linux-scsi.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Bart Van Assche <bvanassche@acm.org>
Cc: linux-scsi <linux-scsi@vger.kernel.org>,
	James Bottomley <jbottomley@parallels.com>,
	Mike Christie <michaelc@cs.wisc.edu>,
	Jens Axboe <axboe@kernel.dk>, Tejun Heo <tj@kernel.org>,
	Chanho Min <chanho.min@lge.com>, Hannes Reinecke <hare@suse.de>
Subject: [PATCH v6 11/13] Make scsi_remove_host() wait until error handling finished
Date: Wed, 28 Nov 2012 13:52:51 +0100	[thread overview]
Message-ID: <50B60923.3080207@acm.org> (raw)
In-Reply-To: <50B60619.4080406@acm.org>

A SCSI LLD may start cleaning up host resources as soon as
scsi_remove_host() returns. These host resources may be needed by
the LLD in an implementation of one of the eh_* functions. So if
one of the eh_* functions is in progress when scsi_remove_host()
is invoked, wait until the eh_* function has finished. Also, do
not invoke any of the eh_* functions after scsi_remove_host() has
started.

Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Mike Christie <michaelc@cs.wisc.edu>
Cc: Tejun Heo <tj@kernel.org>
---
 drivers/scsi/hosts.c      |    2 +-
 drivers/scsi/scsi_error.c |  114 ++++++++++++++++++++++++++++++++++-----------
 include/scsi/scsi_host.h  |    1 +
 3 files changed, 89 insertions(+), 28 deletions(-)

diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c
index 7bd944e..477b8d6 100644
--- a/drivers/scsi/hosts.c
+++ b/drivers/scsi/hosts.c
@@ -155,7 +155,7 @@ static bool __scsi_remove_host_done(struct Scsi_Host *shost)
 {
 	lockdep_assert_held(shost->host_lock);
 
-	return list_empty(&shost->__devices);
+	return list_empty(&shost->__devices) && !shost->eh_active;
 }
 
 /* Test whether scsi_remove_host() may finish, and if so, wake it up. */
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index c1b05a8..cab2ac3 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -536,8 +536,52 @@ static void scsi_eh_done(struct scsi_cmnd *scmd)
 }
 
 /**
+ * scsi_begin_eh - start host-related error handling
+ *
+ * Must be called before invoking any of the scsi_host_template.eh_* functions
+ * to avoid that scsi_remove_host() returns while one of these callback
+ * functions is in progress.
+ *
+ * Returns true if invoking the eh_* function is allowed and false if not.
+ * If this function returns true then scsi_end_eh() must be called eventually.
+ *
+ * Note: scsi_send_eh_cmnd() calls do not have to be protected by a
+ * scsi_begin_eh() / scsi_end_eh() pair since these operate on an unfinished
+ * block layer request. Since scsi_remove_host() waits until all SCSI devices
+ * have been removed and since blk_cleanup_queue() is invoked during SCSI
+ * device removal scsi_remove_host() won't finish while a scsi_send_eh_cmnd()
+ * call is in progress.
+ */
+static bool scsi_begin_eh(struct Scsi_Host *host)
+{
+	bool res;
+
+	spin_lock_irq(host->host_lock);
+	res = scsi_host_scan_allowed(host);
+	if (res) {
+		WARN_ON_ONCE(host->eh_active < 0 || host->eh_active > 1);
+		host->eh_active++;
+	}
+	spin_unlock_irq(host->host_lock);
+
+	return res;
+}
+
+/**
+ * scsi_end_eh - finish host-related error handling
+ */
+static void scsi_end_eh(struct Scsi_Host *host)
+{
+	spin_lock_irq(host->host_lock);
+	host->eh_active--;
+	WARN_ON_ONCE(host->eh_active < 0 || host->eh_active > 1);
+	__scsi_check_remove_host_done(host);
+	spin_unlock_irq(host->host_lock);
+}
+
+/**
  * scsi_try_host_reset - ask host adapter to reset itself
- * @scmd:	SCSI cmd to send hsot reset.
+ * @scmd:	SCSI cmd to send host reset.
  */
 static int scsi_try_host_reset(struct scsi_cmnd *scmd)
 {
@@ -552,14 +596,17 @@ static int scsi_try_host_reset(struct scsi_cmnd *scmd)
 	if (!hostt->eh_host_reset_handler)
 		return FAILED;
 
