Merge tag 'sched-core-2025-03-22' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
 "Core & fair scheduler changes:

   - Cancel the slice protection of the idle entity (Zihan Zhou)
   - Reduce the default slice to avoid tasks getting an extra tick
     (Zihan Zhou)
   - Force propagating min_slice of cfs_rq when {en,de}queue tasks
     (Tianchen Ding)
   - Refactor can_migrate_task() to elimate looping (I Hsin Cheng)
   - Add unlikey branch hints to several system calls (Colin Ian King)
   - Optimize current_clr_polling() on certain architectures (Yujun
     Dong)

  Deadline scheduler: (Juri Lelli)
   - Remove redundant dl_clear_root_domain call
   - Move dl_rebuild_rd_accounting to cpuset.h

  Uclamp:
   - Use the uclamp_is_used() helper instead of open-coding it (Xuewen
     Yan)
   - Optimize sched_uclamp_used static key enabling (Xuewen Yan)

  Scheduler topology support: (Juri Lelli)
   - Ignore special tasks when rebuilding domains
   - Add wrappers for sched_domains_mutex
   - Generalize unique visiting of root domains
   - Rebuild root domain accounting after every update
   - Remove partition_and_rebuild_sched_domains
   - Stop exposing partition_sched_domains_locked

  RSEQ: (Michael Jeanson)
   - Update kernel fields in lockstep with CONFIG_DEBUG_RSEQ=y
   - Fix segfault on registration when rseq_cs is non-zero
   - selftests: Add rseq syscall errors test
   - selftests: Ensure the rseq ABI TLS is actually 1024 bytes

  Membarriers:
   - Fix redundant load of membarrier_state (Nysal Jan K.A.)

  Scheduler debugging:
   - Introduce and use preempt_model_str() (Sebastian Andrzej Siewior)
   - Make CONFIG_SCHED_DEBUG unconditional (Ingo Molnar)

  Fixes and cleanups:
   - Always save/restore x86 TSC sched_clock() on suspend/resume
     (Guilherme G. Piccoli)
   - Misc fixes and cleanups (Thorsten Blum, Juri Lelli, Sebastian
     Andrzej Siewior)"

* tag 'sched-core-2025-03-22' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (40 commits)
  cpuidle, sched: Use smp_mb__after_atomic() in current_clr_polling()
  sched/debug: Remove CONFIG_SCHED_DEBUG
  sched/debug: Remove CONFIG_SCHED_DEBUG from self-test config files
  sched/debug, Documentation: Remove (most) CONFIG_SCHED_DEBUG references from documentation
  sched/debug: Make CONFIG_SCHED_DEBUG functionality unconditional
  sched/debug: Make 'const_debug' tunables unconditional __read_mostly
  sched/debug: Change SCHED_WARN_ON() to WARN_ON_ONCE()
  rseq/selftests: Fix namespace collision with rseq UAPI header
  include/{topology,cpuset}: Move dl_rebuild_rd_accounting to cpuset.h
  sched/topology: Stop exposing partition_sched_domains_locked
  cgroup/cpuset: Remove partition_and_rebuild_sched_domains
  sched/topology: Remove redundant dl_clear_root_domain call
  sched/deadline: Rebuild root domain accounting after every update
  sched/deadline: Generalize unique visiting of root domains
  sched/topology: Wrappers for sched_domains_mutex
  sched/deadline: Ignore special tasks when rebuilding domains
  tracing: Use preempt_model_str()
  xtensa: Rely on generic printing of preemption model
  x86: Rely on generic printing of preemption model
  s390: Rely on generic printing of preemption model
  ...

9 files changed, 162 insertions, 13 deletions

diff --git a/tools/testing/selftests/rseq/.gitignore b/tools/testing/selftests/rseq/.gitignore
index 16496de5f6ce..0fda241fa62b 100644
--- a/tools/testing/selftests/rseq/.gitignore
+++ b/tools/testing/selftests/rseq/.gitignore
@@ -9,3 +9,4 @@ param_test_compare_twice
 param_test_mm_cid
 param_test_mm_cid_benchmark
 param_test_mm_cid_compare_twice
+syscall_errors_test
diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile
index 5a3432fceb58..0d0a5fae5954 100644
--- a/tools/testing/selftests/rseq/Makefile
+++ b/tools/testing/selftests/rseq/Makefile
@@ -16,11 +16,12 @@ OVERRIDE_TARGETS = 1
 
