+	if (bio_failfast_dev(bio))
+		req->cmd_flags |= REQ_FAILFAST_DEV;
+	if (bio_failfast_transport(bio))
+		req->cmd_flags |= REQ_FAILFAST_TRANSPORT;
+	if (bio_failfast_driver(bio))
+		req->cmd_flags |= REQ_FAILFAST_DRIVER;
 
 	/*
 	 * REQ_BARRIER implies no merging, but lets make it explicit
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 103304c1e3b0..9bf3460c5540 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -849,7 +849,7 @@ static int multipath_map(struct dm_target *ti, struct bio *bio,
 	dm_bio_record(&mpio->details, bio);
 
 	map_context->ptr = mpio;
-	bio->bi_rw |= (1 << BIO_RW_FAILFAST);
+	bio->bi_rw |= (1 << BIO_RW_FAILFAST_TRANSPORT);
 	r = map_io(m, bio, mpio, 0);
 	if (r < 0 || r == DM_MAPIO_REQUEUE)
 		mempool_free(mpio, m->mpio_pool);
diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c
index 8bb8794129b3..7ae33ebaf7ec 100644
--- a/drivers/md/multipath.c
+++ b/drivers/md/multipath.c
@@ -176,7 +176,7 @@ static int multipath_make_request (struct request_queue *q, struct bio * bio)
 	mp_bh->bio = *bio;
 	mp_bh->bio.bi_sector += multipath->rdev->data_offset;
 	mp_bh->bio.bi_bdev = multipath->rdev->bdev;
-	mp_bh->bio.bi_rw |= (1 << BIO_RW_FAILFAST);
+	mp_bh->bio.bi_rw |= (1 << BIO_RW_FAILFAST_TRANSPORT);
 	mp_bh->bio.bi_end_io = multipath_end_request;
 	mp_bh->bio.bi_private = mp_bh;
 	generic_make_request(&mp_bh->bio);
@@ -402,7 +402,7 @@ static void multipathd (mddev_t *mddev)
 			*bio = *(mp_bh->master_bio);
 			bio->bi_sector += conf->multipaths[mp_bh->path].rdev->data_offset;
 			bio->bi_bdev = conf->multipaths[mp_bh->path].rdev->bdev;
-			bio->bi_rw |= (1 << BIO_RW_FAILFAST);
+			bio->bi_rw |= (1 << BIO_RW_FAILFAST_TRANSPORT);
 			bio->bi_end_io = multipath_end_request;
 			bio->bi_private = mp_bh;
 			generic_make_request(bio);
diff --git a/drivers/s390/block/dasd_diag.c b/drivers/s390/block/dasd_diag.c
index 85fcb4371054..7844461a995b 100644
--- a/drivers/s390/block/dasd_diag.c
+++ b/drivers/s390/block/dasd_diag.c
@@ -544,7 +544,7 @@ static struct dasd_ccw_req *dasd_diag_build_cp(struct dasd_device *memdev,
 	}
 	cqr->retries = DIAG_MAX_RETRIES;
 	cqr->buildclk = get_clock();
-	if (req->cmd_flags & REQ_FAILFAST)
+	if (blk_noretry_request(req))
 		set_bit(DASD_CQR_FLAGS_FAILFAST, &cqr->flags);
 	cqr->startdev = memdev;
 	cqr->memdev = memdev;
diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c
index 49f9d221e23d..2e60d5f968c8 100644
--- a/drivers/s390/block/dasd_eckd.c
+++ b/drivers/s390/block/dasd_eckd.c
@@ -1700,7 +1700,7 @@ static struct dasd_ccw_req *dasd_eckd_build_cp(struct dasd_device *startdev,
 			recid++;
 		}
 	}
-	if (req->cmd_flags & REQ_FAILFAST)
+	if (blk_noretry_request(req))
 		set_bit(DASD_CQR_FLAGS_FAILFAST, &cqr->flags);
 	cqr->startdev = startdev;
 	cqr->memdev = startdev;
diff --git a/drivers/s390/block/dasd_fba.c b/drivers/s390/block/dasd_fba.c
index 93d9b6452a94..7d442aeff3d1 100644
--- a/drivers/s390/block/dasd_fba.c
+++ b/drivers/s390/block/dasd_fba.c
@@ -355,7 +355,7 @@ static struct dasd_ccw_req *dasd_fba_build_cp(struct dasd_device * memdev,
 			recid++;
 		}
 	}
-	if (req->cmd_flags & REQ_FAILFAST)
+	if (blk_noretry_request(req))
 		set_bit(DASD_CQR_FLAGS_FAILFAST, &cqr->flags);
 	cqr->startdev = memdev;
 	cqr->memdev = memdev;
diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c
index 708e475896b9..cb8aa3b58c22 100644
--- a/drivers/scsi/device_handler/scsi_dh_alua.c
+++ b/drivers/scsi/device_handler/scsi_dh_alua.c
@@ -109,7 +109,8 @@ static struct request *get_alua_req(struct scsi_device *sdev,
 	}
 
 	rq->cmd_type = REQ_TYPE_BLOCK_PC;
-	rq->cmd_flags |= REQ_FAILFAST | REQ_NOMERGE;
+	rq->cmd_flags |= REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
+			 REQ_FAILFAST_DRIVER | REQ_NOMERGE;
 	rq->retries = ALUA_FAILOVER_RETRIES;
 	rq->timeout = ALUA_FAILOVER_TIMEOUT;
 