-	rtn = hostt->eh_host_reset_handler(scmd);
-
-	if (rtn == SUCCESS) {
-		if (!hostt->skip_settle_delay)
-			ssleep(HOST_RESET_SETTLE_TIME);
-		spin_lock_irqsave(host->host_lock, flags);
-		scsi_report_bus_reset(host, scmd_channel(scmd));
-		spin_unlock_irqrestore(host->host_lock, flags);
+	rtn = FAST_IO_FAIL;
+	if (scsi_begin_eh(host)) {
+		rtn = hostt->eh_host_reset_handler(scmd);
+		if (rtn == SUCCESS) {
+			if (!hostt->skip_settle_delay)
+				ssleep(HOST_RESET_SETTLE_TIME);
+			spin_lock_irqsave(host->host_lock, flags);
+			scsi_report_bus_reset(host, scmd_channel(scmd));
+			spin_unlock_irqrestore(host->host_lock, flags);
+		}
+		scsi_end_eh(host);
 	}
 
 	return rtn;
@@ -582,14 +629,17 @@ static int scsi_try_bus_reset(struct scsi_cmnd *scmd)
 	if (!hostt->eh_bus_reset_handler)
 		return FAILED;
 
-	rtn = hostt->eh_bus_reset_handler(scmd);
-
-	if (rtn == SUCCESS) {
-		if (!hostt->skip_settle_delay)
-			ssleep(BUS_RESET_SETTLE_TIME);
-		spin_lock_irqsave(host->host_lock, flags);
-		scsi_report_bus_reset(host, scmd_channel(scmd));
-		spin_unlock_irqrestore(host->host_lock, flags);
+	rtn = FAST_IO_FAIL;
+	if (scsi_begin_eh(host)) {
+		rtn = hostt->eh_bus_reset_handler(scmd);
+		if (rtn == SUCCESS) {
+			if (!hostt->skip_settle_delay)
+				ssleep(BUS_RESET_SETTLE_TIME);
+			spin_lock_irqsave(host->host_lock, flags);
+			scsi_report_bus_reset(host, scmd_channel(scmd));
+			spin_unlock_irqrestore(host->host_lock, flags);
+		}
+		scsi_end_eh(host);
 	}
 
 	return rtn;
@@ -621,12 +671,17 @@ static int scsi_try_target_reset(struct scsi_cmnd *scmd)
 	if (!hostt->eh_target_reset_handler)
 		return FAILED;
 
-	rtn = hostt->eh_target_reset_handler(scmd);
-	if (rtn == SUCCESS) {
-		spin_lock_irqsave(host->host_lock, flags);
-		__starget_for_each_device(scsi_target(scmd->device), NULL,
-					  __scsi_report_device_reset);
-		spin_unlock_irqrestore(host->host_lock, flags);
+	rtn = FAST_IO_FAIL;
+	if (scsi_begin_eh(host)) {
+		rtn = hostt->eh_target_reset_handler(scmd);
+		if (rtn == SUCCESS) {
+			spin_lock_irqsave(host->host_lock, flags);
+			__starget_for_each_device(scsi_target(scmd->device),
+						  NULL,
+						  __scsi_report_device_reset);
+			spin_unlock_irqrestore(host->host_lock, flags);
+		}
+		scsi_end_eh(host);
 	}
 
 	return rtn;
@@ -645,14 +700,19 @@ static int scsi_try_target_reset(struct scsi_cmnd *scmd)
 static int scsi_try_bus_device_reset(struct scsi_cmnd *scmd)
 {
 	int rtn;
-	struct scsi_host_template *hostt = scmd->device->host->hostt;
+	struct Scsi_Host *host = scmd->device->host;
+	struct scsi_host_template *hostt = host->hostt;
 
 	if (!hostt->eh_device_reset_handler)
 		return FAILED;
 
-	rtn = hostt->eh_device_reset_handler(scmd);
-	if (rtn == SUCCESS)
-		__scsi_report_device_reset(scmd->device, NULL);
+	rtn = FAST_IO_FAIL;
+	if (scsi_begin_eh(host)) {
+		rtn = hostt->eh_device_reset_handler(scmd);
+		if (rtn == SUCCESS)
+			__scsi_report_device_reset(scmd->device, NULL);
+		scsi_end_eh(host);
+	}
 	return rtn;
 }
 
