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 --- arch/powerpc/sysdev/grackle.c | 43 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 43 insertions(+) create mode 100644 arch/powerpc/sysdev/grackle.c (limited to 'arch/powerpc/sysdev/grackle.c') diff --git a/arch/powerpc/sysdev/grackle.c b/arch/powerpc/sysdev/grackle.c new file mode 100644 index 000000000..7dce8278b --- /dev/null +++ b/arch/powerpc/sysdev/grackle.c @@ -0,0 +1,43 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Functions for setting up and using a MPC106 northbridge + * Extracted from arch/powerpc/platforms/powermac/pci.c. + * + * Copyright (C) 2003 Benjamin Herrenschmuidt (benh@kernel.crashing.org) + * Copyright (C) 1997 Paul Mackerras (paulus@samba.org) + */ +#include +#include +#include +#include + +#include +#include +#include + +#define GRACKLE_CFA(b, d, o) (0x80 | ((b) << 8) | ((d) << 16) \ + | (((o) & ~3) << 24)) + +#define GRACKLE_PICR1_LOOPSNOOP 0x00000010 + +static inline void grackle_set_loop_snoop(struct pci_controller *bp, int enable) +{ + unsigned int val; + + out_be32(bp->cfg_addr, GRACKLE_CFA(0, 0, 0xa8)); + val = in_le32(bp->cfg_data); + val = enable? (val | GRACKLE_PICR1_LOOPSNOOP) : + (val & ~GRACKLE_PICR1_LOOPSNOOP); + out_be32(bp->cfg_addr, GRACKLE_CFA(0, 0, 0xa8)); + out_le32(bp->cfg_data, val); + (void)in_le32(bp->cfg_data); +} + +void __init setup_grackle(struct pci_controller *hose) +{ + setup_indirect_pci(hose, 0xfec00000, 0xfee00000, 0); + if (of_machine_is_compatible("PowerMac1,1")) + pci_add_flags(PCI_REASSIGN_ALL_BUS); + if (of_machine_is_compatible("AAPL,PowerBook1998")) + grackle_set_loop_snoop(hose, 1); +} -- cgit v1.3.1