linux_dsm_epyc7002/kernel/irq/irqdesc.c
Thomas Gleixner c291ee6221 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: 1f5a5b87f7 "genirq: Implement a sane sparse_irq allocator"
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org
2014-12-13 13:33:07 +01:00

649 lines
14 KiB
C

/*
* 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;
}