176 lines
5.3 KiB
Diff
176 lines
5.3 KiB
Diff
Subject: rcu: Make ksoftirqd do RCU quiescent states
|
|
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
|
|
Date: Wed, 5 Oct 2011 11:45:18 -0700
|
|
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.0/patches-4.0.5-rt3.tar.xz
|
|
|
|
Implementing RCU-bh in terms of RCU-preempt makes the system vulnerable
|
|
to network-based denial-of-service attacks. This patch therefore
|
|
makes __do_softirq() invoke rcu_bh_qs(), but only when __do_softirq()
|
|
is running in ksoftirqd context. A wrapper layer in interposed so that
|
|
other calls to __do_softirq() avoid invoking rcu_bh_qs(). The underlying
|
|
function __do_softirq_common() does the actual work.
|
|
|
|
The reason that rcu_bh_qs() is bad in these non-ksoftirqd contexts is
|
|
that there might be a local_bh_enable() inside an RCU-preempt read-side
|
|
critical section. This local_bh_enable() can invoke __do_softirq()
|
|
directly, so if __do_softirq() were to invoke rcu_bh_qs() (which just
|
|
calls rcu_preempt_qs() in the PREEMPT_RT_FULL case), there would be
|
|
an illegal RCU-preempt quiescent state in the middle of an RCU-preempt
|
|
read-side critical section. Therefore, quiescent states can only happen
|
|
in cases where __do_softirq() is invoked directly from ksoftirqd.
|
|
|
|
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
|
|
Link: http://lkml.kernel.org/r/20111005184518.GA21601@linux.vnet.ibm.com
|
|
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
|
|
|
|
---
|
|
include/linux/rcupdate.h | 6 ------
|
|
kernel/rcu/tree.c | 9 ++++++++-
|
|
kernel/rcu/tree_plugin.h | 9 +++++++--
|
|
kernel/softirq.c | 18 ++++++++++++------
|
|
4 files changed, 27 insertions(+), 15 deletions(-)
|
|
|
|
--- a/include/linux/rcupdate.h
|
|
+++ b/include/linux/rcupdate.h
|
|
@@ -270,13 +270,7 @@ static inline int rcu_preempt_depth(void
|
|
/* Internal to kernel */
|
|
void rcu_init(void);
|
|
void rcu_sched_qs(void);
|
|
-
|
|
-#ifdef CONFIG_PREEMPT_RT_FULL
|
|
-static inline void rcu_bh_qs(void) { }
|
|
-#else
|
|
void rcu_bh_qs(void);
|
|
-#endif
|
|
-
|
|
void rcu_check_callbacks(int user);
|
|
struct notifier_block;
|
|
void rcu_idle_enter(void);
|
|
--- a/kernel/rcu/tree.c
|
|
+++ b/kernel/rcu/tree.c
|
|
@@ -198,7 +198,14 @@ void rcu_sched_qs(void)
|
|
}
|
|
}
|
|
|
|
-#ifndef CONFIG_PREEMPT_RT_FULL
|
|
+#ifdef CONFIG_PREEMPT_RT_FULL
|
|
+static void rcu_preempt_qs(void);
|
|
+
|
|
+void rcu_bh_qs(void)
|
|
+{
|
|
+ rcu_preempt_qs();
|
|
+}
|
|
+#else
|
|
void rcu_bh_qs(void)
|
|
{
|
|
if (!__this_cpu_read(rcu_bh_data.passed_quiesce)) {
|
|
--- a/kernel/rcu/tree_plugin.h
|
|
+++ b/kernel/rcu/tree_plugin.h
|
|
@@ -28,6 +28,7 @@
|
|
#include <linux/gfp.h>
|
|
#include <linux/oom.h>
|
|
#include <linux/smpboot.h>
|
|
+#include <linux/jiffies.h>
|
|
#include "../time/tick-internal.h"
|
|
|
|
#ifdef CONFIG_RCU_BOOST
|
|
@@ -1360,7 +1361,7 @@ static void rcu_prepare_kthreads(int cpu
|
|
|
|
#endif /* #else #ifdef CONFIG_RCU_BOOST */
|
|
|
|
-#if !defined(CONFIG_RCU_FAST_NO_HZ)
|
|
+#if !defined(CONFIG_RCU_FAST_NO_HZ) || defined(CONFIG_PREEMPT_RT_FULL)
|
|
|
|
/*
|
|
* Check to see if any future RCU-related work will need to be done
|
|
@@ -1378,7 +1379,9 @@ int rcu_needs_cpu(unsigned long *delta_j
|
|
return rcu_cpu_has_callbacks(NULL);
|
|
}
|
|
#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
|
|
+#endif /* !defined(CONFIG_RCU_FAST_NO_HZ) || defined(CONFIG_PREEMPT_RT_FULL) */
|
|
|
|
+#if !defined(CONFIG_RCU_FAST_NO_HZ)
|
|
/*
|
|
* Because we do not have RCU_FAST_NO_HZ, don't bother cleaning up
|
|
* after it.
|
|
@@ -1476,6 +1479,8 @@ static bool __maybe_unused rcu_try_advan
|
|
return cbs_ready;
|
|
}
|
|
|
|
+#ifndef CONFIG_PREEMPT_RT_FULL
|
|
+
|
|
/*
|
|
* Allow the CPU to enter dyntick-idle mode unless it has callbacks ready
|
|
* to invoke. If the CPU has callbacks, try to advance them. Tell the
|
|
@@ -1516,7 +1521,7 @@ int rcu_needs_cpu(unsigned long *dj)
|
|
return 0;
|
|
}
|
|
#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
|
|
-
|
|
+#endif /* #ifndef CONFIG_PREEMPT_RT_FULL */
|
|
/*
|
|
* Prepare a CPU for idle from an RCU perspective. The first major task
|
|
* is to sense whether nohz mode has been enabled or disabled via sysfs.
|
|
--- a/kernel/softirq.c
|
|
+++ b/kernel/softirq.c
|
|
@@ -142,7 +142,7 @@ static void wakeup_softirqd(void)
|
|
wake_up_process(tsk);
|
|
}
|
|
|
|
-static void handle_pending_softirqs(u32 pending)
|
|
+static void handle_pending_softirqs(u32 pending, int need_rcu_bh_qs)
|
|
{
|
|
struct softirq_action *h = softirq_vec;
|
|
int softirq_bit;
|
|
@@ -175,7 +175,8 @@ static void handle_pending_softirqs(u32
|
|
pending >>= softirq_bit;
|
|
}
|
|
|
|
- rcu_bh_qs();
|
|
+ if (need_rcu_bh_qs)
|
|
+ rcu_bh_qs();
|
|
local_irq_disable();
|
|
}
|
|
|
|
@@ -355,7 +356,7 @@ asmlinkage __visible void __do_softirq(v
|
|
/* Reset the pending bitmask before enabling irqs */
|
|
set_softirq_pending(0);
|
|
|
|
- handle_pending_softirqs(pending);
|
|
+ handle_pending_softirqs(pending, 1);
|
|
|
|
pending = local_softirq_pending();
|
|
if (pending) {
|
|
@@ -404,7 +405,12 @@ static void ksoftirqd_clr_sched_params(u
|
|
static DEFINE_LOCAL_IRQ_LOCK(local_softirq_lock);
|
|
static DEFINE_PER_CPU(struct task_struct *, local_softirq_runner);
|
|
|
|
-asmlinkage void __do_softirq(void);
|
|
+static void __do_softirq_common(int need_rcu_bh_qs);
|
|
+
|
|
+asmlinkage __do_softirq(void)
|
|
+{
|
|
+ __do_softirq_common(0);
|
|
+}
|
|
|
|
void __init softirq_early_init(void)
|
|
{
|
|
@@ -513,7 +519,7 @@ asmlinkage void __do_softirq(void)
|
|
|
|
lockdep_softirq_enter();
|
|
|
|
- handle_pending_softirqs(pending, cpu);
|
|
+ handle_pending_softirqs(pending, need_rcu_bh_qs);
|
|
|
|
pending = local_softirq_pending();
|
|
if (pending)
|
|
@@ -552,7 +558,7 @@ static int __thread_do_softirq(int cpu)
|
|
* schedule!
|
|
*/
|
|
if (local_softirq_pending())
|
|
- __do_softirq();
|
|
+ __do_softirq_common(cpu >= 0);
|
|
local_unlock(local_softirq_lock);
|
|
unpin_current_cpu();
|
|
preempt_disable();
|