| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20080528072618.GA6496@linux.vnet.ibm.com>
Date: Wed, 28 May 2008 00:26:18 -0700
From: "Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>
To: Linus Torvalds <torvalds@...ux-foundation.org>
Cc: Oleg Nesterov <oleg@...sign.ru>,
Alexey Dobriyan <adobriyan@...il.com>,
Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
Andrew Morton <akpm@...ux-foundation.org>
Subject: Re: 2.6.26-rc4: RIP find_pid_ns+0x6b/0xa0
On Tue, May 27, 2008 at 10:01:50PM -0700, Paul E. McKenney wrote:
> On Tue, May 27, 2008 at 10:06:11AM -0700, Paul E. McKenney wrote:
> > On Tue, May 27, 2008 at 09:11:33AM -0700, Linus Torvalds wrote:
> > > On Tue, 27 May 2008, Paul E. McKenney wrote:
> > > >
> > > > But this will only help until preemptible spinlocks arrive, right?
> > >
> > > I don't think we will ever have preemptible spinlocks.
> > >
> > > If you preempt spinlocks, you have serious issues with contention and
> > > priority inversion etc, and you basically need to turn them into sleeping
> > > mutexes. So now you also need to do interrupts as sleepable threads etc
> > > etc.
> >
> > Indeed, all of these are required in that case.
> >
> > > And it would break the existing non-preempt RCU usage anyway.
> >
> > Yes, preemptable spinlocks cannot work without preemptable RCU.
> >
> > > Yeah, maybe the RT people try to do that, but quite frankly, it is insane.
> > > Spinlocks are *different* from sleeping locks, for a damn good reason.
> >
> > Well, I guess I never claimed to be sane...
> >
> > Anyway, will look at a preemptable RCU that waits for preempt-disable
> > sections of code.
>
> And here is a just-now hacked up patch. Untested, probably fails to compile.
> Just kicked off a light test run, will let you know how it goes.
And it passes light testing on a 4-CPU x86 box.
Thanx, Paul
> Signed-off-by: Paul E. McKenney <paulmck@...ux.vnet.ibm.com>
> ---
>
> include/linux/rcupreempt.h | 15 ++++++++-
> kernel/Kconfig.preempt | 15 +++++++++
> kernel/rcupreempt.c | 71 ++++++++++++++++++++++++++++++++++++++++++++-
> 3 files changed, 99 insertions(+), 2 deletions(-)
>
> diff -urpNa -X dontdiff linux-2.6.26-rc3/include/linux/rcupreempt.h linux-2.6.26-rc3-rcu-gcwnp/include/linux/rcupreempt.h
> --- linux-2.6.26-rc3/include/linux/rcupreempt.h 2008-05-23 02:26:06.000000000 -0700
> +++ linux-2.6.26-rc3-rcu-gcwnp/include/linux/rcupreempt.h 2008-05-27 21:27:35.000000000 -0700
> @@ -40,7 +40,20 @@
> #include <linux/cpumask.h>
> #include <linux/seqlock.h>
>
> -#define rcu_qsctr_inc(cpu)
> +struct rcu_dyntick_sched {
> + int qs;
> + int rcu_qs_snap;
> +};
> +
> +DECLARE_PER_CPU(struct rcu_dyntick_sched, rcu_dyntick_sched);
> +
> +static inline void rcu_qsctr_inc(int cpu)
> +{
> + struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
> +
> + rdssp->qs++;
> +}
> +
> #define rcu_bh_qsctr_inc(cpu)
> #define call_rcu_bh(head, rcu) call_rcu(head, rcu)
>
> diff -urpNa -X dontdiff linux-2.6.26-rc3/kernel/Kconfig.preempt linux-2.6.26-rc3-rcu-gcwnp/kernel/Kconfig.preempt
> --- linux-2.6.26-rc3/kernel/Kconfig.preempt 2008-04-16 19:49:44.000000000 -0700
> +++ linux-2.6.26-rc3-rcu-gcwnp/kernel/Kconfig.preempt 2008-05-27 21:27:39.000000000 -0700
> @@ -77,3 +77,18 @@ config RCU_TRACE
>
> Say Y here if you want to enable RCU tracing
> Say N if you are unsure.
> +
> +config PREEMPT_RCU_WAIT_PREEMPT_DISABLE
> + bool "Cause preemptible RCU to wait for preempt_disable code"
> + depends on PREEMPT_RCU
> + default y
> + help
> + This option causes preemptible RCU's grace periods to wait
> + on preempt_disable() code sections (such as spinlock critical
> + sections in CONFIG_PREEMPT kernels) as well as for RCU
> + read-side critical sections. This preserves this semantic
> + from Classic RCU. Longer term, explicit RCU read-side critical
> + sections need to be added.
> +
> + Say N here if you want strict RCU semantics.
> + Say Y if you are unsure.
> diff -urpNa -X dontdiff linux-2.6.26-rc3/kernel/rcupreempt.c linux-2.6.26-rc3-rcu-gcwnp/kernel/rcupreempt.c
> --- linux-2.6.26-rc3/kernel/rcupreempt.c 2008-05-23 02:26:07.000000000 -0700
> +++ linux-2.6.26-rc3-rcu-gcwnp/kernel/rcupreempt.c 2008-05-27 21:46:51.000000000 -0700
> @@ -123,6 +123,12 @@ enum rcu_try_flip_states {
> rcu_try_flip_waitzero_state,
>
> /*
> + * Wait here for all CPUs to pass through a quiescent state, but
> + * only if CONFIG_PREEMPT_RCU_WAIT_PREEMPT_DISABLE.
> + */
> + rcu_try_flip_waitqs_state,
> +
> + /*
> * Wait here for each of the other CPUs to execute a memory barrier.
> * This is necessary to ensure that these other CPUs really have
> * completed executing their RCU read-side critical sections, despite
> @@ -131,6 +137,14 @@ enum rcu_try_flip_states {
> rcu_try_flip_waitmb_state,
> };
>
> +/* Plumb the grace-period state machine based on Kconfig parameters. */
> +
> +#ifdef CONFIG_PREEMPT_RCU_WAIT_PREEMPT_DISABLE
> +#define rcu_try_flip_waitzero_next_state rcu_try_flip_waitqs_state
> +#else /* #ifdef CONFIG_PREEMPT_RCU_WAIT_PREEMPT_DISABLE */
> +#define rcu_try_flip_waitzero_next_state rcu_try_flip_waitmb_state
> +#endif /* #else #ifdef CONFIG_PREEMPT_RCU_WAIT_PREEMPT_DISABLE */
> +
> struct rcu_ctrlblk {
> spinlock_t fliplock; /* Protect state-machine transitions. */
> long completed; /* Number of last completed batch. */
> @@ -413,6 +427,8 @@ static void __rcu_advance_callbacks(stru
> }
> }
>
> +DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_dyntick_sched, rcu_dyntick_sched);
> +
> #ifdef CONFIG_NO_HZ
>
> DEFINE_PER_CPU(long, dynticks_progress_counter) = 1;
> @@ -619,6 +635,25 @@ rcu_try_flip_waitmb_needed(int cpu)
>
> #endif /* CONFIG_NO_HZ */
>
> +#ifdef CONFIG_PREEMPT_RCU_WAIT_PREEMPT_DISABLE
> +
> +void rcu_try_flip_take_qs_snapshot(void)
> +{
> + struct rcu_dyntick_sched *rdssp;
> + int cpu;
> +
> + for_each_cpu_mask(cpu, rcu_cpu_online_map) {
> + rdssp = &per_cpu(rcu_dyntick_sched, cpu);
> + rdssp->rcu_qs_snap = rdssp->qs;
> + }
> +}
> +
> +#else /* #ifdef CONFIG_PREEMPT_RCU_WAIT_PREEMPT_DISABLE */
> +
> +#define rcu_try_flip_take_qs_snapshot()
> +
> +#endif /* #else #ifdef CONFIG_PREEMPT_RCU_WAIT_PREEMPT_DISABLE */
> +
> /*
> * Get here when RCU is idle. Decide whether we need to
> * move out of idle state, and return non-zero if so.
> @@ -662,6 +697,13 @@ rcu_try_flip_idle(void)
> dyntick_save_progress_counter(cpu);
> }
>
> + /*
> + * And take quiescent-state snapshot if we are also to wait
> + * on preempt_disable() code sequences.
> + */
> +
> + rcu_try_flip_take_qs_snapshot();
> +
> return 1;
> }
>
> @@ -731,6 +773,26 @@ rcu_try_flip_waitzero(void)
> return 1;
> }
>
> +static int
> +rcu_try_flip_waitqs(void)
> +{
> + int cpu;
> + struct rcu_dyntick_sched *rdssp;
> +
> + /* RCU_TRACE_ME(rcupreempt_trace_try_flip_q1); */
> + for_each_cpu_mask(cpu, rcu_cpu_online_map) {
> + rdssp = &per_cpu(rcu_dyntick_sched, cpu);
> + if (rcu_try_flip_waitack_needed(cpu) &&
> + (rdssp->qs == rdssp->rcu_qs_snap)) {
> + /* RCU_TRACE_ME(rcupreempt_trace_try_flip_qe1); */
> + return 0;
> + }
> + }
> +
> + /* RCU_TRACE_ME(rcupreempt_trace_try_flip_q2); */
> + return 1;
> +}
> +
> /*
> * Wait for all CPUs to do their end-of-grace-period memory barrier.
> * Return 0 once all CPUs have done so.
> @@ -775,7 +837,9 @@ static void rcu_try_flip(void)
>
> /*
> * Take the next transition(s) through the RCU grace-period
> - * flip-counter state machine.
> + * flip-counter state machine. The _next_state transition
> + * is defined by the "plumbing" definitions following the
> + * rcu_try_flip_states enum.
> */
>
> switch (rcu_ctrlblk.rcu_try_flip_state) {
> @@ -792,6 +856,11 @@ static void rcu_try_flip(void)
> case rcu_try_flip_waitzero_state:
> if (rcu_try_flip_waitzero())
> rcu_ctrlblk.rcu_try_flip_state =
> + rcu_try_flip_waitzero_next_state;
> + break;
> + case rcu_try_flip_waitqs_state:
> + if (rcu_try_flip_waitqs())
> + rcu_ctrlblk.rcu_try_flip_state =
> rcu_try_flip_waitmb_state;
> break;
> case rcu_try_flip_waitmb_state:
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists