Merge tag 'irqchip-6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/maz/arm-platforms into irq/core

Pull irqchip updates from Marc Zyngier:

  - A number of Loogson/Loogarch fixes

  - Allow the core code to retrigger an interrupt that has
    fired while the same interrupt is being handled on another
    CPU, papering over a GICv3 architecture issue

  - Work around an integration problem on ASR8601, where the CPU
    numbering isn't representable in the GIC implementation...

  - Add some missing interrupt to the STM32 irqchip

  - A bunch of warning squashing triggered by W=1 builds

Link: https://lore.kernel.org/r/20230623224345.3577134-1-maz@kernel.org

17 files changed, 266 insertions, 88 deletions

diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 00c253b84bf5..9901efee4339 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -1215,7 +1215,7 @@ static long htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value
 
 	ret = htab_lock_bucket(htab, b, hash, &flags);
 	if (ret)
-		return ret;
+		goto err_lock_bucket;
 
 	l_old = lookup_elem_raw(head, hash, key, key_size);
 
@@ -1236,6 +1236,7 @@ static long htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value
 err:
 	htab_unlock_bucket(htab, b, hash, flags);
 
+err_lock_bucket:
 	if (ret)
 		htab_lru_push_free(htab, l_new);
 	else if (l_old)
@@ -1338,7 +1339,7 @@ static long __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,
 
 	ret = htab_lock_bucket(htab, b, hash, &flags);
 	if (ret)
-		return ret;
+		goto err_lock_bucket;
 
 	l_old = lookup_elem_raw(head, hash, key, key_size);
 
@@ -1361,6 +1362,7 @@ static long __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,
 	ret = 0;
 err:
 	htab_unlock_bucket(htab, b, hash, flags);
+err_lock_bucket:
 	if (l_new)
 		bpf_lru_push_free(&htab->lru, &l_new->lru_node);
 	return ret;
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index d9c9f45e3529..8a26cd8814c1 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -859,4 +859,4 @@ static int __init bpf_offload_init(void)
 	return rhashtable_init(&offdevs, &offdevs_params);
 }
 
-late_initcall(bpf_offload_init);
+core_initcall(bpf_offload_init);
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index fbcf5a4e2fcd..5871aa78d01a 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -17033,7 +17033,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 					insn_buf[cnt++] = BPF_ALU64_IMM(BPF_RSH,
 									insn->dst_reg,
 									shift);
-				insn_buf[cnt++] = BPF_ALU64_IMM(BPF_AND, insn->dst_reg,
+				insn_buf[cnt++] = BPF_ALU32_IMM(BPF_AND, insn->dst_reg,
 								(1ULL << size * 8) - 1);
 			}
 		}
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 68baa8194d9f..db016e418931 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -10150,8 +10150,20 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size,
 	perf_trace_buf_update(record, event_type);
 
 	hlist_for_each_entry_rcu(event, head, hlist_entry) {
-		if (perf_tp_event_match(event, &data, regs))
+		if (perf_tp_event_match(event, &data, regs)) {
 			perf_swevent_event(event, count, &data, regs);
+
+			/*
+			 * Here use the same on-stack perf_sample_data,
+			 * some members in data are event-specific and
+			 * need to be re-computed for different sweveents.
+			 * Re-initialize data->sample_flags safely to avoid
+			 * the problem that next event skips preparing data
+			 * because data->sample_flags is set.
+			 */
+			perf_sample_data_init(&data, 0, 0);
+			perf_sample_save_raw_data(&data, &raw);
+		}
 	}
 
 	/*
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 2eac5532c3c8..ee8c0acf39df 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -693,8 +693,16 @@ void handle_fasteoi_irq(struct irq_desc *desc)
 
 	raw_spin_lock(&desc->lock);
 
-	if (!irq_may_run(desc))
+	/*
+	 * When an affinity change races with IRQ handling, the next interrupt
+	 * can arrive on the new CPU before the original CPU has completed
+	 * handling the previous one - it may need to be resent.
+	 */
+	if (!irq_may_run(desc)) {
+		if (irqd_needs_resend_when_in_progress(&desc->irq_data))
+			desc->istate |= IRQS_PENDING;
 		goto out;
+	}
 
 	desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
 
@@ -716,6 +724,12 @@ void handle_fasteoi_irq(struct irq_desc *desc)
 
 	cond_unmask_eoi_irq(desc, chip);
 
