Eric Lee / smarc-ti-linux-kernel | Embedian Git Server

Commit ac88ee3b6cbac80c32556a39fe16c4bbc55fcbc5

Authored by Linus Torvalds 2014-12-20 05:26:08 +0800

Exists in ti-lsk-linux-4.1.y and in 10 other branches

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

Pull irq core fix from Thomas Gleixner:
 "A single fix plugging a long standing race between proc/stat and
  proc/interrupts access and freeing of interrupt descriptors"

* 'irq-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  genirq: Prevent proc race against freeing of irq descriptors

Showing 5 changed files Inline Diff

fs/proc/stat.c
include/linux/kernel_stat.h
kernel/irq/internals.h
kernel/irq/irqdesc.c
kernel/irq/proc.c

fs/proc/stat.c

Diff comments View file @ ac88ee3

1	#include <linux/cpumask.h>	1	#include <linux/cpumask.h>
2	#include <linux/fs.h>	2	#include <linux/fs.h>
3	#include <linux/init.h>	3	#include <linux/init.h>
4	#include <linux/interrupt.h>	4	#include <linux/interrupt.h>
5	#include <linux/kernel_stat.h>	5	#include <linux/kernel_stat.h>
6	#include <linux/proc_fs.h>	6	#include <linux/proc_fs.h>
7	#include <linux/sched.h>	7	#include <linux/sched.h>
8	#include <linux/seq_file.h>	8	#include <linux/seq_file.h>
9	#include <linux/slab.h>	9	#include <linux/slab.h>
10	#include <linux/time.h>	10	#include <linux/time.h>
11	#include <linux/irqnr.h>	11	#include <linux/irqnr.h>
12	#include <linux/cputime.h>	12	#include <linux/cputime.h>
13	#include <linux/tick.h>	13	#include <linux/tick.h>
14		14
15	#ifndef arch_irq_stat_cpu	15	#ifndef arch_irq_stat_cpu
16	#define arch_irq_stat_cpu(cpu) 0	16	#define arch_irq_stat_cpu(cpu) 0
17	#endif	17	#endif
18	#ifndef arch_irq_stat	18	#ifndef arch_irq_stat
19	#define arch_irq_stat() 0	19	#define arch_irq_stat() 0
20	#endif	20	#endif
21		21
22	#ifdef arch_idle_time	22	#ifdef arch_idle_time
23		23
24	static cputime64_t get_idle_time(int cpu)	24	static cputime64_t get_idle_time(int cpu)
25	{	25	{
26	cputime64_t idle;	26	cputime64_t idle;
27		27
28	idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE];	28	idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE];
29	if (cpu_online(cpu) && !nr_iowait_cpu(cpu))	29	if (cpu_online(cpu) && !nr_iowait_cpu(cpu))
30	idle += arch_idle_time(cpu);	30	idle += arch_idle_time(cpu);
31	return idle;	31	return idle;
32	}	32	}
33		33
34	static cputime64_t get_iowait_time(int cpu)	34	static cputime64_t get_iowait_time(int cpu)
35	{	35	{
36	cputime64_t iowait;	36	cputime64_t iowait;
37		37
38	iowait = kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT];	38	iowait = kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT];
39	if (cpu_online(cpu) && nr_iowait_cpu(cpu))	39	if (cpu_online(cpu) && nr_iowait_cpu(cpu))
40	iowait += arch_idle_time(cpu);	40	iowait += arch_idle_time(cpu);
41	return iowait;	41	return iowait;
42	}	42	}
43		43
44	#else	44	#else
45		45
46	static u64 get_idle_time(int cpu)	46	static u64 get_idle_time(int cpu)
47	{	47	{
48	u64 idle, idle_time = -1ULL;	48	u64 idle, idle_time = -1ULL;
49		49
50	if (cpu_online(cpu))	50	if (cpu_online(cpu))
51	idle_time = get_cpu_idle_time_us(cpu, NULL);	51	idle_time = get_cpu_idle_time_us(cpu, NULL);
52		52
53	if (idle_time == -1ULL)	53	if (idle_time == -1ULL)
54	/* !NO_HZ or cpu offline so we can rely on cpustat.idle */	54	/* !NO_HZ or cpu offline so we can rely on cpustat.idle */
55	idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE];	55	idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE];
56	else	56	else
57	idle = usecs_to_cputime64(idle_time);	57	idle = usecs_to_cputime64(idle_time);
58		58
59	return idle;	59	return idle;
60	}	60	}
61		61
62	static u64 get_iowait_time(int cpu)	62	static u64 get_iowait_time(int cpu)
63	{	63	{
64	u64 iowait, iowait_time = -1ULL;	64	u64 iowait, iowait_time = -1ULL;
65		65
66	if (cpu_online(cpu))	66	if (cpu_online(cpu))
67	iowait_time = get_cpu_iowait_time_us(cpu, NULL);	67	iowait_time = get_cpu_iowait_time_us(cpu, NULL);
68		68
69	if (iowait_time == -1ULL)	69	if (iowait_time == -1ULL)
70	/* !NO_HZ or cpu offline so we can rely on cpustat.iowait */	70	/* !NO_HZ or cpu offline so we can rely on cpustat.iowait */
71	iowait = kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT];	71	iowait = kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT];
72	else	72	else
73	iowait = usecs_to_cputime64(iowait_time);	73	iowait = usecs_to_cputime64(iowait_time);
74		74
75	return iowait;	75	return iowait;
76	}	76	}
77		77
78	#endif	78	#endif
79		79
80	static int show_stat(struct seq_file p, void v)	80	static int show_stat(struct seq_file p, void v)
81	{	81	{
82	int i, j;	82	int i, j;
83	unsigned long jif;	83	unsigned long jif;
84	u64 user, nice, system, idle, iowait, irq, softirq, steal;	84	u64 user, nice, system, idle, iowait, irq, softirq, steal;
85	u64 guest, guest_nice;	85	u64 guest, guest_nice;
86	u64 sum = 0;	86	u64 sum = 0;
87	u64 sum_softirq = 0;	87	u64 sum_softirq = 0;
88	unsigned int per_softirq_sums[NR_SOFTIRQS] = {0};	88	unsigned int per_softirq_sums[NR_SOFTIRQS] = {0};
89	struct timespec boottime;	89	struct timespec boottime;
90		90
91	user = nice = system = idle = iowait =	91	user = nice = system = idle = iowait =
92	irq = softirq = steal = 0;	92	irq = softirq = steal = 0;
93	guest = guest_nice = 0;	93	guest = guest_nice = 0;
94	getboottime(&boottime);	94	getboottime(&boottime);
95	jif = boottime.tv_sec;	95	jif = boottime.tv_sec;
96		96
97	for_each_possible_cpu(i) {	97	for_each_possible_cpu(i) {
98	user += kcpustat_cpu(i).cpustat[CPUTIME_USER];	98	user += kcpustat_cpu(i).cpustat[CPUTIME_USER];
99	nice += kcpustat_cpu(i).cpustat[CPUTIME_NICE];	99	nice += kcpustat_cpu(i).cpustat[CPUTIME_NICE];
100	system += kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM];	100	system += kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM];
101	idle += get_idle_time(i);	101	idle += get_idle_time(i);
102	iowait += get_iowait_time(i);	102	iowait += get_iowait_time(i);
103	irq += kcpustat_cpu(i).cpustat[CPUTIME_IRQ];	103	irq += kcpustat_cpu(i).cpustat[CPUTIME_IRQ];
104	softirq += kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ];	104	softirq += kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ];
105	steal += kcpustat_cpu(i).cpustat[CPUTIME_STEAL];	105	steal += kcpustat_cpu(i).cpustat[CPUTIME_STEAL];
106	guest += kcpustat_cpu(i).cpustat[CPUTIME_GUEST];	106	guest += kcpustat_cpu(i).cpustat[CPUTIME_GUEST];
107	guest_nice += kcpustat_cpu(i).cpustat[CPUTIME_GUEST_NICE];	107	guest_nice += kcpustat_cpu(i).cpustat[CPUTIME_GUEST_NICE];
108	sum += kstat_cpu_irqs_sum(i);	108	sum += kstat_cpu_irqs_sum(i);
109	sum += arch_irq_stat_cpu(i);	109	sum += arch_irq_stat_cpu(i);
110		110
111	for (j = 0; j < NR_SOFTIRQS; j++) {	111	for (j = 0; j < NR_SOFTIRQS; j++) {
112	unsigned int softirq_stat = kstat_softirqs_cpu(j, i);	112	unsigned int softirq_stat = kstat_softirqs_cpu(j, i);
113		113
