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, 172 insertions, 0 deletions

diff --git a/include/uapi/misc/fastrpc.h b/include/uapi/misc/fastrpc.h
new file mode 100644
index 000000000..ba1ea5ed4
--- /dev/null
+++ b/include/uapi/misc/fastrpc.h
@@ -0,0 +1,172 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+
+#ifndef __QCOM_FASTRPC_H__
+#define __QCOM_FASTRPC_H__
+
+#include <linux/types.h>
+
+#define FASTRPC_IOCTL_ALLOC_DMA_BUFF	_IOWR('R', 1, struct fastrpc_alloc_dma_buf)
+#define FASTRPC_IOCTL_FREE_DMA_BUFF	_IOWR('R', 2, __u32)
+#define FASTRPC_IOCTL_INVOKE		_IOWR('R', 3, struct fastrpc_invoke)
+#define FASTRPC_IOCTL_INIT_ATTACH	_IO('R', 4)
+#define FASTRPC_IOCTL_INIT_CREATE	_IOWR('R', 5, struct fastrpc_init_create)
+#define FASTRPC_IOCTL_MMAP		_IOWR('R', 6, struct fastrpc_req_mmap)
+#define FASTRPC_IOCTL_MUNMAP		_IOWR('R', 7, struct fastrpc_req_munmap)
+#define FASTRPC_IOCTL_INIT_ATTACH_SNS	_IO('R', 8)
+#define FASTRPC_IOCTL_INIT_CREATE_STATIC _IOWR('R', 9, struct fastrpc_init_create_static)
+#define FASTRPC_IOCTL_MEM_MAP		_IOWR('R', 10, struct fastrpc_mem_map)
+#define FASTRPC_IOCTL_MEM_UNMAP		_IOWR('R', 11, struct fastrpc_mem_unmap)
+#define FASTRPC_IOCTL_SET_OPTION	_IOWR('R', 12, struct fastrpc_ioctl_set_option)
+#define FASTRPC_IOCTL_GET_DSP_INFO	_IOWR('R', 13, struct fastrpc_ioctl_capability)
+
+/**
+ * enum fastrpc_map_flags - control flags for mapping memory on DSP user process
+ * @FASTRPC_MAP_STATIC: Map memory pages with RW- permission and CACHE WRITEBACK.
+ * The driver is responsible for cache maintenance when passed
+ * the buffer to FastRPC calls. Same virtual address will be
+ * assigned for subsequent FastRPC calls.
+ * @FASTRPC_MAP_RESERVED: Reserved
+ * @FASTRPC_MAP_FD: Map memory pages with RW- permission and CACHE WRITEBACK.
+ * Mapping tagged with a file descriptor. User is responsible for
+ * CPU and DSP cache maintenance for the buffer. Get virtual address
+ * of buffer on DSP using HAP_mmap_get() and HAP_mmap_put() APIs.
+ * @FASTRPC_MAP_FD_DELAYED: Mapping delayed until user call HAP_mmap() and HAP_munmap()
+ * functions on DSP. It is useful to map a buffer with cache modes
+ * other than default modes. User is responsible for CPU and DSP
+ * cache maintenance for the buffer.
+ * @FASTRPC_MAP_FD_NOMAP: This flag is used to skip CPU mapping,
+ * otherwise behaves similar to FASTRPC_MAP_FD_DELAYED flag.
+ * @FASTRPC_MAP_MAX: max count for flags
+ *
+ */
+enum fastrpc_map_flags {
+	FASTRPC_MAP_STATIC = 0,
+	FASTRPC_MAP_RESERVED,
+	FASTRPC_MAP_FD = 2,
+	FASTRPC_MAP_FD_DELAYED,
+	FASTRPC_MAP_FD_NOMAP = 16,
+	FASTRPC_MAP_MAX,
+};
+
+enum fastrpc_proc_attr {
+	/* Macro for Debug attr */
+	FASTRPC_MODE_DEBUG		= (1 << 0),
+	/* Macro for Ptrace */
+	FASTRPC_MODE_PTRACE		= (1 << 1),
+	/* Macro for CRC Check */
+	FASTRPC_MODE_CRC		= (1 << 2),
+	/* Macro for Unsigned PD */
+	FASTRPC_MODE_UNSIGNED_MODULE	= (1 << 3),
+	/* Macro for Adaptive QoS */
+	FASTRPC_MODE_ADAPTIVE_QOS	= (1 << 4),
+	/* Macro for System Process */
+	FASTRPC_MODE_SYSTEM_PROCESS	= (1 << 5),
+	/* Macro for Prvileged Process */
+	FASTRPC_MODE_PRIVILEGED		= (1 << 6),
+};
+
+/* Fastrpc attribute for memory protection of buffers */
+#define FASTRPC_ATTR_SECUREMAP	(1)
+
+/**
+ * FASTRPC_POLL_MODE - Enable/disable poll mode for FastRPC invocations
+ *
+ * Poll mode is an optimization that allows the CPU to poll shared memory
+ * for completion instead of waiting for an interrupt-based response.
+ * This reduces latency for fast-completing operations.
+ *
+ * Restrictions:
+ * - Only supported for USER_PD (User Protection Domain)
+ * - Only applies to dynamic modules (handle > 20)
+ * - Static modules always use interrupt-based completion
+ *
+ * Values:
+ * - 0: Disable poll mode (use interrupt-based completion)
+ * - 1: Enable poll mode (poll shared memory for completion)
+ */
+#define FASTRPC_POLL_MODE	(1)
+
+/* Values for FASTRPC_POLL_MODE request */
+#define FASTRPC_POLL_MODE_DISABLE	0
+#define FASTRPC_POLL_MODE_ENABLE	1
+
+struct fastrpc_invoke_args {
+	__u64 ptr;
+	__u64 length;
+	__s32 fd;
+	__u32 attr;
+};
+
+struct fastrpc_invoke {
+	__u32 handle;
+	__u32 sc;
+	__u64 args;
+};
+
+struct fastrpc_init_create {
+	__u32 filelen;	/* elf file length */
+	__s32 filefd;	/* fd for the file */
+	__u32 attrs;
+	__u32 siglen;
+	__u64 file;	/* pointer to elf file */
+};
+
+struct fastrpc_init_create_static {
+	__u32 namelen;	/* length of pd process name */
+	__u32 memlen;
+	__u64 name;	/* pd process name */
+};
+
+struct fastrpc_alloc_dma_buf {
+	__s32 fd;	/* fd */
+	__u32 flags;	/* flags to map with */
+	__u64 size;	/* size */
+};
+
+struct fastrpc_req_mmap {
+	__s32 fd;
+	__u32 flags;	/* flags for dsp to map with */
+	__u64 vaddrin;	/* optional virtual address */
+	__u64 size;	/* size */
+	__u64 vaddrout;	/* dsp virtual address */
+};
+
+struct fastrpc_mem_map {
+	__s32 version;
+	__s32 fd;		/* fd */
+	__s32 offset;		/* buffer offset */
+	__u32 flags;		/* flags defined in enum fastrpc_map_flags */
+	__u64 vaddrin;		/* buffer virtual address */
+	__u64 length;		/* buffer length */
+	__u64 vaddrout;		/* [out] remote virtual address */
+	__s32 attrs;		/* buffer attributes used for SMMU mapping */
+	__s32 reserved[4];
+};
+
+struct fastrpc_req_munmap {
+	__u64 vaddrout;	/* address to unmap */
+	__u64 size;	/* size */
+};
+
+struct fastrpc_mem_unmap {
+	__s32 vesion;
+	__s32 fd;		/* fd */
+	__u64 vaddr;		/* remote process (dsp) virtual address */
+	__u64 length;		/* buffer size */
+	__s32 reserved[5];
+};
+
+struct fastrpc_ioctl_set_option {
+	__u32 request_id;	/* Request type (e.g., FASTRPC_POLL_MODE) */
+	__u32 value;	/* Request-specific value */
+	__s32 reserved[6];
+};
+
+struct fastrpc_ioctl_capability {
+	__u32 unused; /* deprecated, ignored by the kernel */
+	__u32 attribute_id;
+	__u32 capability;   /* dsp capability */
+	__u32 reserved[4];
+};
+
+#endif /* __QCOM_FASTRPC_H__ */