summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/audit.c5
-rw-r--r--kernel/context_tracking.c12
-rw-r--r--kernel/events/core.c21
-rw-r--r--kernel/kmod.c4
-rw-r--r--kernel/params.c6
-rw-r--r--kernel/pid.c5
-rw-r--r--kernel/power/snapshot.c5
-rw-r--r--kernel/power/user.c8
-rw-r--r--kernel/reboot.c9
-rw-r--r--kernel/sched/debug.c6
-rw-r--r--kernel/sched/fair.c23
-rw-r--r--kernel/sched/stats.h5
-rw-r--r--kernel/softirq.c15
-rw-r--r--kernel/time/ntp.c6
-rw-r--r--kernel/time/timekeeping.c2
-rw-r--r--kernel/trace/ftrace.c140
-rw-r--r--kernel/trace/trace.c7
-rw-r--r--kernel/trace/trace.h25
-rw-r--r--kernel/trace/trace_functions_graph.c56
-rw-r--r--kernel/trace/trace_stat.c41
-rw-r--r--kernel/watchdog.c60
21 files changed, 349 insertions, 112 deletions
diff --git a/kernel/audit.c b/kernel/audit.c
index 91e53d0..7b0e23a 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -1117,9 +1117,10 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask,
sleep_time = timeout_start + audit_backlog_wait_time -
jiffies;
- if ((long)sleep_time > 0)
+ if ((long)sleep_time > 0) {
wait_for_auditd(sleep_time);
- continue;
+ continue;
+ }
}
if (audit_rate_check() && printk_ratelimit())
printk(KERN_WARNING
diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c
index 247091b..859c8df 100644
--- a/kernel/context_tracking.c
+++ b/kernel/context_tracking.c
@@ -51,6 +51,15 @@ void context_tracking_user_enter(void)
unsigned long flags;
/*
+ * Repeat the user_enter() check here because some archs may be calling
+ * this from asm and if no CPU needs context tracking, they shouldn't
+ * go further. Repeat the check here until they support the static key
+ * check.
+ */
+ if (!static_key_false(&context_tracking_enabled))
+ return;
+
+ /*
* Some contexts may involve an exception occuring in an irq,
* leading to that nesting:
* rcu_irq_enter() rcu_user_exit() rcu_user_exit() rcu_irq_exit()
@@ -151,6 +160,9 @@ void context_tracking_user_exit(void)
{
unsigned long flags;
+ if (!static_key_false(&context_tracking_enabled))
+ return;
+
if (in_interrupt())
return;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index dd236b6..cb4238e 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3660,6 +3660,26 @@ static void calc_timer_values(struct perf_event *event,
*running = ctx_time - event->tstamp_running;
}
+static void perf_event_init_userpage(struct perf_event *event)
+{
+ struct perf_event_mmap_page *userpg;
+ struct ring_buffer *rb;
+
+ rcu_read_lock();
+ rb = rcu_dereference(event->rb);
+ if (!rb)
+ goto unlock;
+
+ userpg = rb->user_page;
+
+ /* Allow new userspace to detect that bit 0 is deprecated */
+ userpg->cap_bit0_is_deprecated = 1;
+ userpg->size = offsetof(struct perf_event_mmap_page, __reserved);
+
+unlock:
+ rcu_read_unlock();
+}
+
void __weak arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
{
}
@@ -4044,6 +4064,7 @@ again:
ring_buffer_attach(event, rb);
rcu_assign_pointer(event->rb, rb);
+ perf_event_init_userpage(event);
perf_event_update_userpage(event);
unlock:
diff --git a/kernel/kmod.c b/kernel/kmod.c
index fb32636..b086006 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -571,6 +571,10 @@ int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait)
DECLARE_COMPLETION_ONSTACK(done);
int retval = 0;
+ if (!sub_info->path) {
+ call_usermodehelper_freeinfo(sub_info);
+ return -EINVAL;
+ }
helper_lock();
if (!khelper_wq || usermodehelper_disabled) {
retval = -EBUSY;
