--- /dev/null
+From 58b116bce13612e5aa6fcd49ecbd4cf8bb59e835 Mon Sep 17 00:00:00 2001
+From: Grant Likely <grant.likely@linaro.org>
+Date: Tue, 29 Apr 2014 12:05:22 +0100
+Subject: drivercore: deferral race condition fix
+
+From: Grant Likely <grant.likely@linaro.org>
+
+commit 58b116bce13612e5aa6fcd49ecbd4cf8bb59e835 upstream.
+
+When the kernel is built with CONFIG_PREEMPT it is possible to reach a state
+when all modules loaded but some driver still stuck in the deferred list
+and there is a need for external event to kick the deferred queue to probe
+these drivers.
+
+The issue has been observed on embedded systems with CONFIG_PREEMPT enabled,
+audio support built as modules and using nfsroot for root filesystem.
+
+The following log fragment shows such sequence when all audio modules
+were loaded but the sound card is not present since the machine driver has
+failed to probe due to missing dependency during it's probe.
+The board is am335x-evmsk (McASP<->tlv320aic3106 codec) with davinci-evm
+machine driver:
+
+...
+[ 12.615118] davinci-mcasp 4803c000.mcasp: davinci_mcasp_probe: ENTER
+[ 12.719969] davinci_evm sound.3: davinci_evm_probe: ENTER
+[ 12.725753] davinci_evm sound.3: davinci_evm_probe: snd_soc_register_card
+[ 12.753846] davinci-mcasp 4803c000.mcasp: davinci_mcasp_probe: snd_soc_register_component
+[ 12.922051] davinci-mcasp 4803c000.mcasp: davinci_mcasp_probe: snd_soc_register_component DONE
+[ 12.950839] davinci_evm sound.3: ASoC: platform (null) not registered
+[ 12.957898] davinci_evm sound.3: davinci_evm_probe: snd_soc_register_card DONE (-517)
+[ 13.099026] davinci-mcasp 4803c000.mcasp: Kicking the deferred list
+[ 13.177838] davinci-mcasp 4803c000.mcasp: really_probe: probe_count = 2
+[ 13.194130] davinci_evm sound.3: snd_soc_register_card failed (-517)
+[ 13.346755] davinci_mcasp_driver_init: LEAVE
+[ 13.377446] platform sound.3: Driver davinci_evm requests probe deferral
+[ 13.592527] platform sound.3: really_probe: probe_count = 0
+
+In the log the machine driver enters it's probe at 12.719969 (this point it
+has been removed from the deferred lists). McASP driver already executing
+it's probing (since 12.615118).
+The machine driver tries to construct the sound card (12.950839) but did
+not found one of the components so it fails. After this McASP driver
+registers all the ASoC components (the machine driver still in it's probe
+function after it failed to construct the card) and the deferred work is
+prepared at 13.099026 (note that this time the machine driver is not in the
+lists so it is not going to be handled when the work is executing).
+Lastly the machine driver exit from it's probe and the core places it to
+the deferred list but there will be no other driver going to load and the
+deferred queue is not going to be kicked again - till we have external event
+like connecting USB stick, etc.
+
+The proposed solution is to try the deferred queue once more when the last
+driver is asking for deferring and we had drivers loaded while this last
+driver was probing.
+
+This way we can avoid drivers stuck in the deferred queue.
+
+Signed-off-by: Grant Likely <grant.likely@linaro.org>
+Reviewed-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
+Tested-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
+Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+Cc: Mark Brown <broonie@kernel.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ drivers/base/dd.c | 17 +++++++++++++++++
+ 1 file changed, 17 insertions(+)
+
+--- a/drivers/base/dd.c
++++ b/drivers/base/dd.c
+@@ -51,6 +51,7 @@ static DEFINE_MUTEX(deferred_probe_mutex
+ static LIST_HEAD(deferred_probe_pending_list);
+ static LIST_HEAD(deferred_probe_active_list);
+ static struct workqueue_struct *deferred_wq;
++static atomic_t deferred_trigger_count = ATOMIC_INIT(0);
+
+ /**
+ * deferred_probe_work_func() - Retry probing devices in the active list.
