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 --- Documentation/userspace-api/ebpf/index.rst | 17 +++++++++++++++++ Documentation/userspace-api/ebpf/syscall.rst | 24 ++++++++++++++++++++++++ 2 files changed, 41 insertions(+) create mode 100644 Documentation/userspace-api/ebpf/index.rst create mode 100644 Documentation/userspace-api/ebpf/syscall.rst (limited to 'Documentation/userspace-api/ebpf') diff --git a/Documentation/userspace-api/ebpf/index.rst b/Documentation/userspace-api/ebpf/index.rst new file mode 100644 index 000000000..473dfba78 --- /dev/null +++ b/Documentation/userspace-api/ebpf/index.rst @@ -0,0 +1,17 @@ +.. SPDX-License-Identifier: GPL-2.0 + +eBPF Userspace API +================== + +eBPF is a kernel mechanism to provide a sandboxed runtime environment in the +Linux kernel for runtime extension and instrumentation without changing kernel +source code or loading kernel modules. eBPF programs can be attached to various +kernel subsystems, including networking, tracing and Linux security modules +(LSM). + +For internal kernel documentation on eBPF, see Documentation/bpf/index.rst. + +.. toctree:: + :maxdepth: 1 + + syscall diff --git a/Documentation/userspace-api/ebpf/syscall.rst b/Documentation/userspace-api/ebpf/syscall.rst new file mode 100644 index 000000000..ea9918084 --- /dev/null +++ b/Documentation/userspace-api/ebpf/syscall.rst @@ -0,0 +1,24 @@ +.. SPDX-License-Identifier: GPL-2.0 + +eBPF Syscall +------------ + +:Authors: - Alexei Starovoitov + - Joe Stringer + - Michael Kerrisk + +The primary info for the bpf syscall is available in the `man-pages`_ +for `bpf(2)`_. + +bpf() subcommand reference +~~~~~~~~~~~~~~~~~~~~~~~~~~ + +.. kernel-doc:: include/uapi/linux/bpf.h + :doc: eBPF Syscall Preamble + +.. kernel-doc:: include/uapi/linux/bpf.h + :doc: eBPF Syscall Commands + +.. Links: +.. _man-pages: https://www.kernel.org/doc/man-pages/ +.. _bpf(2): https://man7.org/linux/man-pages/man2/bpf.2.html -- cgit v1.3.1