diff --git a/kernel/params.c b/kernel/params.c
index 81c4e78..c00d5b5 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -254,11 +254,11 @@ int parse_args(const char *doing,
STANDARD_PARAM_DEF(byte, unsigned char, "%hhu", unsigned long, kstrtoul);
-STANDARD_PARAM_DEF(short, short, "%hi", long, kstrtoul);
+STANDARD_PARAM_DEF(short, short, "%hi", long, kstrtol);
STANDARD_PARAM_DEF(ushort, unsigned short, "%hu", unsigned long, kstrtoul);
-STANDARD_PARAM_DEF(int, int, "%i", long, kstrtoul);
+STANDARD_PARAM_DEF(int, int, "%i", long, kstrtol);
STANDARD_PARAM_DEF(uint, unsigned int, "%u", unsigned long, kstrtoul);
-STANDARD_PARAM_DEF(long, long, "%li", long, kstrtoul);
+STANDARD_PARAM_DEF(long, long, "%li", long, kstrtol);
STANDARD_PARAM_DEF(ulong, unsigned long, "%lu", unsigned long, kstrtoul);
int param_set_charp(const char *val, const struct kernel_param *kp)
diff --git a/kernel/pid.c b/kernel/pid.c
index ebe5e80..9b9a266 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -273,6 +273,11 @@ void free_pid(struct pid *pid)
*/
wake_up_process(ns->child_reaper);
break;
+ case PIDNS_HASH_ADDING:
+ /* Handle a fork failure of the first process */
+ WARN_ON(ns->child_reaper);
+ ns->nr_hashed = 0;
+ /* fall through */
case 0:
schedule_work(&ns->proc_work);
break;
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 358a146..98c3b34 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -743,7 +743,10 @@ int create_basic_memory_bitmaps(void)
struct memory_bitmap *bm1, *bm2;
int error = 0;
- BUG_ON(forbidden_pages_map || free_pages_map);
+ if (forbidden_pages_map && free_pages_map)
+ return 0;
+ else
+ BUG_ON(forbidden_pages_map || free_pages_map);
bm1 = kzalloc(sizeof(struct memory_bitmap), GFP_KERNEL);
if (!bm1)
diff --git a/kernel/power/user.c b/kernel/power/user.c
index 72e8f4f..957f061 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -39,6 +39,7 @@ static struct snapshot_data {
char frozen;
char ready;
char platform_support;
+ bool free_bitmaps;
} snapshot_state;
atomic_t snapshot_device_available = ATOMIC_INIT(1);
@@ -82,6 +83,10 @@ static int snapshot_open(struct inode *inode, struct file *filp)
data->swap = -1;
data->mode = O_WRONLY;
error = pm_notifier_call_chain(PM_RESTORE_PREPARE);
+ if (!error) {
+ error = create_basic_memory_bitmaps();
+ data->free_bitmaps = !error;
+ }
if (error)
pm_notifier_call_chain(PM_POST_RESTORE);
}
@@ -111,6 +116,8 @@ static int snapshot_release(struct inode *inode, struct file *filp)
pm_restore_gfp_mask();
free_basic_memory_bitmaps();
thaw_processes();
+ } else if (data->free_bitmaps) {
+ free_basic_memory_bitmaps();
}
pm_notifier_call_chain(data->mode == O_RDONLY ?
PM_POST_HIBERNATION : PM_POST_RESTORE);
@@ -231,6 +238,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
break;
pm_restore_gfp_mask();
free_basic_memory_bitmaps();
+ data->free_bitmaps = false;
thaw_processes();
data->frozen = 0;
break;
diff --git a/kernel/reboot.c b/kernel/reboot.c
index 269ed93..f813b34 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -32,7 +32,14 @@ EXPORT_SYMBOL(cad_pid);
#endif
enum reboot_mode reboot_mode DEFAULT_REBOOT_MODE;
-int reboot_default;
+/*
+ * This variable is used privately to keep track of whether or not
+ * reboot_type is still set to its default value (i.e., reboot= hasn't
+ * been set on the command line). This is needed so that we can
+ * suppress DMI scanning for reboot quirks. Without it, it's
+ * impossible to override a faulty reboot quirk without recompiling.
