All of lore.kernel.org
 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 v2 sched_ext/for-7.3 04/36] tools/sched_ext: scx - Fix cmask_subset(), cmask_equal() and cmask_weight()
Date: Sun,  5 Jul 2026 15:40:26 -1000	[thread overview]
Message-ID: <20260706014058.439853-5-tj@kernel.org> (raw)
In-Reply-To: <20260706014058.439853-1-tj@kernel.org>

cmask_equal(), cmask_weight() and cmask_subset() bounded their word walks
with CMASK_NR_WORDS(nr_cids), which pads by one word and can't tell the last
word in use without @base. The walks could thus cover a slack word past the
active range, which cmask_reframe() leaves non-zero: a stale bit there gave
cmask_equal() a spurious mismatch, cmask_weight() an inflated count, and
cmask_subset() a spurious violation. cmask_subset() could also read
@b->bits[] one word past its allocation (within the arena's fault-recovered
range, so harmless), and deviated from the kernel scx_cmask_subset() by
failing any @a range that doesn't nest inside @b's even when the overhanging
bits are all clear.

Bound the cmask_equal() and cmask_weight() walks by the words the range
actually spans, with early returns for empty ranges. Rewrite cmask_subset()
to match the kernel semantics: scan @a's overhangs for set bits with
cmask_next_set() and walk the words of the range intersection.
cmask_subset() moves below cmask_next_set(), which it now uses. Padding bits
don't need masking as every cmask helper keeps them clear.

Signed-off-by: Tejun Heo <tj@kernel.org>
---
 tools/sched_ext/include/scx/cid.bpf.h | 88 +++++++++++++++++----------
 1 file changed, 55 insertions(+), 33 deletions(-)

diff --git a/tools/sched_ext/include/scx/cid.bpf.h b/tools/sched_ext/include/scx/cid.bpf.h
index db247e42fb45..6b0b4e41b288 100644
--- a/tools/sched_ext/include/scx/cid.bpf.h
+++ b/tools/sched_ext/include/scx/cid.bpf.h
@@ -391,7 +391,9 @@ static __always_inline bool cmask_equal(const struct scx_cmask __arena *a,
 
 	if (a->base != b->base || a->nr_cids != b->nr_cids)
 		return false;
-	nr_words = CMASK_NR_WORDS(a->nr_cids);
+	if (a->nr_cids == 0)
+		return true;
+	nr_words = (a->base + a->nr_cids - 1) / 64 - a->base / 64 + 1;
 
 	bpf_for(i, 0, CMASK_MAX_WORDS) {
 		if (i >= nr_words)
@@ -402,36 +404,6 @@ static __always_inline bool cmask_equal(const struct scx_cmask __arena *a,
 	return true;
 }
 
-/*
- * True iff every bit set in @a is also set in @b over the intersection of
- * their ranges. Bits of @a outside @b's range fail the test.
- */
-static __always_inline bool cmask_subset(const struct scx_cmask __arena *a,
-					 const struct scx_cmask __arena *b)
-{
-	u32 a_end = a->base + a->nr_cids;
-	u32 b_end = b->base + b->nr_cids;
-	u32 a_wbase = a->base / 64;
-	u32 b_wbase = b->base / 64;
-	u32 nr_words, i;
-
-	/* any bit of @a outside @b's range is a subset violation */
-	if (a->base < b->base || a_end > b_end)
-		return false;
-
-	nr_words = CMASK_NR_WORDS(a->nr_cids);
-	bpf_for(i, 0, CMASK_MAX_WORDS) {
-		u32 wi_b;
-
-		if (i >= nr_words)
-			break;
-		wi_b = a_wbase + i - b_wbase;
-		if (a->bits[i] & ~b->bits[wi_b])
-			return false;
-	}
-	return true;
-}
-
 /**
  * cmask_next_set - find the first set bit at or after @cid
  * @m: cmask to search
@@ -488,16 +460,66 @@ static __always_inline u32 cmask_first_set(const struct scx_cmask __arena *m)
 	     (cid) < (m)->base + (m)->nr_cids;					\
 	     (cid) = cmask_next_set((m), (cid) + 1))
 
