sched/cache: Keep nr_pref_llc_running in the runnable domain, to fix LLC mis-scheduling buggrafted

alb_break_llc() decides whether to break LLC preference during active
load balance. It does so by testing that every runnable fair task on the
source rq prefers its LLC:

	env->src_rq->nr_pref_llc_running == env->src_rq->cfs.h_nr_runnable

But the two counters cover different sets. nr_pref_llc_running is updated
in account_llc_enqueue()/account_llc_dequeue(), next to cfs_rq->nr_queued,
so it follows queued tasks. h_nr_runnable is updated in set_delayed()/
clear_delayed() and drops delay-dequeued tasks.

So under DELAY_DEQUEUE, a preferring task that goes to sleep stays counted
in nr_pref_llc_running while h_nr_runnable falls. The equality then breaks,
alb_break_llc() returns false, and active balance is free to pull a task
off its preferred LLC. Active balance only moves runnable tasks, and this
is the only LLC check it consults: once the stopper runs, LBF_ACTIVE_LB
skips the per-task test in can_migrate_task(). The runnable set is the one
we want.

Fix it on the counter side. A task should be counted in
nr_pref_llc_running exactly while it is both queued on its preferred LLC
(pref_llc_queued) and runnable (!sched_delayed). Define that membership
once in task_pref_llc_runnable(), and adjust the counter only through
pref_llc_running_inc()/pref_llc_running_dec() from the four sites that
change either input: account_llc_enqueue(), account_llc_dequeue(),
set_delayed() and clear_delayed(). Gating every update on the same
predicate keeps the delay, wake and dequeue paths from double-counting
or underflowing; see the comments at those sites for the ordering.

nr_llc_running and sd->llc_counts are not touched and stay on queued
semantics.

Fixes: 714059f79ff0 ("sched/cache: Handle moving single tasks to/from their preferred LLC")
Closes: https://lore.kernel.org/lkml/20260827135000.735138-1-zhanxusheng@xiaomi.com/
Reported-by: Zhan Xusheng <zhanxusheng@xiaomi.com>
Suggested-by: Chen Yu <yu.c.chen@intel.com>
Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Kayra Cizmeci <kayracizmeci@gmail.com>
Cc: <stable@kernel.org> # v7.2.x
Link: https://patch.msgid.link/06af61afedac32e6477f57feb4d658f6c411c3af.1790035273.git.tim.c.chen@linux.intel.com

