error-injection: Support fault injection framework
Support in-kernel fault-injection framework via debugfs. This allows you to inject a conditional error to specified function using debugfs interfaces. Here is the result of test script described in Documentation/fault-injection/fault-injection.txt =========== # ./test_fail_function.sh 1+0 records in 1+0 records out 1048576 bytes (1.0 MB, 1.0 MiB) copied, 0.0227404 s, 46.1 MB/s btrfs-progs v4.4 See http://btrfs.wiki.kernel.org for more information. Label: (null) UUID: bfa96010-12e9-4360-aed0-42eec7af5798 Node size: 16384 Sector size: 4096 Filesystem size: 1001.00MiB Block group profiles: Data: single 8.00MiB Metadata: DUP 58.00MiB System: DUP 12.00MiB SSD detected: no Incompat features: extref, skinny-metadata Number of devices: 1 Devices: ID SIZE PATH 1 1001.00MiB /dev/loop2 mount: mount /dev/loop2 on /opt/tmpmnt failed: Cannot allocate memory SUCCESS! =========== Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org> Reviewed-by: Josef Bacik <jbacik@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
This commit is contained in:
Masami Hiramatsu
Alexei Starovoitov
parent
663faf9f7b
commit
4b1a29a7f5
|
|
@ -30,6 +30,12 @@ o fail_mmc_request
|
|||
injects MMC data errors on devices permitted by setting
|
||||
debugfs entries under /sys/kernel/debug/mmc0/fail_mmc_request
|
||||
|
||||
o fail_function
|
||||
|
||||
injects error return on specific functions, which are marked by
|
||||
ALLOW_ERROR_INJECTION() macro, by setting debugfs entries
|
||||
under /sys/kernel/debug/fail_function. No boot option supported.
|
||||
|
||||
Configure fault-injection capabilities behavior
|
||||
-----------------------------------------------
|
||||
|
||||
|
|
@ -123,6 +129,29 @@ configuration of fault-injection capabilities.
|
|||
default is 'N', setting it to 'Y' will disable failure injections
|
||||
when dealing with private (address space) futexes.
|
||||
|
||||
- /sys/kernel/debug/fail_function/inject:
|
||||
|
||||
Format: { 'function-name' | '!function-name' | '' }
|
||||
specifies the target function of error injection by name.
|
||||
If the function name leads '!' prefix, given function is
|
||||
removed from injection list. If nothing specified ('')
|
||||
injection list is cleared.
|
||||
|
||||
- /sys/kernel/debug/fail_function/injectable:
|
||||
|
||||
(read only) shows error injectable functions and what type of
|
||||
error values can be specified. The error type will be one of
|
||||
below;
|
||||
- NULL: retval must be 0.
|
||||
- ERRNO: retval must be -1 to -MAX_ERRNO (-4096).
|
||||
- ERR_NULL: retval must be 0 or -1 to -MAX_ERRNO (-4096).
|
||||
|
||||
- /sys/kernel/debug/fail_function/<functiuon-name>/retval:
|
||||
|
||||
specifies the "error" return value to inject to the given
|
||||
function for given function. This will be created when
|
||||
user specifies new injection entry.
|
||||
|
||||
o Boot option
|
||||
|
||||
In order to inject faults while debugfs is not available (early boot time),
|
||||
|
|
@ -268,6 +297,45 @@ trap "echo 0 > /sys/kernel/debug/$FAILTYPE/probability" SIGINT SIGTERM EXIT
|
|||
echo "Injecting errors into the module $module... (interrupt to stop)"
|
||||
sleep 1000000
|
||||
|
||||
------------------------------------------------------------------------------
|
||||
|
||||
o Inject open_ctree error while btrfs mount
|
||||
|
||||
#!/bin/bash
|
||||
|
||||
rm -f testfile.img
|
||||
dd if=/dev/zero of=testfile.img bs=1M seek=1000 count=1
|
||||
DEVICE=$(losetup --show -f testfile.img)
|
||||
mkfs.btrfs -f $DEVICE
|
||||
mkdir -p tmpmnt
|
||||
|
||||
FAILTYPE=fail_function
|
||||
FAILFUNC=open_ctree
|
||||
echo $FAILFUNC > /sys/kernel/debug/$FAILTYPE/inject
|
||||
echo -12 > /sys/kernel/debug/$FAILTYPE/$FAILFUNC/retval
|
||||
echo N > /sys/kernel/debug/$FAILTYPE/task-filter
|
||||
echo 100 > /sys/kernel/debug/$FAILTYPE/probability
|
||||
echo 0 > /sys/kernel/debug/$FAILTYPE/interval
|
||||
echo -1 > /sys/kernel/debug/$FAILTYPE/times
|
||||
echo 0 > /sys/kernel/debug/$FAILTYPE/space
|
||||
echo 1 > /sys/kernel/debug/$FAILTYPE/verbose
|
||||
|
||||
mount -t btrfs $DEVICE tmpmnt
|
||||
if [ $? -ne 0 ]
|
||||
then
|
||||
echo "SUCCESS!"