diff --git a/drivers/scsi/device_handler/scsi_dh_emc.c b/drivers/scsi/device_handler/scsi_dh_emc.c
index 8f45570a8a01..0e572d2c5b0a 100644
--- a/drivers/scsi/device_handler/scsi_dh_emc.c
+++ b/drivers/scsi/device_handler/scsi_dh_emc.c
@@ -303,7 +303,8 @@ static struct request *get_req(struct scsi_device *sdev, int cmd,
 
 	rq->cmd[4] = len;
 	rq->cmd_type = REQ_TYPE_BLOCK_PC;
-	rq->cmd_flags |= REQ_FAILFAST;
+	rq->cmd_flags |= REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
+			 REQ_FAILFAST_DRIVER;
 	rq->timeout = CLARIION_TIMEOUT;
 	rq->retries = CLARIION_RETRIES;
 
diff --git a/drivers/scsi/device_handler/scsi_dh_hp_sw.c b/drivers/scsi/device_handler/scsi_dh_hp_sw.c
index 5e93c88ad66b..9aec4ca64e56 100644
--- a/drivers/scsi/device_handler/scsi_dh_hp_sw.c
+++ b/drivers/scsi/device_handler/scsi_dh_hp_sw.c
@@ -112,7 +112,8 @@ static int hp_sw_tur(struct scsi_device *sdev, struct hp_sw_dh_data *h)
 		return SCSI_DH_RES_TEMP_UNAVAIL;
 
 	req->cmd_type = REQ_TYPE_BLOCK_PC;
-	req->cmd_flags |= REQ_FAILFAST;
+	req->cmd_flags |= REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
+			  REQ_FAILFAST_DRIVER;
 	req->cmd_len = COMMAND_SIZE(TEST_UNIT_READY);
 	req->cmd[0] = TEST_UNIT_READY;
 	req->timeout = HP_SW_TIMEOUT;
@@ -204,7 +205,8 @@ static int hp_sw_start_stop(struct scsi_device *sdev, struct hp_sw_dh_data *h)
 		return SCSI_DH_RES_TEMP_UNAVAIL;
 
 	req->cmd_type = REQ_TYPE_BLOCK_PC;
-	req->cmd_flags |= REQ_FAILFAST;
+	req->cmd_flags |= REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
+			  REQ_FAILFAST_DRIVER;
 	req->cmd_len = COMMAND_SIZE(START_STOP);
 	req->cmd[0] = START_STOP;
 	req->cmd[4] = 1;	/* Start spin cycle */
diff --git a/drivers/scsi/device_handler/scsi_dh_rdac.c b/drivers/scsi/device_handler/scsi_dh_rdac.c
index 50bf95f3b5c4..a43c3ed4df28 100644
--- a/drivers/scsi/device_handler/scsi_dh_rdac.c
+++ b/drivers/scsi/device_handler/scsi_dh_rdac.c
@@ -226,7 +226,8 @@ static struct request *get_rdac_req(struct scsi_device *sdev,
 	}
 
 	rq->cmd_type = REQ_TYPE_BLOCK_PC;
-	rq->cmd_flags |= REQ_FAILFAST | REQ_NOMERGE;
+	rq->cmd_flags |= REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
+			 REQ_FAILFAST_DRIVER;
 	rq->retries = RDAC_RETRIES;
 	rq->timeout = RDAC_TIMEOUT;
 
diff --git a/drivers/scsi/scsi_transport_spi.c b/drivers/scsi/scsi_transport_spi.c
index b29360ed0bdc..7c2d28924d2a 100644
--- a/drivers/scsi/scsi_transport_spi.c
+++ b/drivers/scsi/scsi_transport_spi.c
@@ -109,7 +109,9 @@ static int spi_execute(struct scsi_device *sdev, const void *cmd,
 	for(i = 0; i < DV_RETRIES; i++) {
 		result = scsi_execute(sdev, cmd, dir, buffer, bufflen,
 				      sense, DV_TIMEOUT, /* retries */ 1,
-				      REQ_FAILFAST);
+				      REQ_FAILFAST_DEV |
+				      REQ_FAILFAST_TRANSPORT |
+				      REQ_FAILFAST_DRIVER);
 		if (result & DRIVER_SENSE) {
 			struct scsi_sense_hdr sshdr_tmp;
 			if (!sshdr)
diff --git a/include/linux/bio.h b/include/linux/bio.h
index ff5b4cf9e2da..1beda208cbfb 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -129,25 +129,30 @@ struct bio {
  * bit 2 -- barrier
  *	Insert a serialization point in the IO queue, forcing previously
  *	submitted IO to be completed before this oen is issued.
- * bit 3 -- fail fast, don't want low level driver retries
- * bit 4 -- synchronous I/O hint: the block layer will unplug immediately
+ * bit 3 -- synchronous I/O hint: the block layer will unplug immediately
  *	Note that this does NOT indicate that the IO itself is sync, just
  *	that the block layer will not postpone issue of this IO by plugging.
- * bit 5 -- metadata request
+ * bit 4 -- metadata request
  *	Used for tracing to differentiate metadata and data IO. May also
  *	get some preferential treatment in the IO scheduler
- * bit 6 -- discard sectors
+ * bit 5 -- discard sectors
  *	Informs the lower level device that this range of sectors is no longer
  *	used by the file system and may thus be freed by the device. Used
  *	for flash based storage.
+ * bit 6 -- fail fast device errors
+ * bit 7 -- fail fast transport errors
+ * bit 8 -- fail fast driver errors
+ *	Don't want driver retries for any fast fail whatever the reason.
  */
 #define BIO_RW		0	/* Must match RW in req flags (blkdev.h) */
 #define BIO_RW_AHEAD	1	/* Must match FAILFAST in req flags */
 #define BIO_RW_BARRIER	2
-#define BIO_RW_FAILFAST	3
-#define BIO_RW_SYNC	4
-#define BIO_RW_META	5
-#define BIO_RW_DISCARD	6
+#define BIO_RW_SYNC	3
+#define BIO_RW_META	4
+#define BIO_RW_DISCARD	5
+#define BIO_RW_FAILFAST_DEV		6
+#define BIO_RW_FAILFAST_TRANSPORT	7
+#define BIO_RW_FAILFAST_DRIVER		8
 