 TEST_GEN_PROGS = basic_test basic_percpu_ops_test basic_percpu_ops_mm_cid_test param_test \
 		param_test_benchmark param_test_compare_twice param_test_mm_cid \
-		param_test_mm_cid_benchmark param_test_mm_cid_compare_twice
+		param_test_mm_cid_benchmark param_test_mm_cid_compare_twice \
+		syscall_errors_test
 
 TEST_GEN_PROGS_EXTENDED = librseq.so
 
-TEST_PROGS = run_param_test.sh
+TEST_PROGS = run_param_test.sh run_syscall_errors_test.sh
 
 TEST_FILES := settings
 
@@ -54,3 +55,7 @@ $(OUTPUT)/param_test_mm_cid_benchmark: param_test.c $(TEST_GEN_PROGS_EXTENDED) \
 $(OUTPUT)/param_test_mm_cid_compare_twice: param_test.c $(TEST_GEN_PROGS_EXTENDED) \
 					rseq.h rseq-*.h
 	$(CC) $(CFLAGS) -DBUILDOPT_RSEQ_PERCPU_MM_CID -DRSEQ_COMPARE_TWICE $< $(LDLIBS) -lrseq -o $@
+
+$(OUTPUT)/syscall_errors_test: syscall_errors_test.c $(TEST_GEN_PROGS_EXTENDED) \
+					rseq.h rseq-*.h
+	$(CC) $(CFLAGS) $< $(LDLIBS) -lrseq -o $@
diff --git a/tools/testing/selftests/rseq/rseq.c b/tools/testing/selftests/rseq/rseq.c
index f6156790c3b4..663a9cef1952 100644
--- a/tools/testing/selftests/rseq/rseq.c
+++ b/tools/testing/selftests/rseq/rseq.c
@@ -71,9 +71,20 @@ static int rseq_ownership;
 /* Original struct rseq allocation size is 32 bytes. */
 #define ORIG_RSEQ_ALLOC_SIZE		32
 
+/*
+ * Use a union to ensure we allocate a TLS area of 1024 bytes to accomodate an
+ * rseq registration that is larger than the current rseq ABI.
+ */
+union rseq_tls {
+	struct rseq_abi abi;
+	char dummy[RSEQ_THREAD_AREA_ALLOC_SIZE];
+};
+
 static
-__thread struct rseq_abi __rseq_abi __attribute__((tls_model("initial-exec"), aligned(RSEQ_THREAD_AREA_ALLOC_SIZE))) = {
-	.cpu_id = RSEQ_ABI_CPU_ID_UNINITIALIZED,
+__thread union rseq_tls __rseq __attribute__((tls_model("initial-exec"))) = {
+	.abi = {
+		.cpu_id = RSEQ_ABI_CPU_ID_UNINITIALIZED,
+	},
 };
 
 static int sys_rseq(struct rseq_abi *rseq_abi, uint32_t rseq_len,
@@ -87,7 +98,7 @@ static int sys_getcpu(unsigned *cpu, unsigned *node)
 	return syscall(__NR_getcpu, cpu, node, NULL);
 }
 
-int rseq_available(void)
+bool rseq_available(void)
 {
 	int rc;
 
@@ -96,9 +107,9 @@ int rseq_available(void)
 		abort();
 	switch (errno) {
 	case ENOSYS:
-		return 0;
+		return false;
 	case EINVAL:
-		return 1;
+		return true;
 	default:
 		abort();
 	}
@@ -149,7 +160,7 @@ int rseq_register_current_thread(void)
 		/* Treat libc's ownership as a successful registration. */
 		return 0;
 	}
-	rc = sys_rseq(&__rseq_abi, get_rseq_min_alloc_size(), 0, RSEQ_SIG);
+	rc = sys_rseq(&__rseq.abi, get_rseq_min_alloc_size(), 0, RSEQ_SIG);
 	if (rc) {
 		/*
 		 * After at least one thread has registered successfully
@@ -183,7 +194,7 @@ int rseq_unregister_current_thread(void)
 		/* Treat libc's ownership as a successful unregistration. */
 		return 0;
 	}
-	rc = sys_rseq(&__rseq_abi, get_rseq_min_alloc_size(), RSEQ_ABI_FLAG_UNREGISTER, RSEQ_SIG);
+	rc = sys_rseq(&__rseq.abi, get_rseq_min_alloc_size(), RSEQ_ABI_FLAG_UNREGISTER, RSEQ_SIG);
 	if (rc)
 		return -1;
 	return 0;
@@ -249,7 +260,7 @@ void rseq_init(void)
 	rseq_ownership = 1;
 
 	/* Calculate the offset of the rseq area from the thread pointer. */
-	rseq_offset = (void *)&__rseq_abi - rseq_thread_pointer();
+	rseq_offset = (void *)&__rseq.abi - rseq_thread_pointer();
 
 	/* rseq flags are deprecated, always set to 0. */
 	rseq_flags = 0;
diff --git a/tools/testing/selftests/rseq/rseq.h b/tools/testing/selftests/rseq/rseq.h
index ba424ce80a71..f51a5fdb0444 100644
--- a/tools/testing/selftests/rseq/rseq.h
+++ b/tools/testing/selftests/rseq/rseq.h
@@ -160,6 +160,11 @@ int32_t rseq_fallback_current_cpu(void);
 int32_t rseq_fallback_current_node(void);
 
 /*
+ * Returns true if rseq is supported.
+ */
+bool rseq_available(void);
+
+/*
  * Values returned can be either the current CPU number, -1 (rseq is
  * uninitialized), or -2 (rseq initialization has failed).
  */
diff --git a/tools/testing/selftests/rseq/run_syscall_errors_test.sh b/tools/testing/selftests/rseq/run_syscall_errors_test.sh
new file mode 100755
index 000000000000..9272246b39f2
--- /dev/null
+++ b/tools/testing/selftests/rseq/run_syscall_errors_test.sh
@@ -0,0 +1,5 @@
+#!/bin/bash
+# SPDX-License-Identifier: MIT
+# SPDX-FileCopyrightText: 2024 Michael Jeanson <mjeanson@efficios.com>
+
+GLIBC_TUNABLES="${GLIBC_TUNABLES:-}:glibc.pthread.rseq=0" ./syscall_errors_test
diff --git a/tools/testing/selftests/rseq/syscall_errors_test.c b/tools/testing/selftests/rseq/syscall_errors_test.c
new file mode 100644
index 000000000000..a5d9e1f8a2dc
--- /dev/null
+++ b/tools/testing/selftests/rseq/syscall_errors_test.c
@@ -0,0 +1,124 @@
+// SPDX-License-Identifier: MIT
+// SPDX-FileCopyrightText: 2024 Michael Jeanson <mjeanson@efficios.com>
+
+#ifndef _GNU_SOURCE
+#define _GNU_SOURCE
+#endif
+
+#include <assert.h>
+#include <stdint.h>
+#include <syscall.h>
+#include <string.h>
+#include <unistd.h>
+
+#include "rseq.h"
+
+static int sys_rseq(void *rseq_abi, uint32_t rseq_len,
+		    int flags, uint32_t sig)
+{
+	return syscall(__NR_rseq, rseq_abi, rseq_len, flags, sig);
+}
+
+/*
+ * Check the value of errno on some expected failures of the rseq syscall.
+ */
+
+int main(void)
+{
+	struct rseq_abi *global_rseq = rseq_get_abi();
+	int ret;
+	int errno_copy;
+
+	if (!rseq_available()) {
+		fprintf(stderr, "rseq syscall unavailable");
+		goto error;
+	}
+
+	/* The current thread is NOT registered. */
+
+	/* EINVAL */
+	errno = 0;
+	ret = sys_rseq(global_rseq, 32, -1, RSEQ_SIG);
+	errno_copy = errno;
+	fprintf(stderr, "Registration with invalid flag fails with errno set to EINVAL (ret = %d, errno = %s)\n", ret, strerrorname_np(errno_copy));
+	if (ret == 0 || errno_copy != EINVAL)
+		goto error;
+
+	errno = 0;
+	ret = sys_rseq((char *) global_rseq + 1, 32, 0, RSEQ_SIG);
+	errno_copy = errno;
+	fprintf(stderr, "Registration with unaligned rseq_abi fails with errno set to EINVAL (ret = %d, errno = %s)\n", ret, strerrorname_np(errno_copy));
+	if (ret == 0 || errno_copy != EINVAL)
+		goto error;
+
+	errno = 0;
+	ret = sys_rseq(global_rseq, 31, 0, RSEQ_SIG);
+	errno_copy = errno;
+	fprintf(stderr, "Registration with invalid size fails with errno set to EINVAL (ret = %d, errno = %s)\n", ret, strerrorname_np(errno_copy));
+	if (ret == 0 || errno_copy != EINVAL)
+		goto error;
+
+
+#if defined(__LP64__) && (!defined(__s390__) && !defined(__s390x__))
+	/*
