Sched_ext development
 help / color / mirror / Atom feed
From: Tejun Heo <tj@kernel.org>
To: David Vernet <void@manifault.com>,
	Andrea Righi <arighi@nvidia.com>,
	Changwoo Min <changwoo@igalia.com>
Cc: sched-ext@lists.linux.dev, Emil Tsalapatis <emil@etsalapatis.com>,
	linux-kernel@vger.kernel.org, Tejun Heo <tj@kernel.org>
Subject: [PATCH sched_ext/for-7.3 32/32] tools/sched_ext: scx_qmap - Add sub-sched cap fault injection
Date: Thu,  2 Jul 2026 22:01:59 -1000	[thread overview]
Message-ID: <20260703080159.2314350-33-tj@kernel.org> (raw)
In-Reply-To: <20260703080159.2314350-1-tj@kernel.org>

Add a fault-injection mode to the scx_qmap sub-scheduler that deliberately
dispatches one of its own tasks to a cid it does not hold. The kernel cap
check must reject it and re-enqueue with SCX_TASK_REENQ_CAP, so the
nr_inject_attempts counter tracks nr_reenq_cap one to one, exercising the
delivery-time cap enforcement.

Signed-off-by: Tejun Heo <tj@kernel.org>
---
 tools/sched_ext/scx_qmap.bpf.c | 40 ++++++++++++++++++++++++++++++++++
 tools/sched_ext/scx_qmap.c     | 20 +++++++++++++----
 tools/sched_ext/scx_qmap.h     |  8 +++++++
 3 files changed, 64 insertions(+), 4 deletions(-)

diff --git a/tools/sched_ext/scx_qmap.bpf.c b/tools/sched_ext/scx_qmap.bpf.c
index 938a32514b2f..9a93a68c0d42 100644
--- a/tools/sched_ext/scx_qmap.bpf.c
+++ b/tools/sched_ext/scx_qmap.bpf.c
@@ -376,6 +376,24 @@ static u64 needs_immed(s32 cid)
 	return qa.cid_shared[cid] ? SCX_ENQ_IMMED : 0;
 }
 
+/* first cid this node does NOT hold for fault injection, -1 if none */
+static s32 first_unavail_cid(void)
+{
+	s32 nr_cids = qa.nr_cids, c;
+
+	if (nr_cids > SCX_QMAP_MAX_CPUS) {
+		scx_bpf_error("-ERANGE");
+		return -1;
+	}
+
+	bpf_for(c, 0, nr_cids) {
+		if (!cmask_test(c, &qa.held_excl.mask) &&
+		    !cmask_test(c, &qa.held_shared.mask))
+			return c;
+	}
+	return -1;
+}
+
 static int weight_to_idx(u32 weight)
 {
 	/* Coarsely map the compound weight to a FIFO. */
@@ -452,6 +470,28 @@ void BPF_STRUCT_OPS(qmap_enqueue, struct task_struct *p, u64 enq_flags)
 		}
 	}
 