 /*
  * upper 16 bits of bi_rw define the io priority of this bio
@@ -174,7 +179,10 @@ struct bio {
 #define bio_sectors(bio)	((bio)->bi_size >> 9)
 #define bio_barrier(bio)	((bio)->bi_rw & (1 << BIO_RW_BARRIER))
 #define bio_sync(bio)		((bio)->bi_rw & (1 << BIO_RW_SYNC))
-#define bio_failfast(bio)	((bio)->bi_rw & (1 << BIO_RW_FAILFAST))
+#define bio_failfast_dev(bio)	((bio)->bi_rw &	(1 << BIO_RW_FAILFAST_DEV))
+#define bio_failfast_transport(bio)	\
+	((bio)->bi_rw & (1 << BIO_RW_FAILFAST_TRANSPORT))
+#define bio_failfast_driver(bio) ((bio)->bi_rw & (1 << BIO_RW_FAILFAST_DRIVER))
 #define bio_rw_ahead(bio)	((bio)->bi_rw & (1 << BIO_RW_AHEAD))
 #define bio_rw_meta(bio)	((bio)->bi_rw & (1 << BIO_RW_META))
 #define bio_discard(bio)	((bio)->bi_rw & (1 << BIO_RW_DISCARD))
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index a92d9e4ea96e..f3491d225268 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -87,7 +87,9 @@ enum {
  */
 enum rq_flag_bits {
 	__REQ_RW,		/* not set, read. set, write */
-	__REQ_FAILFAST,		/* no low level driver retries */
+	__REQ_FAILFAST_DEV,	/* no driver retries of device errors */
+	__REQ_FAILFAST_TRANSPORT, /* no driver retries of transport errors */
+	__REQ_FAILFAST_DRIVER,	/* no driver retries of driver errors */
 	__REQ_DISCARD,		/* request to discard sectors */
 	__REQ_SORTED,		/* elevator knows about this request */
 	__REQ_SOFTBARRIER,	/* may not be passed by ioscheduler */
@@ -111,8 +113,10 @@ enum rq_flag_bits {
 };
 
 #define REQ_RW		(1 << __REQ_RW)
+#define REQ_FAILFAST_DEV	(1 << __REQ_FAILFAST_DEV)
+#define REQ_FAILFAST_TRANSPORT	(1 << __REQ_FAILFAST_TRANSPORT)
+#define REQ_FAILFAST_DRIVER	(1 << __REQ_FAILFAST_DRIVER)
 #define REQ_DISCARD	(1 << __REQ_DISCARD)
-#define REQ_FAILFAST	(1 << __REQ_FAILFAST)
 #define REQ_SORTED	(1 << __REQ_SORTED)
 #define REQ_SOFTBARRIER	(1 << __REQ_SOFTBARRIER)
 #define REQ_HARDBARRIER	(1 << __REQ_HARDBARRIER)
@@ -560,7 +564,12 @@ enum {
 #define blk_special_request(rq)	((rq)->cmd_type == REQ_TYPE_SPECIAL)
 #define blk_sense_request(rq)	((rq)->cmd_type == REQ_TYPE_SENSE)
 
-#define blk_noretry_request(rq)	((rq)->cmd_flags & REQ_FAILFAST)
+#define blk_failfast_dev(rq)	((rq)->cmd_flags & REQ_FAILFAST_DEV)
+#define blk_failfast_transport(rq) ((rq)->cmd_flags & REQ_FAILFAST_TRANSPORT)
+#define blk_failfast_driver(rq)	((rq)->cmd_flags & REQ_FAILFAST_DRIVER)
+#define blk_noretry_request(rq)	(blk_failfast_dev(rq) ||	\
+				 blk_failfast_transport(rq) ||	\
+				 blk_failfast_driver(rq))
 #define blk_rq_started(rq)	((rq)->cmd_flags & REQ_STARTED)
 
 #define blk_account_rq(rq)	(blk_rq_started(rq) && (blk_fs_request(rq) || blk_discard_rq(rq))) 
-- 
cgit v1.2.3-59-g8ed1b


From e5bd7b54e93ef7151469a12b8c28d863b9f8a088 Mon Sep 17 00:00:00 2001
From: Mike Christie <michaelc@cs.wisc.edu>
Date: Wed, 24 Sep 2008 11:46:10 -0500
Subject: [SCSI] libiscsi: Support drivers initiating session removal

If the driver knows when hardware is removed like with cxgb3i,
bnx2i, qla4xxx and iser then we will want to remove the sessions/devices
that are bound to that device before removing the host.

cxgb3i and in the future bnx2i will remove the host and that will
remove all the sessions on the hba. iser can call iscsi_kill_session
when it gets an event that indicates that a hca is removed.
And when qla4xxx is hooked in to the lib (it is only hooked into
the class right now) it can call iscsi remove host like the
partial offload card drivers.

