1 files changed, 202 insertions, 161 deletions

diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 36f6ee181b0c..77258eafbf63 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -1,6 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
- * linux/kernel/irq/proc.c
- *
  * Copyright (C) 1992, 1998-2004 Linus Torvalds, Ingo Molnar
  *
  * This file contains the /proc/irq/ handling code.
@@ -12,78 +11,138 @@
 #include <linux/seq_file.h>
 #include <linux/interrupt.h>
 #include <linux/kernel_stat.h>
+#include <linux/mutex.h>
 
 #include "internals.h"
 
+/*
+ * Access rules:
+ *
+ * procfs protects read/write of /proc/irq/N/ files against a
+ * concurrent free of the interrupt descriptor. remove_proc_entry()
+ * immediately prevents new read/writes to happen and waits for
+ * already running read/write functions to complete.
+ *
+ * We remove the proc entries first and then delete the interrupt
+ * descriptor from the radix tree and free it. So it is guaranteed
+ * that irq_to_desc(N) is valid as long as the read/writes are
+ * permitted by procfs.
+ *
+ * The read from /proc/interrupts is a different problem because there
+ * is no protection. So the lookup and the access to irqdesc
+ * information must be protected by sparse_irq_lock.
+ */
 static struct proc_dir_entry *root_irq_dir;
 
 #ifdef CONFIG_SMP
 
-static int show_irq_affinity(int type, struct seq_file *m, void *v)
+enum {
+	AFFINITY,
+	AFFINITY_LIST,
+	EFFECTIVE,
+	EFFECTIVE_LIST,
+};
+
+static int show_irq_affinity(int type, struct seq_file *m)
 {
 	struct irq_desc *desc = irq_to_desc((long)m->private);
-	const struct cpumask *mask = desc->irq_data.affinity;
-
-#ifdef CONFIG_GENERIC_PENDING_IRQ
-	if (irqd_is_setaffinity_pending(&desc->irq_data))
-		mask = desc->pending_mask;
+	const struct cpumask *mask;
+
+	guard(raw_spinlock_irq)(&desc->lock);
+
+	switch (type) {
+	case AFFINITY:
+	case AFFINITY_LIST:
+		mask = desc->irq_common_data.affinity;
+		if (irq_move_pending(&desc->irq_data))
+			mask = irq_desc_get_pending_mask(desc);
+		break;
+	case EFFECTIVE:
+	case EFFECTIVE_LIST:
+#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK
+		mask = irq_data_get_effective_affinity_mask(&desc->irq_data);
+		break;
 #endif
-	if (type)
-		seq_cpumask_list(m, mask);
-	else
-		seq_cpumask(m, mask);
-	seq_putc(m, '\n');
+	default:
+		return -EINVAL;
+	}
+
+	switch (type) {
+	case AFFINITY_LIST:
+	case EFFECTIVE_LIST:
+		seq_printf(m, "%*pbl\n", cpumask_pr_args(mask));
+		break;
+	case AFFINITY:
+	case EFFECTIVE:
+		seq_printf(m, "%*pb\n", cpumask_pr_args(mask));
+		break;
+	}
 	return 0;
 }
 
 static int irq_affinity_hint_proc_show(struct seq_file *m, void *v)
 {
 	struct irq_desc *desc = irq_to_desc((long)m->private);
-	unsigned long flags;
 	cpumask_var_t mask;
 
 	if (!zalloc_cpumask_var(&mask, GFP_KERNEL))
 		return -ENOMEM;
 
-	raw_spin_lock_irqsave(&desc->lock, flags);
-	if (desc->affinity_hint)
-		cpumask_copy(mask, desc->affinity_hint);
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
+	scoped_guard(raw_spinlock_irq, &desc->lock) {
+		if (desc->affinity_hint)
+			cpumask_copy(mask, desc->affinity_hint);
+	}
 
-	seq_cpumask(m, mask);
-	seq_putc(m, '\n');
+	seq_printf(m, "%*pb\n", cpumask_pr_args(mask));
 	free_cpumask_var(mask);
-
 	return 0;
 }
 
