summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/syscall.c17
-rw-r--r--kernel/bpf/verifier.c34
-rw-r--r--kernel/cgroup/rstat.c16
-rw-r--r--kernel/sched/debug.c4
-rw-r--r--kernel/sched/fair.c51
5 files changed, 73 insertions, 49 deletions
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 2843bbba9ca1..4e6dee19a668 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -623,9 +623,20 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma)
mutex_lock(&map->freeze_mutex);
- if ((vma->vm_flags & VM_WRITE) && map->frozen) {
- err = -EPERM;
- goto out;
+ if (vma->vm_flags & VM_WRITE) {
+ if (map->frozen) {
+ err = -EPERM;
+ goto out;
+ }
+ /* map is meant to be read-only, so do not allow mapping as
+ * writable, because it's possible to leak a writable page
+ * reference and allows user-space to still modify it after
+ * freezing, while verifier will assume contents do not change
+ */
+ if (map->map_flags & BPF_F_RDONLY_PROG) {
+ err = -EACCES;
+ goto out;
+ }
}
/* set default open/close callbacks */
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 8d7ee40e2748..efe14cf24bc6 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1168,14 +1168,14 @@ static void __reg_assign_32_into_64(struct bpf_reg_state *reg)
* but must be positive otherwise set to worse case bounds
* and refine later from tnum.
*/
- if (reg->s32_min_value > 0)
- reg->smin_value = reg->s32_min_value;
- else
- reg->smin_value = 0;
- if (reg->s32_max_value > 0)
+ if (reg->s32_min_value >= 0 && reg->s32_max_value >= 0)
reg->smax_value = reg->s32_max_value;
else
reg->smax_value = U32_MAX;
+ if (reg->s32_min_value >= 0)
+ reg->smin_value = reg->s32_min_value;
+ else
+ reg->smin_value = 0;
}
static void __reg_combine_32_into_64(struct bpf_reg_state *reg)
@@ -10428,22 +10428,13 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env)
}
#define SECURITY_PREFIX "security_"
-static int check_attach_modify_return(struct bpf_verifier_env *env)
+static int check_attach_modify_return(struct bpf_prog *prog, unsigned long addr)
{
- struct bpf_prog *prog = env->prog;
- unsigned long addr = (unsigned long) prog->aux->trampoline->func.addr;
-
- /* This is expected to be cleaned up in the future with the KRSI effort
- * introducing the LSM_HOOK macro for cleaning up lsm_hooks.h.
- */
if (within_error_injection_list(addr) ||
!strncmp(SECURITY_PREFIX, prog->aux->attach_func_name,
sizeof(SECURITY_PREFIX) - 1))
return 0;
- verbose(env, "fmod_ret attach_btf_id %u (%s) is not modifiable\n",
- prog->aux->attach_btf_id, prog->aux->attach_func_name);
-
return -EINVAL;
}
@@ -10654,11 +10645,18 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
goto out;
}
}
+
+ if (prog->expected_attach_type == BPF_MODIFY_RETURN) {
+ ret = check_attach_modify_return(prog, addr);
+ if (ret)
+ verbose(env, "%s() is not modifiable\n",
+ prog->aux->attach_func_name);
+ }
+
+ if (ret)
+ goto out;
tr->func.addr = (void *)addr;
prog->aux->trampoline = tr;
-
- if (prog->expected_attach_type == BPF_MODIFY_RETURN)
- ret = check_attach_modify_return(env);
out:
mutex_unlock(&tr->mutex);
if (ret)
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index 6f87352f8219..41ca996568df 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -33,12 +33,9 @@ void cgroup_rstat_updated(struct cgroup *cgrp, int cpu)
return;
/*
- * Paired with the one in cgroup_rstat_cpu_pop_updated(). Either we
- * see NULL updated_next or they see our updated stat.
- */
- smp_mb();
-
- /*
+ * Speculative already-on-list test. This may race leading to
+ * temporary inaccuracies, which is fine.
+ *
* Because @parent's updated_children is terminated with @parent
* instead of NULL, we can tell whether @cgrp is on the list by
* testing the next pointer for NULL.
@@ -134,13 +131,6 @@ static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos,
*nextp = rstatc->updated_next;
rstatc->updated_next = NULL;
- /*
- * Paired with the one in cgroup_rstat_cpu_updated().
