1NVMe Fault Injection
  2====================
  3Linux's fault injection framework provides a systematic way to support
  4error injection via debugfs in the /sys/kernel/debug directory. When
  5enabled, the default NVME_SC_INVALID_OPCODE with no retry will be
  6injected into the nvme_try_complete_req. Users can change the default status
  7code and no retry flag via the debugfs. The list of Generic Command
  8Status can be found in include/linux/nvme.h
  9
 10Following examples show how to inject an error into the nvme.
 11
 12First, enable CONFIG_FAULT_INJECTION_DEBUG_FS kernel config,
 13recompile the kernel. After booting up the kernel, do the
 14following.
 15
 16Example 1: Inject default status code with no retry
 17---------------------------------------------------
 18
 19::
 20
 21  mount /dev/nvme0n1 /mnt
 22  echo 1 > /sys/kernel/debug/nvme0n1/fault_inject/times
 23  echo 100 > /sys/kernel/debug/nvme0n1/fault_inject/probability
 24  cp a.file /mnt
 25
 26Expected Result::
 27
 28  cp: cannot stat ‘/mnt/a.file’: Input/output error
 29
 30Message from dmesg::
 31
 32  FAULT_INJECTION: forcing a failure.
 33  name fault_inject, interval 1, probability 100, space 0, times 1
 34  CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.15.0-rc8+ #2
 35  Hardware name: innotek GmbH VirtualBox/VirtualBox,
 36  BIOS VirtualBox 12/01/2006
 37  Call Trace:
 38    <IRQ>
 39    dump_stack+0x5c/0x7d
 40    should_fail+0x148/0x170
 41    nvme_should_fail+0x2f/0x50 [nvme_core]
 42    nvme_process_cq+0xe7/0x1d0 [nvme]
 43    nvme_irq+0x1e/0x40 [nvme]
 44    __handle_irq_event_percpu+0x3a/0x190
 45    handle_irq_event_percpu+0x30/0x70
 46    handle_irq_event+0x36/0x60
 47    handle_fasteoi_irq+0x78/0x120
 48    handle_irq+0xa7/0x130
 49    ? tick_irq_enter+0xa8/0xc0
 50    do_IRQ+0x43/0xc0
 51    common_interrupt+0xa2/0xa2
 52    </IRQ>
 53  RIP: 0010:native_safe_halt+0x2/0x10
 54  RSP: 0018:ffffffff82003e90 EFLAGS: 00000246 ORIG_RAX: ffffffffffffffdd
 55  RAX: ffffffff817a10c0 RBX: ffffffff82012480 RCX: 0000000000000000
 56  RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
 57  RBP: 0000000000000000 R08: 000000008e38ce64 R09: 0000000000000000
 58  R10: 0000000000000000 R11: 0000000000000000 R12: ffffffff82012480
 59  R13: ffffffff82012480 R14: 0000000000000000 R15: 0000000000000000
 60    ? __sched_text_end+0x4/0x4
 61    default_idle+0x18/0xf0
 62    do_idle+0x150/0x1d0
 63    cpu_startup_entry+0x6f/0x80
 64    start_kernel+0x4c4/0x4e4
 65    ? set_init_arg+0x55/0x55
 66    secondary_startup_64+0xa5/0xb0
 67    print_req_error: I/O error, dev nvme0n1, sector 9240
 68  EXT4-fs error (device nvme0n1): ext4_find_entry:1436:
 69  inode #2: comm cp: reading directory lblock 0
 70
 71Example 2: Inject default status code with retry
 72------------------------------------------------
 73
 74::
 75
 76  mount /dev/nvme0n1 /mnt
 77  echo 1 > /sys/kernel/debug/nvme0n1/fault_inject/times
 78  echo 100 > /sys/kernel/debug/nvme0n1/fault_inject/probability
 79  echo 1 > /sys/kernel/debug/nvme0n1/fault_inject/status
 80  echo 0 > /sys/kernel/debug/nvme0n1/fault_inject/dont_retry
 81
 82  cp a.file /mnt
 83
 84Expected Result::
 85
 86  command success without error
 87
 88Message from dmesg::