Signed-off-by: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
---
 drivers/infiniband/ulp/iser/iscsi_iser.c |   1 +
 drivers/scsi/iscsi_tcp.c                 |   1 +
 drivers/scsi/libiscsi.c                  | 107 ++++++++++++++++++++++++++++---
 drivers/scsi/qla4xxx/ql4_os.c            |   2 +-
 drivers/scsi/scsi_transport_iscsi.c      |   6 +-
 include/scsi/iscsi_if.h                  |   1 +
 include/scsi/libiscsi.h                  |  13 ++++
 include/scsi/scsi_transport_iscsi.h      |   3 +-
 8 files changed, 121 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.c b/drivers/infiniband/ulp/iser/iscsi_iser.c
index 5a1cf2580e16..0474da173eb1 100644
--- a/drivers/infiniband/ulp/iser/iscsi_iser.c
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.c
@@ -378,6 +378,7 @@ static void iscsi_iser_session_destroy(struct iscsi_cls_session *cls_session)
 {
 	struct Scsi_Host *shost = iscsi_session_to_shost(cls_session);
 
+	iscsi_session_teardown(cls_session);
 	iscsi_host_remove(shost);
 	iscsi_host_free(shost);
 }
diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c
index e960f00da93a..752f42884cc1 100644
--- a/drivers/scsi/iscsi_tcp.c
+++ b/drivers/scsi/iscsi_tcp.c
@@ -1885,6 +1885,7 @@ static void iscsi_tcp_session_destroy(struct iscsi_cls_session *cls_session)
 	struct Scsi_Host *shost = iscsi_session_to_shost(cls_session);
 
 	iscsi_r2tpool_free(cls_session->dd_data);
+	iscsi_session_teardown(cls_session);
 
 	iscsi_host_remove(shost);
 	iscsi_host_free(shost);
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index f9539af28f02..390781894be9 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -983,6 +983,38 @@ struct iscsi_task *iscsi_itt_to_ctask(struct iscsi_conn *conn, itt_t itt)
 }
 EXPORT_SYMBOL_GPL(iscsi_itt_to_ctask);
 
+void iscsi_session_failure(struct iscsi_cls_session *cls_session,
+			   enum iscsi_err err)
+{
+	struct iscsi_session *session = cls_session->dd_data;
+	struct iscsi_conn *conn;
+	struct device *dev;
+	unsigned long flags;
+
+	spin_lock_irqsave(&session->lock, flags);
+	conn = session->leadconn;
+	if (session->state == ISCSI_STATE_TERMINATE || !conn) {
+		spin_unlock_irqrestore(&session->lock, flags);
+		return;
+	}
+
+	dev = get_device(&conn->cls_conn->dev);
+	spin_unlock_irqrestore(&session->lock, flags);
+	if (!dev)
+	        return;
+	/*
+	 * if the host is being removed bypass the connection
+	 * recovery initialization because we are going to kill
+	 * the session.
+	 */
+	if (err == ISCSI_ERR_INVALID_HOST)
+		iscsi_conn_error_event(conn->cls_conn, err);
+	else
+		iscsi_conn_failure(conn, err);
+	put_device(dev);
+}
+EXPORT_SYMBOL_GPL(iscsi_session_failure);
+
 void iscsi_conn_failure(struct iscsi_conn *conn, enum iscsi_err err)
 {
 	struct iscsi_session *session = conn->session;
@@ -997,9 +1029,10 @@ void iscsi_conn_failure(struct iscsi_conn *conn, enum iscsi_err err)
 	if (conn->stop_stage == 0)
 		session->state = ISCSI_STATE_FAILED;
 	spin_unlock_irqrestore(&session->lock, flags);
+
 	set_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx);
 	set_bit(ISCSI_SUSPEND_BIT, &conn->suspend_rx);
-	iscsi_conn_error(conn->cls_conn, err);
+	iscsi_conn_error_event(conn->cls_conn, err);
 }
 EXPORT_SYMBOL_GPL(iscsi_conn_failure);
 
@@ -1905,6 +1938,7 @@ struct Scsi_Host *iscsi_host_alloc(struct scsi_host_template *sht,
 				   int dd_data_size, uint16_t qdepth)
 {
 	struct Scsi_Host *shost;
+	struct iscsi_host *ihost;
 
 	shost = scsi_host_alloc(sht, sizeof(struct iscsi_host) + dd_data_size);
 	if (!shost)
@@ -1919,22 +1953,43 @@ struct Scsi_Host *iscsi_host_alloc(struct scsi_host_template *sht,
 		qdepth = ISCSI_DEF_CMD_PER_LUN;
 	}
 	shost->cmd_per_lun = qdepth;
+
+	ihost = shost_priv(shost);
+	spin_lock_init(&ihost->lock);
+	ihost->state = ISCSI_HOST_SETUP;
+	ihost->num_sessions = 0;
+	init_waitqueue_head(&ihost->session_removal_wq);
 	return shost;
 }
 EXPORT_SYMBOL_GPL(iscsi_host_alloc);
 
+static void iscsi_notify_host_removed(struct iscsi_cls_session *cls_session)
+{
+	iscsi_session_failure(cls_session, ISCSI_ERR_INVALID_HOST);
+}
+
 /**
  * iscsi_host_remove - remove host and sessions
  * @shost: scsi host
  *
- * This will also remove any sessions attached to the host, but if userspace
- * is managing the session at the same time this will break. TODO: add
- * refcounting to the netlink iscsi interface so a rmmod or host hot unplug
- * does not remove the memory from under us.
+ * If there are any sessions left, this will initiate the removal and wait
+ * for the completion.
  */
 void iscsi_host_remove(struct Scsi_Host *shost)
 {
-	iscsi_host_for_each_session(shost, iscsi_session_teardown);
+	struct iscsi_host *ihost = shost_priv(shost);
+	unsigned long flags;
+
+	spin_lock_irqsave(&ihost->lock, flags);
+	ihost->state = ISCSI_HOST_REMOVED;
+	spin_unlock_irqrestore(&ihost->lock, flags);
+
+	iscsi_host_for_each_session(shost, iscsi_notify_host_removed);
+	wait_event_interruptible(ihost->session_removal_wq,
+				 ihost->num_sessions == 0);
+	if (signal_pending(current))
+		flush_signals(current);
+
 	scsi_remove_host(shost);
 }
 EXPORT_SYMBOL_GPL(iscsi_host_remove);
@@ -1950,6 +2005,27 @@ void iscsi_host_free(struct Scsi_Host *shost)
 }
 EXPORT_SYMBOL_GPL(iscsi_host_free);
 
