Merge tag 'sched-core-2026-02-09' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
 "Scheduler Kconfig space updates:

   - Further consolidate configurable preemption modes (Peter Zijlstra)

     Reduce the number of architectures that are allowed to offer
     PREEMPT_NONE and PREEMPT_VOLUNTARY, reducing the number of
     preemption models from four to just two: 'full' and 'lazy' on
     up-to-date architectures (arm64, loongarch, powerpc, riscv, s390,
     x86).

     None and voluntary are only available as legacy features on
     platforms that don't implement lazy preemption yet, or which don't
     even support preemption.

     The goal is to eventually remove cond_resched() and voluntary
     preemption altogether.

  RSEQ based 'scheduler time slice extension' support (Thomas Gleixner
  and Peter Zijlstra):

  This allows a thread to request a time slice extension when it enters
  a critical section to avoid contention on a resource when the thread
  is scheduled out inside of the critical section.

   - Add fields and constants for time slice extension
   - Provide static branch for time slice extensions
   - Add statistics for time slice extensions
   - Add prctl() to enable time slice extensions
   - Implement sys_rseq_slice_yield()
   - Implement syscall entry work for time slice extensions
   - Implement time slice extension enforcement timer
   - Reset slice extension when scheduled
   - Implement rseq_grant_slice_extension()
   - entry: Hook up rseq time slice extension
   - selftests: Implement time slice extension test
   - Allow registering RSEQ with slice extension
   - Move slice_ext_nsec to debugfs
   - Lower default slice extension
   - selftests/rseq: Add rseq slice histogram script

  Scheduler performance/scalability improvements:

   - Update rq->avg_idle when a task is moved to an idle CPU, which
     improves the scalability of various workloads (Shubhang Kaushik)

   - Reorder fields in 'struct rq' for better caching (Blake Jones)

   - Fair scheduler SMP NOHZ balancing code speedups (Shrikanth Hegde):
      - Move checking for nohz cpus after time check
      - Change likelyhood of nohz.nr_cpus
      - Remove nohz.nr_cpus and use weight of cpumask instead

   - Avoid false sharing for sched_clock_irqtime (Wangyang Guo)

   - Cleanups (Yury Norov):
      - Drop useless cpumask_empty() in find_energy_efficient_cpu()
      - Simplify task_numa_find_cpu()
      - Use cpumask_weight_and() in sched_balance_find_dst_group()

  DL scheduler updates:

   - Add a deadline server for sched_ext tasks (by Andrea Righi and Joel
     Fernandes, with fixes by Peter Zijlstra)

  RT scheduler updates:

   - Skip currently executing CPU in rto_next_cpu() (Chen Jinghuang)

  Entry code updates and performance improvements (Jinjie Ruan)

  This is part of the scheduler tree in this cycle due to inter-
  dependencies with the RSEQ based time slice extension work:

    - Remove unused syscall argument from syscall_trace_enter()
    - Rework syscall_exit_to_user_mode_work() for architecture reuse
    - Add arch_ptrace_report_syscall_entry/exit()
    - Inline syscall_exit_work() and syscall_trace_enter()

  Scheduler core updates (Peter Zijlstra):

   - Rework sched_class::wakeup_preempt() and rq_modified_*()
   - Avoid rq->lock bouncing in sched_balance_newidle()
   - Rename rcu_dereference_check_sched_domain() =>
            rcu_dereference_sched_domain()
   - <linux/compiler_types.h>: Add the __signed_scalar_typeof() helper

  Fair scheduler updates/refactoring (Peter Zijlstra and Ingo Molnar):

   - Fold the sched_avg update
   - Change rcu_dereference_check_sched_domain() to rcu-sched
   - Switch to rcu_dereference_all()
   - Remove superfluous rcu_read_lock()
   - Limit hrtick work
   - Join two #ifdef CONFIG_FAIR_GROUP_SCHED blocks
   - Clean up comments in 'struct cfs_rq'
   - Separate se->vlag from se->vprot
   - Rename cfs_rq::avg_load to cfs_rq::sum_weight
   - Rename cfs_rq::avg_vruntime to ::sum_w_vruntime & helper functions
   - Introduce and use the vruntime_cmp() and vruntime_op() wrappers for
     wrapped-signed aritmetics
   - Sort out 'blocked_load*' namespace noise

  Scheduler debugging code updates:

   - Export hidden tracepoints to modules (Gabriele Monaco)

   - Convert copy_from_user() + kstrtouint() to kstrtouint_from_user()
     (Fushuai Wang)

   - Add assertions to QUEUE_CLASS (Peter Zijlstra)

   - hrtimer: Fix tracing oddity (Thomas Gleixner)

  Misc fixes and cleanups:

   - Re-evaluate scheduling when migrating queued tasks out of throttled
     cgroups (Zicheng Qu)

   - Remove task_struct->faults_disabled_mapping (Christoph Hellwig)

   - Fix math notation errors in avg_vruntime comment (Zhan Xusheng)

