summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/events/core.c32
-rw-r--r--kernel/locking/rtmutex_common.h4
-rw-r--r--kernel/locking/semaphore.c13
-rw-r--r--kernel/pid_namespace.c2
-rw-r--r--kernel/sched/cputime.c8
-rw-r--r--kernel/sched/deadline.c2
-rw-r--r--kernel/sched/ext.c3
-rw-r--r--kernel/sched/fair.c6
-rw-r--r--kernel/sched/sched.h4
-rw-r--r--kernel/trace/trace_events_hist.c24
-rw-r--r--kernel/trace/trace_fprobe.c20
-rw-r--r--kernel/trace/trace_probe.h5
12 files changed, 95 insertions, 28 deletions
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 6364319e2f88..823aa0824916 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -11830,6 +11830,21 @@ free_dev:
static struct lock_class_key cpuctx_mutex;
static struct lock_class_key cpuctx_lock;
+static bool idr_cmpxchg(struct idr *idr, unsigned long id, void *old, void *new)
+{
+ void *tmp, *val = idr_find(idr, id);
+
+ if (val != old)
+ return false;
+
+ tmp = idr_replace(idr, new, id);
+ if (IS_ERR(tmp))
+ return false;
+
+ WARN_ON_ONCE(tmp != val);
+ return true;
+}
+
int perf_pmu_register(struct pmu *pmu, const char *name, int type)
{
int cpu, ret, max = PERF_TYPE_MAX;
@@ -11856,7 +11871,7 @@ int perf_pmu_register(struct pmu *pmu, const char *name, int type)
if (type >= 0)
max = type;
- ret = idr_alloc(&pmu_idr, pmu, max, 0, GFP_KERNEL);
+ ret = idr_alloc(&pmu_idr, NULL, max, 0, GFP_KERNEL);
if (ret < 0)
goto free_pdc;
@@ -11864,6 +11879,7 @@ int perf_pmu_register(struct pmu *pmu, const char *name, int type)
type = ret;
pmu->type = type;
+ atomic_set(&pmu->exclusive_cnt, 0);
if (pmu_bus_running && !pmu->dev) {
ret = pmu_dev_alloc(pmu);
@@ -11912,14 +11928,22 @@ int perf_pmu_register(struct pmu *pmu, const char *name, int type)
if (!pmu->event_idx)
pmu->event_idx = perf_event_idx_default;
+ /*
+ * Now that the PMU is complete, make it visible to perf_try_init_event().
+ */
+ if (!idr_cmpxchg(&pmu_idr, pmu->type, NULL, pmu))
+ goto free_context;
list_add_rcu(&pmu->entry, &pmus);
- atomic_set(&pmu->exclusive_cnt, 0);
+
ret = 0;
unlock:
mutex_unlock(&pmus_lock);
return ret;
+free_context:
+ free_percpu(pmu->cpu_pmu_context);
+
free_dev:
if (pmu->dev && pmu->dev != PMU_NULL_DEV) {
device_del(pmu->dev);
@@ -11939,6 +11963,8 @@ void perf_pmu_unregister(struct pmu *pmu)
{
mutex_lock(&pmus_lock);
list_del_rcu(&pmu->entry);
+ idr_remove(&pmu_idr, pmu->type);
+ mutex_unlock(&pmus_lock);
/*
* We dereference the pmu list under both SRCU and regular RCU, so
@@ -11948,7 +11974,6 @@ void perf_pmu_unregister(struct pmu *pmu)
synchronize_rcu();
free_percpu(pmu->pmu_disable_count);
- idr_remove(&pmu_idr, pmu->type);
if (pmu_bus_running && pmu->dev && pmu->dev != PMU_NULL_DEV) {
if (pmu->nr_addr_filters)
device_remove_file(pmu->dev, &dev_attr_nr_addr_filters);
@@ -11956,7 +11981,6 @@ void perf_pmu_unregister(struct pmu *pmu)
put_device(pmu->dev);
}
free_pmu_context(pmu);
- mutex_unlock(&pmus_lock);
}
EXPORT_SYMBOL_GPL(perf_pmu_unregister);
diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h
index c38a2d2d4a7e..78dd3d8c6554 100644
--- a/kernel/locking/rtmutex_common.h
+++ b/kernel/locking/rtmutex_common.h
@@ -59,8 +59,8 @@ struct rt_mutex_waiter {
};
/**
- * rt_wake_q_head - Wrapper around regular wake_q_head to support
- * "sleeping" spinlocks on RT
+ * struct rt_wake_q_head - Wrapper around regular wake_q_head to support
+ * "sleeping" spinlocks on RT
* @head: The regular wake_q_head for sleeping lock variants
* @rtlock_task: Task pointer for RT lock (spin/rwlock) wakeups
*/
diff --git a/kernel/locking/semaphore.c b/kernel/locking/semaphore.c
index 34bfae72f295..de9117c0e671 100644
--- a/kernel/locking/semaphore.c
+++ b/kernel/locking/semaphore.c
@@ -29,6 +29,7 @@
#include <linux/export.h>
#include <linux/sched.h>
#include <linux/sched/debug.h>
+#include <linux/sched/wake_q.h>
#include <linux/semaphore.h>
#include <linux/spinlock.h>
#include <linux/ftrace.h>
@@ -38,7 +39,7 @@ static noinline void __down(struct semaphore *sem);
static noinline int __down_interruptible(struct semaphore *sem);
static noinline int __down_killable(struct semaphore *sem);
static noinline int __down_timeout(struct semaphore *sem, long timeout);
-static noinline void __up(struct semaphore *sem);
+static noinline void __up(struct semaphore *sem, struct wake_q_head *wake_q);
/**
* down - acquire the semaphore
@@ -183,13 +184,16 @@ EXPORT_SYMBOL(down_timeout);
void __sched up(struct semaphore *sem)
{
unsigned long flags;
+ DEFINE_WAKE_Q(wake_q);
raw_spin_lock_irqsave(&sem->lock, flags);
if (likely(list_empty(&sem->wait_list)))
sem->count++;
else
- __up(sem);
+ __up(sem, &wake_q);
raw_spin_unlock_irqrestore(&sem->lock, flags);
+ if (!wake_q_empty(&wake_q))
+ wake_up_q(&wake_q);
}
EXPORT_SYMBOL(up);
@@ -269,11 +273,12 @@ static noinline int __sched __down_timeout(struct semaphore *sem, long timeout)
return __down_common(sem, TASK_UNINTERRUPTIBLE, timeout);
}
-static noinline void __sched __up(struct semaphore *sem)
+static noinline void __sched __up(struct semaphore *sem,
+ struct wake_q_head *wake_q)
{
struct semaphore_waiter *waiter = list_first_entry(&sem->wait_list,
struct semaphore_waiter, list);
list_del(&waiter->list);
waiter->up = true;
- wake_up_process(waiter->task);
+ wake_q_add(wake_q, waiter->task);
}
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 8f6cfec87555..7098ed44e717 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -107,7 +107,7 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns
goto out_free_idr;
ns->ns.ops = &pidns_operations;
- ns->pid_max = parent_pid_ns->pid_max;
+ ns->pid_max = PID_MAX_LIMIT;
err = register_pidns_sysctls(ns);
if (err)
goto out_free_inum;
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 5d9143dd0879..6dab4854c6c0 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -9,8 +9,6 @@
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
-DEFINE_STATIC_KEY_FALSE(sched_clock_irqtime);
-
/*
* There are no locks covering percpu hardirq/softirq time.