+static void iscsi_host_dec_session_cnt(struct Scsi_Host *shost)
+{
+	struct iscsi_host *ihost = shost_priv(shost);
+	unsigned long flags;
+
+	shost = scsi_host_get(shost);
+	if (!shost) {
+		printk(KERN_ERR "Invalid state. Cannot notify host removal "
+		      "of session teardown event because host already "
+		      "removed.\n");
+		return;
+	}
+
+	spin_lock_irqsave(&ihost->lock, flags);
+	ihost->num_sessions--;
+	if (ihost->num_sessions == 0)
+		wake_up(&ihost->session_removal_wq);
+	spin_unlock_irqrestore(&ihost->lock, flags);
+	scsi_host_put(shost);
+}
+
 /**
  * iscsi_session_setup - create iscsi cls session and host and session
  * @iscsit: iscsi transport template
@@ -1970,9 +2046,19 @@ iscsi_session_setup(struct iscsi_transport *iscsit, struct Scsi_Host *shost,
 		    uint16_t cmds_max, int cmd_task_size,
 		    uint32_t initial_cmdsn, unsigned int id)
 {
+	struct iscsi_host *ihost = shost_priv(shost);
 	struct iscsi_session *session;
 	struct iscsi_cls_session *cls_session;
 	int cmd_i, scsi_cmds, total_cmds = cmds_max;
+	unsigned long flags;
+
+	spin_lock_irqsave(&ihost->lock, flags);
+	if (ihost->state == ISCSI_HOST_REMOVED) {
+		spin_unlock_irqrestore(&ihost->lock, flags);
+		return NULL;
+	}
+	ihost->num_sessions++;
+	spin_unlock_irqrestore(&ihost->lock, flags);
 
 	if (!total_cmds)
 		total_cmds = ISCSI_DEF_XMIT_CMDS_MAX;
@@ -1985,7 +2071,7 @@ iscsi_session_setup(struct iscsi_transport *iscsit, struct Scsi_Host *shost,
 		printk(KERN_ERR "iscsi: invalid can_queue of %d. can_queue "
 		       "must be a power of two that is at least %d.\n",
 		       total_cmds, ISCSI_TOTAL_CMDS_MIN);
-		return NULL;
+		goto dec_session_count;
 	}
 
 	if (total_cmds > ISCSI_TOTAL_CMDS_MAX) {
@@ -2009,7 +2095,7 @@ iscsi_session_setup(struct iscsi_transport *iscsit, struct Scsi_Host *shost,
 	cls_session = iscsi_alloc_session(shost, iscsit,
 					  sizeof(struct iscsi_session));
 	if (!cls_session)
-		return NULL;
+		goto dec_session_count;
 	session = cls_session->dd_data;
 	session->cls_session = cls_session;
 	session->host = shost;
@@ -2048,6 +2134,7 @@ iscsi_session_setup(struct iscsi_transport *iscsit, struct Scsi_Host *shost,
 
 	if (iscsi_add_session(cls_session, id))
 		goto cls_session_fail;
+
 	return cls_session;
 
 cls_session_fail:
@@ -2056,6 +2143,8 @@ module_get_fail:
 	iscsi_pool_free(&session->cmdpool);
 cmdpool_alloc_fail:
 	iscsi_free_session(cls_session);
+dec_session_count:
+	iscsi_host_dec_session_cnt(shost);
 	return NULL;
 }
 EXPORT_SYMBOL_GPL(iscsi_session_setup);
@@ -2071,6 +2160,7 @@ void iscsi_session_teardown(struct iscsi_cls_session *cls_session)
 {
 	struct iscsi_session *session = cls_session->dd_data;
 	struct module *owner = cls_session->transport->owner;
+	struct Scsi_Host *shost = session->host;
 
 	iscsi_pool_free(&session->cmdpool);
 
@@ -2083,6 +2173,7 @@ void iscsi_session_teardown(struct iscsi_cls_session *cls_session)
 	kfree(session->ifacename);
 
 	iscsi_destroy_session(cls_session);
+	iscsi_host_dec_session_cnt(shost);
 	module_put(owner);
 }
 EXPORT_SYMBOL_GPL(iscsi_session_teardown);
diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c
index 4255b36ff968..db7ea3bb4e83 100644
--- a/drivers/scsi/qla4xxx/ql4_os.c
+++ b/drivers/scsi/qla4xxx/ql4_os.c
@@ -353,7 +353,7 @@ void qla4xxx_mark_device_missing(struct scsi_qla_host *ha,
 		      ha->host_no, ddb_entry->bus, ddb_entry->target,
 		      ddb_entry->fw_ddb_index));
 	iscsi_block_session(ddb_entry->sess);
-	iscsi_conn_error(ddb_entry->conn, ISCSI_ERR_CONN_FAILED);
+	iscsi_conn_error_event(ddb_entry->conn, ISCSI_ERR_CONN_FAILED);
 }
 
