summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/auditsc.c4
-rw-r--r--kernel/bpf/bpf_lsm.c1
-rw-r--r--kernel/bpf/btf.c4
-rw-r--r--kernel/bpf/inode.c8
-rw-r--r--kernel/bpf/memalloc.c2
-rw-r--r--kernel/bpf/verifier.c25
-rw-r--r--kernel/capability.c10
-rw-r--r--kernel/cgroup/cgroup.c2
-rw-r--r--kernel/cgroup/cpuset.c48
-rw-r--r--kernel/events/core.c39
-rw-r--r--kernel/irq/irqdomain.c2
-rw-r--r--kernel/locking/rtmutex.c5
-rw-r--r--kernel/sched/core.c5
-rw-r--r--kernel/sched/psi.c7
-rw-r--r--kernel/time/alarmtimer.c33
-rw-r--r--kernel/trace/bpf_trace.c3
-rw-r--r--kernel/trace/trace.c3
-rw-r--r--kernel/trace/trace.h1
-rw-r--r--kernel/trace/trace_events.c39
-rw-r--r--kernel/trace/trace_export.c3
-rw-r--r--kernel/umh.c20
21 files changed, 177 insertions, 87 deletions
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 547c88be8a28..01e33f2d2b1c 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -2252,7 +2252,7 @@ static inline int audit_copy_fcaps(struct audit_names *name,
if (!dentry)
return 0;
- rc = get_vfs_caps_from_disk(&init_user_ns, dentry, &caps);
+ rc = get_vfs_caps_from_disk(&nop_mnt_idmap, dentry, &caps);
if (rc)
return rc;
@@ -2807,7 +2807,7 @@ int __audit_log_bprm_fcaps(struct linux_binprm *bprm,
ax->d.next = context->aux;
context->aux = (void *)ax;
- get_vfs_caps_from_disk(&init_user_ns,
+ get_vfs_caps_from_disk(&nop_mnt_idmap,
bprm->file->f_path.dentry, &vcaps);
ax->fcap.permitted = vcaps.permitted;
diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c
index a4a41ee3e80b..e14c822f8911 100644
--- a/kernel/bpf/bpf_lsm.c
+++ b/kernel/bpf/bpf_lsm.c
@@ -51,7 +51,6 @@ BTF_SET_END(bpf_lsm_current_hooks)
*/
BTF_SET_START(bpf_lsm_locked_sockopt_hooks)
#ifdef CONFIG_SECURITY_NETWORK
-BTF_ID(func, bpf_lsm_socket_sock_rcv_skb)
BTF_ID(func, bpf_lsm_sock_graft)
BTF_ID(func, bpf_lsm_inet_csk_clone)
BTF_ID(func, bpf_lsm_inet_conn_established)
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index f7dd8af06413..b7017cae6fd1 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -7782,9 +7782,9 @@ int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_c
sort(tab->dtors, tab->cnt, sizeof(tab->dtors[0]), btf_id_cmp_func, NULL);
- return 0;
end:
- btf_free_dtor_kfunc_tab(btf);
+ if (ret)
+ btf_free_dtor_kfunc_tab(btf);
btf_put(btf);
return ret;
}
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 4f841e16779e..9948b542a470 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -122,7 +122,7 @@ static struct inode *bpf_get_inode(struct super_block *sb,
inode->i_mtime = inode->i_atime;
inode->i_ctime = inode->i_atime;
- inode_init_owner(&init_user_ns, inode, dir, mode);
+ inode_init_owner(&nop_mnt_idmap, inode, dir, mode);
return inode;
}
@@ -152,7 +152,7 @@ static void bpf_dentry_finalize(struct dentry *dentry, struct inode *inode,
dir->i_ctime = dir->i_mtime;
}
-static int bpf_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
+static int bpf_mkdir(struct mnt_idmap *idmap, struct inode *dir,
struct dentry *dentry, umode_t mode)
{
struct inode *inode;
@@ -382,7 +382,7 @@ bpf_lookup(struct inode *dir, struct dentry *dentry, unsigned flags)
return simple_lookup(dir, dentry, flags);
}
-static int bpf_symlink(struct user_namespace *mnt_userns, struct inode *dir,
+static int bpf_symlink(struct mnt_idmap *idmap, struct inode *dir,
struct dentry *dentry, const char *target)
{
char *link = kstrdup(target, GFP_USER | __GFP_NOWARN);
@@ -559,7 +559,7 @@ int bpf_obj_get_user(const char __user *pathname, int flags)
static struct bpf_prog *__get_prog_inode(struct inode *inode, enum bpf_prog_type type)
{
struct bpf_prog *prog;
- int ret = inode_permission(&init_user_ns, inode, MAY_READ);
+ int ret = inode_permission(&nop_mnt_idmap, inode, MAY_READ);
if (ret)
return ERR_PTR(ret);
diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index ebcc3dd0fa19..1db156405b68 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -71,7 +71,7 @@ static int bpf_mem_cache_idx(size_t size)
if (size <= 192)
return size_index[(size - 1) / 8] - 1;
- return fls(size - 1) - 1;
+ return fls(size - 1) - 2;
}
#define NUM_CACHES 11
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index dbef0b0967ae..7ee218827259 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -3243,13 +3243,24 @@ static bool __is_pointer_value(bool allow_ptr_leaks,
return reg->type != SCALAR_VALUE;
}
+/* Copy src state preserving dst->parent and dst->live fields */
+static void copy_register_state(struct bpf_reg_state *dst, const struct bpf_reg_state *src)
+{
+ struct bpf_reg_state *parent = dst->parent;
+ enum bpf_reg_liveness live = dst->live;
+
+ *dst = *src;
+ dst->parent = parent;
+ dst->live = live;
+}
+
static void save_register_state(struct bpf_func_state *state,
int spi, struct bpf_reg_state *reg,
int size)
{
int i;
- state->stack[spi].spilled_ptr = *reg;
+ copy_register_state(&state->stack[spi].spilled_ptr, reg);
if (size == BPF_REG_SIZE)
state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN;
@@ -3577,7 +3588,7 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env,
*/
s32 subreg_def = state->regs[dst_regno].subreg_def;
- state->regs[dst_regno] = *reg;
+ copy_register_state(&state->regs[dst_regno], reg);
state->regs[dst_regno].subreg_def = subreg_def;
} else {
for (i = 0; i < size; i++) {
@@ -3598,7 +3609,7 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env,
if (dst_regno >= 0) {
/* restore register state from stack */
- state->regs[dst_regno] = *reg;
+ copy_register_state(&state->regs[dst_regno], reg);
/* mark reg as written since spilled pointer state likely
* has its liveness marks cleared by is_state_visited()
* which resets stack/reg liveness for state transitions
@@ -9592,7 +9603,7 @@ do_sim:
*/
if (!ptr_is_dst_reg) {
tmp = *dst_reg;
- *dst_reg = *ptr_reg;
+ copy_register_state(dst_reg, ptr_reg);
}
ret = sanitize_speculative_path(env, NULL, env->insn_idx + 1,
env->insn_idx);
@@ -10845,7 +10856,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
* to propagate min/max range.
*/
src_reg->id = ++env->id_gen;
- *dst_reg = *src_reg;
+ copy_register_state(dst_reg, src_reg);
dst_reg->live |= REG_LIVE_WRITTEN;
dst_reg->subreg_def = DEF_NOT_SUBREG;
} else {
@@ -10856,7 +10867,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
insn->src_reg);
return -EACCES;
} else if (src_reg->type == SCALAR_VALUE) {
- *dst_reg = *src_reg;
+ copy_register_state(dst_reg, src_reg);
/* Make sure ID is cleared otherwise
* dst_reg min/max could be incorrectly
* propagated into src_reg by find_equal_scalars()
@@ -11655,7 +11666,7 @@ static void find_equal_scalars(struct bpf_verifier_state *vstate,
bpf_for_each_reg_in_vstate(vstate, state, reg, ({
if (reg->type == SCALAR_VALUE && reg->id == known_reg->id)
- *reg = *known_reg;
+ copy_register_state(reg, known_reg);
}));
}
diff --git a/kernel/capability.c b/kernel/capability.c
index 860fd22117c1..339a44dfe2f4 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -486,11 +486,11 @@ EXPORT_SYMBOL(file_ns_capable);
* Return true if the inode uid and gid are within the namespace.