   - sched/cpufreq: Use %pe format for PTR_ERR() printing
     (zenghongling)"

* tag 'sched-core-2026-02-09' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (64 commits)
  sched: Re-evaluate scheduling when migrating queued tasks out of throttled cgroups
  sched/cpufreq: Use %pe format for PTR_ERR() printing
  sched/rt: Skip currently executing CPU in rto_next_cpu()
  sched/clock: Avoid false sharing for sched_clock_irqtime
  selftests/sched_ext: Add test for DL server total_bw consistency
  selftests/sched_ext: Add test for sched_ext dl_server
  sched/debug: Fix dl_server (re)start conditions
  sched/debug: Add support to change sched_ext server params
  sched_ext: Add a DL server for sched_ext tasks
  sched/debug: Stop and start server based on if it was active
  sched/debug: Fix updating of ppos on server write ops
  sched/deadline: Clear the defer params
  entry: Inline syscall_exit_work() and syscall_trace_enter()
  entry: Add arch_ptrace_report_syscall_entry/exit()
  entry: Rework syscall_exit_to_user_mode_work() for architecture reuse
  entry: Remove unused syscall argument from syscall_trace_enter()
  sched: remove task_struct->faults_disabled_mapping
  sched: Update rq->avg_idle when a task is moved to an idle CPU
  selftests/rseq: Add rseq slice histogram script
  hrtimer: Fix trace oddity
  ...

9 files changed, 929 insertions, 1 deletions

diff --git a/tools/testing/selftests/rseq/.gitignore b/tools/testing/selftests/rseq/.gitignore
index 0fda241fa62b..ec01d164c1f0 100644
--- a/tools/testing/selftests/rseq/.gitignore
+++ b/tools/testing/selftests/rseq/.gitignore
@@ -10,3 +10,4 @@ param_test_mm_cid
 param_test_mm_cid_benchmark
 param_test_mm_cid_compare_twice
 syscall_errors_test
+slice_test
diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile
index 0d0a5fae5954..4ef90823b652 100644
--- a/tools/testing/selftests/rseq/Makefile
+++ b/tools/testing/selftests/rseq/Makefile
@@ -17,7 +17,7 @@ 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
+		syscall_errors_test slice_test
 
 TEST_GEN_PROGS_EXTENDED = librseq.so
 
@@ -59,3 +59,6 @@ $(OUTPUT)/param_test_mm_cid_compare_twice: param_test.c $(TEST_GEN_PROGS_EXTENDE
 $(OUTPUT)/syscall_errors_test: syscall_errors_test.c $(TEST_GEN_PROGS_EXTENDED) \
 					rseq.h rseq-*.h
 	$(CC) $(CFLAGS) $< $(LDLIBS) -lrseq -o $@
+
+$(OUTPUT)/slice_test: slice_test.c $(TEST_GEN_PROGS_EXTENDED) rseq.h rseq-*.h
+	$(CC) $(CFLAGS) $< $(LDLIBS) -lrseq -o $@
diff --git a/tools/testing/selftests/rseq/rseq-abi.h b/tools/testing/selftests/rseq/rseq-abi.h
index fb4ec8a75dd4..ecef315204b2 100644
--- a/tools/testing/selftests/rseq/rseq-abi.h
+++ b/tools/testing/selftests/rseq/rseq-abi.h
@@ -53,6 +53,27 @@ struct rseq_abi_cs {
 	__u64 abort_ip;
 } __attribute__((aligned(4 * sizeof(__u64))));
 
+/**
+ * rseq_abi_slice_ctrl - Time slice extension control structure
+ * @all:	Compound value
+ * @request:	Request for a time slice extension
+ * @granted:	Granted time slice extension
+ *
+ * @request is set by user space and can be cleared by user space or kernel
+ * space.  @granted is set and cleared by the kernel and must only be read
+ * by user space.
+ */
+struct rseq_abi_slice_ctrl {
+	union {
+		__u32		all;
+		struct {
+			__u8	request;
+			__u8	granted;
+			__u16	__reserved;
+		};
+	};
+};
+
 /*
  * struct rseq_abi is aligned on 4 * 8 bytes to ensure it is always
  * contained within a single cache-line.
@@ -165,6 +186,12 @@ struct rseq_abi {
 	__u32 mm_cid;
 