114	per_softirq_sums[j] += softirq_stat;	114	per_softirq_sums[j] += softirq_stat;
115	sum_softirq += softirq_stat;	115	sum_softirq += softirq_stat;
116	}	116	}
117	}	117	}
118	sum += arch_irq_stat();	118	sum += arch_irq_stat();
119		119
120	seq_puts(p, "cpu ");	120	seq_puts(p, "cpu ");
121	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(user));	121	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(user));
122	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(nice));	122	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(nice));
123	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(system));	123	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(system));
124	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(idle));	124	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(idle));
125	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(iowait));	125	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(iowait));
126	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(irq));	126	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(irq));
127	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(softirq));	127	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(softirq));
128	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(steal));	128	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(steal));
129	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(guest));	129	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(guest));
130	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(guest_nice));	130	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(guest_nice));
131	seq_putc(p, '\n');	131	seq_putc(p, '\n');
132		132
133	for_each_online_cpu(i) {	133	for_each_online_cpu(i) {
134	/* Copy values here to work around gcc-2.95.3, gcc-2.96 */	134	/* Copy values here to work around gcc-2.95.3, gcc-2.96 */
135	user = kcpustat_cpu(i).cpustat[CPUTIME_USER];	135	user = kcpustat_cpu(i).cpustat[CPUTIME_USER];
136	nice = kcpustat_cpu(i).cpustat[CPUTIME_NICE];	136	nice = kcpustat_cpu(i).cpustat[CPUTIME_NICE];
137	system = kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM];	137	system = kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM];
138	idle = get_idle_time(i);	138	idle = get_idle_time(i);
139	iowait = get_iowait_time(i);	139	iowait = get_iowait_time(i);
140	irq = kcpustat_cpu(i).cpustat[CPUTIME_IRQ];	140	irq = kcpustat_cpu(i).cpustat[CPUTIME_IRQ];
141	softirq = kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ];	141	softirq = kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ];
142	steal = kcpustat_cpu(i).cpustat[CPUTIME_STEAL];	142	steal = kcpustat_cpu(i).cpustat[CPUTIME_STEAL];
143	guest = kcpustat_cpu(i).cpustat[CPUTIME_GUEST];	143	guest = kcpustat_cpu(i).cpustat[CPUTIME_GUEST];
144	guest_nice = kcpustat_cpu(i).cpustat[CPUTIME_GUEST_NICE];	144	guest_nice = kcpustat_cpu(i).cpustat[CPUTIME_GUEST_NICE];
145	seq_printf(p, "cpu%d", i);	145	seq_printf(p, "cpu%d", i);
146	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(user));	146	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(user));
147	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(nice));	147	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(nice));
148	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(system));	148	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(system));
149	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(idle));	149	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(idle));
150	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(iowait));	150	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(iowait));
151	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(irq));	151	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(irq));
152	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(softirq));	152	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(softirq));
153	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(steal));	153	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(steal));
154	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(guest));	154	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(guest));
155	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(guest_nice));	155	seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(guest_nice));
156	seq_putc(p, '\n');	156	seq_putc(p, '\n');
157	}	157	}
158	seq_printf(p, "intr %llu", (unsigned long long)sum);	158	seq_printf(p, "intr %llu", (unsigned long long)sum);
159		159
160	/* sum again ? it could be updated? */	160	/* sum again ? it could be updated? */
161	for_each_irq_nr(j)	161	for_each_irq_nr(j)
162	seq_put_decimal_ull(p, ' ', kstat_irqs(j));	162	seq_put_decimal_ull(p, ' ', kstat_irqs_usr(j));
163		163
164	seq_printf(p,	164	seq_printf(p,
165	"\nctxt %llu\n"	165	"\nctxt %llu\n"
166	"btime %lu\n"	166	"btime %lu\n"
167	"processes %lu\n"	167	"processes %lu\n"
168	"procs_running %lu\n"	168	"procs_running %lu\n"
169	"procs_blocked %lu\n",	169	"procs_blocked %lu\n",
170	nr_context_switches(),	170	nr_context_switches(),
171	(unsigned long)jif,	171	(unsigned long)jif,
172	total_forks,	172	total_forks,
173	nr_running(),	173	nr_running(),
174	nr_iowait());	174	nr_iowait());
175		175
176	seq_printf(p, "softirq %llu", (unsigned long long)sum_softirq);	176	seq_printf(p, "softirq %llu", (unsigned long long)sum_softirq);
177		177
178	for (i = 0; i < NR_SOFTIRQS; i++)	178	for (i = 0; i < NR_SOFTIRQS; i++)
179	seq_put_decimal_ull(p, ' ', per_softirq_sums[i]);	179	seq_put_decimal_ull(p, ' ', per_softirq_sums[i]);
180	seq_putc(p, '\n');	180	seq_putc(p, '\n');
181		181
182	return 0;	182	return 0;
183	}	183	}
184		184
185	static int stat_open(struct inode inode, struct file file)	185	static int stat_open(struct inode inode, struct file file)
186	{	186	{
187	size_t size = 1024 + 128 * num_online_cpus();	187	size_t size = 1024 + 128 * num_online_cpus();
188		188
189	/* minimum size to display an interrupt count : 2 bytes */	189	/* minimum size to display an interrupt count : 2 bytes */
190	size += 2 * nr_irqs;	190	size += 2 * nr_irqs;
191	return single_open_size(file, show_stat, NULL, size);	191	return single_open_size(file, show_stat, NULL, size);
192	}	192	}
193		193
194	static const struct file_operations proc_stat_operations = {	194	static const struct file_operations proc_stat_operations = {
195	.open = stat_open,	195	.open = stat_open,
196	.read = seq_read,	196	.read = seq_read,
197	.llseek = seq_lseek,	197	.llseek = seq_lseek,
198	.release = single_release,	198	.release = single_release,
199	};	199	};
200		200
201	static int __init proc_stat_init(void)	201	static int __init proc_stat_init(void)
202	{	202	{
203	proc_create("stat", 0, NULL, &proc_stat_operations);	203	proc_create("stat", 0, NULL, &proc_stat_operations);
204	return 0;	204	return 0;
205	}	205	}
206	fs_initcall(proc_stat_init);	206	fs_initcall(proc_stat_init);
207		207

