aboutsummaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/verifier.c9
-rw-r--r--kernel/cred.c6
-rw-r--r--kernel/exit.c12
-rw-r--r--kernel/locking/spinlock_debug.c32
-rw-r--r--kernel/module.c2
-rw-r--r--kernel/power/snapshot.c9
-rw-r--r--kernel/sched/psi.c5
-rw-r--r--kernel/taskstats.c30
-rw-r--r--kernel/trace/ftrace.c6
-rw-r--r--kernel/trace/trace.c8
-rw-r--r--kernel/trace/trace_events.c8
-rw-r--r--kernel/trace/trace_events_filter.c2
-rw-r--r--kernel/trace/trace_events_hist.c21
-rw-r--r--kernel/trace/tracing_map.c4
14 files changed, 104 insertions, 50 deletions
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 438614c503c7..9be408bc0b67 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5287,6 +5287,7 @@ static bool may_access_skb(enum bpf_prog_type type)
static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
{
struct bpf_reg_state *regs = cur_regs(env);
+ static const int ctx_reg = BPF_REG_6;
u8 mode = BPF_MODE(insn->code);
int i, err;
@@ -5320,7 +5321,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
}
/* check whether implicit source operand (register R6) is readable */
- err = check_reg_arg(env, BPF_REG_6, SRC_OP);
+ err = check_reg_arg(env, ctx_reg, SRC_OP);
if (err)
return err;
@@ -5339,7 +5340,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
return -EINVAL;
}
- if (regs[BPF_REG_6].type != PTR_TO_CTX) {
+ if (regs[ctx_reg].type != PTR_TO_CTX) {
verbose(env,
"at the time of BPF_LD_ABS|IND R6 != pointer to skb\n");
return -EINVAL;
@@ -5352,6 +5353,10 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
return err;
}
+ err = check_ctx_reg(env, &regs[ctx_reg], ctx_reg);
+ if (err < 0)
+ return err;
+
/* reset caller saved regs to unreadable */
for (i = 0; i < CALLER_SAVED_REGS; i++) {
mark_reg_not_init(env, regs, caller_saved[i]);
diff --git a/kernel/cred.c b/kernel/cred.c
index 153ae369e024..7cfd1db529d4 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -218,7 +218,7 @@ struct cred *cred_alloc_blank(void)
new->magic = CRED_MAGIC;
#endif
- if (security_cred_alloc_blank(new, GFP_KERNEL) < 0)
+ if (security_cred_alloc_blank(new, GFP_KERNEL_ACCOUNT) < 0)
goto error;
return new;
@@ -277,7 +277,7 @@ struct cred *prepare_creds(void)
new->security = NULL;
#endif
- if (security_prepare_creds(new, old, GFP_KERNEL) < 0)
+ if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0)
goto error;
validate_creds(new);
return new;
@@ -706,7 +706,7 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon)
#ifdef CONFIG_SECURITY
new->security = NULL;
#endif
- if (security_prepare_creds(new, old, GFP_KERNEL) < 0)
+ if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0)
goto error;
put_cred(old);
diff --git a/kernel/exit.c b/kernel/exit.c
index 235cf6825593..8df4c00e1c15 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -579,10 +579,6 @@ static struct task_struct *find_child_reaper(struct task_struct *father,
}
write_unlock_irq(&tasklist_lock);
- if (unlikely(pid_ns == &init_pid_ns)) {
- panic("Attempted to kill init! exitcode=0x%08x\n",
- father->signal->group_exit_code ?: father->exit_code);
- }
list_for_each_entry_safe(p, n, dead, ptrace_entry) {
list_del_init(&p->ptrace_entry);
@@ -908,6 +904,14 @@ void __noreturn do_exit(long code)
acct_update_integrals(tsk);
group_dead = atomic_dec_and_test(&tsk->signal->live);
if (group_dead) {
+ /*
+ * If the last thread of global init has exited, panic
+ * immediately to get a useable coredump.
