summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/Makefile1
-rw-r--r--kernel/cred.c21
-rw-r--r--kernel/fork.c2
-rw-r--r--kernel/locking/lockdep.c18
-rw-r--r--kernel/locking/lockdep_proc.c8
-rw-r--r--kernel/padata.c12
-rw-r--r--kernel/pid_namespace.c2
-rw-r--r--kernel/sched/fair.c24
-rw-r--r--kernel/time/ntp.c4
-rw-r--r--kernel/time/timer_list.c36
-rw-r--r--kernel/trace/trace.c12
11 files changed, 98 insertions, 42 deletions
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 13272582eee0..677991f29d66 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -1,4 +1,5 @@
obj-y := core.o
+CFLAGS_core.o += $(call cc-disable-warning, override-init)
obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o
obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o
diff --git a/kernel/cred.c b/kernel/cred.c
index 098af0bc0b7e..a2e06b05a90c 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -146,7 +146,10 @@ void __put_cred(struct cred *cred)
BUG_ON(cred == current->cred);
BUG_ON(cred == current->real_cred);
- call_rcu(&cred->rcu, put_cred_rcu);
+ if (cred->non_rcu)
+ put_cred_rcu(&cred->rcu);
+ else
+ call_rcu(&cred->rcu, put_cred_rcu);
}
EXPORT_SYMBOL(__put_cred);
@@ -257,6 +260,7 @@ struct cred *prepare_creds(void)
old = task->cred;
memcpy(new, old, sizeof(struct cred));
+ new->non_rcu = 0;
atomic_set(&new->usage, 1);
set_cred_subscribers(new, 0);
get_group_info(new->group_info);
@@ -536,7 +540,19 @@ const struct cred *override_creds(const struct cred *new)
validate_creds(old);
validate_creds(new);
- get_cred(new);
+
+ /*
+ * NOTE! This uses 'get_new_cred()' rather than 'get_cred()'.
+ *
+ * That means that we do not clear the 'non_rcu' flag, since
+ * we are only installing the cred into the thread-synchronous
+ * '->cred' pointer, not the '->real_cred' pointer that is
+ * visible to other threads under RCU.
+ *
+ * Also note that we did validate_creds() manually, not depending
+ * on the validation in 'get_cred()'.
+ */
+ get_new_cred((struct cred *)new);
alter_cred_subscribers(new, 1);
rcu_assign_pointer(current->cred, new);
alter_cred_subscribers(old, -1);
@@ -619,6 +635,7 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon)
validate_creds(old);
*new = *old;
+ new->non_rcu = 0;
atomic_set(&new->usage, 1);
set_cred_subscribers(new, 0);
get_uid(new->user);
diff --git a/kernel/fork.c b/kernel/fork.c
index c6e26e433445..3891d83df123 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -259,7 +259,7 @@ void __put_task_struct(struct task_struct *tsk)
WARN_ON(tsk == current);
cgroup_free(tsk);
- task_numa_free(tsk);
+ task_numa_free(tsk, true);
security_task_free(tsk);
exit_creds(tsk);
delayacct_tsk_free(tsk);
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 774ab79d3ec7..f2df5f86af28 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -3128,17 +3128,17 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
if (depth) {
hlock = curr->held_locks + depth - 1;
if (hlock->class_idx == class_idx && nest_lock) {
- if (hlock->references) {
- /*
- * Check: unsigned int references:12, overflow.
- */
- if (DEBUG_LOCKS_WARN_ON(hlock->references == (1 << 12)-1))
- return 0;
+ if (!references)
+ references++;
+ if (!hlock->references)
hlock->references++;
- } else {
- hlock->references = 2;
- }
+
+ hlock->references += references;
+
+ /* Overflow */
+ if (DEBUG_LOCKS_WARN_ON(hlock->references < references))
+ return 0;
return 1;
}
diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c
index dbb61a302548..35b34eccdd10 100644
--- a/kernel/locking/lockdep_proc.c
+++ b/kernel/locking/lockdep_proc.c
@@ -217,7 +217,6 @@ static void lockdep_stats_debug_show(struct seq_file *m)
static int lockdep_stats_show(struct seq_file *m, void *v)
{
- struct lock_class *class;
unsigned long nr_unused = 0, nr_uncategorized = 0,
nr_irq_safe = 0, nr_irq_unsafe = 0,
nr_softirq_safe = 0, nr_softirq_unsafe = 0,
@@ -227,6 +226,9 @@ static int lockdep_stats_show(struct seq_file *m, void *v)
nr_hardirq_read_safe = 0, nr_hardirq_read_unsafe = 0,
sum_forward_deps = 0;
+#ifdef CONFIG_PROVE_LOCKING
+ struct lock_class *class;
+
list_for_each_entry(class, &all_lock_classes, lock_entry) {
if (class->usage_mask == 0)
@@ -258,13 +260,13 @@ static int lockdep_stats_show(struct seq_file *m, void *v)
if (class->usage_mask & LOCKF_ENABLED_HARDIRQ_READ)
nr_hardirq_read_unsafe++;
-#ifdef CONFIG_PROVE_LOCKING
sum_forward_deps += lockdep_count_forward_deps(class);
-#endif
}
#ifdef CONFIG_DEBUG_LOCKDEP
DEBUG_LOCKS_WARN_ON(debug_atomic_read(nr_unused_locks) != nr_unused);
#endif
+
+#endif
seq_printf(m, " lock-classes: %11lu [max: %lu]\n",
nr_lock_classes, MAX_LOCKDEP_KEYS);
seq_printf(m, " direct dependencies: %11lu [max: %lu]\n",
diff --git a/kernel/padata.c b/kernel/padata.c
index ecc7b3f452c7..282b489a286d 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -273,7 +273,12 @@ static void padata_reorder(struct parallel_data *pd)
* The next object that needs serialization might have arrived to
* the reorder queues in the meantime, we will be called again
* from the timer function if no one else cares for it.
+ *
+ * Ensure reorder_objects is read after pd->lock is dropped so we see
+ * an increment from another task in padata_do_serial. Pairs with
+ * smp_mb__after_atomic in padata_do_serial.
*/
+ smp_mb();
if (atomic_read(&pd->reorder_objects)
&& !(pinst->flags & PADATA_RESET))
mod_timer(&pd->timer, jiffies + HZ);
@@ -342,6 +347,13 @@ void padata_do_serial(struct padata_priv *padata)
list_add_tail(&padata->list, &pqueue->reorder.list);
spin_unlock(&pqueue->reorder.lock);
+ /*
+ * Ensure the atomic_inc of reorder_objects above is ordered correctly
+ * with the trylock of pd->lock in padata_reorder. Pairs with smp_mb
+ * in padata_reorder.
+ */
+ smp_mb__after_atomic();
+
put_cpu();
padata_reorder(pd);
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 567ecc826bc8..6353372801f2 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -325,7 +325,7 @@ int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd)
}
read_lock(&tasklist_lock);
- force_sig(SIGKILL, pid_ns->child_reaper);
+ send_sig(SIGKILL, pid_ns->child_reaper, 1);
read_unlock(&tasklist_lock);
do_exit(0);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index cf5916ea2ae1..134e2bd6f782 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2210,13 +2210,23 @@ no_join:
return;
}
-void task_numa_free(struct task_struct *p)
+/*
+ * Get rid of NUMA staticstics associated with a task (either current or dead).
+ * If @final is set, the task is dead and has reached refcount zero, so we can
+ * safely free all relevant data structures. Otherwise, there might be
+ * concurrent reads from places like load balancing and procfs, and we should
+ * reset the data back to default state without freeing ->numa_faults.
