summaryrefslogtreecommitdiffstats
path: root/Documentation/fault-injection/fault-injection.txt
diff options
context:
space:
mode:
Diffstat (limited to 'Documentation/fault-injection/fault-injection.txt')
-rw-r--r--Documentation/fault-injection/fault-injection.txt225
1 files changed, 225 insertions, 0 deletions
diff --git a/Documentation/fault-injection/fault-injection.txt b/Documentation/fault-injection/fault-injection.txt
new file mode 100644
index 00000000000..b7ca560b934
--- /dev/null
+++ b/Documentation/fault-injection/fault-injection.txt
@@ -0,0 +1,225 @@
+Fault injection capabilities infrastructure
+===========================================
+
+See also drivers/md/faulty.c and "every_nth" module option for scsi_debug.
+
+
+Available fault injection capabilities
+--------------------------------------
+
+o failslab
+
+ injects slab allocation failures. (kmalloc(), kmem_cache_alloc(), ...)
+
+o fail_page_alloc
+
+ injects page allocation failures. (alloc_pages(), get_free_pages(), ...)
+
+o fail_make_request
+
+ injects disk IO errors on devices permitted by setting
+ /sys/block/<device>/make-it-fail or
+ /sys/block/<device>/<partition>/make-it-fail. (generic_make_request())
+
+Configure fault-injection capabilities behavior
+-----------------------------------------------
+
+o debugfs entries
+
+fault-inject-debugfs kernel module provides some debugfs entries for runtime
+configuration of fault-injection capabilities.
+
+- /debug/fail*/probability:
+
+ likelihood of failure injection, in percent.
+ Format: <percent>
+
+ Note that one-failure-per-hundred is a very high error rate
+ for some testcases. Consider setting probability=100 and configure
+ /debug/fail*/interval for such testcases.
+
+- /debug/fail*/interval:
+
+ specifies the interval between failures, for calls to
+ should_fail() that pass all the other tests.
+
+ Note that if you enable this, by setting interval>1, you will
+ probably want to set probability=100.
+
+- /debug/fail*/times:
+
+ specifies how many times failures may happen at most.
+ A value of -1 means "no limit".
+
+- /debug/fail*/space:
+
+ specifies an initial resource "budget", decremented by "size"
+ on each call to should_fail(,size). Failure injection is
+ suppressed until "space" reaches zero.
+
+- /debug/fail*/verbose
+
+ Format: { 0 | 1 | 2 }
+ specifies the verbosity of the messages when failure is
+ injected. '0' means no messages; '1' will print only a single
+ log line per failure; '2' will print a call trace too -- useful
+ to debug the problems revealed by fault injection.
+
+- /debug/fail*/task-filter:
+
+ Format: { 'Y' | 'N' }
+ A value of 'N' disables filtering by process (default).
+ Any positive value limits failures to only processes indicated by
+ /proc/<pid>/make-it-fail==1.
+
+- /debug/fail*/require-start:
+- /debug/fail*/require-end:
+- /debug/fail*/reject-start:
+- /debug/fail*/reject-end:
+
+ specifies the range of virtual addresses tested during
+ stacktrace walking. Failure is injected only if some caller
+ in the walked stacktrace lies within the required range, and
+ none lies within the rejected range.
+ Default required range is [0,ULONG_MAX) (whole of virtual address space).
+ Default rejected range is [0,0).
+
+- /debug/fail*/stacktrace-depth:
+
+ specifies the maximum stacktrace depth walked during search
+ for a caller within [require-start,require-end) OR
+ [reject-start,reject-end).
+
+- /debug/fail_page_alloc/ignore-gfp-highmem:
+
+ Format: { 'Y' | 'N' }
+ default is 'N', setting it to 'Y' won't inject failures into
+ highmem/user allocations.
+
+- /debug/failslab/ignore-gfp-wait:
+- /debug/fail_page_alloc/ignore-gfp-wait:
+
+ Format: { 'Y' | 'N' }
+ default is 'N', setting it to 'Y' will inject failures
+ only into non-sleep allocations (GFP_ATOMIC allocations).
+
+o Boot option
+
+In order to inject faults while debugfs is not available (early boot time),
+use the boot option:
+
+ failslab=
+ fail_page_alloc=
+ fail_make_request=<interval>,<probability>,<space>,<times>
+
+How to add new fault injection capability
+-----------------------------------------
+
+o #include <linux/fault-inject.h>
+
+o define the fault attributes
+
+ DECLARE_FAULT_INJECTION(name);
+
+ Please see the definition of struct fault_attr in fault-inject.h
+ for details.
+
+o provide a way to configure fault attributes
+
+- boot option
+
+ If you need to enable the fault injection capability from boot time, you can
+ provide boot option to configure it. There is a helper function for it:
+
+ setup_fault_attr(attr, str);
+
+- debugfs entries
+
+ failslab, fail_page_alloc, and fail_make_request use this way.
+ Helper functions:
+
+ init_fault_attr_entries(entries, attr, name);
+ void cleanup_fault_attr_entries(entries);
+
+- module parameters
+
+ If the scope of the fault injection capability is limited to a
+ single kernel module, it is better to provide module parameters to
+ configure the fault attributes.
+
+o add a hook to insert failures
+
+ Upon should_fail() returning true, client code should inject a failure.
+
+ should_fail(attr, size);
+
+Application Examples
+--------------------
+
+o inject slab allocation failures into module init/cleanup code
+
+------------------------------------------------------------------------------
+#!/bin/bash
+
+FAILCMD=Documentation/fault-injection/failcmd.sh
+BLACKLIST="root_plug evbug"
+
+FAILNAME=failslab
+echo Y > /debug/$FAILNAME/task-filter
+echo 10 > /debug/$FAILNAME/probability
+echo 100 > /debug/$FAILNAME/interval
+echo -1 > /debug/$FAILNAME/times
+echo 2 > /debug/$FAILNAME/verbose
+echo 1 > /debug/$FAILNAME/ignore-gfp-wait
+
+blacklist()
+{
+ echo $BLACKLIST | grep $1 > /dev/null 2>&1
+}
+
+oops()
+{
+ dmesg | grep BUG > /dev/null 2>&1
+}
+
+find /lib/modules/`uname -r` -name '*.ko' -exec basename {} .ko \; |
+ while read i
+ do
+ oops && exit 1
+
+ if ! blacklist $i
+ then
+ echo inserting $i...
+ bash $FAILCMD modprobe $i
+ fi
+ done
+
+lsmod | awk '{ if ($3 == 0) { print $1 } }' |
+ while read i
+ do
+ oops && exit 1
+
+ if ! blacklist $i
+ then
+ echo removing $i...
+ bash $FAILCMD modprobe -r $i
+ fi
+ done
+
+------------------------------------------------------------------------------
+
+o inject slab allocation failures only for a specific module
+
+------------------------------------------------------------------------------
+#!/bin/bash
+
+FAILMOD=Documentation/fault-injection/failmodule.sh
+
+echo injecting errors into the module $1...
+
+modprobe $1
+bash $FAILMOD failslab $1 10
+echo 25 > /debug/failslab/probability
+
+------------------------------------------------------------------------------
+