Linux-ARM-Kernel Archive on lore.kernel.org
 help / color / mirror / Atom feed
* [PATCH v7 6/6] PM / devfreq: Use PM QoS for sysfs min/max_freq
From: Leonard Crestez @ 2019-09-23 21:10 UTC (permalink / raw)
  To: MyungJoo Ham, Kyungmin Park, Matthias Kaehlcke
  Cc: Artur Świgoń, Abel Vesa, Saravana Kannan, linux-pm,
	Viresh Kumar, NXP Linux Team, Krzysztof Kozlowski, Lukasz Luba,
	Chanwoo Choi, Alexandre Bailon, Martin Kepplinger, Georgi Djakov,
	linux-arm-kernel, Jacky Bai
In-Reply-To: <cover.1569272883.git.leonard.crestez@nxp.com>

Switch the handling of min_freq and max_freq from sysfs to use the
dev_pm_qos_request interface.

Since PM QoS handles frequencies as kHz this change reduces the
precision of min_freq and max_freq. This shouldn't introduce problems
because frequencies which are not an integer number of kHz are likely
not an integer number of Hz either.

Try to ensure compatibility by rounding min values down and rounding
max values up.

Signed-off-by: Leonard Crestez <leonard.crestez@nxp.com>
Reviewed-by: Matthias Kaehlcke <mka@chromium.org>
---
 drivers/devfreq/devfreq.c | 49 +++++++++++++++++++++++++--------------
 include/linux/devfreq.h   |  9 +++----
 2 files changed, 36 insertions(+), 22 deletions(-)

diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index 9887408f23bb..a00737e34d36 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -132,14 +132,10 @@ static void devfreq_get_freq_range(struct devfreq *devfreq,
 	*min_freq = max(*min_freq, HZ_PER_KHZ * (unsigned long)dev_pm_qos_read_value(
 				devfreq->dev.parent, DEV_PM_QOS_MIN_FREQUENCY));
 	*max_freq = min(*max_freq, HZ_PER_KHZ * (unsigned long)dev_pm_qos_read_value(
 				devfreq->dev.parent, DEV_PM_QOS_MAX_FREQUENCY));
 
-	/* constraints from sysfs */
-	*min_freq = max(*min_freq, devfreq->min_freq);
-	*max_freq = min(*max_freq, devfreq->max_freq);
-
 	/* constraints from OPP interface */
 	*min_freq = max(*min_freq, devfreq->scaling_min_freq);
 	/* scaling_max_freq can be zero on error */
 	if (devfreq->scaling_max_freq)
 		*max_freq = min(*max_freq, devfreq->scaling_max_freq);
@@ -679,10 +675,12 @@ static void devfreq_dev_release(struct device *dev)
 			DEV_PM_QOS_MIN_FREQUENCY);
 
 	if (devfreq->profile->exit)
 		devfreq->profile->exit(devfreq->dev.parent);
 
+	dev_pm_qos_remove_request(&devfreq->user_max_freq_req);
+	dev_pm_qos_remove_request(&devfreq->user_min_freq_req);
 	kfree(devfreq->time_in_state);
 	kfree(devfreq->trans_table);
 	mutex_destroy(&devfreq->lock);
 	kfree(devfreq);
 }
@@ -747,18 +745,26 @@ struct devfreq *devfreq_add_device(struct device *dev,
 	devfreq->scaling_min_freq = find_available_min_freq(devfreq);
 	if (!devfreq->scaling_min_freq) {
 		err = -EINVAL;
 		goto err_dev;
 	}
-	devfreq->min_freq = devfreq->scaling_min_freq;
 
 	devfreq->scaling_max_freq = find_available_max_freq(devfreq);
 	if (!devfreq->scaling_max_freq) {
 		err = -EINVAL;
 		goto err_dev;
 	}
-	devfreq->max_freq = devfreq->scaling_max_freq;
+
+	/* PM QoS requests for min/max freq from sysfs */
+	err = dev_pm_qos_add_request(dev, &devfreq->user_min_freq_req,
+				     DEV_PM_QOS_MIN_FREQUENCY, 0);
+	if (err < 0)
+		goto err_dev;
+	err = dev_pm_qos_add_request(dev, &devfreq->user_max_freq_req,
+				     DEV_PM_QOS_MAX_FREQUENCY, S32_MAX);
+	if (err < 0)
+		goto err_dev;
 