+	/*
+	 * When the race described above happens this will resend the interrupt.
+	 */
+	if (unlikely(desc->istate & IRQS_PENDING))
+		check_irq_resend(desc, false);
+
 	raw_spin_unlock(&desc->lock);
 	return;
 out:
diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c
index bbcaac64038e..5971a66be034 100644
--- a/kernel/irq/debugfs.c
+++ b/kernel/irq/debugfs.c
@@ -133,6 +133,8 @@ static const struct irq_bit_descr irqdata_states[] = {
 	BIT_MASK_DESCR(IRQD_HANDLE_ENFORCE_IRQCTX),
 
 	BIT_MASK_DESCR(IRQD_IRQ_ENABLED_ON_SUSPEND),
+
+	BIT_MASK_DESCR(IRQD_RESEND_WHEN_IN_PROGRESS),
 };
 
 static const struct irq_bit_descr irqdesc_states[] = {
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 7bdb7507efb0..bdd35bb9c735 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -47,9 +47,12 @@ enum {
  *				  detection
  * IRQS_POLL_INPROGRESS		- polling in progress
  * IRQS_ONESHOT			- irq is not unmasked in primary handler
- * IRQS_REPLAY			- irq is replayed
+ * IRQS_REPLAY			- irq has been resent and will not be resent
+ * 				  again until the handler has run and cleared
+ * 				  this flag.
  * IRQS_WAITING			- irq is waiting
- * IRQS_PENDING			- irq is pending and replayed later
+ * IRQS_PENDING			- irq needs to be resent and should be resent
+ * 				  at the next available opportunity.
  * IRQS_SUSPENDED		- irq is suspended
  * IRQS_NMI			- irq line is used to deliver NMIs
  * IRQS_SYSFS			- descriptor has been added to sysfs
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index f34760a1e222..5bd01624e447 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -1915,6 +1915,8 @@ static void irq_domain_check_hierarchy(struct irq_domain *domain)
 #endif	/* CONFIG_IRQ_DOMAIN_HIERARCHY */
 
 #ifdef CONFIG_GENERIC_IRQ_DEBUGFS
+#include "internals.h"
+
 static struct dentry *domain_dir;
 
 static void
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index 7a97bcb086bf..b4c31a5c1147 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -542,7 +542,7 @@ fail:
 	return ret;
 }
 
-#ifdef CONFIG_PCI_MSI_ARCH_FALLBACKS
+#if defined(CONFIG_PCI_MSI_ARCH_FALLBACKS) || defined(CONFIG_PCI_XEN)
 /**
  * msi_device_populate_sysfs - Populate msi_irqs sysfs entries for a device
  * @dev:	The device (PCI, platform etc) which will get sysfs entries
@@ -574,7 +574,7 @@ void msi_device_destroy_sysfs(struct device *dev)
 	msi_for_each_desc(desc, dev, MSI_DESC_ALL)
 		msi_sysfs_remove_desc(dev, desc);
 }
-#endif /* CONFIG_PCI_MSI_ARCH_FALLBACK */
+#endif /* CONFIG_PCI_MSI_ARCH_FALLBACK || CONFIG_PCI_XEN */
 #else /* CONFIG_SYSFS */
 static inline int msi_sysfs_create_group(struct device *dev) { return 0; }
 static inline int msi_sysfs_populate_desc(struct device *dev, struct msi_desc *desc) { return 0; }
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index dcd1d5bfc1e0..4dfd2f3e09b2 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -2263,6 +2263,9 @@ static inline bool usage_match(struct lock_list *entry, void *mask)
 
 static inline bool usage_skip(struct lock_list *entry, void *mask)
 {
+	if (entry->class->lock_type == LD_LOCK_NORMAL)
+		return false;
+
 	/*
 	 * Skip local_lock() for irq inversion detection.
 	 *
@@ -2289,14 +2292,16 @@ static inline bool usage_skip(struct lock_list *entry, void *mask)
 	 * As a result, we will skip local_lock(), when we search for irq
 	 * inversion bugs.
 	 */
-	if (entry->class->lock_type == LD_LOCK_PERCPU) {
-		if (DEBUG_LOCKS_WARN_ON(entry->class->wait_type_inner < LD_WAIT_CONFIG))
-			return false;
+	if (entry->class->lock_type == LD_LOCK_PERCPU &&
+	    DEBUG_LOCKS_WARN_ON(entry->class->wait_type_inner < LD_WAIT_CONFIG))
+		return false;
 
