aboutsummaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/btf.c1
-rw-r--r--kernel/bpf/cgroup.c2
-rw-r--r--kernel/bpf/core.c17
-rw-r--r--kernel/bpf/local_storage.c28
-rw-r--r--kernel/bpf/trampoline.c64
-rw-r--r--kernel/bpf/verifier.c24
-rw-r--r--kernel/events/core.c2
-rw-r--r--kernel/locking/mutex.c4
-rw-r--r--kernel/locking/spinlock_debug.c32
-rw-r--r--kernel/module.c6
-rw-r--r--kernel/sched/cpufreq.c18
-rw-r--r--kernel/sched/cpufreq_schedutil.c8
-rw-r--r--kernel/sched/fair.c13
-rw-r--r--kernel/sched/psi.c5
-rw-r--r--kernel/trace/fgraph.c9
-rw-r--r--kernel/trace/ftrace.c19
-rw-r--r--kernel/trace/ring_buffer.c2
-rw-r--r--kernel/trace/trace.c14
-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/trace_events_inject.c2
-rw-r--r--kernel/trace/tracing_map.c4
-rw-r--r--kernel/workqueue.c4
24 files changed, 206 insertions, 103 deletions
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 7d40da240891..ed2075884724 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -3470,6 +3470,7 @@ static u8 bpf_ctx_convert_map[] = {
[_id] = __ctx_convert##_id,
#include <linux/bpf_types.h>
#undef BPF_PROG_TYPE
+ 0, /* avoid empty array */
};
#undef BPF_MAP_TYPE
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 45346c79613a..ee871d4a51f7 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -1346,7 +1346,7 @@ static u32 sysctl_convert_ctx_access(enum bpf_access_type type,
*insn++ = BPF_LDX_MEM(
BPF_SIZE(si->code), si->dst_reg, si->src_reg,
bpf_target_off(struct bpf_sysctl_kern, write,
- FIELD_SIZEOF(struct bpf_sysctl_kern,
+ sizeof_field(struct bpf_sysctl_kern,
write),
target_size));
break;
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 7622dfc36705..29d47aae0dd1 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2041,23 +2041,28 @@ static void bpf_free_cgroup_storage(struct bpf_prog_aux *aux)
for_each_cgroup_storage_type(stype) {
if (!aux->cgroup_storage[stype])
continue;
- bpf_cgroup_storage_release(aux->prog,
- aux->cgroup_storage[stype]);
+ bpf_cgroup_storage_release(aux, aux->cgroup_storage[stype]);
}
}
-static void bpf_free_used_maps(struct bpf_prog_aux *aux)
+void __bpf_free_used_maps(struct bpf_prog_aux *aux,
+ struct bpf_map **used_maps, u32 len)
{
struct bpf_map *map;
- int i;
+ u32 i;
bpf_free_cgroup_storage(aux);
- for (i = 0; i < aux->used_map_cnt; i++) {
- map = aux->used_maps[i];
+ for (i = 0; i < len; i++) {
+ map = used_maps[i];
if (map->ops->map_poke_untrack)
map->ops->map_poke_untrack(map, aux);
bpf_map_put(map);
}
+}
+
+static void bpf_free_used_maps(struct bpf_prog_aux *aux)
+{
+ __bpf_free_used_maps(aux, aux->used_maps, aux->used_map_cnt);
kfree(aux->used_maps);
}
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index 2ba750725cb2..33d01866bcc2 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -20,7 +20,7 @@ struct bpf_cgroup_storage_map {
struct bpf_map map;
spinlock_t lock;
- struct bpf_prog *prog;
+ struct bpf_prog_aux *aux;
struct rb_root root;
struct list_head list;
};
@@ -357,7 +357,7 @@ static int cgroup_storage_check_btf(const struct bpf_map *map,
* The first field must be a 64 bit integer at 0 offset.