* They are only modified in vtime_account, on corresponding CPU
@@ -24,14 +22,16 @@ DEFINE_STATIC_KEY_FALSE(sched_clock_irqtime);
*/
DEFINE_PER_CPU(struct irqtime, cpu_irqtime);
+int sched_clock_irqtime;
+
void enable_sched_clock_irqtime(void)
{
- static_branch_enable(&sched_clock_irqtime);
+ sched_clock_irqtime = 1;
}
void disable_sched_clock_irqtime(void)
{
- static_branch_disable(&sched_clock_irqtime);
+ sched_clock_irqtime = 0;
}
static void irqtime_account_delta(struct irqtime *irqtime, u64 delta,
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 38e4537790af..ff4df16b5186 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -3189,7 +3189,7 @@ int sched_dl_global_validate(void)
* value smaller than the currently allocated bandwidth in
* any of the root_domains.
*/
- for_each_possible_cpu(cpu) {
+ for_each_online_cpu(cpu) {
rcu_read_lock_sched();
if (dl_bw_visited(cpu, gen))
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 0f1da199cfc7..7b9dfee858e7 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -6422,6 +6422,9 @@ static bool check_builtin_idle_enabled(void)
__bpf_kfunc s32 scx_bpf_select_cpu_dfl(struct task_struct *p, s32 prev_cpu,
u64 wake_flags, bool *is_idle)
{
+ if (!ops_cpu_valid(prev_cpu, NULL))
+ goto prev_cpu;
+
if (!check_builtin_idle_enabled())
goto prev_cpu;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 1c0ef435a7aa..c798d2795243 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4045,15 +4045,17 @@ static inline bool child_cfs_rq_on_list(struct cfs_rq *cfs_rq)
{
struct cfs_rq *prev_cfs_rq;
struct list_head *prev;
+ struct rq *rq = rq_of(cfs_rq);
if (cfs_rq->on_list) {
prev = cfs_rq->leaf_cfs_rq_list.prev;
} else {
- struct rq *rq = rq_of(cfs_rq);
-
prev = rq->tmp_alone_branch;
}
+ if (prev == &rq->leaf_cfs_rq_list)
+ return false;
+
prev_cfs_rq = container_of(prev, struct cfs_rq, leaf_cfs_rq_list);
return (prev_cfs_rq->tg->parent == cfs_rq->tg);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index c8512a9fb022..023b844159c9 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -3259,11 +3259,11 @@ struct irqtime {
};
DECLARE_PER_CPU(struct irqtime, cpu_irqtime);
-DECLARE_STATIC_KEY_FALSE(sched_clock_irqtime);
+extern int sched_clock_irqtime;
static inline int irqtime_enabled(void)
{
- return static_branch_likely(&sched_clock_irqtime);
+ return sched_clock_irqtime;
}
/*
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index ad7419e24055..53dc6719181e 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -5689,12 +5689,16 @@ static int event_hist_open(struct inode *inode, struct file *file)
guard(mutex)(&event_mutex);
event_file = event_file_data(file);
- if (!event_file)
- return -ENODEV;
+ if (!event_file) {
+ ret = -ENODEV;
+ goto err;
+ }
hist_file = kzalloc(sizeof(*hist_file), GFP_KERNEL);
- if (!hist_file)
- return -ENOMEM;
+ if (!hist_file) {
+ ret = -ENOMEM;
+ goto err;
+ }
hist_file->file = file;
hist_file->last_act = get_hist_hit_count(event_file);
@@ -5702,9 +5706,14 @@ static int event_hist_open(struct inode *inode, struct file *file)
/* Clear private_data to avoid warning in single_open() */
file->private_data = NULL;
ret = single_open(file, hist_show, hist_file);
- if (ret)
+ if (ret) {
kfree(hist_file);
