--- /dev/null
+From 345527b1edce8df719e0884500c76832a18211c3 Mon Sep 17 00:00:00 2001
+From: Preeti U Murthy <preeti@linux.vnet.ibm.com>
+Date: Mon, 30 Mar 2015 14:59:19 +0530
+Subject: clockevents: Fix cpu_down() race for hrtimer based broadcasting
+
+From: Preeti U Murthy <preeti@linux.vnet.ibm.com>
+
+commit 345527b1edce8df719e0884500c76832a18211c3 upstream.
+
+It was found when doing a hotplug stress test on POWER, that the
+machine either hit softlockups or rcu_sched stall warnings. The
+issue was traced to commit:
+
+ 7cba160ad789 ("powernv/cpuidle: Redesign idle states management")
+
+which exposed the cpu_down() race with hrtimer based broadcast mode:
+
+ 5d1638acb9f6 ("tick: Introduce hrtimer based broadcast")
+
+The race is the following:
+
+Assume CPU1 is the CPU which holds the hrtimer broadcasting duty
+before it is taken down.
+
+ CPU0 CPU1
+
+ cpu_down() take_cpu_down()
+ disable_interrupts()
+
+ cpu_die()
+
+ while (CPU1 != CPU_DEAD) {
+ msleep(100);
+ switch_to_idle();
+ stop_cpu_timer();
+ schedule_broadcast();
+ }
+
+ tick_cleanup_cpu_dead()
+ take_over_broadcast()
+
+So after CPU1 disabled interrupts it cannot handle the broadcast
+hrtimer anymore, so CPU0 will be stuck forever.
+
+Fix this by explicitly taking over broadcast duty before cpu_die().
+
+This is a temporary workaround. What we really want is a callback
+in the clockevent device which allows us to do that from the dying
+CPU by pushing the hrtimer onto a different cpu. That might involve
+an IPI and is definitely more complex than this immediate fix.
+
+Changelog was picked up from:
+
+ https://lkml.org/lkml/2015/2/16/213
+
+Suggested-by: Thomas Gleixner <tglx@linutronix.de>
+Tested-by: Nicolas Pitre <nico@linaro.org>
+Signed-off-by: Preeti U. Murthy <preeti@linux.vnet.ibm.com>
+Cc: linuxppc-dev@lists.ozlabs.org
+Cc: mpe@ellerman.id.au
+Cc: nicolas.pitre@linaro.org
+Cc: peterz@infradead.org
+Cc: rjw@rjwysocki.net
+Fixes: http://linuxppc.10917.n7.nabble.com/offlining-cpus-breakage-td88619.html
+Link: http://lkml.kernel.org/r/20150330092410.24979.59887.stgit@preeti.in.ibm.com
+[ Merged it to the latest timer tree, renamed the callback, tidied up the changelog. ]
+Signed-off-by: Ingo Molnar <mingo@kernel.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+
+Added a hunk that got missed in the previous post.
+Please add this to stable 3.19 and 4.0. The patch applies on both.