+ */
+int reboot_default = 1;
int reboot_cpu;
enum reboot_type reboot_type = BOOT_ACPI;
int reboot_force;
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index e076bdd..1965599 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -124,7 +124,7 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
SEQ_printf(m, " ");
SEQ_printf(m, "%15s %5d %9Ld.%06ld %9Ld %5d ",
- p->comm, p->pid,
+ p->comm, task_pid_nr(p),
SPLIT_NS(p->se.vruntime),
(long long)(p->nvcsw + p->nivcsw),
p->prio);
@@ -289,7 +289,7 @@ do { \
P(nr_load_updates);
P(nr_uninterruptible);
PN(next_balance);
- P(curr->pid);
+ SEQ_printf(m, " .%-30s: %ld\n", "curr->pid", (long)(task_pid_nr(rq->curr)));
PN(clock);
P(cpu_load[0]);
P(cpu_load[1]);
@@ -492,7 +492,7 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
{
unsigned long nr_switches;
- SEQ_printf(m, "%s (%d, #threads: %d)\n", p->comm, p->pid,
+ SEQ_printf(m, "%s (%d, #threads: %d)\n", p->comm, task_pid_nr(p),
get_nr_threads(p));
SEQ_printf(m,
"---------------------------------------------------------"
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 9b3fe1c..7c70201 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4242,7 +4242,7 @@ static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq)
}
if (!se) {
- cfs_rq->h_load = rq->avg.load_avg_contrib;
+ cfs_rq->h_load = cfs_rq->runnable_load_avg;
cfs_rq->last_h_load_update = now;
}
@@ -4823,8 +4823,8 @@ void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds)
(busiest->load_per_task * SCHED_POWER_SCALE) /
busiest->group_power;
- if (busiest->avg_load - local->avg_load + scaled_busy_load_per_task >=
- (scaled_busy_load_per_task * imbn)) {
+ if (busiest->avg_load + scaled_busy_load_per_task >=
+ local->avg_load + (scaled_busy_load_per_task * imbn)) {
env->imbalance = busiest->load_per_task;
return;
}
@@ -4896,7 +4896,8 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
* max load less than avg load(as we skip the groups at or below
* its cpu_power, while calculating max_load..)
*/
- if (busiest->avg_load < sds->avg_load) {
+ if (busiest->avg_load <= sds->avg_load ||
+ local->avg_load >= sds->avg_load) {
env->imbalance = 0;
return fix_small_imbalance(env, sds);
}
@@ -5928,11 +5929,15 @@ static void task_fork_fair(struct task_struct *p)
cfs_rq = task_cfs_rq(current);
curr = cfs_rq->curr;
- if (unlikely(task_cpu(p) != this_cpu)) {
- rcu_read_lock();
- __set_task_cpu(p, this_cpu);
- rcu_read_unlock();
- }
+ /*
+ * Not only the cpu but also the task_group of the parent might have
+ * been changed after parent->se.parent,cfs_rq were copied to
+ * child->se.parent,cfs_rq. So call __set_task_cpu() to make those
+ * of child point to valid ones.
+ */
+ rcu_read_lock();
+ __set_task_cpu(p, this_cpu);
+ rcu_read_unlock();
update_curr(cfs_rq);
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index 5aef494..c7edee7 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -104,8 +104,9 @@ static inline void sched_info_queued(struct task_struct *t)
}
/*
- * Called when a process ceases being the active-running process, either
- * voluntarily or involuntarily. Now we can calculate how long we ran.
+ * Called when a process ceases being the active-running process involuntarily
+ * due, typically, to expiring its time slice (this may also be called when
+ * switching to the idle task). Now we can calculate how long we ran.
* Also, if the process is still in the TASK_RUNNING state, call
* sched_info_queued() to mark that it has now again started waiting on
* the runqueue.
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 53cc09c..d7d498d 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -328,10 +328,19 @@ void irq_enter(void)
static inline void invoke_softirq(void)
{
- if (!force_irqthreads)
- __do_softirq();
- else
+ if (!force_irqthreads) {
+ /*
+ * We can safely execute softirq on the current stack if
+ * it is the irq stack, because it should be near empty
+ * at this stage. But we have no way to know if the arch
+ * calls irq_exit() on the irq stack. So call softirq
+ * in its own stack to prevent from any overrun on top
+ * of a potentially deep task stack.
