sched/cache: Keep nr_pref_llc_running in the runnable domain, to fix LLC mis-scheduling buggrafted

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 <zhanxusheng@xiaomi.com>
Suggested-by: Chen Yu <yu.c.chen@intel.com>
Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Kayra Cizmeci <kayracizmeci@gmail.com>
Cc: <stable@kernel.org> # v7.2.x
Link: https://patch.msgid.link/06af61afedac32e6477f57feb4d658f6c411c3af.1790035273.git.tim.c.chen@linux.intel.com

1 files changed, 127 insertions, 0 deletions

diff --git a/include/uapi/asm-generic/errno.h b/include/uapi/asm-generic/errno.h
new file mode 100644
index 000000000..bd78e69e0
--- /dev/null
+++ b/include/uapi/asm-generic/errno.h
@@ -0,0 +1,127 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _ASM_GENERIC_ERRNO_H
+#define _ASM_GENERIC_ERRNO_H
+
+#include <asm-generic/errno-base.h>
+
+#define	EDEADLK		35	/* Resource deadlock would occur */
+#define	ENAMETOOLONG	36	/* File name too long */
+#define	ENOLCK		37	/* No record locks available */
+
+/*
+ * This error code is special: arch syscall entry code will return
+ * -ENOSYS if users try to call a syscall that doesn't exist.  To keep
+ * failures of syscalls that really do exist distinguishable from
+ * failures due to attempts to use a nonexistent syscall, syscall
+ * implementations should refrain from returning -ENOSYS.
+ */
+#define	ENOSYS		38	/* Invalid system call number */
+
+#define	ENOTEMPTY	39	/* Directory not empty */
+#define	ELOOP		40	/* Too many symbolic links encountered */
+#define	EWOULDBLOCK	EAGAIN	/* Operation would block */
+#define	ENOMSG		42	/* No message of desired type */
+#define	EIDRM		43	/* Identifier removed */
+#define	ECHRNG		44	/* Channel number out of range */
+#define	EL2NSYNC	45	/* Level 2 not synchronized */
+#define	EL3HLT		46	/* Level 3 halted */
+#define	EL3RST		47	/* Level 3 reset */
+#define	ELNRNG		48	/* Link number out of range */
+#define	EUNATCH		49	/* Protocol driver not attached */
+#define	ENOCSI		50	/* No CSI structure available */
+#define	EL2HLT		51	/* Level 2 halted */
+#define	EBADE		52	/* Invalid exchange */
+#define	EBADR		53	/* Invalid request descriptor */
+#define	EXFULL		54	/* Exchange full */
+#define	ENOANO		55	/* No anode */
+#define	EBADRQC		56	/* Invalid request code */
+#define	EBADSLT		57	/* Invalid slot */
+
+#define	EDEADLOCK	EDEADLK
+
+#define	EBFONT		59	/* Bad font file format */
+#define	ENOSTR		60	/* Device not a stream */
+#define	ENODATA		61	/* No data available */
+#define	ETIME		62	/* Timer expired */
+#define	ENOSR		63	/* Out of streams resources */
+#define	ENONET		64	/* Machine is not on the network */
+#define	ENOPKG		65	/* Package not installed */
+#define	EREMOTE		66	/* Object is remote */
+#define	ENOLINK		67	/* Link has been severed */
+#define	EADV		68	/* Advertise error */
+#define	ESRMNT		69	/* Srmount error */
+#define	ECOMM		70	/* Communication error on send */
+#define	EPROTO		71	/* Protocol error */
+#define	EMULTIHOP	72	/* Multihop attempted */
+#define	EDOTDOT		73	/* RFS specific error */
+#define	EBADMSG		74	/* Not a data message */
+#define	EFSBADCRC	EBADMSG	/* Bad CRC detected */
+#define	EOVERFLOW	75	/* Value too large for defined data type */
+#define	ENOTUNIQ	76	/* Name not unique on network */
+#define	EBADFD		77	/* File descriptor in bad state */
+#define	EREMCHG		78	/* Remote address changed */
+#define	ELIBACC		79	/* Can not access a needed shared library */
+#define	ELIBBAD		80	/* Accessing a corrupted shared library */
+#define	ELIBSCN		81	/* .lib section in a.out corrupted */
+#define	ELIBMAX		82	/* Attempting to link in too many shared libraries */
+#define	ELIBEXEC	83	/* Cannot exec a shared library directly */
+#define	EILSEQ		84	/* Illegal byte sequence */
+#define	ERESTART	85	/* Interrupted system call should be restarted */
+#define	ESTRPIPE	86	/* Streams pipe error */
+#define	EUSERS		87	/* Too many users */
+#define	ENOTSOCK	88	/* Socket operation on non-socket */
+#define	EDESTADDRREQ	89	/* Destination address required */
+#define	EMSGSIZE	90	/* Message too long */
+#define	EPROTOTYPE	91	/* Protocol wrong type for socket */
+#define	ENOPROTOOPT	92	/* Protocol not available */
+#define	EPROTONOSUPPORT	93	/* Protocol not supported */
+#define	ESOCKTNOSUPPORT	94	/* Socket type not supported */
+#define	EOPNOTSUPP	95	/* Operation not supported on transport endpoint */
+#define	EPFNOSUPPORT	96	/* Protocol family not supported */
+#define	EAFNOSUPPORT	97	/* Address family not supported by protocol */
+#define	EADDRINUSE	98	/* Address already in use */
+#define	EADDRNOTAVAIL	99	/* Cannot assign requested address */
+#define	ENETDOWN	100	/* Network is down */
+#define	ENETUNREACH	101	/* Network is unreachable */
+#define	ENETRESET	102	/* Network dropped connection because of reset */
+#define	ECONNABORTED	103	/* Software caused connection abort */
+#define	ECONNRESET	104	/* Connection reset by peer */
+#define	ENOBUFS		105	/* No buffer space available */
+#define	EISCONN		106	/* Transport endpoint is already connected */
+#define	ENOTCONN	107	/* Transport endpoint is not connected */
+#define	ESHUTDOWN	108	/* Cannot send after transport endpoint shutdown */
+#define	ETOOMANYREFS	109	/* Too many references: cannot splice */
+#define	ETIMEDOUT	110	/* Connection timed out */
+#define	ECONNREFUSED	111	/* Connection refused */
+#define	EHOSTDOWN	112	/* Host is down */
+#define	EHOSTUNREACH	113	/* No route to host */
+#define	EALREADY	114	/* Operation already in progress */
+#define	EINPROGRESS	115	/* Operation now in progress */
+#define	ESTALE		116	/* Stale file handle */
+#define	EUCLEAN		117	/* Structure needs cleaning */
+#define	EFSCORRUPTED	EUCLEAN	/* Filesystem is corrupted */
+#define	ENOTNAM		118	/* Not a XENIX named type file */
+#define	ENAVAIL		119	/* No XENIX semaphores available */
+#define	EISNAM		120	/* Is a named type file */
+#define	EREMOTEIO	121	/* Remote I/O error */
+#define	EDQUOT		122	/* Quota exceeded */
+
+#define	ENOMEDIUM	123	/* No medium found */
+#define	EMEDIUMTYPE	124	/* Wrong medium type */
+#define	ECANCELED	125	/* Operation Canceled */
+#define	ENOKEY		126	/* Required key not available */
+#define	EKEYEXPIRED	127	/* Key has expired */
+#define	EKEYREVOKED	128	/* Key has been revoked */
+#define	EKEYREJECTED	129	/* Key was rejected by service */
+
+/* for robust mutexes */
+#define	EOWNERDEAD	130	/* Owner died */
+#define	ENOTRECOVERABLE	131	/* State not recoverable */
+
+#define ERFKILL		132	/* Operation not possible due to RF-kill */
+
+#define EHWPOISON	133	/* Memory page has hardware error */
+
+#define EFTYPE		134	/* Wrong file type for the intended operation */
+
+#endif