mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-13 05:56:38 +07:00
89ad2fa3f0
pcpu_freelist_pop() needs the same lockdep awareness than
pcpu_freelist_populate() to avoid a false positive.
[ INFO: SOFTIRQ-safe -> SOFTIRQ-unsafe lock order detected ]
switchto-defaul/12508 [HC0[0]:SC0[6]:HE0:SE0] is trying to acquire:
(&htab->buckets[i].lock){......}, at: [<ffffffff9dc099cb>] __htab_percpu_map_update_elem+0x1cb/0x300
and this task is already holding:
(dev_queue->dev->qdisc_class ?: &qdisc_tx_lock#2){+.-...}, at: [<ffffffff9e135848>] __dev_queue_xmit+0
x868/0x1240
which would create a new lock dependency:
(dev_queue->dev->qdisc_class ?: &qdisc_tx_lock#2){+.-...} -> (&htab->buckets[i].lock){......}
but this new dependency connects a SOFTIRQ-irq-safe lock:
(dev_queue->dev->qdisc_class ?: &qdisc_tx_lock#2){+.-...}
... which became SOFTIRQ-irq-safe at:
[<ffffffff9db5931b>] __lock_acquire+0x42b/0x1f10
[<ffffffff9db5b32c>] lock_acquire+0xbc/0x1b0
[<ffffffff9da05e38>] _raw_spin_lock+0x38/0x50
[<ffffffff9e135848>] __dev_queue_xmit+0x868/0x1240
[<ffffffff9e136240>] dev_queue_xmit+0x10/0x20
[<ffffffff9e1965d9>] ip_finish_output2+0x439/0x590
[<ffffffff9e197410>] ip_finish_output+0x150/0x2f0
[<ffffffff9e19886d>] ip_output+0x7d/0x260
[<ffffffff9e19789e>] ip_local_out+0x5e/0xe0
[<ffffffff9e197b25>] ip_queue_xmit+0x205/0x620
[<ffffffff9e1b8398>] tcp_transmit_skb+0x5a8/0xcb0
[<ffffffff9e1ba152>] tcp_write_xmit+0x242/0x1070
[<ffffffff9e1baffc>] __tcp_push_pending_frames+0x3c/0xf0
[<ffffffff9e1b3472>] tcp_rcv_established+0x312/0x700
[<ffffffff9e1c1acc>] tcp_v4_do_rcv+0x11c/0x200
[<ffffffff9e1c3dc2>] tcp_v4_rcv+0xaa2/0xc30
[<ffffffff9e191107>] ip_local_deliver_finish+0xa7/0x240
[<ffffffff9e191a36>] ip_local_deliver+0x66/0x200
[<ffffffff9e19137d>] ip_rcv_finish+0xdd/0x560
[<ffffffff9e191e65>] ip_rcv+0x295/0x510
[<ffffffff9e12ff88>] __netif_receive_skb_core+0x988/0x1020
[<ffffffff9e130641>] __netif_receive_skb+0x21/0x70
[<ffffffff9e1306ff>] process_backlog+0x6f/0x230
[<ffffffff9e132129>] net_rx_action+0x229/0x420
[<ffffffff9da07ee8>] __do_softirq+0xd8/0x43d
[<ffffffff9e282bcc>] do_softirq_own_stack+0x1c/0x30
[<ffffffff9dafc2f5>] do_softirq+0x55/0x60
[<ffffffff9dafc3a8>] __local_bh_enable_ip+0xa8/0xb0
[<ffffffff9db4c727>] cpu_startup_entry+0x1c7/0x500
[<ffffffff9daab333>] start_secondary+0x113/0x140
to a SOFTIRQ-irq-unsafe lock:
(&head->lock){+.+...}
... which became SOFTIRQ-irq-unsafe at:
... [<ffffffff9db5971f>] __lock_acquire+0x82f/0x1f10
[<ffffffff9db5b32c>] lock_acquire+0xbc/0x1b0
[<ffffffff9da05e38>] _raw_spin_lock+0x38/0x50
[<ffffffff9dc0b7fa>] pcpu_freelist_pop+0x7a/0xb0
[<ffffffff9dc08b2c>] htab_map_alloc+0x50c/0x5f0
[<ffffffff9dc00dc5>] SyS_bpf+0x265/0x1200
[<ffffffff9e28195f>] entry_SYSCALL_64_fastpath+0x12/0x17
other info that might help us debug this:
Chain exists of:
dev_queue->dev->qdisc_class ?: &qdisc_tx_lock#2 --> &htab->buckets[i].lock --> &head->lock
Possible interrupt unsafe locking scenario:
CPU0 CPU1
---- ----
lock(&head->lock);
local_irq_disable();
lock(dev_queue->dev->qdisc_class ?: &qdisc_tx_lock#2);
lock(&htab->buckets[i].lock);
<Interrupt>
lock(dev_queue->dev->qdisc_class ?: &qdisc_tx_lock#2);
*** DEADLOCK ***
Fixes: e19494edab ("bpf: introduce percpu_freelist")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
105 lines
2.3 KiB
C
105 lines
2.3 KiB
C
/* Copyright (c) 2016 Facebook
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of version 2 of the GNU General Public
|
|
* License as published by the Free Software Foundation.
|
|
*/
|
|
#include "percpu_freelist.h"
|
|
|
|
int pcpu_freelist_init(struct pcpu_freelist *s)
|
|
{
|
|
int cpu;
|
|
|
|
s->freelist = alloc_percpu(struct pcpu_freelist_head);
|
|
if (!s->freelist)
|
|
return -ENOMEM;
|
|
|
|
for_each_possible_cpu(cpu) {
|
|
struct pcpu_freelist_head *head = per_cpu_ptr(s->freelist, cpu);
|
|
|
|
raw_spin_lock_init(&head->lock);
|
|
head->first = NULL;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
void pcpu_freelist_destroy(struct pcpu_freelist *s)
|
|
{
|
|
free_percpu(s->freelist);
|
|
}
|
|
|
|
static inline void __pcpu_freelist_push(struct pcpu_freelist_head *head,
|
|
struct pcpu_freelist_node *node)
|
|
{
|
|
raw_spin_lock(&head->lock);
|
|
node->next = head->first;
|
|
head->first = node;
|
|
raw_spin_unlock(&head->lock);
|
|
}
|
|
|
|
void pcpu_freelist_push(struct pcpu_freelist *s,
|
|
struct pcpu_freelist_node *node)
|
|
{
|
|
struct pcpu_freelist_head *head = this_cpu_ptr(s->freelist);
|
|
|
|
__pcpu_freelist_push(head, node);
|
|
}
|
|
|
|
void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size,
|
|
u32 nr_elems)
|
|
{
|
|
struct pcpu_freelist_head *head;
|
|
unsigned long flags;
|
|
int i, cpu, pcpu_entries;
|
|
|
|
pcpu_entries = nr_elems / num_possible_cpus() + 1;
|
|
i = 0;
|
|
|
|
/* disable irq to workaround lockdep false positive
|
|
* in bpf usage pcpu_freelist_populate() will never race
|
|
* with pcpu_freelist_push()
|
|
*/
|
|
local_irq_save(flags);
|
|
for_each_possible_cpu(cpu) {
|
|
again:
|
|
head = per_cpu_ptr(s->freelist, cpu);
|
|
__pcpu_freelist_push(head, buf);
|
|
i++;
|
|
buf += elem_size;
|
|
if (i == nr_elems)
|
|
break;
|
|
if (i % pcpu_entries)
|
|
goto again;
|
|
}
|
|
local_irq_restore(flags);
|
|
}
|
|
|
|
struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *s)
|
|
{
|
|
struct pcpu_freelist_head *head;
|
|
struct pcpu_freelist_node *node;
|
|
unsigned long flags;
|
|
int orig_cpu, cpu;
|
|
|
|
local_irq_save(flags);
|
|
orig_cpu = cpu = raw_smp_processor_id();
|
|
while (1) {
|
|
head = per_cpu_ptr(s->freelist, cpu);
|
|
raw_spin_lock(&head->lock);
|
|
node = head->first;
|
|
if (node) {
|
|
head->first = node->next;
|
|
raw_spin_unlock_irqrestore(&head->lock, flags);
|
|
return node;
|
|
}
|
|
raw_spin_unlock(&head->lock);
|
|
cpu = cpumask_next(cpu, cpu_possible_mask);
|
|
if (cpu >= nr_cpu_ids)
|
|
cpu = 0;
|
|
if (cpu == orig_cpu) {
|
|
local_irq_restore(flags);
|
|
return NULL;
|
|
}
|
|
}
|
|
}
|