*/
bool privileged_wrt_inode_uidgid(struct user_namespace *ns,
- struct user_namespace *mnt_userns,
+ struct mnt_idmap *idmap,
const struct inode *inode)
{
- return vfsuid_has_mapping(ns, i_uid_into_vfsuid(mnt_userns, inode)) &&
- vfsgid_has_mapping(ns, i_gid_into_vfsgid(mnt_userns, inode));
+ return vfsuid_has_mapping(ns, i_uid_into_vfsuid(idmap, inode)) &&
+ vfsgid_has_mapping(ns, i_gid_into_vfsgid(idmap, inode));
}
/**
@@ -502,13 +502,13 @@ bool privileged_wrt_inode_uidgid(struct user_namespace *ns,
* its own user namespace and that the given inode's uid and gid are
* mapped into the current user namespace.
*/
-bool capable_wrt_inode_uidgid(struct user_namespace *mnt_userns,
+bool capable_wrt_inode_uidgid(struct mnt_idmap *idmap,
const struct inode *inode, int cap)
{
struct user_namespace *ns = current_user_ns();
return ns_capable(ns, cap) &&
- privileged_wrt_inode_uidgid(ns, mnt_userns, inode);
+ privileged_wrt_inode_uidgid(ns, idmap, inode);
}
EXPORT_SYMBOL(capable_wrt_inode_uidgid);
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index c099cf3fa02d..935e8121b21e 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -5065,7 +5065,7 @@ static int cgroup_may_write(const struct cgroup *cgrp, struct super_block *sb)
if (!inode)
return -ENOMEM;
- ret = inode_permission(&init_user_ns, inode, MAY_WRITE);
+ ret = inode_permission(&nop_mnt_idmap, inode, MAY_WRITE);
iput(inode);
return ret;
}
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index a29c0b13706b..ca826bd1eba3 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -1205,12 +1205,13 @@ void rebuild_sched_domains(void)
/**
* update_tasks_cpumask - Update the cpumasks of tasks in the cpuset.
* @cs: the cpuset in which each task's cpus_allowed mask needs to be changed
+ * @new_cpus: the temp variable for the new effective_cpus mask
*
* Iterate through each task of @cs updating its cpus_allowed to the
* effective cpuset's. As this function is called with cpuset_rwsem held,
* cpuset membership stays stable.
*/
-static void update_tasks_cpumask(struct cpuset *cs)
+static void update_tasks_cpumask(struct cpuset *cs, struct cpumask *new_cpus)
{
struct css_task_iter it;
struct task_struct *task;
@@ -1224,7 +1225,10 @@ static void update_tasks_cpumask(struct cpuset *cs)
if (top_cs && (task->flags & PF_KTHREAD) &&
kthread_is_per_cpu(task))
continue;
- set_cpus_allowed_ptr(task, cs->effective_cpus);
+
+ cpumask_and(new_cpus, cs->effective_cpus,
+ task_cpu_possible_mask(task));
+ set_cpus_allowed_ptr(task, new_cpus);
}
css_task_iter_end(&it);
}
@@ -1346,7 +1350,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd,
* A parent can be left with no CPU as long as there is no
* task directly associated with the parent partition.
*/
- if (!cpumask_intersects(cs->cpus_allowed, parent->effective_cpus) &&
+ if (cpumask_subset(parent->effective_cpus, cs->cpus_allowed) &&
partition_is_populated(parent, cs))
return PERR_NOCPUS;
@@ -1509,7 +1513,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd,
spin_unlock_irq(&callback_lock);
if (adding || deleting)
- update_tasks_cpumask(parent);
+ update_tasks_cpumask(parent, tmp->new_cpus);
/*
* Set or clear CS_SCHED_LOAD_BALANCE when partcmd_update, if necessary.