+ */
+ do_softirq();
+ } else {
wakeup_softirqd();
+ }
}
static inline void tick_irq_exit(void)
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 8f5b3b9..bb22151 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -516,13 +516,13 @@ static void sync_cmos_clock(struct work_struct *work)
schedule_delayed_work(&sync_cmos_work, timespec_to_jiffies(&next));
}
-static void notify_cmos_timer(void)
+void ntp_notify_cmos_timer(void)
{
schedule_delayed_work(&sync_cmos_work, 0);
}
#else
-static inline void notify_cmos_timer(void) { }
+void ntp_notify_cmos_timer(void) { }
#endif
@@ -687,8 +687,6 @@ int __do_adjtimex(struct timex *txc, struct timespec *ts, s32 *time_tai)
if (!(time_status & STA_NANO))
txc->time.tv_usec /= NSEC_PER_USEC;
- notify_cmos_timer();
-
return result;
}
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 48b9fff..947ba25 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1703,6 +1703,8 @@ int do_adjtimex(struct timex *txc)
write_seqcount_end(&timekeeper_seq);
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
+ ntp_notify_cmos_timer();
+
return ret;
}
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 03cf44a..44e826a 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -3641,7 +3641,7 @@ __setup("ftrace_filter=", set_ftrace_filter);
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
static char ftrace_graph_buf[FTRACE_FILTER_SIZE] __initdata;
-static int ftrace_set_func(unsigned long *array, int *idx, char *buffer);
+static int ftrace_set_func(unsigned long *array, int *idx, int size, char *buffer);
static int __init set_graph_function(char *str)
{
@@ -3659,7 +3659,7 @@ static void __init set_ftrace_early_graph(char *buf)
func = strsep(&buf, ",");
/* we allow only one expression at a time */
ret = ftrace_set_func(ftrace_graph_funcs, &ftrace_graph_count,
- func);
+ FTRACE_GRAPH_MAX_FUNCS, func);
if (ret)
printk(KERN_DEBUG "ftrace: function %s not "
"traceable\n", func);
@@ -3776,15 +3776,25 @@ static const struct file_operations ftrace_notrace_fops = {
static DEFINE_MUTEX(graph_lock);
int ftrace_graph_count;
-int ftrace_graph_filter_enabled;
+int ftrace_graph_notrace_count;
unsigned long ftrace_graph_funcs[FTRACE_GRAPH_MAX_FUNCS] __read_mostly;
+unsigned long ftrace_graph_notrace_funcs[FTRACE_GRAPH_MAX_FUNCS] __read_mostly;
+
+struct ftrace_graph_data {
+ unsigned long *table;
+ size_t size;
+ int *count;
+ const struct seq_operations *seq_ops;
+};
static void *
__g_next(struct seq_file *m, loff_t *pos)
{
- if (*pos >= ftrace_graph_count)
+ struct ftrace_graph_data *fgd = m->private;
+
+ if (*pos >= *fgd->count)
return NULL;
- return &ftrace_graph_funcs[*pos];
+ return &fgd->table[*pos];
}
static void *
@@ -3796,10 +3806,12 @@ g_next(struct seq_file *m, void *v, loff_t *pos)
static void *g_start(struct seq_file *m, loff_t *pos)
{
+ struct ftrace_graph_data *fgd = m->private;
+
mutex_lock(&graph_lock);
/* Nothing, tell g_show to print all functions are enabled */
- if (!ftrace_graph_filter_enabled && !*pos)
+ if (!*fgd->count && !*pos)
return (void *)1;
return __g_next(m, pos);
@@ -3835,38 +3847,88 @@ static const struct seq_operations ftrace_graph_seq_ops = {
};
static int
-ftrace_graph_open(struct inode *inode, struct file *file)
+__ftrace_graph_open(struct inode *inode, struct file *file,
+ struct ftrace_graph_data *fgd)
{
int ret = 0;
- if (unlikely(ftrace_disabled))
- return -ENODEV;
-
mutex_lock(&graph_lock);
if ((file->f_mode & FMODE_WRITE) &&
(file->f_flags & O_TRUNC)) {
- ftrace_graph_filter_enabled = 0;
- ftrace_graph_count = 0;
- memset(ftrace_graph_funcs, 0, sizeof(ftrace_graph_funcs));
+ *fgd->count = 0;
+ memset(fgd->table, 0, fgd->size * sizeof(*fgd->table));
}
