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, 343 insertions, 0 deletions

diff --git a/arch/powerpc/boot/stdio.c b/arch/powerpc/boot/stdio.c
new file mode 100644
index 000000000..b12aa2c0b
--- /dev/null
+++ b/arch/powerpc/boot/stdio.c
@@ -0,0 +1,343 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) Paul Mackerras 1997.
+ */
+#include <stdarg.h>
+#include <stddef.h>
+#include "string.h"
+#include "stdio.h"
+#include "ops.h"
+
+size_t strnlen(const char * s, size_t count)
+{
+	const char *sc;
+
+	for (sc = s; count-- && *sc != '\0'; ++sc)
+		/* nothing */;
+	return sc - s;
+}
+
+char *strrchr(const char *s, int c)
+{
+	const char *last = NULL;
+	do {
+		if (*s == (char)c)
+			last = s;
+	} while (*s++);
+	return (char *)last;
+}
+
+#ifdef __powerpc64__
+
+# define do_div(n, base) ({						\
+	unsigned int __base = (base);					\
+	unsigned int __rem;						\
+	__rem = ((unsigned long long)(n)) % __base;			\
+	(n) = ((unsigned long long)(n)) / __base;			\
+	__rem;								\
+})
+
+#else
+
+extern unsigned int __div64_32(unsigned long long *dividend,
+			       unsigned int divisor);
+
+/* The unnecessary pointer compare is there
+ * to check for type safety (n must be 64bit)
+ */
+# define do_div(n,base) ({						\
+	unsigned int __base = (base);					\
+	unsigned int __rem;						\
+	(void)(((typeof((n)) *)0) == ((unsigned long long *)0));	\
+	if (((n) >> 32) == 0) {						\
+		__rem = (unsigned int)(n) % __base;			\
+		(n) = (unsigned int)(n) / __base;			\
+	} else								\
+		__rem = __div64_32(&(n), __base);			\
+	__rem;								\
+ })
+
+#endif /* __powerpc64__ */
+
+static int skip_atoi(const char **s)
+{
+	int i, c;
+
+	for (i = 0; '0' <= (c = **s) && c <= '9'; ++*s)
+		i = i*10 + c - '0';
+	return i;
+}
+
+#define ZEROPAD	1		/* pad with zero */
+#define SIGN	2		/* unsigned/signed long */
+#define PLUS	4		/* show plus */
+#define SPACE	8		/* space if plus */
+#define LEFT	16		/* left justified */
+#define SPECIAL	32		/* 0x */
+#define LARGE	64		/* use 'ABCDEF' instead of 'abcdef' */
+
+static char * number(char * str, unsigned long long num, int base, int size, int precision, int type)
+{
+	char c,sign,tmp[66];
+	const char *digits="0123456789abcdefghijklmnopqrstuvwxyz";
+	int i;
+
+	if (type & LARGE)
+		digits = "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ";
+	if (type & LEFT)
+		type &= ~ZEROPAD;
+	if (base < 2 || base > 36)
+		return 0;
+	c = (type & ZEROPAD) ? '0' : ' ';
+	sign = 0;
+	if (type & SIGN) {
+		if ((signed long long)num < 0) {
+			sign = '-';
+			num = - (signed long long)num;
+			size--;
+		} else if (type & PLUS) {
+			sign = '+';
+			size--;
+		} else if (type & SPACE) {
+			sign = ' ';
+			size--;
+		}
+	}
+	if (type & SPECIAL) {
+		if (base == 16)
+			size -= 2;
+		else if (base == 8)
+			size--;
+	}
+	i = 0;
+	if (num == 0)
+		tmp[i++]='0';
+	else while (num != 0) {
+		tmp[i++] = digits[do_div(num, base)];
+	}
+	if (i > precision)
+		precision = i;
+	size -= precision;
+	if (!(type&(ZEROPAD+LEFT)))
+		while(size-->0)
+			*str++ = ' ';
+	if (sign)
+		*str++ = sign;
+	if (type & SPECIAL) {
+		if (base==8)
+			*str++ = '0';
+		else if (base==16) {
+			*str++ = '0';
+			*str++ = digits[33];
+		}
+	}
+	if (!(type & LEFT))
+		while (size-- > 0)
+			*str++ = c;
+	while (i < precision--)
+		*str++ = '0';
+	while (i-- > 0)
+		*str++ = tmp[i];
+	while (size-- > 0)
+		*str++ = ' ';
+	return str;
+}
+
+int vsprintf(char *buf, const char *fmt, va_list args)
+{
+	int len;
+	unsigned long long num;
+	int i, base;
+	char * str;
+	const char *s;
+
+	int flags;		/* flags to number() */
+
+	int field_width;	/* width of output field */
+	int precision;		/* min. # of digits for integers; max
+				   number of chars for from string */
+	int qualifier;		/* 'h', 'l', or 'L' for integer fields */
+	                        /* 'z' support added 23/7/1999 S.H.    */