@@ -1661,7 +1665,7 @@ update_parent_subparts:
WARN_ON(!is_in_v2_mode() &&
!cpumask_equal(cp->cpus_allowed, cp->effective_cpus));
- update_tasks_cpumask(cp);
+ update_tasks_cpumask(cp, tmp->new_cpus);
/*
* On legacy hierarchy, if the effective cpumask of any non-
@@ -2309,7 +2313,7 @@ static int update_prstate(struct cpuset *cs, int new_prs)
}
}
- update_tasks_cpumask(parent);
+ update_tasks_cpumask(parent, tmpmask.new_cpus);
if (parent->child_ecpus_count)
update_sibling_cpumasks(parent, cs, &tmpmask);
@@ -2324,6 +2328,7 @@ out:
new_prs = -new_prs;
spin_lock_irq(&callback_lock);
cs->partition_root_state = new_prs;
+ WRITE_ONCE(cs->prs_err, err);
spin_unlock_irq(&callback_lock);
/*
* Update child cpusets, if present.
@@ -3347,7 +3352,7 @@ hotplug_update_tasks_legacy(struct cpuset *cs,
* as the tasks will be migrated to an ancestor.
*/
if (cpus_updated && !cpumask_empty(cs->cpus_allowed))
- update_tasks_cpumask(cs);
+ update_tasks_cpumask(cs, new_cpus);
if (mems_updated && !nodes_empty(cs->mems_allowed))
update_tasks_nodemask(cs);
@@ -3384,7 +3389,7 @@ hotplug_update_tasks(struct cpuset *cs,
spin_unlock_irq(&callback_lock);
if (cpus_updated)
- update_tasks_cpumask(cs);
+ update_tasks_cpumask(cs, new_cpus);
if (mems_updated)
update_tasks_nodemask(cs);
}
@@ -3691,15 +3696,38 @@ void __init cpuset_init_smp(void)
* Description: Returns the cpumask_var_t cpus_allowed of the cpuset
* attached to the specified @tsk. Guaranteed to return some non-empty
* subset of cpu_online_mask, even if this means going outside the
- * tasks cpuset.
+ * tasks cpuset, except when the task is in the top cpuset.
**/
void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
{
unsigned long flags;
+ struct cpuset *cs;
spin_lock_irqsave(&callback_lock, flags);
- guarantee_online_cpus(tsk, pmask);
+ rcu_read_lock();
+
+ cs = task_cs(tsk);
+ if (cs != &top_cpuset)
+ guarantee_online_cpus(tsk, pmask);
+ /*
+ * Tasks in the top cpuset won't get update to their cpumasks
+ * when a hotplug online/offline event happens. So we include all
+ * offline cpus in the allowed cpu list.
+ */
+ if ((cs == &top_cpuset) || cpumask_empty(pmask)) {
+ const struct cpumask *possible_mask = task_cpu_possible_mask(tsk);
+
+ /*
+ * We first exclude cpus allocated to partitions. If there is no
+ * allowable online cpu left, we fall back to all possible cpus.
+ */
+ cpumask_andnot(pmask, possible_mask, top_cpuset.subparts_cpus);
+ if (!cpumask_intersects(pmask, cpu_online_mask))
+ cpumask_copy(pmask, possible_mask);
+ }
+
+ rcu_read_unlock();
spin_unlock_irqrestore(&callback_lock, flags);
}
diff --git a/kernel/events/core.c b/kernel/events/core.c
index d56328e5080e..c4be13e50547 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4813,19 +4813,17 @@ find_get_pmu_context(struct pmu *pmu, struct perf_event_context *ctx,
cpc = per_cpu_ptr(pmu->cpu_pmu_context, event->cpu);
epc = &cpc->epc;
-
+ raw_spin_lock_irq(&ctx->lock);
if (!epc->ctx) {
atomic_set(&epc->refcount, 1);
epc->embedded = 1;
- raw_spin_lock_irq(&ctx->lock);
list_add(&epc->pmu_ctx_entry, &ctx->pmu_ctx_list);
epc->ctx = ctx;
- raw_spin_unlock_irq(&ctx->lock);
} else {
WARN_ON_ONCE(epc->ctx != ctx);
atomic_inc(&epc->refcount);
}
-
+ raw_spin_unlock_irq(&ctx->lock);
return epc;
}
@@ -4896,33 +4894,30 @@ static void free_epc_rcu(struct rcu_head *head)
static void put_pmu_ctx(struct perf_event_pmu_context *epc)
{
+ struct perf_event_context *ctx = epc->ctx;
unsigned long flags;
- if (!atomic_dec_and_test(&epc->refcount))
+ /*
+ * XXX
+ *
+ * lockdep_assert_held(&ctx->mutex);
+ *
+ * can't because of the call-site in _free_event()/put_event()
+ * which isn't always called under ctx->mutex.
