sched_ext: Maintain an online cid mask in the scheduler arenagrafted

Schedulers on the default cid mapping treat [0, nr_online_cids) as the
online set and restart on hotplug. Schedulers that install their own mapping
with scx_bpf_cid_override() have no way to learn which cids are online: the
count no longer identifies members and the CPU-form cpumask is unusable from
cid programs. This is an obvious hole in the cid API.

Add scx_bpf_online_cmask(), a kernel-maintained cmask in the scheduler's
arena, allocated alongside the per-CPU scratch masks and populated after the
cid mapping is finalized and before ops.init(), for child schedulers too.
The pointer stays valid through ops.exit() with no reference to take. It is
the arena offset as a void pointer, the same form struct_ops arena arguments
arrive in. The verifier types the void return as a scalar for the program's
arena cast.

The mask follows the SCX hotplug notifications: seeded from cpu_active_mask
and updated before ops.cid_online/offline() runs, so it lags cpu_online_mask
only inside a hotplug transition. Updates walk the scheduler list under the
lock that also serializes unlinking. Reads are live, not atomic snapshots.
Root initialization excludes hotplug.

v2: Reworded the getter kerneldoc (Andrea Righi).

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Andrea Righi <arighi@nvidia.com>

1 files changed, 207 insertions, 0 deletions

diff --git a/drivers/reset/reset-simple.c b/drivers/reset/reset-simple.c
new file mode 100644
index 000000000..79e94ecfe
--- /dev/null
+++ b/drivers/reset/reset-simple.c
@@ -0,0 +1,207 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Simple Reset Controller Driver
+ *
+ * Copyright (C) 2017 Pengutronix, Philipp Zabel <kernel@pengutronix.de>
+ *
+ * Based on Allwinner SoCs Reset Controller driver
+ *
+ * Copyright 2013 Maxime Ripard
+ *
+ * Maxime Ripard <maxime.ripard@free-electrons.com>
+ */
+
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/reset-controller.h>
+#include <linux/reset/reset-simple.h>
+#include <linux/spinlock.h>
+
+static inline struct reset_simple_data *
+to_reset_simple_data(struct reset_controller_dev *rcdev)
+{
+	return container_of(rcdev, struct reset_simple_data, rcdev);
+}
+
+static int reset_simple_update(struct reset_controller_dev *rcdev,
+			       unsigned long id, bool assert)
+{
+	struct reset_simple_data *data = to_reset_simple_data(rcdev);
+	int reg_width = sizeof(u32);
+	int bank = id / (reg_width * BITS_PER_BYTE);
+	int offset = id % (reg_width * BITS_PER_BYTE);
+	unsigned long flags;
+	u32 reg;
+
+	spin_lock_irqsave(&data->lock, flags);
+
+	reg = readl(data->membase + (bank * reg_width));
+	if (assert ^ data->active_low)
+		reg |= BIT(offset);
+	else
+		reg &= ~BIT(offset);
+	writel(reg, data->membase + (bank * reg_width));
+
+	spin_unlock_irqrestore(&data->lock, flags);
+
+	return 0;
+}
+
+static int reset_simple_assert(struct reset_controller_dev *rcdev,
+			       unsigned long id)
+{
+	return reset_simple_update(rcdev, id, true);
+}
+
+static int reset_simple_deassert(struct reset_controller_dev *rcdev,
+				 unsigned long id)
+{
+	return reset_simple_update(rcdev, id, false);
+}
+
+static int reset_simple_reset(struct reset_controller_dev *rcdev,
+			      unsigned long id)
+{
+	struct reset_simple_data *data = to_reset_simple_data(rcdev);
+	int ret;
+
+	if (!data->reset_us)
+		return -ENOTSUPP;
+
+	ret = reset_simple_assert(rcdev, id);
+	if (ret)
+		return ret;
+
+	usleep_range(data->reset_us, data->reset_us * 2);
+
+	return reset_simple_deassert(rcdev, id);
+}
+
+static int reset_simple_status(struct reset_controller_dev *rcdev,
+			       unsigned long id)
+{
+	struct reset_simple_data *data = to_reset_simple_data(rcdev);