 	devfreq->suspend_freq = dev_pm_opp_get_suspend_opp_freq(dev);
 	atomic_set(&devfreq->suspend_count, 0);
 
 	devfreq->trans_table = kzalloc(
@@ -843,10 +849,14 @@ struct devfreq *devfreq_add_device(struct device *dev,
 err_dev:
 	/*
 	 * Cleanup path for errors that happen before registration.
 	 * Otherwise we rely on devfreq_dev_release.
 	 */
+	if (dev_pm_qos_request_active(&devfreq->user_max_freq_req))
+		dev_pm_qos_remove_request(&devfreq->user_max_freq_req);
+	if (dev_pm_qos_request_active(&devfreq->user_min_freq_req))
+		dev_pm_qos_remove_request(&devfreq->user_min_freq_req);
 	kfree(devfreq->time_in_state);
 	kfree(devfreq->trans_table);
 	kfree(devfreq);
 err_out:
 	return ERR_PTR(err);
@@ -1387,14 +1397,17 @@ static ssize_t min_freq_store(struct device *dev, struct device_attribute *attr,
 
 	ret = sscanf(buf, "%lu", &value);
 	if (ret != 1)
 		return -EINVAL;
 
-	mutex_lock(&df->lock);
-	df->min_freq = value;
-	update_devfreq(df);
-	mutex_unlock(&df->lock);
+	/* round down to kHz for dev_pm_qos */
+	if (value)
+		value = value / HZ_PER_KHZ;
+
+	ret = dev_pm_qos_update_request(&df->user_min_freq_req, value);
+	if (ret < 0)
+		return ret;
 
 	return count;
 }
 
 static ssize_t min_freq_show(struct device *dev, struct device_attribute *attr,
@@ -1419,19 +1432,19 @@ static ssize_t max_freq_store(struct device *dev, struct device_attribute *attr,
 
 	ret = sscanf(buf, "%lu", &value);
 	if (ret != 1)
 		return -EINVAL;
 
-	mutex_lock(&df->lock);
-
-	/* Interpret zero as "don't care" */
-	if (!value)
-		value = ULONG_MAX;
+	/* round up to kHz for dev_pm_qos and interpret zero as "don't care" */
+	if (value)
+		value = DIV_ROUND_UP(value, HZ_PER_KHZ);
+	else
+		value = S32_MAX;
 
-	df->max_freq = value;
-	update_devfreq(df);
-	mutex_unlock(&df->lock);
+	ret = dev_pm_qos_update_request(&df->user_max_freq_req, value);
+	if (ret < 0)
+		return ret;
 
 	return count;
 }
 static DEVICE_ATTR_RW(min_freq);
 
diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h
index 8b92ccbd1962..3162eb9b0954 100644
--- a/include/linux/devfreq.h
+++ b/include/linux/devfreq.h
@@ -11,10 +11,11 @@
 #define __LINUX_DEVFREQ_H__
 
 #include <linux/device.h>
 #include <linux/notifier.h>
 #include <linux/pm_opp.h>
+#include <linux/pm_qos.h>
 
 #define DEVFREQ_NAME_LEN 16
 
 /* DEVFREQ governor name */
 #define DEVFREQ_GOV_SIMPLE_ONDEMAND	"simple_ondemand"
@@ -121,12 +122,12 @@ struct devfreq_dev_profile {
  *		devfreq.nb to the corresponding register notifier call chain.
  * @work:	delayed work for load monitoring.
  * @previous_freq:	previously configured frequency value.
  * @data:	Private data of the governor. The devfreq framework does not
  *		touch this.
- * @min_freq:	Limit minimum frequency requested by user (0: none)
- * @max_freq:	Limit maximum frequency requested by user (0: none)
+ * @user_min_freq_req:	PM QoS min frequency request from user (via sysfs)
+ * @user_max_freq_req:	PM QoS max frequency request from user (via sysfs)
  * @scaling_min_freq:	Limit minimum frequency requested by OPP interface
  * @scaling_max_freq:	Limit maximum frequency requested by OPP interface
  * @stop_polling:	 devfreq polling status of a device.
  * @suspend_freq:	 frequency of a device set during suspend phase.
  * @resume_freq:	 frequency of a device set in resume phase.
@@ -161,12 +162,12 @@ struct devfreq {
 	unsigned long previous_freq;
 	struct devfreq_dev_status last_status;
 
 	void *data; /* private data for governors */
 
-	unsigned long min_freq;
-	unsigned long max_freq;
+	struct dev_pm_qos_request user_min_freq_req;
+	struct dev_pm_qos_request user_max_freq_req;
 	unsigned long scaling_min_freq;
 	unsigned long scaling_max_freq;
 	bool stop_polling;
 
 	unsigned long suspend_freq;
-- 
2.17.1


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

^ permalink raw reply related

* [PATCH v7 5/6] PM / devfreq: Add PM QoS support
From: Leonard Crestez @ 2019-09-23 21:10 UTC (permalink / raw)
  To: MyungJoo Ham, Kyungmin Park, Matthias Kaehlcke
  Cc: Artur Świgoń, Abel Vesa, Saravana Kannan, linux-pm,
	Viresh Kumar, NXP Linux Team, Krzysztof Kozlowski, Lukasz Luba,
	Chanwoo Choi, Alexandre Bailon, Martin Kepplinger, Georgi Djakov,
	linux-arm-kernel, Jacky Bai
In-Reply-To: <cover.1569272883.git.leonard.crestez@nxp.com>

Register notifiers with the PM QoS framework in order to respond to
requests for DEV_PM_QOS_MIN_FREQUENCY and DEV_PM_QOS_MAX_FREQUENCY.

No notifiers are added by this patch but PM QoS constraints can be
imposed externally (for example from other devices).

Signed-off-by: Leonard Crestez <leonard.crestez@nxp.com>
---
 drivers/devfreq/devfreq.c | 76 +++++++++++++++++++++++++++++++++++++++
 include/linux/devfreq.h   |  5 +++
 2 files changed, 81 insertions(+)

diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index 7f152a582e78..9887408f23bb 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -22,17 +22,20 @@
 #include <linux/platform_device.h>
 #include <linux/list.h>
 #include <linux/printk.h>
 #include <linux/hrtimer.h>
 #include <linux/of.h>
+#include <linux/pm_qos.h>
 #include "governor.h"
 
 #define HZ_PER_KHZ 1000
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/devfreq.h>
 
+#define HZ_PER_KHZ	1000
+
 static struct class *devfreq_class;
 
 /*
  * devfreq core provides delayed work based load monitoring helper
  * functions. Governors can use these or can implement their own
@@ -123,10 +126,16 @@ static void devfreq_get_freq_range(struct devfreq *devfreq,
 	} else {
 		*min_freq = freq_table[devfreq->profile->max_state - 1];
 		*max_freq = freq_table[0];
 	}
 
+	/* constraints from PM QoS */
+	*min_freq = max(*min_freq, HZ_PER_KHZ * (unsigned long)dev_pm_qos_read_value(
+				devfreq->dev.parent, DEV_PM_QOS_MIN_FREQUENCY));
+	*max_freq = min(*max_freq, HZ_PER_KHZ * (unsigned long)dev_pm_qos_read_value(
+				devfreq->dev.parent, DEV_PM_QOS_MAX_FREQUENCY));
+
 	/* constraints from sysfs */
 	*min_freq = max(*min_freq, devfreq->min_freq);
 	*max_freq = min(*max_freq, devfreq->max_freq);
 
 	/* constraints from OPP interface */
@@ -605,10 +614,53 @@ static int devfreq_notifier_call(struct notifier_block *nb, unsigned long type,
 	mutex_unlock(&devfreq->lock);
 
