Since sqthread is userspace like thread now, it should respect cgroup
setting, thus we should consider current allowed cpuset when doing
cpu binding for sqthread.
Signed-off-by: Hao Xu <haoxu@xxxxxxxxxxxxxxxxx>
---
v1-->v2
- add a helper in cpuset.c so that we can directly leverage task_cs()
- remove v1 code which we don't need now
fs/io_uring.c | 21 ++++++++++++++++-----
include/linux/cpuset.h | 7 +++++++
kernel/cgroup/cpuset.c | 11 +++++++++++
3 files changed, 34 insertions(+), 5 deletions(-)
diff --git a/fs/io_uring.c b/fs/io_uring.c
index be3c3aea6398..a0f54c545158 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -79,6 +79,7 @@
#include <linux/pagemap.h>
#include <linux/io_uring.h>
#include <linux/tracehook.h>
+#include <linux/cpuset.h>
#define CREATE_TRACE_POINTS
#include <trace/events/io_uring.h>
@@ -7000,6 +7001,16 @@ static bool io_sqd_handle_event(struct io_sq_data *sqd)
return did_sig || test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state);
}
+static int io_sq_bind_cpu(int cpu)
+{
+ if (!test_cpu_in_current_cpuset(cpu))
+ pr_warn("sqthread %d: bound cpu not allowed\n", current->pid);
+ else
+ set_cpus_allowed_ptr(current, cpumask_of(cpu));
+
+ return 0;
+}
+
static int io_sq_thread(void *data)
{
struct io_sq_data *sqd = data;
@@ -7010,11 +7021,9 @@ static int io_sq_thread(void *data)
snprintf(buf, sizeof(buf), "iou-sqp-%d", sqd->task_pid);
set_task_comm(current, buf);
-
if (sqd->sq_cpu != -1)
- set_cpus_allowed_ptr(current, cpumask_of(sqd->sq_cpu));
- else
- set_cpus_allowed_ptr(current, cpu_online_mask);
+ io_sq_bind_cpu(sqd->sq_cpu);
+
current->flags |= PF_NO_SETAFFINITY;
mutex_lock(&sqd->lock);
@@ -8208,8 +8217,10 @@ static int io_sq_offload_create(struct io_ring_ctx *ctx,
int cpu = p->sq_thread_cpu;
ret = -EINVAL;
- if (cpu >= nr_cpu_ids || !cpu_online(cpu))
+ if (cpu >= nr_cpu_ids || !cpu_online(cpu) ||
+ !test_cpu_in_current_cpuset(cpu))
goto err_sqpoll;
+
sqd->sq_cpu = cpu;
} else {
sqd->sq_cpu = -1;
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 04c20de66afc..fad77c91bc1f 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -116,6 +116,8 @@ static inline int cpuset_do_slab_mem_spread(void)
extern bool current_cpuset_is_being_rebound(void);
+extern bool test_cpu_in_current_cpuset(int cpu);
+
extern void rebuild_sched_domains(void);
extern void cpuset_print_current_mems_allowed(void);
@@ -257,6 +259,11 @@ static inline bool current_cpuset_is_being_rebound(void)
return false;
}
+static inline bool test_cpu_in_current_cpuset(int cpu)
+{
+ return false;
+}
+
static inline void rebuild_sched_domains(void)
{
partition_sched_domains(1, NULL, NULL);
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index adb5190c4429..a63c27e9430e 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -1849,6 +1849,17 @@ bool current_cpuset_is_being_rebound(void)
return ret;
}
+bool test_cpu_in_current_cpuset(int cpu)
+{
+ bool ret;
+
+ rcu_read_lock();
+ ret = cpumask_test_cpu(cpu, task_cs(current)->effective_cpus);
+ rcu_read_unlock();
+
+ return ret;
+}
+
static int update_relax_domain_level(struct cpuset *cs, s64 val)
{
#ifdef CONFIG_SMP
--
2.24.4
