Revision 8700aff089843399f95bc7701ae87b642b35a716 authored by Edward Cree on 20 December 2019, 16:26:40 UTC, committed by David S. Miller on 21 December 2019, 05:56:48 UTC
It was possible for channel allocation logic to get confused between what it had and what it wanted, and end up trying to use the same channel for both PTP and regular TX. This led to a kernel panic: BUG: unable to handle page fault for address: 0000000000047635 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD 0 P4D 0 Oops: 0002 [#1] SMP PTI CPU: 0 PID: 0 Comm: swapper/0 Tainted: G W 5.4.0-rc3-ehc14+ #900 Hardware name: Dell Inc. PowerEdge R710/0M233H, BIOS 6.4.0 07/23/2013 RIP: 0010:native_queued_spin_lock_slowpath+0x188/0x1e0 Code: f3 90 48 8b 32 48 85 f6 74 f6 eb e8 c1 ee 12 83 e0 03 83 ee 01 48 c1 e0 05 48 63 f6 48 05 c0 98 02 00 48 03 04 f5 a0 c6 ed 81 <48> 89 10 8b 42 08 85 c0 75 09 f3 90 8b 42 08 85 c0 74 f7 48 8b 32 RSP: 0018:ffffc90000003d28 EFLAGS: 00010006 RAX: 0000000000047635 RBX: 0000000000000246 RCX: 0000000000040000 RDX: ffff888627a298c0 RSI: 0000000000003ffe RDI: ffff88861f6b8dd4 RBP: ffff8886225c6e00 R08: 0000000000040000 R09: 0000000000000000 R10: 0000000616f080c6 R11: 00000000000000c0 R12: ffff88861f6b8dd4 R13: ffffc90000003dc8 R14: ffff88861942bf00 R15: ffff8886150f2000 FS: 0000000000000000(0000) GS:ffff888627a00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000047635 CR3: 000000000200a000 CR4: 00000000000006f0 Call Trace: <IRQ> _raw_spin_lock_irqsave+0x22/0x30 skb_queue_tail+0x1b/0x50 sock_queue_err_skb+0x9d/0xf0 __skb_complete_tx_timestamp+0x9d/0xc0 efx_dequeue_buffer+0x126/0x180 [sfc] efx_xmit_done+0x73/0x1c0 [sfc] efx_ef10_ev_process+0x56a/0xfe0 [sfc] ? tick_sched_do_timer+0x60/0x60 ? timerqueue_add+0x5d/0x70 ? enqueue_hrtimer+0x39/0x90 efx_poll+0x111/0x380 [sfc] ? rcu_accelerate_cbs+0x50/0x160 net_rx_action+0x14a/0x400 __do_softirq+0xdd/0x2d0 irq_exit+0xa0/0xb0 do_IRQ+0x53/0xe0 common_interrupt+0xf/0xf </IRQ> In the long run we intend to rewrite the channel allocation code, but for 'net' fix this by allocating extra_channels, and giving them TX queues, even if we do not in fact need them (e.g. on NICs without MAC TX timestamping), and thereby using simpler logic to assign the channels once they're allocated. Fixes: 3990a8fffbda ("sfc: allocate channels for XDP tx queues") Signed-off-by: Edward Cree <ecree@solarflare.com> Signed-off-by: David S. Miller <davem@davemloft.net>
1 parent 258a980
blk-ioc.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;
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;
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);
ioc_destroy_icq(icq);
spin_unlock_irqrestore(&ioc->lock, flags);
}
}
/**
* 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);
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...