Merge branch 'for-next' of https://git.kernel.org/pub/scm/linux/kernel/git/s390/linux.git

18 files changed, 204 insertions, 24 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index 9cc50449ecc2..1113199518b6 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6854,6 +6854,13 @@ L:	linux-riscv@lists.infradead.org
 S:	Maintained
 F:	drivers/cpuidle/cpuidle-riscv-sbi.c
 
+CPUIDLE DRIVER - S390
+M:	Mete Durlu <meted@linux.ibm.com>
+L:	linux-pm@vger.kernel.org
+L:	linux-s390@vger.kernel.org
+S:	Maintained
+F:	drivers/cpuidle/cpuidle-s390.c
+
 CPUMASK API [RUST]
 M:	Viresh Kumar <viresh.kumar@linaro.org>
 R:	Yury Norov <yury.norov@gmail.com>
@@ -23810,6 +23817,7 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux.git
 F:	Documentation/driver-api/s390-drivers.rst
 F:	Documentation/arch/s390/
 F:	arch/s390/
+F:	drivers/cpuidle/cpuidle-s390.c
 F:	drivers/s390/
 F:	drivers/watchdog/diag288_wdt.c
 
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index ab8fccc2cc4e..1911144e9128 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -20,6 +20,9 @@ config ARCH_HAS_ILOG2_U64
 config ARCH_PROC_KCORE_TEXT
 	def_bool y
 
+config ARCH_HAS_CPU_RELAX
+	def_bool y
+
 config GENERIC_HWEIGHT
 	def_bool !HAVE_MARCH_Z196_FEATURES
 
@@ -706,6 +709,8 @@ config KERNEL_IMAGE_BASE
 
 endmenu
 
+source "drivers/cpuidle/Kconfig"
+
 menu "Memory setup"
 
 config ARCH_SPARSEMEM_ENABLE
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index 54637be87fb7..007668f95028 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -29,6 +29,8 @@ CONFIG_CGROUP_PIDS=y
 CONFIG_CGROUP_RDMA=y
 CONFIG_CGROUP_FREEZER=y
 CONFIG_CGROUP_HUGETLB=y
+CONFIG_CPU_IDLE=y
+CONFIG_CPU_IDLE_GOV_TEO=y
 CONFIG_CPUSETS=y
 CONFIG_CGROUP_DEVICE=y
 CONFIG_CGROUP_CPUACCT=y
diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig
index 5f5114a253cf..6f5722634b4d 100644
--- a/arch/s390/configs/defconfig
+++ b/arch/s390/configs/defconfig
@@ -27,6 +27,8 @@ CONFIG_CGROUP_PIDS=y
 CONFIG_CGROUP_RDMA=y
 CONFIG_CGROUP_FREEZER=y
 CONFIG_CGROUP_HUGETLB=y
+CONFIG_CPU_IDLE=y
+CONFIG_CPU_IDLE_GOV_TEO=y
 CONFIG_CPUSETS=y
 CONFIG_CGROUP_DEVICE=y
 CONFIG_CGROUP_CPUACCT=y
diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h
index 02821a7d9d91..aea754b67c89 100644
--- a/arch/s390/include/asm/hugetlb.h
+++ b/arch/s390/include/asm/hugetlb.h
@@ -42,9 +42,9 @@ static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 				  pte_t *ptep, unsigned long sz)
 {
 	if ((pte_val(ptep_get(ptep)) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R3)
-		set_pte(ptep, __pte(_REGION3_ENTRY_EMPTY));
+		set_pud((pud_t *)ptep, __pud(_REGION3_ENTRY_EMPTY));
 	else
-		set_pte(ptep, __pte(_SEGMENT_ENTRY_EMPTY));
+		set_pmd((pmd_t *)ptep, __pmd(_SEGMENT_ENTRY_EMPTY));
 }
 
 #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index ecd3341686eb..be8369115f6d 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -14,12 +14,10 @@
 
 #include <linux/bits.h>
 
-#define CIF_NOHZ_DELAY		2	/* delay HZ disable for a tick */
 #define CIF_ENABLED_WAIT	5	/* in enabled wait state */
 #define CIF_MCCK_GUEST		6	/* machine check happening in guest */
 #define CIF_DEDICATED_CPU	7	/* this CPU is dedicated */
 
-#define _CIF_NOHZ_DELAY		BIT(CIF_NOHZ_DELAY)
 #define _CIF_ENABLED_WAIT	BIT(CIF_ENABLED_WAIT)
 #define _CIF_MCCK_GUEST		BIT(CIF_MCCK_GUEST)
 #define _CIF_DEDICATED_CPU	BIT(CIF_DEDICATED_CPU)
@@ -97,8 +95,6 @@ static __always_inline bool test_cpu_flag_of(int flag, int cpu)
 	return test_bit(flag, &per_cpu(pcpu_devices, cpu).flags);
 }
 
