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, 225 insertions, 0 deletions

diff --git a/drivers/firmware/sysfb.c b/drivers/firmware/sysfb.c
new file mode 100644
index 000000000..8833582c1
--- /dev/null
+++ b/drivers/firmware/sysfb.c
@@ -0,0 +1,225 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Generic System Framebuffers
+ * Copyright (c) 2012-2013 David Herrmann <dh.herrmann@gmail.com>
+ */
+
+/*
+ * Simple-Framebuffer support
+ * Create a platform-device for any available boot framebuffer. The
+ * simple-framebuffer platform device is already available on DT systems, so
+ * this module parses the global "screen_info" object and creates a suitable
+ * platform device compatible with the "simple-framebuffer" DT object. If
+ * the framebuffer is incompatible, we instead create a legacy
+ * "vesa-framebuffer", "efi-framebuffer" or "platform-framebuffer" device and
+ * pass the screen_info as platform_data. This allows legacy drivers
+ * to pick these devices up without messing with simple-framebuffer drivers.
+ * The global "screen_info" is still valid at all times.
+ *
+ * If CONFIG_SYSFB_SIMPLEFB is not selected, never register "simple-framebuffer"
+ * platform devices, but only use legacy framebuffer devices for
+ * backwards compatibility.
+ *
+ * TODO: We set the dev_id field of all platform-devices to 0. This allows
+ * other OF/DT parsers to create such devices, too. However, they must
+ * start at offset 1 for this to work.
+ */
+
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/pci.h>
+#include <linux/platform_data/simplefb.h>
+#include <linux/platform_device.h>
+#include <linux/screen_info.h>
+#include <linux/sysfb.h>
+
+static struct platform_device *pd;
+static DEFINE_MUTEX(disable_lock);
+static bool disabled;
+
+static struct device *sysfb_parent_dev(const struct screen_info *si);
+
+static bool sysfb_unregister(void)
+{
+	if (IS_ERR_OR_NULL(pd))
+		return false;
+
+	platform_device_unregister(pd);
+	pd = NULL;
+
+	return true;
+}
+
+/**
+ * sysfb_disable() - disable the Generic System Framebuffers support
+ * @dev:	the device to check if non-NULL
+ *
+ * This disables the registration of system framebuffer devices that match the
+ * generic drivers that make use of the system framebuffer set up by firmware.
+ *
+ * It also unregisters a device if this was already registered by sysfb_init().
+ *
+ * Context: The function can sleep. A @disable_lock mutex is acquired to serialize
+ *          against sysfb_init(), that registers a system framebuffer device.
+ */
+void sysfb_disable(struct device *dev)
+{
+	struct screen_info *si = &sysfb_primary_display.screen;
+	struct device *parent;
+
+	mutex_lock(&disable_lock);
+	parent = sysfb_parent_dev(si);
+	if (!dev || !parent || dev == parent) {
+		sysfb_unregister();
+		disabled = true;
+	}
+	mutex_unlock(&disable_lock);
+}
+EXPORT_SYMBOL_GPL(sysfb_disable);
+
+/**
+ * sysfb_handles_screen_info() - reports if sysfb handles the global screen_info
+ *
+ * Callers can use sysfb_handles_screen_info() to determine whether the Generic
+ * System Framebuffers (sysfb) can handle the global screen_info data structure
+ * or not. Drivers might need this information to know if they have to setup the
+ * system framebuffer, or if they have to delegate this action to sysfb instead.
+ *
+ * Returns:
+ * True if sysfb handles the global screen_info data structure.
+ */
+bool sysfb_handles_screen_info(void)
+{
+	const struct screen_info *si = &sysfb_primary_display.screen;
+
+	return !!screen_info_video_type(si);
+}
+EXPORT_SYMBOL_GPL(sysfb_handles_screen_info);
+
+#if defined(CONFIG_PCI)
+static bool sysfb_pci_dev_is_enabled(struct pci_dev *pdev)
+{
+	/*
+	 * TODO: Try to integrate this code into the PCI subsystem
+	 */
+	int ret;
+	u16 command;
+
+	ret = pci_read_config_word(pdev, PCI_COMMAND, &command);
+	if (ret != PCIBIOS_SUCCESSFUL)
+		return false;
+	if (!(command & PCI_COMMAND_MEMORY))
+		return false;
+	return true;
+}
+#else
+static bool sysfb_pci_dev_is_enabled(struct pci_dev *pdev)
+{
+	return false;
+}
+#endif
+
+static struct device *sysfb_parent_dev(const struct screen_info *si)
+{
+	struct pci_dev *pdev;
+
+	pdev = screen_info_pci_dev(si);
+	if (IS_ERR(pdev)) {
+		return ERR_CAST(pdev);
+	} else if (pdev) {
+		if (!sysfb_pci_dev_is_enabled(pdev)) {
+			pci_dev_put(pdev);
+			return ERR_PTR(-ENODEV);
+		}
+		return &pdev->dev;
+	}
+
+	return NULL;
+}
+
+static __init int sysfb_init(void)
+{
+	struct sysfb_display_info *dpy = &sysfb_primary_display;
+	struct screen_info *si = &dpy->screen;
+	struct device *parent;
+	unsigned int type;
+	struct simplefb_platform_data mode;
+	const char *name;
+	bool compatible;
+	int ret = 0;
+
+	screen_info_apply_fixups();
+
+	mutex_lock(&disable_lock);
+	if (disabled)
+		goto unlock_mutex;
+
+	sysfb_apply_efi_quirks(si);
+
+	parent = sysfb_parent_dev(si);
+	if (IS_ERR(parent)) {
+		ret = PTR_ERR(parent);
+		goto unlock_mutex;
+	}
+
+	/* try to create a simple-framebuffer device */
+	compatible = sysfb_parse_mode(si, &mode);
+	if (compatible) {
+		pd = sysfb_create_simplefb(si, &mode, parent);
+		if (!IS_ERR(pd))
+			goto put_device;
+	}
+
+	type = screen_info_video_type(si);
+
+	/* if the FB is incompatible, create a legacy framebuffer device */
+	switch (type) {
+	case VIDEO_TYPE_EGAC:
+		name = "ega-framebuffer";
+		break;
+	case VIDEO_TYPE_VGAC:
+		name = "vga-framebuffer";
+		break;
+	case VIDEO_TYPE_VLFB:
+		name = "vesa-framebuffer";
+		break;
+	case VIDEO_TYPE_EFI:
+		name = "efi-framebuffer";
+		break;
+	default:
+		name = "platform-framebuffer";
+		break;
+	}
+
+	pd = platform_device_alloc(name, 0);
+	if (!pd) {
+		ret = -ENOMEM;
+		goto put_device;
+	}
+
+	pd->dev.parent = parent;
+
+	sysfb_set_efifb_fwnode(si, pd);
+
+	ret = platform_device_add_data(pd, dpy, sizeof(*dpy));
+	if (ret)
+		goto err;
+
+	ret = platform_device_add(pd);
+	if (ret)
+		goto err;
+
+	goto put_device;
+err:
+	platform_device_put(pd);
+put_device:
+	put_device(parent);
+unlock_mutex:
+	mutex_unlock(&disable_lock);
+	return ret;
+}
+
+/* must execute after PCI subsystem for EFI quirks */
+device_initcall(sysfb_init);