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/drivers/usb/cdns3/cdns3-debug.h b/drivers/usb/cdns3/cdns3-debug.h
new file mode 100644
index 000000000..4618cfe85
--- /dev/null
+++ b/drivers/usb/cdns3/cdns3-debug.h
@@ -0,0 +1,157 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Cadence USBSS DRD Driver.
+ * Debug header file.
+ *
+ * Copyright (C) 2018-2019 Cadence.
+ *
+ * Author: Pawel Laszczak <pawell@cadence.com>
+ */
+#ifndef __LINUX_CDNS3_DEBUG
+#define __LINUX_CDNS3_DEBUG
+
+#include "core.h"
+
+static inline char *cdns3_decode_usb_irq(char *str,
+					 enum usb_device_speed speed,
+					 u32 usb_ists)
+{
+	int ret;
+
+	ret = sprintf(str, "IRQ %08x = ", usb_ists);
+
+	if (usb_ists & (USB_ISTS_CON2I | USB_ISTS_CONI)) {
+		ret += sprintf(str + ret, "Connection %s\n",
+			       usb_speed_string(speed));
+	}
+	if (usb_ists & USB_ISTS_DIS2I || usb_ists & USB_ISTS_DISI)
+		ret += sprintf(str + ret, "Disconnection ");
+	if (usb_ists & USB_ISTS_L2ENTI)
+		ret += sprintf(str + ret, "suspended ");
+	if (usb_ists & USB_ISTS_L1ENTI)
+		ret += sprintf(str + ret, "L1 enter ");
+	if (usb_ists & USB_ISTS_L1EXTI)
+		ret += sprintf(str + ret, "L1 exit ");
+	if (usb_ists & USB_ISTS_L2ENTI)
+		ret += sprintf(str + ret, "L2 enter ");
+	if (usb_ists & USB_ISTS_L2EXTI)
+		ret += sprintf(str + ret, "L2 exit ");
+	if (usb_ists & USB_ISTS_U3EXTI)
+		ret += sprintf(str + ret, "U3 exit ");
+	if (usb_ists & USB_ISTS_UWRESI)
+		ret += sprintf(str + ret, "Warm Reset ");
+	if (usb_ists & USB_ISTS_UHRESI)
+		ret += sprintf(str + ret, "Hot Reset ");
+	if (usb_ists & USB_ISTS_U2RESI)
+		ret += sprintf(str + ret, "Reset");
+
+	return str;
+}
+
+static inline  char *cdns3_decode_ep_irq(char *str,
+					 u32 ep_sts,
+					 const char *ep_name)
+{
+	int ret;
+
+	ret = sprintf(str, "IRQ for %s: %08x ", ep_name, ep_sts);
+
+	if (ep_sts & EP_STS_SETUP)
+		ret += sprintf(str + ret, "SETUP ");
+	if (ep_sts & EP_STS_IOC)
+		ret += sprintf(str + ret, "IOC ");
+	if (ep_sts & EP_STS_ISP)
+		ret += sprintf(str + ret, "ISP ");
+	if (ep_sts & EP_STS_DESCMIS)
+		ret += sprintf(str + ret, "DESCMIS ");
+	if (ep_sts & EP_STS_STREAMR)
+		ret += sprintf(str + ret, "STREAMR ");
+	if (ep_sts & EP_STS_MD_EXIT)
+		ret += sprintf(str + ret, "MD_EXIT ");
+	if (ep_sts & EP_STS_TRBERR)
+		ret += sprintf(str + ret, "TRBERR ");
+	if (ep_sts & EP_STS_NRDY)
+		ret += sprintf(str + ret, "NRDY ");
+	if (ep_sts & EP_STS_PRIME)
+		ret += sprintf(str + ret, "PRIME ");
+	if (ep_sts & EP_STS_SIDERR)
+		ret += sprintf(str + ret, "SIDERRT ");
+	if (ep_sts & EP_STS_OUTSMM)
+		ret += sprintf(str + ret, "OUTSMM ");
+	if (ep_sts & EP_STS_ISOERR)
+		ret += sprintf(str + ret, "ISOERR ");
+	if (ep_sts & EP_STS_IOT)
+		ret += sprintf(str + ret, "IOT ");
+
+	return str;
+}
+
+static inline char *cdns3_decode_epx_irq(char *str,
+					 char *ep_name,
+					 u32 ep_sts)
+{
+	return cdns3_decode_ep_irq(str, ep_sts, ep_name);
+}
+
+static inline char *cdns3_decode_ep0_irq(char *str,
+					 int dir,
+					 u32 ep_sts)
+{
+	return cdns3_decode_ep_irq(str, ep_sts,
+				   dir ? "ep0IN" : "ep0OUT");
+}
+
+/**
+ * Debug a transfer ring.
+ *
+ * Prints out all TRBs in the endpoint ring, even those after the Link TRB.
+ *.
+ */
+static inline char *cdns3_dbg_ring(struct cdns3_endpoint *priv_ep, char *str)
+{
+	dma_addr_t addr = priv_ep->trb_pool_dma;
+	struct cdns3_trb *trb;
+	int trb_per_sector;
+	int ret = 0;
+	int i;
+
+	trb_per_sector = GET_TRBS_PER_SEGMENT(priv_ep->type);
+
+	trb = &priv_ep->trb_pool[priv_ep->dequeue];
+	ret += sprintf(str + ret, "\n\t\tRing contents for %s:", priv_ep->name);
+
+	ret += sprintf(str + ret,
+		       "\n\t\tRing deq index: %d, trb: %p (virt), 0x%llx (dma)\n",
+		       priv_ep->dequeue, trb,
+		       (unsigned long long)cdns3_trb_virt_to_dma(priv_ep, trb));
+
+	trb = &priv_ep->trb_pool[priv_ep->enqueue];
+	ret += sprintf(str + ret,
+		       "\t\tRing enq index: %d, trb: %p (virt), 0x%llx (dma)\n",
+		       priv_ep->enqueue, trb,
+		       (unsigned long long)cdns3_trb_virt_to_dma(priv_ep, trb));
+
+	ret += sprintf(str + ret,
+		       "\t\tfree trbs: %d, CCS=%d, PCS=%d\n",
+		       priv_ep->free_trbs, priv_ep->ccs, priv_ep->pcs);
+
+	if (trb_per_sector > TRBS_PER_SEGMENT) {
+		sprintf(str + ret, "\t\tTransfer ring %d too big\n",
+			trb_per_sector);
+		return str;
+	}
+
+	for (i = 0; i < trb_per_sector; ++i) {
+		trb = &priv_ep->trb_pool[i];
+		ret += sprintf(str + ret,
+			"\t\t@%pad %08x %08x %08x\n", &addr,
+			le32_to_cpu(trb->buffer),
+			le32_to_cpu(trb->length),
+			le32_to_cpu(trb->control));
+		addr += sizeof(*trb);
+	}
+
+	return str;
+}
+
+#endif /*__LINUX_CDNS3_DEBUG*/