+ */
+ if (!atomic_dec_and_raw_lock_irqsave(&epc->refcount, &ctx->lock, flags))
return;
- if (epc->ctx) {
- struct perf_event_context *ctx = epc->ctx;
+ WARN_ON_ONCE(list_empty(&epc->pmu_ctx_entry));
- /*
- * XXX
- *
- * lockdep_assert_held(&ctx->mutex);
- *
- * can't because of the call-site in _free_event()/put_event()
- * which isn't always called under ctx->mutex.
- */
-
- WARN_ON_ONCE(list_empty(&epc->pmu_ctx_entry));
- raw_spin_lock_irqsave(&ctx->lock, flags);
- list_del_init(&epc->pmu_ctx_entry);
- epc->ctx = NULL;
- raw_spin_unlock_irqrestore(&ctx->lock, flags);
- }
+ list_del_init(&epc->pmu_ctx_entry);
+ epc->ctx = NULL;
WARN_ON_ONCE(!list_empty(&epc->pinned_active));
WARN_ON_ONCE(!list_empty(&epc->flexible_active));
+ raw_spin_unlock_irqrestore(&ctx->lock, flags);
+
if (epc->embedded)
return;
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 5c3fb6168eef..798a9042421f 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -1915,7 +1915,7 @@ static void debugfs_add_domain_dir(struct irq_domain *d)
static void debugfs_remove_domain_dir(struct irq_domain *d)
{
- debugfs_remove(debugfs_lookup(d->name, domain_dir));
+ debugfs_lookup_and_remove(d->name, domain_dir);
}
void __init irq_domain_debugfs_init(struct dentry *root)
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 010cf4e6d0b8..728f434de2bb 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -901,8 +901,9 @@ static int __sched rt_mutex_adjust_prio_chain(struct task_struct *task,
* then we need to wake the new top waiter up to try
* to get the lock.
*/
- if (prerequeue_top_waiter != rt_mutex_top_waiter(lock))
- wake_up_state(waiter->task, waiter->wake_state);
+ top_waiter = rt_mutex_top_waiter(lock);
+ if (prerequeue_top_waiter != top_waiter)
+ wake_up_state(top_waiter->task, top_waiter->wake_state);
raw_spin_unlock_irq(&lock->wait_lock);
return 0;
}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e838feb6adc5..2a4918a1faa9 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2951,8 +2951,11 @@ static int __set_cpus_allowed_ptr_locked(struct task_struct *p,
}
if (!(ctx->flags & SCA_MIGRATE_ENABLE)) {
- if (cpumask_equal(&p->cpus_mask, ctx->new_mask))
+ if (cpumask_equal(&p->cpus_mask, ctx->new_mask)) {
+ if (ctx->flags & SCA_USER)
+ swap(p->user_cpus_ptr, ctx->user_mask);
goto out;
+ }
if (WARN_ON_ONCE(p == current &&
is_migration_disabled(p) &&
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index 8ac8b81bfee6..02e011cabe91 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -1343,10 +1343,11 @@ void psi_trigger_destroy(struct psi_trigger *t)
group = t->group;
/*
- * Wakeup waiters to stop polling. Can happen if cgroup is deleted
- * from under a polling process.
+ * Wakeup waiters to stop polling and clear the queue to prevent it from
+ * being accessed later. Can happen if cgroup is deleted from under a
+ * polling process.
*/
- wake_up_interruptible(&t->event_wait);
+ wake_up_pollfree(&t->event_wait);
mutex_lock(&group->trigger_lock);
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 5897828b9d7e..7e5dff602585 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -470,11 +470,35 @@ u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval)
}
EXPORT_SYMBOL_GPL(alarm_forward);
-u64 alarm_forward_now(struct alarm *alarm, ktime_t interval)
+static u64 __alarm_forward_now(struct alarm *alarm, ktime_t interval, bool throttle)
{
struct alarm_base *base = &alarm_bases[alarm->type];
+ ktime_t now = base->get_ktime();
+
+ if (IS_ENABLED(CONFIG_HIGH_RES_TIMERS) && throttle) {
+ /*
+ * Same issue as with posix_timer_fn(). Timers which are
+ * periodic but the signal is ignored can starve the system
+ * with a very small interval. The real fix which was
+ * promised in the context of posix_timer_fn() never
+ * materialized, but someone should really work on it.