mutex_unlock(&graph_lock);
- if (file->f_mode & FMODE_READ)
- ret = seq_open(file, &ftrace_graph_seq_ops);
+ if (file->f_mode & FMODE_READ) {
+ ret = seq_open(file, fgd->seq_ops);
+ if (!ret) {
+ struct seq_file *m = file->private_data;
+ m->private = fgd;
+ }
+ } else
+ file->private_data = fgd;
return ret;
}
static int
+ftrace_graph_open(struct inode *inode, struct file *file)
+{
+ struct ftrace_graph_data *fgd;
+
+ if (unlikely(ftrace_disabled))
+ return -ENODEV;
+
+ fgd = kmalloc(sizeof(*fgd), GFP_KERNEL);
+ if (fgd == NULL)
+ return -ENOMEM;
+
+ fgd->table = ftrace_graph_funcs;
+ fgd->size = FTRACE_GRAPH_MAX_FUNCS;
+ fgd->count = &ftrace_graph_count;
+ fgd->seq_ops = &ftrace_graph_seq_ops;
+
+ return __ftrace_graph_open(inode, file, fgd);
+}
+
+static int
+ftrace_graph_notrace_open(struct inode *inode, struct file *file)
+{
+ struct ftrace_graph_data *fgd;
+
+ if (unlikely(ftrace_disabled))
+ return -ENODEV;
+
+ fgd = kmalloc(sizeof(*fgd), GFP_KERNEL);
+ if (fgd == NULL)
+ return -ENOMEM;
+
+ fgd->table = ftrace_graph_notrace_funcs;
+ fgd->size = FTRACE_GRAPH_MAX_FUNCS;
+ fgd->count = &ftrace_graph_notrace_count;
+ fgd->seq_ops = &ftrace_graph_seq_ops;
+
+ return __ftrace_graph_open(inode, file, fgd);
+}
+
+static int
ftrace_graph_release(struct inode *inode, struct file *file)
{
- if (file->f_mode & FMODE_READ)
+ if (file->f_mode & FMODE_READ) {
+ struct seq_file *m = file->private_data;
+
+ kfree(m->private);
seq_release(inode, file);
+ } else {
+ kfree(file->private_data);
+ }
+
return 0;
}
static int
-ftrace_set_func(unsigned long *array, int *idx, char *buffer)
+ftrace_set_func(unsigned long *array, int *idx, int size, char *buffer)
{
struct dyn_ftrace *rec;
struct ftrace_page *pg;
@@ -3879,7 +3941,7 @@ ftrace_set_func(unsigned long *array, int *idx, char *buffer)
/* decode regex */
type = filter_parse_regex(buffer, strlen(buffer), &search, &not);
- if (!not && *idx >= FTRACE_GRAPH_MAX_FUNCS)
+ if (!not && *idx >= size)
return -EBUSY;
search_len = strlen(search);
@@ -3907,7 +3969,7 @@ ftrace_set_func(unsigned long *array, int *idx, char *buffer)
fail = 0;
if (!exists) {
array[(*idx)++] = rec->ip;
- if (*idx >= FTRACE_GRAPH_MAX_FUNCS)
+ if (*idx >= size)
goto out;
}
} else {
@@ -3925,8 +3987,6 @@ out:
if (fail)
return -EINVAL;
- ftrace_graph_filter_enabled = !!(*idx);
-
return 0;
}
@@ -3935,36 +3995,33 @@ ftrace_graph_write(struct file *file, const char __user *ubuf,
size_t cnt, loff_t *ppos)
{
struct trace_parser parser;
- ssize_t read, ret;
+ ssize_t read, ret = 0;
+ struct ftrace_graph_data *fgd = file->private_data;
if (!cnt)
return 0;
- mutex_lock(&graph_lock);
-
- if (trace_parser_get_init(&parser, FTRACE_BUFF_MAX)) {
- ret = -ENOMEM;
- goto out_unlock;
- }
+ if (trace_parser_get_init(&parser, FTRACE_BUFF_MAX))
+ return -ENOMEM;
read = trace_get_user(&parser, ubuf, cnt, ppos);
if (read >= 0 && trace_parser_loaded((&parser))) {
parser.buffer[parser.idx] = 0;
+ mutex_lock(&graph_lock);
+
/* we allow only one expression at a time */
- ret = ftrace_set_func(ftrace_graph_funcs, &ftrace_graph_count,
- parser.buffer);
- if (ret)
- goto out_free;
+ ret = ftrace_set_func(fgd->table, fgd->count, fgd->size,
+ parser.buffer);
+
+ mutex_unlock(&graph_lock);
}
- ret = read;
+ if (!ret)
+ ret = read;
-out_free:
trace_parser_put(&parser);
-out_unlock:
- mutex_unlock(&graph_lock);
return ret;
}
@@ -3976,6 +4033,14 @@ static const struct file_operations ftrace_graph_fops = {
.llseek = ftrace_filter_lseek,
.release = ftrace_graph_release,
};
+
+static const struct file_operations ftrace_graph_notrace_fops = {
+ .open = ftrace_graph_notrace_open,
+ .read = seq_read,
+ .write = ftrace_graph_write,
+ .llseek = ftrace_filter_lseek,
