| 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: <20240501151312.635565-25-tj@kernel.org>
Date: Wed, 1 May 2024 05:09:59 -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,
Tejun Heo <tj@...nel.org>
Subject: [PATCH 24/39] sched_ext: Make watchdog handle ops.dispatch() looping stall
The dispatch path retries if the local DSQ is still empty after
ops.dispatch() either dispatched or consumed a task. This is both out of
necessity and for convenience. It has to retry because the dispatch path
might lose the tasks to dequeue while the rq lock is released while trying
to migrate tasks across CPUs, and the retry mechanism makes ops.dispatch()
implementation easier as it only needs to make some forward progress each
iteration.
However, this makes it possible for ops.dispatch() to stall CPUs by
repeatedly dispatching ineligible tasks. If all CPUs are stalled that way,
the watchdog or sysrq handler can't run and the system can't be saved. Let's
address the issue by breaking out of the dispatch loop after 32 iterations.
It is unlikely but not impossible for ops.dispatch() to legitimately go over
the iteration limit. We want to come back to the dispatch path in such cases
as not doing so risks stalling the CPU by idling with runnable tasks
pending. As the previous task is still current in balance_scx(),
resched_curr() doesn't do anything - it will just get cleared. Let's instead
use scx_kick_bpf() which will trigger reschedule after switching to the next
task which will likely be the idle task.
Signed-off-by: Tejun Heo <tj@...nel.org>
Reviewed-by: David Vernet <dvernet@...a.com>
---
kernel/sched/ext.c | 17 +++++++++++++++++
tools/sched_ext/scx_qmap.bpf.c | 15 +++++++++++++++
tools/sched_ext/scx_qmap.c | 8 ++++++--
3 files changed, 38 insertions(+), 2 deletions(-)
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 26c6a0b1e909..495210cd12f9 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -8,6 +8,7 @@
enum scx_consts {
SCX_DSP_DFL_MAX_BATCH = 32,
+ SCX_DSP_MAX_LOOPS = 32,
SCX_WATCHDOG_MAX_TIMEOUT = 30 * HZ,
SCX_EXIT_BT_LEN = 64,
@@ -598,6 +599,7 @@ static DEFINE_PER_CPU(struct scx_dsp_ctx, scx_dsp_ctx);
static struct kset *scx_kset;
static struct kobject *scx_root_kobj;
+static void scx_bpf_kick_cpu(s32 cpu, u64 flags);
static __printf(3, 4) void scx_ops_exit_kind(enum scx_exit_kind kind,
s64 exit_code,
const char *fmt, ...);
@@ -1840,6 +1842,7 @@ static int balance_scx(struct rq *rq, struct task_struct *prev,
struct scx_rq *scx_rq = &rq->scx;
struct scx_dsp_ctx *dspc = this_cpu_ptr(&scx_dsp_ctx);
bool prev_on_scx = prev->sched_class == &ext_sched_class;
+ int nr_loops = SCX_DSP_MAX_LOOPS;
bool has_tasks = false;
lockdep_assert_rq_held(rq);
@@ -1896,6 +1899,20 @@ static int balance_scx(struct rq *rq, struct task_struct *prev,
goto has_tasks;
if (consume_dispatch_q(rq, rf, &scx_dsq_global))
goto has_tasks;
+
+ /*
+ * ops.dispatch() can trap us in this loop by repeatedly
+ * dispatching ineligible tasks. Break out once in a while to
+ * allow the watchdog to run. As IRQ can't be enabled in
+ * balance(), we want to complete this scheduling cycle and then
+ * start a new one. IOW, we want to call resched_curr() on the
+ * next, most likely idle, task, not the current one. Use
+ * scx_bpf_kick_cpu() for deferred kicking.