+/*
+ * True iff every bit set in @a is also set in @b. Matches the kernel-side
+ * scx_cmask_subset(): ranges don't need to nest, and set bits of @a outside
+ * @b's range fail the test.
+ */
+static __always_inline bool cmask_subset(const struct scx_cmask __arena *a,
+					 const struct scx_cmask __arena *b)
+{
+	u32 a_end = a->base + a->nr_cids;
+	u32 b_end = b->base + b->nr_cids;
+	u32 a_wbase = a->base / 64;
+	u32 b_wbase = b->base / 64;
+	u32 lo = a->base > b->base ? a->base : b->base;
+	u32 hi = a_end < b_end ? a_end : b_end;
+	u32 lo_word, hi_word, i;
+
+	/* set bits of @a outside @b's range can't be in @b */
+	if (a->base < b->base &&
+	    cmask_next_set(a, a->base) < (b->base < a_end ? b->base : a_end))
+		return false;
+	if (a_end > b_end &&
+	    cmask_next_set(a, a->base > b_end ? a->base : b_end) < a_end)
+		return false;
+
+	if (lo >= hi)
+		return true;
+
+	/*
+	 * Walk the words the range intersection spans. Plain word tests
+	 * suffice: the scans above guarantee @a has no set bit outside @b's
+	 * range and padding bits are kept clear by all cmask helpers.
+	 */
+	lo_word = lo / 64;
+	hi_word = (hi - 1) / 64;
+
+	bpf_for(i, 0, CMASK_MAX_WORDS) {
+		u32 w = lo_word + i;
+
+		if (w > hi_word)
+			break;
+		if (a->bits[w - a_wbase] & ~b->bits[w - b_wbase])
+			return false;
+	}
+	return true;
+}
+
 /*
  * Population count over [base, base + nr_cids). Padding bits in the head/tail
  * words are guaranteed zero by the mutating helpers, so a flat popcount over
- * all words is correct.
+ * the words the range spans is correct.
  */
 static __always_inline u32 cmask_weight(const struct scx_cmask __arena *m)
 {
-	u32 nr_words = CMASK_NR_WORDS(m->nr_cids), i;
+	u32 nr_words, i;
 	u32 count = 0;
 
+	if (!m->nr_cids)
+		return 0;
+	nr_words = (m->base + m->nr_cids - 1) / 64 - m->base / 64 + 1;
+
 	bpf_for(i, 0, CMASK_MAX_WORDS) {
 		if (i >= nr_words)
 			break;
-- 
2.54.0


  parent reply	other threads:[~2026-07-06  1:41 UTC|newest]