-#define arch_needs_cpu() test_cpu_flag(CIF_NOHZ_DELAY)
-
 static inline void get_cpu_id(struct cpuid *ptr)
 {
 	asm volatile("stidp %0" : "=Q" (*ptr));
diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h
index 6a548a819400..2554cef3a6a5 100644
--- a/arch/s390/include/asm/thread_info.h
+++ b/arch/s390/include/asm/thread_info.h
@@ -61,6 +61,7 @@ void arch_setup_new_exec(void);
  */
 #define HAVE_TIF_NEED_RESCHED_LAZY
 #define HAVE_TIF_RESTORE_SIGMASK
+#define HAVE_TIF_POLLING_NRFLAG
 
 #include <asm-generic/thread_info_tif.h>
 
diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c
index 08f3520c6785..dd12efb58201 100644
--- a/arch/s390/kernel/idle.c
+++ b/arch/s390/kernel/idle.c
@@ -136,7 +136,6 @@ void noinstr arch_cpu_idle(void)
 	/* Wait for external, I/O or machine check interrupt. */
 	psw_mask = PSW_KERNEL_BITS | PSW_MASK_WAIT |
 		   PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK;
-	clear_cpu_flag(CIF_NOHZ_DELAY);
 	set_cpu_flag(CIF_ENABLED_WAIT);
 	if (smp_cpu_mtid)
 		stcctm(MT_DIAG, smp_cpu_mtid, (u64 *)&idle->mt_cycles_enter);
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index 04d528639b94..c923496aa7b4 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -166,7 +166,6 @@ void noinstr do_io_irq(struct pt_regs *regs)
 	if (from_idle)
 		account_idle_time_irq();
 
-	set_cpu_flag(CIF_NOHZ_DELAY);
 	do {
 		regs->tpi_info = get_lowcore()->tpi_info;
 		if (get_lowcore()->tpi_info.adapter_IO)
@@ -369,9 +368,6 @@ static irqreturn_t do_ext_interrupt(int irq, void *dummy)
 	int index;
 
 	ext_code.int_code = regs->int_code;
-	if (ext_code.code != EXT_IRQ_CLK_COMP)
-		set_cpu_flag(CIF_NOHZ_DELAY);
-
 	index = ext_hash(ext_code.code);
 	rcu_read_lock();
 	hlist_for_each_entry_rcu(p, &ext_int_hash[index], entry) {
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 0ba7f89b8161..4cc2c119318d 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -909,7 +909,6 @@ int __cpu_disable(void)
 	cregs[6].val  &= ~0xff000000UL;	/* disable all I/O interrupts */
 	cregs[14].val &= ~0x1f000000UL;	/* disable most machine checks */
 	__local_ctl_load(0, 15, cregs);
-	clear_cpu_flag(CIF_NOHZ_DELAY);
 	return 0;
 }
 
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index 564403496a7c..fcd8c1122ef5 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -9,7 +9,9 @@
  *    Copyright (C) 1991, 1992 Linus Torvalds
  */
 
+#include <linux/capability.h>
 #include <linux/cpufeature.h>
+#include <linux/debugfs.h>
 #include <linux/kprobes.h>
 #include <linux/kdebug.h>
 #include <linux/randomize_kstack.h>
@@ -33,6 +35,12 @@
 #include <asm/fault.h>
 #include "entry.h"
 
+struct pgm_stat {
+	unsigned int count[128];
+};
+
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct pgm_stat, pgm_stat);
+
 static inline void __user *get_trap_ip(struct pt_regs *regs)
 {
 	unsigned long address;
@@ -332,6 +340,7 @@ void noinstr __do_pgm_check(struct pt_regs *regs)
 	struct lowcore *lc = get_lowcore();
 	bool percpu_needs_fixup;
 	irqentry_state_t state;
+	struct pgm_stat *stat;
 	unsigned int trapnr;
 	union teid teid;
 
@@ -339,6 +348,10 @@ void noinstr __do_pgm_check(struct pt_regs *regs)
 	regs->int_code = lc->pgm_int_code;
 	regs->int_parm_long = teid.val;
 	regs->monitor_code = lc->monitor_code;
+
+	trapnr = regs->int_code & PGM_INT_CODE_MASK;
+	stat = this_cpu_ptr(&pgm_stat);
+	stat->count[trapnr]++;
 	/*
 	 * In case of a guest fault, short-circuit the fault handler and return.
 	 * This way the sie64a() function will return 0; fault address and
@@ -383,7 +396,6 @@ void noinstr __do_pgm_check(struct pt_regs *regs)
 	if (!irqs_disabled_flags(regs->psw.mask))
 		trace_hardirqs_on();
 	__arch_local_irq_ssm(regs->psw.mask & ~PSW_MASK_PER);
-	trapnr = regs->int_code & PGM_INT_CODE_MASK;
 	if (trapnr)
 		pgm_check_table[trapnr](regs);
 out:
@@ -393,6 +405,33 @@ out:
 	percpu_exit(regs, percpu_needs_fixup);
 }
 