+ goto err;
+ }
+ return 0;
+err:
+ tracing_release_file_tr(inode, file);
return ret;
}
@@ -5979,7 +5988,10 @@ static int event_hist_debug_open(struct inode *inode, struct file *file)
/* Clear private_data to avoid warning in single_open() */
file->private_data = NULL;
- return single_open(file, hist_debug_show, file);
+ ret = single_open(file, hist_debug_show, file);
+ if (ret)
+ tracing_release_file_tr(inode, file);
+ return ret;
}
const struct file_operations event_hist_debug_fops = {
diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c
index b8f3c4ba309b..e27305d31fc5 100644
--- a/kernel/trace/trace_fprobe.c
+++ b/kernel/trace/trace_fprobe.c
@@ -1049,6 +1049,19 @@ static int parse_symbol_and_return(int argc, const char *argv[],
if (*is_return)
return 0;
+ if (is_tracepoint) {
+ tmp = *symbol;
+ while (*tmp && (isalnum(*tmp) || *tmp == '_'))
+ tmp++;
+ if (*tmp) {
+ /* find a wrong character. */
+ trace_probe_log_err(tmp - *symbol, BAD_TP_NAME);
+ kfree(*symbol);
+ *symbol = NULL;
+ return -EINVAL;
+ }
+ }
+
/* If there is $retval, this should be a return fprobe. */
for (i = 2; i < argc; i++) {
tmp = strstr(argv[i], "$retval");
@@ -1056,6 +1069,8 @@ static int parse_symbol_and_return(int argc, const char *argv[],
if (is_tracepoint) {
trace_probe_log_set_index(i);
trace_probe_log_err(tmp - argv[i], RETVAL_ON_PROBE);
+ kfree(*symbol);
+ *symbol = NULL;
return -EINVAL;
}
*is_return = true;
@@ -1215,6 +1230,11 @@ static int trace_fprobe_create_internal(int argc, const char *argv[],
if (is_return && tf->tp.entry_arg) {
tf->fp.entry_handler = trace_fprobe_entry_handler;
tf->fp.entry_data_size = traceprobe_get_entry_data_size(&tf->tp);
+ if (ALIGN(tf->fp.entry_data_size, sizeof(long)) > MAX_FPROBE_DATA_SIZE) {
+ trace_probe_log_set_index(2);
+ trace_probe_log_err(0, TOO_MANY_EARGS);
+ return -E2BIG;
+ }
}
ret = traceprobe_set_print_fmt(&tf->tp,
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 5803e6a41570..96792bc4b092 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -36,7 +36,6 @@
#define MAX_BTF_ARGS_LEN 128
#define MAX_DENTRY_ARGS_LEN 256
#define MAX_STRING_SIZE PATH_MAX
-#define MAX_ARG_BUF_LEN (MAX_TRACE_ARGS * MAX_ARG_NAME_LEN)
/* Reserved field names */
#define FIELD_STRING_IP "__probe_ip"
@@ -481,6 +480,7 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call,
C(NON_UNIQ_SYMBOL, "The symbol is not unique"), \
C(BAD_RETPROBE, "Retprobe address must be an function entry"), \
C(NO_TRACEPOINT, "Tracepoint is not found"), \
+ C(BAD_TP_NAME, "Invalid character in tracepoint name"),\
C(BAD_ADDR_SUFFIX, "Invalid probed address suffix"), \
C(NO_GROUP_NAME, "Group name is not specified"), \
C(GROUP_TOO_LONG, "Group name is too long"), \
@@ -544,7 +544,8 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call,
C(NO_BTF_FIELD, "This field is not found."), \
C(BAD_BTF_TID, "Failed to get BTF type info."),\
C(BAD_TYPE4STR, "This type does not fit for string."),\
- C(NEED_STRING_TYPE, "$comm and immediate-string only accepts string type"),
+ C(NEED_STRING_TYPE, "$comm and immediate-string only accepts string type"),\
+ C(TOO_MANY_EARGS, "Too many entry arguments specified"),
#undef C
#define C(a, b) TP_ERR_##a
generated by cgit (git 2.34.1) at 2025-08-07 08:15:09 +0000