Merge branch into tip/master: 'sched/core'

# New commits in sched/core:
    4a3b51aab6e2 ("smpboot: Don't park the thread if work is pending")
    40dcc9bdbef3 ("irq_work: Flush lazy work CPU down on PREEMPT_RT")
    791b1760accd ("irq_work: Update a comment regarding CPU hotplug invocation")
    648d44bda731 ("sched/topology: Add asymmetric SMT packing override")
    c8fc4136fd3c ("sched/fair: Honor asymmetric SMT priority in idle selection")
    53bc5c556b82 ("sched: Set TIF_NEED_RESCHED before calling __trace_set_need_resched()")
    4b1f75be23c4 ("sched/core: Fix context analysis errors in non-preferred CPU push")
    1fb28c664a19 ("virt/steal_governor: Enable the driver")
    27d47ebce4d6 ("virt/steal_governor: Implement steal_governor policy loop")
    4b9302d494ff ("virt/steal_governor: Add control knobs for handling steal values")
    9a8e740ee9f6 ("virt: Introduce steal governor driver")
    68957caaa9c0 ("sched/debug: Add migration stats due to non preferred CPUs")
    74699f56ebcf ("sched/core: Push current task from non preferred CPU")
    4ee29b029058 ("sched/fair: Load balance only among preferred CPUs")
    d8a3da0de843 ("sched/core: Try to use a preferred CPU in is_cpu_allowed")
    620824516557 ("sysfs: Add preferred CPU file")
    518b32bd5bb3 ("cpumask: Introduce cpu_preferred_mask")
    06a49ef784ac ("sched/docs: Document cpu_preferred_mask and Preferred CPU concept")
    cfb463b7172d ("cpumask: Introduce cpumask_intersects_and")
    a8d0854a76a8 ("sched/cputime: Add kcpustat_field_total helper")
    be100c77178e ("sched: Add sched_ext hooks for proxy execution")
    57c75e3ae38c ("sched: Add helper to block retained proxy donors")
    a49653d0abeb ("sched/core: Mark wakeups completed through ttwu_runnable()")
    8f8c0417e973 ("sched/core: Dequeue waking proxy donors before reset")
    313b652837d0 ("sched/core: Drop mutex locks before proxy rescheduling")
    627ea30aca3b ("sched/wait: Clarify WF_SYNC wakeup semantics")
    d2e010082757 ("sched/eevdf: Handle more short slice waking cases")
    4bf32ec3327d ("sched/eevdf: Align update_protect_slice to set_protect_slice")
    aae2a33ea662 ("sched/eevdf: Ensure that vprot will never go above a min slice")
    c9ce69fc43bd ("sched/fair: Randomize equally shallow slow-path candidates")
    abe440b3770f ("sched/fair: Drop idle recency from slow-path CPU selection")
    fbbc63fed0b0 ("sched/core: Remove redundant core_sched_seq")
    819224e506bc ("sched/fair: Remove dead code on enqueue_task_fair()")
    c72945693b90 ("sched: Restart fair hrtick after same-task repicks")
    a9b3c7570564 ("sched/headers: Replace __ASSEMBLY__ with __ASSEMBLER__ in the <uapi/linux/sched.h> header")
    e81ee0630837 ("sched/fair: Reset NUMA fault locality after scan period update")
    ef9293b3b797 ("sched: dynamic: Fix preemption model strings")
    879eaa76e608 ("sched: Remove unneeded function type cast in do_balance_callbacks()")
    f549101187c8 ("sched/deadline: check start_dl_timer expiry with ktime_before()")
    2a672daa4b27 ("sched/feat: Use the new static key API for sched_feat")
    a5576ebce920 ("sched: Convert paravirt_steal to new static key APIs")
    9650ce11f2e3 ("sched: dynamic: Simplify preempt model accessors")
    5b9a28eeed37 ("sched: dynamic: Remove HAVE_PREEMPT_DYNAMIC_{CALL,KEY}")
    aa4178f63847 ("sched: dynamic: Simplify irqentry_exit_cond_resched()")
    b9d267b9d632 ("sched: dynamic: Simplify preempt_schedule{,_notrace}()")
    88e0b3bb9930 ("sched: dynamic: Simplify {cond,might}_resched()")
    d3d16750693b ("sched: dynamic: Make PREEMPT_DYNAMIC depend on ARCH_HAS_PREEMPT_LAZY")
    772d9ffbfd26 ("sched: Migrate whole chain in proxy_migrate_task()")
    6b73a09e943f ("sched: Break out core of attach_tasks() helper into sched.h")
    1f8805138593 ("sched: Switch rq->next_class in proxy_reset_donor()")
    09351db90a28 ("sched/core: Don't proxy-exec unmatched cookie lock owners")
    9be817f991e2 ("sched/core: Avoid migrating blocked_on tasks")
    3dd95f077371 ("sched/core: Don't steal a proxy-exec donor")

Signed-off-by: Ingo Molnar <mingo@kernel.org>

62 files changed, 1246 insertions, 594 deletions

diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index 82d10d556cc8..8f250b8693b8 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -806,3 +806,17 @@ Date:		Nov 2022
 Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
 Description:
 		(RO) the list of CPUs that can be brought online.
+
+What:		/sys/devices/system/cpu/preferred
+Date:		Sep 2026
+Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
+Description:
+		(RO) the list of preferred CPUs applicable in
+		paravirtualized environments.
+
+		The steal governor driver dynamically adjusts this mask
+		based on observed steal time. Scheduling tasks on
+		CPUs outside of this list may lead to performance
+		degradations due to underlying physical CPU contention.
+
+		See Documentation/scheduler/sched-paravirt.rst for more details.
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index e75344f4e0cd..8157ff434cb5 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -6800,6 +6800,18 @@ Kernel parameters
 			solution to mutex-based priority inversion.
 			Format: <bool>
 
+	sched_smt_asym_packing= [KNL,SMP]
+			Format: on
+			Force asymmetric packing at the SMT scheduling domain.
+			Idle CPU selection prefers siblings with a higher
+			arch_asym_cpu_priority(). The default implementation
+			prefers lower-numbered logical CPUs, but architecture
+			overrides remain authoritative. Equal priorities do
+			not establish a sibling preference. For example, x86
+			with CONFIG_SCHED_MC_PRIO normally assigns the same
+			core priority to both SMT siblings, so this option
+			does not favor either sibling.
+
 	sched_verbose	[KNL,EARLY] Enables verbose scheduler debug messages.
 
 	schedstats=	[KNL,X86] Enable or disable scheduled statistics.
diff --git a/Documentation/driver-api/index.rst b/Documentation/driver-api/index.rst
index 6601a258690f..26b7638a327d 100644
--- a/Documentation/driver-api/index.rst
+++ b/Documentation/driver-api/index.rst
@@ -139,6 +139,7 @@ Subsystem-specific APIs
    sm501
    soundwire/index
    spi
+   steal-governor
    surface_aggregator/index
    switchtec
    sync_file
diff --git a/Documentation/driver-api/steal-governor.rst b/Documentation/driver-api/steal-governor.rst
new file mode 100644
index 000000000000..3817eedb38d7
--- /dev/null
+++ b/Documentation/driver-api/steal-governor.rst
@@ -0,0 +1,151 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Steal Governor
+==============
+
+:Author: Shrikanth Hegde <sshegde@linux.ibm.com>
+
+Introduction
+============
+
+The steal governor is aimed at mitigating the Noisy Neighbour problem
+which occurs in paravirtualized environments with CPU overcommit.
+The performance of a workload running in one VM gets degraded by
+the activity of other VMs on the same host. As a result, all VMs
+collectively make slower forward progress.
+
+In such systems, high utilization in all VMs causes the hypervisor to
+frequently preempt vCPUs. This vCPU preemption is expensive.
+To mitigate this, the kernel aims to restrict workloads to a subset of
+Preferred CPUs to reduce physical CPU contention.
+A detailed explanation of Preferred CPUs is available in
+``Documentation/scheduler/sched-paravirt.rst``.
+
+The steal governor selects ``CONFIG_PREFERRED_CPU=y`` which enables the
+scheduler core infrastructure to move the tasks to Preferred CPUs where
+possible. The driver controls the policy decisions regarding the state of
+preferred CPUs. That is, this driver decides which CPUs are preferred
+and which CPUs are non-preferred.
+
+The driver code is available at ``drivers/virt/steal_governor.c``.
+
+Core idea
+=========
+
+steal time is an indication available today in Guest which shows contention
+for underlying physical CPU. Use it as a hint in the guest to fold the
+workload to a reduced set of vCPUs. When there is contention, steal time
+will show up in all the guests. When each guest honors the hint and folds
+the workload to a smaller set of vCPUs (Preferred CPUs), it reduces the
+contention and thereby reduces vCPU preemption.
+This is achieved without any cross-guest communication.
+
+Steal governor driver effectively does:
+
+1. Periodically computes the steal ratio using accumulated steal time
+   across possible CPUs, normalized by the number of active CPUs.
+
+2. If steal ratio is greater than high threshold, reduce the number of
+   preferred CPUs by 1 core. Ensure at least one core is left always.
+   Skip changing the state of offline CPUs in that core.
+
+3. If steal ratio is less than or equal to low threshold, increase the
+   number of preferred CPUs by 1 core. If preferred is same as active,
+   nothing to be done. Skip changing the state of offline CPUs.
+   This helps to handle cases where few CPUs are offline in a core and
+   those offline CPUs will not be marked as preferred.
+
+4. Ensure preferred CPUs is always subset of active CPUs.
+   On feature disable it is same as active CPUs.
+
+This feature works best only when all the VMs enable the feature as
+it is a co-operative scheme. If a specific VM doesn't enable this feature
+it may end up with more CPUs than others, still should lead to better
+performance when seen from system view. Those who enable this driver must
+ensure it is enabled in all VMs.
+
+Note that this driver is strictly intended for actual guests; for example,
+loading this module in a privileged VM like Xen Dom0 is blocked.
+
+Workload considerations
+=======================
+
+The steal governor is useful for workloads where vCPU preemption has
+costs beyond the lost CPU time, such as lock-holder preemption, critical
+sections, communicating threads, and cache or TLB disruption.
+
+Pure CPU-time workloads with independent workers may not benefit and
+could see a small regression due to additional guest scheduling overhead.
+
+Module Parameters
+=================
+
+interval_ms
+-----------
+
+How often steal governor checks for steal time.
+Default: 1000 i.e. 1 second. Value should be in between 100ms to 100sec.
+
+This controls how fast steal governor driver reacts to changes to the
+contention of physical CPUs. Since it does a fair amount of work, setting
+too low may have overhead. Setting it too high might render it ineffective.
+
+low_threshold
+-------------
+
+lower threshold value in percentage * 100.
+Default: 200, i.e. 2% steal is considered as low threshold.
+Can't be higher than high_threshold.
+
+This determines what values should be considered as nil/no steal values.
+When steal governor sees steal ratio is less than or equal to this value,
+it will increase the preferred CPUs by 1 core.
+Using zero might cause oscillations.
+
+high_threshold
+--------------
+
+higher threshold value in percentage * 100
+Default: 500, i.e. 5% steal is considered as high threshold.
+Can't be lower than low_threshold. Must be less than 10000.
+
+This determines what values should be considered as high steal values.
+When steal governor sees steal ratio is higher than this value, it will
+reduce the preferred CPUs by 1 core.
+
+Limitations of default values
+-----------------------------
+
+Because of the vast diversity in VM configurations and different
+architectures, the default thresholds may not be optimal for all systems.
+Users may need to tune these parameters based on the system under
+test to achieve the best results.
+
+The governor sums the steal time across all possible CPUs, which ensures
+the accumulated steal time remains a monotonically increasing value.
+However, to calculate the effective steal ratio, it divides this sum
+by the number of active CPUs. Because only active CPUs contribute to
+the steal time delta, this prevents threshold dilution on sparsely
+populated systems.
+
+The driver reduces/increases preferred CPUs by core-level. This could provide
+faster convergence for hypervisors such as powerVM. But on KVM and Xen
+convergence could be slower depending on the configuration.
+Using a smaller interval_ms could help one to expedite it.
+
+Reasons for CONFIG_STEAL_GOVERNOR=m
+===================================
+
+Selecting this driver makes CONFIG_PREFERRED_CPU=y. That makes configs
+driven by user preference. Though one can have CONFIG_STEAL_GOVERNOR=y,
+It is recommended to build CONFIG_STEAL_GOVERNOR=m due to below reasons:
+
+1. Doing periodic work has additional overheads. Enabling this driver
+   in systems where steal time cannot happen is of no use. There is no
+   benefit with additional overheads in such systems.
+
+2. This works well when all VMs work in a co-operative manner. When an
+   administrative user enables it in one VM, he/she will likely enable
+   it in all VMs.
+
+3. User can tweak the module parameters by reloading the module.
diff --git a/Documentation/scheduler/index.rst b/Documentation/scheduler/index.rst
index 17ce8d76befc..a43647b9706d 100644
--- a/Documentation/scheduler/index.rst
+++ b/Documentation/scheduler/index.rst
@@ -23,5 +23,6 @@ Scheduler
     sched-stats
     sched-ext
     sched-debug
+    sched-paravirt
 
     text_files
diff --git a/Documentation/scheduler/sched-paravirt.rst b/Documentation/scheduler/sched-paravirt.rst
new file mode 100644
index 000000000000..311cdbf2722b
--- /dev/null
+++ b/Documentation/scheduler/sched-paravirt.rst
@@ -0,0 +1,67 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. _sched-paravirt:
+
+Preferred CPUs
+==============
+
+In paravirtualized environments CPU overcommit is a common scenario.
+i.e. the sum of virtual CPUs (vCPUs) of all VMs is greater than number of
+physical CPUs (pCPUs). Under such conditions when all or many VMs have
+high utilization, hypervisor won't be able to satisfy the CPU requirement
+and has to context switch within or across VMs. The hypervisor needs to
+preempt one vCPU to run another. This is called vCPU preemption.
+This is more expensive compared to task context switch within a vCPU, since
+hypervisor lacks vCPU context and could preempt a critical section which
+slows forward progress.
+
+In such cases it is better that combined vCPU demand from all VMs is reduced
+by not using some of the vCPUs in each VM. vCPUs where workload can be safely
+scheduled which won't increase any contention for pCPU are called
+"Preferred CPUs".
+
+One of the main design constructs is that preferred CPUs are always
+a subset of active CPUs. In most cases preferred CPUs will be same as
+active CPUs. When there is pCPU contention, Preferred CPUs will reduce
+based on the steal time. When the pCPU contention goes away as indicated
+by steal time, Preferred CPUs could become same as active CPUs again.
+The policy decisions are to be taken by driver.
+For example, steal_governor. Look at its documentation for more
+details. (``drivers/virt/steal_governor.c``)
+
+Scheduling decisions such as wakeup, pushing the task etc, need this
+CPU state info. This is maintained in ``cpu_preferred_mask``.
+vCPUs which are not in ``cpu_preferred_mask`` should be treated as vCPUs which
+should not be used at this moment provided it doesn't break user affinity.
+
+This is achieved by:
+
+1. Selecting a preferred CPU at wakeup using fallback mechanism.
+2. Pushing the task away from non-preferred CPU at tick.
+3. Selecting only preferred CPUs for load balance.
+
+``/sys/devices/system/cpu/preferred`` prints the current ``cpu_preferred_mask``
+in cpulist format.
+
+Notes:
+
+1. This feature is available under ``CONFIG_PREFERRED_CPU``. Driver which
+   makes decisions should enable it. For example, steal_governor driver
+   (``CONFIG_STEAL_GOVERNOR``). On enabling the driver, CPU preferred state
+   can change based on steal time. Without the driver, preferred CPUs is
+   same as active CPUs.
+
+2. This feature works for the FAIR class only.
+
+3. A pinned task, which can't be moved to preferred CPUs will continue
+   to run based on its affinity. But no load balancing happens if it is affined
+   only on non-preferred CPUs.
+
+4. Decision to change the preferred CPU state is driven by the kernel.
+   Hence it shouldn't break user affinities. One of the main reasons why
+   CPU hotplug or Isolated cpuset partitions was not a solution.
+
+5. This feature works best only when all the Guest VMs enable the feature as
+   it is a co-operative scheme. If a specific VM doesn't enable this feature
+   it may end up with more CPUs than others, still should lead to better
+   performance when seen from system view.
+   Users who enable this driver must ensure it is enabled in all Guest VMs.
diff --git a/MAINTAINERS b/MAINTAINERS
index 65e8a4b5c90b..2f9886865e90 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -26240,6 +26240,15 @@ F:	rust/helpers/jump_label.c
 F:	rust/kernel/generated_arch_static_branch_asm.rs.S
 F:	rust/kernel/jump_label.rs
 
+STEAL GOVERNOR DRIVER
+M:	Shrikanth Hegde <sshegde@linux.ibm.com>
+R:	Yury Norov <yury.norov@gmail.com>
+L:	linux-kernel@vger.kernel.org
+S:	Maintained
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git sched/core
+F:	Documentation/driver-api/steal-governor.rst
+F:	drivers/virt/steal_governor.c
+
 STI AUDIO (ASoC) DRIVERS
 M:	Arnaud Pouliquen <arnaud.pouliquen@foss.st.com>
 L:	linux-sound@vger.kernel.org
diff --git a/arch/Kconfig b/arch/Kconfig
index 45c657772362..c0a6a13b06a1 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -1712,44 +1712,6 @@ config HAVE_STATIC_CALL_INLINE
 	depends on HAVE_STATIC_CALL
 	select OBJTOOL
 