+	 * We haven't found a reliable way to find an invalid address when
+	 * running a 32bit userspace on a 64bit kernel, so only run this test
+	 * on 64bit builds for the moment.
+	 *
+	 * Also exclude architectures that select
+	 * CONFIG_ALTERNATE_USER_ADDRESS_SPACE where the kernel and userspace
+	 * have their own address space and this failure can't happen.
+	 */
+
+	/* EFAULT */
+	errno = 0;
+	ret = sys_rseq((void *) -4096UL, 32, 0, RSEQ_SIG);
+	errno_copy = errno;
+	fprintf(stderr, "Registration with invalid address fails with errno set to EFAULT (ret = %d, errno = %s)\n", ret, strerrorname_np(errno_copy));
+	if (ret == 0 || errno_copy != EFAULT)
+		goto error;
+#endif
+
+	errno = 0;
+	ret = sys_rseq(global_rseq, 32, 0, RSEQ_SIG);
+	errno_copy = errno;
+	fprintf(stderr, "Registration succeeds for the current thread (ret = %d, errno = %s)\n", ret, strerrorname_np(errno_copy));
+	if (ret != 0 && errno != 0)
+		goto error;
+
+	/* The current thread is registered. */
+
+	/* EBUSY */
+	errno = 0;
+	ret = sys_rseq(global_rseq, 32, 0, RSEQ_SIG);
+	errno_copy = errno;
+	fprintf(stderr, "Double registration fails with errno set to EBUSY (ret = %d, errno = %s)\n", ret, strerrorname_np(errno_copy));
+	if (ret == 0 || errno_copy != EBUSY)
+		goto error;
+
+	/* EPERM */
+	errno = 0;
+	ret = sys_rseq(global_rseq, 32, RSEQ_ABI_FLAG_UNREGISTER, RSEQ_SIG + 1);
+	errno_copy = errno;
+	fprintf(stderr, "Unregistration with wrong RSEQ_SIG fails with errno to EPERM (ret = %d, errno = %s)\n", ret, strerrorname_np(errno_copy));
+	if (ret == 0 || errno_copy != EPERM)
+		goto error;
+
+	errno = 0;
+	ret = sys_rseq(global_rseq, 32, RSEQ_ABI_FLAG_UNREGISTER, RSEQ_SIG);
+	errno_copy = errno;
+	fprintf(stderr, "Unregistration succeeds for the current thread (ret = %d, errno = %s)\n", ret, strerrorname_np(errno_copy));
+	if (ret != 0)
+		goto error;
+
+	errno = 0;
+	ret = sys_rseq(global_rseq, 32, RSEQ_ABI_FLAG_UNREGISTER, RSEQ_SIG);
+	errno_copy = errno;
+	fprintf(stderr, "Double unregistration fails with errno set to EINVAL (ret = %d, errno = %s)\n", ret, strerrorname_np(errno_copy));
+	if (ret == 0 || errno_copy != EINVAL)
+		goto error;
+
+	return 0;
+error:
+	return -1;
+}
diff --git a/tools/testing/selftests/sched/config b/tools/testing/selftests/sched/config
index e8b09aa7c0c4..1bb8bf6d7fd4 100644
--- a/tools/testing/selftests/sched/config
+++ b/tools/testing/selftests/sched/config
@@ -1 +1 @@
-CONFIG_SCHED_DEBUG=y
+# empty
diff --git a/tools/testing/selftests/sched_ext/config b/tools/testing/selftests/sched_ext/config
index 0de9b4ee249d..aa901b05c8ad 100644
--- a/tools/testing/selftests/sched_ext/config
+++ b/tools/testing/selftests/sched_ext/config
@@ -1,4 +1,3 @@
-CONFIG_SCHED_DEBUG=y
 CONFIG_SCHED_CLASS_EXT=y
 CONFIG_CGROUPS=y
 CONFIG_CGROUP_SCHED=y
diff --git a/tools/testing/selftests/wireguard/qemu/debug.config b/tools/testing/selftests/wireguard/qemu/debug.config
index 139fd9aa8b12..c305d2f613f0 100644
--- a/tools/testing/selftests/wireguard/qemu/debug.config
+++ b/tools/testing/selftests/wireguard/qemu/debug.config
@@ -27,7 +27,6 @@ CONFIG_DEBUG_KMEMLEAK=y
 CONFIG_DEBUG_STACK_USAGE=y
 CONFIG_DEBUG_SHIRQ=y
 CONFIG_WQ_WATCHDOG=y
-CONFIG_SCHED_DEBUG=y
 CONFIG_SCHED_INFO=y
 CONFIG_SCHEDSTATS=y
 CONFIG_SCHED_STACK_END_CHECK=y