genirq: Add support for per-cpu dev_id interrupts

The ARM GIC interrupt controller offers per CPU interrupts (PPIs),
which are usually used to connect local timers to each core. Each CPU
has its own private interface to the GIC, and only sees the PPIs that
are directly connect to it.

While these timers are separate devices and have a separate interrupt
line to a core, they all use the same IRQ number.

For these devices, request_irq() is not the right API as it assumes
that an IRQ number is visible by a number of CPUs (through the
affinity setting), but makes it very awkward to express that an IRQ
number can be handled by all CPUs, and yet be a different interrupt
line on each CPU, requiring a different dev_id cookie to be passed
back to the handler.

The *_percpu_irq() functions is designed to overcome these
limitations, by providing a per-cpu dev_id vector:

int request_percpu_irq(unsigned int irq, irq_handler_t handler,
		   const char *devname, void __percpu *percpu_dev_id);
void free_percpu_irq(unsigned int, void __percpu *);
int setup_percpu_irq(unsigned int irq, struct irqaction *new);
void remove_percpu_irq(unsigned int irq, struct irqaction *act);
void enable_percpu_irq(unsigned int irq);
void disable_percpu_irq(unsigned int irq);

The API has a number of limitations:
- no interrupt sharing
- no threading
- common handler across all the CPUs

Once the interrupt is requested using setup_percpu_irq() or
request_percpu_irq(), it must be enabled by each core that wishes its
local interrupt to be delivered.

Based on an initial patch by Thomas Gleixner.

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Cc: linux-arm-kernel@lists.infradead.org
Link: http://lkml.kernel.org/r/1316793788-14500-2-git-send-email-marc.zyngier@arm.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

5 files changed, 302 insertions, 22 deletions

diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index dc5114b4c16c..f7c543a801d9 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -26,7 +26,7 @@
 int irq_set_chip(unsigned int irq, struct irq_chip *chip)
 {
         unsigned long flags;
-        struct irq_desc *desc = irq_get_desc_lock(irq, &flags);
+        struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0);
 
         if (!desc)
                 return -EINVAL;
@@ -54,7 +54,7 @@ EXPORT_SYMBOL(irq_set_chip);
 int irq_set_irq_type(unsigned int irq, unsigned int type)
 {
         unsigned long flags;
-        struct irq_desc *desc = irq_get_desc_buslock(irq, &flags);
+        struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL);
         int ret = 0;
 
         if (!desc)
@@ -78,7 +78,7 @@ EXPORT_SYMBOL(irq_set_irq_type);
 int irq_set_handler_data(unsigned int irq, void *data)
 {
         unsigned long flags;
-        struct irq_desc *desc = irq_get_desc_lock(irq, &flags);
+        struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0);
 
         if (!desc)
                 return -EINVAL;
@@ -98,7 +98,7 @@ EXPORT_SYMBOL(irq_set_handler_data);
 int irq_set_msi_desc(unsigned int irq, struct msi_desc *entry)
 {
         unsigned long flags;
-        struct irq_desc *desc = irq_get_desc_lock(irq, &flags);
+        struct irq_desc *desc = irq_get_desc_lock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL);
 
         if (!desc)
                 return -EINVAL;
@@ -119,7 +119,7 @@ int irq_set_msi_desc(unsigned int irq, struct msi_desc *entry)
 int irq_set_chip_data(unsigned int irq, void *data)
 {
         unsigned long flags;
-        struct irq_desc *desc = irq_get_desc_lock(irq, &flags);
+        struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0);
 
         if (!desc)
                 return -EINVAL;
@@ -204,6 +204,24 @@ void irq_disable(struct irq_desc *desc)
         }
 }
 
+void irq_percpu_enable(struct irq_desc *desc, unsigned int cpu)
+{
+        if (desc->irq_data.chip->irq_enable)
+                desc->irq_data.chip->irq_enable(&desc->irq_data);
+        else
+                desc->irq_data.chip->irq_unmask(&desc->irq_data);
+        cpumask_set_cpu(cpu, desc->percpu_enabled);
+}
+
+void irq_percpu_disable(struct irq_desc *desc, unsigned int cpu)
+{
+        if (desc->irq_data.chip->irq_disable)
+                desc->irq_data.chip->irq_disable(&desc->irq_data);
+        else
+                desc->irq_data.chip->irq_mask(&desc->irq_data);
+        cpumask_clear_cpu(cpu, desc->percpu_enabled);
+}
+
 static inline void mask_ack_irq(struct irq_desc *desc)
 {
         if (desc->irq_data.chip->irq_mask_ack)
@@ -544,12 +562,44 @@ handle_percpu_irq(unsigned int irq, struct irq_desc *desc)
                 chip->irq_eoi(&desc->irq_data);
 }
 
+/**
+ * handle_percpu_devid_irq - Per CPU local irq handler with per cpu dev ids
+ * @irq:        the interrupt number
+ * @desc:       the interrupt description structure for this irq
+ *
+ * Per CPU interrupts on SMP machines without locking requirements. Same as
+ * handle_percpu_irq() above but with the following extras:
+ *
+ * action->percpu_dev_id is a pointer to percpu variables which
+ * contain the real device id for the cpu on which this handler is
+ * called
+ */
+void handle_percpu_devid_irq(unsigned int irq, struct irq_desc *desc)
+{
+        struct irq_chip *chip = irq_desc_get_chip(desc);
+        struct irqaction *action = desc->action;
+        void *dev_id = __this_cpu_ptr(action->percpu_dev_id);
+        irqreturn_t res;
+
+        kstat_incr_irqs_this_cpu(irq, desc);
+
+        if (chip->irq_ack)
+                chip->irq_ack(&desc->irq_data);
+
+        trace_irq_handler_entry(irq, action);
+        res = action->handler(irq, dev_id);
+        trace_irq_handler_exit(irq, action, res);
+
+        if (chip->irq_eoi)
+                chip->irq_eoi(&desc->irq_data);
+}
+
 void
 __irq_set_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
                   const char *name)
 {
         unsigned long flags;
-        struct irq_desc *desc = irq_get_desc_buslock(irq, &flags);
+        struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, 0);
 
         if (!desc)
                 return;
@@ -593,7 +643,7 @@ irq_set_chip_and_handler_name(unsigned int irq, struct irq_chip *chip,
 void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set)
 {
         unsigned long flags;
-        struct irq_desc *desc = irq_get_desc_lock(irq, &flags);
+        struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0);
 
         if (!desc)
                 return;
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 6546431447d7..a73dd6c7372d 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -71,6 +71,8 @@ extern int irq_startup(struct irq_desc *desc);
 extern void irq_shutdown(struct irq_desc *desc);
 extern void irq_enable(struct irq_desc *desc);
 extern void irq_disable(struct irq_desc *desc);
+extern void irq_percpu_enable(struct irq_desc *desc, unsigned int cpu);
+extern void irq_percpu_disable(struct irq_desc *desc, unsigned int cpu);
 extern void mask_irq(struct irq_desc *desc);
 extern void unmask_irq(struct irq_desc *desc);
 
@@ -114,14 +116,21 @@ static inline void chip_bus_sync_unlock(struct irq_desc *desc)
                 desc->irq_data.chip->irq_bus_sync_unlock(&desc->irq_data);
 }
 
+#define _IRQ_DESC_CHECK         (1 << 0)
+#define _IRQ_DESC_PERCPU        (1 << 1)
+
+#define IRQ_GET_DESC_CHECK_GLOBAL       (_IRQ_DESC_CHECK)
+#define IRQ_GET_DESC_CHECK_PERCPU       (_IRQ_DESC_CHECK | _IRQ_DESC_PERCPU)
+
 struct irq_desc *
-__irq_get_desc_lock(unsigned int irq, unsigned long *flags, bool bus);
+__irq_get_desc_lock(unsigned int irq, unsigned long *flags, bool bus,
+                    unsigned int check);
 void __irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags, bool bus);
 
 static inline struct irq_desc *
-irq_get_desc_buslock(unsigned int irq, unsigned long *flags)
+irq_get_desc_buslock(unsigned int irq, unsigned long *flags, unsigned int check)
 {
-        return __irq_get_desc_lock(irq, flags, true);
+        return __irq_get_desc_lock(irq, flags, true, check);
 }
 
 static inline void
@@ -131,9 +140,9 @@ irq_put_desc_busunlock(struct irq_desc *desc, unsigned long flags)
 }
 
 static inline struct irq_desc *
-irq_get_desc_lock(unsigned int irq, unsigned long *flags)
+irq_get_desc_lock(unsigned int irq, unsigned long *flags, unsigned int check)
 {
-        return __irq_get_desc_lock(irq, flags, false);
+        return __irq_get_desc_lock(irq, flags, false, check);
 }
 
 static inline void
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 039b889ea053..1550e8447a16 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -424,11 +424,22 @@ unsigned int irq_get_next_irq(unsigned int offset)
 }
 
 struct irq_desc *
-__irq_get_desc_lock(unsigned int irq, unsigned long *flags, bool bus)
+__irq_get_desc_lock(unsigned int irq, unsigned long *flags, bool bus,
+                    unsigned int check)
 {
         struct irq_desc *desc = irq_to_desc(irq);
 
         if (desc) {
+                if (check & _IRQ_DESC_CHECK) {
+                        if ((check & _IRQ_DESC_PERCPU) &&
+                            !irq_settings_is_per_cpu_devid(desc))
+                                return NULL;
+
+                        if (!(check & _IRQ_DESC_PERCPU) &&
+                            irq_settings_is_per_cpu_devid(desc))
+                                return NULL;
+                }
+
                 if (bus)
                         chip_bus_lock(desc);
                 raw_spin_lock_irqsave(&desc->lock, *flags);
@@ -443,6 +454,25 @@ void __irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags, bool bus)
                 chip_bus_sync_unlock(desc);
 }
 
+int irq_set_percpu_devid(unsigned int irq)
+{
+        struct irq_desc *desc = irq_to_desc(irq);
+
+        if (!desc)
+                return -EINVAL;
+
+        if (desc->percpu_enabled)
+                return -EINVAL;
+
+        desc->percpu_enabled = kzalloc(sizeof(*desc->percpu_enabled), GFP_KERNEL);
+
+        if (!desc->percpu_enabled)
+                return -ENOMEM;
+
+        irq_set_percpu_devid_flags(irq);
+        return 0;
+}
+
 /**
  * dynamic_irq_cleanup - cleanup a dynamically allocated irq
  * @irq:        irq number to initialize
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 7e1a3ed1e61a..7b4b156d065c 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -195,7 +195,7 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *mask)
 int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m)
 {
         unsigned long flags;
-        struct irq_desc *desc = irq_get_desc_lock(irq, &flags);
+        struct irq_desc *desc = irq_get_desc_lock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL);
 
         if (!desc)
                 return -EINVAL;
@@ -356,7 +356,7 @@ void __disable_irq(struct irq_desc *desc, unsigned int irq, bool suspend)
 static int __disable_irq_nosync(unsigned int irq)
 {
         unsigned long flags;
-        struct irq_desc *desc = irq_get_desc_buslock(irq, &flags);
+        struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL);
 
         if (!desc)
                 return -EINVAL;
@@ -448,7 +448,7 @@ void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume)
 void enable_irq(unsigned int irq)
 {
         unsigned long flags;
-        struct irq_desc *desc = irq_get_desc_buslock(irq, &flags);
+        struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL);
 
         if (!desc)
                 return;
@@ -491,7 +491,7 @@ static int set_irq_wake_real(unsigned int irq, unsigned int on)
 int irq_set_irq_wake(unsigned int irq, unsigned int on)
 {
         unsigned long flags;
-        struct irq_desc *desc = irq_get_desc_buslock(irq, &flags);
+        struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL);
         int ret = 0;
 
         if (!desc)
@@ -532,7 +532,7 @@ EXPORT_SYMBOL(irq_set_irq_wake);
 int can_request_irq(unsigned int irq, unsigned long irqflags)
 {
         unsigned long flags;
-        struct irq_desc *desc = irq_get_desc_lock(irq, &flags);
+        struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0);
         int canrequest = 0;
 
         if (!desc)
@@ -1121,6 +1121,8 @@ int setup_irq(unsigned int irq, struct irqaction *act)
         int retval;
         struct irq_desc *desc = irq_to_desc(irq);
 
+        if (WARN_ON(irq_settings_is_per_cpu_devid(desc)))
+                return -EINVAL;
         chip_bus_lock(desc);
         retval = __setup_irq(irq, desc, act);
         chip_bus_sync_unlock(desc);
@@ -1129,7 +1131,7 @@ int setup_irq(unsigned int irq, struct irqaction *act)
 }
 EXPORT_SYMBOL_GPL(setup_irq);
 
- /*
+/*
  * Internal function to unregister an irqaction - used to free
  * regular and special interrupts that are part of the architecture.
  */
@@ -1227,7 +1229,10 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id)
  */
 void remove_irq(unsigned int irq, struct irqaction *act)
 {
-        __free_irq(irq, act->dev_id);
+        struct irq_desc *desc = irq_to_desc(irq);
+
+        if (desc && !WARN_ON(irq_settings_is_per_cpu_devid(desc)))
+            __free_irq(irq, act->dev_id);
 }
 EXPORT_SYMBOL_GPL(remove_irq);
 
@@ -1249,7 +1254,7 @@ void free_irq(unsigned int irq, void *dev_id)
 {
         struct irq_desc *desc = irq_to_desc(irq);
 
-        if (!desc)
+        if (!desc || WARN_ON(irq_settings_is_per_cpu_devid(desc)))
                 return;
 
 #ifdef CONFIG_SMP
@@ -1327,7 +1332,8 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler,
         if (!desc)
                 return -EINVAL;
 
-        if (!irq_settings_can_request(desc))
+        if (!irq_settings_can_request(desc) ||
+            WARN_ON(irq_settings_is_per_cpu_devid(desc)))
                 return -EINVAL;
 
         if (!handler) {
@@ -1412,3 +1418,181 @@ int request_any_context_irq(unsigned int irq, irq_handler_t handler,
         return !ret ? IRQC_IS_HARDIRQ : ret;
 }
 EXPORT_SYMBOL_GPL(request_any_context_irq);
+
+void enable_percpu_irq(unsigned int irq)
+{
+        unsigned int cpu = smp_processor_id();
+        unsigned long flags;
+        struct irq_desc *desc = irq_get_desc_lock(irq, &flags, IRQ_GET_DESC_CHECK_PERCPU);
+
+        if (!desc)
+                return;
+
+        irq_percpu_enable(desc, cpu);
+        irq_put_desc_unlock(desc, flags);
+}
+
+void disable_percpu_irq(unsigned int irq)
+{
+        unsigned int cpu = smp_processor_id();
+        unsigned long flags;
+        struct irq_desc *desc = irq_get_desc_lock(irq, &flags, IRQ_GET_DESC_CHECK_PERCPU);
+
+        if (!desc)
+                return;
+
+        irq_percpu_disable(desc, cpu);
+        irq_put_desc_unlock(desc, flags);
+}
+
+/*
+ * Internal function to unregister a percpu irqaction.
+ */
+static struct irqaction *__free_percpu_irq(unsigned int irq, void __percpu *dev_id)
+{
+        struct irq_desc *desc = irq_to_desc(irq);
+        struct irqaction *action;
+        unsigned long flags;
+
+        WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq);
+
+        if (!desc)
+                return NULL;
+
+        raw_spin_lock_irqsave(&desc->lock, flags);
+
+        action = desc->action;
+        if (!action || action->percpu_dev_id != dev_id) {
+                WARN(1, "Trying to free already-free IRQ %d\n", irq);
+                goto bad;
+        }
+
+        if (!cpumask_empty(desc->percpu_enabled)) {
+                WARN(1, "percpu IRQ %d still enabled on CPU%d!\n",
+                     irq, cpumask_first(desc->percpu_enabled));
+                goto bad;
+        }
+
+        /* Found it - now remove it from the list of entries: */
+        desc->action = NULL;
+
+        raw_spin_unlock_irqrestore(&desc->lock, flags);
+
+        unregister_handler_proc(irq, action);
+
+        module_put(desc->owner);
+        return action;
+
+bad:
+        raw_spin_unlock_irqrestore(&desc->lock, flags);
+        return NULL;
+}
+
+/**
+ *      remove_percpu_irq - free a per-cpu interrupt
+ *      @irq: Interrupt line to free
+ *      @act: irqaction for the interrupt
+ *
+ * Used to remove interrupts statically setup by the early boot process.
+ */
+void remove_percpu_irq(unsigned int irq, struct irqaction *act)
+{
+        struct irq_desc *desc = irq_to_desc(irq);
+
+        if (desc && irq_settings_is_per_cpu_devid(desc))
+            __free_percpu_irq(irq, act->percpu_dev_id);
+}
+
+/**
+ *      free_percpu_irq - free an interrupt allocated with request_percpu_irq
+ *      @irq: Interrupt line to free
+ *      @dev_id: Device identity to free
+ *
+ *      Remove a percpu interrupt handler. The handler is removed, but
+ *      the interrupt line is not disabled. This must be done on each
+ *      CPU before calling this function. The function does not return
+ *      until any executing interrupts for this IRQ have completed.
+ *
+ *      This function must not be called from interrupt context.
+ */
+void free_percpu_irq(unsigned int irq, void __percpu *dev_id)
+{
+        struct irq_desc *desc = irq_to_desc(irq);
+
+        if (!desc || !irq_settings_is_per_cpu_devid(desc))
+                return;
+
+        chip_bus_lock(desc);
+        kfree(__free_percpu_irq(irq, dev_id));
+        chip_bus_sync_unlock(desc);
+}
+
+/**
+ *      setup_percpu_irq - setup a per-cpu interrupt
+ *      @irq: Interrupt line to setup
+ *      @act: irqaction for the interrupt
+ *
+ * Used to statically setup per-cpu interrupts in the early boot process.
+ */
+int setup_percpu_irq(unsigned int irq, struct irqaction *act)
+{
+        struct irq_desc *desc = irq_to_desc(irq);
+        int retval;
+
+        if (!desc || !irq_settings_is_per_cpu_devid(desc))
+                return -EINVAL;
+        chip_bus_lock(desc);
+        retval = __setup_irq(irq, desc, act);
+        chip_bus_sync_unlock(desc);
+
+        return retval;
+}
+
+/**
+ *      request_percpu_irq - allocate a percpu interrupt line
+ *      @irq: Interrupt line to allocate
+ *      @handler: Function to be called when the IRQ occurs.
+ *      @devname: An ascii name for the claiming device
+ *      @dev_id: A percpu cookie passed back to the handler function
+ *
+ *      This call allocates interrupt resources, but doesn't
+ *      automatically enable the interrupt. It has to be done on each
+ *      CPU using enable_percpu_irq().
+ *
+ *      Dev_id must be globally unique. It is a per-cpu variable, and
+ *      the handler gets called with the interrupted CPU's instance of
+ *      that variable.
+ */
+int request_percpu_irq(unsigned int irq, irq_handler_t handler,
+                       const char *devname, void __percpu *dev_id)
+{
+        struct irqaction *action;
+        struct irq_desc *desc;
+        int retval;
+
+        if (!dev_id)
+                return -EINVAL;
+
+        desc = irq_to_desc(irq);
+        if (!desc || !irq_settings_can_request(desc) ||
+            !irq_settings_is_per_cpu_devid(desc))
+                return -EINVAL;
+
+        action = kzalloc(sizeof(struct irqaction), GFP_KERNEL);
+        if (!action)
+                return -ENOMEM;
+
+        action->handler = handler;
+        action->flags = IRQF_PERCPU;
+        action->name = devname;
+        action->percpu_dev_id = dev_id;
+
+        chip_bus_lock(desc);
+        retval = __setup_irq(irq, desc, action);
+        chip_bus_sync_unlock(desc);
+
+        if (retval)
+                kfree(action);
+
+        return retval;
+}
diff --git a/kernel/irq/settings.h b/kernel/irq/settings.h
index f1667833d444..1162f1030f18 100644
--- a/kernel/irq/settings.h
+++ b/kernel/irq/settings.h
@@ -13,6 +13,7 @@ enum {
         _IRQ_MOVE_PCNTXT        = IRQ_MOVE_PCNTXT,
         _IRQ_NO_BALANCING       = IRQ_NO_BALANCING,
         _IRQ_NESTED_THREAD      = IRQ_NESTED_THREAD,
+        _IRQ_PER_CPU_DEVID      = IRQ_PER_CPU_DEVID,
         _IRQF_MODIFY_MASK       = IRQF_MODIFY_MASK,
 };
 
@@ -24,6 +25,7 @@ enum {
 #define IRQ_NOTHREAD            GOT_YOU_MORON
 #define IRQ_NOAUTOEN            GOT_YOU_MORON
 #define IRQ_NESTED_THREAD       GOT_YOU_MORON
+#define IRQ_PER_CPU_DEVID       GOT_YOU_MORON
 #undef IRQF_MODIFY_MASK
 #define IRQF_MODIFY_MASK        GOT_YOU_MORON
 
@@ -39,6 +41,11 @@ static inline bool irq_settings_is_per_cpu(struct irq_desc *desc)
         return desc->status_use_accessors & _IRQ_PER_CPU;
 }
 
+static inline bool irq_settings_is_per_cpu_devid(struct irq_desc *desc)
+{
+        return desc->status_use_accessors & _IRQ_PER_CPU_DEVID;
+}
+
 static inline void irq_settings_set_per_cpu(struct irq_desc *desc)
 {
         desc->status_use_accessors |= _IRQ_PER_CPU;