[PATCH v6] genirq: Machine-parsable version of /proc/interrupts

[Craig Gallek]

From: Craig Gallek <kraig@xxxxxxxxxx>

Export struct irq_desc information through sysfs.  The same information
is available in /proc/interrupts but the format of that file has changed
over kernel versions and differs across architectures.  The procfs version
also has varying column numbers depending on hardware.  This sysfs version
exposes each irq attribute in a separate file in a consistent, machine
parsable way.

This feature is only available when both CONFIG_SPARSE_IRQ and
CONFIG_SYSFS are enabled.

Examples:
  /sys/kernel/irq/18/actions:	i801_smbus,ehci_hcd:usb1,uhci_hcd:usb7
  /sys/kernel/irq/18/chip_name:	IR-IO-APIC
  /sys/kernel/irq/18/hwirq:		18
  /sys/kernel/irq/18/name:		fasteoi
  /sys/kernel/irq/18/per_cpu_count:	0,0
  /sys/kernel/irq/18/type:		level

  /sys/kernel/irq/25/actions:	ahci0
  /sys/kernel/irq/25/chip_name:	IR-PCI-MSI
  /sys/kernel/irq/25/hwirq:		512000
  /sys/kernel/irq/25/name:		edge
  /sys/kernel/irq/25/per_cpu_count:	29036,0
  /sys/kernel/irq/25/type:		edge

Signed-off-by: Craig Gallek <kraig@xxxxxxxxxx>
---
v6 changes:
 * Apply suggestions to commit message (moved some of it to code comments).
 * Move kobject in irq_desc to CONFIG_SPARSE_IRQ guard.
 * Consolidate irq_sysfs_init CONFIG_SYSFS guard with earlier guard.
 * Use sparse_irq_lock to protect initial creation/read of irq sysfs
   directory.

v5 changes:
 * Change per_cpu_count: for_each_online_cpu -> for_each_possible_cpu.

v4 changes:
 * Remove modifications to the !CONFIG_SPARSE_IRQ.
 * Include note in documentation wrt per-cpu interrupt counters and
   offline CPUs.

v3 changes:
 * Add some examples to the commit message and an ABI documentation file.
 * Fix spelling mistake.

v2 changes:
 * Several suggested stylistic changes.
 * Fix one NULL pointer dereference possibility.
 * Do not destroy kobjects in non-SPARSE_IRQ configuration.
 * Include #define CONFIG_SYSFS guards to selectively enable feature.

 Documentation/ABI/testing/sysfs-kernel-irq |  53 ++++++++
 include/linux/irqdesc.h                    |   3 +
 kernel/irq/irqdesc.c                       | 188 ++++++++++++++++++++++++++++-
 3 files changed, 242 insertions(+), 2 deletions(-)
 create mode 100644 Documentation/ABI/testing/sysfs-kernel-irq

diff --git a/Documentation/ABI/testing/sysfs-kernel-irq b/Documentation/ABI/testing/sysfs-kernel-irq
new file mode 100644
index 000000000000..f96a8f271b6e
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-kernel-irq
@@ -0,0 +1,53 @@
+What:		/sys/kernel/irq
+Date:		September 2016
+KernelVersion:	4.9
+Contact:	Craig Gallek <kraig@xxxxxxxxxx>
+Description:	Directory containing information about the system's IRQs.
+		Specifically, data from the associated struct irq_desc.
+		The information here is similar to that in /proc/interrupts
+		but in a more machine-friendly format.  This directory contains
+		one subdirectory for each Linux IRQ number.
+
+What:		/sys/kernel/irq/<irq>/actions
+Date:		September 2016
+KernelVersion:	4.9
+Contact:	Craig Gallek <kraig@xxxxxxxxxx>
+Description:	The IRQ action chain.  A comma-separated list of zero or more
+		device names associated with this interrupt.
+
+What:		/sys/kernel/irq/<irq>/chip_name
+Date:		September 2016
+KernelVersion:	4.9
+Contact:	Craig Gallek <kraig@xxxxxxxxxx>
+Description:	Human-readable chip name supplied by the associated device
+		driver.
+
+What:		/sys/kernel/irq/<irq>/hwirq
+Date:		September 2016
+KernelVersion:	4.9
+Contact:	Craig Gallek <kraig@xxxxxxxxxx>
+Description:	When interrupt translation domains are used, this file contains
+		the underlying hardware IRQ number used for this Linux IRQ.
+
+What:		/sys/kernel/irq/<irq>/name
+Date:		September 2016
+KernelVersion:	4.9
+Contact:	Craig Gallek <kraig@xxxxxxxxxx>
+Description:	Human-readable flow handler name as defined by the device
+		driver.
+
+What:		/sys/kernel/irq/<irq>/per_cpu_count
+Date:		September 2016
+KernelVersion:	4.9
+Contact:	Craig Gallek <kraig@xxxxxxxxxx>
+Description:	The number of times the interrupt has fired since boot.  This
+		is a comma-separated list of counters; one per CPU in CPU id
+		order.  NOTE: This file consistently shows counters for all
+		CPU ids.  This differs from the behavior of /proc/interrupts
+		which only shows counters for online CPUs.
+
+What:		/sys/kernel/irq/<irq>/type
+Date:		September 2016
+KernelVersion:	4.9
+Contact:	Craig Gallek <kraig@xxxxxxxxxx>
+Description:	The type of the interrupt.  Either the string 'level' or 'edge'.
diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index b51beebf9804..c9be57931b58 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -2,6 +2,7 @@
 #define _LINUX_IRQDESC_H
 