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index 1b7fd89..5e2fcd2 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -576,6 +576,7 @@ struct Scsi_Host {
 	struct task_struct    * ehandler;  /* Error recovery thread. */
 	struct completion     * eh_action; /* Wait for specific actions on the
 					      host. */
+	int			eh_active;
 	wait_queue_head_t       host_wait;
 	wait_queue_head_t	remove_host;
 	struct scsi_host_template *hostt;
-- 
1.7.10.4


  parent reply	other threads:[~2012-11-28 12:52 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-11-28 12:39 [PATCH 0/13 v6] More device removal fixes Bart Van Assche
2012-11-28 12:42 ` [PATCH v6 01/13] block: Rename queue dead flag Bart Van Assche
2012-11-28 12:43 ` [PATCH v6 02/13] block: Let blk_drain_queue() caller obtain the queue lock Bart Van Assche
2012-11-28 12:44 ` [PATCH v6 03/13] block: Avoid that request_fn is invoked on a dead queue Bart Van Assche
2012-12-02 13:23   ` Tejun Heo
2012-12-02 13:35     ` Bart Van Assche
2012-11-28 12:45 ` [PATCH v6 04/13] block: Avoid scheduling delayed work " Bart Van Assche
2012-12-02 13:26   ` Tejun Heo
2012-12-02 13:41     ` Bart Van Assche
2012-12-02 13:59       ` Tejun Heo
2012-11-28 12:46 ` [PATCH v6 05/13] block: Make blk_cleanup_queue() wait until request_fn finished Bart Van Assche
2012-12-02 13:28   ` Tejun Heo
2012-11-28 12:47 ` [PATCH v6 06/13] bsg: Remove unused function bsg_goose_queue() Bart Van Assche
2012-12-02 13:29   ` Tejun Heo
2012-11-28 12:48 ` [PATCH v6 07/13] Fix race between starved list processing and device removal Bart Van Assche
2012-12-02 13:32   ` Tejun Heo
2012-11-28 12:48 ` [PATCH v6 08/13] Remove get_device() / put_device() pair from scsi_request_fn() Bart Van Assche
2012-12-02 13:34   ` Tejun Heo
2012-11-28 12:50 ` [PATCH v6 09/13] Avoid saving/restoring interrupt state inside scsi_remove_host() Bart Van Assche
2012-12-02 13:35   ` Tejun Heo
2012-11-28 12:51 ` [PATCH v6 10/13] Make scsi_remove_host() wait for device removal Bart Van Assche
2012-12-02 13:45   ` Tejun Heo
2012-12-02 13:48     ` Tejun Heo
2012-12-03  8:23     ` Bart Van Assche
2012-12-03 16:15       ` Tejun Heo
2012-12-03 16:38         ` Bart Van Assche
2012-12-03 16:42           ` Tejun Heo
2012-12-07  7:41             ` Bart Van Assche
2012-11-28 12:52 ` Bart Van Assche [this message]
2012-12-02 13:51   ` [PATCH v6 11/13] Make scsi_remove_host() wait until error handling finished Tejun Heo
2012-11-28 12:53 ` [PATCH v6 12/13] Avoid that scsi_device_set_state() triggers a race Bart Van Assche
2012-12-02 13:53   ` Tejun Heo
2012-11-28 12:53 ` [PATCH v6 13/13] Do not queue new I/O after scsi_remove_host() started Bart Van Assche
2012-12-02 13:58   ` Tejun Heo
2012-12-02 14:02 ` [PATCH 0/13 v6] More device removal fixes Tejun Heo
2012-12-06 13:33 ` Jens Axboe

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=50B60923.3080207@acm.org \
    --to=bvanassche@acm.org \
    --cc=axboe@kernel.dk \
    --cc=chanho.min@lge.com \
    --cc=hare@suse.de \
    --cc=jbottomley@parallels.com \
    --cc=linux-scsi@vger.kernel.org \
    --cc=michaelc@cs.wisc.edu \
    --cc=tj@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).