+@@ -122,6 +123,17 @@ static bool driver_deferred_probe_enable
+ * This functions moves all devices from the pending list to the active
+ * list and schedules the deferred probe workqueue to process them. It
+ * should be called anytime a driver is successfully bound to a device.
++ *
++ * Note, there is a race condition in multi-threaded probe. In the case where
++ * more than one device is probing at the same time, it is possible for one
++ * probe to complete successfully while another is about to defer. If the second
++ * depends on the first, then it will get put on the pending list after the
++ * trigger event has already occured and will be stuck there.
++ *
++ * The atomic 'deferred_trigger_count' is used to determine if a successful
++ * trigger has occurred in the midst of probing a driver. If the trigger count
++ * changes in the midst of a probe, then deferred processing should be triggered
++ * again.
+ */
+ static void driver_deferred_probe_trigger(void)
+ {
+@@ -134,6 +146,7 @@ static void driver_deferred_probe_trigge
+ * into the active list so they can be retried by the workqueue
+ */
+ mutex_lock(&deferred_probe_mutex);
++ atomic_inc(&deferred_trigger_count);
+ list_splice_tail_init(&deferred_probe_pending_list,
+ &deferred_probe_active_list);
+ mutex_unlock(&deferred_probe_mutex);
+@@ -252,6 +265,7 @@ static DECLARE_WAIT_QUEUE_HEAD(probe_wai
+ static int really_probe(struct device *dev, struct device_driver *drv)
+ {
+ int ret = 0;
++ int local_trigger_count = atomic_read(&deferred_trigger_count);
+
+ atomic_inc(&probe_count);
+ pr_debug("bus: '%s': %s: probing driver %s with device %s\n",
+@@ -290,6 +304,9 @@ probe_failed:
+ /* Driver requested deferred probing */
+ dev_info(dev, "Driver %s requests probe deferral\n", drv->name);
+ driver_deferred_probe_add(dev);
++ /* Did a trigger occur while probing? Need to re-trigger if yes */
++ if (local_trigger_count != atomic_read(&deferred_trigger_count))
++ driver_deferred_probe_trigger();
+ } else if (ret != -ENODEV && ret != -ENXIO) {
+ /* driver matched but the probe failed */
+ printk(KERN_WARNING
--- /dev/null
+From 6c6c0d5a1c949d2e084706f9e5fb1fccc175b265 Mon Sep 17 00:00:00 2001
+From: Stuart Hayes <stuart.w.hayes@gmail.com>
+Date: Tue, 29 Apr 2014 17:55:02 -0500
+Subject: hrtimer: Prevent all reprogramming if hang detected
+
+From: Stuart Hayes <stuart.w.hayes@gmail.com>
+
+commit 6c6c0d5a1c949d2e084706f9e5fb1fccc175b265 upstream.
+
+If the last hrtimer interrupt detected a hang it sets hang_detected=1
+and programs the clock event device with a delay to let the system
+make progress.
+
+If hang_detected == 1, we prevent reprogramming of the clock event
+device in hrtimer_reprogram() but not in hrtimer_force_reprogram().
+
+This can lead to the following situation:
+
+hrtimer_interrupt()
+ hang_detected = 1;
+ program ce device to Xms from now (hang delay)
+
+We have two timers pending:
+ T1 expires 50ms from now
+ T2 expires 5s from now
+
+Now T1 gets canceled, which causes hrtimer_force_reprogram() to be
+invoked, which in turn programs the clock event device to T2 (5
+seconds from now).
+
+Any hrtimer_start after that will not reprogram the hardware due to
+hang_detected still being set. So we effectivly block all timers until
+the T2 event fires and cleans up the hang situation.
+
+Add a check for hang_detected to hrtimer_force_reprogram() which
+prevents the reprogramming of the hang delay in the hardware
+timer. The subsequent hrtimer_interrupt will resolve all outstanding
+issues.
+
+[ tglx: Rewrote subject and changelog and fixed up the comment in
+ hrtimer_force_reprogram() ]
+
+Signed-off-by: Stuart Hayes <stuart.w.hayes@gmail.com>
+Link: http://lkml.kernel.org/r/53602DC6.2060101@gmail.com
+Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ kernel/hrtimer.c | 17 +++++++++++++++++
+ 1 file changed, 17 insertions(+)
+
+--- a/kernel/hrtimer.c
++++ b/kernel/hrtimer.c
+@@ -567,6 +567,23 @@ hrtimer_force_reprogram(struct hrtimer_c
+
+ cpu_base->expires_next.tv64 = expires_next.tv64;
+
++ /*
++ * If a hang was detected in the last timer interrupt then we
++ * leave the hang delay active in the hardware. We want the
++ * system to make progress. That also prevents the following
++ * scenario:
++ * T1 expires 50ms from now
++ * T2 expires 5s from now
++ *
++ * T1 is removed, so this code is called and would reprogram
++ * the hardware to 5s from now. Any hrtimer_start after that
++ * will not reprogram the hardware due to hang_detected being
++ * set. So we'd effectivly block all timers until the T2 event
++ * fires.
++ */
++ if (cpu_base->hang_detected)
++ return;
++
+ if (cpu_base->expires_next.tv64 != KTIME_MAX)
+ tick_program_event(cpu_base->expires_next, 1);
+ }
--- /dev/null
+From 012a45e3f4af68e86d85cce060c6c2fed56498b2 Mon Sep 17 00:00:00 2001
+From: Leon Ma <xindong.ma@intel.com>
+Date: Wed, 30 Apr 2014 16:43:10 +0800
+Subject: hrtimer: Prevent remote enqueue of leftmost timers
+
+From: Leon Ma <xindong.ma@intel.com>
+
+commit 012a45e3f4af68e86d85cce060c6c2fed56498b2 upstream.
+
+If a cpu is idle and starts an hrtimer which is not pinned on that
+same cpu, the nohz code might target the timer to a different cpu.
+
+In the case that we switch the cpu base of the timer we already have a
+sanity check in place, which determines whether the timer is earlier
+than the current leftmost timer on the target cpu. In that case we
+enqueue the timer on the current cpu because we cannot reprogram the
+clock event device on the target.
+
+If the timers base is already the target CPU we do not have this
+sanity check in place so we enqueue the timer as the leftmost timer in
+the target cpus rb tree, but we cannot reprogram the clock event
+device on the target cpu. So the timer expires late and subsequently
+prevents the reprogramming of the target cpu clock event device until
+the previously programmed event fires or a timer with an earlier
+expiry time gets enqueued on the target cpu itself.
+
+Add the same target check as we have for the switch base case and
+start the timer on the current cpu if it would become the leftmost
+timer on the target.
+
+[ tglx: Rewrote subject and changelog ]
+
+Signed-off-by: Leon Ma <xindong.ma@intel.com>
+Link: http://lkml.kernel.org/r/1398847391-5994-1-git-send-email-xindong.ma@intel.com
+Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ kernel/hrtimer.c | 5 +++++
+ 1 file changed, 5 insertions(+)
+
+--- a/kernel/hrtimer.c
++++ b/kernel/hrtimer.c
+@@ -232,6 +232,11 @@ again:
+ goto again;
+ }
+ timer->base = new_base;
++ } else {
++ if (cpu != this_cpu && hrtimer_check_target(timer, new_base)) {
++ cpu = this_cpu;
++ goto again;
++ }
+ }
+ return new_base;
+ }
--- /dev/null
+From 84ea7fe37908254c3bd90910921f6e1045c1747a Mon Sep 17 00:00:00 2001
+From: Viresh Kumar <viresh.kumar@linaro.org>
+Date: Mon, 12 May 2014 13:42:29 +0530
+Subject: hrtimer: Set expiry time before switch_hrtimer_base()
+
+From: Viresh Kumar <viresh.kumar@linaro.org>
+
+commit 84ea7fe37908254c3bd90910921f6e1045c1747a upstream.