+static int pgm_check_stat_show(struct seq_file *p, void *v)
+{
+	int i, cpu;
+
+	cpus_read_lock();
+	seq_puts(p, "          ");
+	for_each_online_cpu(cpu)
+		seq_printf(p, "CPU%-8d", cpu);
+	seq_putc(p, '\n');
+	for (i = 0; i < 128; i++) {
+		seq_printf(p, "%02x: ", i);
+		for_each_online_cpu(cpu)
+			seq_printf(p, "%10u ", per_cpu(pgm_stat, cpu).count[i]);
+		seq_putc(p, '\n');
+	}
+	cpus_read_unlock();
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(pgm_check_stat);
+
+static int __init debugfs_pgm_check_init(void)
+{
+	debugfs_create_file("exceptions", 0400, arch_debugfs_dir, NULL, &pgm_check_stat_fops);
+	return 0;
+}
+late_initcall(debugfs_pgm_check_init);
+
 /*
  * The program check table contains exactly 128 (0x00-0x7f) entries. Each
  * line defines the function to be called corresponding to the program check
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index db35d8fe8609..f84aa9265430 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -147,10 +147,12 @@ void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		if (likely(pte_present(pte)))
 			rste |= _REGION3_ENTRY_LARGE;
 		rste |= _REGION_ENTRY_TYPE_R3;
-	} else if (likely(pte_present(pte)))
-		rste |= _SEGMENT_ENTRY_LARGE;
-
-	set_pte(ptep, __pte(rste));
+		set_pud((pud_t *)ptep, __pud(rste));
+	} else {
+		if (likely(pte_present(pte)))
+			rste |= _SEGMENT_ENTRY_LARGE;
+		set_pmd((pmd_t *)ptep, __pmd(rste));
+	}
 }
 
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
diff --git a/drivers/cpuidle/Kconfig b/drivers/cpuidle/Kconfig
index d6d8386d3f02..00e2562041fd 100644
--- a/drivers/cpuidle/Kconfig
+++ b/drivers/cpuidle/Kconfig
@@ -71,6 +71,11 @@ depends on RISCV
 source "drivers/cpuidle/Kconfig.riscv"
 endmenu
 