-		return true;
-	}
+	/*
+	 * Skip WAIT_OVERRIDE for irq inversion detection -- it's not actually
+	 * a lock and only used to override the wait_type.
+	 */
 
-	return false;
+	return true;
 }
 
 /*
@@ -4768,7 +4773,8 @@ static int check_wait_context(struct task_struct *curr, struct held_lock *next)
 
 	for (; depth < curr->lockdep_depth; depth++) {
 		struct held_lock *prev = curr->held_locks + depth;
-		u8 prev_inner = hlock_class(prev)->wait_type_inner;
+		struct lock_class *class = hlock_class(prev);
+		u8 prev_inner = class->wait_type_inner;
 
 		if (prev_inner) {
 			/*
@@ -4778,6 +4784,14 @@ static int check_wait_context(struct task_struct *curr, struct held_lock *next)
 			 * Also due to trylocks.
 			 */
 			curr_inner = min(curr_inner, prev_inner);
+
+			/*
+			 * Allow override for annotations -- this is typically
+			 * only valid/needed for code that only exists when
+			 * CONFIG_PREEMPT_RT=n.
+			 */
+			if (unlikely(class->lock_type == LD_LOCK_WAIT_OVERRIDE))
+				curr_inner = prev_inner;
 		}
 	}
 
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index acb5a50309a1..9eabd585ce7a 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -1240,7 +1240,7 @@ static struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem)
 /*
  * lock for reading
  */
-static inline int __down_read_common(struct rw_semaphore *sem, int state)
+static __always_inline int __down_read_common(struct rw_semaphore *sem, int state)
 {
 	int ret = 0;
 	long count;
@@ -1258,17 +1258,17 @@ out:
 	return ret;
 }
 
-static inline void __down_read(struct rw_semaphore *sem)
+static __always_inline void __down_read(struct rw_semaphore *sem)
 {
 	__down_read_common(sem, TASK_UNINTERRUPTIBLE);
 }
 
-static inline int __down_read_interruptible(struct rw_semaphore *sem)
+static __always_inline int __down_read_interruptible(struct rw_semaphore *sem)
 {
 	return __down_read_common(sem, TASK_INTERRUPTIBLE);
 }
 
-static inline int __down_read_killable(struct rw_semaphore *sem)
+static __always_inline int __down_read_killable(struct rw_semaphore *sem)
 {
 	return __down_read_common(sem, TASK_KILLABLE);
 }
diff --git a/kernel/module/main.c b/kernel/module/main.c
index 044aa2c9e3cb..b4c7e925fdb0 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -3057,25 +3057,13 @@ SYSCALL_DEFINE3(init_module, void __user *, umod,
 	return load_module(&info, uargs, 0);
 }
 
-SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags)
+static int file_init_module(struct file *file, const char __user * uargs, int flags)
 {
 	struct load_info info = { };
 	void *buf = NULL;
 	int len;
-	int err;
-
-	err = may_init_module();
-	if (err)
-		return err;
-
-	pr_debug("finit_module: fd=%d, uargs=%p, flags=%i\n", fd, uargs, flags);
 
-	if (flags & ~(MODULE_INIT_IGNORE_MODVERSIONS
-		      |MODULE_INIT_IGNORE_VERMAGIC
-		      |MODULE_INIT_COMPRESSED_FILE))
-		return -EINVAL;
-
-	len = kernel_read_file_from_fd(fd, 0, &buf, INT_MAX, NULL,
+	len = kernel_read_file(file, 0, &buf, INT_MAX, NULL,
 				       READING_MODULE);
 	if (len < 0) {
 		mod_stat_inc(&failed_kreads);
@@ -3084,7 +3072,7 @@ SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags)
 	}
 
 	if (flags & MODULE_INIT_COMPRESSED_FILE) {
-		err = module_decompress(&info, buf, len);
+		int err = module_decompress(&info, buf, len);
 		vfree(buf); /* compressed data is no longer needed */
 		if (err) {
 			mod_stat_inc(&failed_decompress);
@@ -3099,6 +3087,46 @@ SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags)
 	return load_module(&info, uargs, flags);
 }
 