+
+switch_hrtimer_base() calls hrtimer_check_target() which ensures that
+we do not migrate a timer to a remote cpu if the timer expires before
+the current programmed expiry time on that remote cpu.
+
+But __hrtimer_start_range_ns() calls switch_hrtimer_base() before the
+new expiry time is set. So the sanity check in hrtimer_check_target()
+is operating on stale or even uninitialized data.
+
+Update expiry time before calling switch_hrtimer_base().
+
+[ tglx: Rewrote changelog once again ]
+
+Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
+Cc: linaro-kernel@lists.linaro.org
+Cc: linaro-networking@linaro.org
+Cc: fweisbec@gmail.com
+Cc: arvind.chauhan@arm.com
+Link: http://lkml.kernel.org/r/81999e148745fc51bbcd0615823fbab9b2e87e23.1399882253.git.viresh.kumar@linaro.org
+Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ kernel/hrtimer.c | 8 ++++----
+ 1 file changed, 4 insertions(+), 4 deletions(-)
+
+--- a/kernel/hrtimer.c
++++ b/kernel/hrtimer.c
+@@ -985,11 +985,8 @@ int __hrtimer_start_range_ns(struct hrti
+ /* Remove an active timer from the queue: */
+ ret = remove_hrtimer(timer, base);
+
+- /* Switch the timer base, if necessary: */
+- new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED);
+-
+ if (mode & HRTIMER_MODE_REL) {
+- tim = ktime_add_safe(tim, new_base->get_time());
++ tim = ktime_add_safe(tim, base->get_time());
+ /*
+ * CONFIG_TIME_LOW_RES is a temporary way for architectures
+ * to signal that they simply return xtime in
+@@ -1004,6 +1001,9 @@ int __hrtimer_start_range_ns(struct hrti
+
+ hrtimer_set_expires_range_ns(timer, tim, delta_ns);
+
++ /* Switch the timer base, if necessary: */
++ new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED);
++
+ timer_stats_hrtimer_set_start_info(timer);
+
+ leftmost = enqueue_hrtimer(timer, new_base);
--- /dev/null
+From 17c048fc4bd95efea208a1920f169547d8588f1f Mon Sep 17 00:00:00 2001
+From: Josef Gajdusek <atx@atx.name>
+Date: Sun, 11 May 2014 14:40:44 +0200
+Subject: hwmon: (emc1403) fix inverted store_hyst()
+
+From: Josef Gajdusek <atx@atx.name>
+
+commit 17c048fc4bd95efea208a1920f169547d8588f1f upstream.
+
+Attempts to set the hysteresis value to a temperature below the target
+limit fails with "write error: Numerical result out of range" due to
+an inverted comparison.
+
+Signed-off-by: Josef Gajdusek <atx@atx.name>
+Reviewed-by: Jean Delvare <jdelvare@suse.de>
+[Guenter Roeck: Updated headline and description]
+Signed-off-by: Guenter Roeck <linux@roeck-us.net>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ drivers/hwmon/emc1403.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+--- a/drivers/hwmon/emc1403.c
++++ b/drivers/hwmon/emc1403.c
+@@ -161,7 +161,7 @@ static ssize_t store_hyst(struct device
+ if (retval < 0)
+ goto fail;
+
+- hyst = val - retval * 1000;
++ hyst = retval * 1000 - val;
+ hyst = DIV_ROUND_CLOSEST(hyst, 1000);
+ if (hyst < 0 || hyst > 255) {
+ retval = -ERANGE;
--- /dev/null
+From 3a18e1398fc2dc9c32bbdc50664da3a77959a8d1 Mon Sep 17 00:00:00 2001
+From: Josef Gajdusek <atx@atx.name>
+Date: Mon, 12 May 2014 13:48:26 +0200
+Subject: hwmon: (emc1403) Support full range of known chip revision numbers
+
+From: Josef Gajdusek <atx@atx.name>
+
+commit 3a18e1398fc2dc9c32bbdc50664da3a77959a8d1 upstream.