+ *
+ * To prevent DOS fake @now to be 1 jiffie out which keeps
+ * the overrun accounting correct but creates an
+ * inconsistency vs. timer_gettime(2).
+ */
+ ktime_t kj = NSEC_PER_SEC / HZ;
+
+ if (interval < kj)
+ now = ktime_add(now, kj);
+ }
+
+ return alarm_forward(alarm, now, interval);
+}
- return alarm_forward(alarm, base->get_ktime(), interval);
+u64 alarm_forward_now(struct alarm *alarm, ktime_t interval)
+{
+ return __alarm_forward_now(alarm, interval, false);
}
EXPORT_SYMBOL_GPL(alarm_forward_now);
@@ -551,9 +575,10 @@ static enum alarmtimer_restart alarm_handle_timer(struct alarm *alarm,
if (posix_timer_event(ptr, si_private) && ptr->it_interval) {
/*
* Handle ignored signals and rearm the timer. This will go
- * away once we handle ignored signals proper.
+ * away once we handle ignored signals proper. Ensure that
+ * small intervals cannot starve the system.
*/
- ptr->it_overrun += alarm_forward_now(alarm, ptr->it_interval);
+ ptr->it_overrun += __alarm_forward_now(alarm, ptr->it_interval, true);
++ptr->it_requeue_pending;
ptr->it_active = 1;
result = ALARMTIMER_RESTART;
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index f47274de012b..c09792c551bf 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -833,6 +833,7 @@ static void do_bpf_send_signal(struct irq_work *entry)
work = container_of(entry, struct send_signal_irq_work, irq_work);
group_send_sig_info(work->sig, SEND_SIG_PRIV, work->task, work->type);
+ put_task_struct(work->task);
}
static int bpf_send_signal_common(u32 sig, enum pid_type type)
@@ -867,7 +868,7 @@ static int bpf_send_signal_common(u32 sig, enum pid_type type)
* to the irq_work. The current task may change when queued
* irq works get executed.
*/
- work->task = current;
+ work->task = get_task_struct(current);
work->sig = sig;
work->type = type;
irq_work_queue(&work->irq_work);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 78ed5f1baa8c..c9e40f692650 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -9148,9 +9148,6 @@ buffer_percent_write(struct file *filp, const char __user *ubuf,
if (val > 100)
return -EINVAL;
- if (!val)
- val = 1;
-
tr->buffer_percent = val;
(*ppos)++;
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 4eb6d6b97a9f..085a31b978a5 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1282,6 +1282,7 @@ struct ftrace_event_field {
int offset;
int size;
int is_signed;
+ int len;
};
struct prog_entry;
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 33e0b4f8ebe6..6a942fa275c7 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -114,7 +114,7 @@ trace_find_event_field(struct trace_event_call *call, char *name)
static int __trace_define_field(struct list_head *head, const char *type,
const char *name, int offset, int size,
- int is_signed, int filter_type)
+ int is_signed, int filter_type, int len)
{
struct ftrace_event_field *field;
@@ -133,6 +133,7 @@ static int __trace_define_field(struct list_head *head, const char *type,
field->offset = offset;
field->size = size;
field->is_signed = is_signed;
+ field->len = len;
list_add(&field->link, head);
@@ -150,14 +151,28 @@ int trace_define_field(struct trace_event_call *call, const char *type,
head = trace_get_fields(call);
return __trace_define_field(head, type, name, offset, size,
- is_signed, filter_type);
+ is_signed, filter_type, 0);
}
EXPORT_SYMBOL_GPL(trace_define_field);
+static int trace_define_field_ext(struct trace_event_call *call, const char *type,
+ const char *name, int offset, int size, int is_signed,
+ int filter_type, int len)
+{
+ struct list_head *head;
+
