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, 103 insertions, 0 deletions

diff --git a/arch/alpha/lib/stacktrace.c b/arch/alpha/lib/stacktrace.c
new file mode 100644
index 000000000..2b1176dd5
--- /dev/null
+++ b/arch/alpha/lib/stacktrace.c
@@ -0,0 +1,103 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+
+typedef unsigned int instr;
+
+#define MAJOR_OP	0xfc000000
+#define LDA_OP		0x20000000
+#define STQ_OP		0xb4000000
+#define BR_OP		0xc0000000
+
+#define STK_ALLOC_1	0x23de8000 /* lda $30,-X($30) */
+#define STK_ALLOC_1M	0xffff8000
+#define STK_ALLOC_2	0x43c0153e /* subq $30,X,$30 */
+#define STK_ALLOC_2M	0xffe01fff
+
+#define MEM_REG		0x03e00000
+#define MEM_BASE	0x001f0000
+#define MEM_OFF		0x0000ffff
+#define MEM_OFF_SIGN	0x00008000
+#define	BASE_SP		0x001e0000
+
+#define STK_ALLOC_MATCH(INSTR)			\
+  (((INSTR) & STK_ALLOC_1M) == STK_ALLOC_1	\
+   || ((INSTR) & STK_ALLOC_2M) == STK_ALLOC_2)
+#define STK_PUSH_MATCH(INSTR) \
+  (((INSTR) & (MAJOR_OP | MEM_BASE | MEM_OFF_SIGN)) == (STQ_OP | BASE_SP))
+#define MEM_OP_OFFSET(INSTR) \
+  (((long)((INSTR) & MEM_OFF) << 48) >> 48)
+#define MEM_OP_REG(INSTR) \
+  (((INSTR) & MEM_REG) >> 22)
+
+/* Branches, jumps, PAL calls, and illegal opcodes end a basic block. */
+#define BB_END(INSTR)						\
+  (((instr)(INSTR) >= BR_OP) | ((instr)(INSTR) < LDA_OP) |	\
+   ((((instr)(INSTR) ^ 0x60000000) < 0x20000000) &		\
+    (((instr)(INSTR) & 0x0c000000) != 0)))
+
+#define IS_KERNEL_TEXT(PC) ((unsigned long)(PC) > START_ADDR)
+
+static char reg_name[][4] = {
+	"v0 ", "t0 ", "t1 ", "t2 ", "t3 ", "t4 ", "t5 ", "t6 ", "t7 ",
+	"s0 ", "s1 ", "s2 ", "s3 ", "s4 ", "s5 ", "s6 ", "a0 ", "a1 ",
+	"a2 ", "a3 ", "a4 ", "a5 ", "t8 ", "t9 ", "t10", "t11", "ra ",
+	"pv ", "at ", "gp ", "sp ", "0"
+};
+
+
+static instr *
+display_stored_regs(instr * pro_pc, unsigned char * sp)
+{
+	instr * ret_pc = 0;
+	int reg;
+	unsigned long value;
+
+	printk("Prologue [<%p>], Frame %p:\n", pro_pc, sp);
+	while (!BB_END(*pro_pc))
+		if (STK_PUSH_MATCH(*pro_pc)) {
+			reg = (*pro_pc & MEM_REG) >> 21;
+			value = *(unsigned long *)(sp + (*pro_pc & MEM_OFF));
+			if (reg == 26)
+				ret_pc = (instr *)value;
+			printk("\t\t%s / 0x%016lx\n", reg_name[reg], value);
+		}
+	return ret_pc;
+}
+
+static instr *
+seek_prologue(instr * pc)
+{
+	while (!STK_ALLOC_MATCH(*pc))
+		--pc;
+	while (!BB_END(*(pc - 1)))
+		--pc;
+	return pc;
+}
+
+static long
+stack_increment(instr * prologue_pc)
+{
+	while (!STK_ALLOC_MATCH(*prologue_pc))
+		++prologue_pc;
+
+	/* Count the bytes allocated. */
+	if ((*prologue_pc & STK_ALLOC_1M) == STK_ALLOC_1M)
+		return -(((long)(*prologue_pc) << 48) >> 48);
+	else
+		return (*prologue_pc >> 13) & 0xff;
+}
+
+void
+stacktrace(void)
+{
+	instr * ret_pc;
+	instr * prologue = (instr *)stacktrace;
+	unsigned char *sp = (unsigned char *)current_stack_pointer;
+
+	printk("\tstack trace:\n");
+	do {
+		ret_pc = display_stored_regs(prologue, sp);
+		sp += stack_increment(prologue);
+		prologue = seek_prologue(ret_pc);
+	} while (IS_KERNEL_TEXT(ret_pc));
+}