+ */
+ if (unlikely(is_global_init(tsk)))
+ panic("Attempted to kill init! exitcode=0x%08x\n",
+ tsk->signal->group_exit_code ?: (int)code);
+
#ifdef CONFIG_POSIX_TIMERS
hrtimer_cancel(&tsk->signal->real_timer);
exit_itimers(tsk->signal);
diff --git a/kernel/locking/spinlock_debug.c b/kernel/locking/spinlock_debug.c
index 399669f7eba8..472dd462a40c 100644
--- a/kernel/locking/spinlock_debug.c
+++ b/kernel/locking/spinlock_debug.c
@@ -51,19 +51,19 @@ EXPORT_SYMBOL(__rwlock_init);
static void spin_dump(raw_spinlock_t *lock, const char *msg)
{
- struct task_struct *owner = NULL;
+ struct task_struct *owner = READ_ONCE(lock->owner);
- if (lock->owner && lock->owner != SPINLOCK_OWNER_INIT)
- owner = lock->owner;
+ if (owner == SPINLOCK_OWNER_INIT)
+ owner = NULL;
printk(KERN_EMERG "BUG: spinlock %s on CPU#%d, %s/%d\n",
msg, raw_smp_processor_id(),
current->comm, task_pid_nr(current));
printk(KERN_EMERG " lock: %pS, .magic: %08x, .owner: %s/%d, "
".owner_cpu: %d\n",
- lock, lock->magic,
+ lock, READ_ONCE(lock->magic),
owner ? owner->comm : "<none>",
owner ? task_pid_nr(owner) : -1,
- lock->owner_cpu);
+ READ_ONCE(lock->owner_cpu));
dump_stack();
}
@@ -80,16 +80,16 @@ static void spin_bug(raw_spinlock_t *lock, const char *msg)
static inline void
debug_spin_lock_before(raw_spinlock_t *lock)
{
- SPIN_BUG_ON(lock->magic != SPINLOCK_MAGIC, lock, "bad magic");
- SPIN_BUG_ON(lock->owner == current, lock, "recursion");
- SPIN_BUG_ON(lock->owner_cpu == raw_smp_processor_id(),
+ SPIN_BUG_ON(READ_ONCE(lock->magic) != SPINLOCK_MAGIC, lock, "bad magic");
+ SPIN_BUG_ON(READ_ONCE(lock->owner) == current, lock, "recursion");
+ SPIN_BUG_ON(READ_ONCE(lock->owner_cpu) == raw_smp_processor_id(),
lock, "cpu recursion");
}
static inline void debug_spin_lock_after(raw_spinlock_t *lock)
{
- lock->owner_cpu = raw_smp_processor_id();
- lock->owner = current;
+ WRITE_ONCE(lock->owner_cpu, raw_smp_processor_id());
+ WRITE_ONCE(lock->owner, current);
}
static inline void debug_spin_unlock(raw_spinlock_t *lock)
@@ -99,8 +99,8 @@ static inline void debug_spin_unlock(raw_spinlock_t *lock)
SPIN_BUG_ON(lock->owner != current, lock, "wrong owner");
SPIN_BUG_ON(lock->owner_cpu != raw_smp_processor_id(),
lock, "wrong CPU");
- lock->owner = SPINLOCK_OWNER_INIT;
- lock->owner_cpu = -1;
+ WRITE_ONCE(lock->owner, SPINLOCK_OWNER_INIT);
+ WRITE_ONCE(lock->owner_cpu, -1);
}
/*
@@ -187,8 +187,8 @@ static inline void debug_write_lock_before(rwlock_t *lock)
static inline void debug_write_lock_after(rwlock_t *lock)
{
- lock->owner_cpu = raw_smp_processor_id();
- lock->owner = current;
+ WRITE_ONCE(lock->owner_cpu, raw_smp_processor_id());
+ WRITE_ONCE(lock->owner, current);
}
static inline void debug_write_unlock(rwlock_t *lock)
@@ -197,8 +197,8 @@ static inline void debug_write_unlock(rwlock_t *lock)
RWLOCK_BUG_ON(lock->owner != current, lock, "wrong owner");
RWLOCK_BUG_ON(lock->owner_cpu != raw_smp_processor_id(),
lock, "wrong CPU");
- lock->owner = SPINLOCK_OWNER_INIT;
- lock->owner_cpu = -1;
+ WRITE_ONCE(lock->owner, SPINLOCK_OWNER_INIT);
+ WRITE_ONCE(lock->owner_cpu, -1);
}
void do_raw_write_lock(rwlock_t *lock)
diff --git a/kernel/module.c b/kernel/module.c
index dcf2cc656e7c..b11d200aebbd 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1019,6 +1019,8 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user,
strlcpy(last_unloaded_module, mod->name, sizeof(last_unloaded_module));
free_module(mod);
+ /* someone could wait for the module in add_unformed_module() */
+ wake_up_all(&module_wq);
return 0;
out:
mutex_unlock(&module_mutex);
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 83105874f255..26b9168321e7 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -734,8 +734,15 @@ zone_found:
* We have found the zone. Now walk the radix tree to find the leaf node
* for our PFN.
