OpenCloudOS-Kernel/lib/fault-inject.c

238 lines
5.9 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/random.h>
#include <linux/sched.h>
#include <linux/stat.h>
#include <linux/types.h>
#include <linux/fs.h>
#include <linux/export.h>
#include <linux/interrupt.h>
#include <linux/stacktrace.h>
#include <linux/fault-inject.h>
/*
* setup_fault_attr() is a helper function for various __setup handlers, so it
* returns 0 on error, because that is what __setup handlers do.
*/
int setup_fault_attr(struct fault_attr *attr, char *str)
{
unsigned long probability;
unsigned long interval;
int times;
int space;
/* "<interval>,<probability>,<space>,<times>" */
if (sscanf(str, "%lu,%lu,%d,%d",
&interval, &probability, &space, &times) < 4) {
printk(KERN_WARNING
"FAULT_INJECTION: failed to parse arguments\n");
return 0;
}
attr->probability = probability;
attr->interval = interval;
atomic_set(&attr->times, times);
atomic_set(&attr->space, space);
return 1;
}
EXPORT_SYMBOL_GPL(setup_fault_attr);
static void fail_dump(struct fault_attr *attr)
{
if (attr->no_warn)
return;
if (attr->verbose > 0 && __ratelimit(&attr->ratelimit_state)) {
printk(KERN_NOTICE "FAULT_INJECTION: forcing a failure.\n"
"name %pd, interval %lu, probability %lu, "
"space %d, times %d\n", attr->dname,
attr->interval, attr->probability,
atomic_read(&attr->space),
atomic_read(&attr->times));
if (attr->verbose > 1)
dump_stack();
}
}
#define atomic_dec_not_zero(v) atomic_add_unless((v), -1, 0)
static bool fail_task(struct fault_attr *attr, struct task_struct *task)
{
return in_task() && task->make_it_fail;
}
#define MAX_STACK_TRACE_DEPTH 32
#ifdef CONFIG_FAULT_INJECTION_STACKTRACE_FILTER
static bool fail_stacktrace(struct fault_attr *attr)
{
int depth = attr->stacktrace_depth;
unsigned long entries[MAX_STACK_TRACE_DEPTH];
fault-inject: Simplify stacktrace retrieval Replace the indirection through struct stack_trace with an invocation of the storage array based interface. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Akinobu Mita <akinobu.mita@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Alexander Potapenko <glider@google.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: linux-mm@kvack.org Cc: David Rientjes <rientjes@google.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: kasan-dev@googlegroups.com Cc: Mike Rapoport <rppt@linux.vnet.ibm.com> Cc: Christoph Hellwig <hch@lst.de> Cc: iommu@lists.linux-foundation.org Cc: Robin Murphy <robin.murphy@arm.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Johannes Thumshirn <jthumshirn@suse.de> Cc: David Sterba <dsterba@suse.com> Cc: Chris Mason <clm@fb.com> Cc: Josef Bacik <josef@toxicpanda.com> Cc: linux-btrfs@vger.kernel.org Cc: dm-devel@redhat.com Cc: Mike Snitzer <snitzer@redhat.com> Cc: Alasdair Kergon <agk@redhat.com> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: intel-gfx@lists.freedesktop.org Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com> Cc: dri-devel@lists.freedesktop.org Cc: David Airlie <airlied@linux.ie> Cc: Jani Nikula <jani.nikula@linux.intel.com> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: Tom Zanussi <tom.zanussi@linux.intel.com> Cc: Miroslav Benes <mbenes@suse.cz> Cc: linux-arch@vger.kernel.org Link: https://lkml.kernel.org/r/20190425094802.158306076@linutronix.de
2019-04-25 17:45:04 +08:00
int n, nr_entries;
bool found = (attr->require_start == 0 && attr->require_end == ULONG_MAX);
if (depth == 0)
return found;
fault-inject: Simplify stacktrace retrieval Replace the indirection through struct stack_trace with an invocation of the storage array based interface. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Akinobu Mita <akinobu.mita@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Alexander Potapenko <glider@google.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: linux-mm@kvack.org Cc: David Rientjes <rientjes@google.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: kasan-dev@googlegroups.com Cc: Mike Rapoport <rppt@linux.vnet.ibm.com> Cc: Christoph Hellwig <hch@lst.de> Cc: iommu@lists.linux-foundation.org Cc: Robin Murphy <robin.murphy@arm.