mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-26 19:00:25 +00:00
![Sahitya Tummala](/assets/img/avatar_default.png)
There is a potential race between ioc_release_fn() and ioc_clear_queue() as shown below, due to which below kernel crash is observed. It also can result into use-after-free issue. context#1: context#2: ioc_release_fn() __ioc_clear_queue() gets the same icq ->spin_lock(&ioc->lock); ->spin_lock(&ioc->lock); ->ioc_destroy_icq(icq); ->list_del_init(&icq->q_node); ->call_rcu(&icq->__rcu_head, icq_free_icq_rcu); ->spin_unlock(&ioc->lock); ->ioc_destroy_icq(icq); ->hlist_del_init(&icq->ioc_node); This results into below crash as this memory is now used by icq->__rcu_head in context#1. There is a chance that icq could be free'd as well. 22150.386550: <6> Unable to handle kernel write to read-only memory at virtual address ffffffaa8d31ca50 ... Call trace: 22150.607350: <2> ioc_destroy_icq+0x44/0x110 22150.611202: <2> ioc_clear_queue+0xac/0x148 22150.615056: <2> blk_cleanup_queue+0x11c/0x1a0 22150.619174: <2> __scsi_remove_device+0xdc/0x128 22150.623465: <2> scsi_forget_host+0x2c/0x78 22150.627315: <2> scsi_remove_host+0x7c/0x2a0 22150.631257: <2> usb_stor_disconnect+0x74/0xc8 22150.635371: <2> usb_unbind_interface+0xc8/0x278 22150.639665: <2> device_release_driver_internal+0x198/0x250 22150.644897: <2> device_release_driver+0x24/0x30 22150.649176: <2> bus_remove_device+0xec/0x140 22150.653204: <2> device_del+0x270/0x460 22150.656712: <2> usb_disable_device+0x120/0x390 22150.660918: <2> usb_disconnect+0xf4/0x2e0 22150.664684: <2> hub_event+0xd70/0x17e8 22150.668197: <2> process_one_work+0x210/0x480 22150.672222: <2> worker_thread+0x32c/0x4c8 Fix this by adding a new ICQ_DESTROYED flag in ioc_destroy_icq() to indicate this icq is once marked as destroyed. Also, ensure __ioc_clear_queue() is accessing icq within rcu_read_lock/unlock so that icq doesn't get free'd up while it is still using it. Signed-off-by: Sahitya Tummala <stummala@codeaurora.org> Co-developed-by: Pradeep P V K <ppvk@codeaurora.org> Signed-off-by: Pradeep P V K <ppvk@codeaurora.org> Signed-off-by: Jens Axboe <axboe@kernel.dk>
422 lines
10 KiB
C
422 lines
10 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* Functions related to io context handling
|
|
*/
|
|
#include <linux/kernel.h>
|
|
#include <linux/module.h>
|
|
#include <linux/init.h>
|
|
#include <linux/bio.h>
|
|
#include <linux/blkdev.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/sched/task.h>
|
|
|
|
#include "blk.h"
|
|
|
|
/*
|
|
* For io context allocations
|
|
*/
|
|
static struct kmem_cache *iocontext_cachep;
|
|
|
|
/**
|
|
* get_io_context - increment reference count to io_context
|
|
* @ioc: io_context to get
|
|
*
|
|
* Increment reference count to @ioc.
|
|
*/
|
|
void get_io_context(struct io_context *ioc)
|
|
{
|
|
BUG_ON(atomic_long_read(&ioc->refcount) <= 0);
|
|
atomic_long_inc(&ioc->refcount);
|
|
}
|
|
|
|
static void icq_free_icq_rcu(struct rcu_head *head)
|
|
{
|
|
struct io_cq *icq = container_of(head, struct io_cq, __rcu_head);
|
|
|
|
kmem_cache_free(icq->__rcu_icq_cache, icq);
|
|
}
|
|
|
|
/*
|
|
* Exit an icq. Called with ioc locked for blk-mq, and with both ioc
|
|
* and queue locked for legacy.
|
|
*/
|
|
static void ioc_exit_icq(struct io_cq *icq)
|
|
{
|
|
struct elevator_type *et = icq->q->elevator->type;
|
|
|
|
if (icq->flags & ICQ_EXITED)
|
|
return;
|
|
|
|
if (et->ops.exit_icq)
|
|
et->ops.exit_icq(icq);
|
|
|
|
icq->flags |= ICQ_EXITED;
|
|
}
|
|
|
|
/*
|
|
* Release an icq. Called with ioc locked for blk-mq, and with both ioc
|
|
* and queue locked for legacy.