+ */
+ if (unlikely(!--nr_loops)) {
+ scx_bpf_kick_cpu(cpu_of(rq), 0);
+ break;
+ }
} while (dspc->nr_tasks);
goto out;
diff --git a/tools/sched_ext/scx_qmap.bpf.c b/tools/sched_ext/scx_qmap.bpf.c
index e18f25017a0a..812004bf027a 100644
--- a/tools/sched_ext/scx_qmap.bpf.c
+++ b/tools/sched_ext/scx_qmap.bpf.c
@@ -31,6 +31,7 @@ char _license[] SEC("license") = "GPL";
const volatile u64 slice_ns = SCX_SLICE_DFL;
const volatile u32 stall_user_nth;
const volatile u32 stall_kernel_nth;
+const volatile u32 dsp_inf_loop_after;
const volatile u32 dsp_batch;
const volatile s32 disallow_tgid;
const volatile bool switch_partial;
@@ -198,6 +199,20 @@ void BPF_STRUCT_OPS(qmap_dispatch, s32 cpu, struct task_struct *prev)
if (scx_bpf_consume(SHARED_DSQ))
return;
+ if (dsp_inf_loop_after && nr_dispatched > dsp_inf_loop_after) {
+ /*
+ * PID 2 should be kthreadd which should mostly be idle and off
+ * the scheduler. Let's keep dispatching it to force the kernel
+ * to call this function over and over again.
+ */
+ p = bpf_task_from_pid(2);
+ if (p) {
+ scx_bpf_dispatch(p, SCX_DSQ_LOCAL, slice_ns, 0);
+ bpf_task_release(p);
+ return;
+ }
+ }
+
if (!(cpuc = bpf_map_lookup_elem(&cpu_ctx_stor, &zero))) {
scx_bpf_error("failed to look up cpu_ctx");
return;
diff --git a/tools/sched_ext/scx_qmap.c b/tools/sched_ext/scx_qmap.c
index 28fd5aa4e62c..36254631589e 100644
--- a/tools/sched_ext/scx_qmap.c
+++ b/tools/sched_ext/scx_qmap.c
@@ -19,13 +19,14 @@ const char help_fmt[] =
"\n"
"See the top-level comment in .bpf.c for more details.\n"
"\n"
-"Usage: %s [-s SLICE_US] [-e COUNT] [-t COUNT] [-T COUNT] [-b COUNT]\n"
+"Usage: %s [-s SLICE_US] [-e COUNT] [-t COUNT] [-T COUNT] [-l COUNT] [-b COUNT]\n"
" [-d PID] [-D LEN] [-p] [-v]\n"
"\n"
" -s SLICE_US Override slice duration\n"
" -e COUNT Trigger scx_bpf_error() after COUNT enqueues\n"
" -t COUNT Stall every COUNT'th user thread\n"
" -T COUNT Stall every COUNT'th kernel thread\n"
+" -l COUNT Trigger dispatch infinite looping after COUNT dispatches\n"
" -b COUNT Dispatch upto COUNT tasks together\n"
" -d PID Disallow a process from switching into SCHED_EXT (-1 for self)\n"
" -D LEN Set scx_exit_info.dump buffer length\n"
@@ -60,7 +61,7 @@ int main(int argc, char **argv)
skel = SCX_OPS_OPEN(qmap_ops, scx_qmap);
- while ((opt = getopt(argc, argv, "s:e:t:T:b:d:D:pvh")) != -1) {
+ while ((opt = getopt(argc, argv, "s:e:t:T:l:b:d:D:pvh")) != -1) {
switch (opt) {
case 's':
skel->rodata->slice_ns = strtoull(optarg, NULL, 0) * 1000;
@@ -74,6 +75,9 @@ int main(int argc, char **argv)
case 'T':
skel->rodata->stall_kernel_nth = strtoul(optarg, NULL, 0);
break;
+ case 'l':
+ skel->rodata->dsp_inf_loop_after = strtoul(optarg, NULL, 0);
+ break;
case 'b':
skel->rodata->dsp_batch = strtoul(optarg, NULL, 0);
break;
--
2.44.0
Powered by blists - more mailing lists