 #include <linux/rcupdate.h>
+#include <linux/kobject.h>
 
 /*
  * Core internal functions to deal with irq descriptors
@@ -43,6 +44,7 @@ struct pt_regs;
  * @force_resume_depth:	number of irqactions on a irq descriptor with
  *			IRQF_FORCE_RESUME set
  * @rcu:		rcu head for delayed free
+ * @kobj:		kobject used to represent this struct in sysfs
  * @dir:		/proc/irq/ procfs entry
  * @name:		flow handler name for /proc/interrupts output
  */
@@ -88,6 +90,7 @@ struct irq_desc {
 #endif
 #ifdef CONFIG_SPARSE_IRQ
 	struct rcu_head		rcu;
+	struct kobject		kobj;
 #endif
 	int			parent_irq;
 	struct module		*owner;
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index a623b44f2d4b..64bbd696686f 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -15,6 +15,7 @@
 #include <linux/radix-tree.h>
 #include <linux/bitmap.h>
 #include <linux/irqdomain.h>
+#include <linux/sysfs.h>
 
 #include "internals.h"
 
@@ -123,6 +124,179 @@ static DECLARE_BITMAP(allocated_irqs, IRQ_BITMAP_BITS);
 
 #ifdef CONFIG_SPARSE_IRQ
 
+static void irq_kobj_release(struct kobject *kobj);
+
+#ifdef CONFIG_SYSFS
+static struct kobject *irq_kobj_base;
+
+#define IRQ_ATTR_RO(_name) \
+static struct kobj_attribute _name##_attr = __ATTR_RO(_name)
+
+static ssize_t per_cpu_count_show(struct kobject *kobj,
+				  struct kobj_attribute *attr, char *buf)
+{
+	struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj);
+	int cpu, irq = desc->irq_data.irq;
+	ssize_t ret = 0;
+	char *p = "";
+
+	for_each_possible_cpu(cpu) {
+		unsigned int c = kstat_irqs_cpu(irq, cpu);
+
+		ret += scnprintf(buf + ret, PAGE_SIZE - ret, "%s%u", p, c);
+		p = ",";
+	}
+
+	ret += scnprintf(buf + ret, PAGE_SIZE - ret, "\n");
+	return ret;
+}
+IRQ_ATTR_RO(per_cpu_count);
+
+static ssize_t chip_name_show(struct kobject *kobj,
+			      struct kobj_attribute *attr, char *buf)
+{
+	struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj);
+	ssize_t ret = 0;
+
+	raw_spin_lock_irq(&desc->lock);
+	if (desc->irq_data.chip && desc->irq_data.chip->name) {
+		ret = scnprintf(buf, PAGE_SIZE, "%s\n",
+				desc->irq_data.chip->name);
+	}
+	raw_spin_unlock_irq(&desc->lock);
+
+	return ret;
+}
+IRQ_ATTR_RO(chip_name);
+
+static ssize_t hwirq_show(struct kobject *kobj,
+			  struct kobj_attribute *attr, char *buf)
+{
+	struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj);
+	ssize_t ret = 0;
+
+	raw_spin_lock_irq(&desc->lock);
+	if (desc->irq_data.domain)
+		ret = sprintf(buf, "%d\n", (int)desc->irq_data.hwirq);
+	raw_spin_unlock_irq(&desc->lock);
+
+	return ret;
+}
+IRQ_ATTR_RO(hwirq);
+
+static ssize_t type_show(struct kobject *kobj,
+			 struct kobj_attribute *attr, char *buf)
+{
+	struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj);
+	ssize_t ret = 0;
+
+	raw_spin_lock_irq(&desc->lock);
+	ret = sprintf(buf, "%s\n",
+		      irqd_is_level_type(&desc->irq_data) ? "level" : "edge");
+	raw_spin_unlock_irq(&desc->lock);
+
+	return ret;
+
+}
+IRQ_ATTR_RO(type);
+
+static ssize_t name_show(struct kobject *kobj,
+			 struct kobj_attribute *attr, char *buf)
+{
+	struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj);
+	ssize_t ret = 0;
+
+	raw_spin_lock_irq(&desc->lock);
+	if (desc->name)
+		ret = scnprintf(buf, PAGE_SIZE, "%s\n", desc->name);
+	raw_spin_unlock_irq(&desc->lock);
+
+	return ret;
+}
+IRQ_ATTR_RO(name);
+
+static ssize_t actions_show(struct kobject *kobj,
+			    struct kobj_attribute *attr, char *buf)
+{
+	struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj);
+	struct irqaction *action;
+	ssize_t ret = 0;
+	char *p = "";
+
+	raw_spin_lock_irq(&desc->lock);
+	for (action = desc->action; action != NULL; action = action->next) {
+		ret += scnprintf(buf + ret, PAGE_SIZE - ret, "%s%s",
+				 p, action->name);
+		p = ",";
+	}
+	raw_spin_unlock_irq(&desc->lock);
+
+	if (ret)
+		ret += scnprintf(buf + ret, PAGE_SIZE - ret, "\n");
+
+	return ret;
+}
+IRQ_ATTR_RO(actions);
+
+static struct attribute *irq_attrs[] = {
+	&per_cpu_count_attr.attr,
+	&chip_name_attr.attr,
+	&hwirq_attr.attr,
+	&type_attr.attr,
+	&name_attr.attr,
+	&actions_attr.attr,
+	NULL
+};
+
+static struct kobj_type irq_kobj_type = {
+	.release	= irq_kobj_release,
+	.sysfs_ops	= &kobj_sysfs_ops,
+	.default_attrs	= irq_attrs,
+};
+
+static void irq_sysfs_add(int irq, struct irq_desc *desc)
+{
+	if (irq_kobj_base) {
+		if (kobject_add(&desc->kobj, irq_kobj_base, "%d", irq))
+			pr_warn("Failed to add kobject for irq %d\n", irq);
+	}
+}
+
+static int __init irq_sysfs_init(void)
+{
+	struct irq_desc *desc;
+	int irq;
+
+	irq_lock_sparse();
+	irq_kobj_base = kobject_create_and_add("irq", kernel_kobj);
+	if (!irq_kobj_base) {
+		irq_unlock_sparse();
+		return -ENOMEM;
+	}
+
+	/*
+	 * Here we catch any interrupts which were added during early_irq_init
+	 * before the sysfs subsystem was available and we add them to our
+	 * newly created sysfs irq directory.
+	 */
+	for_each_irq_desc(irq, desc)
+		irq_sysfs_add(irq, desc);
+	irq_unlock_sparse();
+
+	return 0;
+}
+postcore_initcall(irq_sysfs_init);
+
+#else /* !CONFIG_SYSFS */
+
+static struct kobj_type irq_kobj_type = {
+	.release	= irq_kobj_release,
+};
+
+static void irq_sysfs_add(int irq, struct irq_desc *desc) {}
+
+#endif /* CONFIG_SYSFS */
+
 static RADIX_TREE(irq_desc_tree, GFP_KERNEL);
 
 static void irq_insert_desc(unsigned int irq, struct irq_desc *desc)
@@ -187,6 +361,7 @@ static struct irq_desc *alloc_desc(int irq, int node, unsigned int flags,
 
 	desc_set_defaults(irq, desc, node, affinity, owner);
 	irqd_set(&desc->irq_data, flags);
+	kobject_init(&desc->kobj, &irq_kobj_type);
 
 	return desc;
 
@@ -197,20 +372,28 @@ err_desc:
 	return NULL;
 }
 
-static void delayed_free_desc(struct rcu_head *rhp)
+static void irq_kobj_release(struct kobject *kobj)
 {
-	struct irq_desc *desc = container_of(rhp, struct irq_desc, rcu);
+	struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj);
 
 	free_masks(desc);
 	free_percpu(desc->kstat_irqs);
 	kfree(desc);
 }
 
+static void delayed_free_desc(struct rcu_head *rhp)
+{
+	struct irq_desc *desc = container_of(rhp, struct irq_desc, rcu);
+
+	kobject_put(&desc->kobj);
+}
+
 static void free_desc(unsigned int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 
 	unregister_irq_proc(irq, desc);
+	kobject_del(&desc->kobj);
 
 	/*
 	 * sparse_irq_lock protects also show_interrupts() and
@@ -261,6 +444,7 @@ static int alloc_descs(unsigned int start, unsigned int cnt, int node,
 			goto err;
 		mutex_lock(&sparse_irq_lock);
 		irq_insert_desc(start + i, desc);
+		irq_sysfs_add(start + i, desc);
 		mutex_unlock(&sparse_irq_lock);
 	}
 	return start;
-- 
2.8.0.rc3.226.g39d4020