|
||||
else
|
||||
echo "FAILED!"
|
||||
umount tmpmnt
|
||||
fi
|
||||
|
||||
echo > /sys/kernel/debug/$FAILTYPE/inject
|
||||
|
||||
rmdir tmpmnt
|
||||
losetup -d $DEVICE
|
||||
rm testfile.img
|
||||
|
||||
|
||||
Tool to run command with failslab or fail_page_alloc
|
||||
----------------------------------------------------
|
||||
In order to make it easier to accomplish the tasks mentioned above, we can use
|
||||
|
|
|
|||
|
|
@ -81,6 +81,7 @@ obj-$(CONFIG_AUDIT_TREE) += audit_tree.o
|
|||
obj-$(CONFIG_GCOV_KERNEL) += gcov/
|
||||
obj-$(CONFIG_KCOV) += kcov.o
|
||||
obj-$(CONFIG_KPROBES) += kprobes.o
|
||||
obj-$(CONFIG_FAIL_FUNCTION) += fail_function.o
|
||||
obj-$(CONFIG_KGDB) += debug/
|
||||
obj-$(CONFIG_DETECT_HUNG_TASK) += hung_task.o
|
||||
obj-$(CONFIG_LOCKUP_DETECTOR) += watchdog.o
|
||||
|
|
|
|||
|
|
@ -0,0 +1,349 @@
|
|||
// SPDX-License-Identifier: GPL-2.0
|
||||
/*
|
||||
* fail_function.c: Function-based error injection
|
||||
*/
|
||||
#include <linux/error-injection.h>
|
||||
#include <linux/debugfs.h>
|
||||
#include <linux/fault-inject.h>
|
||||
#include <linux/kallsyms.h>
|
||||
#include <linux/kprobes.h>
|
||||
#include <linux/module.h>
|
||||
#include <linux/mutex.h>
|
||||
#include <linux/slab.h>
|
||||
#include <linux/uaccess.h>
|
||||
|
||||
static int fei_kprobe_handler(struct kprobe *kp, struct pt_regs *regs);
|
||||
|
||||
struct fei_attr {
|
||||
struct list_head list;
|
||||
struct kprobe kp;
|
||||
unsigned long retval;
|
||||
};
|
||||
static DEFINE_MUTEX(fei_lock);
|
||||
static LIST_HEAD(fei_attr_list);
|
||||
static DECLARE_FAULT_ATTR(fei_fault_attr);
|
||||
static struct dentry *fei_debugfs_dir;
|
||||
|
||||
static unsigned long adjust_error_retval(unsigned long addr, unsigned long retv)
|
||||
{
|
||||
switch (get_injectable_error_type(addr)) {
|
||||
case EI_ETYPE_NULL:
|
||||
if (retv != 0)
|
||||
return 0;
|
||||
break;
|
||||
case EI_ETYPE_ERRNO:
|
||||
if (retv < (unsigned long)-MAX_ERRNO)
|
||||
return (unsigned long)-EINVAL;
|
||||
break;
|
||||
case EI_ETYPE_ERRNO_NULL:
|
||||
if (retv != 0 && retv < (unsigned long)-MAX_ERRNO)
|
||||
return (unsigned long)-EINVAL;
|
||||
break;
|
||||
}
|
||||
|
||||
return retv;
|
||||
}
|
||||
|
||||
static struct fei_attr *fei_attr_new(const char *sym, unsigned long addr)
|
||||
{
|
||||
struct fei_attr *attr;
|
||||
|
||||
attr = kzalloc(sizeof(*attr), GFP_KERNEL);
|
||||
if (attr) {
|
||||
attr->kp.symbol_name = kstrdup(sym, GFP_KERNEL);
|
||||
if (!attr->kp.symbol_name) {
|
||||
kfree(attr);
|
||||
return NULL;
|
||||
}
|
||||
attr->kp.pre_handler = fei_kprobe_handler;
|
||||
attr->retval = adjust_error_retval(addr, 0);
|
||||
INIT_LIST_HEAD(&attr->list);
|
||||
}
|
||||
return attr;
|
||||
}
|
||||
|
||||
static void fei_attr_free(struct fei_attr *attr)
|
||||
{
|
||||
if (attr) {
|
||||
kfree(attr->kp.symbol_name);
|
||||
kfree(attr);
|
||||
}
|
||||
}
|
||||
|
||||
static struct fei_attr *fei_attr_lookup(const char *sym)
|
||||
{
|
||||
struct fei_attr *attr;
|
||||
|
||||
list_for_each_entry(attr, &fei_attr_list, list) {
|
||||
if (!strcmp(attr->kp.symbol_name, sym))
|
||||
return attr;
|
||||
}
|
||||
|
||||
return NULL;
|
||||
}
|
||||
|
||||
static bool fei_attr_is_valid(struct fei_attr *_attr)
|
||||
{
|
||||
struct fei_attr *attr;
|
||||
|
||||
list_for_each_entry(attr, &fei_attr_list, list) {
|
||||
if (attr == _attr)
|
||||
return true;
|
||||
}
|
||||
|
||||
return false;
|
||||
}
|
||||
|
||||
static int fei_retval_set(void *data, u64 val)
|
||||
{
|
||||
struct fei_attr *attr = data;
|
||||
unsigned long retv = (unsigned long)val;
|
||||
int err = 0;
|
||||
|
||||
mutex_lock(&fei_lock);
|
||||
/*
|
||||
* Since this operation can be done after retval file is removed,
|
||||
* It is safer to check the attr is still valid before accessing
|
||||
* its member.
|
||||
*/
|
||||
if (!fei_attr_is_valid(attr)) {
|
||||
err = -ENOENT;
|
||||
goto out;
|
||||
}
|
||||
|
||||
if (attr->kp.addr) {
|
||||
if (adjust_error_retval((unsigned long)attr->kp.addr,
|
||||
val) != retv)
|
||||
err = -EINVAL;
|
||||
}
|
||||
if (!err)
|
||||
attr->retval = val;
|
||||
out:
|
||||
mutex_unlock(&fei_lock);
|
||||
|
||||
return err;
|
||||
}
|
||||
|
||||
static int fei_retval_get(void *data, u64 *val)
|
||||
{
|
||||
struct fei_attr *attr = data;
|
||||
int err = 0;
|
||||
|
||||
mutex_lock(&fei_lock);
|
||||
/* Here we also validate @attr to ensure it still exists. */
|
||||
if (!fei_attr_is_valid(attr))
|
||||
err = -ENOENT;
|
||||
else
|
||||
*val = attr->retval;
|
||||
mutex_unlock(&fei_lock);
|
||||
|
||||
return err;
|
||||
}
|
||||
DEFINE_DEBUGFS_ATTRIBUTE(fei_retval_ops, fei_retval_get, fei_retval_set,
|
||||
"%llx\n");
|
||||
|
||||
static int fei_debugfs_add_attr(struct fei_attr *attr)
|
||||
{
|
||||
struct dentry *dir;
|
||||
|
||||
dir = debugfs_create_dir(attr->kp.symbol_name, fei_debugfs_dir);
|
||||
if (!dir)
|
||||
return -ENOMEM;
|
||||
|
||||
if (!debugfs_create_file("retval", 0600, dir, attr, &fei_retval_ops)) {
|
||||
debugfs_remove_recursive(dir);
|
||||
return -ENOMEM;
|
||||
}
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
static void fei_debugfs_remove_attr(struct fei_attr *attr)
|
||||
{
|
||||
struct dentry *dir;
|
||||
|
||||
dir = debugfs_lookup(attr->kp.symbol_name, fei_debugfs_dir);
|
||||
if (dir)
|
||||
debugfs_remove_recursive(dir);
|
||||
}
|
||||
|
||||
static int fei_kprobe_handler(struct kprobe *kp, struct pt_regs *regs)
