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

3 files changed, 119 insertions, 0 deletions

diff --git a/arch/xtensa/boot/lib/.gitignore b/arch/xtensa/boot/lib/.gitignore
new file mode 100644
index 000000000..805a82492
--- /dev/null
+++ b/arch/xtensa/boot/lib/.gitignore
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
+inffast.c
+inflate.c
+inftrees.c
diff --git a/arch/xtensa/boot/lib/Makefile b/arch/xtensa/boot/lib/Makefile
new file mode 100644
index 000000000..0378a22a0
--- /dev/null
+++ b/arch/xtensa/boot/lib/Makefile
@@ -0,0 +1,34 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for some libs needed by zImage.
+#
+
+zlib	:= inffast.c inflate.c inftrees.c
+
+lib-y	+= $(zlib:.c=.o) zmem.o
+
+ccflags-y	:= -I $(srctree)/lib/zlib_inflate
+ifdef CONFIG_FUNCTION_TRACER
+CFLAGS_REMOVE_inflate.o = -pg
+CFLAGS_REMOVE_zmem.o = -pg
+CFLAGS_REMOVE_inftrees.o = -pg
+CFLAGS_REMOVE_inffast.o = -pg
+endif
+
+KASAN_SANITIZE := n
+KCSAN_SANITIZE := n
+KCOV_INSTRUMENT := n
+GCOV_PROFILE := n
+
+CFLAGS_REMOVE_inflate.o += -fstack-protector -fstack-protector-strong
+CFLAGS_REMOVE_zmem.o += -fstack-protector -fstack-protector-strong
+CFLAGS_REMOVE_inftrees.o += -fstack-protector -fstack-protector-strong
+CFLAGS_REMOVE_inffast.o += -fstack-protector -fstack-protector-strong
+
+quiet_cmd_copy_zlib = COPY    $@
+      cmd_copy_zlib = cat $< > $@
+
+$(addprefix $(obj)/,$(zlib)): $(obj)/%: $(srctree)/lib/zlib_inflate/%
+	$(call cmd,copy_zlib)
+
+clean-files	:= $(zlib)
diff --git a/arch/xtensa/boot/lib/zmem.c b/arch/xtensa/boot/lib/zmem.c
new file mode 100644
index 000000000..b89189355
--- /dev/null
+++ b/arch/xtensa/boot/lib/zmem.c
@@ -0,0 +1,81 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/zlib.h>
+
+/* bits taken from ppc */
+
+extern void *avail_ram, *end_avail;
+void gunzip(void *dst, int dstlen, unsigned char *src, int *lenp);
+
+static void exit(void)
+{
+  for (;;);
+}
+
+static void *zalloc(unsigned int size)
+{
+        void *p = avail_ram;
+
+        size = (size + 7) & -8;
+        avail_ram += size;
+        if (avail_ram > end_avail) {
+                //puts("oops... out of memory\n");
+                //pause();
+                exit ();
+        }
+        return p;
+}
+
+#define HEAD_CRC        2
+#define EXTRA_FIELD     4
+#define ORIG_NAME       8
+#define COMMENT         0x10
+#define RESERVED        0xe0
+
+#define DEFLATED        8
+
+void gunzip (void *dst, int dstlen, unsigned char *src, int *lenp)
+{
+	z_stream s;
+	int r, i, flags;
+
+        /* skip header */
+        i = 10;
+        flags = src[3];
+        if (src[2] != DEFLATED || (flags & RESERVED) != 0) {
+                //puts("bad gzipped data\n");
+                exit();
+        }
+        if ((flags & EXTRA_FIELD) != 0)
+                i = 12 + src[10] + (src[11] << 8);
+        if ((flags & ORIG_NAME) != 0)
+                while (src[i++] != 0)
+                        ;
+        if ((flags & COMMENT) != 0)
+                while (src[i++] != 0)
+                        ;
+        if ((flags & HEAD_CRC) != 0)
+                i += 2;
+        if (i >= *lenp) {
+                //puts("gunzip: ran out of data in header\n");
+                exit();
+        }
+
+	s.workspace = zalloc(zlib_inflate_workspacesize());
+        r = zlib_inflateInit2(&s, -MAX_WBITS);
+        if (r != Z_OK) {
+                //puts("inflateInit2 returned "); puthex(r); puts("\n");
+                exit();
+        }
+        s.next_in = src + i;
+        s.avail_in = *lenp - i;
+        s.next_out = dst;
+        s.avail_out = dstlen;
+        r = zlib_inflate(&s, Z_FINISH);
+        if (r != Z_OK && r != Z_STREAM_END) {
+                //puts("inflate returned "); puthex(r); puts("\n");
+                exit();
+        }
+        *lenp = s.next_out - (unsigned char *) dst;
+        zlib_inflateEnd(&s);
+}
+