+ */
+void task_numa_free(struct task_struct *p, bool final)
{
struct numa_group *grp = p->numa_group;
- void *numa_faults = p->numa_faults;
+ unsigned long *numa_faults = p->numa_faults;
unsigned long flags;
int i;
+ if (!numa_faults)
+ return;
+
if (grp) {
spin_lock_irqsave(&grp->lock, flags);
for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++)
@@ -2229,8 +2239,14 @@ void task_numa_free(struct task_struct *p)
put_numa_group(grp);
}
- p->numa_faults = NULL;
- kfree(numa_faults);
+ if (final) {
+ p->numa_faults = NULL;
+ kfree(numa_faults);
+ } else {
+ p->total_numa_faults = 0;
+ for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++)
+ numa_faults[i] = 0;
+ }
}
/*
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 0e0dc5d89911..bbe767b1f454 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -39,6 +39,7 @@ static u64 tick_length_base;
#define MAX_TICKADJ 500LL /* usecs */
#define MAX_TICKADJ_SCALED \
(((MAX_TICKADJ * NSEC_PER_USEC) << NTP_SCALE_SHIFT) / NTP_INTERVAL_FREQ)
+#define MAX_TAI_OFFSET 100000
/*
* phase-lock loop variables
@@ -633,7 +634,8 @@ static inline void process_adjtimex_modes(struct timex *txc,
time_constant = max(time_constant, 0l);
}
- if (txc->modes & ADJ_TAI && txc->constant >= 0)
+ if (txc->modes & ADJ_TAI &&
+ txc->constant >= 0 && txc->constant <= MAX_TAI_OFFSET)
*time_tai = txc->constant;
if (txc->modes & ADJ_OFFSET)
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index 1407ed20ea93..b7c5d230b4b2 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -299,23 +299,6 @@ static inline void timer_list_header(struct seq_file *m, u64 now)
SEQ_printf(m, "\n");
}
-static int timer_list_show(struct seq_file *m, void *v)
-{
- struct timer_list_iter *iter = v;
-
- if (iter->cpu == -1 && !iter->second_pass)
- timer_list_header(m, iter->now);
- else if (!iter->second_pass)
- print_cpu(m, iter->cpu, iter->now);
-#ifdef CONFIG_GENERIC_CLOCKEVENTS
- else if (iter->cpu == -1 && iter->second_pass)
- timer_list_show_tickdevices_header(m);
- else
- print_tickdevice(m, tick_get_device(iter->cpu), iter->cpu);
-#endif
- return 0;
-}
-
void sysrq_timer_list_show(void)
{
u64 now = ktime_to_ns(ktime_get());
@@ -334,6 +317,24 @@ void sysrq_timer_list_show(void)
return;
}
+#ifdef CONFIG_PROC_FS
+static int timer_list_show(struct seq_file *m, void *v)
+{
+ struct timer_list_iter *iter = v;
+
+ if (iter->cpu == -1 && !iter->second_pass)
+ timer_list_header(m, iter->now);
+ else if (!iter->second_pass)
+ print_cpu(m, iter->cpu, iter->now);
+#ifdef CONFIG_GENERIC_CLOCKEVENTS
+ else if (iter->cpu == -1 && iter->second_pass)
+ timer_list_show_tickdevices_header(m);
+ else
+ print_tickdevice(m, tick_get_device(iter->cpu), iter->cpu);
+#endif
+ return 0;
+}
+
static void *move_iter(struct timer_list_iter *iter, loff_t offset)
{
for (; offset; offset--) {
@@ -405,3 +406,4 @@ static int __init init_timer_list_procfs(void)
return 0;
}
__initcall(init_timer_list_procfs);
+#endif
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 405a234aadf4..e71d8da5f260 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -5497,11 +5497,15 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt,
break;
}
#endif
- if (!tr->allocated_snapshot) {
+ if (!tr->allocated_snapshot)
+ ret = resize_buffer_duplicate_size(&tr->max_buffer,
+ &tr->trace_buffer, iter->cpu_file);
+ else
ret = alloc_snapshot(tr);
- if (ret < 0)
- break;
- }
+
+ if (ret < 0)
+ break;
+
local_irq_disable();
/* Now, we're going to swap */
if (iter->cpu_file == RING_BUFFER_ALL_CPUS)
generated by cgit v1.2.3 (git 2.25.1) at 2025-10-23 15:51:22 +0000