+	int reg_width = sizeof(u32);
+	int bank = id / (reg_width * BITS_PER_BYTE);
+	int offset = id % (reg_width * BITS_PER_BYTE);
+	u32 reg;
+
+	reg = readl(data->membase + (bank * reg_width));
+
+	return !(reg & BIT(offset)) ^ !data->status_active_low;
+}
+
+const struct reset_control_ops reset_simple_ops = {
+	.assert		= reset_simple_assert,
+	.deassert	= reset_simple_deassert,
+	.reset		= reset_simple_reset,
+	.status		= reset_simple_status,
+};
+EXPORT_SYMBOL_GPL(reset_simple_ops);
+
+/**
+ * struct reset_simple_devdata - simple reset controller properties
+ * @reg_offset: offset between base address and first reset register.
+ * @nr_resets: number of resets. If not set, default to resource size in bits.
+ * @active_low: if true, bits are cleared to assert the reset. Otherwise, bits
+ *              are set to assert the reset.
+ * @status_active_low: if true, bits read back as cleared while the reset is
+ *                     asserted. Otherwise, bits read back as set while the
+ *                     reset is asserted.
+ */
+struct reset_simple_devdata {
+	u32 reg_offset;
+	u32 nr_resets;
+	bool active_low;
+	bool status_active_low;
+};
+
+#define SOCFPGA_NR_BANKS	8
+
+static const struct reset_simple_devdata reset_simple_socfpga = {
+	.reg_offset = 0x20,
+	.nr_resets = SOCFPGA_NR_BANKS * 32,
+	.status_active_low = true,
+};
+
+static const struct reset_simple_devdata reset_simple_active_low = {
+	.active_low = true,
+	.status_active_low = true,
+};
+
+static const struct of_device_id reset_simple_dt_ids[] = {
+	{ .compatible = "altr,stratix10-rst-mgr",
+		.data = &reset_simple_socfpga },
+	{ .compatible = "st,stm32-rcc", },
+	{ .compatible = "allwinner,sun6i-a31-clock-reset",
+		.data = &reset_simple_active_low },
+	{ .compatible = "zte,zx296718-reset",
+		.data = &reset_simple_active_low },
+	{ .compatible = "aspeed,ast2400-lpc-reset" },
+	{ .compatible = "aspeed,ast2500-lpc-reset" },
+	{ .compatible = "aspeed,ast2600-lpc-reset" },
+	{ .compatible = "bitmain,bm1880-reset",
+		.data = &reset_simple_active_low },
+	{ .compatible = "brcm,bcm4908-misc-pcie-reset",
+		.data = &reset_simple_active_low },
+	{ .compatible = "snps,dw-high-reset" },
+	{ .compatible = "snps,dw-low-reset",
+		.data = &reset_simple_active_low },
+	{ .compatible = "sophgo,cv1800b-reset",
+		.data = &reset_simple_active_low },
+	{ .compatible = "sophgo,sg2042-reset",
+		.data = &reset_simple_active_low },
+	{ /* sentinel */ },
+};
+
+static int reset_simple_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	const struct reset_simple_devdata *devdata;
+	struct reset_simple_data *data;
+	void __iomem *membase;
+	struct resource *res;
+	u32 reg_offset = 0;
+
+	devdata = of_device_get_match_data(dev);
+
+	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	membase = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
+	if (IS_ERR(membase))
+		return PTR_ERR(membase);
+
+	spin_lock_init(&data->lock);
+	data->membase = membase;
+	data->rcdev.owner = THIS_MODULE;
+	data->rcdev.nr_resets = resource_size(res) * BITS_PER_BYTE;
+	data->rcdev.ops = &reset_simple_ops;
+	data->rcdev.of_node = dev->of_node;
+
+	if (devdata) {
+		reg_offset = devdata->reg_offset;
+		if (devdata->nr_resets)
+			data->rcdev.nr_resets = devdata->nr_resets;
+		data->active_low = devdata->active_low;
+		data->status_active_low = devdata->status_active_low;
+	}
+
+	data->membase += reg_offset;
+
+	return devm_reset_controller_register(dev, &data->rcdev);
+}
+
+static struct platform_driver reset_simple_driver = {
+	.probe	= reset_simple_probe,
+	.driver = {
+		.name		= "simple-reset",
+		.of_match_table	= reset_simple_dt_ids,
+	},
+};
+builtin_platform_driver(reset_simple_driver);