+
+ include/linux/tick.h | 7 ++++++-
+ kernel/cpu.c | 2 ++
+ kernel/time/tick-broadcast.c | 19 +++++++++++--------
+ 3 files changed, 19 insertions(+), 9 deletions(-)
+
+--- a/include/linux/tick.h
++++ b/include/linux/tick.h
+@@ -100,8 +100,13 @@ extern struct cpumask *tick_get_broadcas
+
+ # ifdef CONFIG_TICK_ONESHOT
+ extern struct cpumask *tick_get_broadcast_oneshot_mask(void);
+-# endif
++extern void hotplug_cpu__broadcast_tick_pull(int dead_cpu);
++# else
++static inline void hotplug_cpu__broadcast_tick_pull(int dead_cpu) { }
++# endif /* TICK_ONESHOT */
+
++# else
++static inline void hotplug_cpu__broadcast_tick_pull(int dead_cpu) { }
+ # endif /* BROADCAST */
+
+ # ifdef CONFIG_TICK_ONESHOT
+--- a/kernel/cpu.c
++++ b/kernel/cpu.c
+@@ -20,6 +20,7 @@
+ #include <linux/gfp.h>
+ #include <linux/suspend.h>
+ #include <linux/lockdep.h>
++#include <linux/tick.h>
+ #include <trace/events/power.h>
+
+ #include "smpboot.h"
+@@ -411,6 +412,7 @@ static int __ref _cpu_down(unsigned int
+ while (!idle_cpu(cpu))
+ cpu_relax();
+
++ hotplug_cpu__broadcast_tick_pull(cpu);
+ /* This actually kills the CPU. */
+ __cpu_die(cpu);
+
+--- a/kernel/time/tick-broadcast.c
++++ b/kernel/time/tick-broadcast.c
+@@ -669,14 +669,19 @@ static void broadcast_shutdown_local(str
+ clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN);
+ }
+
+-static void broadcast_move_bc(int deadcpu)
++void hotplug_cpu__broadcast_tick_pull(int deadcpu)
+ {
+- struct clock_event_device *bc = tick_broadcast_device.evtdev;
++ struct clock_event_device *bc;
++ unsigned long flags;
++
++ raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
++ bc = tick_broadcast_device.evtdev;
+
+- if (!bc || !broadcast_needs_cpu(bc, deadcpu))
+- return;
+- /* This moves the broadcast assignment to this cpu */
+- clockevents_program_event(bc, bc->next_event, 1);
++ if (bc && broadcast_needs_cpu(bc, deadcpu)) {
++ /* This moves the broadcast assignment to this CPU: */
++ clockevents_program_event(bc, bc->next_event, 1);
++ }
++ raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+ }
+
+ /*
+@@ -913,8 +918,6 @@ void tick_shutdown_broadcast_oneshot(uns
+ cpumask_clear_cpu(cpu, tick_broadcast_pending_mask);
+ cpumask_clear_cpu(cpu, tick_broadcast_force_mask);
+
+- broadcast_move_bc(cpu);
+-
+ raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+ }
+
--- /dev/null
+From 73cffdb65e679b98893f484063462c045adcf212 Mon Sep 17 00:00:00 2001
+From: "K. Y. Srinivasan" <kys@microsoft.com>
+Date: Thu, 19 Mar 2015 08:11:34 -0700
+Subject: Drivers: hv: vmbus: Don't wait after requesting offers
+
+From: "K. Y. Srinivasan" <kys@microsoft.com>
+
+commit 73cffdb65e679b98893f484063462c045adcf212 upstream.
+
+Don't wait after sending request for offers to the host. This wait is
+unnecessary and simply adds 5 seconds to the boot time.
+
+Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
+Cc: <stable@vger.kernel.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ drivers/hv/channel_mgmt.c | 12 +-----------
+ 1 file changed, 1 insertion(+), 11 deletions(-)
+
+--- a/drivers/hv/channel_mgmt.c
++++ b/drivers/hv/channel_mgmt.c
+@@ -787,7 +787,7 @@ int vmbus_request_offers(void)
+ {
+ struct vmbus_channel_message_header *msg;
+ struct vmbus_channel_msginfo *msginfo;
+- int ret, t;
++ int ret;
+
+ msginfo = kmalloc(sizeof(*msginfo) +
+ sizeof(struct vmbus_channel_message_header),
+@@ -795,8 +795,6 @@ int vmbus_request_offers(void)
+ if (!msginfo)
+ return -ENOMEM;
+
+- init_completion(&msginfo->waitevent);
+-
+ msg = (struct vmbus_channel_message_header *)msginfo->msg;
+
+ msg->msgtype = CHANNELMSG_REQUESTOFFERS;
+@@ -810,14 +808,6 @@ int vmbus_request_offers(void)
+ goto cleanup;
+ }
+
+- t = wait_for_completion_timeout(&msginfo->waitevent, 5*HZ);
+- if (t == 0) {
+- ret = -ETIMEDOUT;
+- goto cleanup;
+- }
+-
+-
+-
+ cleanup:
+ kfree(msginfo);
+
projects / thirdparty / kernel / stable-queue.git / commitdiff
