From a9e3760b0838299649c0d57cca44daaf40ba3c33 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 14 Sep 2026 22:12:34 -1000 Subject: sched_ext: Maintain an online cid mask in the scheduler arena 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 Reviewed-by: Andrea Righi --- samples/watch_queue/.gitignore | 2 + samples/watch_queue/Makefile | 4 + samples/watch_queue/watch_test.c | 192 +++++++++++++++++++++++++++++++++++++++ 3 files changed, 198 insertions(+) create mode 100644 samples/watch_queue/.gitignore create mode 100644 samples/watch_queue/Makefile create mode 100644 samples/watch_queue/watch_test.c (limited to 'samples/watch_queue') diff --git a/samples/watch_queue/.gitignore b/samples/watch_queue/.gitignore new file mode 100644 index 000000000..823b351d3 --- /dev/null +++ b/samples/watch_queue/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +/watch_test diff --git a/samples/watch_queue/Makefile b/samples/watch_queue/Makefile new file mode 100644 index 000000000..c0db3a6bc --- /dev/null +++ b/samples/watch_queue/Makefile @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only +userprogs-always-y += watch_test + +userccflags += -I usr/include diff --git a/samples/watch_queue/watch_test.c b/samples/watch_queue/watch_test.c new file mode 100644 index 000000000..24cf7d7a1 --- /dev/null +++ b/samples/watch_queue/watch_test.c @@ -0,0 +1,192 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Use watch_queue API to watch for notifications. + * + * Copyright (C) 2020 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#define _GNU_SOURCE +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +// Work around glibc header silliness +#undef AT_RENAME_NOREPLACE +#undef AT_RENAME_EXCHANGE +#undef AT_RENAME_WHITEOUT + +#include +#include +#include + +#ifndef KEYCTL_WATCH_KEY +#define KEYCTL_WATCH_KEY -1 +#endif +#ifndef __NR_keyctl +#define __NR_keyctl -1 +#endif + +#define BUF_SIZE 256 + +static long keyctl_watch_key(int key, int watch_fd, int watch_id) +{ + return syscall(__NR_keyctl, KEYCTL_WATCH_KEY, key, watch_fd, watch_id); +} + +static const char *key_subtypes[256] = { + [NOTIFY_KEY_INSTANTIATED] = "instantiated", + [NOTIFY_KEY_UPDATED] = "updated", + [NOTIFY_KEY_LINKED] = "linked", + [NOTIFY_KEY_UNLINKED] = "unlinked", + [NOTIFY_KEY_CLEARED] = "cleared", + [NOTIFY_KEY_REVOKED] = "revoked", + [NOTIFY_KEY_INVALIDATED] = "invalidated", + [NOTIFY_KEY_SETATTR] = "setattr", +}; + +static void saw_key_change(struct watch_notification *n, size_t len) +{ + struct key_notification *k = (struct key_notification *)n; + + if (len != sizeof(struct key_notification)) { + fprintf(stderr, "Incorrect key message length\n"); + return; + } + + printf("KEY %08x change=%u[%s] aux=%u\n", + k->key_id, n->subtype, key_subtypes[n->subtype], k->aux); +} + +/* + * Consume and display events. + */ +static void consumer(int fd) +{ + unsigned char buffer[433], *p, *end; + union { + struct watch_notification n; + unsigned char buf1[128]; + } n; + ssize_t buf_len; + + for (;;) { + buf_len = read(fd, buffer, sizeof(buffer)); + if (buf_len == -1) { + perror("read"); + exit(1); + } + + if (buf_len == 0) { + printf("-- END --\n"); + return; + } + + if (buf_len > sizeof(buffer)) { + fprintf(stderr, "Read buffer overrun: %zd\n", buf_len); + return; + } + + printf("read() = %zd\n", buf_len); + + p = buffer; + end = buffer + buf_len; + while (p < end) { + size_t largest, len; + + largest = end - p; + if (largest > 128) + largest = 128; + if (largest < sizeof(struct watch_notification)) { + fprintf(stderr, "Short message header: %zu\n", largest); + return; + } + memcpy(&n, p, largest); + + printf("NOTIFY[%03zx]: ty=%06x sy=%02x i=%08x\n", + p - buffer, n.n.type, n.n.subtype, n.n.info); + + len = n.n.info & WATCH_INFO_LENGTH; + if (len < sizeof(n.n) || len > largest) { + fprintf(stderr, "Bad message length: %zu/%zu\n", len, largest); + exit(1); + } + + switch (n.n.type) { + case WATCH_TYPE_META: + switch (n.n.subtype) { + case WATCH_META_REMOVAL_NOTIFICATION: + printf("REMOVAL of watchpoint %08x\n", + (n.n.info & WATCH_INFO_ID) >> + WATCH_INFO_ID__SHIFT); + break; + case WATCH_META_LOSS_NOTIFICATION: + printf("-- LOSS --\n"); + break; + default: + printf("other meta record\n"); + break; + } + break; + case WATCH_TYPE_KEY_NOTIFY: + saw_key_change(&n.n, len); + break; + default: + printf("other type\n"); + break; + } + + p += len; + } + } +} + +static struct watch_notification_filter filter = { + .nr_filters = 1, + .filters = { + [0] = { + .type = WATCH_TYPE_KEY_NOTIFY, + .subtype_filter[0] = UINT_MAX, + }, + }, +}; + +int main(int argc, char **argv) +{ + int pipefd[2], fd; + + if (pipe2(pipefd, O_NOTIFICATION_PIPE) == -1) { + perror("pipe2"); + exit(1); + } + fd = pipefd[0]; + + if (ioctl(fd, IOC_WATCH_QUEUE_SET_SIZE, BUF_SIZE) == -1) { + perror("watch_queue(size)"); + exit(1); + } + + if (ioctl(fd, IOC_WATCH_QUEUE_SET_FILTER, &filter) == -1) { + perror("watch_queue(filter)"); + exit(1); + } + + if (keyctl_watch_key(KEY_SPEC_SESSION_KEYRING, fd, 0x01) == -1) { + perror("keyctl"); + exit(1); + } + + if (keyctl_watch_key(KEY_SPEC_USER_KEYRING, fd, 0x02) == -1) { + perror("keyctl"); + exit(1); + } + + consumer(fd); + exit(0); +} -- cgit v1.3.1