Re: [PATCH 1/2] list: add hlist_unhashed_lockless()

From: Paul E. McKenney
Date: Sat Nov 09 2019 - 19:56:33 EST

Next message: Paul E. McKenney: "Re: [PATCH 1/2] list: add hlist_unhashed_lockless()"
Previous message: Sudip Mukherjee: "Re: libtraceevent installing in wrong folder"
In reply to: Eric Dumazet: "Re: [PATCH 1/2] list: add hlist_unhashed_lockless()"
Next in thread: Paul E. McKenney: "Re: [PATCH 1/2] list: add hlist_unhashed_lockless()"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

On Fri, Nov 08, 2019 at 07:15:16PM -0800, Eric Dumazet wrote:
> On Fri, Nov 8, 2019 at 3:42 PM Paul E. McKenney <paulmck@xxxxxxxxxx> wrote:
> >
> > On Fri, Nov 08, 2019 at 12:17:49PM -0800, Eric Dumazet wrote:
> > > On Fri, Nov 8, 2019 at 11:24 AM Paul E. McKenney <paulmck@xxxxxxxxxx> wrote:
> > > >
> > > > On Thu, Nov 07, 2019 at 11:37:37AM -0800, Eric Dumazet wrote:
> > > > > We would like to use hlist_unhashed() from timer_pending(),
> > > > > which runs without protection of a lock.
> > > > >
> > > > > Note that other callers might also want to use this variant.
> > > > >
> > > > > Instead of forcing a READ_ONCE() for all hlist_unhashed()
> > > > > callers, add a new helper with an explicit _lockless suffix
> > > > > in the name to better document what is going on.
> > > > >
> > > > > Also add various WRITE_ONCE() in __hlist_del(), hlist_add_head()
> > > > > and hlist_add_before()/hlist_add_behind() to pair with
> > > > > the READ_ONCE().
> > > > >
> > > > > Signed-off-by: Eric Dumazet <edumazet@xxxxxxxxxx>
> > > > > Cc: "Paul E. McKenney" <paulmck@xxxxxxxxxx>
> > > > > Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
> > > >
> > > > I have queued this, but if you prefer it go some other way:
> > > >
> > > > Acked-by: Paul E. McKenney <paulmck@xxxxxxxxxx>
> > > >
> > > > But shouldn't the uses in include/linux/rculist.h also be converted
> > > > into the patch below? If so, I will squash the following into your
> > > > patch.
> > > >
> > > > Thanx, Paul
> > > >
> > > > ------------------------------------------------------------------------
> > >
> > > Agreed, thanks for the addition of this Paul.
> >
> > Very good, squashed and pushed, thank you!
> >
>
> I have another KCSAN report of a bug that will force us to use
> hlist_unhashed_lockless() from sk_unhashed()
>
> (Meaning we also need to add some WRITE_ONCE() annotations to
> include/linux/list_nulls.h )
>
> BUG: KCSAN: data-race in inet_unhash / inet_unhash
>
> write to 0xffff8880a69a0170 of 8 bytes by interrupt on cpu 1:
> __hlist_nulls_del include/linux/list_nulls.h:88 [inline]
> hlist_nulls_del_init_rcu include/linux/rculist_nulls.h:36 [inline]
> __sk_nulls_del_node_init_rcu include/net/sock.h:676 [inline]
> inet_unhash+0x38f/0x4a0 net/ipv4/inet_hashtables.c:612
> tcp_set_state+0xfa/0x3e0 net/ipv4/tcp.c:2249
> tcp_done+0x93/0x1e0 net/ipv4/tcp.c:3854
> tcp_write_err+0x7e/0xc0 net/ipv4/tcp_timer.c:56
> tcp_retransmit_timer+0x9b8/0x16d0 net/ipv4/tcp_timer.c:479
> tcp_write_timer_handler+0x42d/0x510 net/ipv4/tcp_timer.c:599