 	/*
+	 * Time slice extension control structure. CPU local updates from
+	 * kernel and user space.
+	 */
+	struct rseq_abi_slice_ctrl slice_ctrl;
+
+	/*
 	 * Flexible array member at end of structure, after last feature field.
 	 */
 	char end[];
diff --git a/tools/testing/selftests/rseq/rseq-slice-hist.py b/tools/testing/selftests/rseq/rseq-slice-hist.py
new file mode 100644
index 000000000000..b7933eeaefb9
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-slice-hist.py
@@ -0,0 +1,132 @@
+#!/usr/bin/python3
+
+#
+# trace-cmd record -e hrtimer_start -e hrtimer_cancel -e hrtimer_expire_entry -- $cmd
+#
+
+from tracecmd import *
+
+def load_kallsyms(file_path='/proc/kallsyms'):
+    """
+    Parses /proc/kallsyms into a dictionary.
+    Returns: { address_int: symbol_name }
+    """
+    kallsyms_map = {}
+
+    try:
+        with open(file_path, 'r') as f:
+            for line in f:
+                # The format is: [address] [type] [name] [module]
+                parts = line.split()
+                if len(parts) < 3:
+                    continue
+
+                addr = int(parts[0], 16)
+                name = parts[2]
+
+                kallsyms_map[addr] = name
+
+    except PermissionError:
+        print(f"Error: Permission denied reading {file_path}. Try running with sudo.")
+    except FileNotFoundError:
+        print(f"Error: {file_path} not found.")
+
+    return kallsyms_map
+
+ksyms = load_kallsyms()
+
+# pending[timer_ptr] = {'ts': timestamp, 'comm': comm}
+pending = {}
+
+# histograms[comm][bucket] = count
+histograms = {}
+
+class OnlineHarmonicMean:
+    def __init__(self):
+        self.n = 0          # Count of elements
+        self.S = 0.0        # Cumulative sum of reciprocals
+
+    def update(self, x):
+        if x == 0:
+            raise ValueError("Harmonic mean is undefined for zero.")
+
+        self.n += 1
+        self.S += 1.0 / x
+        return self.n / self.S
+
+    @property
+    def mean(self):
+        return self.n / self.S if self.n > 0 else 0
+
+ohms = {}
+
+def handle_start(record):
+    func_name = ksyms[record.num_field("function")]
+    if "rseq_slice_expired" in func_name:
+        timer_ptr = record.num_field("hrtimer")
+        pending[timer_ptr] = {
+            'ts': record.ts,
+            'comm': record.comm
+        }
+    return None
+
+def handle_cancel(record):
+    timer_ptr = record.num_field("hrtimer")
+
+    if timer_ptr in pending:
+        start_data = pending.pop(timer_ptr)
+        duration_ns = record.ts - start_data['ts']
+        duration_us = duration_ns // 1000
+
+        comm = start_data['comm']
+
+        if comm not in ohms:
+            ohms[comm] = OnlineHarmonicMean()
+
+        ohms[comm].update(duration_ns)
+
+        if comm not in histograms:
+            histograms[comm] = {}
+
+        histograms[comm][duration_us] = histograms[comm].get(duration_us, 0) + 1
+    return None
+
+def handle_expire(record):
+    timer_ptr = record.num_field("hrtimer")
+
+    if timer_ptr in pending:
+        start_data = pending.pop(timer_ptr)
+        comm = start_data['comm']
+
+        if comm not in histograms:
+            histograms[comm] = {}
+
+        # Record -1 bucket for expired (failed to cancel)
+        histograms[comm][-1] = histograms[comm].get(-1, 0) + 1
+    return None
+
+if __name__ == "__main__":
+    t = Trace("trace.dat")
+    for cpu in range(0, t.cpus):
+        ev = t.read_event(cpu)
+        while ev:
+            if "hrtimer_start" in ev.name:
+                handle_start(ev)
+            if "hrtimer_cancel" in ev.name:
+                handle_cancel(ev)
+            if "hrtimer_expire_entry" in ev.name:
+                handle_expire(ev)
+
+            ev = t.read_event(cpu)
+
+    print("\n" + "="*40)
+    print("RSEQ SLICE HISTOGRAM (us)")
+    print("="*40)
+    for comm, buckets in histograms.items():
+        print(f"\nTask: {comm}    Mean: {ohms[comm].mean:.3f} ns")
+        print(f"  {'Latency (us)':<15} | {'Count'}")
+        print(f"  {'-'*30}")
+        # Sort buckets numerically, putting -1 at the top
+        for bucket in sorted(buckets.keys()):
+            label = "EXPIRED" if bucket == -1 else f"{bucket} us"
+            print(f"  {label:<15} | {buckets[bucket]}")
diff --git a/tools/testing/selftests/rseq/slice_test.c b/tools/testing/selftests/rseq/slice_test.c
new file mode 100644
index 000000000000..357122dcb487
--- /dev/null
+++ b/tools/testing/selftests/rseq/slice_test.c
@@ -0,0 +1,219 @@
+// SPDX-License-Identifier: LGPL-2.1
+#define _GNU_SOURCE
+#include <assert.h>
+#include <pthread.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <string.h>
+#include <syscall.h>
+#include <unistd.h>
+
+#include <linux/prctl.h>
+#include <sys/prctl.h>
+#include <sys/time.h>
+
+#include "rseq.h"
+
+#include "../kselftest_harness.h"
+
+#ifndef __NR_rseq_slice_yield
+# define __NR_rseq_slice_yield	471
+#endif
+
+#define BITS_PER_INT	32
+#define BITS_PER_BYTE	8
+
+#ifndef PR_RSEQ_SLICE_EXTENSION
+# define PR_RSEQ_SLICE_EXTENSION		79
+#  define PR_RSEQ_SLICE_EXTENSION_GET		1
+#  define PR_RSEQ_SLICE_EXTENSION_SET		2
+#  define PR_RSEQ_SLICE_EXT_ENABLE		0x01
+#endif
+
+#ifndef RSEQ_SLICE_EXT_REQUEST_BIT
+# define RSEQ_SLICE_EXT_REQUEST_BIT	0
+# define RSEQ_SLICE_EXT_GRANTED_BIT	1
+#endif
+
+#ifndef asm_inline
+# define asm_inline	asm __inline
+#endif
+
+#define NSEC_PER_SEC	1000000000L
+#define NSEC_PER_USEC	      1000L
+
+struct noise_params {
+	int64_t	noise_nsecs;
+	int64_t	sleep_nsecs;
+	int64_t	run;
+};
+
+FIXTURE(slice_ext)
+{
+	pthread_t		noise_thread;
+	struct noise_params	noise_params;
+};
+
+FIXTURE_VARIANT(slice_ext)
+{
+	int64_t	total_nsecs;
+	int64_t	slice_nsecs;
+	int64_t	noise_nsecs;
+	int64_t	sleep_nsecs;
+	bool	no_yield;
+};
+
+FIXTURE_VARIANT_ADD(slice_ext, n2_2_50)
+{
+	.total_nsecs	=  5LL * NSEC_PER_SEC,
+	.slice_nsecs	=  2LL * NSEC_PER_USEC,
+	.noise_nsecs    =  2LL * NSEC_PER_USEC,
+	.sleep_nsecs	= 50LL * NSEC_PER_USEC,
+};
+
+FIXTURE_VARIANT_ADD(slice_ext, n50_2_50)
+{
+	.total_nsecs	=  5LL * NSEC_PER_SEC,
+	.slice_nsecs	= 50LL * NSEC_PER_USEC,
+	.noise_nsecs    =  2LL * NSEC_PER_USEC,
+	.sleep_nsecs	= 50LL * NSEC_PER_USEC,
+};
+
+FIXTURE_VARIANT_ADD(slice_ext, n2_2_50_no_yield)
+{
+	.total_nsecs	=  5LL * NSEC_PER_SEC,
+	.slice_nsecs	=  2LL * NSEC_PER_USEC,
+	.noise_nsecs    =  2LL * NSEC_PER_USEC,
+	.sleep_nsecs	= 50LL * NSEC_PER_USEC,
+	.no_yield	= true,
+};
+
+
+static inline bool elapsed(struct timespec *start, struct timespec *now,
+			   int64_t span)
+{
+	int64_t delta = now->tv_sec - start->tv_sec;
+
+	delta *= NSEC_PER_SEC;
+	delta += now->tv_nsec - start->tv_nsec;
+	return delta >= span;
+}
+
+static void *noise_thread(void *arg)
+{
+	struct noise_params *p = arg;
+
+	while (RSEQ_READ_ONCE(p->run)) {
+		struct timespec ts_start, ts_now;
+
+		clock_gettime(CLOCK_MONOTONIC, &ts_start);
+		do {
+			clock_gettime(CLOCK_MONOTONIC, &ts_now);
+		} while (!elapsed(&ts_start, &ts_now, p->noise_nsecs));
+
+		ts_start.tv_sec = 0;
+		ts_start.tv_nsec = p->sleep_nsecs;
+		clock_nanosleep(CLOCK_MONOTONIC, 0, &ts_start, NULL);
+	}
+	return NULL;
+}
+
+FIXTURE_SETUP(slice_ext)
+{
+	cpu_set_t affinity;
+
+	ASSERT_EQ(sched_getaffinity(0, sizeof(affinity), &affinity), 0);
+
+	/* Pin it on a single CPU. Avoid CPU 0 */
+	for (int i = 1; i < CPU_SETSIZE; i++) {
+		if (!CPU_ISSET(i, &affinity))
+			continue;
+
+		CPU_ZERO(&affinity);
+		CPU_SET(i, &affinity);
+		ASSERT_EQ(sched_setaffinity(0, sizeof(affinity), &affinity), 0);
+		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;
+
+	ASSERT_EQ(pthread_create(&self->noise_thread, NULL, noise_thread, &self->noise_params), 0);
+}
+
+FIXTURE_TEARDOWN(slice_ext)
+{
+	self->noise_params.run = 0;
+	pthread_join(self->noise_thread, NULL);
+}
+
+TEST_F(slice_ext, slice_test)
+{
+	unsigned long success = 0, yielded = 0, scheduled = 0, raced = 0;
+	unsigned long total = 0, aborted = 0;
+	struct rseq_abi *rs = rseq_get_abi();
+	struct timespec ts_start, ts_now;
+
+	ASSERT_NE(rs, NULL);
+
+	clock_gettime(CLOCK_MONOTONIC, &ts_start);
+	do {
+		struct timespec ts_cs;
+		bool req = false;
+
+		clock_gettime(CLOCK_MONOTONIC, &ts_cs);
+
+		total++;
+		RSEQ_WRITE_ONCE(rs->slice_ctrl.request, 1);
+		do {
+			clock_gettime(CLOCK_MONOTONIC, &ts_now);
+		} while (!elapsed(&ts_cs, &ts_now, variant->slice_nsecs));
+
+		/*
+		 * request can be cleared unconditionally, but for making
+		 * the stats work this is actually checking it first
+		 */
+		if (RSEQ_READ_ONCE(rs->slice_ctrl.request)) {
+			RSEQ_WRITE_ONCE(rs->slice_ctrl.request, 0);
+			/* Race between check and clear! */
+			req = true;
+			success++;
+		}
+
+		if (RSEQ_READ_ONCE(rs->slice_ctrl.granted)) {
+			/* The above raced against a late grant */
+			if (req)
+				success--;
+			if (variant->no_yield) {
+				syscall(__NR_getpid);
+				aborted++;
+			} else {
+				yielded++;
+				if (!syscall(__NR_rseq_slice_yield))
+					raced++;
+			}
+		} else {
+			if (!req)
+				scheduled++;
+		}
+
+		clock_gettime(CLOCK_MONOTONIC, &ts_now);
+	} while (!elapsed(&ts_start, &ts_now, variant->total_nsecs));
+
+	printf("# Total     %12ld\n", total);
+	printf("# Success   %12ld\n", success);
+	printf("# Yielded   %12ld\n", yielded);
+	printf("# Aborted   %12ld\n", aborted);
+	printf("# Scheduled %12ld\n", scheduled);
+	printf("# Raced     %12ld\n", raced);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/sched_ext/Makefile b/tools/testing/selftests/sched_ext/Makefile
index 5fe45f9c5f8f..2c601a7eaff5 100644
--- a/tools/testing/selftests/sched_ext/Makefile
+++ b/tools/testing/selftests/sched_ext/Makefile
@@ -183,7 +183,9 @@ auto-test-targets :=			\
 	select_cpu_dispatch_bad_dsq	\
 	select_cpu_dispatch_dbl_dsp	\
 	select_cpu_vtime		\
+	rt_stall			\
 	test_example			\
+	total_bw			\
 
