The patch titled
intel_idle: open broadcast clock event - resend
has been added to the -mm tree. Its filename is
intel_idle-open-broadcast-clock-event-resend.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://userweb.kernel.org/~akpm/stuff/added-to-mm.txt to find
out what to do about this
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: intel_idle: open broadcast clock event - resend
From: Shaohua Li <shaohua.li@xxxxxxxxx>
The Intel_idle driver uses
CLOCK_EVT_NOTIFY_BROADCAST_ENTER/CLOCK_EVT_NOTIFY_BROADCAST_EXIT for
broadcast clock events. The _ENTER/_EXIT doesn't really open broadcast
clock events, please see processor_idle.c for an example. In some
situation, this will cause boot hang, because some CPUs enters idle but
local APIC timer stalls.
Signed-off-by: Shaohua Li <shaohua.li@xxxxxxxxx>
Reported-and-tested-by: Yan Zheng <zheng.z.yan@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
drivers/idle/intel_idle.c | 47 +++++++++++++++++++++++++++++++++++-
1 file changed, 46 insertions(+), 1 deletion(-)
diff -puN drivers/idle/intel_idle.c~intel_idle-open-broadcast-clock-event-resend drivers/idle/intel_idle.c
--- a/drivers/idle/intel_idle.c~intel_idle-open-broadcast-clock-event-resend
+++ a/drivers/idle/intel_idle.c
@@ -59,6 +59,8 @@
#include <linux/hrtimer.h> /* ktime_get_real() */
#include <trace/events/power.h>
#include <linux/sched.h>
+#include <linux/notifier.h>
+#include <linux/cpu.h>
#include <asm/mwait.h>
#define INTEL_IDLE_VERSION "0.4"
@@ -73,6 +75,7 @@ static int max_cstate = MWAIT_MAX_NUM_CS
static unsigned int mwait_substates;
+#define LAPIC_TIMER_ALWAYS_RELIABLE 0xFFFFFFFF
/* Reliable LAPIC Timer States, bit 1 for C1 etc. */
static unsigned int lapic_timer_reliable_states = (1 << 1); /* Default to only C1 */
@@ -243,6 +246,39 @@ static int intel_idle(struct cpuidle_dev
return usec_delta;
}
+static void __setup_broadcast_timer(void *arg)
+{
+ unsigned long reason = (unsigned long)arg;
+ int cpu = smp_processor_id();
+
+ reason = reason ?
+ CLOCK_EVT_NOTIFY_BROADCAST_ON : CLOCK_EVT_NOTIFY_BROADCAST_OFF;
+
+ clockevents_notify(reason, &cpu);
+}
+
+static int __cpuinit setup_broadcast_cpuhp_notify(struct notifier_block *n,
+ unsigned long action, void *hcpu)
+{
+ int hotcpu = (unsigned long)hcpu;
+
+ switch (action & 0xf) {
+ case CPU_ONLINE:
+ smp_call_function_single(hotcpu, __setup_broadcast_timer,
+ (void *)true, 1);
+ break;
+ case CPU_DOWN_PREPARE:
+ smp_call_function_single(hotcpu, __setup_broadcast_timer,
+ (void *)false, 1);
+ break;
+ }
+ return NOTIFY_OK;
+}
+
+static struct notifier_block __cpuinitdata setup_broadcast_notifier = {
+ .notifier_call = setup_broadcast_cpuhp_notify,
+};
+
/*
* intel_idle_probe()
*/
@@ -305,7 +341,11 @@ static int intel_idle_probe(void)
}
if (boot_cpu_has(X86_FEATURE_ARAT)) /* Always Reliable APIC Timer */
- lapic_timer_reliable_states = 0xFFFFFFFF;
+ lapic_timer_reliable_states = LAPIC_TIMER_ALWAYS_RELIABLE;
+ else {
+ smp_call_function(__setup_broadcast_timer, (void *)true, 1);
+ register_cpu_notifier(&setup_broadcast_notifier);
+ }
pr_debug(PREFIX "v" INTEL_IDLE_VERSION
" model 0x%X\n", boot_cpu_data.x86_model);
@@ -428,6 +468,11 @@ static void __exit intel_idle_exit(void)
intel_idle_cpuidle_devices_uninit();
cpuidle_unregister_driver(&intel_idle_driver);
+ if (lapic_timer_reliable_states != LAPIC_TIMER_ALWAYS_RELIABLE) {
+ smp_call_function(__setup_broadcast_timer, (void *)false, 1);
+ unregister_cpu_notifier(&setup_broadcast_notifier);
+ }
+
return;
}
_
Patches currently in -mm which might be from shaohua.li@xxxxxxxxx are
linux-next.patch
intel_idle-open-broadcast-clock-event-resend.patch
mm-page-allocator-adjust-the-per-cpu-counter-threshold-when-memory-is-low.patch
writeback-io-less-balance_dirty_pages.patch
writeback-consolidate-variable-names-in-balance_dirty_pages.patch
writeback-per-task-rate-limit-on-balance_dirty_pages.patch
writeback-per-task-rate-limit-on-balance_dirty_pages-fix.patch
writeback-prevent-duplicate-balance_dirty_pages_ratelimited-calls.patch
writeback-account-per-bdi-accumulated-written-pages.patch
writeback-bdi-write-bandwidth-estimation.patch
writeback-bdi-write-bandwidth-estimation-fix.patch
writeback-show-bdi-write-bandwidth-in-debugfs.patch
writeback-quit-throttling-when-bdi-dirty-pages-dropped-low.patch
writeback-reduce-per-bdi-dirty-threshold-ramp-up-time.patch
writeback-make-reasonable-gap-between-the-dirty-background-thresholds.patch
writeback-scale-down-max-throttle-bandwidth-on-concurrent-dirtiers.patch
writeback-add-trace-event-for-balance_dirty_pages.patch
writeback-make-nr_to_write-a-per-file-limit.patch
writeback-make-nr_to_write-a-per-file-limit-fix.patch
mm-kswapd-stop-high-order-balancing-when-any-suitable-zone-is-balanced.patch
mm-kswapd-keep-kswapd-awake-for-high-order-allocations-until-a-percentage-of-the-node-is-balanced.patch
mm-kswapd-use-the-order-that-kswapd-was-reclaiming-at-for-sleeping_prematurely.patch
mm-kswapd-reset-kswapd_max_order-and-classzone_idx-after-reading.patch
mm-kswapd-treat-zone-all_unreclaimable-in-sleeping_prematurely-similar-to-balance_pgdat.patch
mm-kswapd-use-the-classzone-idx-that-kswapd-was-using-for-sleeping_prematurely.patch
include-asm-generic-vmlinuxldsh-make-readmostly-section-correctly-align.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