+menu "S390 CPU Idle Drivers"
+depends on S390
+source "drivers/cpuidle/Kconfig.s390"
+endmenu
+
 config HALTPOLL_CPUIDLE
 	tristate "Halt poll cpuidle driver"
 	depends on X86 && KVM_GUEST
diff --git a/drivers/cpuidle/Kconfig.s390 b/drivers/cpuidle/Kconfig.s390
new file mode 100644
index 000000000000..c9acf7ba8eee
--- /dev/null
+++ b/drivers/cpuidle/Kconfig.s390
@@ -0,0 +1,11 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# S390 CPU Idle drivers
+#
+
+config S390_CPUIDLE
+	bool "S390 CPU idle driver"
+	default y
+	help
+	  Select this option to enable processor idle state management
+	  through cpuidle subsystem.
diff --git a/drivers/cpuidle/Makefile b/drivers/cpuidle/Makefile
index 1de9e92c5b0f..88cbc2a7aea8 100644
--- a/drivers/cpuidle/Makefile
+++ b/drivers/cpuidle/Makefile
@@ -42,3 +42,7 @@ obj-$(CONFIG_POWERNV_CPUIDLE)		+= cpuidle-powernv.o
 ###############################################################################
 # RISC-V drivers
 obj-$(CONFIG_RISCV_SBI_CPUIDLE)		+= cpuidle-riscv-sbi.o
+
+###############################################################################
+# S390 drivers
+obj-$(CONFIG_S390_CPUIDLE)		+= cpuidle-s390.o
diff --git a/drivers/cpuidle/cpuidle-s390.c b/drivers/cpuidle/cpuidle-s390.c
new file mode 100644
index 000000000000..1d02a77ebce0
--- /dev/null
+++ b/drivers/cpuidle/cpuidle-s390.c
@@ -0,0 +1,115 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * s390 generic CPU idle driver.
+ *
+ * Copyright IBM Corp. 2026
+ */
+
+#define pr_fmt(fmt) "CPUidle s390: " fmt
+
+#include <linux/init.h>
+#include <linux/cpuidle.h>
+#include <linux/cpu.h>
+#include <linux/sched/clock.h>
+
+static __cpuidle int s390_enter_idle(struct cpuidle_device *dev,
+				     struct cpuidle_driver *drv,
+				     int index)
+{
+	arch_cpu_idle();
+	return index;
+}
+
+static struct cpuidle_driver s390_cpuidle_driver = {
+	.cpumask = (struct cpumask *)cpu_present_mask,
+	.name = "s390-idle",
+	.states = {
+		{ /* entry 0 is for polling */},
+		{
+			.enter			= s390_enter_idle,
+			.name			= "IDLE",
+			.desc			= "ENABLED WAIT",
+		},
+	},
+	.safe_state_index = 0,
+	.state_count = 2,
+};
+
+static int s390_cpuidle_cpu_online(unsigned int cpu)
+{
+	struct cpuidle_device *dev = &per_cpu(cpuidle_dev, cpu);
+	int rc;
+
+	if (dev->registered) {
+		cpuidle_pause_and_lock();
+		rc = cpuidle_enable_device(dev);
+		cpuidle_resume_and_unlock();
+		if (rc)
+			pr_err("Failed to enable cpuidle device on cpu %u\n", cpu);
+	} else {
+		dev->cpu = cpu;
+		rc = cpuidle_register_device(dev);
+		if (rc)
+			pr_err("Failed to register cpuidle driver on cpu %u\n", cpu);
+	}
+	return rc;
+}
+
+static int s390_cpuidle_cpu_dead(unsigned int cpu)
+{
+	struct cpuidle_device *dev = &per_cpu(cpuidle_dev, cpu);
+
+	if (!dev->registered)
+		return 0;
+	cpuidle_pause_and_lock();
+	cpuidle_disable_device(dev);
+	cpuidle_resume_and_unlock();
+	return 0;
+}
+
+/*
+ * The target_residency and exit_latency values are benchmark-derived estimates
+ * that remain non-deterministic due to s390's virtualized architecture.
+ *
+ * Configuration strategy:
+ * - Poll idle state: Values derived from the next enabled idle state (EW)
+ * - Enabled Wait state: Values selected based on idle behavior and empirical
+ *   measurement data
+ *
+ * Goal is to improve responsiveness for workloads with frequent sleep/wakeup
+ * cycles while minimizing any side effects.
+ */
+static void __init s390_cpuidle_ew_tune(void)
+{
+	struct cpuidle_state *state = &s390_cpuidle_driver.states[1];
+
+	if (machine_is_lpar()) {
+		state->target_residency = 5;
+		state->exit_latency = 5;
+	} else {
+		state->target_residency = 1;
+		state->exit_latency = 1;
+	}
+}
+
+static int __init s390_cpuidle_init(void)
+{
+	int rc;
+
+	s390_cpuidle_ew_tune();
+	cpuidle_poll_state_init(&s390_cpuidle_driver);
+	rc = cpuidle_register(&s390_cpuidle_driver, NULL);
+	if (rc)
+		return rc;
+	rc = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+				       "cpuidle/s390:online",
+				       s390_cpuidle_cpu_online,
+				       s390_cpuidle_cpu_dead);
+	if (rc < 0) {
+		cpuidle_unregister(&s390_cpuidle_driver);
+		pr_err("Failed to allocate hotplug state: cpuidle/s390:online\n");
+		return rc;
+	}
+	return 0;
+}
+device_initcall(s390_cpuidle_init);
diff --git a/include/linux/tick.h b/include/linux/tick.h
index 1cf4651f09ad..a43b7bd8ba3f 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -44,9 +44,6 @@ static inline void tick_unfreeze(void) { }
 
 #ifdef CONFIG_TICK_ONESHOT
 extern void tick_irq_enter(void);
-#  ifndef arch_needs_cpu
-#   define arch_needs_cpu() (0)
-#  endif
 # else
 static inline void tick_irq_enter(void) { }
 #endif
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 98a9cae915c0..6c3fea386713 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -828,8 +828,7 @@ static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu)
 	ts->timer_expires_base = basemono;
 
 	/*
-	 * Keep the periodic tick, when RCU, architecture or irq_work
-	 * requests it.
+	 * Keep the periodic tick, when RCU or irq_work requests it.
 	 * Aside of that, check whether the local timer softirq is
 	 * pending. If so, its a bad idea to call get_next_timer_interrupt(),
 	 * because there is an already expired timer, so it will request
@@ -837,8 +836,8 @@ static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu)
 	 * minimal delta, which brings us back to this place
 	 * immediately. Lather, rinse and repeat...
 	 */
-	if (rcu_needs_cpu() || arch_needs_cpu() ||
-	    irq_work_needs_cpu() || local_timer_softirq_pending()) {
+	if (rcu_needs_cpu() || irq_work_needs_cpu() ||
+	    local_timer_softirq_pending()) {
 		next_tick = basemono + TICK_NSEC;
 	} else {
 		/*