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, 197 insertions, 0 deletions

diff --git a/tools/lib/bpf/strset.c b/tools/lib/bpf/strset.c
new file mode 100644
index 000000000..ace73c6b3
--- /dev/null
+++ b/tools/lib/bpf/strset.c
@@ -0,0 +1,197 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+/* Copyright (c) 2021 Facebook */
+#include <stdint.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <errno.h>
+#include <linux/err.h>
+#include "hashmap.h"
+#include "libbpf_internal.h"
+#include "strset.h"
+
+struct strset {
+	void *strs_data;
+	size_t strs_data_len;
+	size_t strs_data_cap;
+	size_t strs_data_max_len;
+
+	/* lookup index for each unique string in strings set */
+	struct hashmap *strs_hash;
+};
+
+static size_t strset_hash_fn(long key, void *ctx)
+{
+	const struct strset *s = ctx;
+	const char *str = s->strs_data + key;
+
+	return str_hash(str);
+}
+
+static bool strset_equal_fn(long key1, long key2, void *ctx)
+{
+	const struct strset *s = ctx;
+	const char *str1 = s->strs_data + key1;
+	const char *str2 = s->strs_data + key2;
+
+	return strcmp(str1, str2) == 0;
+}
+
+struct strset *strset__new(size_t max_data_sz, const char *init_data, size_t init_data_sz)
+{
+	struct strset *set = calloc(1, sizeof(*set));
+	struct hashmap *hash;
+	int err = -ENOMEM;
+
+	if (!set)
+		return ERR_PTR(-ENOMEM);
+
+	hash = hashmap__new(strset_hash_fn, strset_equal_fn, set);
+	if (IS_ERR(hash))
+		goto err_out;
+
+	set->strs_data_max_len = max_data_sz;
+	set->strs_hash = hash;
+
+	if (init_data) {
+		long off;
+
+		set->strs_data = malloc(init_data_sz);
+		if (!set->strs_data)
+			goto err_out;
+
+		memcpy(set->strs_data, init_data, init_data_sz);
+		set->strs_data_len = init_data_sz;
+		set->strs_data_cap = init_data_sz;
+
+		for (off = 0; off < set->strs_data_len; off += strlen(set->strs_data + off) + 1) {
+			/* hashmap__add() returns EEXIST if string with the same
+			 * content already is in the hash map
+			 */
+			err = hashmap__add(hash, off, off);
+			if (err == -EEXIST)
+				continue; /* duplicate */
+			if (err)
+				goto err_out;
+		}
+	}
+
+	return set;
+err_out:
+	strset__free(set);
+	return ERR_PTR(err);
+}
+
+void strset__free(struct strset *set)
+{
+	if (IS_ERR_OR_NULL(set))
+		return;
+
+	hashmap__free(set->strs_hash);
+	free(set->strs_data);
+	free(set);
+}
+
+size_t strset__data_size(const struct strset *set)
+{
+	return set->strs_data_len;
+}
+
+const char *strset__data(const struct strset *set)
+{
+	return set->strs_data;
+}
+
+static void *strset_add_str_mem(struct strset *set, size_t add_sz)
+{
+	return libbpf_add_mem(&set->strs_data, &set->strs_data_cap, 1,
+			      set->strs_data_len, set->strs_data_max_len, add_sz);
+}
+
+static long strset_str_append(struct strset *set, const char *s)
+{
+	uintptr_t old_data = (uintptr_t)set->strs_data;
+	size_t old_data_len = set->strs_data_len;
+	uintptr_t old_s = (uintptr_t)s;
+	long len = strlen(s) + 1;
+	void *p;
+
+	/*
+	 * Hashmap keys are always offsets within set->strs_data, so to even
+	 * look up some string from the "outside", we need to first append it
+	 * at the end, so that it can be addressed with an offset. Luckily,
+	 * until set->strs_data_len is incremented, that string is just a piece
+	 * of garbage for the rest of the code, so no harm, no foul. On the
+	 * other hand, if the string is unique, it's already appended and
+	 * ready to be used, only a simple set->strs_data_len increment away.
+	 */
+	p = strset_add_str_mem(set, len);
+	if (!p)
+		return -ENOMEM;
+
+	/*
+	 * The set->strs_data might have reallocated and if 's' pointed
+	 * to an internal string within the old buffer, then it became
+	 * dangling and needs to be reconstructed before the copy.
+	 */
+	if (old_data && old_data != (uintptr_t)set->strs_data &&
+	    old_s >= old_data && old_s < old_data + old_data_len)
+		s = set->strs_data + (old_s - old_data);
+
+	memcpy(p, s, len);
+
+	return len;
+}
+
+/* Find string offset that corresponds to a given string *s*.
+ * Returns:
+ *   - >0 offset into string data, if string is found;
+ *   - -ENOENT, if string is not in the string data;
+ *   - <0, on any other error.
+ */
+int strset__find_str(struct strset *set, const char *s)
+{
+	long old_off, new_off, len;
+
+	len = strset_str_append(set, s);
+	if (len < 0)
+		return len;
+
+	new_off = set->strs_data_len;
+
+	if (hashmap__find(set->strs_hash, new_off, &old_off))
+		return old_off;
+
+	return -ENOENT;
+}
+
+/* Add a string s to the string data. If the string already exists, return its
+ * offset within string data.
+ * Returns:
+ *   - > 0 offset into string data, on success;
+ *   - < 0, on error.
+ */
+int strset__add_str(struct strset *set, const char *s)
+{
+	long old_off, new_off, len;
+	int err;
+
+	len = strset_str_append(set, s);
+	if (len < 0)
+		return len;
+
+	new_off = set->strs_data_len;
+
+	/* Now attempt to add the string, but only if the string with the same
+	 * contents doesn't exist already (HASHMAP_ADD strategy). If such
+	 * string exists, we'll get its offset in old_off (that's old_key).
+	 */
+	err = hashmap__insert(set->strs_hash, new_off, new_off,
+			      HASHMAP_ADD, &old_off, NULL);
+	if (err == -EEXIST)
+		return old_off; /* duplicated string, return existing offset */
+	if (err)
+		return err;
+
+	set->strs_data_len += len; /* new unique string, adjust data length */
+	return new_off;
+}