*/
+
+ /*
+ * If the zone we wish to scan is the the current zone and the
+ * pfn falls into the current node then we do not need to walk
+ * the tree.
+ */
node = bm->cur.node;
- if (((pfn - zone->start_pfn) & ~BM_BLOCK_MASK) == bm->cur.node_pfn)
+ if (zone == bm->cur.zone &&
+ ((pfn - zone->start_pfn) & ~BM_BLOCK_MASK) == bm->cur.node_pfn)
goto node_found;
node = zone->rtree;
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index 517e3719027e..ce8f6748678a 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -185,7 +185,8 @@ static void group_init(struct psi_group *group)
for_each_possible_cpu(cpu)
seqcount_init(&per_cpu_ptr(group->pcpu, cpu)->seq);
- group->avg_next_update = sched_clock() + psi_period;
+ group->avg_last_update = sched_clock();
+ group->avg_next_update = group->avg_last_update + psi_period;
INIT_DELAYED_WORK(&group->avgs_work, psi_avgs_work);
mutex_init(&group->avgs_lock);
/* Init trigger-related members */
@@ -481,7 +482,7 @@ static u64 window_update(struct psi_window *win, u64 now, u64 value)
u32 remaining;
remaining = win->size - elapsed;
- growth += div_u64(win->prev_growth * remaining, win->size);
+ growth += div64_u64(win->prev_growth * remaining, win->size);
}
return growth;
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index 13a0f2e6ebc2..e2ac0e37c4ae 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -554,25 +554,33 @@ static int taskstats_user_cmd(struct sk_buff *skb, struct genl_info *info)
static struct taskstats *taskstats_tgid_alloc(struct task_struct *tsk)
{
struct signal_struct *sig = tsk->signal;
- struct taskstats *stats;
+ struct taskstats *stats_new, *stats;
- if (sig->stats || thread_group_empty(tsk))
- goto ret;
+ /* Pairs with smp_store_release() below. */
+ stats = smp_load_acquire(&sig->stats);
+ if (stats || thread_group_empty(tsk))
+ return stats;
/* No problem if kmem_cache_zalloc() fails */
- stats = kmem_cache_zalloc(taskstats_cache, GFP_KERNEL);
+ stats_new = kmem_cache_zalloc(taskstats_cache, GFP_KERNEL);
spin_lock_irq(&tsk->sighand->siglock);
- if (!sig->stats) {
- sig->stats = stats;
- stats = NULL;
+ stats = sig->stats;
+ if (!stats) {
+ /*
+ * Pairs with smp_store_release() above and order the
+ * kmem_cache_zalloc().
+ */
+ smp_store_release(&sig->stats, stats_new);
+ stats = stats_new;
+ stats_new = NULL;
}
spin_unlock_irq(&tsk->sighand->siglock);
- if (stats)
- kmem_cache_free(taskstats_cache, stats);
-ret:
- return sig->stats;
+ if (stats_new)
+ kmem_cache_free(taskstats_cache, stats_new);
+
+ return stats;
}
/* Send pid data out on exit */
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index baa54a76c6aa..018aa2211c2d 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -523,8 +523,7 @@ static int function_stat_show(struct seq_file *m, void *v)
}
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- avg = rec->time;
- do_div(avg, rec->counter);
+ avg = div64_ul(rec->time, rec->counter);
if (tracing_thresh && (avg < tracing_thresh))
goto out;
#endif
@@ -550,7 +549,8 @@ static int function_stat_show(struct seq_file *m, void *v)
* Divide only 1000 for ns^2 -> us^2 conversion.
* trace_print_graph_duration will divide 1000 again.