+
+The datasheet for EMC1413/EMC1414, which is fully compatible to
+EMC1403/1404 and uses the same chip identification, references revision
+numbers 0x01, 0x03, and 0x04. Accept the full range of revision numbers
+from 0x01 to 0x04 to make sure none are missed.
+
+Signed-off-by: Josef Gajdusek <atx@atx.name>
+[Guenter Roeck: Updated headline and description]
+Signed-off-by: Guenter Roeck <linux@roeck-us.net>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ drivers/hwmon/emc1403.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+--- a/drivers/hwmon/emc1403.c
++++ b/drivers/hwmon/emc1403.c
+@@ -294,7 +294,7 @@ static int emc1403_detect(struct i2c_cli
+ }
+
+ id = i2c_smbus_read_byte_data(client, THERMAL_REVISION_REG);
+- if (id != 0x01)
++ if (id < 0x01 || id > 0x04)
+ return -ENODEV;
+
+ return 0;
--- /dev/null
+From 0f62fb220aa4ebabe8547d3a9ce4a16d3c045f21 Mon Sep 17 00:00:00 2001
+From: NeilBrown <neilb@suse.de>
+Date: Tue, 6 May 2014 09:36:08 +1000
+Subject: md: avoid possible spinning md thread at shutdown.
+
+From: NeilBrown <neilb@suse.de>
+
+commit 0f62fb220aa4ebabe8547d3a9ce4a16d3c045f21 upstream.
+
+If an md array with externally managed metadata (e.g. DDF or IMSM)
+is in use, then we should not set safemode==2 at shutdown because:
+
+1/ this is ineffective: user-space need to be involved in any 'safemode' handling,
+2/ The safemode management code doesn't cope with safemode==2 on external metadata
+ and md_check_recover enters an infinite loop.
+
+Even at shutdown, an infinite-looping process can be problematic, so this
+could cause shutdown to hang.
+
+Signed-off-by: NeilBrown <neilb@suse.de>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ drivers/md/md.c | 3 ++-
+ 1 file changed, 2 insertions(+), 1 deletion(-)
+
+--- a/drivers/md/md.c
++++ b/drivers/md/md.c
+@@ -8167,7 +8167,8 @@ static int md_notify_reboot(struct notif
+ if (mddev_trylock(mddev)) {
+ if (mddev->pers)
+ __md_stop_writes(mddev);
+- mddev->safemode = 2;
++ if (mddev->persistent)
++ mddev->safemode = 2;
+ mddev_unlock(mddev);
+ }
+ need_delay = 1;
ipmi-reset-the-kcs-timeout-when-starting-error-recovery.patch
x86-mm-hugetlb-add-missing-tlb-page-invalidation-for-hugetlb_cow.patch
hwpoison-hugetlb-lock_page-unlock_page-does-not-match-for-handling-a-free-hugepage.patch
+hwmon-emc1403-fix-inverted-store_hyst.patch
+hwmon-emc1403-support-full-range-of-known-chip-revision-numbers.patch
+drivercore-deferral-race-condition-fix.patch
+hrtimer-prevent-all-reprogramming-if-hang-detected.patch
+hrtimer-prevent-remote-enqueue-of-leftmost-timers.patch
+hrtimer-set-expiry-time-before-switch_hrtimer_base.patch
+md-avoid-possible-spinning-md-thread-at-shutdown.patch
projects / thirdparty / kernel / stable-queue.git / commitdiff