*/
m = (struct btf_member *)(key_type + 1);
- size = FIELD_SIZEOF(struct bpf_cgroup_storage_key, cgroup_inode_id);
+ size = sizeof_field(struct bpf_cgroup_storage_key, cgroup_inode_id);
if (!btf_member_is_reg_int(btf, key_type, m, 0, size))
return -EINVAL;
@@ -366,7 +366,7 @@ static int cgroup_storage_check_btf(const struct bpf_map *map,
*/
m++;
offset = offsetof(struct bpf_cgroup_storage_key, attach_type);
- size = FIELD_SIZEOF(struct bpf_cgroup_storage_key, attach_type);
+ size = sizeof_field(struct bpf_cgroup_storage_key, attach_type);
if (!btf_member_is_reg_int(btf, key_type, m, offset, size))
return -EINVAL;
@@ -420,7 +420,7 @@ const struct bpf_map_ops cgroup_storage_map_ops = {
.map_seq_show_elem = cgroup_storage_seq_show_elem,
};
-int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *_map)
+int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *_map)
{
enum bpf_cgroup_storage_type stype = cgroup_storage_type(_map);
struct bpf_cgroup_storage_map *map = map_to_storage(_map);
@@ -428,14 +428,14 @@ int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *_map)
spin_lock_bh(&map->lock);
- if (map->prog && map->prog != prog)
+ if (map->aux && map->aux != aux)
goto unlock;
- if (prog->aux->cgroup_storage[stype] &&
- prog->aux->cgroup_storage[stype] != _map)
+ if (aux->cgroup_storage[stype] &&
+ aux->cgroup_storage[stype] != _map)
goto unlock;
- map->prog = prog;
- prog->aux->cgroup_storage[stype] = _map;
+ map->aux = aux;
+ aux->cgroup_storage[stype] = _map;
ret = 0;
unlock:
spin_unlock_bh(&map->lock);
@@ -443,16 +443,16 @@ unlock:
return ret;
}
-void bpf_cgroup_storage_release(struct bpf_prog *prog, struct bpf_map *_map)
+void bpf_cgroup_storage_release(struct bpf_prog_aux *aux, struct bpf_map *_map)
{
enum bpf_cgroup_storage_type stype = cgroup_storage_type(_map);
struct bpf_cgroup_storage_map *map = map_to_storage(_map);
spin_lock_bh(&map->lock);
- if (map->prog == prog) {
- WARN_ON(prog->aux->cgroup_storage[stype] != _map);
- map->prog = NULL;
- prog->aux->cgroup_storage[stype] = NULL;
+ if (map->aux == aux) {
+ WARN_ON(aux->cgroup_storage[stype] != _map);
+ map->aux = NULL;
+ aux->cgroup_storage[stype] = NULL;
}
spin_unlock_bh(&map->lock);
}
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 5ee301ddbd00..505f4e4b31d2 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -3,6 +3,7 @@
#include <linux/hash.h>
#include <linux/bpf.h>
#include <linux/filter.h>
+#include <linux/ftrace.h>
/* btf_vmlinux has ~22k attachable functions. 1k htab is enough. */
#define TRAMPOLINE_HASH_BITS 10
@@ -69,6 +70,60 @@ out:
return tr;
}
+static int is_ftrace_location(void *ip)
+{
+ long addr;
+
+ addr = ftrace_location((long)ip);
+ if (!addr)
+ return 0;
+ if (WARN_ON_ONCE(addr != (long)ip))
+ return -EFAULT;
+ return 1;
+}
+
+static int unregister_fentry(struct bpf_trampoline *tr, void *old_addr)
+{
+ void *ip = tr->func.addr;
+ int ret;
+
+ if (tr->func.ftrace_managed)
+ ret = unregister_ftrace_direct((long)ip, (long)old_addr);
+ else
+ ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, old_addr, NULL);
+ return ret;
+}
+
+static int modify_fentry(struct bpf_trampoline *tr, void *old_addr, void *new_addr)
+{
+ void *ip = tr->func.addr;
+ int ret;
+
+ if (tr->func.ftrace_managed)
+ ret = modify_ftrace_direct((long)ip, (long)old_addr, (long)new_addr);
+ else
+ ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, old_addr, new_addr);
+ return ret;
+}
+
+/* first time registering */
+static int register_fentry(struct bpf_trampoline *tr, void *new_addr)
+{
+ void *ip = tr->func.addr;
+ int ret;
+
+ ret = is_ftrace_location(ip);
+ if (ret < 0)
+ return ret;
+ tr->func.ftrace_managed = ret;
+
+ if (tr->func.ftrace_managed)
+ ret = register_ftrace_direct((long)ip, (long)new_addr);
+ else
+ ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, NULL, new_addr);
+ return ret;
+}
+
/* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50
* bytes on x86. Pick a number to fit into PAGE_SIZE / 2
*/
@@ -87,8 +142,7 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr)
int err;
if (fentry_cnt + fexit_cnt == 0) {
- err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_CALL,
- old_image, NULL);
+ err = unregister_fentry(tr, old_image);
tr->selector = 0;
goto out;
}
@@ -115,12 +169,10 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr)
if (tr->selector)
/* progs already running at this address */
- err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_CALL,
- old_image, new_image);
+ err = modify_fentry(tr, old_image, new_image);
else
/* first time registering */
- err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_CALL, NULL,
- new_image);
+ err = register_fentry(tr, new_image);
if (err)
goto out;
tr->selector++;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 034ef81f935b..4983940cbdca 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -4134,6 +4134,7 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
struct bpf_map *map = meta->map_ptr;
struct tnum range;
u64 val;
+ int err;
if (func_id != BPF_FUNC_tail_call)
return 0;
@@ -4150,6 +4151,10 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
return 0;
}
+ err = mark_chain_precision(env, BPF_REG_3);
+ if (err)
+ return err;
+
val = reg->var_off.value;
if (bpf_map_key_unseen(aux))
bpf_map_key_store(aux, val);
@@ -8268,7 +8273,7 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env)
env->used_maps[env->used_map_cnt++] = map;
if (bpf_map_is_cgroup_storage(map) &&
- bpf_cgroup_storage_assign(env->prog, map)) {
+ bpf_cgroup_storage_assign(env->prog->aux, map)) {
verbose(env, "only one cgroup storage of each type is allowed\n");
fdput(f);
return -EBUSY;
@@ -8298,18 +8303,8 @@ next_insn:
/* drop refcnt of maps used by the rejected program */
static void release_maps(struct bpf_verifier_env *env)
{
- enum bpf_cgroup_storage_type stype;
- int i;
-
- for_each_cgroup_storage_type(stype) {
- if (!env->prog->aux->cgroup_storage[stype])
- continue;
- bpf_cgroup_storage_release(env->prog,
- env->prog->aux->cgroup_storage[stype]);
- }
-
- for (i = 0; i < env->used_map_cnt; i++)
- bpf_map_put(env->used_maps[i]);
+ __bpf_free_used_maps(env->prog->aux, env->used_maps,
+ env->used_map_cnt);
}
/* convert pseudo BPF_LD_IMM64 into generic BPF_LD_IMM64 */
@@ -9282,7 +9277,8 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
insn->code = BPF_JMP | BPF_TAIL_CALL;
aux = &env->insn_aux_data[i + delta];
- if (prog->jit_requested && !expect_blinding &&
+ if (env->allow_ptr_leaks && !expect_blinding &&
+ prog->jit_requested &&
!bpf_map_key_poisoned(aux) &&
!bpf_map_ptr_poisoned(aux) &&
!bpf_map_ptr_unpriv(aux)) {
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 4ff86d57f9e5..a1f8bde19b56 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -10523,7 +10523,7 @@ again:
goto unlock;
}
- list_for_each_entry_rcu(pmu, &pmus, entry) {
+ list_for_each_entry_rcu(pmu, &pmus, entry, lockdep_is_held(&pmus_srcu)) {
ret = perf_try_init_event(pmu, event);
if (!ret)
goto unlock;
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 54cc5f9286e9..5352ce50a97e 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -733,9 +733,6 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
