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/arm/nwfpe/fpopcode.c | 51 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 51 insertions(+) create mode 100644 arch/arm/nwfpe/fpopcode.c (limited to 'arch/arm/nwfpe/fpopcode.c') diff --git a/arch/arm/nwfpe/fpopcode.c b/arch/arm/nwfpe/fpopcode.c new file mode 100644 index 000000000..c680bf1bb --- /dev/null +++ b/arch/arm/nwfpe/fpopcode.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + NetWinder Floating Point Emulator + (c) Rebel.COM, 1998,1999 + + Direct questions, comments to Scott Bambrough + +*/ + +#include "fpa11.h" +#include "softfloat.h" +#include "fpopcode.h" +#include "fpsr.h" +#include "fpmodule.h" +#include "fpmodule.inl" + +#ifdef CONFIG_FPE_NWFPE_XP +const floatx80 floatx80Constant[] = { + { .high = 0x0000, .low = 0x0000000000000000ULL},/* extended 0.0 */ + { .high = 0x3fff, .low = 0x8000000000000000ULL},/* extended 1.0 */ + { .high = 0x4000, .low = 0x8000000000000000ULL},/* extended 2.0 */ + { .high = 0x4000, .low = 0xc000000000000000ULL},/* extended 3.0 */ + { .high = 0x4001, .low = 0x8000000000000000ULL},/* extended 4.0 */ + { .high = 0x4001, .low = 0xa000000000000000ULL},/* extended 5.0 */ + { .high = 0x3ffe, .low = 0x8000000000000000ULL},/* extended 0.5 */ + { .high = 0x4002, .low = 0xa000000000000000ULL},/* extended 10.0 */ +}; +#endif + +const float64 float64Constant[] = { + 0x0000000000000000ULL, /* double 0.0 */ + 0x3ff0000000000000ULL, /* double 1.0 */ + 0x4000000000000000ULL, /* double 2.0 */ + 0x4008000000000000ULL, /* double 3.0 */ + 0x4010000000000000ULL, /* double 4.0 */ + 0x4014000000000000ULL, /* double 5.0 */ + 0x3fe0000000000000ULL, /* double 0.5 */ + 0x4024000000000000ULL /* double 10.0 */ +}; + +const float32 float32Constant[] = { + 0x00000000, /* single 0.0 */ + 0x3f800000, /* single 1.0 */ + 0x40000000, /* single 2.0 */ + 0x40400000, /* single 3.0 */ + 0x40800000, /* single 4.0 */ + 0x40a00000, /* single 5.0 */ + 0x3f000000, /* single 0.5 */ + 0x41200000 /* single 10.0 */ +}; + -- cgit v1.3.1