genirq/debugfs: Add proper debugfs interface

Debugging (hierarchical) interupt domains is tedious as there is no
information about the hierarchy and no information about states of
interrupts in the various domain levels.

Add a debugfs directory 'irq' and subdirectories 'domains' and 'irqs'.

The domains directory contains the domain files. The content is information
about the domain. If the domain is part of a hierarchy then the parent
domains are printed as well.

# ls /sys/kernel/debug/irq/domains/
default     INTEL-IR-2	    INTEL-IR-MSI-2  IO-APIC-IR-2  PCI-MSI
DMAR-MSI    INTEL-IR-3	    INTEL-IR-MSI-3  IO-APIC-IR-3  unknown-1
INTEL-IR-0  INTEL-IR-MSI-0  IO-APIC-IR-0    IO-APIC-IR-4  VECTOR
INTEL-IR-1  INTEL-IR-MSI-1  IO-APIC-IR-1    PCI-HT

# cat /sys/kernel/debug/irq/domains/VECTOR 
name:   VECTOR
 size:   0
 mapped: 216
 flags:  0x00000041

# cat /sys/kernel/debug/irq/domains/IO-APIC-IR-0 
name:   IO-APIC-IR-0
 size:   24
 mapped: 19
 flags:  0x00000041
 parent: INTEL-IR-3
    name:   INTEL-IR-3
     size:   65536
     mapped: 167
     flags:  0x00000041
     parent: VECTOR
        name:   VECTOR
         size:   0
         mapped: 216
         flags:  0x00000041

Unfortunately there is no per cpu information about the VECTOR domain (yet).

The irqs directory contains detailed information about mapped interrupts.

# cat /sys/kernel/debug/irq/irqs/3
handler:  handle_edge_irq
status:   0x00004000
istate:   0x00000000
ddepth:   1
wdepth:   0
dstate:   0x01018000
            IRQD_IRQ_DISABLED
            IRQD_SINGLE_TARGET
            IRQD_MOVE_PCNTXT
node:     0
affinity: 0-143
effectiv: 0
pending:  
domain:  IO-APIC-IR-0
 hwirq:   0x3
 chip:    IR-IO-APIC
  flags:   0x10
             IRQCHIP_SKIP_SET_WAKE
 parent:
    domain:  INTEL-IR-3
     hwirq:   0x20000
     chip:    INTEL-IR
      flags:   0x0
     parent:
        domain:  VECTOR
         hwirq:   0x3
         chip:    APIC
          flags:   0x0

This was developed to simplify the debugging of the managed affinity
changes.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Keith Busch <keith.busch@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Christoph Hellwig <hch@lst.de>
Link: http://lkml.kernel.org/r/20170619235444.537566163@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

include/linux/irqdesc.h

@@ -46,6 +46,7 @@ struct pt_regs;
  * @rcu:		rcu head for delayed free
  * @kobj:		kobject used to represent this struct in sysfs
  * @dir:		/proc/irq/ procfs entry
+ * @debugfs_file:	dentry for the debugfs file
  * @name:		flow handler name for /proc/interrupts output
  */
 struct irq_desc {
@@ -88,6 +89,9 @@ struct irq_desc {
 #ifdef CONFIG_PROC_FS
 	struct proc_dir_entry	*dir;
 #endif
+#ifdef CONFIG_GENERIC_IRQ_DEBUGFS
+	struct dentry		*debugfs_file;
+#endif
 #ifdef CONFIG_SPARSE_IRQ
 	struct rcu_head		rcu;
 	struct kobject		kobj;

include/linux/irqdomain.h

@@ -139,6 +139,7 @@ struct irq_domain_chip_generic;
  *      setting up one or more generic chips for interrupt controllers
  *      drivers using the generic chip library which uses this pointer.
  * @parent: Pointer to parent irq_domain to support hierarchy irq_domains
+ * @debugfs_file: dentry for the domain debugfs file
  *
  * Revmap data, used internally by irq_domain
  * @revmap_direct_max_irq: The largest hwirq that can be set for controllers that
@@ -162,6 +163,9 @@ struct irq_domain {
 #ifdef	CONFIG_IRQ_DOMAIN_HIERARCHY
 	struct irq_domain *parent;
 #endif
+#ifdef CONFIG_GENERIC_IRQ_DEBUGFS
+	struct dentry		*debugfs_file;
+#endif
 
 	/* reverse map data. The linear map gets appended to the irq_domain */
 	irq_hw_number_t hwirq_max;

kernel/irq/Kconfig

@@ -108,4 +108,15 @@ config SPARSE_IRQ
 
 	  If you don't know what to do here, say N.
 
+config GENERIC_IRQ_DEBUGFS
+	bool "Expose irq internals in debugfs"
+	depends on DEBUG_FS
+	default n
+	---help---
+
+	  Exposes internal state information through debugfs. Mostly for
+	  developers and debugging of hard to diagnose interrupt problems.
+
+	  If you don't know what to do here, say N.
+
 endmenu

kernel/irq/Makefile

@@ -10,3 +10,4 @@ obj-$(CONFIG_PM_SLEEP) += pm.o
 obj-$(CONFIG_GENERIC_MSI_IRQ) += msi.o
 obj-$(CONFIG_GENERIC_IRQ_IPI) += ipi.o
 obj-$(CONFIG_SMP) += affinity.o
+obj-$(CONFIG_GENERIC_IRQ_DEBUGFS) += debugfs.o

kernel/irq/debugfs.c

@@ -0,0 +1,215 @@
+/*
+ * Copyright 2017 Thomas Gleixner <tglx@linutronix.de>
+ *
+ * This file is licensed under the GPL V2.
+ */
+#include <linux/debugfs.h>
+#include <linux/irqdomain.h>
+#include <linux/irq.h>
+
+#include "internals.h"
+
+static struct dentry *irq_dir;
+
+struct irq_bit_descr {
+	unsigned int	mask;
+	char		*name;
+};
+#define BIT_MASK_DESCR(m)	{ .mask = m, .name = #m }
+
+static void irq_debug_show_bits(struct seq_file *m, int ind, unsigned int state,
+				const struct irq_bit_descr *sd, int size)
+{
+	int i;
+
+	for (i = 0; i < size; i++, sd++) {
+		if (state & sd->mask)
+			seq_printf(m, "%*s%s\n", ind + 12, "", sd->name);
+	}
+}
+
+#ifdef CONFIG_SMP
+static void irq_debug_show_masks(struct seq_file *m, struct irq_desc *desc)
+{
+	struct irq_data *data = irq_desc_get_irq_data(desc);
+	struct cpumask *msk;
+
+	msk = irq_data_get_affinity_mask(data);
+	seq_printf(m, "affinity: %*pbl\n", cpumask_pr_args(msk));
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+	msk = desc->pending_mask;
+	seq_printf(m, "pending:  %*pbl\n", cpumask_pr_args(msk));
+#endif
+}
+#else
+static void irq_debug_show_masks(struct seq_file *m, struct irq_desc *desc) { }
+#endif
+
+static const struct irq_bit_descr irqchip_flags[] = {
+	BIT_MASK_DESCR(IRQCHIP_SET_TYPE_MASKED),
+	BIT_MASK_DESCR(IRQCHIP_EOI_IF_HANDLED),
+	BIT_MASK_DESCR(IRQCHIP_MASK_ON_SUSPEND),
+	BIT_MASK_DESCR(IRQCHIP_ONOFFLINE_ENABLED),
+	BIT_MASK_DESCR(IRQCHIP_SKIP_SET_WAKE),
+	BIT_MASK_DESCR(IRQCHIP_ONESHOT_SAFE),
+	BIT_MASK_DESCR(IRQCHIP_EOI_THREADED),
+};
+
+static void
+irq_debug_show_chip(struct seq_file *m, struct irq_data *data, int ind)
+{
+	struct irq_chip *chip = data->chip;
+
+	if (!chip) {
+		seq_printf(m, "chip: None\n");
+		return;
+	}
+	seq_printf(m, "%*schip:    %s\n", ind, "", chip->name);
+	seq_printf(m, "%*sflags:   0x%lx\n", ind + 1, "", chip->flags);
+	irq_debug_show_bits(m, ind, chip->flags, irqchip_flags,
+			    ARRAY_SIZE(irqchip_flags));
+}
+
+static void
+irq_debug_show_data(struct seq_file *m, struct irq_data *data, int ind)
+{
+	seq_printf(m, "%*sdomain:  %s\n", ind, "",
+		   data->domain ? data->domain->name : "");
+	seq_printf(m, "%*shwirq:   0x%lx\n", ind + 1, "", data->hwirq);
+	irq_debug_show_chip(m, data, ind + 1);
+#ifdef	CONFIG_IRQ_DOMAIN_HIERARCHY
+	if (!data->parent_data)
+		return;
+	seq_printf(m, "%*sparent:\n", ind + 1, "");
+	irq_debug_show_data(m, data->parent_data, ind + 4);
+#endif
+}
+
+static const struct irq_bit_descr irqdata_states[] = {
+	BIT_MASK_DESCR(IRQ_TYPE_EDGE_RISING),
+	BIT_MASK_DESCR(IRQ_TYPE_EDGE_FALLING),
+	BIT_MASK_DESCR(IRQ_TYPE_LEVEL_HIGH),
+	BIT_MASK_DESCR(IRQ_TYPE_LEVEL_LOW),
+	BIT_MASK_DESCR(IRQD_LEVEL),
+
+	BIT_MASK_DESCR(IRQD_ACTIVATED),
+	BIT_MASK_DESCR(IRQD_IRQ_STARTED),
+	BIT_MASK_DESCR(IRQD_IRQ_DISABLED),
+	BIT_MASK_DESCR(IRQD_IRQ_MASKED),
+	BIT_MASK_DESCR(IRQD_IRQ_INPROGRESS),
+
+	BIT_MASK_DESCR(IRQD_PER_CPU),
+	BIT_MASK_DESCR(IRQD_NO_BALANCING),
+
+	BIT_MASK_DESCR(IRQD_MOVE_PCNTXT),
+	BIT_MASK_DESCR(IRQD_AFFINITY_SET),
+	BIT_MASK_DESCR(IRQD_SETAFFINITY_PENDING),
+	BIT_MASK_DESCR(IRQD_AFFINITY_MANAGED),
+	BIT_MASK_DESCR(IRQD_MANAGED_SHUTDOWN),
+
+	BIT_MASK_DESCR(IRQD_FORWARDED_TO_VCPU),
+
+	BIT_MASK_DESCR(IRQD_WAKEUP_STATE),
+	BIT_MASK_DESCR(IRQD_WAKEUP_ARMED),
+};
+
+static const struct irq_bit_descr irqdesc_states[] = {
+	BIT_MASK_DESCR(_IRQ_NOPROBE),
+	BIT_MASK_DESCR(_IRQ_NOREQUEST),
+	BIT_MASK_DESCR(_IRQ_NOTHREAD),
+	BIT_MASK_DESCR(_IRQ_NOAUTOEN),
+	BIT_MASK_DESCR(_IRQ_NESTED_THREAD),
+	BIT_MASK_DESCR(_IRQ_PER_CPU_DEVID),
+	BIT_MASK_DESCR(_IRQ_IS_POLLED),
+	BIT_MASK_DESCR(_IRQ_DISABLE_UNLAZY),
+};
+
+static const struct irq_bit_descr irqdesc_istates[] = {
+	BIT_MASK_DESCR(IRQS_AUTODETECT),
+	BIT_MASK_DESCR(IRQS_SPURIOUS_DISABLED),
+	BIT_MASK_DESCR(IRQS_POLL_INPROGRESS),
+	BIT_MASK_DESCR(IRQS_ONESHOT),
+	BIT_MASK_DESCR(IRQS_REPLAY),
+	BIT_MASK_DESCR(IRQS_WAITING),
+	BIT_MASK_DESCR(IRQS_PENDING),
+	BIT_MASK_DESCR(IRQS_SUSPENDED),
+};
+
+
+static int irq_debug_show(struct seq_file *m, void *p)
+{
+	struct irq_desc *desc = m->private;
+	struct irq_data *data;
+
+	raw_spin_lock_irq(&desc->lock);
+	data = irq_desc_get_irq_data(desc);
+	seq_printf(m, "handler:  %pf\n", desc->handle_irq);
+	seq_printf(m, "status:   0x%08x\n", desc->status_use_accessors);
+	irq_debug_show_bits(m, 0, desc->status_use_accessors, irqdesc_states,
+			    ARRAY_SIZE(irqdesc_states));
+	seq_printf(m, "istate:   0x%08x\n", desc->istate);
+	irq_debug_show_bits(m, 0, desc->istate, irqdesc_istates,
+			    ARRAY_SIZE(irqdesc_istates));
+	seq_printf(m, "ddepth:   %u\n", desc->depth);
+	seq_printf(m, "wdepth:   %u\n", desc->wake_depth);
+	seq_printf(m, "dstate:   0x%08x\n", irqd_get(data));
+	irq_debug_show_bits(m, 0, irqd_get(data), irqdata_states,
+			    ARRAY_SIZE(irqdata_states));
+	seq_printf(m, "node:     %d\n", irq_data_get_node(data));
+	irq_debug_show_masks(m, desc);
+	irq_debug_show_data(m, data, 0);
+	raw_spin_unlock_irq(&desc->lock);
+	return 0;
+}
+
+static int irq_debug_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, irq_debug_show, inode->i_private);
+}
+
+static const struct file_operations dfs_irq_ops = {
+	.open		= irq_debug_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+void irq_add_debugfs_entry(unsigned int irq, struct irq_desc *desc)
+{
+	char name [10];
+
+	if (!irq_dir || !desc || desc->debugfs_file)
+		return;
+
+	sprintf(name, "%d", irq);
+	desc->debugfs_file = debugfs_create_file(name, 0444, irq_dir, desc,
+						 &dfs_irq_ops);
+}
+
+void irq_remove_debugfs_entry(struct irq_desc *desc)
+{
+	if (desc->debugfs_file)
+		debugfs_remove(desc->debugfs_file);
+}
+
+static int __init irq_debugfs_init(void)
+{
+	struct dentry *root_dir;
+	int irq;
+
+	root_dir = debugfs_create_dir("irq", NULL);
+	if (!root_dir)
+		return -ENOMEM;
+
+	irq_domain_debugfs_init(root_dir);
+
+	irq_dir = debugfs_create_dir("irqs", root_dir);
+
+	irq_lock_sparse();
+	for_each_active_irq(irq)
+		irq_add_debugfs_entry(irq, irq_to_desc(irq));
+	irq_unlock_sparse();
+
+	return 0;
+}
+__initcall(irq_debugfs_init);

kernel/irq/internals.h

@@ -169,6 +169,11 @@ irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags)
 
 #define __irqd_to_state(d) ACCESS_PRIVATE((d)->common, state_use_accessors)
 
+static inline unsigned int irqd_get(struct irq_data *d)
+{
+	return __irqd_to_state(d);
+}
+
 /*
  * Manipulation functions for irq_data.state
  */
@@ -237,3 +242,20 @@ irq_init_generic_chip(struct irq_chip_generic *gc, const char *name,
 		      int num_ct, unsigned int irq_base,
 		      void __iomem *reg_base, irq_flow_handler_t handler) { }
 #endif /* CONFIG_GENERIC_IRQ_CHIP */
+
+#ifdef CONFIG_GENERIC_IRQ_DEBUGFS
+void irq_add_debugfs_entry(unsigned int irq, struct irq_desc *desc);
+void irq_remove_debugfs_entry(struct irq_desc *desc);
+# ifdef CONFIG_IRQ_DOMAIN
+void irq_domain_debugfs_init(struct dentry *root);
+# else
+static inline void irq_domain_debugfs_init(struct dentry *root);
+# endif
+#else /* CONFIG_GENERIC_IRQ_DEBUGFS */
+static inline void irq_add_debugfs_entry(unsigned int irq, struct irq_desc *d)
+{
+}
+static inline void irq_remove_debugfs_entry(struct irq_desc *d)
+{
+}
+#endif /* CONFIG_GENERIC_IRQ_DEBUGFS */

kernel/irq/irqdesc.c

@@ -394,6 +394,7 @@ static void free_desc(unsigned int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 
+	irq_remove_debugfs_entry(desc);
 	unregister_irq_proc(irq, desc);
 
 	/*