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Johannes Thumshirn <jthumshirn@suse.de> Cc: David Sterba <dsterba@suse.com> Cc: Chris Mason <clm@fb.com> Cc: Josef Bacik <josef@toxicpanda.com> Cc: linux-btrfs@vger.kernel.org Cc: dm-devel@redhat.com Cc: Mike Snitzer <snitzer@redhat.com> Cc: Alasdair Kergon <agk@redhat.com> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: intel-gfx@lists.freedesktop.org Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com> Cc: dri-devel@lists.freedesktop.org Cc: David Airlie <airlied@linux.ie> Cc: Jani Nikula <jani.nikula@linux.intel.com> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: Tom Zanussi <tom.zanussi@linux.intel.com> Cc: Miroslav Benes <mbenes@suse.cz> Cc: linux-arch@vger.kernel.org Link: https://lkml.kernel.org/r/20190425094802.158306076@linutronix.de
2019-04-25 17:45:04 +08:00
nr_entries = stack_trace_save(entries, depth, 1);
for (n = 0; n < nr_entries; n++) {
if (attr->reject_start <= entries[n] &&
entries[n] < attr->reject_end)
return false;
if (attr->require_start <= entries[n] &&
entries[n] < attr->require_end)
found = true;
}
return found;
}
#else
static inline bool fail_stacktrace(struct fault_attr *attr)
{
return true;
}
#endif /* CONFIG_FAULT_INJECTION_STACKTRACE_FILTER */
/*
* This code is stolen from failmalloc-1.0
* http://www.nongnu.org/failmalloc/
*/
bool should_fail(struct fault_attr *attr, ssize_t size)
{
if (in_task()) {
unsigned int fail_nth = READ_ONCE(current->fail_nth);
if (fail_nth) {
fail_nth--;
WRITE_ONCE(current->fail_nth, fail_nth);
if (!fail_nth)
goto fail;
return false;
}
fault-inject: support systematic fault injection Add /proc/self/task/<current-tid>/fail-nth file that allows failing 0-th, 1-st, 2-nd and so on calls systematically. Excerpt from the added documentation: "Write to this file of integer N makes N-th call in the current task fail (N is 0-based). Read from this file returns a single char 'Y' or 'N' that says if the fault setup with a previous write to this file was injected or not, and disables the fault if it wasn't yet injected. Note that this file enables all types of faults (slab, futex, etc). This setting takes precedence over all other generic settings like probability, interval, times, etc. But per-capability settings (e.g. fail_futex/ignore-private) take precedence over it. This feature is intended for systematic testing of faults in a single system call. See an example below" Why add a new setting: 1. Existing settings are global rather than per-task. So parallel testing is not possible. 2. attr->interval is close but it depends on attr->count which is non reset to 0, so interval does not work as expected. 3. Trying to model this with existing settings requires manipulations of all of probability, interval, times, space, task-filter and unexposed count and per-task make-it-fail files. 4. Existing settings are per-failure-type, and the set of failure types is potentially expanding. 5. make-it-fail can't be changed by unprivileged user and aggressive stress testing better be done from an unprivileged user. Similarly, this would require opening the debugfs files to the unprivileged user, as he would need to reopen at least times file (not possible to pre-open before dropping privs). The proposed interface solves all of the above (see the example). We want to integrate this into syzkaller fuzzer. A prototype has found 10 bugs in kernel in first day of usage: https://groups.google.com/forum/#!searchin/syzkaller/%22FAULT_INJECTION%22%7Csort:relevance I've made the current interface work with all types of our sandboxes. For setuid the secret sauce was prctl(PR_SET_DUMPABLE, 1, 0, 0, 0) to make /proc entries non-root owned. So I am fine with the current version of the code. [akpm@linux-foundation.org: fix build] Link: http://lkml.kernel.org/r/20170328130128.101773-1-dvyukov@google.com Signed-off-by: Dmitry Vyukov <dvyukov@google.com> Cc: Akinobu Mita <akinobu.mita@gmail.com> Cc: Michal Hocko <mhocko@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-13 05:34:35 +08:00
}
/* No need to check any other properties if the probability is 0 */
if (attr->probability == 0)
return false;
if (attr->task_filter && !fail_task(attr, current))