 89
 90  FAULT_INJECTION: forcing a failure.
 91  name fault_inject, interval 1, probability 100, space 0, times 1
 92  CPU: 1 PID: 0 Comm: swapper/1 Not tainted 4.15.0-rc8+ #4
 93  Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
 94  Call Trace:
 95    <IRQ>
 96    dump_stack+0x5c/0x7d
 97    should_fail+0x148/0x170
 98    nvme_should_fail+0x30/0x60 [nvme_core]
 99    nvme_loop_queue_response+0x84/0x110 [nvme_loop]
100    nvmet_req_complete+0x11/0x40 [nvmet]
101    nvmet_bio_done+0x28/0x40 [nvmet]
102    blk_update_request+0xb0/0x310
103    blk_mq_end_request+0x18/0x60
104    flush_smp_call_function_queue+0x3d/0xf0
105    smp_call_function_single_interrupt+0x2c/0xc0
106    call_function_single_interrupt+0xa2/0xb0
107    </IRQ>
108  RIP: 0010:native_safe_halt+0x2/0x10
109  RSP: 0018:ffffc9000068bec0 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff04
110  RAX: ffffffff817a10c0 RBX: ffff88011a3c9680 RCX: 0000000000000000
111  RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
112  RBP: 0000000000000001 R08: 000000008e38c131 R09: 0000000000000000
113  R10: 0000000000000000 R11: 0000000000000000 R12: ffff88011a3c9680
114  R13: ffff88011a3c9680 R14: 0000000000000000 R15: 0000000000000000
115    ? __sched_text_end+0x4/0x4
116    default_idle+0x18/0xf0
117    do_idle+0x150/0x1d0
118    cpu_startup_entry+0x6f/0x80
119    start_secondary+0x187/0x1e0
120    secondary_startup_64+0xa5/0xb0
121
122Example 3: Inject an error into the 10th admin command
123------------------------------------------------------
124
125::
126
127  echo 100 > /sys/kernel/debug/nvme0/fault_inject/probability
128  echo 10 > /sys/kernel/debug/nvme0/fault_inject/space
129  echo 1 > /sys/kernel/debug/nvme0/fault_inject/times
130  nvme reset /dev/nvme0
131
132Expected Result::
133
134  After NVMe controller reset, the reinitialization may or may not succeed.
135  It depends on which admin command is actually forced to fail.
136
137Message from dmesg::
138
139  nvme nvme0: resetting controller
140  FAULT_INJECTION: forcing a failure.
141  name fault_inject, interval 1, probability 100, space 1, times 1
142  CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.2.0-rc2+ #2
143  Hardware name: MSI MS-7A45/B150M MORTAR ARCTIC (MS-7A45), BIOS 1.50 04/25/2017
144  Call Trace:
145   <IRQ>
146   dump_stack+0x63/0x85
147   should_fail+0x14a/0x170
148   nvme_should_fail+0x38/0x80 [nvme_core]
149   nvme_irq+0x129/0x280 [nvme]
150   ? blk_mq_end_request+0xb3/0x120
151   __handle_irq_event_percpu+0x84/0x1a0
152   handle_irq_event_percpu+0x32/0x80
153   handle_irq_event+0x3b/0x60
154   handle_edge_irq+0x7f/0x1a0
155   handle_irq+0x20/0x30
156   do_IRQ+0x4e/0xe0
157   common_interrupt+0xf/0xf
158   </IRQ>
159  RIP: 0010:cpuidle_enter_state+0xc5/0x460
160  Code: ff e8 8f 5f 86 ff 80 7d c7 00 74 17 9c 58 0f 1f 44 00 00 f6 c4 02 0f 85 69 03 00 00 31 ff e8 62 aa 8c ff fb 66 0f 1f 44 00 00 <45> 85 ed 0f 88 37 03 00 00 4c 8b 45 d0 4c 2b 45 b8 48 ba cf f7 53
161  RSP: 0018:ffffffff88c03dd0 EFLAGS: 00000246 ORIG_RAX: ffffffffffffffdc
162  RAX: ffff9dac25a2ac80 RBX: ffffffff88d53760 RCX: 000000000000001f
163  RDX: 0000000000000000 RSI: 000000002d958403 RDI: 0000000000000000
164  RBP: ffffffff88c03e18 R08: fffffff75e35ffb7 R09: 00000a49a56c0b48
165  R10: ffffffff88c03da0 R11: 0000000000001b0c R12: ffff9dac25a34d00
166  R13: 0000000000000006 R14: 0000000000000006 R15: ffffffff88d53760
167   cpuidle_enter+0x2e/0x40
168   call_cpuidle+0x23/0x40
169   do_idle+0x201/0x280
170   cpu_startup_entry+0x1d/0x20
171   rest_init+0xaa/0xb0
172   arch_call_rest_init+0xe/0x1b
173   start_kernel+0x51c/0x53b
174   x86_64_start_reservations+0x24/0x26
175   x86_64_start_kernel+0x74/0x77
176   secondary_startup_64+0xa4/0xb0
177  nvme nvme0: Could not set queue count (16385)
178  nvme nvme0: IO queues not created