 	return ret;
 }
 
+/**
+ * devfreq_qos_notifier_call() - Common handler for QoS constraints.
+ * @devfreq:    the devfreq instance.
+ */
+static int devfreq_qos_notifier_call(struct devfreq *devfreq)
+{
+	int err;
+
+	mutex_lock(&devfreq->lock);
+	err = update_devfreq(devfreq);
+	mutex_unlock(&devfreq->lock);
+	if (err)
+		dev_err(&devfreq->dev, "dvfs for QoS constraints"
+				" failed with (%d) error\n", err);
+
+	/* QoS is best effort - let all notifiers run on error */
+	return NOTIFY_OK;
+}
+
+/**
+ * devfreq_qos_min_notifier_call() - Callback for QoS min_freq changes.
+ * @nb:		Should be devfreq->nb_min
+ */
+static int devfreq_qos_min_notifier_call(struct notifier_block *nb,
+					 unsigned long val, void *ptr)
+{
+	struct devfreq *devfreq = container_of(nb, struct devfreq, nb_min);
+
+	return devfreq_qos_notifier_call(devfreq);
+}
+
+/**
+ * devfreq_qos_max_notifier_call() - Callback for QoS max_freq changes.
+ * @nb:		Should be devfreq->nb_max
+ */
+static int devfreq_qos_max_notifier_call(struct notifier_block *nb,
+					 unsigned long val, void *ptr)
+{
+	struct devfreq *devfreq = container_of(nb, struct devfreq, nb_max);
+
+	return devfreq_qos_notifier_call(devfreq);
+}
+
 /**
  * devfreq_dev_release() - Callback for struct device to release the device.
  * @dev:	the devfreq device
  *
  * Remove devfreq from the list and release its resources.
@@ -619,10 +671,15 @@ static void devfreq_dev_release(struct device *dev)
 
 	mutex_lock(&devfreq_list_lock);
 	list_del(&devfreq->node);
 	mutex_unlock(&devfreq_list_lock);
 
+	dev_pm_qos_remove_notifier(devfreq->dev.parent, &devfreq->nb_max,
+			DEV_PM_QOS_MAX_FREQUENCY);
+	dev_pm_qos_remove_notifier(devfreq->dev.parent, &devfreq->nb_min,
+			DEV_PM_QOS_MIN_FREQUENCY);
+
 	if (devfreq->profile->exit)
 		devfreq->profile->exit(devfreq->dev.parent);
 
 	kfree(devfreq->time_in_state);
 	kfree(devfreq->trans_table);
@@ -732,10 +789,28 @@ struct devfreq *devfreq_add_device(struct device *dev,
 	if (err) {
 		put_device(&devfreq->dev);
 		goto err_out;
 	}
 
+	/*
+	 * Register notifiers for updates to min/max_freq after device is
+	 * initialized (and we can handle notifications) but before the
+	 * governor is started (which should do an initial enforcement of
+	 * constraints).
+	 */
+	devfreq->nb_min.notifier_call = devfreq_qos_min_notifier_call;
+	err = dev_pm_qos_add_notifier(devfreq->dev.parent, &devfreq->nb_min,
+				      DEV_PM_QOS_MIN_FREQUENCY);
+	if (err)
+		goto err_devfreq;
+
+	devfreq->nb_max.notifier_call = devfreq_qos_max_notifier_call;
+	err = dev_pm_qos_add_notifier(devfreq->dev.parent, &devfreq->nb_max,
+				      DEV_PM_QOS_MAX_FREQUENCY);
+	if (err)
+		goto err_devfreq;
+
 	mutex_lock(&devfreq_list_lock);
 
 	governor = try_then_request_governor(devfreq->governor_name);
 	if (IS_ERR(governor)) {
 		dev_err(dev, "%s: Unable to find governor for the device\n",
@@ -759,10 +834,11 @@ struct devfreq *devfreq_add_device(struct device *dev,
 
 	return devfreq;
 
 err_init:
 	mutex_unlock(&devfreq_list_lock);
+err_devfreq:
 	devfreq_remove_device(devfreq);
 	return ERR_PTR(err);
 
 err_dev:
 	/*
diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h
index 2bae9ed3c783..8b92ccbd1962 100644
--- a/include/linux/devfreq.h
+++ b/include/linux/devfreq.h
@@ -134,10 +134,12 @@ struct devfreq_dev_profile {
  * @total_trans:	Number of devfreq transitions
  * @trans_table:	Statistics of devfreq transitions
  * @time_in_state:	Statistics of devfreq states
  * @last_stat_updated:	The last time stat updated
  * @transition_notifier_list: list head of DEVFREQ_TRANSITION_NOTIFIER notifier
+ * @nb_min:		Notifier block for DEV_PM_QOS_MIN_FREQUENCY
+ * @nb_max:		Notifier block for DEV_PM_QOS_MAX_FREQUENCY
  *
  * This structure stores the devfreq information for a give device.
  *
  * Note that when a governor accesses entries in struct devfreq in its
  * functions except for the context of callbacks defined in struct
@@ -176,10 +178,13 @@ struct devfreq {
 	unsigned int *trans_table;
 	unsigned long *time_in_state;
 	unsigned long last_stat_updated;
 