|
||||
{
|
||||
struct fei_attr *attr = container_of(kp, struct fei_attr, kp);
|
||||
|
||||
if (should_fail(&fei_fault_attr, 1)) {
|
||||
regs_set_return_value(regs, attr->retval);
|
||||
override_function_with_return(regs);
|
||||
/* Kprobe specific fixup */
|
||||
reset_current_kprobe();
|
||||
preempt_enable_no_resched();
|
||||
return 1;
|
||||
}
|
||||
|
||||
return 0;
|
||||
}
|
||||
NOKPROBE_SYMBOL(fei_kprobe_handler)
|
||||
|
||||
static void *fei_seq_start(struct seq_file *m, loff_t *pos)
|
||||
{
|
||||
mutex_lock(&fei_lock);
|
||||
return seq_list_start(&fei_attr_list, *pos);
|
||||
}
|
||||
|
||||
static void fei_seq_stop(struct seq_file *m, void *v)
|
||||
{
|
||||
mutex_unlock(&fei_lock);
|
||||
}
|
||||
|
||||
static void *fei_seq_next(struct seq_file *m, void *v, loff_t *pos)
|
||||
{
|
||||
return seq_list_next(v, &fei_attr_list, pos);
|
||||
}
|
||||
|
||||
static int fei_seq_show(struct seq_file *m, void *v)
|
||||
{
|
||||
struct fei_attr *attr = list_entry(v, struct fei_attr, list);
|
||||
|
||||
seq_printf(m, "%pf\n", attr->kp.addr);
|
||||
return 0;
|
||||
}
|
||||
|
||||
static const struct seq_operations fei_seq_ops = {
|
||||
.start = fei_seq_start,
|
||||
.next = fei_seq_next,
|
||||
.stop = fei_seq_stop,
|
||||
.show = fei_seq_show,
|
||||
};
|
||||
|
||||
static int fei_open(struct inode *inode, struct file *file)
|
||||
{
|
||||
return seq_open(file, &fei_seq_ops);
|
||||
}
|
||||
|
||||
static void fei_attr_remove(struct fei_attr *attr)
|
||||
{
|
||||
fei_debugfs_remove_attr(attr);
|
||||
unregister_kprobe(&attr->kp);
|
||||
list_del(&attr->list);
|
||||
fei_attr_free(attr);
|
||||
}
|
||||
|
||||
static void fei_attr_remove_all(void)
|
||||
{
|
||||
struct fei_attr *attr, *n;
|
||||
|
||||
list_for_each_entry_safe(attr, n, &fei_attr_list, list) {
|
||||
fei_attr_remove(attr);
|
||||
}
|
||||
}
|
||||
|
||||
static ssize_t fei_write(struct file *file, const char __user *buffer,
|
||||
size_t count, loff_t *ppos)
|
||||
{
|
||||
struct fei_attr *attr;
|
||||
unsigned long addr;
|
||||
char *buf, *sym;
|
||||
int ret;
|
||||
|
||||
/* cut off if it is too long */
|
||||
if (count > KSYM_NAME_LEN)
|
||||
count = KSYM_NAME_LEN;
|
||||
buf = kmalloc(sizeof(char) * (count + 1), GFP_KERNEL);
|
||||
if (!buf)
|
||||
return -ENOMEM;
|
||||
|
||||
if (copy_from_user(buf, buffer, count)) {
|
||||
ret = -EFAULT;
|
||||
goto out;
|
||||
}
|
||||
buf[count] = '\0';
|
||||
sym = strstrip(buf);
|
||||
|
||||
mutex_lock(&fei_lock);
|
||||
|
||||
/* Writing just spaces will remove all injection points */
|
||||
if (sym[0] == '\0') {
|
||||
fei_attr_remove_all();
|
||||
ret = count;
|
||||
goto out;
|
||||
}
|
||||
/* Writing !function will remove one injection point */
