[PATCH] fault-injection capability for disk IO

This patch provides fault-injection capability for disk IO.

Boot option:

fail_make_request=<probability>,<interval>,<space>,<times>

	<interval> -- specifies the interval of failures.

	<probability> -- specifies how often it should fail in percent.

	<space> -- specifies the size of free space where disk IO can be issued
		   safely in bytes.

	<times> -- specifies how many times failures may happen at most.

Debugfs:

/debug/fail_make_request/interval
/debug/fail_make_request/probability
/debug/fail_make_request/specifies
/debug/fail_make_request/times

Example:

	fail_make_request=10,100,0,-1
	echo 1 > /sys/blocks/hda/hda1/make-it-fail

generic_make_request() on /dev/hda1 fails once per 10 times.

Cc: Jens Axboe <axboe@suse.de>
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

2 files changed, 71 insertions, 0 deletions

diff --git a/block/genhd.c b/block/genhd.c
index 653919d50cd4..457fdac4c17d 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -417,6 +417,34 @@ static struct disk_attribute disk_attr_stat = {
         .show   = disk_stats_read
 };
 
+#ifdef CONFIG_FAIL_MAKE_REQUEST
+
+static ssize_t disk_fail_store(struct gendisk * disk,
+                               const char *buf, size_t count)
+{
+        int i;
+
+        if (count > 0 && sscanf(buf, "%d", &i) > 0) {
+                if (i == 0)
+                        disk->flags &= ~GENHD_FL_FAIL;
+                else
+                        disk->flags |= GENHD_FL_FAIL;
+        }
+
+        return count;
+}
+static ssize_t disk_fail_read(struct gendisk * disk, char *page)
+{
+        return sprintf(page, "%d\n", disk->flags & GENHD_FL_FAIL ? 1 : 0);
+}
+static struct disk_attribute disk_attr_fail = {
+        .attr = {.name = "make-it-fail", .mode = S_IRUGO | S_IWUSR },
+        .store  = disk_fail_store,
+        .show   = disk_fail_read
+};
+
+#endif
+
 static struct attribute * default_attrs[] = {
         &disk_attr_uevent.attr,
         &disk_attr_dev.attr,
@@ -424,6 +452,9 @@ static struct attribute * default_attrs[] = {
         &disk_attr_removable.attr,
         &disk_attr_size.attr,
         &disk_attr_stat.attr,
+#ifdef CONFIG_FAIL_MAKE_REQUEST
+        &disk_attr_fail.attr,
+#endif
         NULL,
 };
 
diff --git a/block/ll_rw_blk.c b/block/ll_rw_blk.c
index 31512cd9f3ad..4f83fd922377 100644
--- a/block/ll_rw_blk.c
+++ b/block/ll_rw_blk.c
@@ -28,6 +28,7 @@
 #include <linux/interrupt.h>
 #include <linux/cpu.h>
 #include <linux/blktrace_api.h>
+#include <linux/fault-inject.h>
 
 /*
  * for max sense size
@@ -3056,6 +3057,42 @@ static void handle_bad_sector(struct bio *bio)
         set_bit(BIO_EOF, &bio->bi_flags);
 }
 
+#ifdef CONFIG_FAIL_MAKE_REQUEST
+
+static DECLARE_FAULT_ATTR(fail_make_request);
+
+static int __init setup_fail_make_request(char *str)
+{
+        return setup_fault_attr(&fail_make_request, str);
+}
+__setup("fail_make_request=", setup_fail_make_request);
+
+static int should_fail_request(struct bio *bio)
+{
+        if ((bio->bi_bdev->bd_disk->flags & GENHD_FL_FAIL) ||
+            (bio->bi_bdev->bd_part && bio->bi_bdev->bd_part->make_it_fail))
+                return should_fail(&fail_make_request, bio->bi_size);
+
+        return 0;
+}
+
+static int __init fail_make_request_debugfs(void)
+{
+        return init_fault_attr_dentries(&fail_make_request,
+                                        "fail_make_request");
+}
+
+late_initcall(fail_make_request_debugfs);
+
+#else /* CONFIG_FAIL_MAKE_REQUEST */
+
+static inline int should_fail_request(struct bio *bio)
+{
+        return 0;
+}
+
+#endif /* CONFIG_FAIL_MAKE_REQUEST */
+
 /**
  * generic_make_request: hand a buffer to its device driver for I/O
  * @bio:  The bio describing the location in memory and on the device.
@@ -3141,6 +3178,9 @@ end_io:
                 if (unlikely(test_bit(QUEUE_FLAG_DEAD, &q->queue_flags)))
                         goto end_io;
 
+                if (should_fail_request(bio))
+                        goto end_io;
+
                 /*
                  * If this device has partitions, remap block n
                  * of partition p to block n+start(p) of the disk.