- * Either they see NULL updated_next or we see their
- * updated stat.
- */
- smp_mb();
-
return pos;
}
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index a562df57a86e..239970b991c0 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -948,8 +948,8 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
P(se.avg.util_est.enqueued);
#endif
#ifdef CONFIG_UCLAMP_TASK
- __PS("uclamp.min", p->uclamp[UCLAMP_MIN].value);
- __PS("uclamp.max", p->uclamp[UCLAMP_MAX].value);
+ __PS("uclamp.min", p->uclamp_req[UCLAMP_MIN].value);
+ __PS("uclamp.max", p->uclamp_req[UCLAMP_MAX].value);
__PS("effective uclamp.min", uclamp_eff_value(p, UCLAMP_MIN));
__PS("effective uclamp.max", uclamp_eff_value(p, UCLAMP_MAX));
#endif
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 02f323b85b6d..da3e5b54715b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2908,7 +2908,7 @@ static void task_tick_numa(struct rq *rq, struct task_struct *curr)
/*
* We don't care about NUMA placement if we don't have memory.
*/
- if (!curr->mm || (curr->flags & PF_EXITING) || work->next != work)
+ if ((curr->flags & (PF_EXITING | PF_KTHREAD)) || work->next != work)
return;
/*
@@ -4774,7 +4774,6 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
struct rq *rq = rq_of(cfs_rq);
struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
struct sched_entity *se;
- int enqueue = 1;
long task_delta, idle_task_delta;
se = cfs_rq->tg->se[cpu_of(rq)];
@@ -4798,26 +4797,44 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
idle_task_delta = cfs_rq->idle_h_nr_running;
for_each_sched_entity(se) {
if (se->on_rq)
- enqueue = 0;
+ break;
+ cfs_rq = cfs_rq_of(se);
+ enqueue_entity(cfs_rq, se, ENQUEUE_WAKEUP);
+
+ cfs_rq->h_nr_running += task_delta;
+ cfs_rq->idle_h_nr_running += idle_task_delta;
+
+ /* end evaluation on encountering a throttled cfs_rq */
+ if (cfs_rq_throttled(cfs_rq))
+ goto unthrottle_throttle;
+ }
+ for_each_sched_entity(se) {
cfs_rq = cfs_rq_of(se);
- if (enqueue) {
- enqueue_entity(cfs_rq, se, ENQUEUE_WAKEUP);
- } else {
- update_load_avg(cfs_rq, se, 0);
- se_update_runnable(se);
- }
+
+ update_load_avg(cfs_rq, se, UPDATE_TG);
+ se_update_runnable(se);
cfs_rq->h_nr_running += task_delta;
cfs_rq->idle_h_nr_running += idle_task_delta;
+
+ /* end evaluation on encountering a throttled cfs_rq */
if (cfs_rq_throttled(cfs_rq))
- break;
+ goto unthrottle_throttle;
+
+ /*
+ * One parent has been throttled and cfs_rq removed from the
+ * list. Add it back to not break the leaf list.
+ */
+ if (throttled_hierarchy(cfs_rq))
+ list_add_leaf_cfs_rq(cfs_rq);
}
- if (!se)
- add_nr_running(rq, task_delta);
+ /* At this point se is NULL and we are at root level*/
+ add_nr_running(rq, task_delta);
+unthrottle_throttle:
/*
* The cfs_rq_throttled() breaks in the above iteration can result in
* incomplete leaf list maintenance, resulting in triggering the
@@ -4826,7 +4843,8 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
for_each_sched_entity(se) {
cfs_rq = cfs_rq_of(se);
- list_add_leaf_cfs_rq(cfs_rq);
+ if (list_add_leaf_cfs_rq(cfs_rq))
+ break;
}
assert_list_leaf_cfs_rq(rq);
@@ -5479,6 +5497,13 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
/* end evaluation on encountering a throttled cfs_rq */
if (cfs_rq_throttled(cfs_rq))
goto enqueue_throttle;
+
+ /*
+ * One parent has been throttled and cfs_rq removed from the
+ * list. Add it back to not break the leaf list.
+ */
+ if (throttled_hierarchy(cfs_rq))
+ list_add_leaf_cfs_rq(cfs_rq);
}
enqueue_throttle:
generated by cgit v1.2.3 (git 2.46.0) at 2025-09-07 01:18:11 +0000