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 --- io_uring/Makefile | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) create mode 100644 io_uring/Makefile (limited to 'io_uring/Makefile') diff --git a/io_uring/Makefile b/io_uring/Makefile new file mode 100644 index 000000000..c54e328d1 --- /dev/null +++ b/io_uring/Makefile @@ -0,0 +1,28 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for io_uring + +ifdef CONFIG_GCOV_PROFILE_URING +GCOV_PROFILE := y +endif + +obj-$(CONFIG_IO_URING) += io_uring.o opdef.o kbuf.o rsrc.o notif.o \ + tctx.o filetable.o rw.o poll.o \ + tw.o wait.o eventfd.o uring_cmd.o \ + openclose.o sqpoll.o xattr.o nop.o \ + fs.o splice.o sync.o msg_ring.o \ + advise.o openclose.o statx.o timeout.o \ + cancel.o waitid.o register.o \ + truncate.o memmap.o alloc_cache.o \ + query.o loop.o + +obj-$(CONFIG_IO_URING_ZCRX) += zcrx.o +obj-$(CONFIG_IO_WQ) += io-wq.o +obj-$(CONFIG_FUTEX) += futex.o +obj-$(CONFIG_EPOLL) += epoll.o +obj-$(CONFIG_NET_RX_BUSY_POLL) += napi.o +obj-$(CONFIG_NET) += net.o cmd_net.o +obj-$(CONFIG_PROC_FS) += fdinfo.o +obj-$(CONFIG_IO_URING_MOCK_FILE) += mock_file.o +obj-$(CONFIG_IO_URING_BPF) += bpf_filter.o +obj-$(CONFIG_IO_URING_BPF_OPS) += bpf-ops.o -- cgit v1.3.1