diff options
author | Paul E. McKenney <paul.mckenney@linaro.org> | 2012-02-28 19:02:21 (GMT) |
---|---|---|
committer | Paul E. McKenney <paulmck@linux.vnet.ibm.com> | 2012-04-25 03:55:20 (GMT) |
commit | c57afe80db4e169135eb675acc2d241e26cc064e (patch) | |
tree | ec011600725a2884efdca6f4c187ea7e3fa4d277 /kernel | |
parent | 2ee3dc80660ac8285a37e662fd91b2e45c46f06a (diff) | |
download | linux-c57afe80db4e169135eb675acc2d241e26cc064e.tar.xz |
rcu: Make RCU_FAST_NO_HZ account for pauses out of idle
Both Steven Rostedt's new idle-capable trace macros and the RCU_NONIDLE()
macro can cause RCU to momentarily pause out of idle without the rest
of the system being involved. This can cause rcu_prepare_for_idle()
to run through its state machine too quickly, which can in turn result
in needless scheduling-clock interrupts.
This commit therefore adds code to enable rcu_prepare_for_idle() to
distinguish between an initial entry to idle on the one hand (which needs
to advance the rcu_prepare_for_idle() state machine) and an idle reentry
due to idle-capable trace macros and RCU_NONIDLE() on the other hand
(which should avoid advancing the rcu_prepare_for_idle() state machine).
Additional state is maintained to allow the timer to be correctly reposted
when returning after a momentary pause out of idle, and even more state
is maintained to detect when new non-lazy callbacks have been enqueued
(which may require re-evaluation of the approach to idleness).
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/rcutree.c | 2 | ||||
-rw-r--r-- | kernel/rcutree.h | 1 | ||||
-rw-r--r-- | kernel/rcutree_plugin.h | 57 |
3 files changed, 56 insertions, 4 deletions
diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 1050d6d..403306b 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -1829,6 +1829,8 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), rdp->qlen++; if (lazy) rdp->qlen_lazy++; + else + rcu_idle_count_callbacks_posted(); if (__is_kfree_rcu_offset((unsigned long)func)) trace_rcu_kfree_callback(rsp->name, head, (unsigned long)func, diff --git a/kernel/rcutree.h b/kernel/rcutree.h index cdd1be0..36ca28e 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -471,6 +471,7 @@ static void __cpuinit rcu_prepare_kthreads(int cpu); static void rcu_prepare_for_idle_init(int cpu); static void rcu_cleanup_after_idle(int cpu); static void rcu_prepare_for_idle(int cpu); +static void rcu_idle_count_callbacks_posted(void); static void print_cpu_stall_info_begin(void); static void print_cpu_stall_info(struct rcu_state *rsp, int cpu); static void print_cpu_stall_info_end(void); diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index 0f007b3..50c1797 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -1938,6 +1938,14 @@ static void rcu_prepare_for_idle(int cpu) { } +/* + * Don't bother keeping a running count of the number of RCU callbacks + * posted because CONFIG_RCU_FAST_NO_HZ=n. + */ +static void rcu_idle_count_callbacks_posted(void) +{ +} + #else /* #if !defined(CONFIG_RCU_FAST_NO_HZ) */ /* @@ -1981,6 +1989,10 @@ static void rcu_prepare_for_idle(int cpu) static DEFINE_PER_CPU(int, rcu_dyntick_drain); static DEFINE_PER_CPU(unsigned long, rcu_dyntick_holdoff); static DEFINE_PER_CPU(struct timer_list, rcu_idle_gp_timer); +static DEFINE_PER_CPU(unsigned long, rcu_idle_gp_timer_expires); +static DEFINE_PER_CPU(bool, rcu_idle_first_pass); +static DEFINE_PER_CPU(unsigned long, rcu_nonlazy_posted); +static DEFINE_PER_CPU(unsigned long, rcu_nonlazy_posted_snap); /* * Allow the CPU to enter dyntick-idle mode if either: (1) There are no @@ -1993,6 +2005,8 @@ static DEFINE_PER_CPU(struct timer_list, rcu_idle_gp_timer); */ int rcu_needs_cpu(int cpu) { + /* Flag a new idle sojourn to the idle-entry state machine. */ + per_cpu(rcu_idle_first_pass, cpu) = 1; /* If no callbacks, RCU doesn't need the CPU. */ if (!rcu_cpu_has_callbacks(cpu)) return 0; @@ -2096,6 +2110,26 @@ static void rcu_cleanup_after_idle(int cpu) static void rcu_prepare_for_idle(int cpu) { /* + * If this is an idle re-entry, for example, due to use of + * RCU_NONIDLE() or the new idle-loop tracing API within the idle + * loop, then don't take any state-machine actions, unless the + * momentary exit from idle queued additional non-lazy callbacks. + * Instead, repost the rcu_idle_gp_timer if this CPU has callbacks + * pending. + */ + if (!per_cpu(rcu_idle_first_pass, cpu) && + (per_cpu(rcu_nonlazy_posted, cpu) == + per_cpu(rcu_nonlazy_posted_snap, cpu))) { + if (rcu_cpu_has_callbacks(cpu)) + mod_timer(&per_cpu(rcu_idle_gp_timer, cpu), + per_cpu(rcu_idle_gp_timer_expires, cpu)); + return; + } + per_cpu(rcu_idle_first_pass, cpu) = 0; + per_cpu(rcu_nonlazy_posted_snap, cpu) = + per_cpu(rcu_nonlazy_posted, cpu) - 1; + + /* * If there are no callbacks on this CPU, enter dyntick-idle mode. * Also reset state to avoid prejudicing later attempts. */ @@ -2127,11 +2161,15 @@ static void rcu_prepare_for_idle(int cpu) per_cpu(rcu_dyntick_drain, cpu) = 0; per_cpu(rcu_dyntick_holdoff, cpu) = jiffies; if (rcu_cpu_has_nonlazy_callbacks(cpu)) - mod_timer(&per_cpu(rcu_idle_gp_timer, cpu), - jiffies + RCU_IDLE_GP_DELAY); + per_cpu(rcu_idle_gp_timer_expires, cpu) = + jiffies + RCU_IDLE_GP_DELAY; else - mod_timer(&per_cpu(rcu_idle_gp_timer, cpu), - jiffies + RCU_IDLE_LAZY_GP_DELAY); + per_cpu(rcu_idle_gp_timer_expires, cpu) = + jiffies + RCU_IDLE_LAZY_GP_DELAY; + mod_timer(&per_cpu(rcu_idle_gp_timer, cpu), + per_cpu(rcu_idle_gp_timer_expires, cpu)); + per_cpu(rcu_nonlazy_posted_snap, cpu) = + per_cpu(rcu_nonlazy_posted, cpu); return; /* Nothing more to do immediately. */ } else if (--per_cpu(rcu_dyntick_drain, cpu) <= 0) { /* We have hit the limit, so time to give up. */ @@ -2171,6 +2209,17 @@ static void rcu_prepare_for_idle(int cpu) trace_rcu_prep_idle("Callbacks drained"); } +/* + * Keep a running count of callbacks posted so that rcu_prepare_for_idle() + * can detect when something out of the idle loop posts a callback. + * Of course, it had better do so either from a trace event designed to + * be called from idle or from within RCU_NONIDLE(). + */ +static void rcu_idle_count_callbacks_posted(void) +{ + __this_cpu_add(rcu_nonlazy_posted, 1); +} + #endif /* #else #if !defined(CONFIG_RCU_FAST_NO_HZ) */ #ifdef CONFIG_RCU_CPU_STALL_INFO |