tools/sched_ext: scx - Fix cmask_subset(), cmask_equal() and cmask_weight()

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.

Fixes: a58e6b7 ("sched_ext: Add cmask, a base-windowed bitmap over cid space")
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Andrea Righi <arighi@nvidia.com>

Author: htejun

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;