 static struct srb* qla4xxx_get_new_srb(struct scsi_qla_host *ha,
diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index cbaae48f47ed..f9e45f83e467 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -1010,7 +1010,7 @@ int iscsi_recv_pdu(struct iscsi_cls_conn *conn, struct iscsi_hdr *hdr,
 
 	skb = alloc_skb(len, GFP_ATOMIC);
 	if (!skb) {
-		iscsi_conn_error(conn, ISCSI_ERR_CONN_FAILED);
+		iscsi_conn_error_event(conn, ISCSI_ERR_CONN_FAILED);
 		iscsi_cls_conn_printk(KERN_ERR, conn, "can not deliver "
 				      "control PDU: OOM\n");
 		return -ENOMEM;
@@ -1031,7 +1031,7 @@ int iscsi_recv_pdu(struct iscsi_cls_conn *conn, struct iscsi_hdr *hdr,
 }
 EXPORT_SYMBOL_GPL(iscsi_recv_pdu);
 
-void iscsi_conn_error(struct iscsi_cls_conn *conn, enum iscsi_err error)
+void iscsi_conn_error_event(struct iscsi_cls_conn *conn, enum iscsi_err error)
 {
 	struct nlmsghdr	*nlh;
 	struct sk_buff	*skb;
@@ -1063,7 +1063,7 @@ void iscsi_conn_error(struct iscsi_cls_conn *conn, enum iscsi_err error)
 	iscsi_cls_conn_printk(KERN_INFO, conn, "detected conn error (%d)\n",
 			      error);
 }
-EXPORT_SYMBOL_GPL(iscsi_conn_error);
+EXPORT_SYMBOL_GPL(iscsi_conn_error_event);
 
 static int
 iscsi_if_send_reply(int pid, int seq, int type, int done, int multi,
diff --git a/include/scsi/iscsi_if.h b/include/scsi/iscsi_if.h
index 16be12f1cbe8..f274d248a91f 100644
--- a/include/scsi/iscsi_if.h
+++ b/include/scsi/iscsi_if.h
@@ -213,6 +213,7 @@ enum iscsi_err {
 	ISCSI_ERR_DATA_DGST		= ISCSI_ERR_BASE + 15,
 	ISCSI_ERR_PARAM_NOT_FOUND	= ISCSI_ERR_BASE + 16,
 	ISCSI_ERR_NO_SCSI_CMD		= ISCSI_ERR_BASE + 17,
+	ISCSI_ERR_INVALID_HOST		= ISCSI_ERR_BASE + 18,
 };
 
 /*
diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h
index 5e75bb7f311c..7d8cd159f592 100644
--- a/include/scsi/libiscsi.h
+++ b/include/scsi/libiscsi.h
@@ -287,6 +287,11 @@ struct iscsi_session {
 	struct iscsi_pool	cmdpool;	/* PDU's pool */
 };
 
+enum {
+	ISCSI_HOST_SETUP,
+	ISCSI_HOST_REMOVED,
+};
+
 struct iscsi_host {
 	char			*initiatorname;
 	/* hw address or netdev iscsi connection is bound to */
@@ -295,6 +300,12 @@ struct iscsi_host {
 	/* local address */
 	int			local_port;
 	char			local_address[ISCSI_ADDRESS_BUF_LEN];
+
+	wait_queue_head_t	session_removal_wq;
+	/* protects sessions and state */
+	spinlock_t		lock;
+	int			num_sessions;
+	int			state;
 };
 
 /*
@@ -351,6 +362,8 @@ extern void iscsi_conn_stop(struct iscsi_cls_conn *, int);
 extern int iscsi_conn_bind(struct iscsi_cls_session *, struct iscsi_cls_conn *,
 			   int);
 extern void iscsi_conn_failure(struct iscsi_conn *conn, enum iscsi_err err);
+extern void iscsi_session_failure(struct iscsi_cls_session *cls_session,
+				  enum iscsi_err err);
 extern int iscsi_conn_get_param(struct iscsi_cls_conn *cls_conn,
 				enum iscsi_param param, char *buf);
 extern void iscsi_suspend_tx(struct iscsi_conn *conn);
diff --git a/include/scsi/scsi_transport_iscsi.h b/include/scsi/scsi_transport_iscsi.h
index 8b6c91df4c7a..8749d4d8e244 100644
--- a/include/scsi/scsi_transport_iscsi.h
+++ b/include/scsi/scsi_transport_iscsi.h
@@ -135,7 +135,8 @@ extern int iscsi_unregister_transport(struct iscsi_transport *tt);
 /*
  * control plane upcalls
  */
-extern void iscsi_conn_error(struct iscsi_cls_conn *conn, enum iscsi_err error);
+extern void iscsi_conn_error_event(struct iscsi_cls_conn *conn,
+				   enum iscsi_err error);
 extern int iscsi_recv_pdu(struct iscsi_cls_conn *conn, struct iscsi_hdr *hdr,
 			  char *data, uint32_t data_size);
 
-- 
cgit v1.2.3-59-g8ed1b


From 21536062d98938dfcfbae593a26c154e359749dc Mon Sep 17 00:00:00 2001
From: Mike Christie <michaelc@cs.wisc.edu>
Date: Wed, 24 Sep 2008 11:46:11 -0500
Subject: [SCSI] iscsi class: fix endpoint id handling

Some endpoint code was using unsigned int and some
was using uint64_t. This converts it all to uint64_t.