*/
void __sched mutex_unlock(struct mutex *lock)
{
-#ifdef CONFIG_DEBUG_MUTEXES
- WARN_ON(in_interrupt());
-#endif
#ifndef CONFIG_DEBUG_LOCK_ALLOC
if (__mutex_unlock_fast(lock))
return;
@@ -1416,7 +1413,6 @@ int __sched mutex_trylock(struct mutex *lock)
#ifdef CONFIG_DEBUG_MUTEXES
DEBUG_LOCKS_WARN_ON(lock->magic != lock);
- WARN_ON(in_interrupt());
#endif
locked = __mutex_trylock(lock);
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 3a486f826224..b56f3224b161 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -3730,6 +3730,7 @@ static int complete_formation(struct module *mod, struct load_info *info)
module_enable_ro(mod, false);
module_enable_nx(mod);
+ module_enable_x(mod);
/* Mark state as coming so strong_try_module_get() ignores us,
* but kallsyms etc. can see us. */
@@ -3752,11 +3753,6 @@ static int prepare_coming_module(struct module *mod)
if (err)
return err;
- /* Make module executable after ftrace is enabled */
- mutex_lock(&module_mutex);
- module_enable_x(mod);
- mutex_unlock(&module_mutex);
-
blocking_notifier_call_chain(&module_notify_list,
MODULE_STATE_COMING, mod);
return 0;
diff --git a/kernel/sched/cpufreq.c b/kernel/sched/cpufreq.c
index b5dcd1d83c7f..7c2fe50fd76d 100644
--- a/kernel/sched/cpufreq.c
+++ b/kernel/sched/cpufreq.c
@@ -5,6 +5,8 @@
* Copyright (C) 2016, Intel Corporation
* Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
*/
+#include <linux/cpufreq.h>
+
#include "sched.h"
DEFINE_PER_CPU(struct update_util_data __rcu *, cpufreq_update_util_data);
@@ -57,3 +59,19 @@ void cpufreq_remove_update_util_hook(int cpu)
rcu_assign_pointer(per_cpu(cpufreq_update_util_data, cpu), NULL);
}
EXPORT_SYMBOL_GPL(cpufreq_remove_update_util_hook);
+
+/**
+ * cpufreq_this_cpu_can_update - Check if cpufreq policy can be updated.
+ * @policy: cpufreq policy to check.
+ *
+ * Return 'true' if:
+ * - the local and remote CPUs share @policy,
+ * - dvfs_possible_from_any_cpu is set in @policy and the local CPU is not going
+ * offline (in which case it is not expected to run cpufreq updates any more).
+ */
+bool cpufreq_this_cpu_can_update(struct cpufreq_policy *policy)
+{
+ return cpumask_test_cpu(smp_processor_id(), policy->cpus) ||
+ (policy->dvfs_possible_from_any_cpu &&
+ rcu_dereference_sched(*this_cpu_ptr(&cpufreq_update_util_data)));
+}
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 322ca8860f54..9b8916fd00a2 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -82,12 +82,10 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time)
* by the hardware, as calculating the frequency is pointless if
* we cannot in fact act on it.
*
- * For the slow switching platforms, the kthread is always scheduled on
- * the right set of CPUs and any CPU can find the next frequency and
- * schedule the kthread.
+ * This is needed on the slow switching platforms too to prevent CPUs
+ * going offline from leaving stale IRQ work items behind.
*/
- if (sg_policy->policy->fast_switch_enabled &&
- !cpufreq_this_cpu_can_update(sg_policy->policy))
+ if (!cpufreq_this_cpu_can_update(sg_policy->policy))
return false;
if (unlikely(sg_policy->limits_changed)) {
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 08a233e97a01..ba749f579714 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7328,7 +7328,14 @@ static int detach_tasks(struct lb_env *env)
load < 16 && !env->sd->nr_balance_failed)
goto next;
- if (load/2 > env->imbalance)
+ /*
+ * Make sure that we don't migrate too much load.
