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, 139 insertions, 0 deletions

diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
new file mode 100644
index 000000000..3f9fb3698
--- /dev/null
+++ b/arch/x86/boot/Makefile
@@ -0,0 +1,139 @@
+#
+# arch/x86/boot/Makefile
+#
+# This file is subject to the terms and conditions of the GNU General Public
+# License.  See the file "COPYING" in the main directory of this archive
+# for more details.
+#
+# Copyright (C) 1994 by Linus Torvalds
+# Changed by many, many contributors over the years.
+#
+
+# If you want to preset the SVGA mode, uncomment the next line and
+# set SVGA_MODE to whatever number you want.
+# Set it to -DSVGA_MODE=NORMAL_VGA if you just want the EGA/VGA mode.
+# The number is the same as you would ordinarily press at bootup.
+
+SVGA_MODE	:= -DSVGA_MODE=NORMAL_VGA
+
+targets		:= vmlinux.bin setup.bin setup.elf bzImage
+targets		+= fdimage fdimage144 fdimage288 image.iso hdimage
+subdir-		:= compressed
+
+setup-y		+= a20.o bioscall.o cmdline.o copy.o cpu.o cpuflags.o cpucheck.o
+setup-y		+= early_serial_console.o edd.o header.o main.o memory.o
+setup-y		+= pm.o pmjump.o printf.o regs.o string.o tty.o video.o
+setup-y		+= video-mode.o version.o
+setup-$(CONFIG_X86_APM_BOOT) += apm.o
+
+# The link order of the video-*.o modules can matter.  In particular,
+# video-vga.o *must* be listed first, followed by video-vesa.o.
+# Hardware-specific drivers should follow in the order they should be
+# probed, and video-bios.o should typically be last.
+setup-y		+= video-vga.o
+setup-y		+= video-vesa.o
+setup-y		+= video-bios.o
+
+targets		+= $(setup-y)
+hostprogs	+= mkcpustr
+
+HOST_EXTRACFLAGS += -I$(srctree)/tools/include \
+		    -include include/generated/autoconf.h \
+	            -D__EXPORTED_HEADERS__
+
+$(obj)/cpu.o: $(obj)/cpustr.h
+
+quiet_cmd_cpustr = CPUSTR  $@
+      cmd_cpustr = $(obj)/mkcpustr > $@
+$(obj)/cpustr.h: $(obj)/mkcpustr FORCE
+	$(call if_changed,cpustr)
+targets += cpustr.h
+
+# ---------------------------------------------------------------------------
+
+KBUILD_CFLAGS	:= $(REALMODE_CFLAGS) -D_SETUP
+KBUILD_AFLAGS	:= $(KBUILD_CFLAGS) -D__ASSEMBLY__
+KBUILD_CFLAGS	+= -fno-asynchronous-unwind-tables
+KBUILD_CFLAGS	+= $(CONFIG_CC_IMPLICIT_FALLTHROUGH)
+
+$(obj)/bzImage: asflags-y  := $(SVGA_MODE)
+
+quiet_cmd_image = BUILD   $@
+      cmd_image = (dd if=$< bs=4k conv=sync status=none; cat $(filter-out $<,$(real-prereqs))) >$@
+
+$(obj)/bzImage: $(obj)/setup.bin $(obj)/vmlinux.bin FORCE
+	$(call if_changed,image)
+	@$(kecho) 'Kernel: $@ is ready' ' (#'$(or $(KBUILD_BUILD_VERSION),`cat .version`)')'
+
+OBJCOPYFLAGS_vmlinux.bin := -O binary -R .note -R .comment -S
+$(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE
+	$(call if_changed,objcopy)
+
+SETUP_OBJS = $(addprefix $(obj)/,$(setup-y))
+
+sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [a-zA-Z] \(startup_32\|efi.._stub_entry\|efi\(32\)\?_pe_entry\|input_data\|kernel_info\|_end\|_ehead\|_text\|_e\?data\|_e\?sbat\|z_.*\)$$/\#define ZO_\2 0x\1/p'
+
+quiet_cmd_zoffset = ZOFFSET $@
+      cmd_zoffset = $(NM) $< | sed -n $(sed-zoffset) > $@
+
+targets += zoffset.h
+$(obj)/zoffset.h: $(obj)/compressed/vmlinux FORCE
+	$(call if_changed,zoffset)
+
+
+AFLAGS_header.o += -I$(objtree)/$(obj)
+$(obj)/header.o: $(obj)/zoffset.h
+
+LDFLAGS_setup.elf	:= -m elf_i386 -z noexecstack -T
+$(obj)/setup.elf: $(src)/setup.ld $(SETUP_OBJS) FORCE
+	$(call if_changed,ld)
+
+OBJCOPYFLAGS_setup.bin	:= -O binary
+$(obj)/setup.bin: $(obj)/setup.elf FORCE
+	$(call if_changed,objcopy)
+
+$(obj)/compressed/vmlinux: FORCE
+	$(Q)$(MAKE) $(build)=$(obj)/compressed $@
+
+# Set this if you want to pass append arguments to the
+# bzdisk/fdimage/hdimage/isoimage kernel
+FDARGS =
+# Set this if you want one or more initrds included in the image
+FDINITRD =
+
+imgdeps = $(obj)/bzImage $(obj)/mtools.conf $(src)/genimage.sh
+
+$(obj)/mtools.conf: $(src)/mtools.conf.in
+	sed -e 's|@OBJ@|$(obj)|g' < $< > $@
+
+targets += mtools.conf
+
+# genimage.sh requires bash, but it also has a bunch of other
+# external dependencies.
+quiet_cmd_genimage = GENIMAGE $3
+      cmd_genimage = $(BASH) $(src)/genimage.sh $2 $3 $(obj)/bzImage \
+		$(obj)/mtools.conf '$(FDARGS)' $(FDINITRD)
+
+PHONY += bzdisk fdimage fdimage144 fdimage288 hdimage isoimage
+
+# This requires write access to /dev/fd0
+# All images require syslinux to be installed; hdimage also requires
+# EDK2/OVMF if the kernel is compiled with the EFI stub.
+bzdisk: $(imgdeps)
+	$(call cmd,genimage,bzdisk,/dev/fd0)
+
+fdimage fdimage144: $(imgdeps)
+	$(call cmd,genimage,fdimage144,$(obj)/fdimage)
+	@$(kecho) 'Kernel: $(obj)/fdimage is ready'
+
+fdimage288: $(imgdeps)
+	$(call cmd,genimage,fdimage288,$(obj)/fdimage)
+	@$(kecho) 'Kernel: $(obj)/fdimage is ready'
+
+hdimage: $(imgdeps)
+	$(call cmd,genimage,hdimage,$(obj)/hdimage)
+	@$(kecho) 'Kernel: $(obj)/hdimage is ready'
+
+isoimage: $(imgdeps)
+	$(call cmd,genimage,isoimage,$(obj)/image.iso)
+	@$(kecho) 'Kernel: $(obj)/image.iso is ready'