-config HAVE_PREEMPT_DYNAMIC
-	bool
-
-config HAVE_PREEMPT_DYNAMIC_CALL
-	bool
-	depends on HAVE_STATIC_CALL
-	select HAVE_PREEMPT_DYNAMIC
-	help
-	  An architecture should select this if it can handle the preemption
-	  model being selected at boot time using static calls.
-
-	  Where an architecture selects HAVE_STATIC_CALL_INLINE, any call to a
-	  preemption function will be patched directly.
-
-	  Where an architecture does not select HAVE_STATIC_CALL_INLINE, any
-	  call to a preemption function will go through a trampoline, and the
-	  trampoline will be patched.
-
-	  It is strongly advised to support inline static call to avoid any
-	  overhead.
-
-config HAVE_PREEMPT_DYNAMIC_KEY
-	bool
-	depends on HAVE_ARCH_JUMP_LABEL
-	select HAVE_PREEMPT_DYNAMIC
-	help
-	  An architecture should select this if it can handle the preemption
-	  model being selected at boot time using static keys.
-
-	  Each preemption function will be given an early return based on a
-	  static key. This should have slightly lower overhead than non-inline
-	  static calls, as this effectively inlines each trampoline into the
-	  start of its callee. This may avoid redundant work, and may
-	  integrate better with CFI schemes.
-
-	  This will have greater overhead than using inline static calls as
-	  the call to the preemption function cannot be entirely elided.
-
 config ARCH_WANT_LD_ORPHAN_WARN
 	bool
 	help
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 8ded9566f192..cce20d87dd69 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -217,7 +217,6 @@ config ARM64
 	select HAVE_PERF_EVENTS_NMI if ARM64_PSEUDO_NMI
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
-	select HAVE_PREEMPT_DYNAMIC_KEY
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RELIABLE_STACKTRACE
 	select HAVE_POSIX_CPU_TIMERS_TASK_WORK
diff --git a/arch/arm64/include/asm/preempt.h b/arch/arm64/include/asm/preempt.h
index 9ecc2766a9f2..e86e850e9b17 100644
--- a/arch/arm64/include/asm/preempt.h
+++ b/arch/arm64/include/asm/preempt.h
@@ -104,19 +104,9 @@ static inline bool should_resched(int preempt_offset)
 void preempt_schedule(void);
 void preempt_schedule_notrace(void);
 
-#ifdef CONFIG_PREEMPT_DYNAMIC
-
-void dynamic_preempt_schedule(void);
-#define __preempt_schedule()		dynamic_preempt_schedule()
-void dynamic_preempt_schedule_notrace(void);
-#define __preempt_schedule_notrace()	dynamic_preempt_schedule_notrace()
-
-#else /* CONFIG_PREEMPT_DYNAMIC */
-
 #define __preempt_schedule()		preempt_schedule()
 #define __preempt_schedule_notrace()	preempt_schedule_notrace()
 
-#endif /* CONFIG_PREEMPT_DYNAMIC */
 #endif /* CONFIG_PREEMPTION */
 
 #endif /* __ASM_PREEMPT_H */
diff --git a/arch/arm64/kernel/paravirt.c b/arch/arm64/kernel/paravirt.c
index 572efb96b23f..30bf61d031eb 100644
--- a/arch/arm64/kernel/paravirt.c
+++ b/arch/arm64/kernel/paravirt.c
@@ -157,9 +157,9 @@ int __init pv_time_init(void)
 
 	static_call_update(pv_steal_clock, para_steal_clock);
 
-	static_key_slow_inc(&paravirt_steal_enabled);
+	static_branch_inc(&paravirt_steal_enabled);
 	if (steal_acc)
-		static_key_slow_inc(&paravirt_steal_rq_enabled);
+		static_branch_inc(&paravirt_steal_rq_enabled);
 
 	pr_info("using stolen time PV\n");
 
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 2067d1f2ad7a..c346a9229542 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -170,7 +170,6 @@ config LOONGARCH
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_POSIX_CPU_TIMERS_TASK_WORK
-	select HAVE_PREEMPT_DYNAMIC_KEY
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RELIABLE_STACKTRACE if UNWINDER_ORC
 	select HAVE_RETHOOK
diff --git a/arch/loongarch/kernel/paravirt.c b/arch/loongarch/kernel/paravirt.c
index 10821cce554c..e8965a3f8082 100644
--- a/arch/loongarch/kernel/paravirt.c
+++ b/arch/loongarch/kernel/paravirt.c
@@ -308,10 +308,10 @@ int __init pv_time_init(void)
 
 	static_call_update(pv_steal_clock, paravt_steal_clock);
 
-	static_key_slow_inc(&paravirt_steal_enabled);
+	static_branch_inc(&paravirt_steal_enabled);
 #ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
 	if (steal_acc)
-		static_key_slow_inc(&paravirt_steal_rq_enabled);
+		static_branch_inc(&paravirt_steal_rq_enabled);
 #endif
 
 	if (static_key_enabled(&virt_preempt_key))
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 2580e27e4328..143381d267ce 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -279,7 +279,6 @@ config PPC
 	select HAVE_PERF_EVENTS_NMI		if PPC64
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
-	select HAVE_PREEMPT_DYNAMIC_KEY
 	select HAVE_POSIX_CPU_TIMERS_TASK_WORK
 	select HAVE_RETHOOK			if KPROBES
 	select HAVE_REGS_AND_STACK_ACCESS_API
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index f29e7547c995..c181df4dec70 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -876,9 +876,9 @@ static void __init pSeries_setup_arch(void)
 			static_branch_enable(&shared_processor);
 			pv_spinlocks_init();
 #ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
-			static_key_slow_inc(&paravirt_steal_enabled);
+			static_branch_inc(&paravirt_steal_enabled);
 			if (steal_acc)
-				static_key_slow_inc(&paravirt_steal_rq_enabled);
+				static_branch_inc(&paravirt_steal_rq_enabled);
 #endif
 		}
 
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index d6c2dbf8455c..de1923dc6137 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -195,7 +195,6 @@ config RISCV
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_POSIX_CPU_TIMERS_TASK_WORK
-	select HAVE_PREEMPT_DYNAMIC_KEY
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RETHOOK
 	select HAVE_RSEQ
diff --git a/arch/riscv/kernel/paravirt.c b/arch/riscv/kernel/paravirt.c
index 5f56be79cd06..9c13a6f1ea2a 100644
--- a/arch/riscv/kernel/paravirt.c
+++ b/arch/riscv/kernel/paravirt.c
@@ -116,9 +116,9 @@ int __init pv_time_init(void)
 
 	static_call_update(pv_steal_clock, pv_time_steal_clock);
 
-	static_key_slow_inc(&paravirt_steal_enabled);
+	static_branch_inc(&paravirt_steal_enabled);
 	if (steal_acc)
-		static_key_slow_inc(&paravirt_steal_rq_enabled);
+		static_branch_inc(&paravirt_steal_rq_enabled);
 
 	pr_info("Computing paravirt steal-time\n");
 
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 4b51bc6e8948..2682a2bacc58 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -246,7 +246,6 @@ config S390
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_POSIX_CPU_TIMERS_TASK_WORK
-	select HAVE_PREEMPT_DYNAMIC_KEY
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RELIABLE_STACKTRACE
 	select HAVE_RETHOOK
diff --git a/arch/s390/include/asm/preempt.h b/arch/s390/include/asm/preempt.h
index 5560d5fca2a3..60c6f019ec45 100644
--- a/arch/s390/include/asm/preempt.h
+++ b/arch/s390/include/asm/preempt.h
@@ -155,20 +155,9 @@ static __always_inline int __preempt_count_sub_return(int val)
 void preempt_schedule(void);
 void preempt_schedule_notrace(void);
 
-#ifdef CONFIG_PREEMPT_DYNAMIC
-
-void dynamic_preempt_schedule(void);
-void dynamic_preempt_schedule_notrace(void);
-#define __preempt_schedule()		dynamic_preempt_schedule()
-#define __preempt_schedule_notrace()	dynamic_preempt_schedule_notrace()
-
-#else /* CONFIG_PREEMPT_DYNAMIC */
-
 #define __preempt_schedule()		preempt_schedule()
 #define __preempt_schedule_notrace()	preempt_schedule_notrace()
 
-#endif /* CONFIG_PREEMPT_DYNAMIC */
-
 #endif /* CONFIG_PREEMPTION */
 
 #endif /* __ASM_PREEMPT_H */
diff --git a/arch/s390/kernel/hiperdispatch.c b/arch/s390/kernel/hiperdispatch.c
index 217206522266..c21496f0a141 100644
--- a/arch/s390/kernel/hiperdispatch.c
+++ b/arch/s390/kernel/hiperdispatch.c
@@ -207,16 +207,12 @@ static unsigned long hd_calculate_steal_percentage(void)
 {
 	unsigned long time_delta, steal_delta, steal, percentage;
 	static ktime_t prev;
-	int cpus, cpu;
+	int cpus;
 	ktime_t now;
 
-	cpus = 0;
-	steal = 0;
 	percentage = 0;
-	for_each_cpu(cpu, &hd_vmvl_cpumask) {
-		steal += kcpustat_cpu(cpu).cpustat[CPUTIME_STEAL];
-		cpus++;
-	}
+	steal = kcpustat_field_total(CPUTIME_STEAL, &hd_vmvl_cpumask);
+	cpus = cpumask_weight(&hd_vmvl_cpumask);
 	/*
 	 * If there is no vertical medium and low CPUs steal time
 	 * is 0 as vertical high CPUs shouldn't experience steal time.
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 15fd9ec5ecac..5a84998b6021 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -297,7 +297,6 @@ config X86
 	select HAVE_STACK_VALIDATION		if HAVE_OBJTOOL
 	select HAVE_STATIC_CALL
 	select HAVE_STATIC_CALL_INLINE		if HAVE_OBJTOOL
-	select HAVE_PREEMPT_DYNAMIC_CALL
 	select HAVE_RSEQ
 	select HAVE_RUST			if X86_64
 	select HAVE_SYSCALL_TRACEPOINTS
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index fafb6f8cdac3..d16d9c2f7b08 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -137,43 +137,15 @@ static __always_inline bool should_resched(int preempt_offset)
 extern asmlinkage void preempt_schedule(void);
 extern asmlinkage void preempt_schedule_thunk(void);
 
-#define preempt_schedule_dynamic_enabled	preempt_schedule_thunk
-#define preempt_schedule_dynamic_disabled	NULL
-
 extern asmlinkage void preempt_schedule_notrace(void);
 extern asmlinkage void preempt_schedule_notrace_thunk(void);
 
-#define preempt_schedule_notrace_dynamic_enabled	preempt_schedule_notrace_thunk
-#define preempt_schedule_notrace_dynamic_disabled	NULL
-
-#ifdef CONFIG_PREEMPT_DYNAMIC
-
-DECLARE_STATIC_CALL(preempt_schedule, preempt_schedule_dynamic_enabled);
-
-#define __preempt_schedule() \
-do { \
-	__STATIC_CALL_MOD_ADDRESSABLE(preempt_schedule); \
-	asm volatile ("call " STATIC_CALL_TRAMP_STR(preempt_schedule) : ASM_CALL_CONSTRAINT); \
-} while (0)
-
-DECLARE_STATIC_CALL(preempt_schedule_notrace, preempt_schedule_notrace_dynamic_enabled);
-
-#define __preempt_schedule_notrace() \
-do { \
-	__STATIC_CALL_MOD_ADDRESSABLE(preempt_schedule_notrace); \
-	asm volatile ("call " STATIC_CALL_TRAMP_STR(preempt_schedule_notrace) : ASM_CALL_CONSTRAINT); \
-} while (0)
-
-#else /* PREEMPT_DYNAMIC */
-
 #define __preempt_schedule() \
 	asm volatile ("call preempt_schedule_thunk" : ASM_CALL_CONSTRAINT);
 
 #define __preempt_schedule_notrace() \
 	asm volatile ("call preempt_schedule_notrace_thunk" : ASM_CALL_CONSTRAINT);
 
-#endif /* PREEMPT_DYNAMIC */
-
 #endif /* PREEMPTION */
 
 #undef __pc_op
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 34b73573b108..f7ab9e7902cf 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -328,9 +328,9 @@ static int vmware_cpu_down_prepare(unsigned int cpu)
 static __init int activate_jump_labels(void)
 {
 	if (has_steal_clock) {
-		static_key_slow_inc(&paravirt_steal_enabled);
+		static_branch_inc(&paravirt_steal_enabled);
 		if (steal_acc)
-			static_key_slow_inc(&paravirt_steal_rq_enabled);
+			static_branch_inc(&paravirt_steal_rq_enabled);
 	}
 
 	return 0;
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 6b0a5861ccb8..2ce01fdb8b4b 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -1054,9 +1054,9 @@ const __initconst struct hypervisor_x86 x86_hyper_kvm = {
 static __init int activate_jump_labels(void)
 {
 	if (has_steal_clock) {
-		static_key_slow_inc(&paravirt_steal_enabled);
+		static_branch_inc(&paravirt_steal_enabled);
 		if (steal_acc)
-			static_key_slow_inc(&paravirt_steal_rq_enabled);
+			static_branch_inc(&paravirt_steal_rq_enabled);
 	}
 
 	return 0;
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 69e52fed4241..747915ff974f 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -391,6 +391,15 @@ static int cpu_uevent(const struct device *dev, struct kobj_uevent_env *env)
 }
 #endif
 
+#ifdef CONFIG_PREFERRED_CPU
+static ssize_t preferred_show(struct device *dev,
+			      struct device_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(cpu_preferred_mask));
+}
+static DEVICE_ATTR_RO(preferred);
+#endif
+
 const struct bus_type cpu_subsys = {
 	.name = "cpu",
 	.dev_name = "cpu",
@@ -532,6 +541,9 @@ static struct attribute *cpu_root_attrs[] = {
 #ifdef CONFIG_GENERIC_CPU_AUTOPROBE
 	&dev_attr_modalias.attr,
 #endif
+#ifdef CONFIG_PREFERRED_CPU
+	&dev_attr_preferred.attr,
+#endif
 	NULL
 };
 
diff --git a/drivers/virt/Kconfig b/drivers/virt/Kconfig
index 52eb7e4ba71f..eeb84e578ddf 100644
--- a/drivers/virt/Kconfig
+++ b/drivers/virt/Kconfig
@@ -41,6 +41,23 @@ config FSL_HV_MANAGER
           4) A kernel interface for receiving callbacks when a managed
 	     partition shuts down.
 
+config STEAL_GOVERNOR
+	tristate "Dynamic vCPU management based on steal time"
+	depends on PARAVIRT && SMP
+	select PREFERRED_CPU
+	default m
+	help
+	  This driver helps to reduce the steal time in paravirtualized
+	  environments, thereby reducing vCPU preemption costs.
+
+	  By default preferred CPUs will be same as active CPUs. Depending
+	  on the steal time when steal_governor driver is enabled,
+	  preferred CPUs could become subset of active CPUs.
+	  More details are at: Documentation/driver-api/steal-governor.rst
+
+	  It is recommended to build it as module and load the module
+	  to enable it.
+
 source "drivers/virt/vboxguest/Kconfig"
 
 source "drivers/virt/nitro_enclaves/Kconfig"
diff --git a/drivers/virt/Makefile b/drivers/virt/Makefile
index f29901bd7820..05fb075ef5b8 100644
--- a/drivers/virt/Makefile
+++ b/drivers/virt/Makefile
@@ -5,6 +5,7 @@
 
 obj-$(CONFIG_FSL_HV_MANAGER)	+= fsl_hypervisor.o
 obj-$(CONFIG_VMGENID)		+= vmgenid.o
+obj-$(CONFIG_STEAL_GOVERNOR)	+= steal_governor.o
 obj-y				+= vboxguest/
 
 obj-$(CONFIG_NITRO_ENCLAVES)	+= nitro_enclaves/
diff --git a/drivers/virt/steal_governor.c b/drivers/virt/steal_governor.c
new file mode 100644
index 000000000000..6e31f9923dea
--- /dev/null
+++ b/drivers/virt/steal_governor.c
@@ -0,0 +1,296 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Steal time governor driver periodically computes steal time.
+ * Based on the thresholds it either reduce/increase the preferred
+ * CPUs which can be used by the workload to avoid vCPU preemption
+ * to an extent possible in paravirtualized environment.
+ *
+ * Available with CONFIG_STEAL_GOVERNOR
+ *
+ * Copyright (C) 2026 IBM
+ * Author: Shrikanth Hegde <sshegde@linux.ibm.com>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/cleanup.h>
+#include <linux/cpuhplock.h>
+#include <linux/cpumask.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/kernel_stat.h>
+#include <linux/kconfig.h>
+#include <linux/ktime.h>
+#include <linux/math64.h>
+#include <linux/module.h>
+#include <linux/sched/isolation.h>
+#include <linux/topology.h>
+#include <linux/types.h>
+#include <linux/workqueue.h>
+#ifdef CONFIG_XEN
+#include <xen/xen.h>
+#endif
+
+#if !IS_ENABLED(CONFIG_PREFERRED_CPU)
+#error "Steal Governor requires CONFIG_PREFERRED_CPU"
+#endif
+
+struct steal_governor {
+	ktime_t			time;
+	u64			steal;
+	unsigned long		delay;
+	unsigned int		interval_ms;
+	unsigned int		high_threshold;
+	unsigned int		low_threshold;
+	struct delayed_work	work;
+};
+
+static struct steal_governor sg_ctx = {
+	.interval_ms	=	1000,	/* 1 second */
+	.high_threshold =	500,	/* 5% */
+	.low_threshold	=	200,	/* 2% */
+};
+
+static void restore_preferred_to_active(void)
+{
+	int cpu;
+
+	guard(cpus_read_lock)();
+	for_each_cpu(cpu, cpu_active_mask)
+		set_cpu_preferred(cpu, true);
+}
+
+static int param_set_interval_ms(const char *val, const struct kernel_param *kp)
+{
+	unsigned int interval;
+	int ret;
+
+	ret = kstrtouint(val, 0, &interval);
+	if (ret)
+		return ret;
+
+	if (interval < 100 || interval > 100000) {
+		pr_err("interval_ms must be between 100 and 100000\n");
+		return -EINVAL;
+	}
+
+	return param_set_uint(val, kp);
+}
+
+static const struct kernel_param_ops interval_ms_ops = {
+	.set = param_set_interval_ms,
+	.get = param_get_uint,
+};
+
+module_param_cb(interval_ms, &interval_ms_ops, &sg_ctx.interval_ms, 0444);
+MODULE_PARM_DESC(interval_ms,
+		 "Sampling frequency in milliseconds. default: 1000");
+
+static int param_set_high_threshold(const char *val, const struct kernel_param *kp)
+{
+	unsigned int threshold;
+	int ret;
+
+	ret = kstrtouint(val, 0, &threshold);
+	if (ret)
+		return ret;
+
+	if (threshold >= 100 * 100) {
+		pr_err("high_threshold (%u) can't be more than 99.99%%\n", threshold);
+		return -EINVAL;
+	}
+
+	return param_set_uint(val, kp);
+}
+
+static const struct kernel_param_ops high_threshold_ops = {
+	.set = param_set_high_threshold,
+	.get = param_get_uint,
+};
+
+module_param_cb(high_threshold, &high_threshold_ops, &sg_ctx.high_threshold, 0444);
+MODULE_PARM_DESC(high_threshold,
+		 "High steal threshold. default: 500 i.e 5%. Must be > low_threshold");
+
+module_param_named(low_threshold, sg_ctx.low_threshold, uint, 0444);
+MODULE_PARM_DESC(low_threshold,
+		 "Low steal threshold. default: 200 i.e 2%. Must be < high_threshold");
+
+/* Return collective steal time across system. */
+static u64 get_system_steal_time(void)
+{
+	return kcpustat_field_total(CPUTIME_STEAL, cpu_possible_mask);
+}
+
+/* Return number of CPUs to consider for steal ratio. */
+static unsigned int get_system_cpus(void)
+{
+	return num_active_cpus();
+}
+
+/*
+ * Called when the steal governor detects high physical CPU contention.
+ * It finds the last active core in the preferred mask and mark those
+ * CPUs as non-preferred.
+ *
+ * Must ensure:
+ * - at least one core is always kept as preferred
+ * - preferred is always subset of active.
+ */
+static void decrease_preferred_cpus(void)
+{
+	const struct cpumask *first_hk_core;
+	int target_cpu = nr_cpu_ids;
+	int cpu;
+
+	guard(cpus_read_lock)();
+	cpu = cpumask_first_and(housekeeping_cpumask(HK_TYPE_KERNEL_NOISE),
+				cpu_preferred_mask);
+	if (cpu >= nr_cpu_ids)
+		return;
+
+	/* Always leave first housekeeping core as preferred. */
+	first_hk_core = topology_sibling_cpumask(cpu);
+	cpu = cpumask_last(cpu_preferred_mask);
+	if (cpu >= nr_cpu_ids)
+		return;
+
+	/* Find the last CPU which doesn't belong to that first hk_core. */
+	if (!cpumask_test_cpu(cpu, first_hk_core)) {
+		target_cpu = cpu;
+	} else {
+		for_each_cpu_andnot(cpu, cpu_preferred_mask, first_hk_core)
+			target_cpu = cpu;
+	}
+
+	/* Only the first housekeeping core remains */
+	if (target_cpu >= nr_cpu_ids)
+		return;
+
+	for_each_cpu_and(cpu, topology_sibling_cpumask(target_cpu),
+			 cpu_preferred_mask)
+		set_cpu_preferred(cpu, false);
+}
+
+/*
+ * Called when the steal governor detects no/low physical CPU contention.
+ * It finds the first active core outside of preferred mask and mark
+ * those CPUs as preferred.
+ *
+ * Must ensure preferred is subset of active.
+ */
+static void increase_preferred_cpus(void)
+{
+	int first_cpu, cpu;
+
+	guard(cpus_read_lock)();
+	first_cpu = cpumask_first_andnot(cpu_active_mask, cpu_preferred_mask);
+
+	/* All CPUs are preferred. Nothing to increase further */
+	if (first_cpu >= nr_cpu_ids)
+		return;
+
+	for_each_cpu_and(cpu, topology_sibling_cpumask(first_cpu),
+			 cpu_active_mask)
+		set_cpu_preferred(cpu, true);
+}
+
+static bool preferred_cpus_valid(void)
+{
+	if (cpumask_empty(cpu_preferred_mask)) {
+		pr_err("empty preferred mask. stopping\n");
+		return false;
+	}
+
+	if (!cpumask_subset(cpu_preferred_mask, cpu_active_mask)) {
+		pr_err("preferred: %*pbl is not subset of active: %*pbl, stopping\n",
+		       cpumask_pr_args(cpu_preferred_mask),
+		       cpumask_pr_args(cpu_active_mask));
+		return false;
+	}
+
+	return true;
+}
+
+static void steal_governor_loop(struct work_struct *work)
+{
+	u64 curr_steal, delta_steal, delta_ns, steal_ratio;
+	ktime_t now;
+
+	now = ktime_get();
+	delta_ns = ktime_to_ns(ktime_sub(now, sg_ctx.time));
+
+	if (unlikely(delta_ns < NSEC_PER_MSEC)) {
+		pr_err_ratelimited("work scheduled too soon delta_ns: %llu\n", delta_ns);
+		goto requeue_work;
+	}
+
+	curr_steal = get_system_steal_time();
+	delta_steal = curr_steal > sg_ctx.steal ? curr_steal - sg_ctx.steal : 0;
+	sg_ctx.steal = curr_steal;
+	sg_ctx.time = now;
+
+	/*
+	 * steal_ratio = (delta_steal * 100*100)/(delta_ns * num_cpus())
+	 * To avoid possible overflow, divide the denominator early.
+	 * Note minimum interval is 100ms.
+	 */
+	delta_ns = max_t(u64, div_u64(delta_ns * get_system_cpus(), 10000), 1);
+	steal_ratio = div64_u64(delta_steal, delta_ns);
+
+	if (steal_ratio > sg_ctx.high_threshold)
+		decrease_preferred_cpus();
+	else if (steal_ratio <= sg_ctx.low_threshold)
+		increase_preferred_cpus();
+	/*
+	 * else: steal ratio is within bounds. Still do design checks so that
+	 * module restores to active if CPU hotplug breaks those assumptions.
+	 */
+	if (!preferred_cpus_valid()) {
+		restore_preferred_to_active();
+		return;
+	}
+
+requeue_work:
+	schedule_delayed_work(&sg_ctx.work, sg_ctx.delay);
+}
+
+static int __init steal_governor_init(void)
+{
+#ifdef CONFIG_XEN
+	if (xen_initial_domain()) {
+		pr_err("Cannot load in Xen Dom0 (Host OS). Driver is for guests only.\n");
+		return -ENODEV;
+	}
+#endif
+
+	if (sg_ctx.low_threshold >= sg_ctx.high_threshold) {
+		pr_err("low_threshold (%u) must be less than high_threshold (%u)\n",
+		       sg_ctx.low_threshold, sg_ctx.high_threshold);
+		return -EINVAL;
+	}
+
+	sg_ctx.delay = msecs_to_jiffies(sg_ctx.interval_ms);
+	INIT_DELAYED_WORK(&sg_ctx.work, steal_governor_loop);
+	sg_ctx.steal = get_system_steal_time();
+	sg_ctx.time = ktime_get();
+	schedule_delayed_work(&sg_ctx.work, sg_ctx.delay);
+	pr_info("enabled. interval: %ums, high_threshold: %u, low_threshold: %u\n",
+		sg_ctx.interval_ms, sg_ctx.high_threshold, sg_ctx.low_threshold);
+
+	return 0;
+}
+
+static void __exit steal_governor_exit(void)
+{
+	disable_delayed_work_sync(&sg_ctx.work);
+	restore_preferred_to_active();
+	pr_info("disabled\n");
+}
+
+module_init(steal_governor_init);
+module_exit(steal_governor_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("IBM Corporation");
+MODULE_DESCRIPTION("Virtualization Steal Time Governor");
diff --git a/drivers/xen/time.c b/drivers/xen/time.c
index a2be0a4d45b0..a02d48a2aa68 100644
--- a/drivers/xen/time.c
+++ b/drivers/xen/time.c
@@ -169,7 +169,7 @@ void __init xen_time_setup_guest(void)
 
 	static_call_update(pv_steal_clock, xen_steal_clock);
 
-	static_key_slow_inc(&paravirt_steal_enabled);
+	static_branch_inc(&paravirt_steal_enabled);
 	if (xen_runstate_remote)
-		static_key_slow_inc(&paravirt_steal_rq_enabled);
+		static_branch_inc(&paravirt_steal_rq_enabled);
 }
diff --git a/fs/proc/uptime.c b/fs/proc/uptime.c
index 433aa947cd57..53143c66cbe1 100644
--- a/fs/proc/uptime.c
+++ b/fs/proc/uptime.c
@@ -15,12 +15,8 @@ static int uptime_proc_show(struct seq_file *m, void *v)
 	struct timespec64 idle;
 	u64 idle_nsec;
 	u32 rem;
-	int i;
-
-	idle_nsec = 0;
-	for_each_possible_cpu(i)
-		idle_nsec += kcpustat_field(CPUTIME_IDLE, i);
 
+	idle_nsec = kcpustat_field_total(CPUTIME_IDLE, cpu_possible_mask);
 	ktime_get_boottime_ts64(&uptime);
 	timens_add_boottime(&uptime);
 
diff --git a/include/asm-generic/preempt.h b/include/asm-generic/preempt.h
index c8683c046615..1adddeab8545 100644
--- a/include/asm-generic/preempt.h
+++ b/include/asm-generic/preempt.h
@@ -96,19 +96,9 @@ static __always_inline bool should_resched(int preempt_offset)
 extern asmlinkage void preempt_schedule(void);
 extern asmlinkage void preempt_schedule_notrace(void);
 
-#if defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
-
-void dynamic_preempt_schedule(void);
-void dynamic_preempt_schedule_notrace(void);
-#define __preempt_schedule()		dynamic_preempt_schedule()
-#define __preempt_schedule_notrace()	dynamic_preempt_schedule_notrace()
-
-#else /* !CONFIG_PREEMPT_DYNAMIC || !CONFIG_HAVE_PREEMPT_DYNAMIC_KEY*/
-
 #define __preempt_schedule() preempt_schedule()
 #define __preempt_schedule_notrace() preempt_schedule_notrace()
 
-#endif /* CONFIG_PREEMPT_DYNAMIC && CONFIG_HAVE_PREEMPT_DYNAMIC_KEY*/
 #endif /* CONFIG_PREEMPTION */
 
 #endif /* __ASM_PREEMPT_H */
diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index 7df1573a409c..adafbcf2016b 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -52,6 +52,7 @@ struct device;
  *  bitmap_complement(dst, src, nbits)          *dst = ~(*src)
  *  bitmap_equal(src1, src2, nbits)             Are *src1 and *src2 equal?
  *  bitmap_intersects(src1, src2, nbits)        Do *src1 and *src2 overlap?
+ *  bitmap_intersects_and(src1, src2, src3, nbits) Do *src1, *src2 and *src3 overlap?
  *  bitmap_subset(src1, src2, nbits)            Is *src1 a subset of *src2?
  *  bitmap_empty(src, nbits)                    Are all bits zero in *src?
  *  bitmap_full(src, nbits)                     Are all bits set in *src?
@@ -181,6 +182,9 @@ void __bitmap_replace(unsigned long *dst,
 		      const unsigned long *mask, unsigned int nbits);
 bool __bitmap_intersects(const unsigned long *bitmap1,
 			 const unsigned long *bitmap2, unsigned int nbits);
+bool __bitmap_intersects_and(const unsigned long *bitmap1,
+			     const unsigned long *bitmap2,
+			     const unsigned long *bitmap3, unsigned int nbits);
 bool __bitmap_subset(const unsigned long *bitmap1,
 		     const unsigned long *bitmap2, unsigned int nbits);
 unsigned int __bitmap_weight(const unsigned long *bitmap, unsigned int nbits);
@@ -446,6 +450,16 @@ bool bitmap_intersects(const unsigned long *src1, const unsigned long *src2, uns
 }
 
 static __always_inline
+bool bitmap_intersects_and(const unsigned long *src1, const unsigned long *src2,
+			   const unsigned long *src3, unsigned int nbits)
+{
+	if (small_const_nbits(nbits))
+		return ((*src1 & *src2 & *src3) & BITMAP_LAST_WORD_MASK(nbits)) != 0;
+	else
+		return __bitmap_intersects_and(src1, src2, src3, nbits);
+}
+
+static __always_inline
 bool bitmap_subset(const unsigned long *src1, const unsigned long *src2, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 4c8bb6953107..bf89bb3f30f6 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -121,12 +121,20 @@ extern struct cpumask __cpu_enabled_mask;
 extern struct cpumask __cpu_present_mask;
 extern struct cpumask __cpu_active_mask;
 extern struct cpumask __cpu_dying_mask;
+
+#ifdef CONFIG_PREFERRED_CPU
+extern struct cpumask __cpu_preferred_mask;
+#else
+#define __cpu_preferred_mask __cpu_active_mask
+#endif
+
 #define cpu_possible_mask ((const struct cpumask *)&__cpu_possible_mask)
 #define cpu_online_mask   ((const struct cpumask *)&__cpu_online_mask)
 #define cpu_enabled_mask   ((const struct cpumask *)&__cpu_enabled_mask)
 #define cpu_present_mask  ((const struct cpumask *)&__cpu_present_mask)
 #define cpu_active_mask   ((const struct cpumask *)&__cpu_active_mask)
 #define cpu_dying_mask    ((const struct cpumask *)&__cpu_dying_mask)
+#define cpu_preferred_mask ((const struct cpumask *)&__cpu_preferred_mask)
 
 extern atomic_t __num_online_cpus;
 extern unsigned int __num_possible_cpus;
@@ -825,6 +833,24 @@ bool cpumask_intersects(const struct cpumask *src1p, const struct cpumask *src2p
 }
 
 /**
+ * cpumask_intersects_and - (*src1p & *src2p & *src3p) != 0
+ * @src1p: the first input
+ * @src2p: the second input
+ * @src3p: the third input
+ *
+ * Return: true if AND of the three cpumasks is non-empty,
+ *	   otherwise false
+ */
+static __always_inline
+bool cpumask_intersects_and(const struct cpumask *src1p,
+			    const struct cpumask *src2p,
+			    const struct cpumask *src3p)
+{
+	return bitmap_intersects_and(cpumask_bits(src1p), cpumask_bits(src2p),
+				 cpumask_bits(src3p), small_cpumask_bits);
+}
+
+/**
  * cpumask_subset - (*src1p & ~*src2p) == 0
  * @src1p: the first input
  * @src2p: the second input
@@ -1163,6 +1189,12 @@ void init_cpu_possible(const struct cpumask *src);
 #define set_cpu_active(cpu, active)	assign_cpu((cpu), &__cpu_active_mask, (active))
 #define set_cpu_dying(cpu, dying)	assign_cpu((cpu), &__cpu_dying_mask, (dying))
 
+#ifdef CONFIG_PREFERRED_CPU
+#define set_cpu_preferred(cpu, preferred) assign_cpu((cpu), &__cpu_preferred_mask, (preferred))
+#else
+#define set_cpu_preferred(cpu, preferred) do { } while (0)
+#endif
+
 void set_cpu_online(unsigned int cpu, bool online);
 void set_cpu_possible(unsigned int cpu, bool possible);
 
@@ -1257,6 +1289,11 @@ static __always_inline bool cpu_dying(unsigned int cpu)
 	return cpumask_test_cpu(cpu, cpu_dying_mask);
 }
 
+static __always_inline bool cpu_preferred(unsigned int cpu)
+{
+	return cpumask_test_cpu(cpu, cpu_preferred_mask);
+}
+
 #else
 
 #define num_online_cpus()	1U
@@ -1295,6 +1332,11 @@ static __always_inline bool cpu_dying(unsigned int cpu)
 	return false;
 }
 
+static __always_inline bool cpu_preferred(unsigned int cpu)
+{
+	return cpu == 0;
+}
+
 #endif /* NR_CPUS > 1 */
 
 #define cpu_is_offline(cpu)	unlikely(!cpu_online(cpu))
diff --git a/include/linux/irq-entry-common.h b/include/linux/irq-entry-common.h
index 0bb6c03481fa..2be273bb68f0 100644
--- a/include/linux/irq-entry-common.h
+++ b/include/linux/irq-entry-common.h
@@ -346,22 +346,7 @@ typedef struct irqentry_state {
  *
  * Conditional reschedule with additional sanity checks.
  */
-void raw_irqentry_exit_cond_resched(void);
-
-#ifdef CONFIG_PREEMPT_DYNAMIC
-#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
-#define irqentry_exit_cond_resched_dynamic_enabled	raw_irqentry_exit_cond_resched
-#define irqentry_exit_cond_resched_dynamic_disabled	NULL
-DECLARE_STATIC_CALL(irqentry_exit_cond_resched, raw_irqentry_exit_cond_resched);
-#define irqentry_exit_cond_resched()	static_call(irqentry_exit_cond_resched)()
-#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
-DECLARE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched);
-void dynamic_irqentry_exit_cond_resched(void);
-#define irqentry_exit_cond_resched()	dynamic_irqentry_exit_cond_resched()
-#endif
-#else /* CONFIG_PREEMPT_DYNAMIC */
-#define irqentry_exit_cond_resched()	raw_irqentry_exit_cond_resched()
-#endif /* CONFIG_PREEMPT_DYNAMIC */
+void irqentry_exit_cond_resched(void);
 
 /**
  * irqentry_enter_from_kernel_mode - Establish state before invoking the irq handler
diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h
index c5afd053ae32..7184e1273965 100644
--- a/include/linux/irq_work.h
+++ b/include/linux/irq_work.h
@@ -59,6 +59,7 @@ void irq_work_sync(struct irq_work *work);
 #include <asm/irq_work.h>
 
 void irq_work_run(void);
+void irq_work_run_cpu(unsigned int cpu);
 bool irq_work_needs_cpu(void);
 void irq_work_single(void *arg);
 
@@ -67,6 +68,7 @@ void arch_irq_work_raise(void);
 #else
 static inline bool irq_work_needs_cpu(void) { return false; }
 static inline void irq_work_run(void) { }
+static inline void irq_work_run_cpu(unsigned int cpu) { }
 static inline void irq_work_single(void *arg) { }
 #endif
 
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 24414c79e59a..4b11d1dc0a67 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -43,30 +43,10 @@ struct completion;
 struct user;
 
 #ifdef CONFIG_PREEMPT_VOLUNTARY_BUILD
-
 extern int __cond_resched(void);
 # define might_resched() __cond_resched()
-
-#elif defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
-
-extern int __cond_resched(void);
-
-DECLARE_STATIC_CALL(might_resched, __cond_resched);
-
-static __always_inline void might_resched(void)
-{
-	static_call_mod(might_resched)();
-}
-
-#elif defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
-
-extern int dynamic_might_resched(void);
-# define might_resched() dynamic_might_resched()
-
 #else
-
 # define might_resched() do { } while (0)
-
 #endif /* CONFIG_PREEMPT_* */
 
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index 9ca6c2259dfe..c1e85550bf12 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -196,6 +196,17 @@ static inline void kcpustat_cpu_fetch(struct kernel_cpustat *dst, int cpu)
 }
 #endif /* !CONFIG_VIRT_CPU_ACCOUNTING_GEN */
 
+static inline u64 kcpustat_field_total(enum cpu_usage_stat usage, const struct cpumask *cpus)
+{
+	u64 total = 0;
+	int cpu;
+
+	for_each_cpu(cpu, cpus)
+		total += kcpustat_field(usage, cpu);
+
+	return total;
+}
+
 extern void account_user_time(struct task_struct *, u64);
 extern void account_guest_time(struct task_struct *, u64);
 extern void account_system_time(struct task_struct *, int, u64);
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index 2e689de7b29a..06ff44a4b8b6 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -498,21 +498,11 @@ DEFINE_LOCK_GUARD_0(preempt_notrace, preempt_disable_notrace(), preempt_enable_n
 
 #ifdef CONFIG_PREEMPT_DYNAMIC
 
-extern bool preempt_model_none(void);
-extern bool preempt_model_voluntary(void);
 extern bool preempt_model_full(void);
 extern bool preempt_model_lazy(void);
 
 #else
 
-static inline bool preempt_model_none(void)
-{
-	return IS_ENABLED(CONFIG_PREEMPT_NONE);
-}
-static inline bool preempt_model_voluntary(void)
-{
-	return IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY);
-}
 static inline bool preempt_model_full(void)
 {
 	return IS_ENABLED(CONFIG_PREEMPT);
@@ -525,6 +515,16 @@ static inline bool preempt_model_lazy(void)
 
 #endif
 
+static inline bool preempt_model_none(void)
+{
+	return IS_ENABLED(CONFIG_PREEMPT_NONE);
+}
+
+static inline bool preempt_model_voluntary(void)
+{
+	return IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY);
+}
+
 static inline bool preempt_model_rt(void)
 {
 	return IS_ENABLED(CONFIG_PREEMPT_RT);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index d35ae49a991f..0cb03f9acfe3 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -554,6 +554,7 @@ struct sched_statistics {
 	u64				nr_failed_migrations_running;
 	u64				nr_failed_migrations_hot;
 	u64				nr_forced_migrations;
+	u64				nr_migrations_cpu_non_preferred;
 
 	u64				nr_wakeups;
 	u64				nr_wakeups_sync;
@@ -2105,10 +2106,9 @@ static inline int test_tsk_thread_flag(struct task_struct *tsk, int flag)
 
 static inline void set_tsk_need_resched(struct task_struct *tsk)
 {
-	if (tracepoint_enabled(sched_set_need_resched_tp) &&
-	    !test_tsk_thread_flag(tsk, TIF_NEED_RESCHED))
+	if (!test_and_set_tsk_thread_flag(tsk, TIF_NEED_RESCHED) &&
+	    tracepoint_enabled(sched_set_need_resched_tp))
 		__trace_set_need_resched(tsk, TIF_NEED_RESCHED);
-	set_tsk_thread_flag(tsk,TIF_NEED_RESCHED);
 }
 
 static inline void clear_tsk_need_resched(struct task_struct *tsk)
@@ -2135,44 +2135,19 @@ static inline void set_need_resched_current(void)
  * value indicates whether a reschedule was done in fact.
  * cond_resched_lock() will drop the spinlock before scheduling,
  */
-#if !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC)
+#if !defined(CONFIG_PREEMPTION)
 extern int __cond_resched(void);
 
-#if defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
-
-DECLARE_STATIC_CALL(cond_resched, __cond_resched);
-
-static __always_inline int _cond_resched(void)
-{
-	return static_call_mod(cond_resched)();
-}
-
-#elif defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
-
-extern int dynamic_cond_resched(void);
-
-static __always_inline int _cond_resched(void)
-{
-	return dynamic_cond_resched();
-}
-
-#else /* !CONFIG_PREEMPTION */
-
 static inline int _cond_resched(void)
 {
 	return __cond_resched();
 }
-
-#endif /* PREEMPT_DYNAMIC && CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */
-
-#else /* CONFIG_PREEMPTION && !CONFIG_PREEMPT_DYNAMIC */
-
+#else
 static inline int _cond_resched(void)
 {
 	return 0;
 }
-
-#endif /* !CONFIG_PREEMPTION || CONFIG_PREEMPT_DYNAMIC */
+#endif
 
 #define cond_resched() ({			\
 	__might_resched(__FILE__, __LINE__, 0);	\
diff --git a/include/linux/sched/cputime.h b/include/linux/sched/cputime.h
index e90efaf6d26e..694126411dfe 100644
--- a/include/linux/sched/cputime.h
+++ b/include/linux/sched/cputime.h
@@ -182,9 +182,9 @@ extern unsigned long long
 task_sched_runtime(struct task_struct *task);
 
 #ifdef CONFIG_PARAVIRT
-struct static_key;
-extern struct static_key paravirt_steal_enabled;
-extern struct static_key paravirt_steal_rq_enabled;
+#include <linux/jump_label.h>
+DECLARE_STATIC_KEY_FALSE(paravirt_steal_enabled);
+DECLARE_STATIC_KEY_FALSE(paravirt_steal_rq_enabled);
 
 #ifdef CONFIG_HAVE_PV_STEAL_CLOCK_GEN
 u64 dummy_steal_clock(int cpu);
diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h
index 33a4624285cd..19ffeba89428 100644
--- a/include/uapi/linux/sched.h
+++ b/include/uapi/linux/sched.h
@@ -53,7 +53,7 @@
  */
 #define UNSHARE_EMPTY_MNTNS 0x00100000 /* Unshare an empty mount namespace. */
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 /**
  * struct clone_args - arguments for the clone3 syscall
  * @flags:        Flags for the new process as listed above.
diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt
index f294dad43bd7..edc067a0c422 100644
--- a/kernel/Kconfig.preempt
+++ b/kernel/Kconfig.preempt
@@ -132,10 +132,9 @@ config PREEMPTION
 
 config PREEMPT_DYNAMIC
 	bool "Preemption behaviour defined on boot"
-	depends on HAVE_PREEMPT_DYNAMIC
-	select JUMP_LABEL if HAVE_PREEMPT_DYNAMIC_KEY
+	depends on ARCH_HAS_PREEMPT_LAZY
 	select PREEMPT_BUILD
-	default y if HAVE_PREEMPT_DYNAMIC_CALL
+	default y
 	help
 	  This option allows to define the preemption model on the kernel
 	  command line parameter and thus override the default preemption
@@ -145,9 +144,7 @@ config PREEMPT_DYNAMIC
 	  provide a pre-built kernel binary to reduce the number of kernel
 	  flavors they offer while still offering different usecases.
 
-	  The runtime overhead is negligible with HAVE_STATIC_CALL_INLINE enabled
-	  but if runtime patching is not available for the specific architecture
-	  then the potential overhead should be considered.
+	  The runtime overhead is negligible.
 
 	  Interesting if you want the same pre-built kernel should be used for
 	  both Server and Desktop workloads.
@@ -197,3 +194,7 @@ config SCHED_CLASS_EXT
 	  For more information:
 	    Documentation/scheduler/sched-ext.rst
 	    https://github.com/sched-ext/scx
+
+config PREFERRED_CPU
+	bool
+	depends on SMP && PARAVIRT
diff --git a/kernel/cpu.c b/kernel/cpu.c
index b3c8553d7bd6..376d297a6292 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -3103,6 +3103,11 @@ EXPORT_SYMBOL(__cpu_dying_mask);
 atomic_t __num_online_cpus __read_mostly;
 EXPORT_SYMBOL(__num_online_cpus);
 
+#ifdef CONFIG_PREFERRED_CPU
+struct cpumask __cpu_preferred_mask __read_mostly;
+EXPORT_SYMBOL_GPL(__cpu_preferred_mask);
+#endif
+
 void init_cpu_present(const struct cpumask *src)
 {
 	cpumask_copy(&__cpu_present_mask, src);
@@ -3160,6 +3165,7 @@ void __init boot_cpu_init(void)
 	/* Mark the boot cpu "present", "online" etc for SMP and UP case */
 	set_cpu_online(cpu, true);
 	set_cpu_active(cpu, true);
+	set_cpu_preferred(cpu, true);
 	set_cpu_present(cpu, true);
 	set_cpu_possible(cpu, true);
 
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index e3d381fd3d25..e234b04373fe 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -123,7 +123,7 @@ noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs)
 /**
  * arch_irqentry_exit_need_resched - Architecture specific need resched function
  *
- * Invoked from raw_irqentry_exit_cond_resched() to check if resched is needed.
+ * Invoked from irqentry_exit_cond_resched() to check if resched is needed.
  * Defaults return true.
  *
  * The main purpose is to permit arch to avoid preemption of a task from an IRQ.
@@ -134,7 +134,7 @@ static inline bool arch_irqentry_exit_need_resched(void);
 static inline bool arch_irqentry_exit_need_resched(void) { return true; }
 #endif
 
-void raw_irqentry_exit_cond_resched(void)
+void irqentry_exit_cond_resched(void)
 {
 	if (!preempt_count()) {
 		/* Sanity check RCU and thread stack */
@@ -145,19 +145,6 @@ void raw_irqentry_exit_cond_resched(void)
 			preempt_schedule_irq();
 	}
 }
-#ifdef CONFIG_PREEMPT_DYNAMIC
-#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
-DEFINE_STATIC_CALL(irqentry_exit_cond_resched, raw_irqentry_exit_cond_resched);
-#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
-DEFINE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched);
-void dynamic_irqentry_exit_cond_resched(void)
-{
-	if (!static_branch_unlikely(&sk_dynamic_irqentry_exit_cond_resched))
-		return;
-	raw_irqentry_exit_cond_resched();
-}
-#endif
-#endif
 
 noinstr void irqentry_exit(struct pt_regs *regs, irqentry_state_t state)
 {
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index f7e2dc2c30c6..73eabcbdcd50 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -252,10 +252,7 @@ static void irq_work_run_list(struct llist_head *list)
 		irq_work_single(work);
 }
 
-/*
- * hotplug calls this through:
- *  hotplug_cfd() -> flush_smp_call_function_queue()
- */
+/* CPU hotplug calls this through smpcfd_dying_cpu() */
 void irq_work_run(void)
 {
 	irq_work_run_list(this_cpu_ptr(&raised_list));
@@ -266,6 +263,17 @@ void irq_work_run(void)
 }
 EXPORT_SYMBOL_GPL(irq_work_run);
 
+void irq_work_run_cpu(unsigned int cpu)
+{
+	if (WARN_ON_ONCE(!cpumask_test_cpu(cpu, cpu_dying_mask)))
+		return;
+
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+		return;
+
+	irq_work_run_list(per_cpu_ptr(&lazy_list, cpu));
+}
+
 void irq_work_tick(void)
 {
 	struct llist_head *raised = this_cpu_ptr(&raised_list);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 1fe40de6ebe3..047fbe8ef298 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -805,7 +805,7 @@ struct rq *_task_rq_lock(struct task_struct *p, struct rq_flags *rf)
 
 /* Use CONFIG_PARAVIRT as this will avoid more #ifdef in arch code. */
 #ifdef CONFIG_PARAVIRT
-struct static_key paravirt_steal_rq_enabled;
+DEFINE_STATIC_KEY_FALSE(paravirt_steal_rq_enabled);
 #endif
 
 static void update_rq_clock_task(struct rq *rq, s64 delta)
@@ -844,7 +844,7 @@ static void update_rq_clock_task(struct rq *rq, s64 delta)
 	}
 #endif
 #ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
-	if (static_key_false((&paravirt_steal_rq_enabled))) {
+	if (static_branch_unlikely(&paravirt_steal_rq_enabled)) {
 		u64 prev_steal;
 
 		steal = prev_steal = paravirt_steal_clock(cpu_of(rq));
@@ -1196,6 +1196,7 @@ static void __resched_curr(struct rq *rq, int tif)
 {
 	struct task_struct *curr = rq->curr;
 	struct thread_info *cti = task_thread_info(curr);
+	bool need_ipi;
 	int cpu;
 
 	lockdep_assert_rq_held(rq);
@@ -1212,15 +1213,17 @@ static void __resched_curr(struct rq *rq, int tif)
 
 	cpu = cpu_of(rq);
 
-	trace_sched_set_need_resched_tp(curr, cpu, tif);
 	if (cpu == smp_processor_id()) {
 		set_ti_thread_flag(cti, tif);
 		if (tif == TIF_NEED_RESCHED)
 			set_preempt_need_resched();
+		trace_sched_set_need_resched_tp(curr, cpu, tif);
 		return;
 	}
 
-	if (set_nr_and_not_polling(cti, tif)) {
+	need_ipi = set_nr_and_not_polling(cti, tif);
+	trace_sched_set_need_resched_tp(curr, cpu, tif);
+	if (need_ipi) {
 		if (tif == TIF_NEED_RESCHED)
 			smp_send_reschedule(cpu);
 	} else {
@@ -2252,7 +2255,8 @@ void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
 	dequeue_task(rq, p, flags);
 }
 
-static void block_task(struct rq *rq, struct task_struct *p, unsigned long task_state)
+static bool dequeue_block_task(struct rq *rq, struct task_struct *p,
+			       unsigned long task_state)
 {
 	int flags = DEQUEUE_NOCLOCK;
 
@@ -2273,9 +2277,15 @@ static void block_task(struct rq *rq, struct task_struct *p, unsigned long task_
 	 *
 	 * Where __schedule() and ttwu() have matching control dependencies.
 	 *
-	 * After this, schedule() must not care about p->state any more.
+	 * Once the caller invokes __block_task(), schedule() must not care about
+	 * p->state any more.
 	 */
-	if (dequeue_task(rq, p, DEQUEUE_SLEEP | flags))
+	return dequeue_task(rq, p, DEQUEUE_SLEEP | flags);
+}
+
+static void block_task(struct rq *rq, struct task_struct *p, unsigned long task_state)
+{
+	if (dequeue_block_task(rq, p, task_state))
 		__block_task(rq, p);
 }
 
@@ -2504,6 +2514,24 @@ static inline bool rq_has_pinned_tasks(struct rq *rq)
 	return rq->nr_pinned;
 }
 
+static inline bool task_can_migrate_to_preferred(struct task_struct *p, int cpu)
+{
+	/* No need to migrate from a preferred CPU */
+	if (cpu_preferred(cpu))
+		return false;
+
+	/* Only FAIR tasks honor preferred CPU state */
+	if (unlikely(p->sched_class != &fair_sched_class))
+		return false;
+
+	/* Ignore preferred state if task affinity is changing */
+	if (unlikely(!cpumask_test_cpu(task_cpu(p), p->cpus_ptr)))
+		return false;
+
+	return cpumask_intersects_and(p->cpus_ptr, cpu_preferred_mask,
+				      task_cpu_possible_mask(p));
+}
+
 /*
  * Per-CPU kthreads are allowed to run on !active && online CPUs, see
  * __set_cpus_allowed_ptr() and select_fallback_rq().
@@ -2519,8 +2547,12 @@ static inline bool is_cpu_allowed(struct task_struct *p, int cpu)
 		return cpu_online(cpu);
 
 	/* Non kernel threads are not allowed during either online or offline. */
-	if (!(p->flags & PF_KTHREAD))
+	if (!(p->flags & PF_KTHREAD)) {
+		/* Try to use preferred CPU if task's affinity allows */
+		if (task_can_migrate_to_preferred(p, cpu))
+			return false;
 		return cpu_active(cpu);
+	}
 
 	/* KTHREAD_IS_PER_CPU is always allowed. */
 	if (kthread_is_per_cpu(p))
@@ -2530,7 +2562,11 @@ static inline bool is_cpu_allowed(struct task_struct *p, int cpu)
 	if (cpu_dying(cpu))
 		return false;
 
-	/* But are allowed during online. */
+	/* Try to keep unbound kthreads on a preferred CPU if possible. */
+	if (task_can_migrate_to_preferred(p, cpu))
+		return false;
+
+	/* Otherwise, they are allowed to run on online CPU. */
 	return cpu_online(cpu);
 }
 
@@ -3773,6 +3809,7 @@ static inline void proxy_reset_donor(struct rq *rq)
 	WARN_ON_ONCE(rq->donor == rq->curr);
 
 	put_prev_set_next_task(rq, rq->donor, rq->curr);
+	rq->next_class = rq->curr->sched_class;
 	rq_set_donor(rq, rq->curr);
 	zap_balance_callbacks(rq);
 	resched_curr(rq);
@@ -3787,6 +3824,8 @@ static inline void proxy_reset_donor(struct rq *rq)
  */
 static inline bool proxy_needs_return(struct rq *rq, struct task_struct *p)
 {
+	bool dequeued;
+
 	/*
 	 * Typically per __set_task_cpu(), task_cpu(p) == p->wake_cpu.
 	 *
@@ -3809,12 +3848,23 @@ static inline bool proxy_needs_return(struct rq *rq, struct task_struct *p)
 		/* If already current, don't need to return migrate */
 		if (task_current(rq, p))
 			return false;
-
-		/* If we're return migrating the rq->donor, switch it out for idle */
-		if (task_current_donor(rq, p))
-			proxy_reset_donor(rq);
 	}
-	block_task(rq, p, TASK_WAKING);
+
+	dequeued = dequeue_block_task(rq, p, TASK_WAKING);
+
+	/*
+	 * Dequeue @p from its scheduling class before resetting rq->donor.
+	 * In particular, sched_ext needs to end the donor's running session
+	 * and clear SCX_TASK_QUEUED before put_prev_task_scx() is called by
+	 * proxy_reset_donor(); otherwise it would reenqueue the blocked donor.
+	 *
+	 * Keep on_rq set until all donor references have been replaced.
+	 */
+	if (task_current_donor(rq, p))
+		proxy_reset_donor(rq);
+
+	if (dequeued)
+		__block_task(rq, p);
 	return true;
 }
 #else /* !CONFIG_SCHED_PROXY_EXEC */
@@ -3905,7 +3955,7 @@ static int ttwu_runnable(struct task_struct *p, int wake_flags)
 		 * When on_rq && !on_cpu the task is preempted, see if
 		 * it should preempt the task that is current now.
 		 */
-		wakeup_preempt(rq, p, wake_flags);
+		wakeup_preempt(rq, p, wake_flags | WF_TTWU_RQ);
 	}
 	ttwu_do_wakeup(p);
 	return 1;
@@ -5149,7 +5199,7 @@ static void do_balance_callbacks(struct rq *rq, struct balance_callback *head)
 	lockdep_assert_rq_held(rq);
 
 	while (head) {
-		func = (void (*)(struct rq *))head->func;
+		func = head->func;
 		next = head->next;
 		head->next = NULL;
 		head = next;
@@ -5789,6 +5839,9 @@ void sched_tick(void)
 	unsigned long hw_pressure;
 	u64 resched_latency;
 
+	if (!cpu_preferred(cpu))
+		sched_push_current_non_preferred_cpu(rq);
+
 	if (housekeeping_cpu(cpu, HK_TYPE_KERNEL_NOISE))
 		arch_scale_freq_tick();
 
@@ -6283,10 +6336,7 @@ pick_next_task(struct rq *rq, struct rq_flags *rf)
 	 * selection. In this case, do a core-wide selection.
 	 */
 	if (rq->core->core_pick_seq == rq->core->core_task_seq &&
-	    rq->core->core_pick_seq != rq->core_sched_seq &&
 	    rq->core_pick) {
-		WRITE_ONCE(rq->core_sched_seq, rq->core->core_pick_seq);
-
 		next = rq->core_pick;
 		rq->dl_server = rq->core_dl_server;
 		rq->core_pick = NULL;
@@ -6318,11 +6368,13 @@ restart:
 	}
 
 	/*
-	 * core->core_task_seq, core->core_pick_seq, rq->core_sched_seq
+	 * core->core_task_seq, core->core_pick_seq
 	 *
 	 * @task_seq guards the task state ({en,de}queues)
 	 * @pick_seq is the @task_seq we did a selection on
-	 * @sched_seq is the @pick_seq we scheduled
+	 *
+	 * Once a core-wide selection is committed, a non-NULL core_pick denotes
+	 * a pick which still needs to be consumed on this CPU.
 	 *
 	 * However, preemptions can cause multiple picks on the same task set.
 	 * 'Fix' this by also increasing @task_seq for every pick.
@@ -6429,7 +6481,6 @@ restart:
 
 	rq->core->core_pick_seq = rq->core->core_task_seq;
 	next = rq->core_pick;
-	rq->core_sched_seq = rq->core->core_pick_seq;
 
 	/* Something should have been selected for current CPU */
 	WARN_ON_ONCE(!next);
@@ -6517,7 +6568,10 @@ static bool try_steal_cookie(int this, int that)
 		return false;
 
 	do {
-		if (p == src->core_pick || p == src->curr)
+		if (p == src->core_pick || p == src->curr || p == src->donor)
+			goto next;
+
+		if (task_is_blocked(p))
 			goto next;
 
 		if (!is_cpu_allowed(p, this))
@@ -6820,6 +6874,34 @@ static void proxy_deactivate(struct rq *rq, struct task_struct *donor)
 	block_task(rq, donor, state);
 }
 
+/*
+ * Remove a retained proxy donor before changing its scheduler ownership.
+ * The caller holds p->pi_lock, so p cannot wake and migrate if block_task()
+ * drops it from the runqueue. If DELAY_DEQUEUE keeps a blocked fair task
+ * queued, switching_from_fair() completes the dequeue in the immediately
+ * following sched_change_begin().
+ */
+void sched_proxy_block_task(struct rq *rq, struct task_struct *p)
+{
+	unsigned long state = READ_ONCE(p->__state);
+
+	lockdep_assert_held(&p->pi_lock);
+	lockdep_assert_rq_held(rq);
+
+	if (!p->is_blocked || !task_on_rq_queued(p))
+		return;
+	if (WARN_ON_ONCE(state == TASK_RUNNING))
+		return;
+
+	if (task_current_donor(rq, p))
+		proxy_reset_donor(rq);
+
+	if (!p->se.sched_delayed)
+		block_task(rq, p, state);
+
+	WARN_ON_ONCE(task_on_rq_queued(p) && !p->se.sched_delayed);
+}
+
 static inline void proxy_release_rq_lock(struct rq *rq, struct rq_flags *rf)
 	__releases(__rq_lockp(rq))
 {
@@ -6865,9 +6947,9 @@ static void proxy_migrate_task(struct rq *rq, struct rq_flags *rf,
 	__must_hold(__rq_lockp(rq))
 {
 	struct rq *target_rq = cpu_rq(target_cpu);
+	LIST_HEAD(migrate_list);
 
 	lockdep_assert_rq_held(rq);
-	WARN_ON(p == rq->curr);
 	/*
 	 * Since we are migrating a blocked donor, it could be rq->donor,
 	 * and we want to make sure there aren't any references from this
@@ -6880,13 +6962,20 @@ static void proxy_migrate_task(struct rq *rq, struct rq_flags *rf,
 	 * before we release the lock.
 	 */
 	proxy_resched_idle(rq);
-
-	deactivate_task(rq, p, DEQUEUE_NOCLOCK);
-	proxy_set_task_cpu(p, target_cpu);
-
+	for (; p; p = p->blocked_donor) {
+		WARN_ON(p == rq->curr);
+		deactivate_task(rq, p, DEQUEUE_NOCLOCK);
+		proxy_set_task_cpu(p, target_cpu);
+		/*
+		 * We can re-use se.group_node to migrate the thing,
+		 * because @p is deactivated (won't be balanced) and
+		 * we hold the rq_lock.
+		 */
+		list_add(&p->se.group_node, &migrate_list);
+	}
 	proxy_release_rq_lock(rq, rf);
 
-	attach_one_task(target_rq, p);
+	__attach_tasks(target_rq, &migrate_list);
 
 	proxy_reacquire_rq_lock(rq, rf);
 }
@@ -6979,7 +7068,7 @@ find_proxy_task(struct rq *rq, struct task_struct *donor, struct rq_flags *rf)
 		if (!READ_ONCE(owner->on_rq) || owner->se.sched_delayed) {
 			/* XXX Don't handle blocked owners/delayed dequeue yet */
 			if (curr_in_chain)
-				return proxy_resched_idle(rq);
+				goto resched_idle;
 			__clear_task_blocked_on(p, NULL);
 			goto deactivate;
 		}
@@ -6991,7 +7080,7 @@ find_proxy_task(struct rq *rq, struct task_struct *donor, struct rq_flags *rf)
 			 * and leave that CPU to sort things out.
 			 */
 			if (curr_in_chain)
-				return proxy_resched_idle(rq);
+				goto resched_idle;
 			goto migrate_task;
 		}
 
@@ -7004,7 +7093,7 @@ find_proxy_task(struct rq *rq, struct task_struct *donor, struct rq_flags *rf)
 			 * case we should end up back in find_proxy_task(), this time
 			 * hopefully with all relevant tasks already enqueued.
 			 */
-			return proxy_resched_idle(rq);
+			goto resched_idle;
 		}
 
 		/*
@@ -7041,7 +7130,7 @@ find_proxy_task(struct rq *rq, struct task_struct *donor, struct rq_flags *rf)
 			 * So schedule rq->idle so that ttwu_runnable() can get the rq
 			 * lock and mark owner as running.
 			 */
-			return proxy_resched_idle(rq);
+			goto resched_idle;
 		}
 		/*
 		 * OK, now we're absolutely sure @owner is on this
@@ -7051,8 +7140,18 @@ find_proxy_task(struct rq *rq, struct task_struct *donor, struct rq_flags *rf)
 		owner->blocked_donor = p;
 	}
 	WARN_ON_ONCE(owner && !owner->on_rq);
+
+	if (owner && !sched_cpu_cookie_match(rq, owner)) {
+		if (curr_in_chain)
+			return proxy_resched_idle(rq);
+		p = donor; /* Deactivate the donor, not the runnable owner */
+		clear_task_blocked_on(p, NULL);
+		goto deactivate;
+	}
 	return owner;
 
+resched_idle:
+	return proxy_resched_idle(rq);
 deactivate:
 	proxy_deactivate(rq, p);
 	return NULL;
@@ -7184,13 +7283,12 @@ static void __sched notrace __schedule(int sched_mode)
 		}
 	} else if (!preempt && prev_state) {
 		/*
-		 * We pass task_is_blocked() as the should_block arg
-		 * in order to keep mutex-blocked tasks on the runqueue
-		 * for slection with proxy-exec (without proxy-exec
-		 * task_is_blocked() will always be false).
+		 * Keep mutex-blocked tasks on the runqueue for proxy execution
+		 * only when their scheduling class allows it. Without proxy
+		 * execution, task_is_blocked() always returns false.
 		 */
 		try_to_block_task(rq, prev, &prev_state,
-				  !task_is_blocked(prev));
+				  !task_is_blocked(prev) || !scx_allow_proxy_exec(prev));
 		switch_count = &prev->nvcsw;
 	}
 
@@ -7211,6 +7309,7 @@ pick_again:
 			}
 			if (next == rq->idle) {
 				zap_balance_callbacks(rq);
+				scx_proxy_reenqueue_retry(rq, next);
 				goto keep_resched;
 			}
 		}
@@ -7229,8 +7328,10 @@ pick_again:
 			 * on_cpu.
 			 */
 			donor->sched_class->put_prev_task(rq, donor, donor);
-			donor->sched_class->set_next_task(rq, donor, true);
+			donor->sched_class->set_next_task(rq, donor, SNT_PICK);
 		}
+		scx_proxy_donor_start(rq);
+		scx_proxy_reenqueue_retry(rq, next);
 	} else {
 		rq_set_donor(rq, next);
 	}
@@ -7489,27 +7590,6 @@ asmlinkage __visible void __sched notrace preempt_schedule(void)
 NOKPROBE_SYMBOL(preempt_schedule);
 EXPORT_SYMBOL(preempt_schedule);
 
-#ifdef CONFIG_PREEMPT_DYNAMIC
-# ifdef CONFIG_HAVE_PREEMPT_DYNAMIC_CALL
-#  ifndef preempt_schedule_dynamic_enabled
-#   define preempt_schedule_dynamic_enabled	preempt_schedule
-#   define preempt_schedule_dynamic_disabled	NULL
-#  endif
-DEFINE_STATIC_CALL(preempt_schedule, preempt_schedule_dynamic_enabled);
-EXPORT_STATIC_CALL_TRAMP(preempt_schedule);
-# elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
-static DEFINE_STATIC_KEY_TRUE(sk_dynamic_preempt_schedule);
-void __sched notrace dynamic_preempt_schedule(void)
-{
-	if (!static_branch_unlikely(&sk_dynamic_preempt_schedule))
-		return;
-	preempt_schedule();
-}
-NOKPROBE_SYMBOL(dynamic_preempt_schedule);
-EXPORT_SYMBOL(dynamic_preempt_schedule);
-# endif
-#endif /* CONFIG_PREEMPT_DYNAMIC */
-
 /**
  * preempt_schedule_notrace - preempt_schedule called by tracing
  *
@@ -7562,27 +7642,6 @@ asmlinkage __visible void __sched notrace preempt_schedule_notrace(void)
 }
 EXPORT_SYMBOL_GPL(preempt_schedule_notrace);
 
-#ifdef CONFIG_PREEMPT_DYNAMIC
-# if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
-#  ifndef preempt_schedule_notrace_dynamic_enabled
-#   define preempt_schedule_notrace_dynamic_enabled	preempt_schedule_notrace
-#   define preempt_schedule_notrace_dynamic_disabled	NULL
-#  endif
-DEFINE_STATIC_CALL(preempt_schedule_notrace, preempt_schedule_notrace_dynamic_enabled);
-EXPORT_STATIC_CALL_TRAMP(preempt_schedule_notrace);
-# elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
-static DEFINE_STATIC_KEY_TRUE(sk_dynamic_preempt_schedule_notrace);
-void __sched notrace dynamic_preempt_schedule_notrace(void)
-{
-	if (!static_branch_unlikely(&sk_dynamic_preempt_schedule_notrace))
-		return;
-	preempt_schedule_notrace();
-}
-NOKPROBE_SYMBOL(dynamic_preempt_schedule_notrace);
-EXPORT_SYMBOL(dynamic_preempt_schedule_notrace);
-# endif
-#endif
-
 #endif /* CONFIG_PREEMPTION */
 
 /*
@@ -7799,7 +7858,7 @@ out_unlock:
 }
 #endif /* CONFIG_RT_MUTEXES */
 
-#if !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC)
+#if !defined(CONFIG_PREEMPTION)
 int __sched __cond_resched(void)
 {
 	if (should_resched(0) && !irqs_disabled()) {
@@ -7827,38 +7886,6 @@ int __sched __cond_resched(void)
 EXPORT_SYMBOL(__cond_resched);
 #endif
 
-#ifdef CONFIG_PREEMPT_DYNAMIC
-# ifdef CONFIG_HAVE_PREEMPT_DYNAMIC_CALL
-#  define cond_resched_dynamic_enabled	__cond_resched
-#  define cond_resched_dynamic_disabled	((void *)&__static_call_return0)
-DEFINE_STATIC_CALL_RET0(cond_resched, __cond_resched);
-EXPORT_STATIC_CALL_TRAMP(cond_resched);
-
-#  define might_resched_dynamic_enabled	__cond_resched
-#  define might_resched_dynamic_disabled ((void *)&__static_call_return0)
-DEFINE_STATIC_CALL_RET0(might_resched, __cond_resched);
-EXPORT_STATIC_CALL_TRAMP(might_resched);
-# elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
-static DEFINE_STATIC_KEY_FALSE(sk_dynamic_cond_resched);
-int __sched dynamic_cond_resched(void)
-{
-	if (!static_branch_unlikely(&sk_dynamic_cond_resched))
-		return 0;
-	return __cond_resched();
-}
-EXPORT_SYMBOL(dynamic_cond_resched);
-
-static DEFINE_STATIC_KEY_FALSE(sk_dynamic_might_resched);
-int __sched dynamic_might_resched(void)
-{
-	if (!static_branch_unlikely(&sk_dynamic_might_resched))
-		return 0;
-	return __cond_resched();
-}
-EXPORT_SYMBOL(dynamic_might_resched);
-# endif
-#endif /* CONFIG_PREEMPT_DYNAMIC */
-
 /*
  * __cond_resched_lock() - if a reschedule is pending, drop the given lock,
  * call schedule, and on return reacquire the lock.
@@ -7928,50 +7955,21 @@ EXPORT_SYMBOL(__cond_resched_rwlock_write);
 # endif
 
 /*
- * SC:cond_resched
- * SC:might_resched
- * SC:preempt_schedule
- * SC:preempt_schedule_notrace
- * SC:irqentry_exit_cond_resched
- *
- *
  * NONE:
- *   cond_resched               <- __cond_resched
- *   might_resched              <- RET0
- *   preempt_schedule           <- NOP
- *   preempt_schedule_notrace   <- NOP
- *   irqentry_exit_cond_resched <- NOP
- *   dynamic_preempt_lazy       <- false
+ *   (unselectable)
  *
  * VOLUNTARY:
- *   cond_resched               <- __cond_resched
- *   might_resched              <- __cond_resched
- *   preempt_schedule           <- NOP
- *   preempt_schedule_notrace   <- NOP
- *   irqentry_exit_cond_resched <- NOP
- *   dynamic_preempt_lazy       <- false
+ *   (unselectable)
  *
  * FULL:
- *   cond_resched               <- RET0
- *   might_resched              <- RET0
- *   preempt_schedule           <- preempt_schedule
- *   preempt_schedule_notrace   <- preempt_schedule_notrace
- *   irqentry_exit_cond_resched <- irqentry_exit_cond_resched
  *   dynamic_preempt_lazy       <- false
  *
  * LAZY:
- *   cond_resched               <- RET0
- *   might_resched              <- RET0
- *   preempt_schedule           <- preempt_schedule
- *   preempt_schedule_notrace   <- preempt_schedule_notrace
- *   irqentry_exit_cond_resched <- irqentry_exit_cond_resched
  *   dynamic_preempt_lazy       <- true
  */
 
 enum {
 	preempt_dynamic_undefined = -1,
-	preempt_dynamic_none,
-	preempt_dynamic_voluntary,
 	preempt_dynamic_full,
 	preempt_dynamic_lazy,
 };
@@ -7980,21 +7978,11 @@ int preempt_dynamic_mode = preempt_dynamic_undefined;
 
 int sched_dynamic_mode(const char *str)
 {
-# if !(defined(CONFIG_PREEMPT_RT) || defined(CONFIG_ARCH_HAS_PREEMPT_LAZY))
-	if (!strcmp(str, "none"))
-		return preempt_dynamic_none;
-
-	if (!strcmp(str, "voluntary"))
-		return preempt_dynamic_voluntary;
-# endif
-
 	if (!strcmp(str, "full"))
 		return preempt_dynamic_full;
 
-# ifdef CONFIG_ARCH_HAS_PREEMPT_LAZY
 	if (!strcmp(str, "lazy"))
 		return preempt_dynamic_lazy;
-# endif
 
 	return -EINVAL;
 }
@@ -8002,71 +7990,18 @@ int sched_dynamic_mode(const char *str)
 # define preempt_dynamic_key_enable(f)	static_key_enable(&sk_dynamic_##f.key)
 # define preempt_dynamic_key_disable(f)	static_key_disable(&sk_dynamic_##f.key)
 
-# if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
-#  define preempt_dynamic_enable(f)	static_call_update(f, f##_dynamic_enabled)
-#  define preempt_dynamic_disable(f)	static_call_update(f, f##_dynamic_disabled)
-# elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
-#  define preempt_dynamic_enable(f)	preempt_dynamic_key_enable(f)
-#  define preempt_dynamic_disable(f)	preempt_dynamic_key_disable(f)
-# else
-#  error "Unsupported PREEMPT_DYNAMIC mechanism"
-# endif
-
 static DEFINE_MUTEX(sched_dynamic_mutex);
 
 static void __sched_dynamic_update(int mode)
 {
-	/*
-	 * Avoid {NONE,VOLUNTARY} -> FULL transitions from ever ending up in
-	 * the ZERO state, which is invalid.
-	 */
-	preempt_dynamic_enable(cond_resched);
-	preempt_dynamic_enable(might_resched);
-	preempt_dynamic_enable(preempt_schedule);
-	preempt_dynamic_enable(preempt_schedule_notrace);
-	preempt_dynamic_enable(irqentry_exit_cond_resched);
-	preempt_dynamic_key_disable(preempt_lazy);
-
 	switch (mode) {
-	case preempt_dynamic_none:
-		preempt_dynamic_enable(cond_resched);
-		preempt_dynamic_disable(might_resched);
-		preempt_dynamic_disable(preempt_schedule);
-		preempt_dynamic_disable(preempt_schedule_notrace);
-		preempt_dynamic_disable(irqentry_exit_cond_resched);
-		preempt_dynamic_key_disable(preempt_lazy);
-		if (mode != preempt_dynamic_mode)
-			pr_info("Dynamic Preempt: none\n");
-		break;
-
-	case preempt_dynamic_voluntary:
-		preempt_dynamic_enable(cond_resched);
-		preempt_dynamic_enable(might_resched);
-		preempt_dynamic_disable(preempt_schedule);
-		preempt_dynamic_disable(preempt_schedule_notrace);
-		preempt_dynamic_disable(irqentry_exit_cond_resched);
-		preempt_dynamic_key_disable(preempt_lazy);
-		if (mode != preempt_dynamic_mode)
-			pr_info("Dynamic Preempt: voluntary\n");
-		break;
-
 	case preempt_dynamic_full:
-		preempt_dynamic_disable(cond_resched);
-		preempt_dynamic_disable(might_resched);
-		preempt_dynamic_enable(preempt_schedule);
-		preempt_dynamic_enable(preempt_schedule_notrace);
-		preempt_dynamic_enable(irqentry_exit_cond_resched);
 		preempt_dynamic_key_disable(preempt_lazy);
 		if (mode != preempt_dynamic_mode)
 			pr_info("Dynamic Preempt: full\n");
 		break;
 
 	case preempt_dynamic_lazy:
-		preempt_dynamic_disable(cond_resched);
-		preempt_dynamic_disable(might_resched);
-		preempt_dynamic_enable(preempt_schedule);
-		preempt_dynamic_enable(preempt_schedule_notrace);
-		preempt_dynamic_enable(irqentry_exit_cond_resched);
 		preempt_dynamic_key_enable(preempt_lazy);
 		if (mode != preempt_dynamic_mode)
 			pr_info("Dynamic Preempt: lazy\n");
@@ -8099,11 +8034,7 @@ __setup("preempt=", setup_preempt_mode);
 static void __init preempt_dynamic_init(void)
 {
 	if (preempt_dynamic_mode == preempt_dynamic_undefined) {
-		if (IS_ENABLED(CONFIG_PREEMPT_NONE)) {
-			sched_dynamic_update(preempt_dynamic_none);
-		} else if (IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY)) {
-			sched_dynamic_update(preempt_dynamic_voluntary);
-		} else if (IS_ENABLED(CONFIG_PREEMPT_LAZY)) {
+		if (IS_ENABLED(CONFIG_PREEMPT_LAZY)) {
 			sched_dynamic_update(preempt_dynamic_lazy);
 		} else {
 			/* Default static call setting, nothing to do */
@@ -8123,8 +8054,6 @@ static void __init preempt_dynamic_init(void)
 	}								\
 	EXPORT_SYMBOL_GPL(preempt_model_##mode)
 
-PREEMPT_MODEL_ACCESSOR(none);
-PREEMPT_MODEL_ACCESSOR(voluntary);
 PREEMPT_MODEL_ACCESSOR(full);
 PREEMPT_MODEL_ACCESSOR(lazy);
 
@@ -8137,7 +8066,7 @@ static inline void preempt_dynamic_init(void) { }
 #endif /* CONFIG_PREEMPT_DYNAMIC */
 
 const char *preempt_modes[] = {
-	"none", "voluntary", "full", "lazy", NULL,
+	"full", "lazy", NULL,
 };
 
 const char *preempt_model_str(void)
@@ -8759,6 +8688,9 @@ int sched_cpu_activate(unsigned int cpu)
 	 */
 	sched_set_rq_online(rq, cpu);
 
+	/* preferred is subset of active and follows its state */
+	set_cpu_preferred(cpu, true);
+
 	return 0;
 }
 
@@ -8772,6 +8704,8 @@ int sched_cpu_deactivate(unsigned int cpu)
 	if (ret)
 		return ret;
 
+	set_cpu_preferred(cpu, false);
+
 	/*
 	 * Remove CPU from nohz.idle_cpus_mask to prevent participating in
 	 * load balancing when not active
@@ -11349,3 +11283,88 @@ void sched_change_end(struct sched_change_ctx *ctx)
 		p->sched_class->prio_changed(rq, p, ctx->prio);
 	}
 }
+
+#ifdef CONFIG_PREFERRED_CPU
+static DEFINE_PER_CPU(struct cpu_stop_work, npc_push_task_work);
+
+static int sched_non_preferred_cpu_push_stop(void *arg)
+{
+	struct task_struct *p = arg;
+	struct rq *rq = this_rq();
+	struct rq_flags rf;
+	int cpu;
+
+	if (cpu_preferred(rq->cpu)) {
+		scoped_guard(rq_lock_irqsave, rq)
+			rq->npc_push_work_pending = false;
+		put_task_struct(p);
+		return 0;
+	}
+
+	scoped_guard (raw_spinlock_irq, &p->pi_lock) {
+		/*
+		 * select_fallback_rq() may acquire the rq lock in case of
+		 * fallback. So call it before grabbing rq lock. If the task
+		 * migrates to another CPU before the rq lock is acquired,
+		 * subsequent validation of task's current rq will help to
+		 * safely bail out.
+		 */
+		cpu = select_fallback_rq(rq->cpu, p);
+		context_unsafe_alias(rq);
+		rq_lock(rq, &rf);
+		rq->npc_push_work_pending = false;
+		update_rq_clock(rq);
+
+		if (task_rq(p) == rq && task_on_rq_queued(p)) {
+			struct rq *dest_rq = __migrate_task(rq, &rf, p, cpu);
+
+			if (rq != dest_rq)
+				schedstat_inc(p->stats.nr_migrations_cpu_non_preferred);
+			rq = dest_rq;
+		}
+		rq_unlock(rq, &rf);
+	}
+
+	put_task_struct(p);
+	return 0;
+}
+
+/*
+ * Push the current task running on non-preferred CPU(npc).
+ * Using this non preferred CPU will lead to more contention
+ * in the host. So it is better not to use this CPU.
+ *
+ * Since task is running, call a stopper to push the task out. This is
+ * similar to how task moves during hotplug. In select_fallback_rq() a
+ * preferred CPU will be chosen and henceforth task shouldn't come back to
+ * this CPU again.
+ *
+ * Works for FAIR class only.
+ *
+ * If task is affined only on non-preferred CPUs, no point in moving it out.
+ */
+void sched_push_current_non_preferred_cpu(struct rq *rq)
+{
+	struct task_struct *push_task = rq->curr;
+
+	scoped_guard(rq_lock, rq) {
+		/* Push the task if its explicit affinity allows */
+		if (!task_can_migrate_to_preferred(push_task, rq->cpu))
+			return;
+
+		/* There is already a stopper thread. Don't race with it. */
+		if (rq->npc_push_work_pending)
+			return;
+
+		if (is_migration_disabled(push_task))
+			return;
+
+		rq->npc_push_work_pending = true;
+	}
+
+	/* sched_tick runs with interrupts disabled. */
+	get_task_struct(push_task);
+	stop_one_cpu_nowait(rq->cpu, sched_non_preferred_cpu_push_stop,
+			    push_task, this_cpu_ptr(&npc_push_task_work));
+}
+#endif
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 06bddaa738e5..f16970ca81d0 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -255,7 +255,7 @@ void __account_forceidle_time(struct task_struct *p, u64 delta)
  * occasion account more time than the calling functions think elapsed.
  */
 #ifdef CONFIG_PARAVIRT
-struct static_key paravirt_steal_enabled;
+DEFINE_STATIC_KEY_FALSE(paravirt_steal_enabled);
 
 #ifdef CONFIG_HAVE_PV_STEAL_CLOCK_GEN
 static u64 native_steal_clock(int cpu)
@@ -270,7 +270,7 @@ DEFINE_STATIC_CALL(pv_steal_clock, native_steal_clock);
 static __always_inline u64 steal_account_process_time(u64 maxtime)
 {
 #ifdef CONFIG_PARAVIRT
-	if (static_key_false(&paravirt_steal_enabled)) {
+	if (static_branch_unlikely(&paravirt_steal_enabled)) {
 		u64 steal;
 
 		steal = paravirt_steal_clock(smp_processor_id());
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 0663c00c41c0..c0ebdcde5fe5 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1097,7 +1097,7 @@ static int start_dl_timer(struct sched_dl_entity *dl_se)
 	 * chosen as the deadline is too small, don't even try to
 	 * start the timer in the past!
 	 */
-	if (ktime_us_delta(act, now) < 0)
+	if (ktime_before(act, now))
 		return 0;
 
 	/*
@@ -2773,11 +2773,14 @@ static void start_hrtick_dl(struct rq *rq, struct sched_dl_entity *dl_se)
  * DL keeps current in tree, because ->deadline is not typically changed while
  * a task is runnable.
  */
-static void set_next_task_dl(struct rq *rq, struct task_struct *p, bool first)
+static void set_next_task_dl(struct rq *rq, struct task_struct *p, enum snt_e type)
 {
 	struct sched_dl_entity *dl_se = &p->dl;
 	struct dl_rq *dl_rq = &rq->dl;
 
+	if (type == SNT_REPICK)
+		return;
+
 	p->se.exec_start = rq_clock_task(rq);
 	if (on_dl_rq(&p->dl))
 		update_stats_wait_end_dl(dl_rq, dl_se);
@@ -2788,7 +2791,7 @@ static void set_next_task_dl(struct rq *rq, struct task_struct *p, bool first)
 	WARN_ON_ONCE(dl_rq->curr);
 	dl_rq->curr = dl_se;
 
-	if (!first)
+	if (type != SNT_PICK)
 		return;
 
 	if (rq->donor->sched_class != &dl_sched_class)
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 72236db67983..e6a3b516c703 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -73,13 +73,13 @@ static int sched_feat_show(struct seq_file *m, void *v)
 
 #ifdef CONFIG_JUMP_LABEL
 
-#define jump_label_key__true  STATIC_KEY_INIT_TRUE
-#define jump_label_key__false STATIC_KEY_INIT_FALSE
+#define jump_label_key__true  { .key_true  = STATIC_KEY_TRUE_INIT  }
+#define jump_label_key__false { .key_false = STATIC_KEY_FALSE_INIT }
 
 #define SCHED_FEAT(name, enabled)	\
 	jump_label_key__##enabled ,
 
-struct static_key sched_feat_keys[__SCHED_FEAT_NR] = {
+union sched_feat_key sched_feat_keys[__SCHED_FEAT_NR] = {
 #include "features.h"
 };
 
@@ -87,12 +87,12 @@ struct static_key sched_feat_keys[__SCHED_FEAT_NR] = {
 
 static void sched_feat_disable(int i)
 {
-	static_key_disable_cpuslocked(&sched_feat_keys[i]);
+	static_branch_disable_cpuslocked(&sched_feat_keys[i].key_true);
 }
 
 static void sched_feat_enable(int i)
 {
-	static_key_enable_cpuslocked(&sched_feat_keys[i]);
+	static_branch_enable_cpuslocked(&sched_feat_keys[i].key_false);
 }
 #else /* !CONFIG_JUMP_LABEL: */
 static void sched_feat_disable(int i) { };
@@ -280,16 +280,10 @@ static ssize_t sched_dynamic_write(struct file *filp, const char __user *ubuf,
 
 static int sched_dynamic_show(struct seq_file *m, void *v)
 {
-	int i = (IS_ENABLED(CONFIG_PREEMPT_RT) || IS_ENABLED(CONFIG_ARCH_HAS_PREEMPT_LAZY)) * 2;
 	int mode = READ_ONCE(preempt_dynamic_mode);
-	int j;
 
-	/* Count entries in NULL terminated preempt_modes */
-	for (j = 0; preempt_modes[j]; j++)
-		;
-	j -= !IS_ENABLED(CONFIG_ARCH_HAS_PREEMPT_LAZY);
-
-	for (; i < j; i++) {
+	/* Stop at NULL terminator */
+	for (int i = 0; preempt_modes[i]; i++) {
 		if (mode == i)
 			seq_puts(m, "(");
 		seq_puts(m, preempt_modes[i]);
@@ -1446,6 +1440,7 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
 		P_SCHEDSTAT(nr_failed_migrations_running);
 		P_SCHEDSTAT(nr_failed_migrations_hot);
 		P_SCHEDSTAT(nr_forced_migrations);
+		P_SCHEDSTAT(nr_migrations_cpu_non_preferred);
 		P_SCHEDSTAT(nr_wakeups);
 		P_SCHEDSTAT(nr_wakeups_sync);
 		P_SCHEDSTAT(nr_wakeups_migrate);
diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c
index 5fe980da545d..522cf6e98e31 100644
--- a/kernel/sched/ext/ext.c
+++ b/kernel/sched/ext/ext.c
@@ -24,6 +24,11 @@
 
 DEFINE_RAW_SPINLOCK(scx_sched_lock);
 
+bool scx_allow_proxy_exec(const struct task_struct *p)
+{
+	return true;
+}
+
 /*
  * NOTE: sched_ext is in the process of growing multiple scheduler support and
  * scx_root usage is in a transitional state. Naked dereferences are safe if the
@@ -1087,6 +1092,10 @@ static void schedule_deferred_locked(struct rq *rq)
 	schedule_deferred(rq);
 }
 
+void scx_proxy_reenqueue_retry(struct rq *rq, struct task_struct *next)
+{
+}
+
 void schedule_dsq_reenq(struct scx_sched *sch, struct scx_dispatch_q *dsq,
 			u64 reenq_flags, struct rq *locked_rq)
 {
@@ -3031,10 +3040,13 @@ has_tasks:
 	return verdict;
 }
 
-static void set_next_task_scx(struct rq *rq, struct task_struct *p, bool first)
+static void set_next_task_scx(struct rq *rq, struct task_struct *p, enum snt_e type)
 {
 	struct scx_sched *sch = scx_task_sched(p);
 
+	if (type == SNT_REPICK)
+		return;
+
 	if (p->scx.flags & SCX_TASK_QUEUED) {
 		/*
 		 * Core-sched might decide to execute @p before it is
@@ -3092,6 +3104,10 @@ static void set_next_task_scx(struct rq *rq, struct task_struct *p, bool first)
 	}
 }
 
+void scx_proxy_donor_start(struct rq *rq)
+{
+}
+
 static enum scx_cpu_preempt_reason
 preempt_reason_from_class(const struct sched_class *class)
 {
diff --git a/kernel/sched/ext/ext.h b/kernel/sched/ext/ext.h
index 0b7fc46aee08..3cfbfeb1bf9d 100644
--- a/kernel/sched/ext/ext.h
+++ b/kernel/sched/ext/ext.h
@@ -20,6 +20,9 @@ void scx_rq_deactivate(struct rq *rq);
 int scx_check_setscheduler(struct task_struct *p, int policy);
 bool task_should_scx(int policy);
 bool scx_allow_ttwu_queue(const struct task_struct *p);
+bool scx_allow_proxy_exec(const struct task_struct *p);
+void scx_proxy_donor_start(struct rq *rq);
+void scx_proxy_reenqueue_retry(struct rq *rq, struct task_struct *next);
 void init_sched_ext_class(void);
 
 static inline u32 scx_cpuperf_target(s32 cpu)
@@ -54,6 +57,10 @@ static inline void scx_rq_deactivate(struct rq *rq) {}
 static inline int scx_check_setscheduler(struct task_struct *p, int policy) { return 0; }
 static inline bool task_on_scx(const struct task_struct *p) { return false; }
 static inline bool scx_allow_ttwu_queue(const struct task_struct *p) { return true; }
+static inline bool scx_allow_proxy_exec(const struct task_struct *p) { return true; }
+static inline void scx_proxy_donor_start(struct rq *rq) {}
+static inline void scx_proxy_reenqueue_retry(struct rq *rq,
+					     struct task_struct *next) {}
 static inline void init_sched_ext_class(void) {}
 
 #endif	/* CONFIG_SCHED_CLASS_EXT */
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 57360f5cdde4..5c98d8dfce5d 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -24,6 +24,7 @@
 #include <linux/mmap_lock.h>
 #include <linux/hugetlb_inline.h>
 #include <linux/jiffies.h>
+#include <linux/math.h>
 #include <linux/mm_api.h>
 #include <linux/highmem.h>
 #include <linux/hrtimer.h>
@@ -820,12 +821,6 @@ static u64 ineligible_vruntime(struct cfs_rq *cfs_rq)
 	if (curr && !curr->on_rq)
 		curr = NULL;
 
-	/*
-	 * This is called from set_next_task_fair(.first=true) /
-	 * set_protect_slice() so curr had better be set and on_rq.
-	 */
-	WARN_ON_ONCE(!curr);
-
 	if (weight) {
 		s64 runtime = cfs_rq->sum_w_vruntime;
 
@@ -1137,10 +1132,9 @@ static inline void set_protect_slice(struct cfs_rq *cfs_rq, struct sched_entity
 
 	/* If there are shorter slices than se's one */
 	if (slice != se->slice) {
+		vprot = min_vruntime(vprot, se->vruntime + calc_delta_fair(slice, se));
 		if (sched_feat(PREEMPT_SHORT))
 			vprot = min_vruntime(vprot, ineligible_vruntime(cfs_rq));
-		else
-			vprot = min_vruntime(vprot, se->vruntime + calc_delta_fair(slice, se));
 	}
 
 	se->vprot = vprot;
@@ -1148,10 +1142,19 @@ static inline void set_protect_slice(struct cfs_rq *cfs_rq, struct sched_entity
 
 static inline void update_protect_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	u64 slice = cfs_rq_min_slice(cfs_rq);
 	u64 vruntime = min_vruntime(se->vruntime, avg_vruntime(cfs_rq));
+	u64 slice = normalized_sysctl_sched_base_slice;
+	u64 vprot;
 
-	se->vprot = min_vruntime(se->vprot, vruntime + calc_delta_fair(slice, se));
+	if (sched_feat(RUN_TO_PARITY))
+		slice = cfs_rq_min_slice(cfs_rq);
+
+	vprot = min_vruntime(se->vprot, vruntime + calc_delta_fair(slice, se));
+
+	if (sched_feat(PREEMPT_SHORT) && slice != se->slice)
+		vprot = min_vruntime(vprot, ineligible_vruntime(cfs_rq));
+
+	se->vprot = vprot;
 }
 
 static inline bool protect_slice(struct sched_entity *se)
@@ -3713,7 +3716,7 @@ static void update_task_scan_period(struct task_struct *p,
 		p->mm->numa_next_scan = jiffies +
 			msecs_to_jiffies(p->numa_scan_period);
 
-		return;
+		goto out;
 	}
 
 	/*
@@ -3757,7 +3760,10 @@ static void update_task_scan_period(struct task_struct *p,
 
 	p->numa_scan_period = clamp(p->numa_scan_period + diff,
 			task_scan_min(p), task_scan_max(p));
-	memset(p->numa_faults_locality, 0, sizeof(p->numa_faults_locality));
+
+out:
+	memset(p->numa_faults_locality, 0,
+	       sizeof(p->numa_faults_locality));
 }
 
 /*
@@ -8209,7 +8215,6 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	struct sched_entity *se = &p->se;
 	struct cfs_rq *cfs_rq = &rq->cfs;
 	unsigned long weight;
-	bool curr;
 
 	if (task_is_throttled(p) && enqueue_throttled_task(p))
 		return;
@@ -8238,23 +8243,14 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	if (p->in_iowait)
 		cpufreq_update_util(rq, SCHED_CPUFREQ_IOWAIT);
 
-	/*
-	 * XXX comment on the curr thing
-	 */
-	curr = (cfs_rq->curr == se);
-	if (curr)
-		place_entity(cfs_rq, se, flags);
 
 	if (se->on_rq && se->sched_delayed)
 		requeue_delayed_entity(cfs_rq, se);
 
 	weight = enqueue_hierarchy(p, flags);
-
-	if (!curr) {
-		reweight_eevdf(cfs_rq, se, weight, false);
-		place_entity(cfs_rq, se, flags | ENQUEUE_QUEUED);
-		__enqueue_entity(cfs_rq, se);
-	}
+	reweight_eevdf(cfs_rq, se, weight, false);
+	place_entity(cfs_rq, se, flags | ENQUEUE_QUEUED);
+	__enqueue_entity(cfs_rq, se);
 
 	if (!rq_h_nr_queued && rq->cfs.h_nr_queued)
 		dl_server_start(&rq->fair_server);
@@ -8674,8 +8670,8 @@ static int
 sched_balance_find_dst_group_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
 {
 	unsigned long load, min_load = ULONG_MAX;
-	unsigned int min_exit_latency = UINT_MAX;
-	u64 latest_idle_timestamp = 0;
+	u64 min_exit_latency = U64_MAX;
+	unsigned int nr_candidates = 0;
 	int least_loaded_cpu = this_cpu;
 	int shallowest_idle_cpu = -1;
 	int i;
@@ -8696,24 +8692,16 @@ sched_balance_find_dst_group_cpu(struct sched_group *group, struct task_struct *
 
 		if (available_idle_cpu(i)) {
 			struct cpuidle_state *idle = idle_get_state(rq);
-			if (idle && idle->exit_latency < min_exit_latency) {
-				/*
-				 * We give priority to a CPU whose idle state
-				 * has the smallest exit latency irrespective
-				 * of any idle timestamp.
-				 */
-				min_exit_latency = idle->exit_latency;
-				latest_idle_timestamp = rq->idle_stamp;
-				shallowest_idle_cpu = i;
-			} else if ((!idle || idle->exit_latency == min_exit_latency) &&
-				   rq->idle_stamp > latest_idle_timestamp) {
-				/*
-				 * If equal or no active idle state, then
-				 * the most recently idled CPU might have
-				 * a warmer cache.
-				 */
-				latest_idle_timestamp = rq->idle_stamp;
+			u64 exit_latency = idle ? idle->exit_latency : U64_MAX;
+
+			if (shallowest_idle_cpu == -1 || exit_latency < min_exit_latency) {
+				min_exit_latency = exit_latency;
 				shallowest_idle_cpu = i;
+				nr_candidates = 1;
+			} else if (exit_latency == min_exit_latency) {
+				nr_candidates++;
+				if (!reciprocal_scale(sched_rng(), nr_candidates))
+					shallowest_idle_cpu = i;
 			}
 		} else if (shallowest_idle_cpu == -1) {
 			load = cpu_load(cpu_rq(i));
@@ -8812,6 +8800,35 @@ static inline bool test_idle_cores(int cpu)
 }
 
 /*
+ * Redirect a CPU to a higher-priority available sibling in its SMT domain,
+ * subject to task affinity.
+ */
+static inline int select_idle_smt_cpu(struct task_struct *p, int cpu)
+{
+	struct sched_domain *sd;
+	int best = cpu;
+	int sibling;
+
+	if (!sched_smt_active())
+		return cpu;
+
+	sd = rcu_dereference_all(cpu_rq(cpu)->sd);
+	if (!sd || !(sd->flags & SD_SHARE_CPUCAPACITY) ||
+	    !(sd->flags & SD_ASYM_PACKING))
+		return cpu;
+
+	for_each_cpu_and(sibling, sched_domain_span(sd), p->cpus_ptr) {
+		if (sibling == best || !choose_idle_cpu(sibling, p))
+			continue;
+
+		if (sched_asym_prefer(sibling, best))
+			best = sibling;
+	}
+
+	return best;
+}
+
+/*
  * Scans the local SMT mask to see if the entire core is idle, and records this
  * information in sd_balance_shared->has_idle_cores.
  *
@@ -9195,7 +9212,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 
 	if (choose_idle_cpu(target, p) &&
 	    asym_fits_cpu(task_util, util_min, util_max, target))
-		return target;
+		goto select_smt_priority;
 
 	/*
 	 * If the previous CPU is cache affine and idle, don't be stupid:
@@ -9205,8 +9222,10 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	    asym_fits_cpu(task_util, util_min, util_max, prev)) {
 
 		if (!static_branch_unlikely(&sched_cluster_active) ||
-		    cpus_share_resources(prev, target))
-			return prev;
+		    cpus_share_resources(prev, target)) {
+			target = prev;
+			goto select_smt_priority;
+		}
 
 		prev_aff = prev;
 	}
@@ -9224,7 +9243,8 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	    prev == smp_processor_id() &&
 	    this_rq()->nr_running <= 1 &&
 	    asym_fits_cpu(task_util, util_min, util_max, prev)) {
-		return prev;
+		target = prev;
+		goto select_smt_priority;
 	}
 
 	/* Check a recently used CPU as a potential idle candidate: */
@@ -9238,8 +9258,10 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	    asym_fits_cpu(task_util, util_min, util_max, recent_used_cpu)) {
 
 		if (!static_branch_unlikely(&sched_cluster_active) ||
-		    cpus_share_resources(recent_used_cpu, target))
-			return recent_used_cpu;
+		    cpus_share_resources(recent_used_cpu, target)) {
+			target = recent_used_cpu;
+			goto select_smt_priority;
+		}
 
 	} else {
 		recent_used_cpu = -1;
@@ -9261,7 +9283,11 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 		 */
 		if (sd) {
 			i = select_idle_capacity(p, sd, target);
-			return ((unsigned)i < nr_cpumask_bits) ? i : target;
+			if ((unsigned int)i < nr_cpumask_bits) {
+				target = i;
+				goto select_smt_priority;
+			}
+			return target;
 		}
 	}
 
@@ -9274,14 +9300,18 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 
 		if (!has_idle_core && cpus_share_cache(prev, target)) {
 			i = select_idle_smt(p, sd, prev);
-			if ((unsigned int)i < nr_cpumask_bits)
-				return i;
+			if ((unsigned int)i < nr_cpumask_bits) {
+				target = i;
+				goto select_smt_priority;
+			}
 		}
 	}
 
 	i = select_idle_cpu(p, sd, has_idle_core, target);
-	if ((unsigned)i < nr_cpumask_bits)
-		return i;
+	if ((unsigned int)i < nr_cpumask_bits) {
+		target = i;
+		goto select_smt_priority;
+	}
 
 	/*
 	 * For cluster machines which have lower sharing cache like L2 or
@@ -9289,12 +9319,19 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	 * first. But prev_cpu or recent_used_cpu may also be a good candidate,
 	 * use them if possible when no idle CPU found in select_idle_cpu().
 	 */
-	if ((unsigned int)prev_aff < nr_cpumask_bits)
-		return prev_aff;
-	if ((unsigned int)recent_used_cpu < nr_cpumask_bits)
-		return recent_used_cpu;
+	if ((unsigned int)prev_aff < nr_cpumask_bits) {
+		target = prev_aff;
+		goto select_smt_priority;
+	}
+	if ((unsigned int)recent_used_cpu < nr_cpumask_bits) {
+		target = recent_used_cpu;
+		goto select_smt_priority;
+	}
 
 	return target;
+
+select_smt_priority:
+	return select_idle_smt_cpu(p, target);
 }
 
 /**
@@ -9971,8 +10008,10 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int wake_flags)
 	}
 
 	/* Slow path */
-	if (unlikely(sd))
-		return sched_balance_find_dst_cpu(sd, p, cpu, prev_cpu, sd_flag);
+	if (unlikely(sd)) {
+		new_cpu = sched_balance_find_dst_cpu(sd, p, cpu, prev_cpu, sd_flag);
+		return select_idle_smt_cpu(p, new_cpu);
+	}
 
 	/* Fast path */
 	if (wake_flags & WF_TTWU)
@@ -10072,8 +10111,14 @@ static inline bool set_preempt_buddy(struct cfs_rq *cfs_rq, struct sched_entity
 
 static inline bool set_short_buddy(struct cfs_rq *cfs_rq, struct sched_entity *pse)
 {
-	if (cfs_rq->next && cfs_rq->next->slice < pse->slice)
-		return false;
+	if (cfs_rq->next) {
+		if (cfs_rq->next->slice < pse->slice)
+			return false;
+
+		if (cfs_rq->next->slice == pse->slice &&
+		    entity_before(cfs_rq->next, pse))
+			return false;
+	}
 
 	set_next_buddy(cfs_rq, pse);
 	return true;
@@ -11439,21 +11484,7 @@ next:
  */
 static void attach_tasks(struct lb_env *env)
 {
-	struct list_head *tasks = &env->tasks;
-	struct task_struct *p;
-	struct rq_flags rf;
-
-	rq_lock(env->dst_rq, &rf);
-	update_rq_clock(env->dst_rq);
-
-	while (!list_empty(tasks)) {
-		p = list_first_entry(tasks, struct task_struct, se.group_node);
-		list_del_init(&p->se.group_node);
-
-		attach_task(env->dst_rq, p);
-	}
-
-	rq_unlock(env->dst_rq, &rf);
+	__attach_tasks(env->dst_rq, &env->tasks);
 }
 
 #ifdef CONFIG_NO_HZ_COMMON
@@ -13746,7 +13777,7 @@ static int sched_balance_rq(int this_cpu, struct rq *this_rq,
 	};
 	bool need_unlock = false;
 
-	cpumask_and(cpus, sched_domain_span(sd), cpu_active_mask);
+	cpumask_and(cpus, sched_domain_span(sd), cpu_preferred_mask);
 
 	schedstat_inc(sd->lb_count[idle]);
 
@@ -14871,10 +14902,8 @@ static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf)
 	 */
 	this_rq->idle_stamp = rq_clock(this_rq);
 
-	/*
-	 * Do not pull tasks towards !active CPUs...
-	 */
-	if (!cpu_active(this_cpu))
+	/* Do not pull tasks towards !preferred CPUs */
+	if (!cpu_preferred(this_cpu))
 		return 0;
 
 	/*
@@ -15514,14 +15543,18 @@ static void switched_to_fair(struct rq *rq, struct task_struct *p)
 	}
 }
 
-static void set_next_task_fair(struct rq *rq, struct task_struct *p, bool first)
+static void set_next_task_fair(struct rq *rq, struct task_struct *p, enum snt_e type)
 {
 	struct sched_entity *se = &p->se;
-	bool throttled = false;
 	struct cfs_rq *cfs_rq = &rq->cfs;
 	unsigned long weight = NICE_0_LOAD;
+	bool first = type == SNT_PICK;
+	bool throttled = false;
 	bool on_rq = se->on_rq;
 
+	if (type == SNT_REPICK)
+		goto repick;
+
 	clear_buddies(cfs_rq, se);
 
 	if (on_rq)
@@ -15565,11 +15598,18 @@ static void set_next_task_fair(struct rq *rq, struct task_struct *p, bool first)
 
 	WARN_ON_ONCE(se->sched_delayed);
 
-	if (hrtick_enabled_fair(rq))
-		hrtick_start_fair(rq, p);
-
 	update_misfit_status(p, rq);
 	sched_fair_update_stop_tick(rq, p);
+
+repick:
+	/*
+	 * A same-task repick skips put_prev_task_fair(), but
+	 * pick_task_fair() refreshed the entity hrtick_start_fair() reads
+	 * before selecting it again. rq->cfs.curr identifies that entity,
+	 * including with group scheduling.
+	 */
+	if (hrtick_enabled_fair(rq))
+		hrtick_start_fair(rq, p);
 }
 
 void init_cfs_rq(struct cfs_rq *cfs_rq)
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index eb73b65ce6c4..76f3c84ca684 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -487,8 +487,11 @@ static void put_prev_task_idle(struct rq *rq, struct task_struct *prev, struct t
 	update_rq_avg_idle(rq);
 }
 
-static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool first)
+static void set_next_task_idle(struct rq *rq, struct task_struct *next, enum snt_e type)
 {
+	if (type == SNT_REPICK)
+		return;
+
 	update_idle_core(rq);
 	scx_update_idle(rq, true, true);
 	schedstat_inc(rq->sched_goidle);
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 85303add726d..1535046a23ff 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1654,11 +1654,14 @@ static void wakeup_preempt_rt(struct rq *rq, struct task_struct *p, int flags)
 		check_preempt_equal_prio(rq, p);
 }
 
-static inline void set_next_task_rt(struct rq *rq, struct task_struct *p, bool first)
+static inline void set_next_task_rt(struct rq *rq, struct task_struct *p, enum snt_e type)
 {
 	struct sched_rt_entity *rt_se = &p->rt;
 	struct rt_rq *rt_rq = &rq->rt;
 
+	if (type == SNT_REPICK)
+		return;
+
 	p->se.exec_start = rq_clock_task(rq);
 	if (on_rt_rq(&p->rt))
 		update_stats_wait_end_rt(rt_rq, rt_se);
@@ -1666,7 +1669,7 @@ static inline void set_next_task_rt(struct rq *rq, struct task_struct *p, bool f
 	/* The running task is never eligible for pushing */
 	dequeue_pushable_task(rq, p);
 
-	if (!first)
+	if (type != SNT_PICK)
 		return;
 
 	/*
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 4c25fbe84fb5..499a5649582e 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1325,6 +1325,9 @@ struct rq {
 #ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
 	u64			prev_steal_time_rq;
 #endif
+#ifdef CONFIG_PREFERRED_CPU
+	bool			npc_push_work_pending;
+#endif
 
 	/* calc_load related fields */
 	unsigned long		calc_load_update;
@@ -1370,7 +1373,6 @@ struct rq {
 	struct task_struct	*core_pick;
 	struct sched_dl_entity	*core_dl_server;
 	unsigned int		core_enabled;
-	unsigned int		core_sched_seq;
 	struct rb_root		core_tree;
 
 	/* shared state -- careful with sched_core_cpu_deactivate() */
@@ -2446,16 +2448,25 @@ extern __read_mostly unsigned int sysctl_sched_features;
 
 #ifdef CONFIG_JUMP_LABEL
 
-#define SCHED_FEAT(name, enabled)					\
-static __always_inline bool static_branch_##name(struct static_key *key) \
-{									\
-	return static_key_##enabled(key);				\
+union sched_feat_key {
+	struct static_key_true	key_true;
+	struct static_key_false	key_false;
+};
+
+#define sched_feat_branch_true(key)	static_branch_likely(&(key)->key_true)
+#define sched_feat_branch_false(key)	static_branch_unlikely(&(key)->key_false)
+
+#define SCHED_FEAT(name, enabled)			\
+static __always_inline bool				\
+static_branch_##name(union sched_feat_key *key) 	\
+{							\
+	return sched_feat_branch_##enabled(key);	\
 }
 
 #include "features.h"
 #undef SCHED_FEAT
 
-extern struct static_key sched_feat_keys[__SCHED_FEAT_NR];
+extern union sched_feat_key sched_feat_keys[__SCHED_FEAT_NR];
 #define sched_feat(x) (static_branch_##x(&sched_feat_keys[__SCHED_FEAT_##x]))
 
 #else /* !CONFIG_JUMP_LABEL: */
@@ -2507,6 +2518,12 @@ static inline bool task_is_blocked(struct task_struct *p)
 	return !!p->blocked_on;
 }
 
+#ifdef CONFIG_SCHED_PROXY_EXEC
+void sched_proxy_block_task(struct rq *rq, struct task_struct *p);
+#else
+static inline void sched_proxy_block_task(struct rq *rq, struct task_struct *p) {}
+#endif
+
 static inline int task_on_cpu(struct rq *rq, struct task_struct *p)
 {
 	return p->on_cpu;
@@ -2526,11 +2543,17 @@ static inline int task_on_rq_migrating(struct task_struct *p)
 #define WF_EXEC			0x02 /* Wakeup after exec; maps to SD_BALANCE_EXEC */
 #define WF_FORK			0x04 /* Wakeup after fork; maps to SD_BALANCE_FORK */
 #define WF_TTWU			0x08 /* Wakeup;            maps to SD_BALANCE_WAKE */
-
-#define WF_SYNC			0x10 /* Waker goes to sleep after wakeup */
+/*
+ * Hint that the caller expects the waker to sleep soon.
+ * Scheduler classes may use it for placement or preemption.
+ * Callers must not rely on it to prevent migration,
+ * preserve CPU locality or make the wakee run next.
+ */
+#define WF_SYNC			0x10
 #define WF_MIGRATED		0x20 /* Internal use, task got migrated */
 #define WF_CURRENT_CPU		0x40 /* Prefer to move the wakee to the current CPU. */
 #define WF_RQ_SELECTED		0x80 /* ->select_task_rq() was called */
+#define WF_TTWU_RQ		0x100 /* Wakeup completed through ttwu_runnable() */
 
 static_assert(WF_EXEC == SD_BALANCE_EXEC);
 static_assert(WF_FORK == SD_BALANCE_FORK);
@@ -2620,6 +2643,12 @@ struct affinity_context {
 
 extern s64 update_curr_common(struct rq *rq);
 
+enum snt_e {
+	SNT_NORMAL,	/* set_next_task() */
+	SNT_PICK,	/* put_prev_set_next_task(): prev != next */
+	SNT_REPICK,	/* put_prev_set_next_task(): prev == next */
+};
+
 struct sched_class {
 
 #ifdef CONFIG_UCLAMP_TASK
@@ -2677,7 +2706,7 @@ struct sched_class {
 	 * __schedule: rq->lock
 	 */
 	void (*put_prev_task)(struct rq *rq, struct task_struct *p, struct task_struct *next);
-	void (*set_next_task)(struct rq *rq, struct task_struct *p, bool first);
+	void (*set_next_task)(struct rq *rq, struct task_struct *p, enum snt_e type);
 
 	/*
 	 * select_task_rq: p->pi_lock
@@ -2780,7 +2809,7 @@ static inline void put_prev_task(struct rq *rq, struct task_struct *prev)
 
 static inline void set_next_task(struct rq *rq, struct task_struct *next)
 {
-	next->sched_class->set_next_task(rq, next, false);
+	next->sched_class->set_next_task(rq, next, SNT_NORMAL);
 }
 
 static inline void
@@ -2801,11 +2830,13 @@ static inline void put_prev_set_next_task(struct rq *rq,
 
 	__put_prev_set_next_dl_server(rq, prev, next);
 
-	if (next == prev)
+	if (next == prev) {
+		next->sched_class->set_next_task(rq, next, SNT_REPICK);
 		return;
+	}
 
 	prev->sched_class->put_prev_task(rq, prev, next);
-	next->sched_class->set_next_task(rq, next, true);
+	next->sched_class->set_next_task(rq, next, SNT_PICK);
 }
 
 /*
@@ -3138,6 +3169,25 @@ static inline void attach_one_task(struct rq *rq, struct task_struct *p)
 	attach_task(rq, p);
 }
 
+/*
+ * __attach_tasks() - attaches a list of tasks (using se.group_node) to
+ * the new rq
+ */
+static inline void __attach_tasks(struct rq *rq, struct list_head *tasks)
+{
+	guard(rq_lock)(rq);
+	update_rq_clock(rq);
+
+	while (!list_empty(tasks)) {
+		struct task_struct *p;
+
+		p = list_first_entry(tasks, struct task_struct, se.group_node);
+		list_del_init(&p->se.group_node);
+
+		attach_task(rq, p);
+	}
+}
+
 #ifdef CONFIG_PREEMPT_RT
 # define SCHED_NR_MIGRATE_BREAK 8
 #else
@@ -4252,4 +4302,10 @@ DEFINE_CLASS_IS_UNCONDITIONAL(sched_change)
 
 #include "ext/ext.h"
 
+#ifdef CONFIG_PREFERRED_CPU
+void sched_push_current_non_preferred_cpu(struct rq *rq);
+#else	/* !CONFIG_PREFERRED_CPU */
+static inline void sched_push_current_non_preferred_cpu(struct rq *rq) { }
+#endif
+
 #endif /* _KERNEL_SCHED_SCHED_H */
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index c909ca0d8c87..1e0109ec36b3 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -27,8 +27,11 @@ wakeup_preempt_stop(struct rq *rq, struct task_struct *p, int flags)
 	/* we're never preempted */
 }
 
-static void set_next_task_stop(struct rq *rq, struct task_struct *stop, bool first)
+static void set_next_task_stop(struct rq *rq, struct task_struct *stop, enum snt_e type)
 {
+	if (type == SNT_REPICK)
+		return;
+
 	stop->se.exec_start = rq_clock_task(rq);
 }
 
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 3dab0253976f..919d0fb00bd9 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -32,6 +32,20 @@ static int __init sched_debug_setup(char *str)
 }
 early_param("sched_verbose", sched_debug_setup);
 
+#ifdef CONFIG_SCHED_SMT
+static bool sched_smt_asym_packing __read_mostly;
+
+static int __init setup_sched_smt_asym_packing(char *str)
+{
+	if (strcmp(str, "on"))
+		return 0;
+
+	sched_smt_asym_packing = true;
+	return 1;
+}
+__setup("sched_smt_asym_packing=", setup_sched_smt_asym_packing);
+#endif
+
 static inline bool sched_debug(void)
 {
 	return sched_debug_verbose;
@@ -1954,6 +1968,10 @@ sd_init(struct sched_domain_topology_level *tl,
 	if (WARN_ONCE(sd_flags & ~TOPOLOGY_SD_FLAGS,
 		      "wrong sd_flags in topology description\n"))
 		sd_flags &= TOPOLOGY_SD_FLAGS;
+#ifdef CONFIG_SCHED_SMT
+	if (sched_smt_asym_packing && (sd_flags & SD_SHARE_CPUCAPACITY))
+		sd_flags |= SD_ASYM_PACKING;
+#endif
 	sd_flags |= asym_cpu_capacity_classify(sd_span, cpu_map);
 
 	*sd = (struct sched_domain){
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index d033f600f48c..477e4bf9c01e 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -174,15 +174,11 @@ EXPORT_SYMBOL_GPL(__wake_up_locked_key);
  * @mode: which threads
  * @key: opaque value to be passed to wakeup targets
  *
- * The sync wakeup differs that the waker knows that it will schedule
- * away soon, so while the target thread will be woken up, it will not
- * be migrated to another CPU - ie. the two threads are 'synchronized'
- * with each other. This can prevent needless bouncing between CPUs.
+ * Passes WF_SYNC to waitqueue wake functions. The default wake function
+ * forwards it to the scheduler; see WF_SYNC for the hint's semantics.
  *
- * On UP it can prevent extra preemption.
- *
- * If this function wakes up a task, it executes a full memory barrier before
- * accessing the task state.
+ * If this function wakes up a task, it executes a full memory barrier
+ * before accessing the task state.
  */
 void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode,
 			void *key)
@@ -200,15 +196,7 @@ EXPORT_SYMBOL_GPL(__wake_up_sync_key);
  * @mode: which threads
  * @key: opaque value to be passed to wakeup targets
  *
- * The sync wakeup differs in that the waker knows that it will schedule
- * away soon, so while the target thread will be woken up, it will not
- * be migrated to another CPU - ie. the two threads are 'synchronized'
- * with each other. This can prevent needless bouncing between CPUs.
- *
- * On UP it can prevent extra preemption.
- *
- * If this function wakes up a task, it executes a full memory barrier before
- * accessing the task state.
+ * Same as __wake_up_sync_key(), but called with @wq_head->lock held.
  */
 void __wake_up_locked_sync_key(struct wait_queue_head *wq_head,
 			       unsigned int mode, void *key)
diff --git a/kernel/smp.c b/kernel/smp.c
index b696bcc60c08..8f530a094c30 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -87,6 +87,7 @@ int smpcfd_dead_cpu(unsigned int cpu)
 
 	free_cpumask_var(cfd->cpumask);
 	free_cpumask_var(cfd->cpumask_ipi);
+	irq_work_run_cpu(cpu);
 	return 0;
 }
 
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
index 4503b60ce9bd..3f60e8c6dd30 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -103,6 +103,7 @@ static int smpboot_thread_fn(void *data)
 {
 	struct smpboot_thread_data *td = data;
 	struct smp_hotplug_thread *ht = td->ht;
+	bool should_run;
 
 	while (1) {
 		set_current_state(TASK_INTERRUPTIBLE);
@@ -117,7 +118,8 @@ static int smpboot_thread_fn(void *data)
 			return 0;
 		}
 
-		if (kthread_should_park()) {
+		should_run = td->status == HP_THREAD_ACTIVE && ht->thread_should_run(td->cpu);
+		if (kthread_should_park() && !should_run) {
 			__set_current_state(TASK_RUNNING);
 			preempt_enable();
 			if (ht->park && td->status == HP_THREAD_ACTIVE) {
@@ -151,7 +153,7 @@ static int smpboot_thread_fn(void *data)
 			continue;
 		}
 
-		if (!ht->thread_should_run(td->cpu)) {
+		if (!should_run) {
 			preempt_enable_no_resched();
 			schedule();
 		} else {
diff --git a/lib/bitmap.c b/lib/bitmap.c
index ed685127a107..d1cb8a507c60 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -308,6 +308,23 @@ bool __bitmap_intersects(const unsigned long *bitmap1,
 }
 EXPORT_SYMBOL(__bitmap_intersects);
 
+bool __bitmap_intersects_and(const unsigned long *bitmap1,
+			     const unsigned long *bitmap2,
+			     const unsigned long *bitmap3, unsigned int bits)
+{
+	unsigned int k, lim = bits / BITS_PER_LONG;
+
+	for (k = 0; k < lim; ++k)
+		if (bitmap1[k] & bitmap2[k] & bitmap3[k])
+			return true;
+
+	if (bits % BITS_PER_LONG)
+		if ((bitmap1[k] & bitmap2[k] & bitmap3[k]) & BITMAP_LAST_WORD_MASK(bits))
+			return true;
+	return false;
+}
+EXPORT_SYMBOL(__bitmap_intersects_and);
+
 bool __bitmap_subset(const unsigned long *bitmap1,
 		     const unsigned long *bitmap2, unsigned int bits)
 {
diff --git a/tools/perf/trace/beauty/include/uapi/linux/sched.h b/tools/perf/trace/beauty/include/uapi/linux/sched.h
index 33a4624285cd..19ffeba89428 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/sched.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/sched.h
@@ -53,7 +53,7 @@
  */
 #define UNSHARE_EMPTY_MNTNS 0x00100000 /* Unshare an empty mount namespace. */
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 /**
  * struct clone_args - arguments for the clone3 syscall
  * @flags:        Flags for the new process as listed above.