block: add configurable error injection

Add a new block error injection interface that allows to inject specific
status code for specific ranges.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Hannes Reinecke <hare@kernel.org>
Reviewed-by: Md Haris Iqbal <haris.iqbal@linux.dev>
Link: https://patch.msgid.link/20260611140703.2401204-5-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Author: Christoph Hellwig

Documentation/block/error-injection.rst

@@ -0,0 +1,59 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+============================
+Configurable Error Injection
+============================
+
+Overview
+--------
+
+Configurable error injection allows injecting specific block layer status codes
+for sector ranges of a block device.  Errors can be injected unconditionally, or
+with a given probability.
+
+To use configurable error injection, CONFIG_BLK_ERROR_INJECTION must be enabled.
+
+The only interface is the error_injection debugfs file, which is created for
+each registered gendisk.  Writes to this file are used to create or delete rules
+and reads return a list of the current error injection sites.
+
+Options
+-------
+
+The following options specify the operations:
+
+===================	=======================================================
+add			add a new rule
+removeall		remove all existing rules
+===================	=======================================================
+
+The following options specify the details of the rule for the add operation:
+
+===================	=======================================================
+op=<string>		block layer operation this rule applies to.  This uses
+			the XYZ for each REQ_OP_XYZ operation, e.g. READ, WRITE
+			or DISCARD. Mandatory.
+status=<string>		Status to return.  This uses XYZ for each BLK_STS_XYZ
+			code, e.g. IOERR or MEDIUM. Mandatory.
+start=<number>		First block layer sector the rule applies to.
+			Optional, defaults to 0.
+nr_sectors=<number>	Number of sectors this rule applies.
+			Optional, defaults to the remainder of the device.
+chance=<number>		Only return a failure with a likelihood of 1/chance.
+			Optional, defaults to 1 (always).
+===================	=======================================================
+
+Example
+-------
+
+Return BLK_STS_IOERR for one in 10 reads of sector 0 of /dev/nvme0n1:
+
+	$ echo 'add,op=READ,start=0,status=IOERR,chance=10' > /sys/kernel/debug/block/nvme0n1/error_injection
+
+Return BLK_STS_MEDIUM for every write to /dev/nvme0n1:
+
+	$ echo 'add,op=WRITE,start=0,status=MEDIUM' > /sys/kernel/debug/block/nvme0n1/error_injection
+
+Remove all rules for /dev/nvme0n1:
+
+	$ echo 'removeall' > /sys/kernel/debug/block/nvme0n1/error_injection

Documentation/block/index.rst

@@ -22,3 +22,4 @@ Block
    switching-sched
    writeback_cache_control
    ublk
+   error-injection

block/Kconfig

@@ -221,6 +221,14 @@ config BLOCK_HOLDER_DEPRECATED
 config BLK_MQ_STACKING
 	bool
 
+config BLK_ERROR_INJECTION
+	bool "Enable block layer error injection"
+	select JUMP_LABEL if HAVE_ARCH_JUMP_LABEL
+	help
+	  Enable inserting arbitrary block errors through a debugfs interface.
+
+	  See Documentation/block/error-injection.rst for details.
+
 source "block/Kconfig.iosched"
 
 endif # BLOCK

block/Makefile

@@ -13,6 +13,7 @@ obj-y		:= bdev.o fops.o bio.o elevator.o blk-core.o blk-sysfs.o \
 			genhd.o ioprio.o badblocks.o partitions/ blk-rq-qos.o \
 			disk-events.o blk-ia-ranges.o early-lookup.o
 
+obj-$(CONFIG_BLK_ERROR_INJECTION) += error-injection.o
 obj-$(CONFIG_BLK_DEV_BSG_COMMON) += bsg.o
 obj-$(CONFIG_BLK_DEV_BSGLIB)	+= bsg-lib.o
 obj-$(CONFIG_BLK_CGROUP)	+= blk-cgroup.o

block/blk-core.c

@@ -50,6 +50,7 @@
 #include "blk-cgroup.h"
 #include "blk-throttle.h"
 #include "blk-ioprio.h"
+#include "error-injection.h"
 
 struct dentry *blk_debugfs_root;
 
@@ -767,6 +768,9 @@ static void __submit_bio_noacct_mq(struct bio *bio)
 
 void submit_bio_noacct_nocheck(struct bio *bio, bool split)
 {
+	if (unlikely(blk_error_inject(bio)))
+		return;
+
 	blk_cgroup_bio_start(bio);
 
 	if (!bio_flagged(bio, BIO_TRACE_COMPLETION)) {

block/blk-sysfs.c

@@ -19,6 +19,7 @@
 #include "blk-wbt.h"
 #include "blk-cgroup.h"
 #include "blk-throttle.h"
+#include "error-injection.h"
 
 struct queue_sysfs_entry {
 	struct attribute attr;
@@ -933,6 +934,8 @@ static void blk_debugfs_remove(struct gendisk *disk)
 
 	blk_debugfs_lock_nomemsave(q);
 	blk_trace_shutdown(q);
+	if (IS_ENABLED(CONFIG_BLK_ERROR_INJECTION))
+		blk_error_injection_exit(disk);
 	debugfs_remove_recursive(q->debugfs_dir);
 	q->debugfs_dir = NULL;
 	q->sched_debugfs_dir = NULL;
@@ -963,6 +966,8 @@ int blk_register_queue(struct gendisk *disk)
 
 	memflags = blk_debugfs_lock(q);
 	q->debugfs_dir = debugfs_create_dir(disk->disk_name, blk_debugfs_root);
+	if (IS_ENABLED(CONFIG_BLK_ERROR_INJECTION))
+		blk_error_injection_init(disk);
 	if (queue_is_mq(q))
 		blk_mq_debugfs_register(q);
 	blk_debugfs_unlock(q, memflags);