Signed-off-by: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
---
 drivers/scsi/scsi_transport_iscsi.c | 9 +++++----
 include/scsi/scsi_transport_iscsi.h | 2 +-
 2 files changed, 6 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index f9e45f83e467..4a803ebaf508 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -138,7 +138,7 @@ static ssize_t
 show_ep_handle(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	struct iscsi_endpoint *ep = iscsi_dev_to_endpoint(dev);
-	return sprintf(buf, "%u\n", ep->id);
+	return sprintf(buf, "%llu\n", (unsigned long long) ep->id);
 }
 static ISCSI_ATTR(ep, handle, S_IRUGO, show_ep_handle, NULL);
 
@@ -156,7 +156,7 @@ static struct attribute_group iscsi_endpoint_group = {
 static int iscsi_match_epid(struct device *dev, void *data)
 {
 	struct iscsi_endpoint *ep = iscsi_dev_to_endpoint(dev);
-	unsigned int *epid = (unsigned int *) data;
+	uint64_t *epid = (uint64_t *) data;
 
 	return *epid == ep->id;
 }
@@ -166,7 +166,7 @@ iscsi_create_endpoint(int dd_size)
 {
 	struct device *dev;
 	struct iscsi_endpoint *ep;
-	unsigned int id;
+	uint64_t id;
 	int err;
 
 	for (id = 1; id < ISCSI_MAX_EPID; id++) {
@@ -187,7 +187,8 @@ iscsi_create_endpoint(int dd_size)
 
 	ep->id = id;
 	ep->dev.class = &iscsi_endpoint_class;
-	snprintf(ep->dev.bus_id, BUS_ID_SIZE, "ep-%u", id);
+	snprintf(ep->dev.bus_id, BUS_ID_SIZE, "ep-%llu",
+		 (unsigned long long) id);
 	err = device_register(&ep->dev);
         if (err)
                 goto free_ep;
diff --git a/include/scsi/scsi_transport_iscsi.h b/include/scsi/scsi_transport_iscsi.h
index 8749d4d8e244..c667cc396545 100644
--- a/include/scsi/scsi_transport_iscsi.h
+++ b/include/scsi/scsi_transport_iscsi.h
@@ -208,7 +208,7 @@ extern void iscsi_host_for_each_session(struct Scsi_Host *shost,
 struct iscsi_endpoint {
 	void *dd_data;			/* LLD private data */
 	struct device dev;
-	unsigned int id;
+	uint64_t id;
 };
 
 /*
-- 
cgit v1.2.3-59-g8ed1b


From 8e12452549ba2dfa17db97bc495172fac221a7ab Mon Sep 17 00:00:00 2001
From: Mike Christie <michaelc@cs.wisc.edu>
Date: Wed, 24 Sep 2008 11:46:12 -0500
Subject: [SCSI] libiscsi: rename host reset to target reset

I had this in my patchset to add target reset support, but
it got dropped due to patching conflicts. This initial patch
just renames the function and users. We are actually just
dropping the session, and so this does not have anything to do
with the host exactly. It does for software iscsi because
we allocate a host per session, but for cxgb3i this makes no
sense.

Signed-off-by: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
---
 drivers/infiniband/ulp/iser/iscsi_iser.c |  2 +-
 drivers/scsi/iscsi_tcp.c                 |  2 +-
 drivers/scsi/libiscsi.c                  | 10 +++++-----
 include/scsi/libiscsi.h                  |  2 +-
 4 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.c b/drivers/infiniband/ulp/iser/iscsi_iser.c
index 0474da173eb1..1e5b6446231d 100644
--- a/drivers/infiniband/ulp/iser/iscsi_iser.c
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.c
@@ -598,7 +598,7 @@ static struct scsi_host_template iscsi_iser_sht = {
 	.cmd_per_lun            = ISCSI_MAX_CMD_PER_LUN,
 	.eh_abort_handler       = iscsi_eh_abort,
 	.eh_device_reset_handler= iscsi_eh_device_reset,
-	.eh_host_reset_handler	= iscsi_eh_host_reset,
+	.eh_target_reset_handler= iscsi_eh_target_reset,
 	.use_clustering         = DISABLE_CLUSTERING,
 	.proc_name              = "iscsi_iser",
 	.this_id                = -1,
diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c
index 752f42884cc1..4f096de81525 100644
--- a/drivers/scsi/iscsi_tcp.c
+++ b/drivers/scsi/iscsi_tcp.c
@@ -1909,7 +1909,7 @@ static struct scsi_host_template iscsi_sht = {
 	.cmd_per_lun		= ISCSI_DEF_CMD_PER_LUN,
 	.eh_abort_handler       = iscsi_eh_abort,
 	.eh_device_reset_handler= iscsi_eh_device_reset,
-	.eh_host_reset_handler	= iscsi_eh_host_reset,
+	.eh_target_reset_handler= iscsi_eh_target_reset,
 	.use_clustering         = DISABLE_CLUSTERING,
 	.slave_configure        = iscsi_tcp_slave_configure,
 	.proc_name		= "iscsi_tcp",
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index 390781894be9..e3e57cce4886 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -1367,7 +1367,7 @@ void iscsi_session_recovery_timedout(struct iscsi_cls_session *cls_session)
 }
 EXPORT_SYMBOL_GPL(iscsi_session_recovery_timedout);
 