Thread overview: 73+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-07-06  1:40 [PATCHSET v2 sched_ext/for-7.3] sched_ext: Capability-based CPU delegation for sub-schedulers Tejun Heo
2026-07-06  1:40 ` [PATCH v2 sched_ext/for-7.3 01/36] sched_ext: Add SCX_CALL_CID_OP_TASK() for cid-form op dispatch Tejun Heo
2026-07-06  1:40 ` [PATCH v2 sched_ext/for-7.3 02/36] sched_ext: Rename extra_enq_flags to remote_activate_enq_flags Tejun Heo
2026-07-06  1:40 ` [PATCH v2 sched_ext/for-7.3 03/36] sched_ext: Fix premature ops->priv publication in scx_alloc_and_add_sched() Tejun Heo
2026-07-06  1:40 ` Tejun Heo [this message]
2026-07-06  1:40 ` [PATCH v2 sched_ext/for-7.3 05/36] sched_ext: Use READ_ONCE/WRITE_ONCE in cmask word ops and drop _RACY variants Tejun Heo
2026-07-06  1:40 ` [PATCH v2 sched_ext/for-7.3 06/36] tools/sched_ext: scx_qmap - Use bare u64/u32/s32 integer types Tejun Heo
2026-07-06  1:40 ` [PATCH v2 sched_ext/for-7.3 07/36] sched_ext: Reject direct slice and dsq_vtime writes for cid-form schedulers Tejun Heo
2026-07-06  1:40 ` [PATCH v2 sched_ext/for-7.3 08/36] sched_ext: Make scx_bpf_kick_cid() return void Tejun Heo
2026-07-06  1:40 ` [PATCH v2 sched_ext/for-7.3 09/36] sched_ext: Make the kick machinery per-sched Tejun Heo
2026-07-06  1:40 ` [PATCH v2 sched_ext/for-7.3 10/36] sched_ext: Add ops.init_cids() to finalize the cid layout before init Tejun Heo
2026-07-06  2:08   ` sashiko-bot
2026-07-06 23:40     ` Tejun Heo
2026-07-06  1:40 ` [PATCH v2 sched_ext/for-7.3 11/36] sched_ext: Add CID sharding Tejun Heo
2026-07-06  1:53   ` sashiko-bot
2026-07-06 23:40     ` Tejun Heo
2026-07-06  1:40 ` [PATCH v2 sched_ext/for-7.3 12/36] sched_ext: Add shard boundaries to scx_bpf_cid_override() Tejun Heo
2026-07-06  1:40 ` [PATCH v2 sched_ext/for-7.3 13/36] sched_ext: Defer scx_sched kobj sysfs add into the enable workfns Tejun Heo
2026-07-06  1:40 ` [PATCH v2 sched_ext/for-7.3 14/36] sched_ext: Add per-shard scx_sched storage scaffolding Tejun Heo
2026-07-06  1:40 ` [PATCH v2 sched_ext/for-7.3 15/36] sched_ext: Add scx_cmask_ref for validated arena cmask access Tejun Heo
2026-07-06  1:58   ` sashiko-bot
2026-07-06 23:40     ` Tejun Heo
2026-07-06  9:04   ` Andrea Righi
2026-07-06 23:40     ` Tejun Heo
2026-07-06  1:40 ` [PATCH v2 sched_ext/for-7.3 16/36] sched_ext: Build the set_cmask scratch from trusted geometry Tejun Heo
2026-07-06  1:59   ` sashiko-bot
2026-07-06 23:40     ` Tejun Heo
2026-07-06  1:40 ` [PATCH v2 sched_ext/for-7.3 17/36] sched_ext: RCU-protect the sub-sched tree's children/sibling lists Tejun Heo
2026-07-06  2:08   ` sashiko-bot
2026-07-06 23:40     ` Tejun Heo
2026-07-06  1:40 ` [PATCH v2 sched_ext/for-7.3 18/36] sched_ext: Add scx_skip_subtree_pre() Tejun Heo
2026-07-06  1:40 ` [PATCH v2 sched_ext/for-7.3 19/36] sched_ext: Add per-shard cap delegation for sub-schedulers Tejun Heo
2026-07-06  2:13   ` sashiko-bot
2026-07-06 23:40     ` Tejun Heo
2026-07-06  1:40 ` [PATCH v2 sched_ext/for-7.3 20/36] sched_ext: Add coalescing sub_caps_updated() notifier " Tejun Heo
2026-07-06  2:06   ` sashiko-bot
2026-07-06 23:40     ` Tejun Heo
2026-07-06  1:40 ` [PATCH v2 sched_ext/for-7.3 21/36] sched_ext: Maintain per-cpu effective cap copies for single-read checks Tejun Heo
2026-07-06  2:07   ` sashiko-bot
2026-07-06 23:40     ` Tejun Heo
2026-07-06  1:40 ` [PATCH v2 sched_ext/for-7.3 22/36] sched_ext: Add sub_ecaps_updated() effective-cap change notifier Tejun Heo
2026-07-06  2:09   ` sashiko-bot
2026-07-06 23:40     ` Tejun Heo
2026-07-06  1:40 ` [PATCH v2 sched_ext/for-7.3 23/36] sched_ext: Generalize local-DSQ handling to rq-owned DSQs Tejun Heo
2026-07-06  1:40 ` [PATCH v2 sched_ext/for-7.3 24/36] sched_ext: Add reject DSQ for cap-rejected dispatches Tejun Heo
2026-07-06  2:08   ` sashiko-bot
2026-07-06 23:40     ` Tejun Heo
2026-07-06  1:40 ` [PATCH v2 sched_ext/for-7.3 25/36] sched_ext: Add the SCX_CAP_ENQ_IMMED cap Tejun Heo
2026-07-06  2:10   ` sashiko-bot
2026-07-06 23:40     ` Tejun Heo
2026-07-06  1:40 ` [PATCH v2 sched_ext/for-7.3 26/36] sched_ext: Assign a unique id to each scheduler instance Tejun Heo
2026-07-06  1:40 ` [PATCH v2 sched_ext/for-7.3 27/36] sched_ext: Route task slice writes through set_task_slice() Tejun Heo
2026-07-06  2:05   ` sashiko-bot
2026-07-06 23:40     ` Tejun Heo
2026-07-06  9:10   ` Andrea Righi
2026-07-06 23:40     ` Tejun Heo
2026-07-06  1:40 ` [PATCH v2 sched_ext/for-7.3 28/36] sched_ext: Tie cpu occupancy to SCX_CAP_BASE through the task slice Tejun Heo
2026-07-06  2:07   ` sashiko-bot
2026-07-06 23:40     ` Tejun Heo
2026-07-06  1:40 ` [PATCH v2 sched_ext/for-7.3 29/36] sched_ext: Add the SCX_CAP_ENQ cap Tejun Heo
2026-07-06  1:40 ` [PATCH v2 sched_ext/for-7.3 30/36] sched_ext: Gate kicks on SCX_CAP_BASE and preemption on SCX_CAP_PREEMPT Tejun Heo
2026-07-06  1:40 ` [PATCH v2 sched_ext/for-7.3 31/36] sched_ext: Authorize remote-move inserts against the placing scheduler Tejun Heo
2026-07-06  1:40 ` [PATCH v2 sched_ext/for-7.3 32/36] sched_ext: Route ops.update_idle() to sub-schedulers and re-notify owed scheds Tejun Heo
2026-07-06  1:40 ` [PATCH v2 sched_ext/for-7.3 33/36] sched_ext: Replay ecaps notifications suppressed by bypass Tejun Heo
2026-07-06  2:11   ` sashiko-bot
2026-07-06 23:40     ` Tejun Heo
2026-07-06  1:40 ` [PATCH v2 sched_ext/for-7.3 34/36] sched_ext: Add scx_bpf_sub_kill() to evict a child sub-scheduler Tejun Heo
2026-07-06  2:12   ` sashiko-bot
2026-07-06 23:40     ` Tejun Heo
2026-07-06  1:40 ` [PATCH v2 sched_ext/for-7.3 35/36] tools/sched_ext: scx_qmap - Expand hierarchical sub-scheduling Tejun Heo
2026-07-06  2:10   ` sashiko-bot
2026-07-06 23:40     ` Tejun Heo
2026-07-06  1:40 ` [PATCH v2 sched_ext/for-7.3 36/36] tools/sched_ext: scx_qmap - Add sub-sched cap fault injection Tejun Heo

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=20260706014058.439853-5-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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.