-#ifndef is_affinity_mask_valid
-#define is_affinity_mask_valid(val) 1
-#endif
-
 int no_irq_affinity;
 static int irq_affinity_proc_show(struct seq_file *m, void *v)
 {
-	return show_irq_affinity(0, m, v);
+	return show_irq_affinity(AFFINITY, m);
 }
 
 static int irq_affinity_list_proc_show(struct seq_file *m, void *v)
 {
-	return show_irq_affinity(1, m, v);
+	return show_irq_affinity(AFFINITY_LIST, m);
 }
 
+#ifndef CONFIG_AUTO_IRQ_AFFINITY
+static inline int irq_select_affinity_usr(unsigned int irq)
+{
+	/*
+	 * If the interrupt is started up already then this fails. The
+	 * interrupt is assigned to an online CPU already. There is no
+	 * point to move it around randomly. Tell user space that the
+	 * selected mask is bogus.
+	 *
+	 * If not then any change to the affinity is pointless because the
+	 * startup code invokes irq_setup_affinity() which will select
+	 * a online CPU anyway.
+	 */
+	return -EINVAL;
+}
+#else
+/* ALPHA magic affinity auto selector. Keep it for historical reasons. */
+static inline int irq_select_affinity_usr(unsigned int irq)
+{
+	return irq_select_affinity(irq);
+}
+#endif
 
 static ssize_t write_irq_affinity(int type, struct file *file,
 		const char __user *buffer, size_t count, loff_t *pos)
 {
-	unsigned int irq = (int)(long)PDE_DATA(file_inode(file));
+	unsigned int irq = (int)(long)pde_data(file_inode(file));
 	cpumask_var_t new_value;
 	int err;
 
-	if (!irq_can_set_affinity(irq) || no_irq_affinity)
-		return -EIO;
+	if (!irq_can_set_affinity_usr(irq) || no_irq_affinity)
+		return -EPERM;
 
-	if (!alloc_cpumask_var(&new_value, GFP_KERNEL))
+	if (!zalloc_cpumask_var(&new_value, GFP_KERNEL))
 		return -ENOMEM;
 
 	if (type)
@@ -93,23 +152,21 @@ static ssize_t write_irq_affinity(int type, struct file *file,
 	if (err)
 		goto free_cpumask;
 
-	if (!is_affinity_mask_valid(new_value)) {
-		err = -EINVAL;
-		goto free_cpumask;
-	}
-
 	/*
 	 * Do not allow disabling IRQs completely - it's a too easy
 	 * way to make the system unusable accidentally :-) At least
 	 * one online CPU still has to be targeted.
 	 */
 	if (!cpumask_intersects(new_value, cpu_online_mask)) {
-		/* Special case for empty set - allow the architecture
-		   code to set default SMP affinity. */
-		err = irq_select_affinity_usr(irq, new_value) ? -EINVAL : count;
+		/*
+		 * Special case for empty set - allow the architecture code
+		 * to set default SMP affinity.
+		 */
+		err = irq_select_affinity_usr(irq) ? -EINVAL : count;
 	} else {
-		irq_set_affinity(irq, new_value);
-		err = count;
+		err = irq_set_affinity(irq, new_value);
+		if (!err)
+			err = count;
 	}
 
 free_cpumask:
@@ -131,46 +188,45 @@ static ssize_t irq_affinity_list_proc_write(struct file *file,
 
 static int irq_affinity_proc_open(struct inode *inode, struct file *file)
 {
-	return single_open(file, irq_affinity_proc_show, PDE_DATA(inode));
+	return single_open(file, irq_affinity_proc_show, pde_data(inode));
 }
 
 static int irq_affinity_list_proc_open(struct inode *inode, struct file *file)
 {
-	return single_open(file, irq_affinity_list_proc_show, PDE_DATA(inode));
-}
-
-static int irq_affinity_hint_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, irq_affinity_hint_proc_show, PDE_DATA(inode));
+	return single_open(file, irq_affinity_list_proc_show, pde_data(inode));
 }
 
-static const struct file_operations irq_affinity_proc_fops = {
-	.open		= irq_affinity_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= irq_affinity_proc_write,
+static const struct proc_ops irq_affinity_proc_ops = {
+	.proc_open	= irq_affinity_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= irq_affinity_proc_write,
 };
 
