block: add fault injection mechanism for faking request timeouts

Only works for the generic request timer handling. Allows one to
sporadically ignore request completions, thus exercising the timeout
handling.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>

6 files changed, 94 insertions, 1 deletions

diff --git a/block/blk-softirq.c b/block/blk-softirq.c
index 7ab344a..e660d26 100644
--- a/block/blk-softirq.c
+++ b/block/blk-softirq.c
@@ -154,6 +154,8 @@ do_local:
  **/
 void blk_complete_request(struct request *req)
 {
+	if (unlikely(blk_should_fake_timeout(req->q)))
+		return;
 	if (!blk_mark_rq_complete(req))
 		__blk_complete_request(req);
 }
diff --git a/block/blk-timeout.c b/block/blk-timeout.c
index 6e5c781..9b4ad13 100644
--- a/block/blk-timeout.c
+++ b/block/blk-timeout.c
@@ -4,9 +4,68 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/blkdev.h>
+#include <linux/fault-inject.h>
 
 #include "blk.h"
 
+#ifdef CONFIG_FAIL_IO_TIMEOUT
+
+static DECLARE_FAULT_ATTR(fail_io_timeout);
+
+static int __init setup_fail_io_timeout(char *str)
+{
+	return setup_fault_attr(&fail_io_timeout, str);
+}
+__setup("fail_io_timeout=", setup_fail_io_timeout);
+
+int blk_should_fake_timeout(struct request_queue *q)
+{
+	if (!test_bit(QUEUE_FLAG_FAIL_IO, &q->queue_flags))
+		return 0;
+
+	return should_fail(&fail_io_timeout, 1);
+}
+
+static int __init fail_io_timeout_debugfs(void)
+{
+	return init_fault_attr_dentries(&fail_io_timeout, "fail_io_timeout");
+}
+
+late_initcall(fail_io_timeout_debugfs);
+
+ssize_t part_timeout_show(struct device *dev, struct device_attribute *attr,
+			  char *buf)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+	int set = test_bit(QUEUE_FLAG_FAIL_IO, &disk->queue->queue_flags);
+
+	return sprintf(buf, "%d\n", set != 0);
+}
+
+ssize_t part_timeout_store(struct device *dev, struct device_attribute *attr,
+			   const char *buf, size_t count)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+	int val;
+
+	if (count) {
+		struct request_queue *q = disk->queue;
+		char *p = (char *) buf;
+
+		val = simple_strtoul(p, &p, 10);
+		spin_lock_irq(q->queue_lock);
+		if (val)
+			queue_flag_set(QUEUE_FLAG_FAIL_IO, q);
+		else
+			queue_flag_clear(QUEUE_FLAG_FAIL_IO, q);
+		spin_unlock_irq(q->queue_lock);
+	}
+
+	return count;
+}
+
+#endif /* CONFIG_FAIL_IO_TIMEOUT */
+
 /*
  * blk_delete_timer - Delete/cancel timer for a given function.
  * @req:	request that we are canceling timer for
diff --git a/block/blk.h b/block/blk.h
index a4f4a50..e5c5797 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -42,6 +42,18 @@ static inline void blk_clear_rq_complete(struct request *rq)
 	clear_bit(REQ_ATOM_COMPLETE, &rq->atomic_flags);
 }
 
+#ifdef CONFIG_FAIL_IO_TIMEOUT
+int blk_should_fake_timeout(struct request_queue *);
+ssize_t part_timeout_show(struct device *, struct device_attribute *, char *);
+ssize_t part_timeout_store(struct device *, struct device_attribute *,
+				const char *, size_t);
+#else
+static inline int blk_should_fake_timeout(struct request_queue *q)
+{
+	return 0;
+}
+#endif
+
 struct io_context *current_io_context(gfp_t gfp_flags, int node);
 
 int ll_back_merge_fn(struct request_queue *q, struct request *req,
diff --git a/block/genhd.c b/block/genhd.c
index 8acaff0..4cd3433 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -817,6 +817,11 @@ static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL);
 static struct device_attribute dev_attr_fail =
 	__ATTR(make-it-fail, S_IRUGO|S_IWUSR, part_fail_show, part_fail_store);
 #endif
+#ifdef CONFIG_FAIL_IO_TIMEOUT
+static struct device_attribute dev_attr_fail_timeout =
+	__ATTR(io-timeout-fail,  S_IRUGO|S_IWUSR, part_timeout_show,
+		part_timeout_store);
+#endif
 
 static struct attribute *disk_attrs[] = {
 	&dev_attr_range.attr,
@@ -829,6 +834,9 @@ static struct attribute *disk_attrs[] = {
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 	&dev_attr_fail.attr,
 #endif
+#ifdef CONFIG_FAIL_IO_TIMEOUT
+	&dev_attr_fail_timeout.attr,
+#endif
 	NULL
 };
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index b47767c..e34999d 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -440,6 +440,7 @@ struct request_queue
 #define QUEUE_FLAG_BIDI		9	/* queue supports bidi requests */
 #define QUEUE_FLAG_NOMERGES    10	/* disable merge attempts */
 #define QUEUE_FLAG_SAME_COMP   11	/* force complete on same CPU */
+#define QUEUE_FLAG_FAIL_IO     12	/* fake timeout */
 
 static inline int queue_is_locked(struct request_queue *q)
 {
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index c556896..7d7a31d 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -683,10 +683,21 @@ config FAIL_PAGE_ALLOC
 
 config FAIL_MAKE_REQUEST
 	bool "Fault-injection capability for disk IO"
-	depends on FAULT_INJECTION
+	depends on FAULT_INJECTION && BLOCK
 	help
 	  Provide fault-injection capability for disk IO.
 
+config FAIL_IO_TIMEOUT
+	bool "Faul-injection capability for faking disk interrupts"
+	depends on FAULT_INJECTION && BLOCK
+	help
+	  Provide fault-injection capability on end IO handling. This
+	  will make the block layer "forget" an interrupt as configured,
+	  thus exercising the error handling.
+
+	  Only works with drivers that use the generic timeout handling,
+	  for others it wont do anything.
+
 config FAULT_INJECTION_DEBUG_FS
 	bool "Debugfs entries for fault-injection capabilities"
 	depends on FAULT_INJECTION && SYSFS && DEBUG_FS