+ .release = ftrace_graph_release,
+};
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
static __init int ftrace_init_dyn_debugfs(struct dentry *d_tracer)
@@ -3997,6 +4062,9 @@ static __init int ftrace_init_dyn_debugfs(struct dentry *d_tracer)
trace_create_file("set_graph_function", 0444, d_tracer,
NULL,
&ftrace_graph_fops);
+ trace_create_file("set_graph_notrace", 0444, d_tracer,
+ NULL,
+ &ftrace_graph_notrace_fops);
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
return 0;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 7974ba2..063a92b 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -843,9 +843,12 @@ int trace_get_user(struct trace_parser *parser, const char __user *ubuf,
if (isspace(ch)) {
parser->buffer[parser->idx] = 0;
parser->cont = false;
- } else {
+ } else if (parser->idx < parser->size - 1) {
parser->cont = true;
parser->buffer[parser->idx++] = ch;
+ } else {
+ ret = -EINVAL;
+ goto out;
}
*ppos += read;
@@ -2760,7 +2763,7 @@ static void show_snapshot_main_help(struct seq_file *m)
seq_printf(m, "# echo 0 > snapshot : Clears and frees snapshot buffer\n");
seq_printf(m, "# echo 1 > snapshot : Allocates snapshot buffer, if not already allocated.\n");
seq_printf(m, "# Takes a snapshot of the main buffer.\n");
- seq_printf(m, "# echo 2 > snapshot : Clears snapshot buffer (but does not allocate)\n");
+ seq_printf(m, "# echo 2 > snapshot : Clears snapshot buffer (but does not allocate or free)\n");
seq_printf(m, "# (Doesn't have to be '2' works with any number that\n");
seq_printf(m, "# is not a '0' or '1')\n");
}
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 10c86fb..d1cf515 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -730,15 +730,16 @@ extern void __trace_graph_return(struct trace_array *tr,
#ifdef CONFIG_DYNAMIC_FTRACE
/* TODO: make this variable */
#define FTRACE_GRAPH_MAX_FUNCS 32
-extern int ftrace_graph_filter_enabled;
extern int ftrace_graph_count;
extern unsigned long ftrace_graph_funcs[FTRACE_GRAPH_MAX_FUNCS];
+extern int ftrace_graph_notrace_count;
+extern unsigned long ftrace_graph_notrace_funcs[FTRACE_GRAPH_MAX_FUNCS];
static inline int ftrace_graph_addr(unsigned long addr)
{
int i;
- if (!ftrace_graph_filter_enabled)
+ if (!ftrace_graph_count)
return 1;
for (i = 0; i < ftrace_graph_count; i++) {
@@ -758,11 +759,31 @@ static inline int ftrace_graph_addr(unsigned long addr)
return 0;
}
+
+static inline int ftrace_graph_notrace_addr(unsigned long addr)
+{
+ int i;
+
+ if (!ftrace_graph_notrace_count)
+ return 0;
+
+ for (i = 0; i < ftrace_graph_notrace_count; i++) {
+ if (addr == ftrace_graph_notrace_funcs[i])
+ return 1;
+ }
+
+ return 0;
+}
#else
static inline int ftrace_graph_addr(unsigned long addr)
{
return 1;
}
+
+static inline int ftrace_graph_notrace_addr(unsigned long addr)
+{
+ return 0;
+}
#endif /* CONFIG_DYNAMIC_FTRACE */
#else /* CONFIG_FUNCTION_GRAPH_TRACER */
static inline enum print_line_t
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index b5c0924..e08c030 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -114,16 +114,37 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth,
return -EBUSY;
}
+ /*
+ * The curr_ret_stack is an index to ftrace return stack of
+ * current task. Its value should be in [0, FTRACE_RETFUNC_
+ * DEPTH) when the function graph tracer is used. To support
+ * filtering out specific functions, it makes the index
+ * negative by subtracting huge value (FTRACE_NOTRACE_DEPTH)
+ * so when it sees a negative index the ftrace will ignore
+ * the record. And the index gets recovered when returning
+ * from the filtered function by adding the FTRACE_NOTRACE_
+ * DEPTH and then it'll continue to record functions normally.