+/*
+ * kernel_read_file() will already deny write access, but module
+ * loading wants _exclusive_ access to the file, so we do that
+ * here, along with basic sanity checks.
+ */
+static int prepare_file_for_module_load(struct file *file)
+{
+	if (!file || !(file->f_mode & FMODE_READ))
+		return -EBADF;
+	if (!S_ISREG(file_inode(file)->i_mode))
+		return -EINVAL;
+	return exclusive_deny_write_access(file);
+}
+
+SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags)
+{
+	struct fd f;
+	int err;
+
+	err = may_init_module();
+	if (err)
+		return err;
+
+	pr_debug("finit_module: fd=%d, uargs=%p, flags=%i\n", fd, uargs, flags);
+
+	if (flags & ~(MODULE_INIT_IGNORE_MODVERSIONS
+		      |MODULE_INIT_IGNORE_VERMAGIC
+		      |MODULE_INIT_COMPRESSED_FILE))
+		return -EINVAL;
+
+	f = fdget(fd);
+	err = prepare_file_for_module_load(f.file);
+	if (!err) {
+		err = file_init_module(f.file, uargs, flags);
+		allow_write_access(f.file);
+	}
+	fdput(f);
+	return err;
+}
+
 /* Keep in sync with MODULE_FLAGS_BUF_SIZE !!! */
 char *module_flags(struct module *mod, char *buf, bool show_state)
 {
diff --git a/kernel/module/stats.c b/kernel/module/stats.c
index ad7b6ada29f2..6ab2c94d6bc3 100644
--- a/kernel/module/stats.c
+++ b/kernel/module/stats.c
@@ -276,6 +276,7 @@ static ssize_t read_file_mod_stats(struct file *file, char __user *user_buf,
 	struct mod_fail_load *mod_fail;
 	unsigned int len, size, count_failed = 0;
 	char *buf;
+	int ret;
 	u32 live_mod_count, fkreads, fdecompress, fbecoming, floads;
 	unsigned long total_size, text_size, ikread_bytes, ibecoming_bytes,
 		idecompress_bytes, imod_bytes, total_virtual_lost;
@@ -390,8 +391,9 @@ static ssize_t read_file_mod_stats(struct file *file, char __user *user_buf,
 out_unlock:
 	mutex_unlock(&module_mutex);
 out:
+	ret = simple_read_from_buffer(user_buf, count, ppos, buf, len);
 	kfree(buf);
-        return simple_read_from_buffer(user_buf, count, ppos, buf, len);
+	return ret;
 }
 #undef MAX_PREAMBLE
 #undef MAX_FAILED_MOD_PRINT
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 944c3ae39861..a68d1276bab0 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -11492,7 +11492,7 @@ void call_trace_sched_update_nr_running(struct rq *rq, int count)
 
 #ifdef CONFIG_SCHED_MM_CID
 
-/**
+/*
  * @cid_lock: Guarantee forward-progress of cid allocation.
  *
  * Concurrency ID allocation within a bitmap is mostly lock-free. The cid_lock
@@ -11501,7 +11501,7 @@ void call_trace_sched_update_nr_running(struct rq *rq, int count)
  */
 DEFINE_RAW_SPINLOCK(cid_lock);
 
-/**
+/*
  * @use_cid_lock: Select cid allocation behavior: lock-free vs spinlock.
  *
  * When @use_cid_lock is 0, the cid allocation is lock-free. When contention is
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 93bf2b4e47e5..771d1e040303 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -35,14 +35,15 @@ static __cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(tick_broadcast_lock);
 #ifdef CONFIG_TICK_ONESHOT
 static DEFINE_PER_CPU(struct clock_event_device *, tick_oneshot_wakeup_device);
 
