linux-sg2042/kernel/irq/proc.c

502 lines
12 KiB
C
Raw Normal View History

/*
* 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 cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#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"
genirq: Prevent proc race against freeing of irq descriptors Since the rework of the sparse interrupt code to actually free the unused interrupt descriptors there exists a race between the /proc interfaces to the irq subsystem and the code which frees the interrupt descriptor. CPU0 CPU1 show_interrupts() desc = irq_to_desc(X); free_desc(desc) remove_from_radix_tree(); kfree(desc); raw_spinlock_irq(&desc->lock); /proc/interrupts is the only interface which can actively corrupt kernel memory via the lock access. /proc/stat can only read from freed memory. Extremly hard to trigger, but possible. The interfaces in /proc/irq/N/ are not affected by this because the removal of the proc file is serialized in procfs against concurrent readers/writers. The removal happens before the descriptor is freed. For architectures which have CONFIG_SPARSE_IRQ=n this is a non issue as the descriptor is never freed. It's merely cleared out with the irq descriptor lock held. So any concurrent proc access will either see the old correct value or the cleared out ones. Protect the lookup and access to the irq descriptor in show_interrupts() with the sparse_irq_lock. Provide kstat_irqs_usr() which is protecting the lookup and access with sparse_irq_lock and switch /proc/stat to use it. Document the existing kstat_irqs interfaces so it's clear that the caller needs to take care about protection. The users of these interfaces are either not affected due to SPARSE_IRQ=n or already protected against removal. Fixes: 1f5a5b87f78f "genirq: Implement a sane sparse_irq allocator" Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: stable@vger.kernel.org
2014-12-12 06:01:41 +08:00
/*
* 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_printf(m, "%*pbl\n", cpumask_pr_args(mask));
else
seq_printf(m, "%*pb\n", cpumask_pr_args(mask));
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_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);
}
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_printf(m, "%*pb\n", cpumask_pr_args(irq_default_affinity));
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", 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)
{
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');
}
genirq: Prevent proc race against freeing of irq descriptors Since the rework of the sparse interrupt code to actually free the unused interrupt descriptors there exists a race between the /proc interfaces to the irq subsystem and the code which frees the interrupt descriptor. CPU0 CPU1 show_interrupts() desc = irq_to_desc(X); free_desc(desc) remove_from_radix_tree(); kfree(desc); raw_spinlock_irq(&desc->lock); /proc/interrupts is the only interface which can actively corrupt kernel memory via the lock access. /proc/stat can only read from freed memory. Extremly hard to trigger, but possible. The interfaces in /proc/irq/N/ are not affected by this because the removal of the proc file is serialized in procfs against concurrent readers/writers. The removal happens before the descriptor is freed. For architectures which have CONFIG_SPARSE_IRQ=n this is a non issue as the descriptor is never freed. It's merely cleared out with the irq descriptor lock held. So any concurrent proc access will either see the old correct value or the cleared out ones. Protect the lookup and access to the irq descriptor in show_interrupts() with the sparse_irq_lock. Provide kstat_irqs_usr() which is protecting the lookup and access with sparse_irq_lock and switch /proc/stat to use it. Document the existing kstat_irqs interfaces so it's clear that the caller needs to take care about protection. The users of these interfaces are either not affected due to SPARSE_IRQ=n or already protected against removal. Fixes: 1f5a5b87f78f "genirq: Implement a sane sparse_irq allocator" Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: stable@vger.kernel.org
2014-12-12 06:01:41 +08:00
irq_lock_sparse();
desc = irq_to_desc(i);
if (!desc)
genirq: Prevent proc race against freeing of irq descriptors Since the rework of the sparse interrupt code to actually free the unused interrupt descriptors there exists a race between the /proc interfaces to the irq subsystem and the code which frees the interrupt descriptor. CPU0 CPU1 show_interrupts() desc = irq_to_desc(X); free_desc(desc) remove_from_radix_tree(); kfree(desc); raw_spinlock_irq(&desc->lock); /proc/interrupts is the only interface which can actively corrupt kernel memory via the lock access. /proc/stat can only read from freed memory. Extremly hard to trigger, but possible. The interfaces in /proc/irq/N/ are not affected by this because the removal of the proc file is serialized in procfs against concurrent readers/writers. The removal happens before the descriptor is freed. For architectures which have CONFIG_SPARSE_IRQ=n this is a non issue as the descriptor is never freed. It's merely cleared out with the irq descriptor lock held. So any concurrent proc access will either see the old correct value or the cleared out ones. Protect the lookup and access to the irq descriptor in show_interrupts() with the sparse_irq_lock. Provide kstat_irqs_usr() which is protecting the lookup and access with sparse_irq_lock and switch /proc/stat to use it. Document the existing kstat_irqs interfaces so it's clear that the caller needs to take care about protection. The users of these interfaces are either not affected due to SPARSE_IRQ=n or already protected against removal. Fixes: 1f5a5b87f78f "genirq: Implement a sane sparse_irq allocator" Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: stable@vger.kernel.org
2014-12-12 06:01:41 +08:00
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);
genirq: Prevent proc race against freeing of irq descriptors Since the rework of the sparse interrupt code to actually free the unused interrupt descriptors there exists a race between the /proc interfaces to the irq subsystem and the code which frees the interrupt descriptor. CPU0 CPU1 show_interrupts() desc = irq_to_desc(X); free_desc(desc) remove_from_radix_tree(); kfree(desc); raw_spinlock_irq(&desc->lock); /proc/interrupts is the only interface which can actively corrupt kernel memory via the lock access. /proc/stat can only read from freed memory. Extremly hard to trigger, but possible. The interfaces in /proc/irq/N/ are not affected by this because the removal of the proc file is serialized in procfs against concurrent readers/writers. The removal happens before the descriptor is freed. For architectures which have CONFIG_SPARSE_IRQ=n this is a non issue as the descriptor is never freed. It's merely cleared out with the irq descriptor lock held. So any concurrent proc access will either see the old correct value or the cleared out ones. Protect the lookup and access to the irq descriptor in show_interrupts() with the sparse_irq_lock. Provide kstat_irqs_usr() which is protecting the lookup and access with sparse_irq_lock and switch /proc/stat to use it. Document the existing kstat_irqs interfaces so it's clear that the caller needs to take care about protection. The users of these interfaces are either not affected due to SPARSE_IRQ=n or already protected against removal. Fixes: 1f5a5b87f78f "genirq: Implement a sane sparse_irq allocator" Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: stable@vger.kernel.org
2014-12-12 06:01:41 +08:00
outsparse:
irq_unlock_sparse();
return 0;
}
#endif