+	/*
+	 * Fault injection: deliberately dispatch one of our own tasks to a cid
+	 * we don't hold. The kernel cap check must reject it and re-enqueue
+	 * with SCX_TASK_REENQ_CAP, so nr_inject_attempts tracks nr_reenq_cap
+	 * and proves delivery-time enforcement. Throttled.
+	 */
+	if (qa.inject_mode == QMAP_INJ_WRONG_CID && p->nr_cpus_allowed > 1 &&
+	    !(enq_flags & SCX_ENQ_REENQ)) {
+		static u32 inj_cnt;
+
+		if (!(++inj_cnt % 64)) {
+			s32 bad = first_unavail_cid();
+
+			if (bad >= 0 && cmask_test(bad, &taskc->cpus_allowed)) {
+				__sync_fetch_and_add(&qa.nr_inject_attempts, 1);
+				scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL_ON | bad,
+						   slice_ns, enq_flags);
+				return;
+			}
+		}
+	}
+
 	/*
 	 * IMMED stress testing: Every immed_stress_nth'th enqueue, dispatch
 	 * directly to prev_cpu's local DSQ even when busy to force dsq->nr > 1
diff --git a/tools/sched_ext/scx_qmap.c b/tools/sched_ext/scx_qmap.c
index 1efffaaa8fe8..d3f766b692b8 100644
--- a/tools/sched_ext/scx_qmap.c
+++ b/tools/sched_ext/scx_qmap.c
@@ -52,7 +52,7 @@ const char help_fmt[] =
 "\n"
 "Usage: %s [-s SLICE_US] [-e COUNT] [-t COUNT] [-T COUNT] [-l COUNT] [-b COUNT]\n"
 "       [-N COUNT] [-P] [-M] [-H] [-c CG_PATH] [-d PID] [-D LEN] [-S] [-p] [-I]\n"
-"       [-F COUNT] [-i SEC] [-R MS] [-v]\n"
+"       [-F COUNT] [-i SEC] [-R MS] [-J MODE] [-v]\n"
 "\n"
 "  -s SLICE_US   Override slice duration\n"
 "  -e COUNT      Trigger scx_bpf_error() after COUNT enqueues\n"
@@ -74,6 +74,7 @@ const char help_fmt[] =
 "  -C MODE       cid-override test (shuffle|bad-dup|bad-range|bad-mono)\n"
 "  -i SEC        Stats and weight-refresh interval, seconds (default 5)\n"
 "  -R MS         Round-robin period for time-shared cpus, ms (default 200)\n"
+"  -J MODE       Fault injection (wrong-cid: dispatch to a cid not held)\n"
 "  -v            Print libbpf debug messages\n"
 "  -h            Display this help and exit\n";
 
@@ -183,6 +184,7 @@ struct hier_prev {
 	u64 nr_dsps[MAX_SUB_SCHEDS];
 	u64 nr_reenq_cap;
 	u64 nr_reenq_immed;
+	u64 nr_inject_attempts;
 };
 
 /* current wall-clock time as "HH:MM:SS" for the startup and interval headers */
@@ -264,12 +266,14 @@ static void print_hier(struct qmap_arena *qa, struct hier_prev *prev, u64 own_cg
 	}
 
 	format_cid_ranges(qa, CID_SHARED, ranges, sizeof(ranges));
-	printf("hier   : nsub=%llu excl=%u shared=%s rr=%s reenq cap/immed +%llu/+%llu\n",
+	printf("hier   : nsub=%llu excl=%u shared=%s rr=%s reenq cap/immed +%llu/+%llu inj=+%llu\n",
 	       (unsigned long long)qa->nr_sub_scheds, qa->part.nr_excl, ranges, rr,
 	       (unsigned long long)(qa->nr_reenq_cap - prev->nr_reenq_cap),
-	       (unsigned long long)(qa->nr_reenq_immed - prev->nr_reenq_immed));
+	       (unsigned long long)(qa->nr_reenq_immed - prev->nr_reenq_immed),
+	       (unsigned long long)(qa->nr_inject_attempts - prev->nr_inject_attempts));
 	prev->nr_reenq_cap = qa->nr_reenq_cap;
 	prev->nr_reenq_immed = qa->nr_reenq_immed;
+	prev->nr_inject_attempts = qa->nr_inject_attempts;
 
 	printf("hier   : %-4s %10s %4s %6s %8s  %s\n",
 	       "", "cgroup", "w", "alloc", "disp/s", "cids");
@@ -310,6 +314,7 @@ int main(int argc, char **argv)
 	struct hier_prev hprev = {};
 	const char *sub_cg_path = NULL;
 	char tbuf[32];
+	u32 inject_mode = 0;
 	u64 own_cgid = 0;
 
 	libbpf_set_print(libbpf_print_fn);
@@ -330,7 +335,7 @@ int main(int argc, char **argv)
 	skel->rodata->slice_ns = __COMPAT_ENUM_OR_ZERO("scx_public_consts", "SCX_SLICE_DFL");
 	skel->rodata->max_tasks = 16384;
 