-int iscsi_eh_host_reset(struct scsi_cmnd *sc)
+int iscsi_eh_target_reset(struct scsi_cmnd *sc)
 {
 	struct iscsi_cls_session *cls_session;
 	struct iscsi_session *session;
@@ -1381,7 +1381,7 @@ int iscsi_eh_host_reset(struct scsi_cmnd *sc)
 	spin_lock_bh(&session->lock);
 	if (session->state == ISCSI_STATE_TERMINATE) {
 failed:
-		debug_scsi("failing host reset: session terminated "
+		debug_scsi("failing target reset: session terminated "
 			   "[CID %d age %d]\n", conn->id, session->age);
 		spin_unlock_bh(&session->lock);
 		mutex_unlock(&session->eh_mutex);
@@ -1396,7 +1396,7 @@ failed:
 	 */
 	iscsi_conn_failure(conn, ISCSI_ERR_CONN_FAILED);
 
-	debug_scsi("iscsi_eh_host_reset wait for relogin\n");
+	debug_scsi("iscsi_eh_target_reset wait for relogin\n");
 	wait_event_interruptible(conn->ehwait,
 				 session->state == ISCSI_STATE_TERMINATE ||
 				 session->state == ISCSI_STATE_LOGGED_IN ||
@@ -1408,14 +1408,14 @@ failed:
 	spin_lock_bh(&session->lock);
 	if (session->state == ISCSI_STATE_LOGGED_IN)
 		iscsi_session_printk(KERN_INFO, session,
-				     "host reset succeeded\n");
+				     "target reset succeeded\n");
 	else
 		goto failed;
 	spin_unlock_bh(&session->lock);
 	mutex_unlock(&session->eh_mutex);
 	return SUCCESS;
 }
-EXPORT_SYMBOL_GPL(iscsi_eh_host_reset);
+EXPORT_SYMBOL_GPL(iscsi_eh_target_reset);
 
 static void iscsi_tmf_timedout(unsigned long data)
 {
diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h
index 7d8cd159f592..61e53f14f7e1 100644
--- a/include/scsi/libiscsi.h
+++ b/include/scsi/libiscsi.h
@@ -313,7 +313,7 @@ struct iscsi_host {
  */
 extern int iscsi_change_queue_depth(struct scsi_device *sdev, int depth);
 extern int iscsi_eh_abort(struct scsi_cmnd *sc);
-extern int iscsi_eh_host_reset(struct scsi_cmnd *sc);
+extern int iscsi_eh_target_reset(struct scsi_cmnd *sc);
 extern int iscsi_eh_device_reset(struct scsi_cmnd *sc);
 extern int iscsi_queuecommand(struct scsi_cmnd *sc,
 			      void (*done)(struct scsi_cmnd *));
-- 
cgit v1.2.3-59-g8ed1b


From 6f481e3cefeb33094e87af176587e6a3027f104e Mon Sep 17 00:00:00 2001
From: Mike Christie <michaelc@cs.wisc.edu>
Date: Wed, 24 Sep 2008 11:46:13 -0500
Subject: [SCSI] iscsi_tcp: return a descriptive error value during connection
 errors

The segment->done functions return a iscsi error value which gives
a lot more info than conn failed, so this patch has us return
that value. I also add a new one for xmit failures.

Signed-off-by: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
---
 drivers/scsi/iscsi_tcp.c | 12 +++++++-----
 include/scsi/iscsi_if.h  |  1 +
 2 files changed, 8 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c
index 4f096de81525..ed6c54cae7b1 100644
--- a/drivers/scsi/iscsi_tcp.c
+++ b/drivers/scsi/iscsi_tcp.c
@@ -979,7 +979,7 @@ iscsi_tcp_recv(read_descriptor_t *rd_desc, struct sk_buff *skb,
 
 error:
 	debug_tcp("Error receiving PDU, errno=%d\n", rc);
-	iscsi_conn_failure(conn, ISCSI_ERR_CONN_FAILED);
+	iscsi_conn_failure(conn, rc);
 	return 0;
 }
 
@@ -1098,8 +1098,10 @@ iscsi_xmit(struct iscsi_conn *conn)
 
 	while (1) {
 		rc = iscsi_tcp_xmit_segment(tcp_conn, segment);
-		if (rc < 0)
+		if (rc < 0) {
+			rc = ISCSI_ERR_XMIT_FAILED;
 			goto error;
+		}
 		if (rc == 0)
 			break;
 
@@ -1108,7 +1110,7 @@ iscsi_xmit(struct iscsi_conn *conn)
 		if (segment->total_copied >= segment->total_size) {
 			if (segment->done != NULL) {
 				rc = segment->done(tcp_conn, segment);
-				if (rc < 0)
+				if (rc != 0)
 					goto error;
 			}
 		}
@@ -1123,8 +1125,8 @@ error:
 	/* Transmit error. We could initiate error recovery
 	 * here. */
 	debug_tcp("Error sending PDU, errno=%d\n", rc);
-	iscsi_conn_failure(conn, ISCSI_ERR_CONN_FAILED);
-	return rc;
+	iscsi_conn_failure(conn, rc);
+	return -EIO;
 }
 
 /**
diff --git a/include/scsi/iscsi_if.h b/include/scsi/iscsi_if.h
index f274d248a91f..0c9514de5df7 100644
--- a/include/scsi/iscsi_if.h
+++ b/include/scsi/iscsi_if.h
@@ -214,6 +214,7 @@ enum iscsi_err {
 	ISCSI_ERR_PARAM_NOT_FOUND	= ISCSI_ERR_BASE + 16,
 	ISCSI_ERR_NO_SCSI_CMD		= ISCSI_ERR_BASE + 17,
 	ISCSI_ERR_INVALID_HOST		= ISCSI_ERR_BASE + 18,
+	ISCSI_ERR_XMIT_FAILED		= ISCSI_ERR_BASE + 19,
 };
 
 /*
-- 
cgit v1.2.3-59-g8ed1b