|
|
*/
|
|
static void ioc_destroy_icq(struct io_cq *icq)
|
|
{
|
|
struct io_context *ioc = icq->ioc;
|
|
struct request_queue *q = icq->q;
|
|
struct elevator_type *et = q->elevator->type;
|
|
|
|
lockdep_assert_held(&ioc->lock);
|
|
|
|
radix_tree_delete(&ioc->icq_tree, icq->q->id);
|
|
hlist_del_init(&icq->ioc_node);
|
|
list_del_init(&icq->q_node);
|
|
|
|
/*
|
|
* Both setting lookup hint to and clearing it from @icq are done
|
|
* under queue_lock. If it's not pointing to @icq now, it never
|
|
* will. Hint assignment itself can race safely.
|
|
*/
|
|
if (rcu_access_pointer(ioc->icq_hint) == icq)
|
|
rcu_assign_pointer(ioc->icq_hint, NULL);
|
|
|
|
ioc_exit_icq(icq);
|
|
|
|
/*
|
|
* @icq->q might have gone away by the time RCU callback runs
|
|
* making it impossible to determine icq_cache. Record it in @icq.
|
|
*/
|
|
icq->__rcu_icq_cache = et->icq_cache;
|
|
icq->flags |= ICQ_DESTROYED;
|
|
call_rcu(&icq->__rcu_head, icq_free_icq_rcu);
|
|
}
|
|
|
|
/*
|
|
* Slow path for ioc release in put_io_context(). Performs double-lock
|
|
* dancing to unlink all icq's and then frees ioc.
|
|
*/
|
|
static void ioc_release_fn(struct work_struct *work)
|
|
{
|
|
struct io_context *ioc = container_of(work, struct io_context,
|
|
release_work);
|
|
unsigned long flags;
|
|
|
|
/*
|
|
* Exiting icq may call into put_io_context() through elevator
|
|
* which will trigger lockdep warning. The ioc's are guaranteed to
|
|
* be different, use a different locking subclass here. Use
|
|
* irqsave variant as there's no spin_lock_irq_nested().
|
|
*/
|
|
spin_lock_irqsave_nested(&ioc->lock, flags, 1);
|
|
|
|
while (!hlist_empty(&ioc->icq_list)) {
|
|
struct io_cq *icq = hlist_entry(ioc->icq_list.first,
|
|
struct io_cq, ioc_node);
|
|
struct request_queue *q = icq->q;
|
|
|
|
if (spin_trylock(&q->queue_lock)) {
|
|
ioc_destroy_icq(icq);
|
|
spin_unlock(&q->queue_lock);
|
|
} else {
|
|
spin_unlock_irqrestore(&ioc->lock, flags);
|
|
cpu_relax();
|
|
spin_lock_irqsave_nested(&ioc->lock, flags, 1);
|
|
}
|
|
}
|
|
|
|
spin_unlock_irqrestore(&ioc->lock, flags);
|
|
|
|
kmem_cache_free(iocontext_cachep, ioc);
|
|
}
|
|
|
|
/**
|
|
* put_io_context - put a reference of io_context
|
|
* @ioc: io_context to put
|
|
*
|
|
* Decrement reference count of @ioc and release it if the count reaches
|
|
* zero.
|
|
*/
|
|
void put_io_context(struct io_context *ioc)
|
|
{
|
|
unsigned long flags;
|
|
bool free_ioc = false;
|
|
|
|
if (ioc == NULL)
|
|
return;
|
|
|
|
BUG_ON(atomic_long_read(&ioc->refcount) <= 0);
|
|
|
|
/*
|
|
* Releasing ioc requires reverse order double locking and we may
|
|
* already be holding a queue_lock. Do it asynchronously from wq.
|
|
*/
|
|
if (atomic_long_dec_and_test(&ioc->refcount)) {
|
|
spin_lock_irqsave(&ioc->lock, flags);
|
|
if (!hlist_empty(&ioc->icq_list))
|
|
queue_work(system_power_efficient_wq,
|
|
&ioc->release_work);
|
|
else
|
|
free_ioc = true;
|
|
spin_unlock_irqrestore(&ioc->lock, flags);
|
|
}
|
|
|
|
if (free_ioc)
|
|
kmem_cache_free(iocontext_cachep, ioc);
|
|
}
|
|
|
|
/**
|
|
* put_io_context_active - put active reference on ioc
|
|
* @ioc: ioc of interest
|
|
*
|
|
* Undo get_io_context_active(). If active reference reaches zero after
|
|
* put, @ioc can never issue further IOs and ioscheds are notified.
|
|
*/
|
|
void put_io_context_active(struct io_context *ioc)
|
|
{
|
|
unsigned long flags;
|
|
struct io_cq *icq;
|
|
|
|
if (!atomic_dec_and_test(&ioc->active_ref)) {
|
|
put_io_context(ioc);
|
|
return;
|
|
}
|
|
|
|
/*
|
|
* Need ioc lock to walk icq_list and q lock to exit icq. Perform
|
|
* reverse double locking. Read comment in ioc_release_fn() for
|
|
* explanation on the nested locking annotation.
|
|
*/
|
|
spin_lock_irqsave_nested(&ioc->lock, flags, 1);
|
|
hlist_for_each_entry(icq, &ioc->icq_list, ioc_node) {
|
|
if (icq->flags & ICQ_EXITED)
|
|
continue;
|
|
|
|
ioc_exit_icq(icq);
|
|
}
|
|
spin_unlock_irqrestore(&ioc->lock, flags);
|
|
|
|
put_io_context(ioc);
|
|
}
|
|
|
|
/* Called by the exiting task */
|
|
void exit_io_context(struct task_struct *task)
|
|
{
|
|
struct io_context *ioc;
|
|
|
|
task_lock(task);
|
|
ioc = task->io_context;
|
|
task->io_context = NULL;
|
|
task_unlock(task);
|
|
|
|
atomic_dec(&ioc->nr_tasks);
|
|
put_io_context_active(ioc);
|
|
}
|
|
|
|
static void __ioc_clear_queue(struct list_head *icq_list)
|
|
{
|
|
unsigned long flags;
|
|
|
|
rcu_read_lock();
|
|
while (!list_empty(icq_list)) {
|
|
struct io_cq *icq = list_entry(icq_list->next,
|
|
struct io_cq, q_node);
|
|
struct io_context *ioc = icq->ioc;
|
|
|
|
spin_lock_irqsave(&ioc->lock, flags);
|
|
if (icq->flags & ICQ_DESTROYED) {
|
|
spin_unlock_irqrestore(&ioc->lock, flags);
|
|
continue;
|
|
}
|
|
ioc_destroy_icq(icq);
|
|
spin_unlock_irqrestore(&ioc->lock, flags);
|
|
}
|
|
rcu_read_unlock();
|
|
}
|
|
|
|
/**
|
|
* ioc_clear_queue - break any ioc association with the specified queue
|
|
* @q: request_queue being cleared
|
|
*
|
|
* Walk @q->icq_list and exit all io_cq's.
|
|
*/
|
|
void ioc_clear_queue(struct request_queue *q)
|
|
{
|
|
LIST_HEAD(icq_list);
|
|
|
|
spin_lock_irq(&q->queue_lock);
|
|
list_splice_init(&q->icq_list, &icq_list);
|
|
spin_unlock_irq(&q->queue_lock);
|
|
|
|
__ioc_clear_queue(&icq_list);
|
|
}
|
|
|
|
int create_task_io_context(struct task_struct *task, gfp_t gfp_flags, int node)
|
|
{
|
|
struct io_context *ioc;
|
|
int ret;
|
|
|
|
ioc = kmem_cache_alloc_node(iocontext_cachep, gfp_flags | __GFP_ZERO,
|
|
node);
|
|
if (unlikely(!ioc))
|
|
return -ENOMEM;
|
|
|
|
/* initialize */
|
|
atomic_long_set(&ioc->refcount, 1);
|
|
atomic_set(&ioc->nr_tasks, 1);
|
|
atomic_set(&ioc->active_ref, 1);
|
|
spin_lock_init(&ioc->lock);
|
|
INIT_RADIX_TREE(&ioc->icq_tree, GFP_ATOMIC);
|
|
INIT_HLIST_HEAD(&ioc->icq_list);
|
|
INIT_WORK(&ioc->release_work, ioc_release_fn);
|
|
|
|
/*
|
|
* Try to install. ioc shouldn't be installed if someone else
|
|
* already did or @task, which isn't %current, is exiting. Note
|
|
* that we need to allow ioc creation on exiting %current as exit
|
|
* path may issue IOs from e.g. exit_files(). The exit path is
|
|
* responsible for not issuing IO after exit_io_context().
|
|
*/
|
|
task_lock(task);
|
|
if (!task->io_context &&
|
|
(task == current || !(task->flags & PF_EXITING)))
|
|
task->io_context = ioc;
|
|
else
|
|
kmem_cache_free(iocontext_cachep, ioc);
|
|
|
|
ret = task->io_context ? 0 : -EBUSY;
|
|
|
|
task_unlock(task);
|
|
|
|
return ret;
|
|
}
|
|
|
|
/**
|
|
* get_task_io_context - get io_context of a task
|
|
* @task: task of interest
|
|
* @gfp_flags: allocation flags, used if allocation is necessary
|
|
* @node: allocation node, used if allocation is necessary
|
|
*
|
|
* Return io_context of @task. If it doesn't exist, it is created with
|
|
* @gfp_flags and @node. The returned io_context has its reference count
|
|
* incremented.
|
|
*
|
|
* This function always goes through task_lock() and it's better to use
|
|
* %current->io_context + get_io_context() for %current.
|
|
*/
|
|
struct io_context *get_task_io_context(struct task_struct *task,
|
|
gfp_t gfp_flags, int node)
|
|
{
|
|
struct io_context *ioc;
|
|
|
|
might_sleep_if(gfpflags_allow_blocking(gfp_flags));
|
|
|
|
do {
|
|
task_lock(task);
|
|
ioc = task->io_context;
|
|
if (likely(ioc)) {
|
|
get_io_context(ioc);
|
|
task_unlock(task);
|
|
return ioc;
|
|
}
|
|
task_unlock(task);
|
|
} while (!create_task_io_context(task, gfp_flags, node));
|
|
|
|
return NULL;
|
|
}
|
|
|
|
/**
|
|
* ioc_lookup_icq - lookup io_cq from ioc
|
|
* @ioc: the associated io_context
|
|
* @q: the associated request_queue
|
|
*
|
|
* Look up io_cq associated with @ioc - @q pair from @ioc. Must be called
|
|
* with @q->queue_lock held.
|
|
*/
|
|
struct io_cq *ioc_lookup_icq(struct io_context *ioc, struct request_queue *q)
|
|
{
|
|
struct io_cq *icq;
|
|
|
|
lockdep_assert_held(&q->queue_lock);
|
|
|
|
/*
|
|
* icq's are indexed from @ioc using radix tree and hint pointer,
|
|
* both of which are protected with RCU. All removals are done
|
|
* holding both q and ioc locks, and we're holding q lock - if we
|
|
* find a icq which points to us, it's guaranteed to be valid.
|
|
*/
|
|
rcu_read_lock();
|
|
icq = rcu_dereference(ioc->icq_hint);
|
|
if (icq && icq->q == q)
|
|
goto out;
|
|
|
|
icq = radix_tree_lookup(&ioc->icq_tree, q->id);
|
|
if (icq && icq->q == q)
|
|
rcu_assign_pointer(ioc->icq_hint, icq); /* allowed to race */
|
|
else
|
|
icq = NULL;
|
|
out:
|
|
rcu_read_unlock();
|
|
return icq;
|
|
}
|
|
EXPORT_SYMBOL(ioc_lookup_icq);
|
|
|
|
/**
|
|
* ioc_create_icq - create and link io_cq
|
|
* @ioc: io_context of interest
|
|
* @q: request_queue of interest
|
|
* @gfp_mask: allocation mask
|
|
*
|
|
* Make sure io_cq linking @ioc and @q exists. If icq doesn't exist, they
|
|
* will be created using @gfp_mask.
|
|
*
|
|
* The caller is responsible for ensuring @ioc won't go away and @q is
|
|
* alive and will stay alive until this function returns.
|
|
*/
|
|
struct io_cq *ioc_create_icq(struct io_context *ioc, struct request_queue *q,
|
|
gfp_t gfp_mask)
|
|
{
|
|
struct elevator_type *et = q->elevator->type;
|
|
struct io_cq *icq;
|
|
|
|
/* allocate stuff */
|
|
icq = kmem_cache_alloc_node(et->icq_cache, gfp_mask | __GFP_ZERO,
|
|
q->node);
|
|
if (!icq)
|
|
return NULL;
|
|
|
|
if (radix_tree_maybe_preload(gfp_mask) < 0) {
|
|
kmem_cache_free(et->icq_cache, icq);
|
|
return NULL;
|
|
}
|
|
|
|
icq->ioc = ioc;
|
|
icq->q = q;
|
|
INIT_LIST_HEAD(&icq->q_node);
|
|
INIT_HLIST_NODE(&icq->ioc_node);
|
|
|
|
/* lock both q and ioc and try to link @icq */
|
|
spin_lock_irq(&q->queue_lock);
|
|
spin_lock(&ioc->lock);
|
|
|
|
if (likely(!radix_tree_insert(&ioc->icq_tree, q->id, icq))) {
|
|
hlist_add_head(&icq->ioc_node, &ioc->icq_list);
|
|
list_add(&icq->q_node, &q->icq_list);
|
|
if (et->ops.init_icq)
|
|
et->ops.init_icq(icq);
|
|
} else {
|
|
kmem_cache_free(et->icq_cache, icq);
|
|
icq = ioc_lookup_icq(ioc, q);
|
|
if (!icq)
|
|
printk(KERN_ERR "cfq: icq link failed!\n");
|
|
}
|
|
|
|
spin_unlock(&ioc->lock);
|
|
spin_unlock_irq(&q->queue_lock);
|
|
radix_tree_preload_end();
|
|
return icq;
|
|
}
|
|
|
|
static int __init blk_ioc_init(void)
|
|
{
|
|
iocontext_cachep = kmem_cache_create("blkdev_ioc",
|
|
sizeof(struct io_context), 0, SLAB_PANIC, NULL);
|
|
return 0;
|
|
}
|
|
subsys_initcall(blk_ioc_init);
|