*/
- do_div(stddev, rec->counter * (rec->counter - 1) * 1000);
+ stddev = div64_ul(stddev,
+ rec->counter * (rec->counter - 1) * 1000);
}
trace_seq_init(&s);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 51a64fbd8bd0..74fa91ab7608 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4569,6 +4569,10 @@ int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set)
int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled)
{
+ if ((mask == TRACE_ITER_RECORD_TGID) ||
+ (mask == TRACE_ITER_RECORD_CMD))
+ lockdep_assert_held(&event_mutex);
+
/* do nothing if flag is already set */
if (!!(tr->trace_flags & mask) == !!enabled)
return 0;
@@ -4636,6 +4640,7 @@ static int trace_set_options(struct trace_array *tr, char *option)
cmp += len;
+ mutex_lock(&event_mutex);
mutex_lock(&trace_types_lock);
ret = match_string(trace_options, -1, cmp);
@@ -4646,6 +4651,7 @@ static int trace_set_options(struct trace_array *tr, char *option)
ret = set_tracer_flag(tr, 1 << ret, !neg);
mutex_unlock(&trace_types_lock);
+ mutex_unlock(&event_mutex);
/*
* If the first trailing whitespace is replaced with '\0' by strstrip,
@@ -7948,9 +7954,11 @@ trace_options_core_write(struct file *filp, const char __user *ubuf, size_t cnt,
if (val != 0 && val != 1)
return -EINVAL;
+ mutex_lock(&event_mutex);
mutex_lock(&trace_types_lock);
ret = set_tracer_flag(tr, 1 << index, val);
mutex_unlock(&trace_types_lock);
+ mutex_unlock(&event_mutex);
if (ret < 0)
return ret;
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 0ce3db67f556..f9ca020e8a51 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -327,7 +327,8 @@ void trace_event_enable_cmd_record(bool enable)
struct trace_event_file *file;
struct trace_array *tr;
- mutex_lock(&event_mutex);
+ lockdep_assert_held(&event_mutex);
+
do_for_each_event_file(tr, file) {
if (!(file->flags & EVENT_FILE_FL_ENABLED))
@@ -341,7 +342,6 @@ void trace_event_enable_cmd_record(bool enable)
clear_bit(EVENT_FILE_FL_RECORDED_CMD_BIT, &file->flags);
}
} while_for_each_event_file();
- mutex_unlock(&event_mutex);
}
void trace_event_enable_tgid_record(bool enable)
@@ -349,7 +349,8 @@ void trace_event_enable_tgid_record(bool enable)
struct trace_event_file *file;
struct trace_array *tr;
- mutex_lock(&event_mutex);
+ lockdep_assert_held(&event_mutex);
+
do_for_each_event_file(tr, file) {
if (!(file->flags & EVENT_FILE_FL_ENABLED))
continue;
@@ -363,7 +364,6 @@ void trace_event_enable_tgid_record(bool enable)
&file->flags);
}
} while_for_each_event_file();
- mutex_unlock(&event_mutex);
}
static int __ftrace_event_enable_disable(struct trace_event_file *file,
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index d5a4bda9ce7b..b878d0ec8181 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -1659,7 +1659,7 @@ static int process_system_preds(struct trace_subsystem_dir *dir,
parse_error(pe, FILT_ERR_BAD_SUBSYS_FILTER, 0);
return -EINVAL;
fail_mem:
- kfree(filter);
+ __free_filter(filter);
/* If any call succeeded, we still need to sync */
if (!fail)
tracepoint_synchronize_unregister();
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 725b9b35f933..3a03b5dd1419 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -891,7 +891,26 @@ static notrace void trace_event_raw_event_synth(void *__data,
strscpy(str_field, str_val, STR_VAR_LEN_MAX);
n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
} else {
- entry->fields[n_u64] = var_ref_vals[var_ref_idx + i];
+ struct synth_field *field = event->fields[i];
+ u64 val = var_ref_vals[var_ref_idx + i];
+
+ switch (field->size) {
+ case 1:
+ *(u8 *)&entry->fields[n_u64] = (u8)val;
+ break;
+
+ case 2:
+ *(u16 *)&entry->fields[n_u64] = (u16)val;
+ break;
+
+ case 4:
+ *(u32 *)&entry->fields[n_u64] = (u32)val;
+ break;
+
+ default:
+ entry->fields[n_u64] = val;
+ break;
+ }
n_u64++;
}
}
diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c
index 9a1c22310323..9e31bfc818ff 100644
--- a/kernel/trace/tracing_map.c
+++ b/kernel/trace/tracing_map.c
@@ -148,8 +148,8 @@ static int tracing_map_cmp_atomic64(void *val_a, void *val_b)
#define DEFINE_TRACING_MAP_CMP_FN(type) \
static int tracing_map_cmp_##type(void *val_a, void *val_b) \
{ \
- type a = *(type *)val_a; \
- type b = *(type *)val_b; \
+ type a = (type)(*(u64 *)val_a); \
+ type b = (type)(*(u64 *)val_b); \
\
return (a > b) ? 1 : ((a < b) ? -1 : 0); \
}
generated by cgit 1.2.3-korg (git 2.39.0) at 2024-05-02 15:52:15 +0000