From 0d6526f82c3cdefcca47f73f5fc08dc6f335eac6 Mon Sep 17 00:00:00 2001 From: Tim Chen Date: Mon, 21 Sep 2026 17:37:22 -0700 Subject: sched/cache: Keep nr_pref_llc_running in the runnable domain, to fix LLC mis-scheduling bug 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 Suggested-by: Chen Yu Signed-off-by: Tim Chen Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Reviewed-by: Kayra Cizmeci Cc: # v7.2.x Link: https://patch.msgid.link/06af61afedac32e6477f57feb4d658f6c411c3af.1790035273.git.tim.c.chen@linux.intel.com --- drivers/block/Makefile | 43 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 43 insertions(+) create mode 100644 drivers/block/Makefile (limited to 'drivers/block/Makefile') diff --git a/drivers/block/Makefile b/drivers/block/Makefile new file mode 100644 index 000000000..2d8096eb8 --- /dev/null +++ b/drivers/block/Makefile @@ -0,0 +1,43 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for the kernel block device drivers. +# +# 12 June 2000, Christoph Hellwig +# Rewritten to use lists instead of if-statements. +# + +# needed for trace events +ccflags-y += -I$(src) + +obj-$(CONFIG_MAC_FLOPPY) += swim3.o +obj-$(CONFIG_BLK_DEV_SWIM) += swim_mod.o +obj-$(CONFIG_BLK_DEV_FD) += floppy.o +obj-$(CONFIG_AMIGA_FLOPPY) += amiflop.o +obj-$(CONFIG_PS3_DISK) += ps3disk.o +obj-$(CONFIG_PS3_VRAM) += ps3vram.o +obj-$(CONFIG_ATARI_FLOPPY) += ataflop.o +obj-$(CONFIG_AMIGA_Z2RAM) += z2ram.o +obj-$(CONFIG_N64CART) += n64cart.o +obj-$(CONFIG_BLK_DEV_RAM) += brd.o +obj-$(CONFIG_BLK_DEV_LOOP) += loop.o +obj-$(CONFIG_SUNVDC) += sunvdc.o + +obj-$(CONFIG_BLK_DEV_NBD) += nbd.o +obj-$(CONFIG_VIRTIO_BLK) += virtio_blk.o + +obj-$(CONFIG_XEN_BLKDEV_FRONTEND) += xen-blkfront.o +obj-$(CONFIG_XEN_BLKDEV_BACKEND) += xen-blkback/ +obj-$(CONFIG_BLK_DEV_DRBD) += drbd/ +obj-$(CONFIG_BLK_DEV_RBD) += rbd.o +obj-$(CONFIG_BLK_DEV_PCIESSD_MTIP32XX) += mtip32xx/ + +obj-$(CONFIG_ZRAM) += zram/ +obj-$(CONFIG_BLK_DEV_RNBD) += rnbd/ + +obj-$(CONFIG_BLK_DEV_NULL_BLK) += null_blk/ +obj-$(CONFIG_BLK_DEV_RUST_NULL) += rnull/ + +obj-$(CONFIG_BLK_DEV_UBLK) += ublk_drv.o +obj-$(CONFIG_BLK_DEV_ZONED_LOOP) += zloop.o + +swim_mod-y := swim.o swim_asm.o -- cgit v1.3.1