 testcase-targets := $(addsuffix .o,$(addprefix $(SCXOBJ_DIR)/,$(auto-test-targets)))
 
diff --git a/tools/testing/selftests/sched_ext/rt_stall.bpf.c b/tools/testing/selftests/sched_ext/rt_stall.bpf.c
new file mode 100644
index 000000000000..80086779dd1e
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/rt_stall.bpf.c
@@ -0,0 +1,23 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * A scheduler that verified if RT tasks can stall SCHED_EXT tasks.
+ *
+ * Copyright (c) 2025 NVIDIA Corporation.
+ */
+
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+UEI_DEFINE(uei);
+
+void BPF_STRUCT_OPS(rt_stall_exit, struct scx_exit_info *ei)
+{
+	UEI_RECORD(uei, ei);
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops rt_stall_ops = {
+	.exit			= (void *)rt_stall_exit,
+	.name			= "rt_stall",
+};
diff --git a/tools/testing/selftests/sched_ext/rt_stall.c b/tools/testing/selftests/sched_ext/rt_stall.c
new file mode 100644
index 000000000000..015200f80f6e
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/rt_stall.c
@@ -0,0 +1,240 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2025 NVIDIA Corporation.
+ */
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <sched.h>
+#include <sys/prctl.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <time.h>
+#include <linux/sched.h>
+#include <signal.h>
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include <unistd.h>
+#include "rt_stall.bpf.skel.h"
+#include "scx_test.h"
+#include "../kselftest.h"
+
+#define CORE_ID		0	/* CPU to pin tasks to */
+#define RUN_TIME        5	/* How long to run the test in seconds */
+
+/* Simple busy-wait function for test tasks */
+static void process_func(void)
+{
+	while (1) {
+		/* Busy wait */
+		for (volatile unsigned long i = 0; i < 10000000UL; i++)
+			;
+	}
+}
+
+/* Set CPU affinity to a specific core */
+static void set_affinity(int cpu)
+{
+	cpu_set_t mask;
+
+	CPU_ZERO(&mask);
+	CPU_SET(cpu, &mask);
+	if (sched_setaffinity(0, sizeof(mask), &mask) != 0) {
+		perror("sched_setaffinity");
+		exit(EXIT_FAILURE);
+	}
+}
+
+/* Set task scheduling policy and priority */
+static void set_sched(int policy, int priority)
+{
+	struct sched_param param;
+
+	param.sched_priority = priority;
+	if (sched_setscheduler(0, policy, &param) != 0) {
+		perror("sched_setscheduler");
+		exit(EXIT_FAILURE);
+	}
+}
+
+/* Get process runtime from /proc/<pid>/stat */
+static float get_process_runtime(int pid)
+{
+	char path[256];
+	FILE *file;
+	long utime, stime;
+	int fields;
+
+	snprintf(path, sizeof(path), "/proc/%d/stat", pid);
+	file = fopen(path, "r");
+	if (file == NULL) {
+		perror("Failed to open stat file");
+		return -1;
+	}
+
+	/* Skip the first 13 fields and read the 14th and 15th */
+	fields = fscanf(file,
+			"%*d %*s %*c %*d %*d %*d %*d %*d %*u %*u %*u %*u %*u %lu %lu",
+			&utime, &stime);
+	fclose(file);
+
+	if (fields != 2) {
+		fprintf(stderr, "Failed to read stat file\n");
+		return -1;
+	}
+
+	/* Calculate the total time spent in the process */
+	long total_time = utime + stime;
+	long ticks_per_second = sysconf(_SC_CLK_TCK);
+	float runtime_seconds = total_time * 1.0 / ticks_per_second;
+
+	return runtime_seconds;
+}
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct rt_stall *skel;
+
+	skel = rt_stall__open();
+	SCX_FAIL_IF(!skel, "Failed to open");
+	SCX_ENUM_INIT(skel);
+	SCX_FAIL_IF(rt_stall__load(skel), "Failed to load skel");
+
+	*ctx = skel;
+
+	return SCX_TEST_PASS;
+}
+
+static bool sched_stress_test(bool is_ext)
+{
+	/*
+	 * We're expecting the EXT task to get around 5% of CPU time when
+	 * competing with the RT task (small 1% fluctuations are expected).
+	 *
+	 * However, the EXT task should get at least 4% of the CPU to prove
+	 * that the EXT deadline server is working correctly. A percentage
+	 * less than 4% indicates a bug where RT tasks can potentially
+	 * stall SCHED_EXT tasks, causing the test to fail.
+	 */
+	const float expected_min_ratio = 0.04; /* 4% */
+	const char *class_str = is_ext ? "EXT" : "FAIR";
+
+	float ext_runtime, rt_runtime, actual_ratio;
+	int ext_pid, rt_pid;
+
+	ksft_print_header();
+	ksft_set_plan(1);
+
+	/* Create and set up a EXT task */
+	ext_pid = fork();
+	if (ext_pid == 0) {
+		set_affinity(CORE_ID);
+		process_func();
+		exit(0);
+	} else if (ext_pid < 0) {
+		perror("fork task");
+		ksft_exit_fail();
+	}
+
+	/* Create an RT task */
+	rt_pid = fork();
+	if (rt_pid == 0) {
+		set_affinity(CORE_ID);
+		set_sched(SCHED_FIFO, 50);
+		process_func();
+		exit(0);
+	} else if (rt_pid < 0) {
+		perror("fork for RT task");
+		ksft_exit_fail();
+	}
+
+	/* Let the processes run for the specified time */
+	sleep(RUN_TIME);
+
+	/* Get runtime for the EXT task */
+	ext_runtime = get_process_runtime(ext_pid);
+	if (ext_runtime == -1)
+		ksft_exit_fail_msg("Error getting runtime for %s task (PID %d)\n",
+				   class_str, ext_pid);
+	ksft_print_msg("Runtime of %s task (PID %d) is %f seconds\n",
+		       class_str, ext_pid, ext_runtime);
+
+	/* Get runtime for the RT task */
+	rt_runtime = get_process_runtime(rt_pid);
+	if (rt_runtime == -1)
+		ksft_exit_fail_msg("Error getting runtime for RT task (PID %d)\n", rt_pid);
+	ksft_print_msg("Runtime of RT task (PID %d) is %f seconds\n", rt_pid, rt_runtime);
+
+	/* Kill the processes */
+	kill(ext_pid, SIGKILL);
+	kill(rt_pid, SIGKILL);
+	waitpid(ext_pid, NULL, 0);
+	waitpid(rt_pid, NULL, 0);
+
+	/* Verify that the scx task got enough runtime */
+	actual_ratio = ext_runtime / (ext_runtime + rt_runtime);
+	ksft_print_msg("%s task got %.2f%% of total runtime\n",
+		       class_str, actual_ratio * 100);
+
+	if (actual_ratio >= expected_min_ratio) {
+		ksft_test_result_pass("PASS: %s task got more than %.2f%% of runtime\n",
+				      class_str, expected_min_ratio * 100);
+		return true;
+	}
+	ksft_test_result_fail("FAIL: %s task got less than %.2f%% of runtime\n",
+			      class_str, expected_min_ratio * 100);
+	return false;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct rt_stall *skel = ctx;
+	struct bpf_link *link = NULL;
+	bool res;
+	int i;
+
+	/*
+	 * Test if the dl_server is working both with and without the
+	 * sched_ext scheduler attached.
+	 *
+	 * This ensures all the scenarios are covered:
+	 *   - fair_server stop -> ext_server start
+	 *   - ext_server stop -> fair_server stop
+	 */
+	for (i = 0; i < 4; i++) {
+		bool is_ext = i % 2;
+
+		if (is_ext) {
+			memset(&skel->data->uei, 0, sizeof(skel->data->uei));
+			link = bpf_map__attach_struct_ops(skel->maps.rt_stall_ops);
+			SCX_FAIL_IF(!link, "Failed to attach scheduler");
+		}
+		res = sched_stress_test(is_ext);
+		if (is_ext) {
+			SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_NONE));
+			bpf_link__destroy(link);
+		}
+
+		if (!res)
+			ksft_exit_fail();
+	}
+
+	return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	struct rt_stall *skel = ctx;
+
+	rt_stall__destroy(skel);
+}
+
+struct scx_test rt_stall = {
+	.name = "rt_stall",
+	.description = "Verify that RT tasks cannot stall SCHED_EXT tasks",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&rt_stall)
diff --git a/tools/testing/selftests/sched_ext/total_bw.c b/tools/testing/selftests/sched_ext/total_bw.c
new file mode 100644
index 000000000000..5b0a619bab86
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/total_bw.c
@@ -0,0 +1,281 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test to verify that total_bw value remains consistent across all CPUs
+ * in different BPF program states.
+ *
+ * Copyright (C) 2025 NVIDIA Corporation.
+ */
+#include <bpf/bpf.h>
+#include <errno.h>
+#include <pthread.h>
+#include <scx/common.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "minimal.bpf.skel.h"
+#include "scx_test.h"
+
+#define MAX_CPUS 512
+#define STRESS_DURATION_SEC 5
+
+struct total_bw_ctx {
+	struct minimal *skel;
+	long baseline_bw[MAX_CPUS];
+	int nr_cpus;
+};
+
+static void *cpu_stress_thread(void *arg)
+{
+	volatile int i;
+	time_t end_time = time(NULL) + STRESS_DURATION_SEC;
+
+	while (time(NULL) < end_time)
+		for (i = 0; i < 1000000; i++)
+			;
+
+	return NULL;
+}
+
+/*
+ * The first enqueue on a CPU causes the DL server to start, for that
+ * reason run stressor threads in the hopes it schedules on all CPUs.
+ */
+static int run_cpu_stress(int nr_cpus)
+{
+	pthread_t *threads;
+	int i, ret = 0;
+
+	threads = calloc(nr_cpus, sizeof(pthread_t));
+	if (!threads)
+		return -ENOMEM;
+
+	/* Create threads to run on each CPU */
+	for (i = 0; i < nr_cpus; i++) {
+		if (pthread_create(&threads[i], NULL, cpu_stress_thread, NULL)) {
+			ret = -errno;
+			fprintf(stderr, "Failed to create thread %d: %s\n", i, strerror(-ret));
+			break;
+		}
+	}
+
+	/* Wait for all threads to complete */
+	for (i = 0; i < nr_cpus; i++) {
+		if (threads[i])
+			pthread_join(threads[i], NULL);
+	}
+
+	free(threads);
+	return ret;
+}
+
+static int read_total_bw_values(long *bw_values, int max_cpus)
+{
+	FILE *fp;
+	char line[256];
+	int cpu_count = 0;
+
+	fp = fopen("/sys/kernel/debug/sched/debug", "r");
+	if (!fp) {
+		SCX_ERR("Failed to open debug file");
+		return -1;
+	}
+
+	while (fgets(line, sizeof(line), fp)) {
+		char *bw_str = strstr(line, "total_bw");
+
+		if (bw_str) {
+			bw_str = strchr(bw_str, ':');
+			if (bw_str) {
+				/* Only store up to max_cpus values */
+				if (cpu_count < max_cpus)
+					bw_values[cpu_count] = atol(bw_str + 1);
+				cpu_count++;
+			}
+		}
+	}
+
+	fclose(fp);