-static void tick_broadcast_setup_oneshot(struct clock_event_device *bc);
+static void tick_broadcast_setup_oneshot(struct clock_event_device *bc, bool from_periodic);
 static void tick_broadcast_clear_oneshot(int cpu);
 static void tick_resume_broadcast_oneshot(struct clock_event_device *bc);
 # ifdef CONFIG_HOTPLUG_CPU
 static void tick_broadcast_oneshot_offline(unsigned int cpu);
 # endif
 #else
-static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc) { BUG(); }
+static inline void
+tick_broadcast_setup_oneshot(struct clock_event_device *bc, bool from_periodic) { BUG(); }
 static inline void tick_broadcast_clear_oneshot(int cpu) { }
 static inline void tick_resume_broadcast_oneshot(struct clock_event_device *bc) { }
 # ifdef CONFIG_HOTPLUG_CPU
@@ -264,7 +265,7 @@ int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu)
 		if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
 			tick_broadcast_start_periodic(bc);
 		else
-			tick_broadcast_setup_oneshot(bc);
+			tick_broadcast_setup_oneshot(bc, false);
 		ret = 1;
 	} else {
 		/*
@@ -500,7 +501,7 @@ void tick_broadcast_control(enum tick_broadcast_mode mode)
 			if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
 				tick_broadcast_start_periodic(bc);
 			else
-				tick_broadcast_setup_oneshot(bc);
+				tick_broadcast_setup_oneshot(bc, false);
 		}
 	}
 out:
@@ -1020,48 +1021,101 @@ static inline ktime_t tick_get_next_period(void)
 /**
  * tick_broadcast_setup_oneshot - setup the broadcast device
  */
-static void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
+static void tick_broadcast_setup_oneshot(struct clock_event_device *bc,
+					 bool from_periodic)
 {
 	int cpu = smp_processor_id();
+	ktime_t nexttick = 0;
 
 	if (!bc)
 		return;
 
-	/* Set it up only once ! */
-	if (bc->event_handler != tick_handle_oneshot_broadcast) {
-		int was_periodic = clockevent_state_periodic(bc);
-
-		bc->event_handler = tick_handle_oneshot_broadcast;
-
+	/*
+	 * When the broadcast device was switched to oneshot by the first
+	 * CPU handling the NOHZ change, the other CPUs will reach this
+	 * code via hrtimer_run_queues() -> tick_check_oneshot_change()
+	 * too. Set up the broadcast device only once!
+	 */
+	if (bc->event_handler == tick_handle_oneshot_broadcast) {
 		/*
-		 * We must be careful here. There might be other CPUs
-		 * waiting for periodic broadcast. We need to set the
-		 * oneshot_mask bits for those and program the
-		 * broadcast device to fire.
+		 * The CPU which switched from periodic to oneshot mode
+		 * set the broadcast oneshot bit for all other CPUs which
+		 * are in the general (periodic) broadcast mask to ensure
+		 * that CPUs which wait for the periodic broadcast are
+		 * woken up.
+		 *
+		 * Clear the bit for the local CPU as the set bit would
+		 * prevent the first tick_broadcast_enter() after this CPU
+		 * switched to oneshot state to program the broadcast
+		 * device.
+		 *
+		 * This code can also be reached via tick_broadcast_control(),
+		 * but this cannot avoid the tick_broadcast_clear_oneshot()
+		 * as that would break the periodic to oneshot transition of
+		 * secondary CPUs. But that's harmless as the below only
+		 * clears already cleared bits.
 		 */
+		tick_broadcast_clear_oneshot(cpu);
+		return;
+	}
+
+
+	bc->event_handler = tick_handle_oneshot_broadcast;
+	bc->next_event = KTIME_MAX;
+
+	/*
+	 * When the tick mode is switched from periodic to oneshot it must
+	 * be ensured that CPUs which are waiting for periodic broadcast
+	 * get their wake-up at the next tick.  This is achieved by ORing
+	 * tick_broadcast_mask into tick_broadcast_oneshot_mask.
+	 *
+	 * For other callers, e.g. broadcast device replacement,
+	 * tick_broadcast_oneshot_mask must not be touched as this would
+	 * set bits for CPUs which are already NOHZ, but not idle. Their
+	 * next tick_broadcast_enter() would observe the bit set and fail
+	 * to update the expiry time and the broadcast event device.
+	 */
+	if (from_periodic) {
 		cpumask_copy(tmpmask, tick_broadcast_mask);
+		/* Remove the local CPU as it is obviously not idle */
 		cpumask_clear_cpu(cpu, tmpmask);
-		cpumask_or(tick_broadcast_oneshot_mask,
-			   tick_broadcast_oneshot_mask, tmpmask);
+		cpumask_or(tick_broadcast_oneshot_mask, tick_broadcast_oneshot_mask, tmpmask);
 