+ * Nevertheless, let relax the constraint if
+ * scheduler fails to find a good waiting task to
+ * migrate.
+ */
+ if (load/2 > env->imbalance &&
+ env->sd->nr_balance_failed <= env->sd->cache_nice_tries)
goto next;
env->imbalance -= load;
@@ -8417,6 +8424,10 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
if (!idlest)
return NULL;
+ /* The local group has been skipped because of CPU affinity */
+ if (!local)
+ return idlest;
+
/*
* If the local group is idler than the selected idlest group
* don't try and push the task.
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/trace/fgraph.c b/kernel/trace/fgraph.c
index 67e0c462b059..a2659735db73 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -101,6 +101,15 @@ int function_graph_enter(unsigned long ret, unsigned long func,
{
struct ftrace_graph_ent trace;
+ /*
+ * Skip graph tracing if the return location is served by direct trampoline,
+ * since call sequence and return addresses is unpredicatable anymore.
+ * Ex: BPF trampoline may call original function and may skip frame
+ * depending on type of BPF programs attached.
+ */
+ if (ftrace_direct_func_count &&
+ ftrace_find_rec_direct(ret - MCOUNT_INSN_SIZE))
+ return -EBUSY;
trace.func = func;
trace.depth = ++current->curr_ret_depth;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 74439ab5c2b6..ac99a3500076 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -2364,7 +2364,7 @@ int ftrace_direct_func_count;
* Search the direct_functions hash to see if the given instruction pointer
* has a direct caller attached to it.
*/
-static unsigned long find_rec_direct(unsigned long ip)
+unsigned long ftrace_find_rec_direct(unsigned long ip)
{
struct ftrace_func_entry *entry;
@@ -2380,7 +2380,7 @@ static void call_direct_funcs(unsigned long ip, unsigned long pip,
{
unsigned long addr;
- addr = find_rec_direct(ip);
+ addr = ftrace_find_rec_direct(ip);
if (!addr)
return;
@@ -2393,11 +2393,6 @@ struct ftrace_ops direct_ops = {
| FTRACE_OPS_FL_DIRECT | FTRACE_OPS_FL_SAVE_REGS
| FTRACE_OPS_FL_PERMANENT,
};
-#else
-static inline unsigned long find_rec_direct(unsigned long ip)
-{
- return 0;
-}
#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
/**
@@ -2417,7 +2412,7 @@ unsigned long ftrace_get_addr_new(struct dyn_ftrace *rec)
if ((rec->flags & FTRACE_FL_DIRECT) &&
(ftrace_rec_count(rec) == 1)) {
- addr = find_rec_direct(rec->ip);
+ addr = ftrace_find_rec_direct(rec->ip);
if (addr)
return addr;
WARN_ON_ONCE(1);
@@ -2458,7 +2453,7 @@ unsigned long ftrace_get_addr_curr(struct dyn_ftrace *rec)
/* Direct calls take precedence over trampolines */
if (rec->flags & FTRACE_FL_DIRECT_EN) {
- addr = find_rec_direct(rec->ip);
+ addr = ftrace_find_rec_direct(rec->ip);
if (addr)
return addr;
WARN_ON_ONCE(1);
@@ -3604,7 +3599,7 @@ static int t_show(struct seq_file *m, void *v)
if (rec->flags & FTRACE_FL_DIRECT) {
unsigned long direct;
- direct = find_rec_direct(rec->ip);
+ direct = ftrace_find_rec_direct(rec->ip);
if (direct)
seq_printf(m, "\n\tdirect-->%pS", (void *)direct);
}
@@ -5008,7 +5003,7 @@ int register_ftrace_direct(unsigned long ip, unsigned long addr)
mutex_lock(&direct_mutex);
/* See if there's a direct function at @ip already */
- if (find_rec_direct(ip))
+ if (ftrace_find_rec_direct(ip))
goto out_unlock;
ret = -ENODEV;
@@ -5027,7 +5022,7 @@ int register_ftrace_direct(unsigned long ip, unsigned long addr)
if (ip != rec->ip) {
ip = rec->ip;
/* Need to check this ip for a direct. */
- if (find_rec_direct(ip))
+ if (ftrace_find_rec_direct(ip))
goto out_unlock;
}
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 4bf050fcfe3b..3f655371eaf6 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -5070,7 +5070,7 @@ static __init int test_ringbuffer(void)
int ret = 0;
if (security_locked_down(LOCKDOWN_TRACEFS)) {
- pr_warning("Lockdown is enabled, skipping ring buffer tests\n");
+ pr_warn("Lockdown is enabled, skipping ring buffer tests\n");
return 0;
}
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 23459d53d576..ddb7e7f5fe8d 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1889,7 +1889,7 @@ int __init register_tracer(struct tracer *type)
}
if (security_locked_down(LOCKDOWN_TRACEFS)) {
- pr_warning("Can not register tracer %s due to lockdown\n",
+ pr_warn("Can not register tracer %s due to lockdown\n",
type->name);
return -EPERM;
}
@@ -4685,6 +4685,10 @@ 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;
@@ -4752,6 +4756,7 @@ 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);
@@ -4762,6 +4767,7 @@ 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,
@@ -8076,9 +8082,11 @@ 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;
@@ -8796,7 +8804,7 @@ struct dentry *tracing_init_dentry(void)
struct trace_array *tr = &global_trace;
if (security_locked_down(LOCKDOWN_TRACEFS)) {
- pr_warning("Tracing disabled due to lockdown\n");
+ pr_warn("Tracing disabled due to lockdown\n");
return ERR_PTR(-EPERM);
}
@@ -9244,7 +9252,7 @@ __init static int tracer_alloc_buffers(void)
if (security_locked_down(LOCKDOWN_TRACEFS)) {
- pr_warning("Tracing disabled due to lockdown\n");
+ pr_warn("Tracing disabled due to lockdown\n");
return -EPERM;
}
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index c6de3cebc127..a5b614cc3887 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -320,7 +320,8 @@ 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))
@@ -334,7 +335,6 @@ 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)
@@ -342,7 +342,8 @@ 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;
@@ -356,7 +357,6 @@ 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 c9a74f82b14a..bf44f6bbd0c3 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -1662,7 +1662,7 @@ 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 f49d1a36d3ae..f62de5f43e79 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -911,7 +911,26 @@ 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/trace_events_inject.c b/kernel/trace/trace_events_inject.c
index d43710718ee5..d45079ee62f8 100644
--- a/kernel/trace/trace_events_inject.c
+++ b/kernel/trace/trace_events_inject.c
@@ -17,12 +17,10 @@ static int
trace_inject_entry(struct trace_event_file *file, void *rec, int len)
{
struct trace_event_buffer fbuffer;
- struct ring_buffer *buffer;
int written = 0;
void *entry;
rcu_read_lock_sched();
- buffer = file->tr->trace_buffer.buffer;
entry = trace_event_buffer_reserve(&fbuffer, file, len);
if (entry) {
memcpy(entry, rec, len);
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); \
}
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index bc88fd939f4e..cfc923558e04 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -4374,8 +4374,8 @@ void destroy_workqueue(struct workqueue_struct *wq)
for_each_pwq(pwq, wq) {
spin_lock_irq(&pwq->pool->lock);
if (WARN_ON(pwq_busy(pwq))) {
- pr_warning("%s: %s has the following busy pwq\n",
- __func__, wq->name);
+ pr_warn("%s: %s has the following busy pwq\n",
+ __func__, wq->name);
show_pwq(pwq);
spin_unlock_irq(&pwq->pool->lock);
mutex_unlock(&wq->mutex);
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.