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/soc/apple/tunable.c | 80 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 80 insertions(+) create mode 100644 drivers/soc/apple/tunable.c (limited to 'drivers/soc/apple/tunable.c') diff --git a/drivers/soc/apple/tunable.c b/drivers/soc/apple/tunable.c new file mode 100644 index 000000000..659323839 --- /dev/null +++ b/drivers/soc/apple/tunable.c @@ -0,0 +1,80 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* + * Apple Silicon hardware tunable support + * + * Each tunable is a list with each entry containing a offset into the MMIO + * region, a mask of bits to be cleared and a set of bits to be set. These + * tunables are passed along by the previous boot stages and vary from device + * to device such that they cannot be hardcoded in the individual drivers. + * + * Copyright (C) The Asahi Linux Contributors + */ + +#include +#include +#include +#include +#include + +struct apple_tunable *devm_apple_tunable_parse(struct device *dev, + struct device_node *np, + const char *name, + struct resource *res) +{ + struct apple_tunable *tunable; + struct property *prop; + const __be32 *p; + size_t sz; + int i; + + if (resource_size(res) < 4) + return ERR_PTR(-EINVAL); + + prop = of_find_property(np, name, NULL); + if (!prop) + return ERR_PTR(-ENOENT); + + if (prop->length % (3 * sizeof(u32))) + return ERR_PTR(-EINVAL); + sz = prop->length / (3 * sizeof(u32)); + + tunable = devm_kzalloc(dev, struct_size(tunable, values, sz), GFP_KERNEL); + if (!tunable) + return ERR_PTR(-ENOMEM); + tunable->sz = sz; + + for (i = 0, p = NULL; i < tunable->sz; ++i) { + p = of_prop_next_u32(prop, p, &tunable->values[i].offset); + p = of_prop_next_u32(prop, p, &tunable->values[i].mask); + p = of_prop_next_u32(prop, p, &tunable->values[i].value); + + /* Sanity checks to catch bugs in our bootloader */ + if (tunable->values[i].offset % 4) + return ERR_PTR(-EINVAL); + if (tunable->values[i].offset > (resource_size(res) - 4)) + return ERR_PTR(-EINVAL); + } + + return tunable; +} +EXPORT_SYMBOL(devm_apple_tunable_parse); + +void apple_tunable_apply(void __iomem *regs, struct apple_tunable *tunable) +{ + size_t i; + + for (i = 0; i < tunable->sz; ++i) { + u32 val, old_val; + + old_val = readl(regs + tunable->values[i].offset); + val = old_val & ~tunable->values[i].mask; + val |= tunable->values[i].value; + if (val != old_val) + writel(val, regs + tunable->values[i].offset); + } +} +EXPORT_SYMBOL(apple_tunable_apply); + +MODULE_LICENSE("Dual MIT/GPL"); +MODULE_AUTHOR("Sven Peter "); +MODULE_DESCRIPTION("Apple Silicon hardware tunable support"); -- cgit v1.3.1