Merge branch 'irq-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull genirq updates from Thomas Gleixner:
 "The irq departement provides:

   - A synchronization fix for free_irq() to synchronize just the
     removed interrupt thread on shared interrupt lines.

   - Consolidate the multi low level interrupt entry handling and mvoe
     it to the generic code instead of adding yet another copy for
     RISC-V

   - Refactoring of the ARM LPI allocator and LPI exposure to the
     hypervisor

   - Yet another interrupt chip driver for the JZ4725B SoC

   - Speed up for /proc/interrupts as people seem to love reading this
     file with high frequency

   - Miscellaneous fixes and updates"

* 'irq-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (23 commits)
  irqchip/gic-v3-its: Make its_lock a raw_spin_lock_t
  genirq/irqchip: Remove MULTI_IRQ_HANDLER as it's now obselete
  openrisc: Use the new GENERIC_IRQ_MULTI_HANDLER
  arm64: Use the new GENERIC_IRQ_MULTI_HANDLER
  ARM: Convert to GENERIC_IRQ_MULTI_HANDLER
  irqchip: Port the ARM IRQ drivers to GENERIC_IRQ_MULTI_HANDLER
  irqchip/gic-v3-its: Reduce minimum LPI allocation to 1 for PCI devices
  dt-bindings: irqchip: renesas-irqc: Document r8a77980 support
  dt-bindings: irqchip: renesas-irqc: Document r8a77470 support
  irqchip/ingenic: Add support for the JZ4725B SoC
  irqchip/stm32: Add exti0 translation for stm32mp1
  genirq: Remove redundant NULL pointer check in __free_irq()
  irqchip/gic-v3-its: Honor hypervisor enforced LPI range
  irqchip/gic-v3: Expose GICD_TYPER in the rdist structure
  irqchip/gic-v3-its: Drop chunk allocation compatibility
  irqchip/gic-v3-its: Move minimum LPI requirements to individual busses
  irqchip/gic-v3-its: Use full range of LPIs
  irqchip/gic-v3-its: Refactor LPI allocator
  genirq: Synchronize only with single thread on free_irq()
  genirq: Update code comments wrt recycled thread_mask
  ...

4 files changed, 47 insertions, 36 deletions

diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index c6766f326072..5f3e2baefca9 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -134,7 +134,6 @@ config GENERIC_IRQ_DEBUGFS
 endmenu
 
 config GENERIC_IRQ_MULTI_HANDLER
-	depends on !MULTI_IRQ_HANDLER
 	bool
 	help
 	  Allow to specify the low level IRQ handler at run time.
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index afc7f902d74a..578d0e5f1b5b 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -443,6 +443,7 @@ static void free_desc(unsigned int irq)
 	 * We free the descriptor, masks and stat fields via RCU. That
 	 * allows demultiplex interrupts to do rcu based management of
 	 * the child interrupts.
+	 * This also allows us to use rcu in kstat_irqs_usr().
 	 */
 	call_rcu(&desc->rcu, delayed_free_desc);
 }
@@ -928,17 +929,17 @@ unsigned int kstat_irqs(unsigned int irq)
  * kstat_irqs_usr - Get the statistics for an interrupt
  * @irq:	The interrupt number
  *
- * Returns the sum of interrupt counts on all cpus since boot for
- * @irq. Contrary to kstat_irqs() this can be called from any
- * preemptible context. It's protected against concurrent removal of
- * an interrupt descriptor when sparse irqs are enabled.
+ * Returns the sum of interrupt counts on all cpus since boot for @irq.
+ * Contrary to kstat_irqs() this can be called from any context.
+ * It uses rcu since a concurrent removal of an interrupt descriptor is
+ * observing an rcu grace period before delayed_free_desc()/irq_kobj_release().
  */
 unsigned int kstat_irqs_usr(unsigned int irq)
 {
 	unsigned int sum;
 
-	irq_lock_sparse();
+	rcu_read_lock();
 	sum = kstat_irqs(irq);
-	irq_unlock_sparse();
+	rcu_read_unlock();
 	return sum;
 }
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 9a8b7ba9aa88..fb86146037a7 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -790,9 +790,19 @@ static irqreturn_t irq_forced_secondary_handler(int irq, void *dev_id)
 
 static int irq_wait_for_interrupt(struct irqaction *action)
 {
-	set_current_state(TASK_INTERRUPTIBLE);
+	for (;;) {
+		set_current_state(TASK_INTERRUPTIBLE);
 
-	while (!kthread_should_stop()) {
+		if (kthread_should_stop()) {
+			/* may need to run one last time */
+			if (test_and_clear_bit(IRQTF_RUNTHREAD,
+					       &action->thread_flags)) {
+				__set_current_state(TASK_RUNNING);
+				return 0;
+			}
+			__set_current_state(TASK_RUNNING);
+			return -1;
+		}
 
 		if (test_and_clear_bit(IRQTF_RUNTHREAD,
 				       &action->thread_flags)) {
@@ -800,10 +810,7 @@ static int irq_wait_for_interrupt(struct irqaction *action)
 			return 0;
 		}
 		schedule();
-		set_current_state(TASK_INTERRUPTIBLE);
 	}
-	__set_current_state(TASK_RUNNING);
-	return -1;
 }
 
 /*
@@ -1024,11 +1031,8 @@ static int irq_thread(void *data)
 	/*
 	 * This is the regular exit path. __free_irq() is stopping the
 	 * thread via kthread_stop() after calling
-	 * synchronize_irq(). So neither IRQTF_RUNTHREAD nor the
-	 * oneshot mask bit can be set. We cannot verify that as we
-	 * cannot touch the oneshot mask at this point anymore as
-	 * __setup_irq() might have given out currents thread_mask
-	 * again.
+	 * synchronize_hardirq(). So neither IRQTF_RUNTHREAD nor the
+	 * oneshot mask bit can be set.
 	 */
 	task_work_cancel(current, irq_thread_dtor);
 	return 0;
@@ -1251,8 +1255,10 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 
 	/*
 	 * Protects against a concurrent __free_irq() call which might wait
-	 * for synchronize_irq() to complete without holding the optional
-	 * chip bus lock and desc->lock.
+	 * for synchronize_hardirq() to complete without holding the optional
+	 * chip bus lock and desc->lock. Also protects against handing out
+	 * a recycled oneshot thread_mask bit while it's still in use by
+	 * its previous owner.
 	 */
 	mutex_lock(&desc->request_mutex);
 
@@ -1571,9 +1577,6 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
 
 	WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq);
 
-	if (!desc)
-		return NULL;
-
 	mutex_lock(&desc->request_mutex);
 	chip_bus_lock(desc);
 	raw_spin_lock_irqsave(&desc->lock, flags);
@@ -1620,11 +1623,11 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
 	/*
 	 * Drop bus_lock here so the changes which were done in the chip
 	 * callbacks above are synced out to the irq chips which hang
-	 * behind a slow bus (I2C, SPI) before calling synchronize_irq().
+	 * behind a slow bus (I2C, SPI) before calling synchronize_hardirq().
 	 *
 	 * Aside of that the bus_lock can also be taken from the threaded
 	 * handler in irq_finalize_oneshot() which results in a deadlock
-	 * because synchronize_irq() would wait forever for the thread to
+	 * because kthread_stop() would wait forever for the thread to
 	 * complete, which is blocked on the bus lock.
 	 *
 	 * The still held desc->request_mutex() protects against a
@@ -1636,7 +1639,7 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
 	unregister_handler_proc(irq, action);
 
 	/* Make sure it's not being used on another CPU: */
-	synchronize_irq(irq);
+	synchronize_hardirq(irq);
 
 #ifdef CONFIG_DEBUG_SHIRQ
 	/*
@@ -1645,7 +1648,7 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
 	 * is so by doing an extra call to the handler ....
 	 *
 	 * ( We do this after actually deregistering it, to make sure that a
-	 *   'real' IRQ doesn't run in * parallel with our fake. )
+	 *   'real' IRQ doesn't run in parallel with our fake. )
 	 */
 	if (action->flags & IRQF_SHARED) {
 		local_irq_save(flags);
@@ -1654,6 +1657,12 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
 	}
 #endif
 
+	/*
+	 * The action has already been removed above, but the thread writes
+	 * its oneshot mask bit when it completes. Though request_mutex is
+	 * held across this which prevents __setup_irq() from handing out
+	 * the same bit to a newly requested action.
+	 */
 	if (action->thread) {
 		kthread_stop(action->thread);
 		put_task_struct(action->thread);
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 37eda10f5c36..da9addb8d655 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -475,22 +475,24 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_putc(p, '\n');
 	}
 
-	irq_lock_sparse();
+	rcu_read_lock();
 	desc = irq_to_desc(i);
 	if (!desc)
 		goto outsparse;
 
-	raw_spin_lock_irqsave(&desc->lock, flags);
-	for_each_online_cpu(j)
-		any_count |= kstat_irqs_cpu(i, j);
-	action = desc->action;
-	if ((!action || irq_desc_is_chained(desc)) && !any_count)
-		goto out;
+	if (desc->kstat_irqs)
+		for_each_online_cpu(j)
+			any_count |= *per_cpu_ptr(desc->kstat_irqs, j);
+
+	if ((!desc->action || irq_desc_is_chained(desc)) && !any_count)
+		goto outsparse;
 
 	seq_printf(p, "%*d: ", prec, i);
 	for_each_online_cpu(j)
-		seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
+		seq_printf(p, "%10u ", desc->kstat_irqs ?
+					*per_cpu_ptr(desc->kstat_irqs, j) : 0);
 
+	raw_spin_lock_irqsave(&desc->lock, flags);
 	if (desc->irq_data.chip) {
 		if (desc->irq_data.chip->irq_print_chip)
 			desc->irq_data.chip->irq_print_chip(&desc->irq_data, p);
@@ -511,6 +513,7 @@ int show_interrupts(struct seq_file *p, void *v)
 	if (desc->name)
 		seq_printf(p, "-%-8s", desc->name);
 
+	action = desc->action;
 	if (action) {
 		seq_printf(p, "  %s", action->name);
 		while ((action = action->next) != NULL)
@@ -518,10 +521,9 @@ int show_interrupts(struct seq_file *p, void *v)
 	}
 
 	seq_putc(p, '\n');
-out:
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 outsparse:
-	irq_unlock_sparse();
+	rcu_read_unlock();
 	return 0;
 }
 #endif