| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20240501151312.635565-20-tj@kernel.org>
Date: Wed, 1 May 2024 05:09:54 -1000
From: Tejun Heo <tj@...nel.org>
To: torvalds@...ux-foundation.org,
mingo@...hat.com,
peterz@...radead.org,
juri.lelli@...hat.com,
vincent.guittot@...aro.org,
dietmar.eggemann@....com,
rostedt@...dmis.org,
bsegall@...gle.com,
mgorman@...e.de,
bristot@...hat.com,
vschneid@...hat.com,
ast@...nel.org,
daniel@...earbox.net,
andrii@...nel.org,
martin.lau@...nel.org,
joshdon@...gle.com,
brho@...gle.com,
pjt@...gle.com,
derkling@...gle.com,
haoluo@...gle.com,
dvernet@...a.com,
dschatzberg@...a.com,
dskarlat@...cmu.edu,
riel@...riel.com,
changwoo@...lia.com,
himadrics@...ia.fr,
memxor@...il.com,
andrea.righi@...onical.com,
joel@...lfernandes.org
Cc: linux-kernel@...r.kernel.org,
bpf@...r.kernel.org,
kernel-team@...a.com,
David Vernet <void@...ifault.com>,
Tejun Heo <tj@...nel.org>
Subject: [PATCH 19/39] sched_ext: Print sched_ext info when dumping stack
From: David Vernet <void@...ifault.com>
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]
...
v3: - scx_ops_enable_state_str[] definition moved to an earlier patch as
it's now used by core implementation.
- Convert jiffy delta to msecs using jiffies_to_msecs() instead of
multiplying by (HZ / MSEC_PER_SEC). The conversion is implemented in
jiffies_delta_msecs().
v2: - We are now using scx_ops_enable_state_str[] outside
CONFIG_SCHED_DEBUG. Move it outside of CONFIG_SCHED_DEBUG and to the
top. This was reported by Changwoo and Andrea.
Signed-off-by: David Vernet <void@...ifault.com>
Reported-by: Changwoo Min <changwoo@...lia.com>
Reported-by: Andrea Righi <andrea.righi@...onical.com>
Signed-off-by: Tejun Heo <tj@...nel.org>
---
include/linux/sched/ext.h | 2 ++
kernel/sched/core.c | 1 +
kernel/sched/ext.c | 53 +++++++++++++++++++++++++++++++++++++++
lib/dump_stack.c | 1 +
4 files changed, 57 insertions(+)
diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h
index 2608a8f548db..123d6dffdf26 100644
--- a/include/linux/sched/ext.h
+++ b/include/linux/sched/ext.h
@@ -155,10 +155,12 @@ 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 aae9c1297622..42fe654bf946 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -9272,6 +9272,7 @@ 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 8d2ff81e8dd4..ff080b5f0330 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -577,6 +577,14 @@ static __printf(3, 4) void scx_ops_exit_kind(enum scx_exit_kind kind,
#define SCX_HAS_OP(op) static_branch_likely(&scx_has_op[SCX_OP_IDX(op)])
+static long jiffies_delta_msecs(unsigned long at, unsigned long now)
+{
+ if (time_after(at, now))
+ return jiffies_to_msecs(at - now);
+ else
+ return -(long)jiffies_to_msecs(now - at);
+}
+
/* if the highest set bit is N, return a mask with bits [N+1, 31] set */
static u32 higher_bits(u32 flags)
{
@@ -3695,6 +3703,51 @@ 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), "%+ldms",
+ jiffies_delta_msecs(runnable_at, jiffies));
+
+ /* print everything onto one line to conserve console space */
+ 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)
{
s32 cpu, v;
diff --git a/lib/dump_stack.c b/lib/dump_stack.c
index 222c6d6c8281..9581ef4efec5 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);
}
/**
--
2.44.0
Powered by blists - more mailing lists