1 files changed, 157 insertions, 0 deletions

diff --git a/arch/arm64/lib/csum.c b/arch/arm64/lib/csum.c
new file mode 100644
index 000000000..2432683e4
--- /dev/null
+++ b/arch/arm64/lib/csum.c
@@ -0,0 +1,157 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2019-2020 Arm Ltd.
+
+#include <linux/compiler.h>
+#include <linux/kasan-checks.h>
+#include <linux/kernel.h>
+
+#include <net/checksum.h>
+
+/* Looks dumb, but generates nice-ish code */
+static u64 accumulate(u64 sum, u64 data)
+{
+	__uint128_t tmp = (__uint128_t)sum + data;
+	return tmp + (tmp >> 64);
+}
+
+/*
+ * We over-read the buffer and this makes KASAN unhappy. Instead, disable
+ * instrumentation and call kasan explicitly.
+ */
+unsigned int __no_sanitize_address do_csum(const unsigned char *buff, int len)
+{
+	unsigned int offset, shift, sum;
+	const u64 *ptr;
+	u64 data, sum64 = 0;
+
+	if (unlikely(len <= 0))
+		return 0;
+
+	offset = (unsigned long)buff & 7;
+	/*
+	 * This is to all intents and purposes safe, since rounding down cannot
+	 * result in a different page or cache line being accessed, and @buff
+	 * should absolutely not be pointing to anything read-sensitive. We do,
+	 * however, have to be careful not to piss off KASAN, which means using
+	 * unchecked reads to accommodate the head and tail, for which we'll
+	 * compensate with an explicit check up-front.
+	 */
+	kasan_check_read(buff, len);
+	ptr = (u64 *)(buff - offset);
+	len = len + offset - 8;
+
+	/*
+	 * Head: zero out any excess leading bytes. Shifting back by the same
+	 * amount should be at least as fast as any other way of handling the
+	 * odd/even alignment, and means we can ignore it until the very end.
+	 */
+	shift = offset * 8;
+	data = *ptr++;
+#ifdef __LITTLE_ENDIAN
+	data = (data >> shift) << shift;
+#else
+	data = (data << shift) >> shift;
+#endif
+
+	/*
+	 * Body: straightforward aligned loads from here on (the paired loads
+	 * underlying the quadword type still only need dword alignment). The
+	 * main loop strictly excludes the tail, so the second loop will always
+	 * run at least once.
+	 */
+	while (unlikely(len > 64)) {
+		__uint128_t tmp1, tmp2, tmp3, tmp4;
+
+		tmp1 = *(__uint128_t *)ptr;
+		tmp2 = *(__uint128_t *)(ptr + 2);
+		tmp3 = *(__uint128_t *)(ptr + 4);
+		tmp4 = *(__uint128_t *)(ptr + 6);
+
+		len -= 64;
+		ptr += 8;
+
+		/* This is the "don't dump the carry flag into a GPR" idiom */
+		tmp1 += (tmp1 >> 64) | (tmp1 << 64);
+		tmp2 += (tmp2 >> 64) | (tmp2 << 64);
+		tmp3 += (tmp3 >> 64) | (tmp3 << 64);
+		tmp4 += (tmp4 >> 64) | (tmp4 << 64);
+		tmp1 = ((tmp1 >> 64) << 64) | (tmp2 >> 64);
+		tmp1 += (tmp1 >> 64) | (tmp1 << 64);
+		tmp3 = ((tmp3 >> 64) << 64) | (tmp4 >> 64);
+		tmp3 += (tmp3 >> 64) | (tmp3 << 64);
+		tmp1 = ((tmp1 >> 64) << 64) | (tmp3 >> 64);
+		tmp1 += (tmp1 >> 64) | (tmp1 << 64);
+		tmp1 = ((tmp1 >> 64) << 64) | sum64;
+		tmp1 += (tmp1 >> 64) | (tmp1 << 64);
+		sum64 = tmp1 >> 64;
+	}
+	while (len > 8) {
+		__uint128_t tmp;
+
+		sum64 = accumulate(sum64, data);
+		tmp = *(__uint128_t *)ptr;
+
+		len -= 16;
+		ptr += 2;
+
+#ifdef __LITTLE_ENDIAN
+		data = tmp >> 64;
+		sum64 = accumulate(sum64, tmp);
+#else
+		data = tmp;
+		sum64 = accumulate(sum64, tmp >> 64);
+#endif
+	}
+	if (len > 0) {
+		sum64 = accumulate(sum64, data);
+		data = *ptr;
+		len -= 8;
+	}
+	/*
+	 * Tail: zero any over-read bytes similarly to the head, again
+	 * preserving odd/even alignment.
+	 */
+	shift = len * -8;
+#ifdef __LITTLE_ENDIAN
+	data = (data << shift) >> shift;
+#else
+	data = (data >> shift) << shift;
+#endif
+	sum64 = accumulate(sum64, data);
+
+	/* Finally, folding */
+	sum64 += (sum64 >> 32) | (sum64 << 32);
+	sum = sum64 >> 32;
+	sum += (sum >> 16) | (sum << 16);
+	if (offset & 1)
+		return (u16)swab32(sum);
+
+	return sum >> 16;
+}
+
+__sum16 csum_ipv6_magic(const struct in6_addr *saddr,
+			const struct in6_addr *daddr,
+			__u32 len, __u8 proto, __wsum csum)
+{
+	__uint128_t src, dst;
+	u64 sum = (__force u64)csum;
+
+	src = *(const __uint128_t *)saddr->s6_addr;
+	dst = *(const __uint128_t *)daddr->s6_addr;
+
+	sum += (__force u32)htonl(len);
+#ifdef __LITTLE_ENDIAN
+	sum += (u32)proto << 24;
+#else
+	sum += proto;
+#endif
+	src += (src >> 64) | (src << 64);
+	dst += (dst >> 64) | (dst << 64);
+
+	sum = accumulate(sum, src >> 64);
+	sum = accumulate(sum, dst >> 64);
+
+	sum += ((sum >> 32) | (sum << 32));
+	return csum_fold((__force __wsum)(sum >> 32));
+}
+EXPORT_SYMBOL(csum_ipv6_magic);