Merge tag 'sched-urgent-2026-05-09' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler fixes from Ingo Molnar:

 - Fix spurious failures in rseq self-tests (Mark Brown)

 - Fix rseq rseq::cpu_id_start ABI regression due to TCMalloc's creative
   use of the supposedly read-only field

   The fix is to introduce a new ABI variant based on a new (larger)
   rseq area registration size, to keep the TCMalloc use of rseq
   backwards compatible on new kernels (Thomas Gleixner)

 - Fix wakeup_preempt_fair() for not waking up task (Vincent Guittot)

 - Fix s64 mult overflow in vruntime_eligible() (Zhan Xusheng)

* tag 'sched-urgent-2026-05-09' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/fair: Fix wakeup_preempt_fair() for not waking up task
  sched/fair: Fix overflow in vruntime_eligible()
  selftests/rseq: Expand for optimized RSEQ ABI v2
  rseq: Reenable performance optimizations conditionally
  rseq: Implement read only ABI enforcement for optimized RSEQ V2 mode
  selftests/rseq: Validate legacy behavior
  selftests/rseq: Make registration flexible for legacy and optimized mode
  selftests/rseq: Skip tests if time slice extensions are not available
  rseq: Revert to historical performance killing behaviour
  rseq: Don't advertise time slice extensions if disabled
  rseq: Protect rseq_reset() against interrupts
  rseq: Set rseq::cpu_id_start to 0 on unregistration
  selftests/rseq: Don't run tests with runner scripts outside of the scripts

11 files changed, 208 insertions, 43 deletions

diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile
index 4ef90823b652..50d69e22ee7a 100644
--- a/tools/testing/selftests/rseq/Makefile
+++ b/tools/testing/selftests/rseq/Makefile
@@ -14,14 +14,20 @@ LDLIBS += -lpthread -ldl
 # still track changes to header files and depend on shared object.
 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 \
-		syscall_errors_test slice_test
+TEST_GEN_PROGS = basic_test basic_percpu_ops_test basic_percpu_ops_mm_cid_test \
+		 param_test_benchmark param_test_mm_cid_benchmark
 
-TEST_GEN_PROGS_EXTENDED = librseq.so
+TEST_GEN_PROGS_EXTENDED = librseq.so \
+	param_test \
+	param_test_compare_twice \
+	param_test_mm_cid \
+	param_test_mm_cid_compare_twice \
+	syscall_errors_test \
+	legacy_check \
+	slice_test \
+	check_optimized
 
-TEST_PROGS = run_param_test.sh run_syscall_errors_test.sh
+TEST_PROGS = run_param_test.sh run_syscall_errors_test.sh run_legacy_check.sh run_timeslice_test.sh
 
 TEST_FILES := settings
 
@@ -62,3 +68,6 @@ $(OUTPUT)/syscall_errors_test: syscall_errors_test.c $(TEST_GEN_PROGS_EXTENDED)
 
 $(OUTPUT)/slice_test: slice_test.c $(TEST_GEN_PROGS_EXTENDED) rseq.h rseq-*.h
 	$(CC) $(CFLAGS) $< $(LDLIBS) -lrseq -o $@
+
+$(OUTPUT)/check_optimized: check_optimized.c $(TEST_GEN_PROGS_EXTENDED) rseq.h rseq-*.h
+	$(CC) $(CFLAGS) $< $(LDLIBS) -lrseq -o $@
diff --git a/tools/testing/selftests/rseq/check_optimized.c b/tools/testing/selftests/rseq/check_optimized.c
new file mode 100644
index 000000000000..a13e3f2c8fc6
--- /dev/null
+++ b/tools/testing/selftests/rseq/check_optimized.c
@@ -0,0 +1,17 @@
+// SPDX-License-Identifier: LGPL-2.1
+#define _GNU_SOURCE
+#include <assert.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdio.h>
+#include <string.h>
+#include <sys/time.h>
+
+#include "rseq.h"
+
+int main(int argc, char **argv)
+{
+	if (__rseq_register_current_thread(true, false))
+		return -1;
+	return 0;
+}
diff --git a/tools/testing/selftests/rseq/legacy_check.c b/tools/testing/selftests/rseq/legacy_check.c
new file mode 100644
index 000000000000..3f7de4e28303
--- /dev/null
+++ b/tools/testing/selftests/rseq/legacy_check.c
@@ -0,0 +1,65 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef _GNU_SOURCE
+#define _GNU_SOURCE
+#endif
+
+#include <errno.h>
+#include <signal.h>
+#include <stdint.h>
+#include <unistd.h>
+
+#include "rseq.h"
+
+#include "../kselftest_harness.h"
+
+FIXTURE(legacy)
+{
+};
+
+static int cpu_id_in_sigfn = -1;
+
+static void sigfn(int sig)
+{
+	struct rseq_abi *rs = rseq_get_abi();
+
+	cpu_id_in_sigfn = rs->cpu_id_start;
+}
+
+FIXTURE_SETUP(legacy)
+{
+	int res = __rseq_register_current_thread(true, true);
+
+	switch (res) {
+	case -ENOSYS:
+		SKIP(return, "RSEQ not enabled\n");
+	case -EBUSY:
+		SKIP(return, "GLIBC owns RSEQ. Disable GLIBC RSEQ registration\n");
+	default:
+		ASSERT_EQ(res, 0);
+	}
+
+	ASSERT_NE(signal(SIGUSR1, sigfn), SIG_ERR);
+}
+
+FIXTURE_TEARDOWN(legacy)
+{
+}
+
+TEST_F(legacy, legacy_test)
+{
+	struct rseq_abi *rs = rseq_get_abi();
+
+	ASSERT_NE(rs, NULL);
+
+	/* Overwrite rs::cpu_id_start */
+	rs->cpu_id_start = -1;
+	sleep(1);
+	ASSERT_NE(rs->cpu_id_start, -1);
+
+	rs->cpu_id_start = -1;
+	ASSERT_EQ(raise(SIGUSR1), 0);
+	ASSERT_NE(rs->cpu_id_start, -1);
+	ASSERT_NE(cpu_id_in_sigfn, -1);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/rseq/param_test.c b/tools/testing/selftests/rseq/param_test.c
index 05d03e679e06..e1e98dbabe4b 100644
--- a/tools/testing/selftests/rseq/param_test.c
+++ b/tools/testing/selftests/rseq/param_test.c
@@ -38,7 +38,7 @@ static int opt_modulo, verbose;
 static int opt_yield, opt_signal, opt_sleep,
 		opt_disable_rseq, opt_threads = 200,
 		opt_disable_mod = 0, opt_test = 's';
-
+static bool opt_rseq_legacy;
 static long long opt_reps = 5000;
 
 static __thread __attribute__((tls_model("initial-exec")))
@@ -281,9 +281,12 @@ unsigned int yield_mod_cnt, nr_abort;
 	} \
 }
 
+#define rseq_no_glibc			true
+
 #else
 
 #define printf_verbose(fmt, ...)
+#define rseq_no_glibc			false
 
 #endif /* BENCHMARK */
 
@@ -481,7 +484,7 @@ void *test_percpu_spinlock_thread(void *arg)
 	long long i, reps;
 
 	if (!opt_disable_rseq && thread_data->reg &&
-	    rseq_register_current_thread())
+	    __rseq_register_current_thread(rseq_no_glibc, opt_rseq_legacy))
 		abort();
 	reps = thread_data->reps;
 	for (i = 0; i < reps; i++) {
@@ -558,7 +561,7 @@ void *test_percpu_inc_thread(void *arg)
 	long long i, reps;
 
 	if (!opt_disable_rseq && thread_data->reg &&
-	    rseq_register_current_thread())
+	    __rseq_register_current_thread(rseq_no_glibc, opt_rseq_legacy))
 		abort();
 	reps = thread_data->reps;
 	for (i = 0; i < reps; i++) {
@@ -712,7 +715,7 @@ void *test_percpu_list_thread(void *arg)
 	long long i, reps;
 	struct percpu_list *list = (struct percpu_list *)arg;
 
-	if (!opt_disable_rseq && rseq_register_current_thread())
+	if (!opt_disable_rseq && __rseq_register_current_thread(rseq_no_glibc, opt_rseq_legacy))
 		abort();
 
 	reps = opt_reps;
@@ -895,7 +898,7 @@ void *test_percpu_buffer_thread(void *arg)
 	long long i, reps;
 	struct percpu_buffer *buffer = (struct percpu_buffer *)arg;
 
-	if (!opt_disable_rseq && rseq_register_current_thread())
+	if (!opt_disable_rseq && __rseq_register_current_thread(rseq_no_glibc, opt_rseq_legacy))
 		abort();
 
 	reps = opt_reps;
@@ -1105,7 +1108,7 @@ void *test_percpu_memcpy_buffer_thread(void *arg)
 	long long i, reps;
 	struct percpu_memcpy_buffer *buffer = (struct percpu_memcpy_buffer *)arg;
 
-	if (!opt_disable_rseq && rseq_register_current_thread())
+	if (!opt_disable_rseq && __rseq_register_current_thread(rseq_no_glibc, opt_rseq_legacy))
 		abort();
 
 	reps = opt_reps;
@@ -1258,7 +1261,7 @@ void *test_membarrier_worker_thread(void *arg)
 	const int iters = opt_reps;
 	int i;
 
-	if (rseq_register_current_thread()) {
+	if (__rseq_register_current_thread(rseq_no_glibc, opt_rseq_legacy)) {
 		fprintf(stderr, "Error: rseq_register_current_thread(...) failed(%d): %s\n",
 			errno, strerror(errno));
 		abort();
@@ -1323,7 +1326,7 @@ void *test_membarrier_manager_thread(void *arg)
 	intptr_t expect_a = 0, expect_b = 0;
 	int cpu_a = 0, cpu_b = 0;
 
-	if (rseq_register_current_thread()) {
+	if (__rseq_register_current_thread(rseq_no_glibc, opt_rseq_legacy)) {
 		fprintf(stderr, "Error: rseq_register_current_thread(...) failed(%d): %s\n",
 			errno, strerror(errno));
 		abort();
@@ -1475,6 +1478,7 @@ static void show_usage(int argc, char **argv)
 	printf("	[-D M] Disable rseq for each M threads\n");
 	printf("	[-T test] Choose test: (s)pinlock, (l)ist, (b)uffer, (m)emcpy, (i)ncrement, membarrie(r)\n");
 	printf("	[-M] Push into buffer and memcpy buffer with memory barriers.\n");
+	printf("	[-O] Test with optimized RSEQ\n");
 	printf("	[-v] Verbose output.\n");
 	printf("	[-h] Show this help.\n");
 	printf("\n");
@@ -1602,6 +1606,9 @@ int main(int argc, char **argv)
 		case 'M':
 			opt_mo = RSEQ_MO_RELEASE;
 			break;
+		case 'L':
+			opt_rseq_legacy = true;
+			break;
 		default:
 			show_usage(argc, argv);
 			goto error;
@@ -1618,7 +1625,7 @@ int main(int argc, char **argv)
 	if (set_signal_handler())
 		goto error;
 
-	if (!opt_disable_rseq && rseq_register_current_thread())
+	if (!opt_disable_rseq && __rseq_register_current_thread(rseq_no_glibc, opt_rseq_legacy))
 		goto error;
 	if (!opt_disable_rseq && !rseq_validate_cpu_id()) {
 		fprintf(stderr, "Error: cpu id getter unavailable\n");
diff --git a/tools/testing/selftests/rseq/rseq-abi.h b/tools/testing/selftests/rseq/rseq-abi.h
index ecef315204b2..5f4ea2152c2f 100644
--- a/tools/testing/selftests/rseq/rseq-abi.h
+++ b/tools/testing/selftests/rseq/rseq-abi.h
@@ -192,9 +192,14 @@ struct rseq_abi {
 	struct rseq_abi_slice_ctrl slice_ctrl;
 
 	/*
+	 * Place holder to push the size above 32 bytes.
+	 */
+	__u8 __reserved;
+
+	/*
 	 * Flexible array member at end of structure, after last feature field.
 	 */
 	char end[];
-} __attribute__((aligned(4 * sizeof(__u64))));
+} __attribute__((aligned(256)));
 
 #endif /* _RSEQ_ABI_H */
diff --git a/tools/testing/selftests/rseq/rseq.c b/tools/testing/selftests/rseq/rseq.c
index a736727b83c1..be0d0a97031e 100644
--- a/tools/testing/selftests/rseq/rseq.c
+++ b/tools/testing/selftests/rseq/rseq.c
@@ -56,6 +56,7 @@ ptrdiff_t rseq_offset;
  * unsuccessful.
  */
 unsigned int rseq_size = -1U;
+static unsigned int rseq_alloc_size;
 
 /* Flags used during rseq registration.  */
 unsigned int rseq_flags;
@@ -115,29 +116,17 @@ bool rseq_available(void)
 	}
 }
 
-/* The rseq areas need to be at least 32 bytes. */
-static
-unsigned int get_rseq_min_alloc_size(void)
-{
-	unsigned int alloc_size = rseq_size;
-
-	if (alloc_size < ORIG_RSEQ_ALLOC_SIZE)
-		alloc_size = ORIG_RSEQ_ALLOC_SIZE;
-	return alloc_size;
-}
-
 /*
  * Return the feature size supported by the kernel.
  *
  * Depending on the value returned by getauxval(AT_RSEQ_FEATURE_SIZE):
  *
- * 0:   Return ORIG_RSEQ_FEATURE_SIZE (20)
+ *   0: Return ORIG_RSEQ_FEATURE_SIZE (20)
  * > 0: Return the value from getauxval(AT_RSEQ_FEATURE_SIZE).
  *
  * It should never return a value below ORIG_RSEQ_FEATURE_SIZE.
  */
-static
-unsigned int get_rseq_kernel_feature_size(void)
+static unsigned int get_rseq_kernel_feature_size(void)
 {
 	unsigned long auxv_rseq_feature_size, auxv_rseq_align;
 
@@ -152,15 +141,24 @@ unsigned int get_rseq_kernel_feature_size(void)
 		return ORIG_RSEQ_FEATURE_SIZE;
 }
 
-int rseq_register_current_thread(void)
+int __rseq_register_current_thread(bool nolibc, bool legacy)
 {
+	unsigned int size;
 	int rc;
 
 	if (!rseq_ownership) {
 		/* Treat libc's ownership as a successful registration. */
-		return 0;
+		return nolibc ? -EBUSY : 0;
 	}
-	rc = sys_rseq(&__rseq.abi, get_rseq_min_alloc_size(), 0, RSEQ_SIG);
+
+	/* The minimal allocation size is 32, which is the legacy allocation size */
+	size = get_rseq_kernel_feature_size();
+	if (legacy || size < ORIG_RSEQ_ALLOC_SIZE)
+		rseq_alloc_size = ORIG_RSEQ_ALLOC_SIZE;
+	else
+		rseq_alloc_size = size;
+
+	rc = sys_rseq(&__rseq.abi, rseq_alloc_size, 0, RSEQ_SIG);
 	if (rc) {
 		/*
 		 * After at least one thread has registered successfully
@@ -179,9 +177,8 @@ int rseq_register_current_thread(void)
 	 * The first thread to register sets the rseq_size to mimic the libc
 	 * behavior.
 	 */
-	if (RSEQ_READ_ONCE(rseq_size) == 0) {
-		RSEQ_WRITE_ONCE(rseq_size, get_rseq_kernel_feature_size());
-	}
+	if (RSEQ_READ_ONCE(rseq_size) == 0)
+		RSEQ_WRITE_ONCE(rseq_size, size);
 
 	return 0;
 }
@@ -194,7 +191,7 @@ 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, rseq_alloc_size, RSEQ_ABI_FLAG_UNREGISTER, RSEQ_SIG);
 	if (rc)
 		return -1;
 	return 0;
diff --git a/tools/testing/selftests/rseq/rseq.h b/tools/testing/selftests/rseq/rseq.h
index f51a5fdb0444..c62ebb9290c0 100644
--- a/tools/testing/selftests/rseq/rseq.h
+++ b/tools/testing/selftests/rseq/rseq.h
@@ -8,6 +8,7 @@
 #ifndef RSEQ_H
 #define RSEQ_H
 
+#include <assert.h>
 #include <stdint.h>
 #include <stdbool.h>
 #include <pthread.h>
@@ -142,7 +143,12 @@ static inline struct rseq_abi *rseq_get_abi(void)
  * succeed. A restartable sequence executed from a non-registered
  * thread will always fail.
  */
-int rseq_register_current_thread(void);
+int __rseq_register_current_thread(bool nolibc, bool legacy);
+
+static inline int rseq_register_current_thread(void)
+{
+	return __rseq_register_current_thread(false, false);
+}
 
 /*
  * Unregister rseq for current thread.
diff --git a/tools/testing/selftests/rseq/run_legacy_check.sh b/tools/testing/selftests/rseq/run_legacy_check.sh
new file mode 100755
index 000000000000..5577b46ea092
--- /dev/null
+++ b/tools/testing/selftests/rseq/run_legacy_check.sh
@@ -0,0 +1,4 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+GLIBC_TUNABLES="${GLIBC_TUNABLES:-}:glibc.pthread.rseq=0" ./legacy_check
diff --git a/tools/testing/selftests/rseq/run_param_test.sh b/tools/testing/selftests/rseq/run_param_test.sh
index 8d31426ab41f..69a3fa049929 100755
--- a/tools/testing/selftests/rseq/run_param_test.sh
+++ b/tools/testing/selftests/rseq/run_param_test.sh
@@ -34,6 +34,11 @@ REPS=1000
 SLOW_REPS=100
 NR_THREADS=$((6*${NR_CPUS}))
 
+# Prevent GLIBC from registering RSEQ so the selftest can run in legacy and
+# performance optimized mode.
+GLIBC_TUNABLES="${GLIBC_TUNABLES:-}:glibc.pthread.rseq=0"
+export GLIBC_TUNABLES
+
 function do_tests()
 {
 	local i=0
@@ -103,6 +108,40 @@ function inject_blocking()
 	NR_LOOPS=
 }
 
+echo "Testing in legacy RSEQ mode"
+echo "Yield injection (25%)"
+inject_blocking -m 4 -y -L
+
+echo "Yield injection (50%)"
+inject_blocking -m 2 -y -L
+
+echo "Yield injection (100%)"
+inject_blocking -m 1 -y -L
+
+echo "Kill injection (25%)"
+inject_blocking -m 4 -k -L
+
+echo "Kill injection (50%)"
+inject_blocking -m 2 -k -L
+
+echo "Kill injection (100%)"
+inject_blocking -m 1 -k -L
+
+echo "Sleep injection (1ms, 25%)"
+inject_blocking -m 4 -s 1 -L
+
+echo "Sleep injection (1ms, 50%)"
+inject_blocking -m 2 -s 1 -L
+
+echo "Sleep injection (1ms, 100%)"
+inject_blocking -m 1 -s 1 -L
+
+./check_optimized || {
+    echo "Skipping optimized RSEQ mode test. Not supported";
+    exit 0
+}
+
+echo "Testing in optimized RSEQ mode"
 echo "Yield injection (25%)"
 inject_blocking -m 4 -y
 
diff --git a/tools/testing/selftests/rseq/run_timeslice_test.sh b/tools/testing/selftests/rseq/run_timeslice_test.sh
new file mode 100755
index 000000000000..551ebed71ec6
--- /dev/null
+++ b/tools/testing/selftests/rseq/run_timeslice_test.sh
@@ -0,0 +1,14 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
+
+# Prevent GLIBC from registering RSEQ so the selftest can run in legacy
+# and performance optimized mode.
+GLIBC_TUNABLES="${GLIBC_TUNABLES:-}:glibc.pthread.rseq=0"
+export GLIBC_TUNABLES
+
+./check_optimized || {
+    echo "Skipping optimized RSEQ mode test. Not supported";
+    exit 0
+}
+
+./slice_test
diff --git a/tools/testing/selftests/rseq/slice_test.c b/tools/testing/selftests/rseq/slice_test.c
index 357122dcb487..e402d4440bc2 100644
--- a/tools/testing/selftests/rseq/slice_test.c
+++ b/tools/testing/selftests/rseq/slice_test.c
@@ -124,6 +124,13 @@ FIXTURE_SETUP(slice_ext)
 {
 	cpu_set_t affinity;
 
+	if (__rseq_register_current_thread(true, false))
+		SKIP(return, "RSEQ not supported\n");
+
+	if (prctl(PR_RSEQ_SLICE_EXTENSION, PR_RSEQ_SLICE_EXTENSION_SET,
+		  PR_RSEQ_SLICE_EXT_ENABLE, 0, 0))
+		SKIP(return, "Time slice extension not supported\n");
+
 	ASSERT_EQ(sched_getaffinity(0, sizeof(affinity), &affinity), 0);
 
 	/* Pin it on a single CPU. Avoid CPU 0 */
@@ -137,11 +144,6 @@ FIXTURE_SETUP(slice_ext)
 		break;
 	}
 
-	ASSERT_EQ(rseq_register_current_thread(), 0);
-
-	ASSERT_EQ(prctl(PR_RSEQ_SLICE_EXTENSION, PR_RSEQ_SLICE_EXTENSION_SET,
-			PR_RSEQ_SLICE_EXT_ENABLE, 0, 0), 0);
-
 	self->noise_params.noise_nsecs = variant->noise_nsecs;
 	self->noise_params.sleep_nsecs = variant->sleep_nsecs;
 	self->noise_params.run = 1;