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, 87 insertions, 0 deletions

diff --git a/arch/powerpc/boot/simpleboot.c b/arch/powerpc/boot/simpleboot.c
new file mode 100644
index 000000000..27591df41
--- /dev/null
+++ b/arch/powerpc/boot/simpleboot.c
@@ -0,0 +1,87 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * The simple platform -- for booting when firmware doesn't supply a device
+ *                        tree or any platform configuration information.
+ *                        All data is extracted from an embedded device tree
+ *                        blob.
+ *
+ * Authors: Scott Wood <scottwood@freescale.com>
+ *          Grant Likely <grant.likely@secretlab.ca>
+ *
+ * Copyright (c) 2007 Freescale Semiconductor, Inc.
+ * Copyright (c) 2008 Secret Lab Technologies Ltd.
+ */
+
+#include "ops.h"
+#include "types.h"
+#include "io.h"
+#include "stdio.h"
+#include <libfdt.h>
+
+BSS_STACK(4*1024);
+
+extern int platform_specific_init(void) __attribute__((weak));
+
+void platform_init(unsigned long r3, unsigned long r4, unsigned long r5,
+		   unsigned long r6, unsigned long r7)
+{
+	const u32 *na, *ns, *reg, *timebase;
+	u64 memsize64;
+	int node, size, i;
+
+	/* Make sure FDT blob is sane */
+	if (fdt_check_header(_dtb_start) != 0)
+		fatal("Invalid device tree blob\n");
+
+	/* Find the #address-cells and #size-cells properties */
+	node = fdt_path_offset(_dtb_start, "/");
+	if (node < 0)
+		fatal("Cannot find root node\n");
+	na = fdt_getprop(_dtb_start, node, "#address-cells", &size);
+	if (!na || (size != 4))
+		fatal("Cannot find #address-cells property");
+	ns = fdt_getprop(_dtb_start, node, "#size-cells", &size);
+	if (!ns || (size != 4))
+		fatal("Cannot find #size-cells property");
+
+	/* Find the memory range */
+	node = fdt_node_offset_by_prop_value(_dtb_start, -1, "device_type",
+					     "memory", sizeof("memory"));
+	if (node < 0)
+		fatal("Cannot find memory node\n");
+	reg = fdt_getprop(_dtb_start, node, "reg", &size);
+	if (size < (*na+*ns) * sizeof(u32))
+		fatal("cannot get memory range\n");
+
+	/* Only interested in memory based at 0 */
+	for (i = 0; i < *na; i++)
+		if (*reg++ != 0)
+			fatal("Memory range is not based at address 0\n");
+
+	/* get the memsize and truncate it to under 4G on 32 bit machines */
+	memsize64 = 0;
+	for (i = 0; i < *ns; i++)
+		memsize64 = (memsize64 << 32) | *reg++;
+	if (sizeof(void *) == 4 && memsize64 >= 0x100000000ULL)
+		memsize64 = 0xffffffff;
+
+	/* finally, setup the timebase */
+	node = fdt_node_offset_by_prop_value(_dtb_start, -1, "device_type",
+					     "cpu", sizeof("cpu"));
+	if (node < 0)
+		fatal("Cannot find cpu node\n");
+	timebase = fdt_getprop(_dtb_start, node, "timebase-frequency", &size);
+	if (timebase && (size == 4))
+		timebase_period_ns = 1000000000 / *timebase;
+
+	/* Now we have the memory size; initialize the heap */
+	simple_alloc_init(_end, memsize64 - (unsigned long)_end, 32, 64);
+
+	/* prepare the device tree and find the console */
+	fdt_init(_dtb_start);
+
+	if (platform_specific_init)
+		platform_specific_init();
+
+	serial_console_init();
+}