-	while ((opt = getopt(argc, argv, "s:e:t:T:l:b:N:PMHc:d:D:SpIF:C:i:R:vh")) != -1) {
+	while ((opt = getopt(argc, argv, "s:e:t:T:l:b:N:PMHc:d:D:SpIF:C:i:R:J:vh")) != -1) {
 		switch (opt) {
 		case 's':
 			skel->rodata->slice_ns = strtoull(optarg, NULL, 0) * 1000;
@@ -464,6 +469,12 @@ int main(int argc, char **argv)
 			if (round_robin_ms < 10)
 				round_robin_ms = 10;
 			break;
+		case 'J':
+			if (!strcmp(optarg, "wrong-cid"))
+				inject_mode = QMAP_INJ_WRONG_CID;
+			else
+				inject_mode = strtoul(optarg, NULL, 0);
+			break;
 		case 'v':
 			verbose = true;
 			break;
@@ -480,6 +491,7 @@ int main(int argc, char **argv)
 
 	qa = &skel->arena->qa;
 	qa->test_error_cnt = test_error_cnt;
+	qa->inject_mode = inject_mode;
 
 	if (sub_cg_path)
 		printf("%s scx_qmap started: sub-scheduler on %s, stats every %ds\n",
diff --git a/tools/sched_ext/scx_qmap.h b/tools/sched_ext/scx_qmap.h
index c87d61c37fe1..7b22b0f9737f 100644
--- a/tools/sched_ext/scx_qmap.h
+++ b/tools/sched_ext/scx_qmap.h
@@ -60,6 +60,12 @@ struct qmap_fifo {
 	s32 idx;
 };
 
+/* -J fault-injection modes. Selects inject_mode in struct qmap_arena. */
+enum qmap_inject {
+	QMAP_INJ_OFF		= 0,
+	QMAP_INJ_WRONG_CID	= 1,	/* dispatch to a cid we don't hold */
+};
+
 /*
  * scx_cmask's are embedded in struct qmap_arena with inline backing storage.
  * The bpf side uses &field.mask with the normal cmask_* helpers. Userspace
@@ -167,6 +173,8 @@ struct qmap_arena {
 	/* bpf -> userspace: stats */
 	u64 nr_reenq_cap;		/* SCX_TASK_REENQ_CAP bounces */
 	u64 nr_reenq_immed;		/* SCX_TASK_REENQ_IMMED bounces */
+	u64 nr_inject_attempts;		/* fault-injection: dispatches to an unheld cid */
+	u32 inject_mode;		/* fault-injection mode (QMAP_INJ_*) */
 };
 
 #endif /* __SCX_QMAP_H */
-- 
2.54.0


      parent reply	other threads:[~2026-07-03  8:02 UTC|newest]