+ *
+ * The curr_ret_stack is initialized to -1 and get increased
+ * in this function. So it can be less than -1 only if it was
+ * filtered out via ftrace_graph_notrace_addr() which can be
+ * set from set_graph_notrace file in debugfs by user.
+ */
+ if (current->curr_ret_stack < -1)
+ return -EBUSY;
+
calltime = trace_clock_local();
index = ++current->curr_ret_stack;
+ if (ftrace_graph_notrace_addr(func))
+ current->curr_ret_stack -= FTRACE_NOTRACE_DEPTH;
barrier();
current->ret_stack[index].ret = ret;
current->ret_stack[index].func = func;
current->ret_stack[index].calltime = calltime;
current->ret_stack[index].subtime = 0;
current->ret_stack[index].fp = frame_pointer;
- *depth = index;
+ *depth = current->curr_ret_stack;
return 0;
}
@@ -137,7 +158,17 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret,
index = current->curr_ret_stack;
- if (unlikely(index < 0)) {
+ /*
+ * A negative index here means that it's just returned from a
+ * notrace'd function. Recover index to get an original
+ * return address. See ftrace_push_return_trace().
+ *
+ * TODO: Need to check whether the stack gets corrupted.
+ */
+ if (index < 0)
+ index += FTRACE_NOTRACE_DEPTH;
+
+ if (unlikely(index < 0 || index >= FTRACE_RETFUNC_DEPTH)) {
ftrace_graph_stop();
WARN_ON(1);
/* Might as well panic, otherwise we have no where to go */
@@ -193,6 +224,15 @@ unsigned long ftrace_return_to_handler(unsigned long frame_pointer)
trace.rettime = trace_clock_local();
barrier();
current->curr_ret_stack--;
+ /*
+ * The curr_ret_stack can be less than -1 only if it was
+ * filtered out and it's about to return from the function.
+ * Recover the index and continue to trace normal functions.
+ */
+ if (current->curr_ret_stack < -1) {
+ current->curr_ret_stack += FTRACE_NOTRACE_DEPTH;
+ return ret;
+ }
/*
* The trace should run after decrementing the ret counter
@@ -259,10 +299,20 @@ int trace_graph_entry(struct ftrace_graph_ent *trace)
/* trace it when it is-nested-in or is a function enabled. */
if ((!(trace->depth || ftrace_graph_addr(trace->func)) ||
- ftrace_graph_ignore_irqs()) ||
+ ftrace_graph_ignore_irqs()) || (trace->depth < 0) ||
(max_depth && trace->depth >= max_depth))
return 0;
+ /*
+ * Do not trace a function if it's filtered by set_graph_notrace.
+ * Make the index of ret stack negative to indicate that it should
+ * ignore further functions. But it needs its own ret stack entry
+ * to recover the original index in order to continue tracing after
+ * returning from the function.
+ */
+ if (ftrace_graph_notrace_addr(trace->func))
+ return 1;
+
local_irq_save(flags);
cpu = raw_smp_processor_id();
data = per_cpu_ptr(tr->trace_buffer.data, cpu);
diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c
index 847f88a..7af6736 100644
--- a/kernel/trace/trace_stat.c
+++ b/kernel/trace/trace_stat.c
@@ -43,46 +43,15 @@ static DEFINE_MUTEX(all_stat_sessions_mutex);
/* The root directory for all stat files */
static struct dentry *stat_dir;
-/*
- * Iterate through the rbtree using a post order traversal path
- * to release the next node.
- * It won't necessary release one at each iteration
- * but it will at least advance closer to the next one
- * to be released.