+ if (WARN_ON(!call->class))
+ return 0;
+
+ head = trace_get_fields(call);
+ return __trace_define_field(head, type, name, offset, size,
+ is_signed, filter_type, len);
+}
+
#define __generic_field(type, item, filter_type) \
ret = __trace_define_field(&ftrace_generic_fields, #type, \
#item, 0, 0, is_signed_type(type), \
- filter_type); \
+ filter_type, 0); \
if (ret) \
return ret;
@@ -166,7 +181,7 @@ EXPORT_SYMBOL_GPL(trace_define_field);
"common_" #item, \
offsetof(typeof(ent), item), \
sizeof(ent.item), \
- is_signed_type(type), FILTER_OTHER); \
+ is_signed_type(type), FILTER_OTHER, 0); \
if (ret) \
return ret;
@@ -1588,12 +1603,17 @@ static int f_show(struct seq_file *m, void *v)
seq_printf(m, "\tfield:%s %s;\toffset:%u;\tsize:%u;\tsigned:%d;\n",
field->type, field->name, field->offset,
field->size, !!field->is_signed);
- else
- seq_printf(m, "\tfield:%.*s %s%s;\toffset:%u;\tsize:%u;\tsigned:%d;\n",
+ else if (field->len)
+ seq_printf(m, "\tfield:%.*s %s[%d];\toffset:%u;\tsize:%u;\tsigned:%d;\n",
(int)(array_descriptor - field->type),
field->type, field->name,
- array_descriptor, field->offset,
+ field->len, field->offset,
field->size, !!field->is_signed);
+ else
+ seq_printf(m, "\tfield:%.*s %s[];\toffset:%u;\tsize:%u;\tsigned:%d;\n",
+ (int)(array_descriptor - field->type),
+ field->type, field->name,
+ field->offset, field->size, !!field->is_signed);
return 0;
}
@@ -2379,9 +2399,10 @@ event_define_fields(struct trace_event_call *call)
}
offset = ALIGN(offset, field->align);
- ret = trace_define_field(call, field->type, field->name,
+ ret = trace_define_field_ext(call, field->type, field->name,
offset, field->size,
- field->is_signed, field->filter_type);
+ field->is_signed, field->filter_type,
+ field->len);
if (WARN_ON_ONCE(ret)) {
pr_err("error code is %d\n", ret);
break;
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index d960f6b11b5e..58f3946081e2 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -111,7 +111,8 @@ static void __always_unused ____ftrace_check_##name(void) \
#define __array(_type, _item, _len) { \
.type = #_type"["__stringify(_len)"]", .name = #_item, \
.size = sizeof(_type[_len]), .align = __alignof__(_type), \
- is_signed_type(_type), .filter_type = FILTER_OTHER },
+ is_signed_type(_type), .filter_type = FILTER_OTHER, \
+ .len = _len },
#undef __array_desc
#define __array_desc(_type, _container, _item, _len) __array(_type, _item, _len)
diff --git a/kernel/umh.c b/kernel/umh.c
index 850631518665..fbf872c624cb 100644
--- a/kernel/umh.c
+++ b/kernel/umh.c
@@ -438,21 +438,27 @@ int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait)
if (wait == UMH_NO_WAIT) /* task has freed sub_info */
goto unlock;
- if (wait & UMH_KILLABLE)
- state |= TASK_KILLABLE;
-
if (wait & UMH_FREEZABLE)
state |= TASK_FREEZABLE;
- retval = wait_for_completion_state(&done, state);
- if (!retval)
- goto wait_done;
-
if (wait & UMH_KILLABLE) {
+ retval = wait_for_completion_state(&done, state | TASK_KILLABLE);
+ if (!retval)
+ goto wait_done;
+
/* umh_complete() will see NULL and free sub_info */
if (xchg(&sub_info->complete, NULL))
goto unlock;
+
+ /*
+ * fallthrough; in case of -ERESTARTSYS now do uninterruptible
+ * wait_for_completion_state(). Since umh_complete() shall call
+ * complete() in a moment if xchg() above returned NULL, this
+ * uninterruptible wait_for_completion_state() will not block
+ * SIGKILL'ed processes for long.
+ */
}
+ wait_for_completion_state(&done, state);
wait_done:
retval = sub_info->retval;
generated by cgit v1.2.3-70-g09d2 (git 2.51.1) at 2025-11-03 10:47:24 +0000