linux/drivers/nvme/host/fault_inject.c
Thomas Tai b9e03857f2 nvme: Add fault injection feature
Linux's fault injection framework provides a systematic way to support
error injection via debugfs in the /sys/kernel/debug directory. This
patch uses the framework to add error injection to NVMe driver. The
fault injection source code is stored in a separate file and only linked
if CONFIG_FAULT_INJECTION_DEBUG_FS kernel config is selected.

Once the error injection is enabled, NVME_SC_INVALID_OPCODE with no
retry will be injected into the nvme_end_request. Users can change
the default status code and no retry flag via debufs. Following example
shows how to enable and inject an error. For more examples, refer to
Documentation/fault-injection/nvme-fault-injection.txt

How to enable nvme fault injection:

First, enable CONFIG_FAULT_INJECTION_DEBUG_FS kernel config,
recompile the kernel. After booting up the kernel, do the
following.

How to inject an error:

mount /dev/nvme0n1 /mnt
echo 1 > /sys/kernel/debug/nvme0n1/fault_inject/times
echo 100 > /sys/kernel/debug/nvme0n1/fault_inject/probability
cp a.file /mnt

Expected Result:

cp: cannot stat ‘/mnt/a.file’: Input/output error

Message from dmesg:

FAULT_INJECTION: forcing a failure.
name fault_inject, interval 1, probability 100, space 0, times 1
CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.15.0-rc8+ #2
Hardware name: innotek GmbH VirtualBox/VirtualBox,
BIOS VirtualBox 12/01/2006
Call Trace:
  <IRQ>
  dump_stack+0x5c/0x7d
  should_fail+0x148/0x170
  nvme_should_fail+0x2f/0x50 [nvme_core]
  nvme_process_cq+0xe7/0x1d0 [nvme]
  nvme_irq+0x1e/0x40 [nvme]
  __handle_irq_event_percpu+0x3a/0x190
  handle_irq_event_percpu+0x30/0x70
  handle_irq_event+0x36/0x60
  handle_fasteoi_irq+0x78/0x120
  handle_irq+0xa7/0x130
  ? tick_irq_enter+0xa8/0xc0
  do_IRQ+0x43/0xc0
  common_interrupt+0xa2/0xa2
  </IRQ>
RIP: 0010:native_safe_halt+0x2/0x10
RSP: 0018:ffffffff82003e90 EFLAGS: 00000246 ORIG_RAX: ffffffffffffffdd
RAX: ffffffff817a10c0 RBX: ffffffff82012480 RCX: 0000000000000000
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
RBP: 0000000000000000 R08: 000000008e38ce64 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: ffffffff82012480
R13: ffffffff82012480 R14: 0000000000000000 R15: 0000000000000000
  ? __sched_text_end+0x4/0x4
  default_idle+0x18/0xf0
  do_idle+0x150/0x1d0
  cpu_startup_entry+0x6f/0x80
  start_kernel+0x4c4/0x4e4
  ? set_init_arg+0x55/0x55
  secondary_startup_64+0xa5/0xb0
  print_req_error: I/O error, dev nvme0n1, sector 9240
EXT4-fs error (device nvme0n1): ext4_find_entry:1436:
inode #2: comm cp: reading directory lblock 0

Signed-off-by: Thomas Tai <thomas.tai@oracle.com>
Reviewed-by: Eric Saint-Etienne <eric.saint.etienne@oracle.com>
Signed-off-by: Karl Volz <karl.volz@oracle.com>
Reviewed-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-03-26 08:53:43 -06:00

80 lines
2.0 KiB
C

/*
* fault injection support for nvme.
*
* Copyright (c) 2018, Oracle and/or its affiliates
*
*/
#include <linux/moduleparam.h>
#include "nvme.h"
static DECLARE_FAULT_ATTR(fail_default_attr);
/* optional fault injection attributes boot time option:
* nvme_core.fail_request=<interval>,<probability>,<space>,<times>
*/
static char *fail_request;
module_param(fail_request, charp, 0000);
void nvme_fault_inject_init(struct nvme_ns *ns)
{
struct dentry *dir, *parent;
char *name = ns->disk->disk_name;
struct nvme_fault_inject *fault_inj = &ns->fault_inject;
struct fault_attr *attr = &fault_inj->attr;
/* set default fault injection attribute */
if (fail_request)
setup_fault_attr(&fail_default_attr, fail_request);
/* create debugfs directory and attribute */
parent = debugfs_create_dir(name, NULL);
if (!parent) {
pr_warn("%s: failed to create debugfs directory\n", name);
return;
}
*attr = fail_default_attr;
dir = fault_create_debugfs_attr("fault_inject", parent, attr);
if (IS_ERR(dir)) {
pr_warn("%s: failed to create debugfs attr\n", name);
debugfs_remove_recursive(parent);
return;
}
ns->fault_inject.parent = parent;
/* create debugfs for status code and dont_retry */
fault_inj->status = NVME_SC_INVALID_OPCODE;
fault_inj->dont_retry = true;
debugfs_create_x16("status", 0600, dir, &fault_inj->status);
debugfs_create_bool("dont_retry", 0600, dir, &fault_inj->dont_retry);
}
void nvme_fault_inject_fini(struct nvme_ns *ns)
{
/* remove debugfs directories */
debugfs_remove_recursive(ns->fault_inject.parent);
}
void nvme_should_fail(struct request *req)
{
struct gendisk *disk = req->rq_disk;
struct nvme_ns *ns = NULL;
u16 status;
/*
* make sure this request is coming from a valid namespace
*/
if (!disk)
return;
ns = disk->private_data;
if (ns && should_fail(&ns->fault_inject.attr, 1)) {
/* inject status code and DNR bit */
status = ns->fault_inject.status;
if (ns->fault_inject.dont_retry)
status |= NVME_SC_DNR;
nvme_req(req)->status = status;
}
}
EXPORT_SYMBOL_GPL(nvme_should_fail);