- */
-static struct rb_node *release_next(struct tracer_stat *ts,
- struct rb_node *node)
+static void __reset_stat_session(struct stat_session *session)
{
- struct stat_node *snode;
- struct rb_node *parent = rb_parent(node);
-
- if (node->rb_left)
- return node->rb_left;
- else if (node->rb_right)
- return node->rb_right;
- else {
- if (!parent)
- ;
- else if (parent->rb_left == node)
- parent->rb_left = NULL;
- else
- parent->rb_right = NULL;
+ struct stat_node *snode, *n;
- snode = container_of(node, struct stat_node, node);
- if (ts->stat_release)
- ts->stat_release(snode->stat);
+ rbtree_postorder_for_each_entry_safe(snode, n, &session->stat_root, node) {
+ if (session->ts->stat_release)
+ session->ts->stat_release(snode->stat);
kfree(snode);
-
- return parent;
}
-}
-
-static void __reset_stat_session(struct stat_session *session)
-{
- struct rb_node *node = session->stat_root.rb_node;
-
- while (node)
- node = release_next(session->ts, node);
session->stat_root = RB_ROOT;
}
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 51c4f34..4431610 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -486,7 +486,52 @@ static struct smp_hotplug_thread watchdog_threads = {
.unpark = watchdog_enable,
};
-static int watchdog_enable_all_cpus(void)
+static void restart_watchdog_hrtimer(void *info)
+{
+ struct hrtimer *hrtimer = &__raw_get_cpu_var(watchdog_hrtimer);
+ int ret;
+
+ /*
+ * No need to cancel and restart hrtimer if it is currently executing
+ * because it will reprogram itself with the new period now.
+ * We should never see it unqueued here because we are running per-cpu
+ * with interrupts disabled.
+ */
+ ret = hrtimer_try_to_cancel(hrtimer);
+ if (ret == 1)
+ hrtimer_start(hrtimer, ns_to_ktime(sample_period),
+ HRTIMER_MODE_REL_PINNED);
+}
+
+static void update_timers(int cpu)
+{
+ struct call_single_data data = {.func = restart_watchdog_hrtimer};
+ /*
+ * Make sure that perf event counter will adopt to a new
+ * sampling period. Updating the sampling period directly would
+ * be much nicer but we do not have an API for that now so
+ * let's use a big hammer.
+ * Hrtimer will adopt the new period on the next tick but this
+ * might be late already so we have to restart the timer as well.
+ */
+ watchdog_nmi_disable(cpu);
+ __smp_call_function_single(cpu, &data, 1);
+ watchdog_nmi_enable(cpu);
+}
+
+static void update_timers_all_cpus(void)
+{
+ int cpu;
+
+ get_online_cpus();
+ preempt_disable();
+ for_each_online_cpu(cpu)
+ update_timers(cpu);
+ preempt_enable();
+ put_online_cpus();
+}
+
+static int watchdog_enable_all_cpus(bool sample_period_changed)
{
int err = 0;
@@ -496,6 +541,8 @@ static int watchdog_enable_all_cpus(void)
pr_err("Failed to create watchdog threads, disabled\n");
else
watchdog_running = 1;
+ } else if (sample_period_changed) {
+ update_timers_all_cpus();
}
return err;
@@ -520,13 +567,15 @@ int proc_dowatchdog(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
int err, old_thresh, old_enabled;
+ static DEFINE_MUTEX(watchdog_proc_mutex);
+ mutex_lock(&watchdog_proc_mutex);
old_thresh = ACCESS_ONCE(watchdog_thresh);
old_enabled = ACCESS_ONCE(watchdog_user_enabled);
err = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
if (err || !write)
- return err;
+ goto out;
set_sample_period();
/*
@@ -535,7 +584,7 @@ int proc_dowatchdog(struct ctl_table *table, int write,
* watchdog_*_all_cpus() function takes care of this.
*/
if (watchdog_user_enabled && watchdog_thresh)
- err = watchdog_enable_all_cpus();
+ err = watchdog_enable_all_cpus(old_thresh != watchdog_thresh);
else
watchdog_disable_all_cpus();
@@ -544,7 +593,8 @@ int proc_dowatchdog(struct ctl_table *table, int write,
watchdog_thresh = old_thresh;
watchdog_user_enabled = old_enabled;
}
-
+out:
+ mutex_unlock(&watchdog_proc_mutex);
return err;
}
#endif /* CONFIG_SYSCTL */
@@ -554,5 +604,5 @@ void __init lockup_detector_init(void)
set_sample_period();
if (watchdog_user_enabled)
- watchdog_enable_all_cpus();
+ watchdog_enable_all_cpus(false);
}
OpenPOWER on IntegriCloud