-static const struct file_operations irq_affinity_hint_proc_fops = {
-	.open		= irq_affinity_hint_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
+static const struct proc_ops irq_affinity_list_proc_ops = {
+	.proc_open	= irq_affinity_list_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= irq_affinity_list_proc_write,
 };
 
-static const struct file_operations irq_affinity_list_proc_fops = {
-	.open		= irq_affinity_list_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= irq_affinity_list_proc_write,
-};
+#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK
+static int irq_effective_aff_proc_show(struct seq_file *m, void *v)
+{
+	return show_irq_affinity(EFFECTIVE, m);
+}
+
+static int irq_effective_aff_list_proc_show(struct seq_file *m, void *v)
+{
+	return show_irq_affinity(EFFECTIVE_LIST, m);
+}
+#endif
 
 static int default_affinity_show(struct seq_file *m, void *v)
 {
-	seq_cpumask(m, irq_default_affinity);
-	seq_putc(m, '\n');
+	seq_printf(m, "%*pb\n", cpumask_pr_args(irq_default_affinity));
 	return 0;
 }
 
@@ -180,18 +236,13 @@ static ssize_t default_affinity_write(struct file *file,
 	cpumask_var_t new_value;
 	int err;
 
-	if (!alloc_cpumask_var(&new_value, GFP_KERNEL))
+	if (!zalloc_cpumask_var(&new_value, GFP_KERNEL))
 		return -ENOMEM;
 
 	err = cpumask_parse_user(buffer, count, new_value);
 	if (err)
 		goto out;
 
-	if (!is_affinity_mask_valid(new_value)) {
-		err = -EINVAL;
-		goto out;
-	}
-
 	/*
 	 * Do not allow disabling IRQs completely - it's a too easy
 	 * way to make the system unusable accidentally :-) At least
@@ -212,36 +263,24 @@ out:
 
 static int default_affinity_open(struct inode *inode, struct file *file)
 {
-	return single_open(file, default_affinity_show, PDE_DATA(inode));
+	return single_open(file, default_affinity_show, pde_data(inode));
 }
 
-static const struct file_operations default_affinity_proc_fops = {
-	.open		= default_affinity_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= default_affinity_write,
+static const struct proc_ops default_affinity_proc_ops = {
+	.proc_open	= default_affinity_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= default_affinity_write,
 };
 
 static int irq_node_proc_show(struct seq_file *m, void *v)
 {
 	struct irq_desc *desc = irq_to_desc((long) m->private);
 
-	seq_printf(m, "%d\n", desc->irq_data.node);
+	seq_printf(m, "%d\n", irq_desc_get_node(desc));
 	return 0;
 }
-
-static int irq_node_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, irq_node_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations irq_node_proc_fops = {
-	.open		= irq_node_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
 #endif
 
 static int irq_spurious_proc_show(struct seq_file *m, void *v)
@@ -254,49 +293,30 @@ static int irq_spurious_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int irq_spurious_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, irq_spurious_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations irq_spurious_proc_fops = {
-	.open		= irq_spurious_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 #define MAX_NAMELEN 128
 
-static int name_unique(unsigned int irq, struct irqaction *new_action)
+static bool name_unique(unsigned int irq, struct irqaction *new_action)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	struct irqaction *action;
-	unsigned long flags;
-	int ret = 1;
 
-	raw_spin_lock_irqsave(&desc->lock, flags);
-	for (action = desc->action ; action; action = action->next) {
+	guard(raw_spinlock_irq)(&desc->lock);
+	for_each_action_of_desc(desc, action) {
 		if ((action != new_action) && action->name &&
-				!strcmp(new_action->name, action->name)) {
-			ret = 0;
-			break;
-		}
+		    !strcmp(new_action->name, action->name))
+			return false;
 	}
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
-	return ret;
+	return true;
 }
 
 void register_handler_proc(unsigned int irq, struct irqaction *action)
 {
-	char name [MAX_NAMELEN];
+	char name[MAX_NAMELEN];
 	struct irq_desc *desc = irq_to_desc(irq);
 
-	if (!desc->dir || action->dir || !action->name ||
-					!name_unique(irq, action))
+	if (!desc->dir || action->dir || !action->name || !name_unique(irq, action))
 		return;
 
-	memset(name, 0, MAX_NAMELEN);
 	snprintf(name, MAX_NAMELEN, "%s", action->name);
 
 	/* create /proc/irq/1234/handler/ */
@@ -309,38 +329,57 @@ void register_handler_proc(unsigned int irq, struct irqaction *action)
 
 void register_irq_proc(unsigned int irq, struct irq_desc *desc)
 {
+	static DEFINE_MUTEX(register_lock);
+	void __maybe_unused *irqp = (void *)(unsigned long) irq;
 	char name [MAX_NAMELEN];
 
-	if (!root_irq_dir || (desc->irq_data.chip == &no_irq_chip) || desc->dir)
+	if (!root_irq_dir || (desc->irq_data.chip == &no_irq_chip))
 		return;
 
-	memset(name, 0, MAX_NAMELEN);
-	sprintf(name, "%d", irq);
+	/*
+	 * irq directories are registered only when a handler is
+	 * added, not when the descriptor is created, so multiple
+	 * tasks might try to register at the same time.
+	 */
+	guard(mutex)(&register_lock);
+
+	if (desc->dir)
+		return;
 
 	/* create /proc/irq/1234 */
+	sprintf(name, "%u", irq);
 	desc->dir = proc_mkdir(name, root_irq_dir);
 	if (!desc->dir)
 		return;
 
 #ifdef CONFIG_SMP
+	umode_t umode = S_IRUGO;
+
+	if (irq_can_set_affinity_usr(desc->irq_data.irq))
+		umode |= S_IWUSR;
+
 	/* create /proc/irq/<irq>/smp_affinity */
-	proc_create_data("smp_affinity", 0600, desc->dir,
-			 &irq_affinity_proc_fops, (void *)(long)irq);
+	proc_create_data("smp_affinity", umode, desc->dir, &irq_affinity_proc_ops, irqp);
 
 	/* create /proc/irq/<irq>/affinity_hint */
-	proc_create_data("affinity_hint", 0400, desc->dir,
-			 &irq_affinity_hint_proc_fops, (void *)(long)irq);
+	proc_create_single_data("affinity_hint", 0444, desc->dir,
+				irq_affinity_hint_proc_show, irqp);
 
 	/* create /proc/irq/<irq>/smp_affinity_list */
-	proc_create_data("smp_affinity_list", 0600, desc->dir,
-			 &irq_affinity_list_proc_fops, (void *)(long)irq);
-
-	proc_create_data("node", 0444, desc->dir,
-			 &irq_node_proc_fops, (void *)(long)irq);
+	proc_create_data("smp_affinity_list", umode, desc->dir,
+			 &irq_affinity_list_proc_ops, irqp);
+
+	proc_create_single_data("node", 0444, desc->dir, irq_node_proc_show, irqp);
+# ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK
+	proc_create_single_data("effective_affinity", 0444, desc->dir,
+				irq_effective_aff_proc_show, irqp);
+	proc_create_single_data("effective_affinity_list", 0444, desc->dir,
+				irq_effective_aff_list_proc_show, irqp);
+# endif
 #endif
+	proc_create_single_data("spurious", 0444, desc->dir,
+				irq_spurious_proc_show, (void *)(long)irq);
 
-	proc_create_data("spurious", 0444, desc->dir,
-			 &irq_spurious_proc_fops, (void *)(long)irq);
 }
 
 void unregister_irq_proc(unsigned int irq, struct irq_desc *desc)
@@ -354,10 +393,13 @@ void unregister_irq_proc(unsigned int irq, struct irq_desc *desc)
 	remove_proc_entry("affinity_hint", desc->dir);
 	remove_proc_entry("smp_affinity_list", desc->dir);
 	remove_proc_entry("node", desc->dir);
+# ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK
+	remove_proc_entry("effective_affinity", desc->dir);
+	remove_proc_entry("effective_affinity_list", desc->dir);
+# endif
 #endif
 	remove_proc_entry("spurious", desc->dir);
 
-	memset(name, 0, MAX_NAMELEN);
 	sprintf(name, "%u", irq);
 	remove_proc_entry(name, root_irq_dir);
 }
@@ -372,8 +414,8 @@ void unregister_handler_proc(unsigned int irq, struct irqaction *action)
 static void register_default_affinity_proc(void)
 {
 #ifdef CONFIG_SMP
-	proc_create("irq/default_smp_affinity", 0600, NULL,
-		    &default_affinity_proc_fops);
+	proc_create("irq/default_smp_affinity", 0644, NULL,
+		    &default_affinity_proc_ops);
 #endif
 }
 
@@ -392,12 +434,8 @@ void init_irq_proc(void)
 	/*
 	 * Create entries for all existing IRQs.
 	 */
-	for_each_irq_desc(irq, desc) {
-		if (!desc)
-			continue;
-
+	for_each_irq_desc(irq, desc)
 		register_irq_proc(irq, desc);
-	}
 }
 
 #ifdef CONFIG_GENERIC_IRQ_SHOW
@@ -408,14 +446,14 @@ int __weak arch_show_interrupts(struct seq_file *p, int prec)
 }
 
 #ifndef ACTUAL_NR_IRQS
-# define ACTUAL_NR_IRQS nr_irqs
+# define ACTUAL_NR_IRQS irq_get_nr_irqs()
 #endif
 
 int show_interrupts(struct seq_file *p, void *v)
 {
+	const unsigned int nr_irqs = irq_get_nr_irqs();
 	static int prec;
 
-	unsigned long flags, any_count = 0;
 	int i = *(loff_t *) v, j;
 	struct irqaction *action;
 	struct irq_desc *desc;
@@ -437,39 +475,44 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_putc(p, '\n');
 	}
 
+	guard(rcu)();
 	desc = irq_to_desc(i);
-	if (!desc)
+	if (!desc || irq_settings_is_hidden(desc))
 		return 0;
 
-	raw_spin_lock_irqsave(&desc->lock, flags);
-	for_each_online_cpu(j)
-		any_count |= kstat_irqs_cpu(i, j);
-	action = desc->action;
-	if (!action && !any_count)
-		goto out;
+	if (!desc->action || irq_desc_is_chained(desc) || !desc->kstat_irqs)
+		return 0;
 
-	seq_printf(p, "%*d: ", prec, i);
-	for_each_online_cpu(j)
-		seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
+	seq_printf(p, "%*d:", prec, i);
+	for_each_online_cpu(j) {
+		unsigned int cnt = desc->kstat_irqs ? per_cpu(desc->kstat_irqs->cnt, j) : 0;
 
+		seq_put_decimal_ull_width(p, " ", cnt, 10);
+	}
+	seq_putc(p, ' ');
+
+	guard(raw_spinlock_irq)(&desc->lock);
 	if (desc->irq_data.chip) {
 		if (desc->irq_data.chip->irq_print_chip)
 			desc->irq_data.chip->irq_print_chip(&desc->irq_data, p);
 		else if (desc->irq_data.chip->name)
-			seq_printf(p, " %8s", desc->irq_data.chip->name);
+			seq_printf(p, "%8s", desc->irq_data.chip->name);
 		else
-			seq_printf(p, " %8s", "-");
+			seq_printf(p, "%8s", "-");
 	} else {
-		seq_printf(p, " %8s", "None");
+		seq_printf(p, "%8s", "None");
 	}
 	if (desc->irq_data.domain)
-		seq_printf(p, " %*d", prec, (int) desc->irq_data.hwirq);
+		seq_printf(p, " %*lu", prec, desc->irq_data.hwirq);
+	else
+		seq_printf(p, " %*s", prec, "");
 #ifdef CONFIG_GENERIC_IRQ_SHOW_LEVEL
 	seq_printf(p, " %-8s", irqd_is_level_type(&desc->irq_data) ? "Level" : "Edge");
 #endif
 	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)
@@ -477,8 +520,6 @@ int show_interrupts(struct seq_file *p, void *v)
 	}
 
 	seq_putc(p, '\n');
-out:
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
 	return 0;
 }
 #endif