Thread overview: 61+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-07-03  8:01 [PATCHSET sched_ext/for-7.3] sched_ext: Capability-based CPU delegation for sub-schedulers Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 01/32] sched_ext: Fix premature ops->priv publication in scx_alloc_and_add_sched() Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 02/32] tools/sched_ext: scx - Fix cmask_subset(), cmask_equal() and cmask_weight() Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 03/32] sched_ext: Use READ_ONCE/WRITE_ONCE in cmask word ops and drop _RACY variants Tejun Heo
2026-07-03  8:33   ` sashiko-bot
2026-07-04  0:54     ` Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 04/32] tools/sched_ext: scx_qmap - Use bare u64/u32/s32 integer types Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 05/32] sched_ext: Reject direct slice and dsq_vtime writes for cid-form schedulers Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 06/32] sched_ext: Make scx_bpf_kick_cid() return void Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 07/32] sched_ext: Make the kick machinery per-sched Tejun Heo
2026-07-03  9:02   ` sashiko-bot
2026-07-04  0:54     ` Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 08/32] sched_ext: Add ops.init_cids() to finalize the cid layout before init Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 09/32] sched_ext: Add CID sharding Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 10/32] sched_ext: Add shard boundaries to scx_bpf_cid_override() Tejun Heo
2026-07-03  9:51   ` sashiko-bot
2026-07-04  0:54     ` Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 11/32] sched_ext: Defer scx_sched kobj sysfs add into the enable workfns Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 12/32] sched_ext: Add per-shard scx_sched storage scaffolding Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 13/32] sched_ext: Add scx_cmask_ref for validated arena cmask access Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 14/32] sched_ext: RCU-protect the sub-sched tree's children/sibling lists Tejun Heo
2026-07-03 10:49   ` sashiko-bot
2026-07-04  0:54     ` Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 15/32] sched_ext: Add scx_skip_subtree_pre() Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 16/32] sched_ext: Add per-shard cap delegation for sub-schedulers Tejun Heo
2026-07-03 11:17   ` sashiko-bot
2026-07-04  0:54     ` Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 17/32] sched_ext: Add coalescing sub_caps_updated() notifier " Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 18/32] sched_ext: Maintain per-cpu effective cap copies for single-read checks Tejun Heo
2026-07-03 12:05   ` sashiko-bot
2026-07-04  0:54     ` Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 19/32] sched_ext: Add sub_ecaps_updated() effective-cap change notifier Tejun Heo
2026-07-03 12:25   ` sashiko-bot
2026-07-04  0:54     ` Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 20/32] sched_ext: Generalize local-DSQ handling to rq-owned DSQs Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 21/32] sched_ext: Add reject DSQ for cap-rejected dispatches Tejun Heo
2026-07-03 12:57   ` sashiko-bot
2026-07-04  0:54     ` Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 22/32] sched_ext: Add the SCX_CAP_ENQ_IMMED cap Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 23/32] sched_ext: Assign a unique id to each scheduler instance Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 24/32] sched_ext: Route task slice writes through set_task_slice() Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 25/32] sched_ext: Tie cpu occupancy to SCX_CAP_BASE through the task slice Tejun Heo
2026-07-03 13:34   ` sashiko-bot
2026-07-04  0:54     ` Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 26/32] sched_ext: Add the SCX_CAP_ENQ cap Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 27/32] sched_ext: Gate kicks on SCX_CAP_BASE and preemption on SCX_CAP_PREEMPT Tejun Heo
2026-07-03 14:01   ` sashiko-bot
2026-07-04  0:54     ` Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 28/32] sched_ext: Route ops.update_idle() to sub-schedulers and re-notify owed scheds Tejun Heo
2026-07-03 14:14   ` sashiko-bot
2026-07-04  0:54     ` Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 29/32] sched_ext: Replay ecaps notifications suppressed by bypass Tejun Heo
2026-07-03 14:28   ` sashiko-bot
2026-07-04  0:54     ` Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 30/32] sched_ext: Add scx_bpf_sub_kill() to evict a child sub-scheduler Tejun Heo
2026-07-03 14:45   ` sashiko-bot
2026-07-04  0:54     ` Tejun Heo
2026-07-03  8:01 ` [PATCH sched_ext/for-7.3 31/32] tools/sched_ext: scx_qmap - Expand hierarchical sub-scheduling Tejun Heo
2026-07-03 14:57   ` sashiko-bot
2026-07-04  0:54     ` Tejun Heo
2026-07-03  8:01 ` Tejun Heo [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260703080159.2314350-33-tj@kernel.org \
    --to=tj@kernel.org \
    --cc=arighi@nvidia.com \
    --cc=changwoo@igalia.com \
    --cc=emil@etsalapatis.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=sched-ext@lists.linux.dev \
    --cc=void@manifault.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox