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 --- include/asm-generic/rwonce.h | 98 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 98 insertions(+) create mode 100644 include/asm-generic/rwonce.h (limited to 'include/asm-generic/rwonce.h') diff --git a/include/asm-generic/rwonce.h b/include/asm-generic/rwonce.h new file mode 100644 index 000000000..52b969c7c --- /dev/null +++ b/include/asm-generic/rwonce.h @@ -0,0 +1,98 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Prevent the compiler from merging or refetching reads or writes. The + * compiler is also forbidden from reordering successive instances of + * READ_ONCE and WRITE_ONCE, but only when the compiler is aware of some + * particular ordering. One way to make the compiler aware of ordering is to + * put the two invocations of READ_ONCE or WRITE_ONCE in different C + * statements. + * + * These two macros will also work on aggregate data types like structs or + * unions. + * + * Their two major use cases are: (1) Mediating communication between + * process-level code and irq/NMI handlers, all running on the same CPU, + * and (2) Ensuring that the compiler does not fold, spindle, or otherwise + * mutilate accesses that either do not require ordering or that interact + * with an explicit memory barrier or atomic instruction that provides the + * required ordering. + */ +#ifndef __ASM_GENERIC_RWONCE_H +#define __ASM_GENERIC_RWONCE_H + +#ifndef __ASSEMBLY__ + +#include +#include +#include + +/* + * Yes, this permits 64-bit accesses on 32-bit architectures. These will + * actually be atomic in some cases (namely Armv7 + LPAE), but for others we + * rely on the access being split into 2x32-bit accesses for a 32-bit quantity + * (e.g. a virtual address) and a strong prevailing wind. + */ +#define compiletime_assert_rwonce_type(t) \ + compiletime_assert(__native_word(t) || sizeof(t) == sizeof(long long), \ + "Unsupported access size for {READ,WRITE}_ONCE().") + +/* + * Use __READ_ONCE() instead of READ_ONCE() if you do not require any + * atomicity. Note that this may result in tears! + */ +#ifndef __READ_ONCE +#define __READ_ONCE(x) (*(const volatile __unqual_scalar_typeof(x) *)&(x)) +#endif + +#define READ_ONCE(x) \ +({ \ + compiletime_assert_rwonce_type(x); \ + __READ_ONCE(x); \ +}) + +#define __WRITE_ONCE(x, val) \ +do { \ + *(volatile typeof(x) *)&(x) = (val); \ +} while (0) + +#define WRITE_ONCE(x, val) \ +do { \ + compiletime_assert_rwonce_type(x); \ + __WRITE_ONCE(x, val); \ +} while (0) + +static __no_sanitize_or_inline +unsigned long __read_once_word_nocheck(const void *addr) +{ + return __READ_ONCE(*(unsigned long *)addr); +} + +/* + * Use READ_ONCE_NOCHECK() instead of READ_ONCE() if you need to load a + * word from memory atomically but without telling KASAN/KCSAN. This is + * usually used by unwinding code when walking the stack of a running process. + */ +#define READ_ONCE_NOCHECK(x) \ +({ \ + compiletime_assert(sizeof(x) == sizeof(unsigned long), \ + "Unsupported access size for READ_ONCE_NOCHECK()."); \ + (typeof(x))__read_once_word_nocheck(&(x)); \ +}) + +static __no_sanitize_or_inline +unsigned long read_word_at_a_time(const void *addr) +{ + /* open-coded instrument_read(addr, 1) */ + kasan_check_read(addr, 1); + kcsan_check_read(addr, 1); + + /* + * This load can race with concurrent stores to out-of-bounds memory, + * but READ_ONCE() can't be used because it requires higher alignment + * than plain loads in arm64 builds with LTO. + */ + return *(unsigned long *)addr; +} + +#endif /* __ASSEMBLY__ */ +#endif /* __ASM_GENERIC_RWONCE_H */ -- cgit v1.3.1