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, 77 insertions, 0 deletions

diff --git a/fs/ntfs/malloc.h b/fs/ntfs/malloc.h
new file mode 100644
index 000000000..706842573
--- /dev/null
+++ b/fs/ntfs/malloc.h
@@ -0,0 +1,77 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * malloc.h - NTFS kernel memory handling. Part of the Linux-NTFS project.
+ *
+ * Copyright (c) 2001-2005 Anton Altaparmakov
+ */
+
+#ifndef _LINUX_NTFS_MALLOC_H
+#define _LINUX_NTFS_MALLOC_H
+
+#include <linux/vmalloc.h>
+#include <linux/slab.h>
+#include <linux/highmem.h>
+
+/**
+ * __ntfs_malloc - allocate memory in multiples of pages
+ * @size:	number of bytes to allocate
+ * @gfp_mask:	extra flags for the allocator
+ *
+ * Internal function.  You probably want ntfs_malloc_nofs()...
+ *
+ * Allocates @size bytes of memory, rounded up to multiples of PAGE_SIZE and
+ * returns a pointer to the allocated memory.
+ *
+ * If there was insufficient memory to complete the request, return NULL.
+ * Depending on @gfp_mask the allocation may be guaranteed to succeed.
+ */
+static inline void *__ntfs_malloc(unsigned long size, gfp_t gfp_mask)
+{
+	if (likely(size <= PAGE_SIZE)) {
+		BUG_ON(!size);
+		/* kmalloc() has per-CPU caches so is faster for now. */
+		return kmalloc(PAGE_SIZE, gfp_mask & ~__GFP_HIGHMEM);
+		/* return (void *)__get_free_page(gfp_mask); */
+	}
+	if (likely((size >> PAGE_SHIFT) < totalram_pages()))
+		return __vmalloc(size, gfp_mask);
+	return NULL;
+}
+
+/**
+ * ntfs_malloc_nofs - allocate memory in multiples of pages
+ * @size:	number of bytes to allocate
+ *
+ * Allocates @size bytes of memory, rounded up to multiples of PAGE_SIZE and
+ * returns a pointer to the allocated memory.
+ *
+ * If there was insufficient memory to complete the request, return NULL.
+ */
+static inline void *ntfs_malloc_nofs(unsigned long size)
+{
+	return __ntfs_malloc(size, GFP_NOFS | __GFP_HIGHMEM);
+}
+
+/**
+ * ntfs_malloc_nofs_nofail - allocate memory in multiples of pages
+ * @size:	number of bytes to allocate
+ *
+ * Allocates @size bytes of memory, rounded up to multiples of PAGE_SIZE and
+ * returns a pointer to the allocated memory.
+ *
+ * This function guarantees that the allocation will succeed.  It will sleep
+ * for as long as it takes to complete the allocation.
+ *
+ * If there was insufficient memory to complete the request, return NULL.
+ */
+static inline void *ntfs_malloc_nofs_nofail(unsigned long size)
+{
+	return __ntfs_malloc(size, GFP_NOFS | __GFP_HIGHMEM | __GFP_NOFAIL);
+}
+
+static inline void ntfs_free(void *addr)
+{
+	kvfree(addr);
+}
+
+#endif /* _LINUX_NTFS_MALLOC_H */