> tcp_write_timer+0xd1/0xf0 net/ipv4/tcp_timer.c:619
> call_timer_fn+0x5f/0x2f0 kernel/time/timer.c:1404
> expire_timers kernel/time/timer.c:1449 [inline]
> __run_timers kernel/time/timer.c:1773 [inline]
> __run_timers kernel/time/timer.c:1740 [inline]
> run_timer_softirq+0xc0c/0xcd0 kernel/time/timer.c:1786
> __do_softirq+0x115/0x33f kernel/softirq.c:292
> invoke_softirq kernel/softirq.c:373 [inline]
> irq_exit+0xbb/0xe0 kernel/softirq.c:413
> exiting_irq arch/x86/include/asm/apic.h:536 [inline]
> smp_apic_timer_interrupt+0xe6/0x280 arch/x86/kernel/apic/apic.c:1137
> apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:830
> native_safe_halt+0xe/0x10 arch/x86/kernel/paravirt.c:71
> arch_cpu_idle+0x1f/0x30 arch/x86/kernel/process.c:571
> default_idle_call+0x1e/0x40 kernel/sched/idle.c:94
> cpuidle_idle_call kernel/sched/idle.c:154 [inline]
> do_idle+0x1af/0x280 kernel/sched/idle.c:263
> cpu_startup_entry+0x1b/0x20 kernel/sched/idle.c:355
> start_secondary+0x208/0x260 arch/x86/kernel/smpboot.c:264
> secondary_startup_64+0xa4/0xb0 arch/x86/kernel/head_64.S:241
>
> read to 0xffff8880a69a0170 of 8 bytes by interrupt on cpu 0:
> sk_unhashed include/net/sock.h:607 [inline]
> inet_unhash+0x3d/0x4a0 net/ipv4/inet_hashtables.c:592
> tcp_set_state+0xfa/0x3e0 net/ipv4/tcp.c:2249
> tcp_done+0x93/0x1e0 net/ipv4/tcp.c:3854
> tcp_write_err+0x7e/0xc0 net/ipv4/tcp_timer.c:56
> tcp_retransmit_timer+0x9b8/0x16d0 net/ipv4/tcp_timer.c:479
> tcp_write_timer_handler+0x42d/0x510 net/ipv4/tcp_timer.c:599
> tcp_write_timer+0xd1/0xf0 net/ipv4/tcp_timer.c:619
> call_timer_fn+0x5f/0x2f0 kernel/time/timer.c:1404
> expire_timers kernel/time/timer.c:1449 [inline]
> __run_timers kernel/time/timer.c:1773 [inline]
> __run_timers kernel/time/timer.c:1740 [inline]
> run_timer_softirq+0xc0c/0xcd0 kernel/time/timer.c:1786
> __do_softirq+0x115/0x33f kernel/softirq.c:292
> invoke_softirq kernel/softirq.c:373 [inline]
> irq_exit+0xbb/0xe0 kernel/softirq.c:413
> exiting_irq arch/x86/include/asm/apic.h:536 [inline]
> smp_apic_timer_interrupt+0xe6/0x280 arch/x86/kernel/apic/apic.c:1137
> apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:830
> native_safe_halt+0xe/0x10 arch/x86/kernel/paravirt.c:71
> arch_cpu_idle+0x1f/0x30 arch/x86/kernel/process.c:571
> default_idle_call+0x1e/0x40 kernel/sched/idle.c:94
> cpuidle_idle_call kernel/sched/idle.c:154 [inline]
> do_idle+0x1af/0x280 kernel/sched/idle.c:263
> cpu_startup_entry+0x1b/0x20 kernel/sched/idle.c:355
> rest_init+0xec/0xf6 init/main.c:452
> arch_call_rest_init+0x17/0x37
> start_kernel+0x838/0x85e init/main.c:786
> x86_64_start_reservations+0x29/0x2b arch/x86/kernel/head64.c:490
> x86_64_start_kernel+0x72/0x76 arch/x86/kernel/head64.c:471
> secondary_startup_64+0xa4/0xb0 arch/x86/kernel/head_64.S:241
>
> Reported by Kernel Concurrency Sanitizer on:
> CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.4.0-rc6+ #0
> Hardware name: Google Google Compute Engine/Google Compute Engine,
> BIOS Google 01/01/2011

Like this?

Thanx, Paul

------------------------------------------------------------------------

commit fef2da9c0cfa4f9ec405ff059fceb00d29de34dc
Author: Paul E. McKenney <paulmck@xxxxxxxxxx>
Date: Sat Nov 9 09:42:13 2019 -0800

rcu: Use WRITE_ONCE() for assignments to ->pprev for hlist_nulls

Eric Dumazet supplied a KCSAN report of a bug that forces use
of hlist_unhashed_lockless() from sk_unhashed():

------------------------------------------------------------------------

BUG: KCSAN: data-race in inet_unhash / inet_unhash

write to 0xffff8880a69a0170 of 8 bytes by interrupt on cpu 1:
__hlist_nulls_del include/linux/list_nulls.h:88 [inline]
hlist_nulls_del_init_rcu include/linux/rculist_nulls.h:36 [inline]
__sk_nulls_del_node_init_rcu include/net/sock.h:676 [inline]
inet_unhash+0x38f/0x4a0 net/ipv4/inet_hashtables.c:612
tcp_set_state+0xfa/0x3e0 net/ipv4/tcp.c:2249
tcp_done+0x93/0x1e0 net/ipv4/tcp.c:3854
tcp_write_err+0x7e/0xc0 net/ipv4/tcp_timer.c:56
tcp_retransmit_timer+0x9b8/0x16d0 net/ipv4/tcp_timer.c:479
tcp_write_timer_handler+0x42d/0x510 net/ipv4/tcp_timer.c:599
tcp_write_timer+0xd1/0xf0 net/ipv4/tcp_timer.c:619
call_timer_fn+0x5f/0x2f0 kernel/time/timer.c:1404
expire_timers kernel/time/timer.c:1449 [inline]
__run_timers kernel/time/timer.c:1773 [inline]
__run_timers kernel/time/timer.c:1740 [inline]
run_timer_softirq+0xc0c/0xcd0 kernel/time/timer.c:1786
__do_softirq+0x115/0x33f kernel/softirq.c:292
invoke_softirq kernel/softirq.c:373 [inline]
irq_exit+0xbb/0xe0 kernel/softirq.c:413
exiting_irq arch/x86/include/asm/apic.h:536 [inline]
smp_apic_timer_interrupt+0xe6/0x280 arch/x86/kernel/apic/apic.c:1137
apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:830
native_safe_halt+0xe/0x10 arch/x86/kernel/paravirt.c:71
arch_cpu_idle+0x1f/0x30 arch/x86/kernel/process.c:571
default_idle_call+0x1e/0x40 kernel/sched/idle.c:94
cpuidle_idle_call kernel/sched/idle.c:154 [inline]
do_idle+0x1af/0x280 kernel/sched/idle.c:263
cpu_startup_entry+0x1b/0x20 kernel/sched/idle.c:355
start_secondary+0x208/0x260 arch/x86/kernel/smpboot.c:264
secondary_startup_64+0xa4/0xb0 arch/x86/kernel/head_64.S:241

read to 0xffff8880a69a0170 of 8 bytes by interrupt on cpu 0:
sk_unhashed include/net/sock.h:607 [inline]
inet_unhash+0x3d/0x4a0 net/ipv4/inet_hashtables.c:592
tcp_set_state+0xfa/0x3e0 net/ipv4/tcp.c:2249
tcp_done+0x93/0x1e0 net/ipv4/tcp.c:3854
tcp_write_err+0x7e/0xc0 net/ipv4/tcp_timer.c:56
tcp_retransmit_timer+0x9b8/0x16d0 net/ipv4/tcp_timer.c:479
tcp_write_timer_handler+0x42d/0x510 net/ipv4/tcp_timer.c:599
tcp_write_timer+0xd1/0xf0 net/ipv4/tcp_timer.c:619
call_timer_fn+0x5f/0x2f0 kernel/time/timer.c:1404
expire_timers kernel/time/timer.c:1449 [inline]
__run_timers kernel/time/timer.c:1773 [inline]
__run_timers kernel/time/timer.c:1740 [inline]
run_timer_softirq+0xc0c/0xcd0 kernel/time/timer.c:1786
__do_softirq+0x115/0x33f kernel/softirq.c:292
invoke_softirq kernel/softirq.c:373 [inline]
irq_exit+0xbb/0xe0 kernel/softirq.c:413
exiting_irq arch/x86/include/asm/apic.h:536 [inline]
smp_apic_timer_interrupt+0xe6/0x280 arch/x86/kernel/apic/apic.c:1137
apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:830
native_safe_halt+0xe/0x10 arch/x86/kernel/paravirt.c:71
arch_cpu_idle+0x1f/0x30 arch/x86/kernel/process.c:571
default_idle_call+0x1e/0x40 kernel/sched/idle.c:94
cpuidle_idle_call kernel/sched/idle.c:154 [inline]
do_idle+0x1af/0x280 kernel/sched/idle.c:263
cpu_startup_entry+0x1b/0x20 kernel/sched/idle.c:355
rest_init+0xec/0xf6 init/main.c:452
arch_call_rest_init+0x17/0x37
start_kernel+0x838/0x85e init/main.c:786
x86_64_start_reservations+0x29/0x2b arch/x86/kernel/head64.c:490
x86_64_start_kernel+0x72/0x76 arch/x86/kernel/head64.c:471
secondary_startup_64+0xa4/0xb0 arch/x86/kernel/head_64.S:241

Reported by Kernel Concurrency Sanitizer on:
CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.4.0-rc6+ #0
Hardware name: Google Google Compute Engine/Google Compute Engine,
BIOS Google 01/01/2011

------------------------------------------------------------------------

This commit therefore replaces C-language assignments with WRITE_ONCE()
in include/linux/list_nulls.h and include/linux/rculist_nulls.h.

Reported-by: Eric Dumazet <edumazet@xxxxxxxxxx> # For KCSAN
Signed-off-by: Paul E. McKenney <paulmck@xxxxxxxxxx>

diff --git a/include/linux/list_nulls.h b/include/linux/list_nulls.h
index 3ef9674..1ecd356 100644
--- a/include/linux/list_nulls.h
+++ b/include/linux/list_nulls.h
@@ -72,10 +72,10 @@ static inline void hlist_nulls_add_head(struct hlist_nulls_node *n,
struct hlist_nulls_node *first = h->first;

n->next = first;
- n->pprev = &h->first;
+ WRITE_ONCE(n->pprev, &h->first);
h->first = n;
if (!is_a_nulls(first))
- first->pprev = &n->next;
+ WRITE_ONCE(first->pprev, &n->next);
}

static inline void __hlist_nulls_del(struct hlist_nulls_node *n)
@@ -85,13 +85,13 @@ static inline void __hlist_nulls_del(struct hlist_nulls_node *n)

WRITE_ONCE(*pprev, next);
if (!is_a_nulls(next))
- next->pprev = pprev;
+ WRITE_ONCE(next->pprev, pprev);
}

static inline void hlist_nulls_del(struct hlist_nulls_node *n)
{
__hlist_nulls_del(n);
- n->pprev = LIST_POISON2;
+ WRITE_ONCE(n->pprev, LIST_POISON2);
}

/**
diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h
index bc8206a..517a06f 100644
--- a/include/linux/rculist_nulls.h
+++ b/include/linux/rculist_nulls.h
@@ -34,7 +34,7 @@ static inline void hlist_nulls_del_init_rcu(struct hlist_nulls_node *n)
{
if (!hlist_nulls_unhashed(n)) {
__hlist_nulls_del(n);
- n->pprev = NULL;
+ WRITE_ONCE(n->pprev, NULL);
}
}

@@ -66,7 +66,7 @@ static inline void hlist_nulls_del_init_rcu(struct hlist_nulls_node *n)
static inline void hlist_nulls_del_rcu(struct hlist_nulls_node *n)
{
__hlist_nulls_del(n);
- n->pprev = LIST_POISON2;
+ WRITE_ONCE(n->pprev, LIST_POISON2);
}

/**
@@ -94,10 +94,10 @@ static inline void hlist_nulls_add_head_rcu(struct hlist_nulls_node *n,
struct hlist_nulls_node *first = h->first;

n->next = first;
- n->pprev = &h->first;
+ WRITE_ONCE(n->pprev, &h->first);
rcu_assign_pointer(hlist_nulls_first_rcu(h), n);
if (!is_a_nulls(first))
- first->pprev = &n->next;
+ WRITE_ONCE(first->pprev, &n->next);
}

/**

Next message: Paul E. McKenney: "Re: [PATCH 1/2] list: add hlist_unhashed_lockless()"
Previous message: Sudip Mukherjee: "Re: libtraceevent installing in wrong folder"
In reply to: Eric Dumazet: "Re: [PATCH 1/2] list: add hlist_unhashed_lockless()"
Next in thread: Paul E. McKenney: "Re: [PATCH 1/2] list: add hlist_unhashed_lockless()"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]