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-stat.c
// SPDX-License-Identifier: GPL-2.0
/*
* Block stat tracking code
*
* Copyright (C) 2016 Jens Axboe
*/
#include <linux/kernel.h>
#include <linux/rculist.h>
#include <linux/blk-mq.h>
#include "blk-stat.h"
#include "blk-mq.h"
#include "blk.h"
struct blk_queue_stats {
struct list_head callbacks;
spinlock_t lock;
bool enable_accounting;
};
void blk_rq_stat_init(struct blk_rq_stat *stat)
{
stat->min = -1ULL;
stat->max = stat->nr_samples = stat->mean = 0;
stat->batch = 0;
}
/* src is a per-cpu stat, mean isn't initialized */
void blk_rq_stat_sum(struct blk_rq_stat *dst, struct blk_rq_stat *src)
{
if (!src->nr_samples)
return;
dst->min = min(dst->min, src->min);
dst->max = max(dst->max, src->max);
dst->mean = div_u64(src->batch + dst->mean * dst->nr_samples,
dst->nr_samples + src->nr_samples);
dst->nr_samples += src->nr_samples;
}
void blk_rq_stat_add(struct blk_rq_stat *stat, u64 value)
{
stat->min = min(stat->min, value);
stat->max = max(stat->max, value);
stat->batch += value;
stat->nr_samples++;
}
void blk_stat_add(struct request *rq, u64 now)
{
struct request_queue *q = rq->q;
struct blk_stat_callback *cb;
struct blk_rq_stat *stat;
int bucket, cpu;
u64 value;
value = (now >= rq->io_start_time_ns) ? now - rq->io_start_time_ns : 0;
blk_throtl_stat_add(rq, value);
rcu_read_lock();
cpu = get_cpu();
list_for_each_entry_rcu(cb, &q->stats->callbacks, list) {
if (!blk_stat_is_active(cb))
continue;
bucket = cb->bucket_fn(rq);
if (bucket < 0)
continue;
stat = &per_cpu_ptr(cb->cpu_stat, cpu)[bucket];
blk_rq_stat_add(stat, value);
}
put_cpu();
rcu_read_unlock();
}
static void blk_stat_timer_fn(struct timer_list *t)
{
struct blk_stat_callback *cb = from_timer(cb, t, timer);
unsigned int bucket;
int cpu;
for (bucket = 0; bucket < cb->buckets; bucket++)
blk_rq_stat_init(&cb->stat[bucket]);
for_each_online_cpu(cpu) {
struct blk_rq_stat *cpu_stat;
cpu_stat = per_cpu_ptr(cb->cpu_stat, cpu);
for (bucket = 0; bucket < cb->buckets; bucket++) {
blk_rq_stat_sum(&cb->stat[bucket], &cpu_stat[bucket]);
blk_rq_stat_init(&cpu_stat[bucket]);
}
}
cb->timer_fn(cb);
}
struct blk_stat_callback *
blk_stat_alloc_callback(void (*timer_fn)(struct blk_stat_callback *),
int (*bucket_fn)(const struct request *),
unsigned int buckets, void *data)
{
struct blk_stat_callback *cb;
cb = kmalloc(sizeof(*cb), GFP_KERNEL);
if (!cb)
return NULL;
cb->stat = kmalloc_array(buckets, sizeof(struct blk_rq_stat),
GFP_KERNEL);
if (!cb->stat) {
kfree(cb);
return NULL;
}
cb->cpu_stat = __alloc_percpu(buckets * sizeof(struct blk_rq_stat),
__alignof__(struct blk_rq_stat));
if (!cb->cpu_stat) {
kfree(cb->stat);
kfree(cb);
return NULL;
}
cb->timer_fn = timer_fn;
cb->bucket_fn = bucket_fn;
cb->data = data;
cb->buckets = buckets;
timer_setup(&cb->timer, blk_stat_timer_fn, 0);
return cb;
}
void blk_stat_add_callback(struct request_queue *q,
struct blk_stat_callback *cb)
{
unsigned int bucket;
int cpu;
for_each_possible_cpu(cpu) {
struct blk_rq_stat *cpu_stat;
cpu_stat = per_cpu_ptr(cb->cpu_stat, cpu);
for (bucket = 0; bucket < cb->buckets; bucket++)
blk_rq_stat_init(&cpu_stat[bucket]);
}
spin_lock(&q->stats->lock);
list_add_tail_rcu(&cb->list, &q->stats->callbacks);
blk_queue_flag_set(QUEUE_FLAG_STATS, q);
spin_unlock(&q->stats->lock);
}
void blk_stat_remove_callback(struct request_queue *q,
struct blk_stat_callback *cb)
{
spin_lock(&q->stats->lock);
list_del_rcu(&cb->list);
if (list_empty(&q->stats->callbacks) && !q->stats->enable_accounting)
blk_queue_flag_clear(QUEUE_FLAG_STATS, q);
spin_unlock(&q->stats->lock);
del_timer_sync(&cb->timer);
}
static void blk_stat_free_callback_rcu(struct rcu_head *head)
{
struct blk_stat_callback *cb;
cb = container_of(head, struct blk_stat_callback, rcu);
free_percpu(cb->cpu_stat);
kfree(cb->stat);
kfree(cb);
}
void blk_stat_free_callback(struct blk_stat_callback *cb)
{
if (cb)
call_rcu(&cb->rcu, blk_stat_free_callback_rcu);
}
void blk_stat_enable_accounting(struct request_queue *q)
{
spin_lock(&q->stats->lock);
q->stats->enable_accounting = true;
blk_queue_flag_set(QUEUE_FLAG_STATS, q);
spin_unlock(&q->stats->lock);
}
EXPORT_SYMBOL_GPL(blk_stat_enable_accounting);
struct blk_queue_stats *blk_alloc_queue_stats(void)
{
struct blk_queue_stats *stats;
stats = kmalloc(sizeof(*stats), GFP_KERNEL);
if (!stats)
return NULL;
INIT_LIST_HEAD(&stats->callbacks);
spin_lock_init(&stats->lock);
stats->enable_accounting = false;
return stats;
}
void blk_free_queue_stats(struct blk_queue_stats *stats)
{
if (!stats)
return;
WARN_ON(!list_empty(&stats->callbacks));
kfree(stats);
}
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...