|
||||
if (sym[0] == '!') {
|
||||
attr = fei_attr_lookup(sym + 1);
|
||||
if (!attr) {
|
||||
ret = -ENOENT;
|
||||
goto out;
|
||||
}
|
||||
fei_attr_remove(attr);
|
||||
ret = count;
|
||||
goto out;
|
||||
}
|
||||
|
||||
addr = kallsyms_lookup_name(sym);
|
||||
if (!addr) {
|
||||
ret = -EINVAL;
|
||||
goto out;
|
||||
}
|
||||
if (!within_error_injection_list(addr)) {
|
||||
ret = -ERANGE;
|
||||
goto out;
|
||||
}
|
||||
if (fei_attr_lookup(sym)) {
|
||||
ret = -EBUSY;
|
||||
goto out;
|
||||
}
|
||||
attr = fei_attr_new(sym, addr);
|
||||
if (!attr) {
|
||||
ret = -ENOMEM;
|
||||
goto out;
|
||||
}
|
||||
|
||||
ret = register_kprobe(&attr->kp);
|
||||
if (!ret)
|
||||
ret = fei_debugfs_add_attr(attr);
|
||||
if (ret < 0)
|
||||
fei_attr_remove(attr);
|
||||
else {
|
||||
list_add_tail(&attr->list, &fei_attr_list);
|
||||
ret = count;
|
||||
}
|
||||
out:
|
||||
kfree(buf);
|
||||
mutex_unlock(&fei_lock);
|
||||
return ret;
|
||||
}
|
||||
|
||||
static const struct file_operations fei_ops = {
|
||||
.open = fei_open,
|
||||
.read = seq_read,
|
||||
.write = fei_write,
|
||||
.llseek = seq_lseek,
|
||||
.release = seq_release,
|
||||
};
|
||||
|
||||
static int __init fei_debugfs_init(void)
|
||||
{
|
||||
struct dentry *dir;
|
||||
|
||||
dir = fault_create_debugfs_attr("fail_function", NULL,
|
||||
&fei_fault_attr);
|
||||
if (IS_ERR(dir))
|
||||
return PTR_ERR(dir);
|
||||
|
||||
/* injectable attribute is just a symlink of error_inject/list */
|
||||
if (!debugfs_create_symlink("injectable", dir,
|
||||
"../error_injection/list"))
|
||||
goto error;
|
||||
|
||||
if (!debugfs_create_file("inject", 0600, dir, NULL, &fei_ops))
|
||||
goto error;
|
||||
|
||||
fei_debugfs_dir = dir;
|
||||
|
||||
return 0;
|
||||
error:
|
||||
debugfs_remove_recursive(dir);
|
||||
return -ENOMEM;
|
||||
}
|
||||
|
||||
late_initcall(fei_debugfs_init);
|
||||
|
|
@ -1551,6 +1551,16 @@ config FAIL_FUTEX
|
|||
help
|
||||
Provide fault-injection capability for futexes.
|
||||
|
||||
config FAIL_FUNCTION
|
||||
bool "Fault-injection capability for functions"
|
||||
depends on FAULT_INJECTION_DEBUG_FS && FUNCTION_ERROR_INJECTION
|
||||
help
|
||||
Provide function-based fault-injection capability.
|
||||
This will allow you to override a specific function with a return
|
||||
with given return value. As a result, function caller will see
|
||||
an error value and have to handle it. This is useful to test the
|
||||
error handling in various subsystems.
|
||||
|
||||
config FAULT_INJECTION_DEBUG_FS
|
||||
bool "Debugfs entries for fault-injection capabilities"
|
||||
depends on FAULT_INJECTION && SYSFS && DEBUG_FS
|
||||
|
|
|
|||
Loading…
Reference in New Issue