return false;
if (atomic_read(&attr->times) == 0)
return false;
if (atomic_read(&attr->space) > size) {
atomic_sub(size, &attr->space);
return false;
}
if (attr->interval > 1) {
attr->count++;
if (attr->count % attr->interval)
return false;
}
treewide: use prandom_u32_max() when possible, part 1 Rather than incurring a division or requesting too many random bytes for the given range, use the prandom_u32_max() function, which only takes the minimum required bytes from the RNG and avoids divisions. This was done mechanically with this coccinelle script: @basic@ expression E; type T; identifier get_random_u32 =~ "get_random_int|prandom_u32|get_random_u32"; typedef u64; @@ ( - ((T)get_random_u32() % (E)) + prandom_u32_max(E) | - ((T)get_random_u32() & ((E) - 1)) + prandom_u32_max(E * XXX_MAKE_SURE_E_IS_POW2) | - ((u64)(E) * get_random_u32() >> 32) + prandom_u32_max(E) | - ((T)get_random_u32() & ~PAGE_MASK) + prandom_u32_max(PAGE_SIZE) ) @multi_line@ identifier get_random_u32 =~ "get_random_int|prandom_u32|get_random_u32"; identifier RAND; expression E; @@ - RAND = get_random_u32(); ... when != RAND - RAND %= (E); + RAND = prandom_u32_max(E); // Find a potential literal @literal_mask@ expression LITERAL; type T; identifier get_random_u32 =~ "get_random_int|prandom_u32|get_random_u32"; position p; @@ ((T)get_random_u32()@p & (LITERAL)) // Add one to the literal. @script:python add_one@ literal << literal_mask.LITERAL; RESULT; @@ value = None if literal.startswith('0x'): value = int(literal, 16) elif literal[0] in '123456789': value = int(literal, 10) if value is None: print("I don't know how to handle %s" % (literal)) cocci.include_match(False) elif value == 2**32 - 1 or value == 2**31 - 1 or value == 2**24 - 1 or value == 2**16 - 1 or value == 2**8 - 1: print("Skipping 0x%x for cleanup elsewhere" % (value)) cocci.include_match(False) elif value & (value + 1) != 0: print("Skipping 0x%x because it's not a power of two minus one" % (value)) cocci.include_match(False) elif literal.startswith('0x'): coccinelle.RESULT = cocci.make_expr("0x%x" % (value + 1)) else: coccinelle.RESULT = cocci.make_expr("%d" % (value + 1)) // Replace the literal mask with the calculated result. @plus_one@ expression literal_mask.LITERAL; position literal_mask.p; expression add_one.RESULT; identifier FUNC; @@ - (FUNC()@p & (LITERAL)) + prandom_u32_max(RESULT) @collapse_ret@ type T; identifier VAR; expression E; @@ { - T VAR; - VAR = (E); - return VAR; + return E; } @drop_var@ type T; identifier VAR; @@ { - T VAR; ... when != VAR } Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Kees Cook <keescook@chromium.org> Reviewed-by: Yury Norov <yury.norov@gmail.com> Reviewed-by: KP Singh <kpsingh@kernel.org> Reviewed-by: Jan Kara <jack@suse.cz> # for ext4 and sbitmap Reviewed-by: Christoph Böhmwalder <christoph.boehmwalder@linbit.com> # for drbd Acked-by: Jakub Kicinski <kuba@kernel.org> Acked-by: Heiko Carstens <hca@linux.ibm.com> # for s390 Acked-by: Ulf Hansson <ulf.hansson@linaro.org> # for mmc Acked-by: Darrick J. Wong <djwong@kernel.org> # for xfs Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2022-10-05 22:43:38 +08:00
if (attr->probability <= prandom_u32_max(100))
return false;
if (!fail_stacktrace(attr))
return false;
fault-inject: support systematic fault injection Add /proc/self/task/<current-tid>/fail-nth file that allows failing 0-th, 1-st, 2-nd and so on calls systematically. Excerpt from the added documentation: "Write to this file of integer N makes N-th call in the current task fail (N is 0-based). Read from this file returns a single char 'Y' or 'N' that says if the fault setup with a previous write to this file was injected or not, and disables the fault if it wasn't yet injected. Note that this file enables all types of faults (slab, futex, etc). This setting takes precedence over all other generic settings like probability, interval, times, etc. But per-capability settings (e.g. fail_futex/ignore-private) take precedence over it. This feature is intended for systematic testing of faults in a single system call. See an example below" Why add a new setting: 1. Existing settings are global rather than per-task. So parallel testing is not possible. 