+	return cpu_count;
+}
+
+static bool verify_total_bw_consistency(long *bw_values, int count)
+{
+	int i;
+	long first_value;
+
+	if (count <= 0)
+		return false;
+
+	first_value = bw_values[0];
+
+	for (i = 1; i < count; i++) {
+		if (bw_values[i] != first_value) {
+			SCX_ERR("Inconsistent total_bw: CPU0=%ld, CPU%d=%ld",
+				first_value, i, bw_values[i]);
+			return false;
+		}
+	}
+
+	return true;
+}
+
+static int fetch_verify_total_bw(long *bw_values, int nr_cpus)
+{
+	int attempts = 0;
+	int max_attempts = 10;
+	int count;
+
+	/*
+	 * The first enqueue on a CPU causes the DL server to start, for that
+	 * reason run stressor threads in the hopes it schedules on all CPUs.
+	 */
+	if (run_cpu_stress(nr_cpus) < 0) {
+		SCX_ERR("Failed to run CPU stress");
+		return -1;
+	}
+
+	/* Try multiple times to get stable values */
+	while (attempts < max_attempts) {
+		count = read_total_bw_values(bw_values, nr_cpus);
+		fprintf(stderr, "Read %d total_bw values (testing %d CPUs)\n", count, nr_cpus);
+		/* If system has more CPUs than we're testing, that's OK */
+		if (count < nr_cpus) {
+			SCX_ERR("Expected at least %d CPUs, got %d", nr_cpus, count);
+			attempts++;
+			sleep(1);
+			continue;
+		}
+
+		/* Only verify the CPUs we're testing */
+		if (verify_total_bw_consistency(bw_values, nr_cpus)) {
+			fprintf(stderr, "Values are consistent: %ld\n", bw_values[0]);
+			return 0;
+		}
+
+		attempts++;
+		sleep(1);
+	}
+
+	return -1;
+}
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct total_bw_ctx *test_ctx;
+
+	if (access("/sys/kernel/debug/sched/debug", R_OK) != 0) {
+		fprintf(stderr, "Skipping test: debugfs sched/debug not accessible\n");
+		return SCX_TEST_SKIP;
+	}
+
+	test_ctx = calloc(1, sizeof(*test_ctx));
+	if (!test_ctx)
+		return SCX_TEST_FAIL;
+
+	test_ctx->nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
+	if (test_ctx->nr_cpus <= 0) {
+		free(test_ctx);
+		return SCX_TEST_FAIL;
+	}
+
+	/* If system has more CPUs than MAX_CPUS, just test the first MAX_CPUS */
+	if (test_ctx->nr_cpus > MAX_CPUS)
+		test_ctx->nr_cpus = MAX_CPUS;
+
+	/* Test scenario 1: BPF program not loaded */
+	/* Read and verify baseline total_bw before loading BPF program */
+	fprintf(stderr, "BPF prog initially not loaded, reading total_bw values\n");
+	if (fetch_verify_total_bw(test_ctx->baseline_bw, test_ctx->nr_cpus) < 0) {
+		SCX_ERR("Failed to get stable baseline values");
+		free(test_ctx);
+		return SCX_TEST_FAIL;
+	}
+
+	/* Load the BPF skeleton */
+	test_ctx->skel = minimal__open();
+	if (!test_ctx->skel) {
+		free(test_ctx);
+		return SCX_TEST_FAIL;
+	}
+
+	SCX_ENUM_INIT(test_ctx->skel);
+	if (minimal__load(test_ctx->skel)) {
+		minimal__destroy(test_ctx->skel);
+		free(test_ctx);
+		return SCX_TEST_FAIL;
+	}
+
+	*ctx = test_ctx;
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct total_bw_ctx *test_ctx = ctx;
+	struct bpf_link *link;
+	long loaded_bw[MAX_CPUS];
+	long unloaded_bw[MAX_CPUS];
+	int i;
+
+	/* Test scenario 2: BPF program loaded */
+	link = bpf_map__attach_struct_ops(test_ctx->skel->maps.minimal_ops);
+	if (!link) {
+		SCX_ERR("Failed to attach scheduler");
+		return SCX_TEST_FAIL;
+	}
+
+	fprintf(stderr, "BPF program loaded, reading total_bw values\n");
+	if (fetch_verify_total_bw(loaded_bw, test_ctx->nr_cpus) < 0) {
+		SCX_ERR("Failed to get stable values with BPF loaded");
+		bpf_link__destroy(link);
+		return SCX_TEST_FAIL;
+	}
+	bpf_link__destroy(link);
+
+	/* Test scenario 3: BPF program unloaded */
+	fprintf(stderr, "BPF program unloaded, reading total_bw values\n");
+	if (fetch_verify_total_bw(unloaded_bw, test_ctx->nr_cpus) < 0) {
+		SCX_ERR("Failed to get stable values after BPF unload");
+		return SCX_TEST_FAIL;
+	}
+
+	/* Verify all three scenarios have the same total_bw values */
+	for (i = 0; i < test_ctx->nr_cpus; i++) {
+		if (test_ctx->baseline_bw[i] != loaded_bw[i]) {
+			SCX_ERR("CPU%d: baseline_bw=%ld != loaded_bw=%ld",
+				i, test_ctx->baseline_bw[i], loaded_bw[i]);
+			return SCX_TEST_FAIL;
+		}
+
+		if (test_ctx->baseline_bw[i] != unloaded_bw[i]) {
+			SCX_ERR("CPU%d: baseline_bw=%ld != unloaded_bw=%ld",
+				i, test_ctx->baseline_bw[i], unloaded_bw[i]);
+			return SCX_TEST_FAIL;
+		}
+	}
+
+	fprintf(stderr, "All total_bw values are consistent across all scenarios\n");
+	return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	struct total_bw_ctx *test_ctx = ctx;
+
+	if (test_ctx) {
+		if (test_ctx->skel)
+			minimal__destroy(test_ctx->skel);
+		free(test_ctx);
+	}
+}
+
+struct scx_test total_bw = {
+	.name = "total_bw",
+	.description = "Verify total_bw consistency across BPF program states",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&total_bw)