-		if (was_periodic && !cpumask_empty(tmpmask)) {
-			ktime_t nextevt = tick_get_next_period();
+		/*
+		 * Ensure that the oneshot broadcast handler will wake the
+		 * CPUs which are still waiting for periodic broadcast.
+		 */
+		nexttick = tick_get_next_period();
+		tick_broadcast_init_next_event(tmpmask, nexttick);
 
-			clockevents_switch_state(bc, CLOCK_EVT_STATE_ONESHOT);
-			tick_broadcast_init_next_event(tmpmask, nextevt);
-			tick_broadcast_set_event(bc, cpu, nextevt);
-		} else
-			bc->next_event = KTIME_MAX;
-	} else {
 		/*
-		 * The first cpu which switches to oneshot mode sets
-		 * the bit for all other cpus which are in the general
-		 * (periodic) broadcast mask. So the bit is set and
-		 * would prevent the first broadcast enter after this
-		 * to program the bc device.
+		 * If the underlying broadcast clock event device is
+		 * already in oneshot state, then there is nothing to do.
+		 * The device was already armed for the next tick
+		 * in tick_handle_broadcast_periodic()
 		 */
-		tick_broadcast_clear_oneshot(cpu);
+		if (clockevent_state_oneshot(bc))
+			return;
 	}
+
+	/*
+	 * When switching from periodic to oneshot mode arm the broadcast
+	 * device for the next tick.
+	 *
+	 * If the broadcast device has been replaced in oneshot mode and
+	 * the oneshot broadcast mask is not empty, then arm it to expire
+	 * immediately in order to reevaluate the next expiring timer.
+	 * @nexttick is 0 and therefore in the past which will cause the
+	 * clockevent code to force an event.
+	 *
+	 * For both cases the programming can be avoided when the oneshot
+	 * broadcast mask is empty.
+	 *
+	 * tick_broadcast_set_event() implicitly switches the broadcast
+	 * device to oneshot state.
+	 */
+	if (!cpumask_empty(tick_broadcast_oneshot_mask))
+		tick_broadcast_set_event(bc, cpu, nexttick);
 }
 
 /*
@@ -1070,14 +1124,16 @@ static void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 void tick_broadcast_switch_to_oneshot(void)
 {
 	struct clock_event_device *bc;
+	enum tick_device_mode oldmode;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
 
+	oldmode = tick_broadcast_device.mode;
 	tick_broadcast_device.mode = TICKDEV_MODE_ONESHOT;
 	bc = tick_broadcast_device.evtdev;
 	if (bc)
-		tick_broadcast_setup_oneshot(bc);
+		tick_broadcast_setup_oneshot(bc, oldmode == TICKDEV_MODE_PERIODIC);
 
 	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 }
diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c
index 9abb3905bc8e..18d36842faf5 100644
--- a/kernel/trace/fprobe.c
+++ b/kernel/trace/fprobe.c
@@ -17,36 +17,30 @@
 struct fprobe_rethook_node {
 	struct rethook_node node;
 	unsigned long entry_ip;
+	unsigned long entry_parent_ip;
 	char data[];
 };
 
-static void fprobe_handler(unsigned long ip, unsigned long parent_ip,
-			   struct ftrace_ops *ops, struct ftrace_regs *fregs)
+static inline void __fprobe_handler(unsigned long ip, unsigned long parent_ip,
+			struct ftrace_ops *ops, struct ftrace_regs *fregs)
 {
 	struct fprobe_rethook_node *fpr;
 	struct rethook_node *rh = NULL;
 	struct fprobe *fp;
 	void *entry_data = NULL;
-	int bit, ret;
+	int ret = 0;
 
 	fp = container_of(ops, struct fprobe, ops);
-	if (fprobe_disabled(fp))
-		return;
-
-	bit = ftrace_test_recursion_trylock(ip, parent_ip);
-	if (bit < 0) {
-		fp->nmissed++;
-		return;
-	}
 
 	if (fp->exit_handler) {
 		rh = rethook_try_get(fp->rethook);
 		if (!rh) {
 			fp->nmissed++;
-			goto out;
+			return;
 		}
 		fpr = container_of(rh, struct fprobe_rethook_node, node);
 		fpr->entry_ip = ip;
+		fpr->entry_parent_ip = parent_ip;
 		if (fp->entry_data_size)
 			entry_data = fpr->data;
 	}
@@ -61,23 +55,60 @@ static void fprobe_handler(unsigned long ip, unsigned long parent_ip,
 		else
 			rethook_hook(rh, ftrace_get_regs(fregs), true);
 	}
-out:
+}
+
+static void fprobe_handler(unsigned long ip, unsigned long parent_ip,
+		struct ftrace_ops *ops, struct ftrace_regs *fregs)
+{
+	struct fprobe *fp;
+	int bit;
+
+	fp = container_of(ops, struct fprobe, ops);
+	if (fprobe_disabled(fp))
+		return;
+
+	/* recursion detection has to go before any traceable function and
+	 * all functions before this point should be marked as notrace
+	 */
+	bit = ftrace_test_recursion_trylock(ip, parent_ip);
+	if (bit < 0) {
+		fp->nmissed++;
+		return;
+	}
+	__fprobe_handler(ip, parent_ip, ops, fregs);
 	ftrace_test_recursion_unlock(bit);
+
 }
 NOKPROBE_SYMBOL(fprobe_handler);
 
 static void fprobe_kprobe_handler(unsigned long ip, unsigned long parent_ip,
 				  struct ftrace_ops *ops, struct ftrace_regs *fregs)
 {
-	struct fprobe *fp = container_of(ops, struct fprobe, ops);
+	struct fprobe *fp;
+	int bit;
+
+	fp = container_of(ops, struct fprobe, ops);
+	if (fprobe_disabled(fp))
+		return;
+
+	/* recursion detection has to go before any traceable function and
+	 * all functions called before this point should be marked as notrace
+	 */
+	bit = ftrace_test_recursion_trylock(ip, parent_ip);
+	if (bit < 0) {
+		fp->nmissed++;
+		return;
+	}
 
 	if (unlikely(kprobe_running())) {
 		fp->nmissed++;
 		return;
 	}
+
 	kprobe_busy_begin();
-	fprobe_handler(ip, parent_ip, ops, fregs);
+	__fprobe_handler(ip, parent_ip, ops, fregs);
 	kprobe_busy_end();
+	ftrace_test_recursion_unlock(bit);
 }
 
 static void fprobe_exit_handler(struct rethook_node *rh, void *data,
@@ -85,14 +116,26 @@ static void fprobe_exit_handler(struct rethook_node *rh, void *data,
 {
 	struct fprobe *fp = (struct fprobe *)data;
 	struct fprobe_rethook_node *fpr;
+	int bit;
 
 	if (!fp || fprobe_disabled(fp))
 		return;
 
 	fpr = container_of(rh, struct fprobe_rethook_node, node);
 
+	/*
+	 * we need to assure no calls to traceable functions in-between the
+	 * end of fprobe_handler and the beginning of fprobe_exit_handler.
+	 */
+	bit = ftrace_test_recursion_trylock(fpr->entry_ip, fpr->entry_parent_ip);
+	if (bit < 0) {
+		fp->nmissed++;
+		return;
+	}
+
 	fp->exit_handler(fp, fpr->entry_ip, regs,
 			 fp->entry_data_size ? (void *)fpr->data : NULL);
+	ftrace_test_recursion_unlock(bit);
 }
 NOKPROBE_SYMBOL(fprobe_exit_handler);
 
diff --git a/kernel/trace/rethook.c b/kernel/trace/rethook.c
index 32c3dfdb4d6a..60f6cb2b486b 100644
--- a/kernel/trace/rethook.c
+++ b/kernel/trace/rethook.c
@@ -288,7 +288,7 @@ unsigned long rethook_trampoline_handler(struct pt_regs *regs,
 	 * These loops must be protected from rethook_free_rcu() because those
 	 * are accessing 'rhn->rethook'.
 	 */
-	preempt_disable();
+	preempt_disable_notrace();
 
 	/*
 	 * Run the handler on the shadow stack. Do not unlink the list here because
@@ -321,7 +321,7 @@ unsigned long rethook_trampoline_handler(struct pt_regs *regs,
 		first = first->next;
 		rethook_recycle(rhn);
 	}
-	preempt_enable();
+	preempt_enable_notrace();
 
 	return correct_ret_addr;
 }