[PATCH 18/36] sched_ext: Print sched_ext info when dumping stack

From: Tejun Heo
Date: Fri Nov 10 2023 - 21:50:35 EST


From: David Vernet <void@xxxxxxxxxxxxx>

It would be useful to see what the sched_ext scheduler state is, and what
scheduler is running, when we're dumping a task's stack. This patch
therefore adds a new print_scx_info() function that's called in the same
context as print_worker_info() and print_stop_info(). An example dump
follows.

BUG: kernel NULL pointer dereference, address: 0000000000000999
#PF: supervisor write access in kernel mode
#PF: error_code(0x0002) - not-present page
PGD 0 P4D 0
Oops: 0002 [#1] PREEMPT SMP
CPU: 13 PID: 2047 Comm: insmod Tainted: G O 6.6.0-work-10323-gb58d4cae8e99-dirty #34
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS unknown 2/2/2022
Sched_ext: qmap (enabled+all), task: runnable_at=-17ms
RIP: 0010:init_module+0x9/0x1000 [test_module]
...

Signed-off-by: David Vernet <void@xxxxxxxxxxxxx>
Signed-off-by: Tejun Heo <tj@xxxxxxxxxx>
---
include/linux/sched/ext.h | 2 ++
kernel/sched/core.c | 1 +
kernel/sched/ext.c | 45 +++++++++++++++++++++++++++++++++++++++
lib/dump_stack.c | 1 +
4 files changed, 49 insertions(+)

diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h
index 9d41acaf89c0..55f649bd065c 100644
--- a/include/linux/sched/ext.h
+++ b/include/linux/sched/ext.h
@@ -428,10 +428,12 @@ struct sched_ext_entity {
};

void sched_ext_free(struct task_struct *p);
+void print_scx_info(const char *log_lvl, struct task_struct *p);

#else /* !CONFIG_SCHED_CLASS_EXT */

static inline void sched_ext_free(struct task_struct *p) {}
+static inline void print_scx_info(const char *log_lvl, struct task_struct *p) {}

#endif /* CONFIG_SCHED_CLASS_EXT */
#endif /* _LINUX_SCHED_EXT_H */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 1906f8397c28..957ae28a6e3f 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -9217,6 +9217,7 @@ void sched_show_task(struct task_struct *p)

print_worker_info(KERN_INFO, p);
print_stop_info(KERN_INFO, p);
+ print_scx_info(KERN_INFO, p);
show_stack(p, NULL, KERN_INFO);
put_task_stack(p);
}
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 4e2aa9f308fb..65ee99ea111b 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -2787,6 +2787,51 @@ static const struct sysrq_key_op sysrq_sched_ext_reset_op = {
.enable_mask = SYSRQ_ENABLE_RTNICE,
};

+/**
+ * print_scx_info - print out sched_ext scheduler state
+ * @log_lvl: the log level to use when printing
+ * @p: target task
+ *
+ * If a sched_ext scheduler is enabled, print the name and state of the
+ * scheduler. If @p is on sched_ext, print further information about the task.
+ *
+ * This function can be safely called on any task as long as the task_struct
+ * itself is accessible. While safe, this function isn't synchronized and may
+ * print out mixups or garbages of limited length.
+ */
+void print_scx_info(const char *log_lvl, struct task_struct *p)
+{
+ enum scx_ops_enable_state state = scx_ops_enable_state();
+ const char *all = READ_ONCE(scx_switching_all) ? "+all" : "";
+ char runnable_at_buf[22] = "?";
+ struct sched_class *class;
+ unsigned long runnable_at;
+
+ if (state == SCX_OPS_DISABLED)
+ return;
+
+ /*
+ * Carefully check if the task was running on sched_ext, and then
+ * carefully copy the time it's been runnable, and its state.
+ */
+ if (copy_from_kernel_nofault(&class, &p->sched_class, sizeof(class)) ||
+ class != &ext_sched_class) {
+ printk("%sSched_ext: %s (%s%s)", log_lvl, scx_ops.name,
+ scx_ops_enable_state_str[state], all);
+ return;
+ }
+
+ if (!copy_from_kernel_nofault(&runnable_at, &p->scx.runnable_at,
+ sizeof(runnable_at)))
+ scnprintf(runnable_at_buf, sizeof(runnable_at_buf), "%+lldms",
+ (s64)(runnable_at - jiffies) * (HZ / MSEC_PER_SEC));
+
+ /* Print everything onto one line to conserve console spce. */
+ printk("%sSched_ext: %s (%s%s), task: runnable_at=%s",
+ log_lvl, scx_ops.name, scx_ops_enable_state_str[state], all,
+ runnable_at_buf);
+}
+
void __init init_sched_ext_class(void)
{
int cpu;
diff --git a/lib/dump_stack.c b/lib/dump_stack.c
index 83471e81501a..6e667c445539 100644
--- a/lib/dump_stack.c
+++ b/lib/dump_stack.c
@@ -68,6 +68,7 @@ void dump_stack_print_info(const char *log_lvl)

print_worker_info(log_lvl, current);
print_stop_info(log_lvl, current);
+ print_scx_info(log_lvl, current);
}

/**
--
2.42.0