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, 119 insertions, 0 deletions

diff --git a/include/drm/drm_prime.h b/include/drm/drm_prime.h
new file mode 100644
index 000000000..f50f862f0
--- /dev/null
+++ b/include/drm/drm_prime.h
@@ -0,0 +1,119 @@
+/*
+ * Copyright © 2012 Red Hat
+ * Copyright 1999 Precision Insight, Inc., Cedar Park, Texas.
+ * Copyright 2000 VA Linux Systems, Inc., Sunnyvale, California.
+ * Copyright (c) 2009-2010, Code Aurora Forum.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ *
+ * Authors:
+ *      Dave Airlie <airlied@redhat.com>
+ *      Rob Clark <rob.clark@linaro.org>
+ *
+ */
+
+#ifndef __DRM_PRIME_H__
+#define __DRM_PRIME_H__
+
+#include <linux/mutex.h>
+#include <linux/rbtree.h>
+#include <linux/scatterlist.h>
+
+/**
+ * struct drm_prime_file_private - per-file tracking for PRIME
+ *
+ * This just contains the internal &struct dma_buf and handle caches for each
+ * &struct drm_file used by the PRIME core code.
+ */
+struct drm_prime_file_private {
+/* private: */
+	struct mutex lock;
+	struct rb_root dmabufs;
+	struct rb_root handles;
+};
+
+struct device;
+
+struct dma_buf_export_info;
+struct dma_buf;
+struct dma_buf_attachment;
+struct iosys_map;
+
+enum dma_data_direction;
+
+struct drm_device;
+struct drm_gem_object;
+struct drm_file;
+
+/* core prime functions */
+struct dma_buf *drm_gem_dmabuf_export(struct drm_device *dev,
+				      struct dma_buf_export_info *exp_info);
+void drm_gem_dmabuf_release(struct dma_buf *dma_buf);
+
+int drm_gem_prime_fd_to_handle(struct drm_device *dev,
+			       struct drm_file *file_priv, int prime_fd, uint32_t *handle);
+struct dma_buf *drm_gem_prime_handle_to_dmabuf(struct drm_device *dev,
+			       struct drm_file *file_priv, uint32_t handle,
+			       uint32_t flags);
+int drm_gem_prime_handle_to_fd(struct drm_device *dev,
+			       struct drm_file *file_priv, uint32_t handle, uint32_t flags,
+			       int *prime_fd);
+
+/* helper functions for exporting */
+int drm_gem_map_attach(struct dma_buf *dma_buf,
+		       struct dma_buf_attachment *attach);
+void drm_gem_map_detach(struct dma_buf *dma_buf,
+			struct dma_buf_attachment *attach);
+struct sg_table *drm_gem_map_dma_buf(struct dma_buf_attachment *attach,
+				     enum dma_data_direction dir);
+void drm_gem_unmap_dma_buf(struct dma_buf_attachment *attach,
+			   struct sg_table *sgt,
+			   enum dma_data_direction dir);
+int drm_gem_dmabuf_vmap(struct dma_buf *dma_buf, struct iosys_map *map);
+void drm_gem_dmabuf_vunmap(struct dma_buf *dma_buf, struct iosys_map *map);
+
+int drm_gem_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma);
+int drm_gem_dmabuf_mmap(struct dma_buf *dma_buf, struct vm_area_struct *vma);
+
+struct sg_table *drm_prime_pages_to_sg(struct drm_device *dev,
+				       struct page **pages, unsigned int nr_pages);
+struct dma_buf *drm_gem_prime_export(struct drm_gem_object *obj,
+				     int flags);
+
+unsigned long drm_prime_get_contiguous_size(struct sg_table *sgt);
+
+/* helper functions for importing */
+bool drm_gem_is_prime_exported_dma_buf(struct drm_device *dev,
+				       struct dma_buf *dma_buf);
+
+struct drm_gem_object *drm_gem_prime_import_dev(struct drm_device *dev,
+						struct dma_buf *dma_buf,
+						struct device *attach_dev);
+struct drm_gem_object *drm_gem_prime_import(struct drm_device *dev,
+					    struct dma_buf *dma_buf);
+
+void drm_prime_gem_destroy(struct drm_gem_object *obj, struct sg_table *sg);
+
+int drm_prime_sg_to_page_array(struct sg_table *sgt, struct page **pages,
+			       int max_pages);
+int drm_prime_sg_to_dma_addr_array(struct sg_table *sgt, dma_addr_t *addrs,
+				   int max_pages);
+
+#endif /* __DRM_PRIME_H__ */