linux-stable/kernel/bpf/percpu_freelist.c
Song Liu 39d8f0d102 bpf: Use raw_spin_trylock() for pcpu_freelist_push/pop in NMI
Recent improvements in LOCKDEP highlighted a potential A-A deadlock with
pcpu_freelist in NMI:

./tools/testing/selftests/bpf/test_progs -t stacktrace_build_id_nmi

[   18.984807] ================================
[   18.984807] WARNING: inconsistent lock state
[   18.984808] 5.9.0-rc6-01771-g1466de1330e1 #2967 Not tainted
[   18.984809] --------------------------------
[   18.984809] inconsistent {INITIAL USE} -> {IN-NMI} usage.
[   18.984810] test_progs/1990 [HC2[2]:SC0[0]:HE0:SE1] takes:
[   18.984810] ffffe8ffffc219c0 (&head->lock){....}-{2:2}, at: __pcpu_freelist_pop+0xe3/0x180
[   18.984813] {INITIAL USE} state was registered at:
[   18.984814]   lock_acquire+0x175/0x7c0
[   18.984814]   _raw_spin_lock+0x2c/0x40
[   18.984815]   __pcpu_freelist_pop+0xe3/0x180
[   18.984815]   pcpu_freelist_pop+0x31/0x40
[   18.984816]   htab_map_alloc+0xbbf/0xf40
[   18.984816]   __do_sys_bpf+0x5aa/0x3ed0
[   18.984817]   do_syscall_64+0x2d/0x40
[   18.984818]   entry_SYSCALL_64_after_hwframe+0x44/0xa9
[   18.984818] irq event stamp: 12
[...]
[   18.984822] other info that might help us debug this:
[   18.984823]  Possible unsafe locking scenario:
[   18.984823]
[   18.984824]        CPU0
[   18.984824]        ----
[   18.984824]   lock(&head->lock);
[   18.984826]   <Interrupt>
[   18.984826]     lock(&head->lock);
[   18.984827]
[   18.984828]  *** DEADLOCK ***
[   18.984828]
[   18.984829] 2 locks held by test_progs/1990:
[...]
[   18.984838]  <NMI>
[   18.984838]  dump_stack+0x9a/0xd0
[   18.984839]  lock_acquire+0x5c9/0x7c0
[   18.984839]  ? lock_release+0x6f0/0x6f0
[   18.984840]  ? __pcpu_freelist_pop+0xe3/0x180
[   18.984840]  _raw_spin_lock+0x2c/0x40
[   18.984841]  ? __pcpu_freelist_pop+0xe3/0x180
[   18.984841]  __pcpu_freelist_pop+0xe3/0x180
[   18.984842]  pcpu_freelist_pop+0x17/0x40
[   18.984842]  ? lock_release+0x6f0/0x6f0
[   18.984843]  __bpf_get_stackid+0x534/0xaf0
[   18.984843]  bpf_prog_1fd9e30e1438d3c5_oncpu+0x73/0x350
[   18.984844]  bpf_overflow_handler+0x12f/0x3f0

This is because pcpu_freelist_head.lock is accessed in both NMI and
non-NMI context. Fix this issue by using raw_spin_trylock() in NMI.

Since NMI interrupts non-NMI context, when NMI context tries to lock the
raw_spinlock, non-NMI context of the same CPU may already have locked a
lock and is blocked from unlocking the lock. For a system with N CPUs,
there could be N NMIs at the same time, and they may block N non-NMI
raw_spinlocks. This is tricky for pcpu_freelist_push(), where unlike
_pop(), failing _push() means leaking memory. This issue is more likely to
trigger in non-SMP system.

Fix this issue with an extra list, pcpu_freelist.extralist. The extralist
is primarily used to take _push() when raw_spin_trylock() failed on all
the per CPU lists. It should be empty most of the time. The following
table summarizes the behavior of pcpu_freelist in NMI and non-NMI:

non-NMI pop(): 	use _lock(); check per CPU lists first;
                if all per CPU lists are empty, check extralist;
                if extralist is empty, return NULL.

non-NMI push(): use _lock(); only push to per CPU lists.

NMI pop():    use _trylock(); check per CPU lists first;
              if all per CPU lists are locked or empty, check extralist;
              if extralist is locked or empty, return NULL.

NMI push():   use _trylock(); check per CPU lists first;
              if all per CPU lists are locked; try push to extralist;
              if extralist is also locked, keep trying on per CPU lists.

Reported-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20201005165838.3735218-1-songliubraving@fb.com
2020-10-06 00:04:11 +02:00

209 lines
4.7 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2016 Facebook
*/
#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;
}
raw_spin_lock_init(&s->extralist.lock);
s->extralist.first = NULL;
return 0;
}
void pcpu_freelist_destroy(struct pcpu_freelist *s)
{
free_percpu(s->freelist);
}
static inline void pcpu_freelist_push_node(struct pcpu_freelist_head *head,
struct pcpu_freelist_node *node)
{
node->next = head->first;
head->first = node;
}
static inline void ___pcpu_freelist_push(struct pcpu_freelist_head *head,
struct pcpu_freelist_node *node)
{
raw_spin_lock(&head->lock);
pcpu_freelist_push_node(head, node);
raw_spin_unlock(&head->lock);
}
static inline bool pcpu_freelist_try_push_extra(struct pcpu_freelist *s,
struct pcpu_freelist_node *node)
{
if (!raw_spin_trylock(&s->extralist.lock))
return false;
pcpu_freelist_push_node(&s->extralist, node);
raw_spin_unlock(&s->extralist.lock);
return true;
}
static inline void ___pcpu_freelist_push_nmi(struct pcpu_freelist *s,
struct pcpu_freelist_node *node)
{
int cpu, orig_cpu;
orig_cpu = cpu = raw_smp_processor_id();
while (1) {
struct pcpu_freelist_head *head;
head = per_cpu_ptr(s->freelist, cpu);
if (raw_spin_trylock(&head->lock)) {
pcpu_freelist_push_node(head, node);
raw_spin_unlock(&head->lock);
return;
}
cpu = cpumask_next(cpu, cpu_possible_mask);
if (cpu >= nr_cpu_ids)
cpu = 0;
/* cannot lock any per cpu lock, try extralist */
if (cpu == orig_cpu &&
pcpu_freelist_try_push_extra(s, node))
return;
}
}
void __pcpu_freelist_push(struct pcpu_freelist *s,
struct pcpu_freelist_node *node)
{
if (in_nmi())
___pcpu_freelist_push_nmi(s, node);
else
___pcpu_freelist_push(this_cpu_ptr(s->freelist), node);
}
void pcpu_freelist_push(struct pcpu_freelist *s,
struct pcpu_freelist_node *node)
{
unsigned long flags;
local_irq_save(flags);
__pcpu_freelist_push(s, node);
local_irq_restore(flags);
}
void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size,
u32 nr_elems)
{
struct pcpu_freelist_head *head;
int i, cpu, pcpu_entries;
pcpu_entries = nr_elems / num_possible_cpus() + 1;
i = 0;
for_each_possible_cpu(cpu) {
again:
head = per_cpu_ptr(s->freelist, cpu);
/* No locking required as this is not visible yet. */
pcpu_freelist_push_node(head, buf);
i++;
buf += elem_size;
if (i == nr_elems)
break;
if (i % pcpu_entries)
goto again;
}
}
static struct pcpu_freelist_node *___pcpu_freelist_pop(struct pcpu_freelist *s)
{
struct pcpu_freelist_head *head;
struct pcpu_freelist_node *node;
int orig_cpu, cpu;
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(&head->lock);
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)
break;
}
/* per cpu lists are all empty, try extralist */
raw_spin_lock(&s->extralist.lock);
node = s->extralist.first;
if (node)
s->extralist.first = node->next;
raw_spin_unlock(&s->extralist.lock);
return node;
}
static struct pcpu_freelist_node *
___pcpu_freelist_pop_nmi(struct pcpu_freelist *s)
{
struct pcpu_freelist_head *head;
struct pcpu_freelist_node *node;
int orig_cpu, cpu;
orig_cpu = cpu = raw_smp_processor_id();
while (1) {
head = per_cpu_ptr(s->freelist, cpu);
if (raw_spin_trylock(&head->lock)) {
node = head->first;
if (node) {
head->first = node->next;
raw_spin_unlock(&head->lock);
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)
break;
}
/* cannot pop from per cpu lists, try extralist */
if (!raw_spin_trylock(&s->extralist.lock))
return NULL;
node = s->extralist.first;
if (node)
s->extralist.first = node->next;
raw_spin_unlock(&s->extralist.lock);
return node;
}
struct pcpu_freelist_node *__pcpu_freelist_pop(struct pcpu_freelist *s)
{
if (in_nmi())
return ___pcpu_freelist_pop_nmi(s);
return ___pcpu_freelist_pop(s);
}
struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *s)
{
struct pcpu_freelist_node *ret;
unsigned long flags;
local_irq_save(flags);
ret = __pcpu_freelist_pop(s);
local_irq_restore(flags);
return ret;
}