+				/* 'z' changed to 'Z' --davidm 1/25/99 */
+
+	
+	for (str=buf ; *fmt ; ++fmt) {
+		if (*fmt != '%') {
+			*str++ = *fmt;
+			continue;
+		}
+			
+		/* process flags */
+		flags = 0;
+		repeat:
+			++fmt;		/* this also skips first '%' */
+			switch (*fmt) {
+				case '-': flags |= LEFT; goto repeat;
+				case '+': flags |= PLUS; goto repeat;
+				case ' ': flags |= SPACE; goto repeat;
+				case '#': flags |= SPECIAL; goto repeat;
+				case '0': flags |= ZEROPAD; goto repeat;
+				}
+		
+		/* get field width */
+		field_width = -1;
+		if ('0' <= *fmt && *fmt <= '9')
+			field_width = skip_atoi(&fmt);
+		else if (*fmt == '*') {
+			++fmt;
+			/* it's the next argument */
+			field_width = va_arg(args, int);
+			if (field_width < 0) {
+				field_width = -field_width;
+				flags |= LEFT;
+			}
+		}
+
+		/* get the precision */
+		precision = -1;
+		if (*fmt == '.') {
+			++fmt;	
+			if ('0' <= *fmt && *fmt <= '9')
+				precision = skip_atoi(&fmt);
+			else if (*fmt == '*') {
+				++fmt;
+				/* it's the next argument */
+				precision = va_arg(args, int);
+			}
+			if (precision < 0)
+				precision = 0;
+		}
+
+		/* get the conversion qualifier */
+		qualifier = -1;
+		if (*fmt == 'l' && *(fmt + 1) == 'l') {
+			qualifier = 'q';
+			fmt += 2;
+		} else if (*fmt == 'h' || *fmt == 'l' || *fmt == 'L'
+			|| *fmt == 'Z') {
+			qualifier = *fmt;
+			++fmt;
+		}
+
+		/* default base */
+		base = 10;
+
+		switch (*fmt) {
+		case 'c':
+			if (!(flags & LEFT))
+				while (--field_width > 0)
+					*str++ = ' ';
+			*str++ = (unsigned char) va_arg(args, int);
+			while (--field_width > 0)
+				*str++ = ' ';
+			continue;
+
+		case 's':
+			s = va_arg(args, char *);
+			if (!s)
+				s = "<NULL>";
+
+			len = strnlen(s, precision);
+
+			if (!(flags & LEFT))
+				while (len < field_width--)
+					*str++ = ' ';
+			for (i = 0; i < len; ++i)
+				*str++ = *s++;
+			while (len < field_width--)
+				*str++ = ' ';
+			continue;
+
+		case 'p':
+			if (field_width == -1) {
+				field_width = 2*sizeof(void *);
+				flags |= ZEROPAD;
+			}
+			str = number(str,
+				(unsigned long) va_arg(args, void *), 16,
+				field_width, precision, flags);
+			continue;
+
+
+		case 'n':
+			if (qualifier == 'l') {
+				long * ip = va_arg(args, long *);
+				*ip = (str - buf);
+			} else if (qualifier == 'Z') {
+				size_t * ip = va_arg(args, size_t *);
+				*ip = (str - buf);
+			} else {
+				int * ip = va_arg(args, int *);
+				*ip = (str - buf);
+			}
+			continue;
+
+		case '%':
+			*str++ = '%';
+			continue;
+
+		/* integer number formats - set up the flags and "break" */
+		case 'o':
+			base = 8;
+			break;
+
+		case 'X':
+			flags |= LARGE;
+		case 'x':
+			base = 16;
+			break;
+
+		case 'd':
+		case 'i':
+			flags |= SIGN;
+		case 'u':
+			break;
+
+		default:
+			*str++ = '%';
+			if (*fmt)
+				*str++ = *fmt;
+			else
+				--fmt;
+			continue;
+		}
+		if (qualifier == 'l') {
+			num = va_arg(args, unsigned long);
+			if (flags & SIGN)
+				num = (signed long) num;
+		} else if (qualifier == 'q') {
+			num = va_arg(args, unsigned long long);
+			if (flags & SIGN)
+				num = (signed long long) num;
+		} else if (qualifier == 'Z') {
+			num = va_arg(args, size_t);
+		} else if (qualifier == 'h') {
+			num = (unsigned short) va_arg(args, int);
+			if (flags & SIGN)
+				num = (signed short) num;
+		} else {
+			num = va_arg(args, unsigned int);
+			if (flags & SIGN)
+				num = (signed int) num;
+		}
+		str = number(str, num, base, field_width, precision, flags);
+	}
+	*str = '\0';
+	return str-buf;
+}
+
+static char sprint_buf[1024];
+
+int
+printf(const char *fmt, ...)
+{
+	va_list args;
+	int n;
+
+	va_start(args, fmt);
+	n = vsprintf(sprint_buf, fmt, args);
+	va_end(args);
+	if (console_ops.write)
+		console_ops.write(sprint_buf, n);
+	return n;
+}