2. attr->interval is close but it depends on attr->count which is non reset to 0, so interval does not work as expected. 3. Trying to model this with existing settings requires manipulations of all of probability, interval, times, space, task-filter and unexposed count and per-task make-it-fail files. 4. Existing settings are per-failure-type, and the set of failure types is potentially expanding. 5. make-it-fail can't be changed by unprivileged user and aggressive stress testing better be done from an unprivileged user. Similarly, this would require opening the debugfs files to the unprivileged user, as he would need to reopen at least times file (not possible to pre-open before dropping privs). The proposed interface solves all of the above (see the example). We want to integrate this into syzkaller fuzzer. A prototype has found 10 bugs in kernel in first day of usage: https://groups.google.com/forum/#!searchin/syzkaller/%22FAULT_INJECTION%22%7Csort:relevance I've made the current interface work with all types of our sandboxes. For setuid the secret sauce was prctl(PR_SET_DUMPABLE, 1, 0, 0, 0) to make /proc entries non-root owned. So I am fine with the current version of the code. [akpm@linux-foundation.org: fix build] Link: http://lkml.kernel.org/r/20170328130128.101773-1-dvyukov@google.com Signed-off-by: Dmitry Vyukov <dvyukov@google.com> Cc: Akinobu Mita <akinobu.mita@gmail.com> Cc: Michal Hocko <mhocko@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-13 05:34:35 +08:00
fail:
fail_dump(attr);
if (atomic_read(&attr->times) != -1)
atomic_dec_not_zero(&attr->times);
return true;
}
EXPORT_SYMBOL_GPL(should_fail);
#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
static int debugfs_ul_set(void *data, u64 val)
{
*(unsigned long *)data = val;
return 0;
}
static int debugfs_ul_get(void *data, u64 *val)
{
*val = *(unsigned long *)data;
return 0;
}
DEFINE_SIMPLE_ATTRIBUTE(fops_ul, debugfs_ul_get, debugfs_ul_set, "%llu\n");
static void debugfs_create_ul(const char *name, umode_t mode,
struct dentry *parent, unsigned long *value)
{
debugfs_create_file(name, mode, parent, value, &fops_ul);
}
#ifdef CONFIG_FAULT_INJECTION_STACKTRACE_FILTER
static int debugfs_stacktrace_depth_set(void *data, u64 val)
{
*(unsigned long *)data =
min_t(unsigned long, val, MAX_STACK_TRACE_DEPTH);
return 0;
}
DEFINE_SIMPLE_ATTRIBUTE(fops_stacktrace_depth, debugfs_ul_get,
debugfs_stacktrace_depth_set, "%llu\n");
static void debugfs_create_stacktrace_depth(const char *name, umode_t mode,
struct dentry *parent,
unsigned long *value)
{
debugfs_create_file(name, mode, parent, value, &fops_stacktrace_depth);
}
#endif /* CONFIG_FAULT_INJECTION_STACKTRACE_FILTER */
struct dentry *fault_create_debugfs_attr(const char *name,
struct dentry *parent, struct fault_attr *attr)
{
umode_t mode = S_IFREG | S_IRUSR | S_IWUSR;
struct dentry *dir;
dir = debugfs_create_dir(name, parent);
if (IS_ERR(dir))
return dir;
debugfs_create_ul("probability", mode, dir, &attr->probability);
debugfs_create_ul("interval", mode, dir, &attr->interval);
debugfs_create_atomic_t("times", mode, dir, &attr->times);
debugfs_create_atomic_t("space", mode, dir, &attr->space);
debugfs_create_ul("verbose", mode, dir, &attr->verbose);
debugfs_create_u32("verbose_ratelimit_interval_ms", mode, dir,
&attr->ratelimit_state.interval);
debugfs_create_u32("verbose_ratelimit_burst", mode, dir,
&attr->ratelimit_state.burst);
debugfs_create_bool("task-filter", mode, dir, &attr->task_filter);
#ifdef CONFIG_FAULT_INJECTION_STACKTRACE_FILTER
debugfs_create_stacktrace_depth("stacktrace-depth", mode, dir,
&attr->stacktrace_depth);
debugfs_create_ul("require-start", mode, dir, &attr->require_start);
debugfs_create_ul("require-end", mode, dir, &attr->require_end);
debugfs_create_ul("reject-start", mode, dir, &attr->reject_start);
debugfs_create_ul("reject-end", mode, dir, &attr->reject_end);
#endif /* CONFIG_FAULT_INJECTION_STACKTRACE_FILTER */
attr->dname = dget(dir);
return dir;
}
EXPORT_SYMBOL_GPL(fault_create_debugfs_attr);
#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */