summaryrefslogtreecommitdiff
path: root/include
diff options
context:
space:
mode:
authorPaul E. McKenney <paulmck@linux.vnet.ibm.com>2009-02-26 05:03:42 +0300
committerIngo Molnar <mingo@elte.hu>2009-02-26 06:08:14 +0300
commita682604838763981613e42015cd0e39f2989d6bb (patch)
tree29eae425e484edc494807702696c240ce09ba3f5 /include
parent694593e3374a67d95ece6a275a1f181644c2c4d8 (diff)
downloadlinux-a682604838763981613e42015cd0e39f2989d6bb.tar.xz
rcu: Teach RCU that idle task is not quiscent state at boot
This patch fixes a bug located by Vegard Nossum with the aid of kmemcheck, updated based on review comments from Nick Piggin, Ingo Molnar, and Andrew Morton. And cleans up the variable-name and function-name language. ;-) The boot CPU runs in the context of its idle thread during boot-up. During this time, idle_cpu(0) will always return nonzero, which will fool Classic and Hierarchical RCU into deciding that a large chunk of the boot-up sequence is a big long quiescent state. This in turn causes RCU to prematurely end grace periods during this time. This patch changes the rcutree.c and rcuclassic.c rcu_check_callbacks() function to ignore the idle task as a quiescent state until the system has started up the scheduler in rest_init(), introducing a new non-API function rcu_idle_now_means_idle() to inform RCU of this transition. RCU maintains an internal rcu_idle_cpu_truthful variable to track this state, which is then used by rcu_check_callback() to determine if it should believe idle_cpu(). Because this patch has the effect of disallowing RCU grace periods during long stretches of the boot-up sequence, this patch also introduces Josh Triplett's UP-only optimization that makes synchronize_rcu() be a no-op if num_online_cpus() returns 1. This allows boot-time code that calls synchronize_rcu() to proceed normally. Note, however, that RCU callbacks registered by call_rcu() will likely queue up until later in the boot sequence. Although rcuclassic and rcutree can also use this same optimization after boot completes, rcupreempt must restrict its use of this optimization to the portion of the boot sequence before the scheduler starts up, given that an rcupreempt RCU read-side critical section may be preeempted. In addition, this patch takes Nick Piggin's suggestion to make the system_state global variable be __read_mostly. Changes since v4: o Changes the name of the introduced function and variable to be less emotional. ;-) Changes since v3: o WARN_ON(nr_context_switches() > 0) to verify that RCU switches out of boot-time mode before the first context switch, as suggested by Nick Piggin. Changes since v2: o Created rcu_blocking_is_gp() internal-to-RCU API that determines whether a call to synchronize_rcu() is itself a grace period. o The definition of rcu_blocking_is_gp() for rcuclassic and rcutree checks to see if but a single CPU is online. o The definition of rcu_blocking_is_gp() for rcupreempt checks to see both if but a single CPU is online and if the system is still in early boot. This allows rcupreempt to again work correctly if running on a single CPU after booting is complete. o Added check to rcupreempt's synchronize_sched() for there being but one online CPU. Tested all three variants both SMP and !SMP, booted fine, passed a short rcutorture test on both x86 and Power. Located-by: Vegard Nossum <vegard.nossum@gmail.com> Tested-by: Vegard Nossum <vegard.nossum@gmail.com> Tested-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Diffstat (limited to 'include')
-rw-r--r--include/linux/rcuclassic.h6
-rw-r--r--include/linux/rcupdate.h4
-rw-r--r--include/linux/rcupreempt.h15
-rw-r--r--include/linux/rcutree.h6
4 files changed, 31 insertions, 0 deletions
diff --git a/include/linux/rcuclassic.h b/include/linux/rcuclassic.h
index f3f697df1d71..80044a4f3ab9 100644
--- a/include/linux/rcuclassic.h
+++ b/include/linux/rcuclassic.h
@@ -181,4 +181,10 @@ extern long rcu_batches_completed_bh(void);
#define rcu_enter_nohz() do { } while (0)
#define rcu_exit_nohz() do { } while (0)
+/* A context switch is a grace period for rcuclassic. */
+static inline int rcu_blocking_is_gp(void)
+{
+ return num_online_cpus() == 1;
+}
+
#endif /* __LINUX_RCUCLASSIC_H */
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 921340a7b71c..528343e6da51 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -52,6 +52,9 @@ struct rcu_head {
void (*func)(struct rcu_head *head);
};
+/* Internal to kernel, but needed by rcupreempt.h. */
+extern int rcu_scheduler_active;
+
#if defined(CONFIG_CLASSIC_RCU)
#include <linux/rcuclassic.h>
#elif defined(CONFIG_TREE_RCU)
@@ -265,6 +268,7 @@ extern void rcu_barrier_sched(void);
/* Internal to kernel */
extern void rcu_init(void);
+extern void rcu_scheduler_starting(void);
extern int rcu_needs_cpu(int cpu);
#endif /* __LINUX_RCUPDATE_H */
diff --git a/include/linux/rcupreempt.h b/include/linux/rcupreempt.h
index 3e05c09b54a2..74304b4538d8 100644
--- a/include/linux/rcupreempt.h
+++ b/include/linux/rcupreempt.h
@@ -142,4 +142,19 @@ static inline void rcu_exit_nohz(void)
#define rcu_exit_nohz() do { } while (0)
#endif /* CONFIG_NO_HZ */
+/*
+ * A context switch is a grace period for rcupreempt synchronize_rcu()
+ * only during early boot, before the scheduler has been initialized.
+ * So, how the heck do we get a context switch? Well, if the caller
+ * invokes synchronize_rcu(), they are willing to accept a context
+ * switch, so we simply pretend that one happened.
+ *
+ * After boot, there might be a blocked or preempted task in an RCU
+ * read-side critical section, so we cannot then take the fastpath.
+ */
+static inline int rcu_blocking_is_gp(void)
+{
+ return num_online_cpus() == 1 && !rcu_scheduler_active;
+}
+
#endif /* __LINUX_RCUPREEMPT_H */
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index d4368b7975c3..a722fb67bb2d 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -326,4 +326,10 @@ static inline void rcu_exit_nohz(void)
}
#endif /* CONFIG_NO_HZ */
+/* A context switch is a grace period for rcutree. */
+static inline int rcu_blocking_is_gp(void)
+{
+ return num_online_cpus() == 1;
+}
+
#endif /* __LINUX_RCUTREE_H */