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, 158 insertions, 0 deletions

diff --git a/arch/powerpc/boot/elf.h b/arch/powerpc/boot/elf.h
new file mode 100644
index 000000000..f6aa7c20f
--- /dev/null
+++ b/arch/powerpc/boot/elf.h
@@ -0,0 +1,158 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _PPC_BOOT_ELF_H_
+#define _PPC_BOOT_ELF_H_
+
+/* 32-bit ELF base types. */
+typedef unsigned int Elf32_Addr;
+typedef unsigned short Elf32_Half;
+typedef unsigned int Elf32_Off;
+typedef signed int Elf32_Sword;
+typedef unsigned int Elf32_Word;
+
+/* 64-bit ELF base types. */
+typedef unsigned long long Elf64_Addr;
+typedef unsigned short Elf64_Half;
+typedef signed short Elf64_SHalf;
+typedef unsigned long long Elf64_Off;
+typedef signed int Elf64_Sword;
+typedef unsigned int Elf64_Word;
+typedef unsigned long long Elf64_Xword;
+typedef signed long long Elf64_Sxword;
+
+/* These constants are for the segment types stored in the image headers */
+#define PT_NULL    0
+#define PT_LOAD    1
+#define PT_DYNAMIC 2
+#define PT_INTERP  3
+#define PT_NOTE    4
+#define PT_SHLIB   5
+#define PT_PHDR    6
+#define PT_TLS     7		/* Thread local storage segment */
+#define PT_LOOS    0x60000000	/* OS-specific */
+#define PT_HIOS    0x6fffffff	/* OS-specific */
+#define PT_LOPROC  0x70000000
+#define PT_HIPROC  0x7fffffff
+#define PT_GNU_EH_FRAME		0x6474e550
+
+#define PT_GNU_STACK	(PT_LOOS + 0x474e551)
+
+/* These constants define the different elf file types */
+#define ET_NONE   0
+#define ET_REL    1
+#define ET_EXEC   2
+#define ET_DYN    3
+#define ET_CORE   4
+#define ET_LOPROC 0xff00
+#define ET_HIPROC 0xffff
+
+/* These constants define the various ELF target machines */
+#define EM_NONE  0
+#define EM_PPC	       20	/* PowerPC */
+#define EM_PPC64       21	/* PowerPC64 */
+
+#define EI_NIDENT	16
+
+typedef struct elf32_hdr {
+	unsigned char e_ident[EI_NIDENT];
+	Elf32_Half e_type;
+	Elf32_Half e_machine;
+	Elf32_Word e_version;
+	Elf32_Addr e_entry;	/* Entry point */
+	Elf32_Off e_phoff;
+	Elf32_Off e_shoff;
+	Elf32_Word e_flags;
+	Elf32_Half e_ehsize;
+	Elf32_Half e_phentsize;
+	Elf32_Half e_phnum;
+	Elf32_Half e_shentsize;
+	Elf32_Half e_shnum;
+	Elf32_Half e_shstrndx;
+} Elf32_Ehdr;
+
+typedef struct elf64_hdr {
+	unsigned char e_ident[16];	/* ELF "magic number" */
+	Elf64_Half e_type;
+	Elf64_Half e_machine;
+	Elf64_Word e_version;
+	Elf64_Addr e_entry;	/* Entry point virtual address */
+	Elf64_Off e_phoff;	/* Program header table file offset */
+	Elf64_Off e_shoff;	/* Section header table file offset */
+	Elf64_Word e_flags;
+	Elf64_Half e_ehsize;
+	Elf64_Half e_phentsize;
+	Elf64_Half e_phnum;
+	Elf64_Half e_shentsize;
+	Elf64_Half e_shnum;
+	Elf64_Half e_shstrndx;
+} Elf64_Ehdr;
+
+/* These constants define the permissions on sections in the program
+   header, p_flags. */
+#define PF_R		0x4
+#define PF_W		0x2
+#define PF_X		0x1
+
+typedef struct elf32_phdr {
+	Elf32_Word p_type;
+	Elf32_Off p_offset;
+	Elf32_Addr p_vaddr;
+	Elf32_Addr p_paddr;
+	Elf32_Word p_filesz;
+	Elf32_Word p_memsz;
+	Elf32_Word p_flags;
+	Elf32_Word p_align;
+} Elf32_Phdr;
+
+typedef struct elf64_phdr {
+	Elf64_Word p_type;
+	Elf64_Word p_flags;
+	Elf64_Off p_offset;	/* Segment file offset */
+	Elf64_Addr p_vaddr;	/* Segment virtual address */
+	Elf64_Addr p_paddr;	/* Segment physical address */
+	Elf64_Xword p_filesz;	/* Segment size in file */
+	Elf64_Xword p_memsz;	/* Segment size in memory */
+	Elf64_Xword p_align;	/* Segment alignment, file & memory */
+} Elf64_Phdr;
+
+#define	EI_MAG0		0	/* e_ident[] indexes */
+#define	EI_MAG1		1
+#define	EI_MAG2		2
+#define	EI_MAG3		3
+#define	EI_CLASS	4
+#define	EI_DATA		5
+#define	EI_VERSION	6
+#define	EI_OSABI	7
+#define	EI_PAD		8
+
+#define	ELFMAG0		0x7f	/* EI_MAG */
+#define	ELFMAG1		'E'
+#define	ELFMAG2		'L'
+#define	ELFMAG3		'F'
+#define	ELFMAG		"\177ELF"
+#define	SELFMAG		4
+
+#define	ELFCLASSNONE	0	/* EI_CLASS */
+#define	ELFCLASS32	1
+#define	ELFCLASS64	2
+#define	ELFCLASSNUM	3
+
+#define ELFDATANONE	0	/* e_ident[EI_DATA] */
+#define ELFDATA2LSB	1
+#define ELFDATA2MSB	2
+
+#define EV_NONE		0	/* e_version, EI_VERSION */
+#define EV_CURRENT	1
+#define EV_NUM		2
+
+#define ELFOSABI_NONE	0
+#define ELFOSABI_LINUX	3
+
+struct elf_info {
+	unsigned long loadsize;
+	unsigned long memsize;
+	unsigned long elfoffset;
+};
+int parse_elf64(void *hdr, struct elf_info *info);
+int parse_elf32(void *hdr, struct elf_info *info);
+
+#endif				/* _PPC_BOOT_ELF_H_ */