include/linux/kernel_stat.h

Diff comments View file @ ac88ee3

 #ifndef _LINUX_KERNEL_STAT_H
 #define _LINUX_KERNEL_STAT_H
 #include <linux/smp.h>
 #include <linux/threads.h>
 #include <linux/percpu.h>
 #include <linux/cpumask.h>
 #include <linux/interrupt.h>
 #include <linux/sched.h>
 #include <linux/vtime.h>
 #include <asm/irq.h>
 #include <linux/cputime.h>
 /*
  * 'kernel_stat.h' contains the definitions needed for doing
  * some kernel statistics (CPU usage, context switches ...),
  * used by rstatd/perfmeter
  */
 enum cpu_usage_stat {
 	CPUTIME_USER,
 	CPUTIME_NICE,
 	CPUTIME_SYSTEM,
 	CPUTIME_SOFTIRQ,
 	CPUTIME_IRQ,
 	CPUTIME_IDLE,
 	CPUTIME_IOWAIT,
 	CPUTIME_STEAL,
 	CPUTIME_GUEST,
 	CPUTIME_GUEST_NICE,
 	NR_STATS,
 };
 struct kernel_cpustat {
 	u64 cpustat[NR_STATS];
 };
 struct kernel_stat {
 	unsigned long irqs_sum;
 	unsigned int softirqs[NR_SOFTIRQS];
 };
 DECLARE_PER_CPU(struct kernel_stat, kstat);
 DECLARE_PER_CPU(struct kernel_cpustat, kernel_cpustat);
 /* Must have preemption disabled for this to be meaningful. */
 #define kstat_this_cpu this_cpu_ptr(&kstat)
 #define kcpustat_this_cpu this_cpu_ptr(&kernel_cpustat)
 #define kstat_cpu(cpu) per_cpu(kstat, cpu)
 #define kcpustat_cpu(cpu) per_cpu(kernel_cpustat, cpu)
 extern unsigned long long nr_context_switches(void);
 extern unsigned int kstat_irqs_cpu(unsigned int irq, int cpu);
 extern void kstat_incr_irq_this_cpu(unsigned int irq);
 static inline void kstat_incr_softirqs_this_cpu(unsigned int irq)
 {
 	__this_cpu_inc(kstat.softirqs[irq]);
 }
 static inline unsigned int kstat_softirqs_cpu(unsigned int irq, int cpu)
 {
        return kstat_cpu(cpu).softirqs[irq];
 }
 /*
  * Number of interrupts per specific IRQ source, since bootup
  */
 extern unsigned int kstat_irqs(unsigned int irq);
+extern unsigned int kstat_irqs_usr(unsigned int irq);
 /*
  * Number of interrupts per cpu, since bootup
  */
 static inline unsigned int kstat_cpu_irqs_sum(unsigned int cpu)
 {
 	return kstat_cpu(cpu).irqs_sum;
 }
 extern void account_user_time(struct task_struct *, cputime_t, cputime_t);
 extern void account_system_time(struct task_struct *, int, cputime_t, cputime_t);
 extern void account_steal_time(cputime_t);
 extern void account_idle_time(cputime_t);
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 static inline void account_process_tick(struct task_struct *tsk, int user)
 {
 	vtime_account_user(tsk);
 }
 #else
 extern void account_process_tick(struct task_struct *, int user);
 #endif
 extern void account_steal_ticks(unsigned long ticks);
 extern void account_idle_ticks(unsigned long ticks);
 #endif /* _LINUX_KERNEL_STAT_H */

kernel/irq/internals.h

Diff comments View file @ ac88ee3

 /*
  * IRQ subsystem internal functions and variables:
  *
  * Do not ever include this file from anything else than
  * kernel/irq/. Do not even think about using any information outside
  * of this file for your non core code.
  */
 #include <linux/irqdesc.h>
 #include <linux/kernel_stat.h>
 #ifdef CONFIG_SPARSE_IRQ
 # define IRQ_BITMAP_BITS	(NR_IRQS + 8196)
 #else
 # define IRQ_BITMAP_BITS	NR_IRQS
 #endif
 #define istate core_internal_state__do_not_mess_with_it
 extern bool noirqdebug;
 /*
  * Bits used by threaded handlers:
  * IRQTF_RUNTHREAD - signals that the interrupt handler thread should run
  * IRQTF_WARNED    - warning "IRQ_WAKE_THREAD w/o thread_fn" has been printed
  * IRQTF_AFFINITY  - irq thread is requested to adjust affinity
  * IRQTF_FORCED_THREAD  - irq action is force threaded
  */
 enum {
 	IRQTF_RUNTHREAD,
 	IRQTF_WARNED,
 	IRQTF_AFFINITY,
 	IRQTF_FORCED_THREAD,
 };
 /*
  * Bit masks for desc->core_internal_state__do_not_mess_with_it
  *
  * IRQS_AUTODETECT		- autodetection in progress
  * IRQS_SPURIOUS_DISABLED	- was disabled due to spurious interrupt
  *				  detection
  * IRQS_POLL_INPROGRESS		- polling in progress
  * IRQS_ONESHOT			- irq is not unmasked in primary handler
  * IRQS_REPLAY			- irq is replayed
  * IRQS_WAITING			- irq is waiting
  * IRQS_PENDING			- irq is pending and replayed later
  * IRQS_SUSPENDED		- irq is suspended
  */
 enum {
 	IRQS_AUTODETECT		= 0x00000001,
 	IRQS_SPURIOUS_DISABLED	= 0x00000002,
 	IRQS_POLL_INPROGRESS	= 0x00000008,
 	IRQS_ONESHOT		= 0x00000020,
 	IRQS_REPLAY		= 0x00000040,
 	IRQS_WAITING		= 0x00000080,
 	IRQS_PENDING		= 0x00000200,
 	IRQS_SUSPENDED		= 0x00000800,
 };
 #include "debug.h"
 #include "settings.h"
 #define irq_data_to_desc(data)	container_of(data, struct irq_desc, irq_data)
 extern int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
 		unsigned long flags);
 extern void __disable_irq(struct irq_desc *desc, unsigned int irq);
 extern void __enable_irq(struct irq_desc *desc, unsigned int irq);
 extern int irq_startup(struct irq_desc *desc, bool resend);
 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);
 extern void unmask_threaded_irq(struct irq_desc *desc);
 #ifdef CONFIG_SPARSE_IRQ
 static inline void irq_mark_irq(unsigned int irq) { }
+extern void irq_lock_sparse(void);
+extern void irq_unlock_sparse(void);
 #else
 extern void irq_mark_irq(unsigned int irq);
+static inline void irq_lock_sparse(void) { }
+static inline void irq_unlock_sparse(void) { }
 #endif
 extern void init_kstat_irqs(struct irq_desc *desc, int node, int nr);
 irqreturn_t handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action);
 irqreturn_t handle_irq_event(struct irq_desc *desc);
 /* Resending of interrupts :*/
 void check_irq_resend(struct irq_desc *desc, unsigned int irq);
 bool irq_wait_for_poll(struct irq_desc *desc);
 void __irq_wake_thread(struct irq_desc *desc, struct irqaction *action);
 #ifdef CONFIG_PROC_FS
 extern void register_irq_proc(unsigned int irq, struct irq_desc *desc);
 extern void unregister_irq_proc(unsigned int irq, struct irq_desc *desc);
 extern void register_handler_proc(unsigned int irq, struct irqaction *action);
 extern void unregister_handler_proc(unsigned int irq, struct irqaction *action);
 #else
 static inline void register_irq_proc(unsigned int irq, struct irq_desc *desc) { }
 static inline void unregister_irq_proc(unsigned int irq, struct irq_desc *desc) { }
 static inline void register_handler_proc(unsigned int irq,
 					 struct irqaction *action) { }
 static inline void unregister_handler_proc(unsigned int irq,
 					   struct irqaction *action) { }
 #endif
 extern int irq_select_affinity_usr(unsigned int irq, struct cpumask *mask);
 extern void irq_set_thread_affinity(struct irq_desc *desc);
 extern int irq_do_set_affinity(struct irq_data *data,
 			       const struct cpumask *dest, bool force);
 /* Inline functions for support of irq chips on slow busses */
 static inline void chip_bus_lock(struct irq_desc *desc)
 {
 	if (unlikely(desc->irq_data.chip->irq_bus_lock))
 		desc->irq_data.chip->irq_bus_lock(&desc->irq_data);
 }
 static inline void chip_bus_sync_unlock(struct irq_desc *desc)
 {
 	if (unlikely(desc->irq_data.chip->irq_bus_sync_unlock))
 		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,
 		    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, unsigned int check)
 {
 	return __irq_get_desc_lock(irq, flags, true, check);
 }
 static inline void
 irq_put_desc_busunlock(struct irq_desc *desc, unsigned long flags)
 {
 	__irq_put_desc_unlock(desc, flags, true);
 }
 static inline struct irq_desc *
 irq_get_desc_lock(unsigned int irq, unsigned long *flags, unsigned int check)
 {
 	return __irq_get_desc_lock(irq, flags, false, check);
 }
 static inline void
 irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags)
 {
 	__irq_put_desc_unlock(desc, flags, false);
 }
 /*
  * Manipulation functions for irq_data.state
  */
 static inline void irqd_set_move_pending(struct irq_data *d)
 {
 	d->state_use_accessors |= IRQD_SETAFFINITY_PENDING;
 }
 static inline void irqd_clr_move_pending(struct irq_data *d)
 {
 	d->state_use_accessors &= ~IRQD_SETAFFINITY_PENDING;
 }
 static inline void irqd_clear(struct irq_data *d, unsigned int mask)
 {
 	d->state_use_accessors &= ~mask;
 }
 static inline void irqd_set(struct irq_data *d, unsigned int mask)
 {
 	d->state_use_accessors |= mask;
 }
 static inline bool irqd_has_set(struct irq_data *d, unsigned int mask)
 {
 	return d->state_use_accessors & mask;
 }
 static inline void kstat_incr_irqs_this_cpu(unsigned int irq, struct irq_desc *desc)
 {
 	__this_cpu_inc(*desc->kstat_irqs);
 	__this_cpu_inc(kstat.irqs_sum);
 }
 #ifdef CONFIG_PM_SLEEP
 bool irq_pm_check_wakeup(struct irq_desc *desc);
 void irq_pm_install_action(struct irq_desc *desc, struct irqaction *action);
 void irq_pm_remove_action(struct irq_desc *desc, struct irqaction *action);
 #else
 static inline bool irq_pm_check_wakeup(struct irq_desc *desc) { return false; }
 static inline void
 irq_pm_install_action(struct irq_desc *desc, struct irqaction *action) { }
 static inline void
 irq_pm_remove_action(struct irq_desc *desc, struct irqaction *action) { }
 #endif

kernel/irq/irqdesc.c

Diff comments View file @ ac88ee3

 /*
  * Copyright (C) 1992, 1998-2006 Linus Torvalds, Ingo Molnar
  * Copyright (C) 2005-2006, Thomas Gleixner, Russell King
  *
  * This file contains the interrupt descriptor management code
  *
  * Detailed information is available in Documentation/DocBook/genericirq
  *
  */
 #include <linux/irq.h>
 #include <linux/slab.h>
 #include <linux/export.h>
 #include <linux/interrupt.h>
 #include <linux/kernel_stat.h>
 #include <linux/radix-tree.h>
 #include <linux/bitmap.h>
 #include <linux/irqdomain.h>
 #include "internals.h"
 /*
  * lockdep: we want to handle all irq_desc locks as a single lock-class:
  */
 static struct lock_class_key irq_desc_lock_class;
 #if defined(CONFIG_SMP)
 static void __init init_irq_default_affinity(void)
 {
 	alloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT);
 	cpumask_setall(irq_default_affinity);
 }
 #else
 static void __init init_irq_default_affinity(void)
 {
 }
 #endif
 #ifdef CONFIG_SMP
 static int alloc_masks(struct irq_desc *desc, gfp_t gfp, int node)
 {
 	if (!zalloc_cpumask_var_node(&desc->irq_data.affinity, gfp, node))
 		return -ENOMEM;
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	if (!zalloc_cpumask_var_node(&desc->pending_mask, gfp, node)) {
 		free_cpumask_var(desc->irq_data.affinity);
 		return -ENOMEM;
 	}
 #endif
 	return 0;
 }
 static void desc_smp_init(struct irq_desc *desc, int node)
 {
 	desc->irq_data.node = node;
 	cpumask_copy(desc->irq_data.affinity, irq_default_affinity);
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	cpumask_clear(desc->pending_mask);
 #endif
 }
 static inline int desc_node(struct irq_desc *desc)
 {
 	return desc->irq_data.node;
 }
 #else
 static inline int
 alloc_masks(struct irq_desc *desc, gfp_t gfp, int node) { return 0; }
 static inline void desc_smp_init(struct irq_desc *desc, int node) { }
 static inline int desc_node(struct irq_desc *desc) { return 0; }
 #endif
 static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node,
 		struct module *owner)
 {
 	int cpu;
 	desc->irq_data.irq = irq;
 	desc->irq_data.chip = &no_irq_chip;
 	desc->irq_data.chip_data = NULL;
 	desc->irq_data.handler_data = NULL;
 	desc->irq_data.msi_desc = NULL;
 	irq_settings_clr_and_set(desc, ~0, _IRQ_DEFAULT_INIT_FLAGS);
 	irqd_set(&desc->irq_data, IRQD_IRQ_DISABLED);
 	desc->handle_irq = handle_bad_irq;
 	desc->depth = 1;
 	desc->irq_count = 0;
 	desc->irqs_unhandled = 0;
 	desc->name = NULL;
 	desc->owner = owner;
 	for_each_possible_cpu(cpu)
 		*per_cpu_ptr(desc->kstat_irqs, cpu) = 0;
 	desc_smp_init(desc, node);
 }
 int nr_irqs = NR_IRQS;
 EXPORT_SYMBOL_GPL(nr_irqs);
 static DEFINE_MUTEX(sparse_irq_lock);
 static DECLARE_BITMAP(allocated_irqs, IRQ_BITMAP_BITS);
 #ifdef CONFIG_SPARSE_IRQ
 static RADIX_TREE(irq_desc_tree, GFP_KERNEL);
 static void irq_insert_desc(unsigned int irq, struct irq_desc *desc)
 {
 	radix_tree_insert(&irq_desc_tree, irq, desc);
 }
 struct irq_desc *irq_to_desc(unsigned int irq)
 {
 	return radix_tree_lookup(&irq_desc_tree, irq);
 }
 EXPORT_SYMBOL(irq_to_desc);
 static void delete_irq_desc(unsigned int irq)
 {
 	radix_tree_delete(&irq_desc_tree, irq);
 }
 #ifdef CONFIG_SMP
 static void free_masks(struct irq_desc *desc)
 {
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	free_cpumask_var(desc->pending_mask);
 #endif
 	free_cpumask_var(desc->irq_data.affinity);
 }
 #else
 static inline void free_masks(struct irq_desc *desc) { }
 #endif
+void irq_lock_sparse(void)
+{
+	mutex_lock(&sparse_irq_lock);
+}
+void irq_unlock_sparse(void)
+{
+	mutex_unlock(&sparse_irq_lock);
+}
 static struct irq_desc *alloc_desc(int irq, int node, struct module *owner)
 {
 	struct irq_desc *desc;
 	gfp_t gfp = GFP_KERNEL;
 	desc = kzalloc_node(sizeof(*desc), gfp, node);
 	if (!desc)
 		return NULL;
 	/* allocate based on nr_cpu_ids */
 	desc->kstat_irqs = alloc_percpu(unsigned int);
 	if (!desc->kstat_irqs)
 		goto err_desc;
 	if (alloc_masks(desc, gfp, node))
 		goto err_kstat;
 	raw_spin_lock_init(&desc->lock);
 	lockdep_set_class(&desc->lock, &irq_desc_lock_class);
 	desc_set_defaults(irq, desc, node, owner);
 	return desc;
 err_kstat:
 	free_percpu(desc->kstat_irqs);
 err_desc:
 	kfree(desc);
 	return NULL;
 }
 static void free_desc(unsigned int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	unregister_irq_proc(irq, desc);
+	/*
+	 * sparse_irq_lock protects also show_interrupts() and
+	 * kstat_irq_usr(). Once we deleted the descriptor from the
+	 * sparse tree we can free it. Access in proc will fail to
+	 * lookup the descriptor.
+	 */
 	mutex_lock(&sparse_irq_lock);
 	delete_irq_desc(irq);
 	mutex_unlock(&sparse_irq_lock);
 	free_masks(desc);
 	free_percpu(desc->kstat_irqs);
 	kfree(desc);
 }
 static int alloc_descs(unsigned int start, unsigned int cnt, int node,
 		       struct module *owner)
 {
 	struct irq_desc *desc;
 	int i;
 	for (i = 0; i < cnt; i++) {
 		desc = alloc_desc(start + i, node, owner);
 		if (!desc)
 			goto err;
 		mutex_lock(&sparse_irq_lock);
 		irq_insert_desc(start + i, desc);
 		mutex_unlock(&sparse_irq_lock);
 	}
 	return start;
 err:
 	for (i--; i >= 0; i--)
 		free_desc(start + i);
 	mutex_lock(&sparse_irq_lock);
 	bitmap_clear(allocated_irqs, start, cnt);
 	mutex_unlock(&sparse_irq_lock);
 	return -ENOMEM;
 }
 static int irq_expand_nr_irqs(unsigned int nr)
 {
 	if (nr > IRQ_BITMAP_BITS)
 		return -ENOMEM;
 	nr_irqs = nr;
 	return 0;
 }
 int __init early_irq_init(void)
 {
 	int i, initcnt, node = first_online_node;
 	struct irq_desc *desc;
 	init_irq_default_affinity();
 	/* Let arch update nr_irqs and return the nr of preallocated irqs */
 	initcnt = arch_probe_nr_irqs();
 	printk(KERN_INFO "NR_IRQS:%d nr_irqs:%d %d\n", NR_IRQS, nr_irqs, initcnt);
 	if (WARN_ON(nr_irqs > IRQ_BITMAP_BITS))
 		nr_irqs = IRQ_BITMAP_BITS;
 	if (WARN_ON(initcnt > IRQ_BITMAP_BITS))
 		initcnt = IRQ_BITMAP_BITS;
 	if (initcnt > nr_irqs)
 		nr_irqs = initcnt;
 	for (i = 0; i < initcnt; i++) {
 		desc = alloc_desc(i, node, NULL);
 		set_bit(i, allocated_irqs);
 		irq_insert_desc(i, desc);
 	}
 	return arch_early_irq_init();
 }
 #else /* !CONFIG_SPARSE_IRQ */
 struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
 	[0 ... NR_IRQS-1] = {
 		.handle_irq	= handle_bad_irq,
 		.depth		= 1,
 		.lock		= __RAW_SPIN_LOCK_UNLOCKED(irq_desc->lock),
 	}
 };
 int __init early_irq_init(void)
 {
 	int count, i, node = first_online_node;
 	struct irq_desc *desc;
 	init_irq_default_affinity();
 	printk(KERN_INFO "NR_IRQS:%d\n", NR_IRQS);
 	desc = irq_desc;
 	count = ARRAY_SIZE(irq_desc);
 	for (i = 0; i < count; i++) {
 		desc[i].kstat_irqs = alloc_percpu(unsigned int);
 		alloc_masks(&desc[i], GFP_KERNEL, node);
 		raw_spin_lock_init(&desc[i].lock);
 		lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
 		desc_set_defaults(i, &desc[i], node, NULL);
 	}
 	return arch_early_irq_init();
 }
 struct irq_desc *irq_to_desc(unsigned int irq)
 {
 	return (irq < NR_IRQS) ? irq_desc + irq : NULL;
 }
 EXPORT_SYMBOL(irq_to_desc);
 static void free_desc(unsigned int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;
 	raw_spin_lock_irqsave(&desc->lock, flags);
 	desc_set_defaults(irq, desc, desc_node(desc), NULL);
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 }
 static inline int alloc_descs(unsigned int start, unsigned int cnt, int node,
 			      struct module *owner)
 {
 	u32 i;
 	for (i = 0; i < cnt; i++) {
 		struct irq_desc *desc = irq_to_desc(start + i);
 		desc->owner = owner;
 	}
 	return start;
 }
 static int irq_expand_nr_irqs(unsigned int nr)
 {
 	return -ENOMEM;
 }
 void irq_mark_irq(unsigned int irq)
 {
 	mutex_lock(&sparse_irq_lock);
 	bitmap_set(allocated_irqs, irq, 1);
 	mutex_unlock(&sparse_irq_lock);
 }
 #ifdef CONFIG_GENERIC_IRQ_LEGACY
 void irq_init_desc(unsigned int irq)
 {
 	free_desc(irq);
 }
 #endif
 #endif /* !CONFIG_SPARSE_IRQ */
 /**
  * generic_handle_irq - Invoke the handler for a particular irq
  * @irq:	The irq number to handle
  *
  */
 int generic_handle_irq(unsigned int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	if (!desc)
 		return -EINVAL;
 	generic_handle_irq_desc(irq, desc);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(generic_handle_irq);
 #ifdef CONFIG_HANDLE_DOMAIN_IRQ
 /**
  * __handle_domain_irq - Invoke the handler for a HW irq belonging to a domain
  * @domain:	The domain where to perform the lookup
  * @hwirq:	The HW irq number to convert to a logical one
  * @lookup:	Whether to perform the domain lookup or not
  * @regs:	Register file coming from the low-level handling code
  *
  * Returns:	0 on success, or -EINVAL if conversion has failed
  */
 int __handle_domain_irq(struct irq_domain *domain, unsigned int hwirq,
 			bool lookup, struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 	unsigned int irq = hwirq;
 	int ret = 0;
 	irq_enter();
 #ifdef CONFIG_IRQ_DOMAIN
 	if (lookup)
 		irq = irq_find_mapping(domain, hwirq);
 #endif
 	/*
 	 * Some hardware gives randomly wrong interrupts.  Rather
 	 * than crashing, do something sensible.
 	 */
 	if (unlikely(!irq || irq >= nr_irqs)) {
 		ack_bad_irq(irq);
 		ret = -EINVAL;
 	} else {
 		generic_handle_irq(irq);
 	}
 	irq_exit();
 	set_irq_regs(old_regs);
 	return ret;
 }
 #endif
 /* Dynamic interrupt handling */
 /**
  * irq_free_descs - free irq descriptors
  * @from:	Start of descriptor range
  * @cnt:	Number of consecutive irqs to free
  */
 void irq_free_descs(unsigned int from, unsigned int cnt)
 {
 	int i;
 	if (from >= nr_irqs || (from + cnt) > nr_irqs)
 		return;
 	for (i = 0; i < cnt; i++)
 		free_desc(from + i);
 	mutex_lock(&sparse_irq_lock);
 	bitmap_clear(allocated_irqs, from, cnt);
 	mutex_unlock(&sparse_irq_lock);
 }
 EXPORT_SYMBOL_GPL(irq_free_descs);
 /**
  * irq_alloc_descs - allocate and initialize a range of irq descriptors
  * @irq:	Allocate for specific irq number if irq >= 0
  * @from:	Start the search from this irq number
  * @cnt:	Number of consecutive irqs to allocate.
  * @node:	Preferred node on which the irq descriptor should be allocated
  * @owner:	Owning module (can be NULL)
  *
  * Returns the first irq number or error code
  */
 int __ref
 __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node,
 		  struct module *owner)
 {
 	int start, ret;
 	if (!cnt)
 		return -EINVAL;
 	if (irq >= 0) {
 		if (from > irq)
 			return -EINVAL;
 		from = irq;
 	} else {
 		/*
 		 * For interrupts which are freely allocated the
 		 * architecture can force a lower bound to the @from
 		 * argument. x86 uses this to exclude the GSI space.
 		 */
 		from = arch_dynirq_lower_bound(from);
 	}
 	mutex_lock(&sparse_irq_lock);
 	start = bitmap_find_next_zero_area(allocated_irqs, IRQ_BITMAP_BITS,
 					   from, cnt, 0);
 	ret = -EEXIST;
 	if (irq >=0 && start != irq)
 		goto err;
 	if (start + cnt > nr_irqs) {
 		ret = irq_expand_nr_irqs(start + cnt);
 		if (ret)
 			goto err;
 	}
 	bitmap_set(allocated_irqs, start, cnt);
 	mutex_unlock(&sparse_irq_lock);
 	return alloc_descs(start, cnt, node, owner);
 err:
 	mutex_unlock(&sparse_irq_lock);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(__irq_alloc_descs);
 #ifdef CONFIG_GENERIC_IRQ_LEGACY_ALLOC_HWIRQ
 /**
  * irq_alloc_hwirqs - Allocate an irq descriptor and initialize the hardware
  * @cnt:	number of interrupts to allocate
  * @node:	node on which to allocate
  *
  * Returns an interrupt number > 0 or 0, if the allocation fails.
  */
 unsigned int irq_alloc_hwirqs(int cnt, int node)
 {
 	int i, irq = __irq_alloc_descs(-1, 0, cnt, node, NULL);
 	if (irq < 0)
 		return 0;
 	for (i = irq; cnt > 0; i++, cnt--) {
 		if (arch_setup_hwirq(i, node))
 			goto err;
 		irq_clear_status_flags(i, _IRQ_NOREQUEST);
 	}
 	return irq;
 err:
 	for (i--; i >= irq; i--) {
 		irq_set_status_flags(i, _IRQ_NOREQUEST | _IRQ_NOPROBE);
 		arch_teardown_hwirq(i);
 	}
 	irq_free_descs(irq, cnt);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(irq_alloc_hwirqs);
 /**
  * irq_free_hwirqs - Free irq descriptor and cleanup the hardware
  * @from:	Free from irq number
  * @cnt:	number of interrupts to free
  *
  */
 void irq_free_hwirqs(unsigned int from, int cnt)
 {
 	int i, j;
 	for (i = from, j = cnt; j > 0; i++, j--) {
 		irq_set_status_flags(i, _IRQ_NOREQUEST | _IRQ_NOPROBE);
 		arch_teardown_hwirq(i);
 	}
 	irq_free_descs(from, cnt);
 }
 EXPORT_SYMBOL_GPL(irq_free_hwirqs);
 #endif
 /**
  * irq_get_next_irq - get next allocated irq number
  * @offset:	where to start the search
  *
  * Returns next irq number after offset or nr_irqs if none is found.
  */
 unsigned int irq_get_next_irq(unsigned int offset)
 {
 	return find_next_bit(allocated_irqs, nr_irqs, offset);
 }
 struct irq_desc *
 __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);
 	}
 	return desc;
 }
 void __irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags, bool bus)
 {
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 	if (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;
 }
 void kstat_incr_irq_this_cpu(unsigned int irq)
 {
 	kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
 }
+/**
+ * kstat_irqs_cpu - Get the statistics for an interrupt on a cpu
+ * @irq:	The interrupt number
+ * @cpu:	The cpu number
+ *
+ * Returns the sum of interrupt counts on @cpu since boot for
+ * @irq. The caller must ensure that the interrupt is not removed
+ * concurrently.
+ */
 unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	return desc && desc->kstat_irqs ?
 			*per_cpu_ptr(desc->kstat_irqs, cpu) : 0;
 }
+/**
+ * kstat_irqs - Get the statistics for an interrupt
+ * @irq:	The interrupt number
+ *
+ * Returns the sum of interrupt counts on all cpus since boot for
+ * @irq. The caller must ensure that the interrupt is not removed
+ * concurrently.
+ */
 unsigned int kstat_irqs(unsigned int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	int cpu;
 	int sum = 0;
 	if (!desc || !desc->kstat_irqs)
 		return 0;
 	for_each_possible_cpu(cpu)
 		sum += *per_cpu_ptr(desc->kstat_irqs, cpu);
+	return sum;
+}
+/**
+ * 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.
+ */
+unsigned int kstat_irqs_usr(unsigned int irq)
+{
+	int sum;
+	irq_lock_sparse();
+	sum = kstat_irqs(irq);
+	irq_unlock_sparse();
 	return sum;
 }

kernel/irq/proc.c

Diff comments View file @ ac88ee3

 /*
  * linux/kernel/irq/proc.c
  *
  * Copyright (C) 1992, 1998-2004 Linus Torvalds, Ingo Molnar
  *
  * This file contains the /proc/irq/ handling code.
  */
 #include <linux/irq.h>
 #include <linux/gfp.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/interrupt.h>
 #include <linux/kernel_stat.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)
 {
 	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;
 #endif
 	if (type)
 		seq_cpumask_list(m, mask);
 	else
 		seq_cpumask(m, mask);
 	seq_putc(m, '\n');
 	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);
 	seq_cpumask(m, mask);
 	seq_putc(m, '\n');
 	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);
 }
 static int irq_affinity_list_proc_show(struct seq_file *m, void *v)
 {
 	return show_irq_affinity(1, m, v);
 }
 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));
 	cpumask_var_t new_value;
 	int err;
 	if (!irq_can_set_affinity(irq) || no_irq_affinity)
 		return -EIO;
 	if (!alloc_cpumask_var(&new_value, GFP_KERNEL))
 		return -ENOMEM;
 	if (type)
 		err = cpumask_parselist_user(buffer, count, new_value);
 	else
 		err = cpumask_parse_user(buffer, count, new_value);
 	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;
 	} else {
 		irq_set_affinity(irq, new_value);
 		err = count;
 	}
 free_cpumask:
 	free_cpumask_var(new_value);
 	return err;
 }
 static ssize_t irq_affinity_proc_write(struct file *file,
 		const char __user *buffer, size_t count, loff_t *pos)
 {
 	return write_irq_affinity(0, file, buffer, count, pos);
 }
 static ssize_t irq_affinity_list_proc_write(struct file *file,
 		const char __user *buffer, size_t count, loff_t *pos)
 {
 	return write_irq_affinity(1, file, buffer, count, pos);
 }
 static int irq_affinity_proc_open(struct inode *inode, struct file *file)
 {
 	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));
 }
 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 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 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,
 };
 static int default_affinity_show(struct seq_file *m, void *v)
 {
 	seq_cpumask(m, irq_default_affinity);
 	seq_putc(m, '\n');
 	return 0;
 }
 static ssize_t default_affinity_write(struct file *file,
 		const char __user *buffer, size_t count, loff_t *ppos)
 {
 	cpumask_var_t new_value;
 	int err;
 	if (!alloc_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
 	 * one online CPU still has to be targeted.
 	 */
 	if (!cpumask_intersects(new_value, cpu_online_mask)) {
 		err = -EINVAL;
 		goto out;
 	}
 	cpumask_copy(irq_default_affinity, new_value);
 	err = count;
 out:
 	free_cpumask_var(new_value);
 	return err;
 }
 static int default_affinity_open(struct inode *inode, struct file *file)
 {
 	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 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);
 	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)
 {
 	struct irq_desc *desc = irq_to_desc((long) m->private);
 	seq_printf(m, "count %u\n" "unhandled %u\n" "last_unhandled %u ms\n",
 		   desc->irq_count, desc->irqs_unhandled,
 		   jiffies_to_msecs(desc->last_unhandled));
 	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)
 {
 	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) {
 		if ((action != new_action) && action->name &&
 				!strcmp(new_action->name, action->name)) {
 			ret = 0;
 			break;
 		}
 	}
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 	return ret;
 }
 void register_handler_proc(unsigned int irq, struct irqaction *action)
 {
 	char name [MAX_NAMELEN];
 	struct irq_desc *desc = irq_to_desc(irq);
 	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/ */
 	action->dir = proc_mkdir(name, desc->dir);
 }
 #undef MAX_NAMELEN
 #define MAX_NAMELEN 10
 void register_irq_proc(unsigned int irq, struct irq_desc *desc)
 {
 	char name [MAX_NAMELEN];
 	if (!root_irq_dir || (desc->irq_data.chip == &no_irq_chip) || desc->dir)
 		return;
 	memset(name, 0, MAX_NAMELEN);
 	sprintf(name, "%d", irq);
 	/* create /proc/irq/1234 */
 	desc->dir = proc_mkdir(name, root_irq_dir);
 	if (!desc->dir)
 		return;
 #ifdef CONFIG_SMP
 	/* create /proc/irq/<irq>/smp_affinity */
 	proc_create_data("smp_affinity", 0644, desc->dir,
 			 &irq_affinity_proc_fops, (void *)(long)irq);
 	/* create /proc/irq/<irq>/affinity_hint */
 	proc_create_data("affinity_hint", 0444, desc->dir,
 			 &irq_affinity_hint_proc_fops, (void *)(long)irq);
 	/* create /proc/irq/<irq>/smp_affinity_list */
 	proc_create_data("smp_affinity_list", 0644, desc->dir,
 			 &irq_affinity_list_proc_fops, (void *)(long)irq);
 	proc_create_data("node", 0444, desc->dir,
 			 &irq_node_proc_fops, (void *)(long)irq);
 #endif
 	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)
 {
 	char name [MAX_NAMELEN];
 	if (!root_irq_dir || !desc->dir)
 		return;
 #ifdef CONFIG_SMP
 	remove_proc_entry("smp_affinity", desc->dir);
 	remove_proc_entry("affinity_hint", desc->dir);
 	remove_proc_entry("smp_affinity_list", desc->dir);
 	remove_proc_entry("node", desc->dir);
 #endif
 	remove_proc_entry("spurious", desc->dir);
 	memset(name, 0, MAX_NAMELEN);
 	sprintf(name, "%u", irq);
 	remove_proc_entry(name, root_irq_dir);
 }
 #undef MAX_NAMELEN
 void unregister_handler_proc(unsigned int irq, struct irqaction *action)
 {
 	proc_remove(action->dir);
 }
 static void register_default_affinity_proc(void)
 {
 #ifdef CONFIG_SMP
 	proc_create("irq/default_smp_affinity", 0644, NULL,
 		    &default_affinity_proc_fops);
 #endif
 }
 void init_irq_proc(void)
 {
 	unsigned int irq;
 	struct irq_desc *desc;
 	/* create /proc/irq */
 	root_irq_dir = proc_mkdir("irq", NULL);
 	if (!root_irq_dir)
 		return;
 	register_default_affinity_proc();
 	/*
 	 * Create entries for all existing IRQs.
 	 */
 	for_each_irq_desc(irq, desc) {
 		if (!desc)
 			continue;
 		register_irq_proc(irq, desc);
 	}
 }
 #ifdef CONFIG_GENERIC_IRQ_SHOW
 int __weak arch_show_interrupts(struct seq_file *p, int prec)
 {
 	return 0;
 }
 #ifndef ACTUAL_NR_IRQS
 # define ACTUAL_NR_IRQS nr_irqs
 #endif
 int show_interrupts(struct seq_file *p, void *v)
 {
 	static int prec;
 	unsigned long flags, any_count = 0;
 	int i = *(loff_t *) v, j;
 	struct irqaction *action;
 	struct irq_desc *desc;
 	if (i > ACTUAL_NR_IRQS)
 		return 0;
 	if (i == ACTUAL_NR_IRQS)
 		return arch_show_interrupts(p, prec);
 	/* print header and calculate the width of the first column */
 	if (i == 0) {
 		for (prec = 3, j = 1000; prec < 10 && j <= nr_irqs; ++prec)
 			j *= 10;
 		seq_printf(p, "%*s", prec + 8, "");
 		for_each_online_cpu(j)
 			seq_printf(p, "CPU%-8d", j);
 		seq_putc(p, '\n');
 	}
+	irq_lock_sparse();
 	desc = irq_to_desc(i);
 	if (!desc)
-		return 0;
+		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 && !any_count)
 		goto out;
 	seq_printf(p, "%*d: ", prec, i);
 	for_each_online_cpu(j)
 		seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
 	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);
 		else
 			seq_printf(p, " %8s", "-");
 	} else {
 		seq_printf(p, " %8s", "None");
 	}
 	if (desc->irq_data.domain)
 		seq_printf(p, " %*d", prec, (int) desc->irq_data.hwirq);
 #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);
 	if (action) {
 		seq_printf(p, "  %s", action->name);
 		while ((action = action->next) != NULL)
 			seq_printf(p, ", %s", action->name);
 	}
 	seq_putc(p, '\n');
 out:
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
+outsparse:
+	irq_unlock_sparse();
 	return 0;
 }
 #endif