 	struct srcu_notifier_head transition_notifier_list;
+
+	struct notifier_block nb_min;
+	struct notifier_block nb_max;
 };
 
 struct devfreq_freqs {
 	unsigned long old;
 	unsigned long new;
-- 
2.17.1


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

^ permalink raw reply related

* [PATCH v7 4/6] PM / devfreq: Introduce devfreq_get_freq_range
From: Leonard Crestez @ 2019-09-23 21:10 UTC (permalink / raw)
  To: MyungJoo Ham, Kyungmin Park, Matthias Kaehlcke
  Cc: Artur Świgoń, Abel Vesa, Saravana Kannan, linux-pm,
	Viresh Kumar, NXP Linux Team, Krzysztof Kozlowski, Lukasz Luba,
	Chanwoo Choi, Alexandre Bailon, Martin Kepplinger, Georgi Djakov,
	linux-arm-kernel, Jacky Bai
In-Reply-To: <cover.1569272883.git.leonard.crestez@nxp.com>

Moving handling of min/max freq to a single function and call it from
update_devfreq and for printing min/max freq values in sysfs.

This changes the behavior of out-of-range min_freq/max_freq: clamping
is now done at evaluation time. This means that if an out-of-range
constraint is imposed by sysfs and it later becomes valid then it will
be enforced.

Signed-off-by: Leonard Crestez <leonard.crestez@nxp.com>
Reviewed-by: Matthias Kaehlcke <mka@chromium.org>
---
 drivers/devfreq/devfreq.c | 111 +++++++++++++++++++++-----------------
 1 file changed, 63 insertions(+), 48 deletions(-)

diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index 1cec816d3d00..7f152a582e78 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -24,10 +24,12 @@
 #include <linux/printk.h>
 #include <linux/hrtimer.h>
 #include <linux/of.h>
 #include "governor.h"
 
+#define HZ_PER_KHZ 1000
+
 #define CREATE_TRACE_POINTS
 #include <trace/events/devfreq.h>
 
 static struct class *devfreq_class;
 
@@ -96,10 +98,50 @@ static unsigned long find_available_max_freq(struct devfreq *devfreq)
 		dev_pm_opp_put(opp);
 
 	return max_freq;
 }
 
+/**
+ * devfreq_get_freq_range() - Get the current freq range
+ * @devfreq:	the devfreq instance
+ * @min_freq:	the min frequency
+ * @max_freq:	the max frequency
+ *
+ * This takes into consideration all constraints.
+ */
+static void devfreq_get_freq_range(struct devfreq *devfreq,
+				   unsigned long *min_freq,
+				   unsigned long *max_freq)
+{
+	unsigned long *freq_table = devfreq->profile->freq_table;
+
+	lockdep_assert_held(&devfreq->lock);
+
+	/* Init min/max frequency from freq table */
+	if (freq_table[0] < freq_table[devfreq->profile->max_state - 1]) {
+		*min_freq = freq_table[0];
+		*max_freq = freq_table[devfreq->profile->max_state - 1];
+	} else {
+		*min_freq = freq_table[devfreq->profile->max_state - 1];
+		*max_freq = freq_table[0];
+	}
+
+	/* constraints from sysfs */
+	*min_freq = max(*min_freq, devfreq->min_freq);
+	*max_freq = min(*max_freq, devfreq->max_freq);
+
+	/* constraints from OPP interface */
+	*min_freq = max(*min_freq, devfreq->scaling_min_freq);
+	/* scaling_max_freq can be zero on error */
+	if (devfreq->scaling_max_freq)
+		*max_freq = min(*max_freq, devfreq->scaling_max_freq);
+
+	/* max_freq takes precedence over min_freq */
+	if (*min_freq > *max_freq)
+		*min_freq = *max_freq;
+}
+
 /**
  * devfreq_get_freq_level() - Lookup freq_table for the frequency
  * @devfreq:	the devfreq instance
  * @freq:	the target frequency
  */
@@ -349,21 +391,13 @@ int update_devfreq(struct devfreq *devfreq)
 
 	/* Reevaluate the proper frequency */
 	err = devfreq->governor->get_target_freq(devfreq, &freq);
 	if (err)
 		return err;
+	devfreq_get_freq_range(devfreq, &min_freq, &max_freq);
 
-	/*
-	 * Adjust the frequency with user freq, QoS and available freq.
-	 *
-	 * List from the highest priority
-	 * max_freq
-	 * min_freq
-	 */
-	max_freq = min(devfreq->scaling_max_freq, devfreq->max_freq);
-	min_freq = max(devfreq->scaling_min_freq, devfreq->min_freq);
-
+	/* max freq takes priority over min freq */
 	if (freq < min_freq) {
 		freq = min_freq;
 		flags &= ~DEVFREQ_FLAG_LEAST_UPPER_BOUND; /* Use GLB */
 	}
 	if (freq > max_freq) {
@@ -1278,40 +1312,28 @@ static ssize_t min_freq_store(struct device *dev, struct device_attribute *attr,
 	ret = sscanf(buf, "%lu", &value);
 	if (ret != 1)
 		return -EINVAL;
 
 	mutex_lock(&df->lock);
-
-	if (value) {
-		if (value > df->max_freq) {
-			ret = -EINVAL;
-			goto unlock;
-		}
-	} else {
-		unsigned long *freq_table = df->profile->freq_table;
-
-		/* Get minimum frequency according to sorting order */
-		if (freq_table[0] < freq_table[df->profile->max_state - 1])
-			value = freq_table[0];
-		else
-			value = freq_table[df->profile->max_state - 1];
-	}
-
 	df->min_freq = value;
 	update_devfreq(df);
-	ret = count;
-unlock:
 	mutex_unlock(&df->lock);
-	return ret;
+
+	return count;
 }
 
 static ssize_t min_freq_show(struct device *dev, struct device_attribute *attr,
 			     char *buf)
 {
 	struct devfreq *df = to_devfreq(dev);
+	unsigned long min_freq, max_freq;
 
-	return sprintf(buf, "%lu\n", max(df->scaling_min_freq, df->min_freq));
+	mutex_lock(&df->lock);
+	devfreq_get_freq_range(df, &min_freq, &max_freq);
+	mutex_unlock(&df->lock);
+
+	return sprintf(buf, "%lu\n", min_freq);
 }
 
 static ssize_t max_freq_store(struct device *dev, struct device_attribute *attr,
 			      const char *buf, size_t count)
 {
@@ -1323,40 +1345,33 @@ static ssize_t max_freq_store(struct device *dev, struct device_attribute *attr,
 	if (ret != 1)
 		return -EINVAL;
 
 	mutex_lock(&df->lock);
 
-	if (value) {
-		if (value < df->min_freq) {
-			ret = -EINVAL;
-			goto unlock;
-		}
-	} else {
-		unsigned long *freq_table = df->profile->freq_table;
-
-		/* Get maximum frequency according to sorting order */
-		if (freq_table[0] < freq_table[df->profile->max_state - 1])
-			value = freq_table[df->profile->max_state - 1];
-		else
-			value = freq_table[0];
-	}
+	/* Interpret zero as "don't care" */
+	if (!value)
+		value = ULONG_MAX;
 
 	df->max_freq = value;
 	update_devfreq(df);
-	ret = count;
-unlock:
 	mutex_unlock(&df->lock);
-	return ret;
+
+	return count;
 }
 static DEVICE_ATTR_RW(min_freq);
 
 static ssize_t max_freq_show(struct device *dev, struct device_attribute *attr,
 			     char *buf)
 {
 	struct devfreq *df = to_devfreq(dev);
+	unsigned long min_freq, max_freq;
+
+	mutex_lock(&df->lock);
+	devfreq_get_freq_range(df, &min_freq, &max_freq);
+	mutex_unlock(&df->lock);
 
-	return sprintf(buf, "%lu\n", min(df->scaling_max_freq, df->max_freq));
+	return sprintf(buf, "%lu\n", max_freq);
 }
 static DEVICE_ATTR_RW(max_freq);
 
 static ssize_t available_frequencies_show(struct device *d,
 					  struct device_attribute *attr,
-- 
2.17.1


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

^ permalink raw reply related

* [PATCH v7 3/6] PM / devfreq: Don't take lock in devfreq_add_device
From: Leonard Crestez @ 2019-09-23 21:10 UTC (permalink / raw)
  To: MyungJoo Ham, Kyungmin Park, Matthias Kaehlcke
  Cc: Artur Świgoń, Abel Vesa, Saravana Kannan, linux-pm,
	Viresh Kumar, NXP Linux Team, Krzysztof Kozlowski, Lukasz Luba,
	Chanwoo Choi, Alexandre Bailon, Martin Kepplinger, Georgi Djakov,
	linux-arm-kernel, Jacky Bai
In-Reply-To: <cover.1569272883.git.leonard.crestez@nxp.com>

A device usually doesn't need to lock itself during initialization
because it is not yet reachable from other threads.

This simplifies the code and helps avoid recursive lock warnings.

Signed-off-by: Leonard Crestez <leonard.crestez@nxp.com>
Reviewed-by: Matthias Kaehlcke <mka@chromium.org>
---
 drivers/devfreq/devfreq.c | 10 ----------
 1 file changed, 10 deletions(-)

diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index 8bbcd4efa09f..1cec816d3d00 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -634,11 +634,10 @@ struct devfreq *devfreq_add_device(struct device *dev,
 		err = -ENOMEM;
 		goto err_out;
 	}
 
 	mutex_init(&devfreq->lock);
-	mutex_lock(&devfreq->lock);
 	devfreq->dev.parent = dev;
 	devfreq->dev.class = devfreq_class;
 	devfreq->dev.release = devfreq_dev_release;
 	INIT_LIST_HEAD(&devfreq->node);
 	devfreq->profile = profile;
@@ -647,28 +646,24 @@ struct devfreq *devfreq_add_device(struct device *dev,
 	devfreq->last_status.current_frequency = profile->initial_freq;
 	devfreq->data = data;
 	devfreq->nb.notifier_call = devfreq_notifier_call;
 
 	if (!devfreq->profile->max_state && !devfreq->profile->freq_table) {
-		mutex_unlock(&devfreq->lock);
 		err = set_freq_table(devfreq);
 		if (err < 0)
 			goto err_dev;
-		mutex_lock(&devfreq->lock);
 	}
 
 	devfreq->scaling_min_freq = find_available_min_freq(devfreq);
 	if (!devfreq->scaling_min_freq) {
-		mutex_unlock(&devfreq->lock);
 		err = -EINVAL;
 		goto err_dev;
 	}
 	devfreq->min_freq = devfreq->scaling_min_freq;
 
 	devfreq->scaling_max_freq = find_available_max_freq(devfreq);
 	if (!devfreq->scaling_max_freq) {
-		mutex_unlock(&devfreq->lock);
 		err = -EINVAL;
 		goto err_dev;
 	}
 	devfreq->max_freq = devfreq->scaling_max_freq;
 
@@ -679,20 +674,18 @@ struct devfreq *devfreq_add_device(struct device *dev,
 			array3_size(sizeof(unsigned int),
 				    devfreq->profile->max_state,
 				    devfreq->profile->max_state),
 			GFP_KERNEL);
 	if (!devfreq->trans_table) {
-		mutex_unlock(&devfreq->lock);
 		err = -ENOMEM;
 		goto err_dev;
 	}
 
 	devfreq->time_in_state = kcalloc(devfreq->profile->max_state,
 					 sizeof(unsigned long),
 					 GFP_KERNEL);
 	if (!devfreq->time_in_state) {
-		mutex_unlock(&devfreq->lock);
 		err = -ENOMEM;
 		goto err_dev;
 	}
 
 	devfreq->last_stat_updated = jiffies;
@@ -701,17 +694,14 @@ struct devfreq *devfreq_add_device(struct device *dev,
 
 	dev_set_name(&devfreq->dev, "devfreq%d",
 				atomic_inc_return(&devfreq_no));
 	err = device_register(&devfreq->dev);
 	if (err) {
-		mutex_unlock(&devfreq->lock);
 		put_device(&devfreq->dev);
 		goto err_out;
 	}
 
-	mutex_unlock(&devfreq->lock);
-
 	mutex_lock(&devfreq_list_lock);
 
 	governor = try_then_request_governor(devfreq->governor_name);
 	if (IS_ERR(governor)) {
 		dev_err(dev, "%s: Unable to find governor for the device\n",
-- 
2.17.1


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

^ permalink raw reply related

* [PATCH v7 2/6] PM / devfreq: Move more initialization before registration
From: Leonard Crestez @ 2019-09-23 21:10 UTC (permalink / raw)
  To: MyungJoo Ham, Kyungmin Park, Matthias Kaehlcke
  Cc: Artur Świgoń, Abel Vesa, Saravana Kannan, linux-pm,
	Viresh Kumar, NXP Linux Team, Krzysztof Kozlowski, Lukasz Luba,
	Chanwoo Choi, Alexandre Bailon, Martin Kepplinger, Georgi Djakov,
	linux-arm-kernel, Jacky Bai
In-Reply-To: <cover.1569272883.git.leonard.crestez@nxp.com>

In general it is a better to initialize an object before making it
accessible externally (through device_register).

This makes it possible to avoid relying on locking a partially
initialized object.

Signed-off-by: Leonard Crestez <leonard.crestez@nxp.com>
Reviewed-by: Matthias Kaehlcke <mka@chromium.org>
---
 drivers/devfreq/devfreq.c | 43 +++++++++++++++++++++++----------------
 1 file changed, 25 insertions(+), 18 deletions(-)

diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index f5bea7350f72..8bbcd4efa09f 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -588,10 +588,12 @@ static void devfreq_dev_release(struct device *dev)
 	mutex_unlock(&devfreq_list_lock);
 
 	if (devfreq->profile->exit)
 		devfreq->profile->exit(devfreq->dev.parent);
 
+	kfree(devfreq->time_in_state);
+	kfree(devfreq->trans_table);
 	mutex_destroy(&devfreq->lock);
 	kfree(devfreq);
 }
 
 /**
@@ -671,44 +673,43 @@ struct devfreq *devfreq_add_device(struct device *dev,
 	devfreq->max_freq = devfreq->scaling_max_freq;
 
 	devfreq->suspend_freq = dev_pm_opp_get_suspend_opp_freq(dev);
 	atomic_set(&devfreq->suspend_count, 0);
 
-	dev_set_name(&devfreq->dev, "devfreq%d",
-				atomic_inc_return(&devfreq_no));
-	err = device_register(&devfreq->dev);
-	if (err) {
-		mutex_unlock(&devfreq->lock);
-		put_device(&devfreq->dev);
-		goto err_out;
-	}
-
-	devfreq->trans_table = devm_kzalloc(&devfreq->dev,
+	devfreq->trans_table = kzalloc(
 			array3_size(sizeof(unsigned int),
 				    devfreq->profile->max_state,
 				    devfreq->profile->max_state),
 			GFP_KERNEL);
 	if (!devfreq->trans_table) {
 		mutex_unlock(&devfreq->lock);
 		err = -ENOMEM;
-		goto err_devfreq;
+		goto err_dev;
 	}
 
-	devfreq->time_in_state = devm_kcalloc(&devfreq->dev,
-			devfreq->profile->max_state,
-			sizeof(unsigned long),
-			GFP_KERNEL);
+	devfreq->time_in_state = kcalloc(devfreq->profile->max_state,
+					 sizeof(unsigned long),
+					 GFP_KERNEL);
 	if (!devfreq->time_in_state) {
 		mutex_unlock(&devfreq->lock);
 		err = -ENOMEM;
-		goto err_devfreq;
+		goto err_dev;
 	}
 
 	devfreq->last_stat_updated = jiffies;
 
 	srcu_init_notifier_head(&devfreq->transition_notifier_list);
 
+	dev_set_name(&devfreq->dev, "devfreq%d",
+				atomic_inc_return(&devfreq_no));
+	err = device_register(&devfreq->dev);
+	if (err) {
+		mutex_unlock(&devfreq->lock);
+		put_device(&devfreq->dev);
+		goto err_out;
+	}
+
 	mutex_unlock(&devfreq->lock);
 
 	mutex_lock(&devfreq_list_lock);
 
 	governor = try_then_request_governor(devfreq->governor_name);
@@ -734,14 +735,20 @@ struct devfreq *devfreq_add_device(struct device *dev,
 
 	return devfreq;
 
 err_init:
 	mutex_unlock(&devfreq_list_lock);
-err_devfreq:
 	devfreq_remove_device(devfreq);
-	devfreq = NULL;
+	return ERR_PTR(err);
+
 err_dev:
+	/*
+	 * Cleanup path for errors that happen before registration.
+	 * Otherwise we rely on devfreq_dev_release.
+	 */
+	kfree(devfreq->time_in_state);
+	kfree(devfreq->trans_table);
 	kfree(devfreq);
 err_out:
 	return ERR_PTR(err);
 }
 EXPORT_SYMBOL(devfreq_add_device);
-- 
2.17.1


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

^ permalink raw reply related

* [PATCH v7 1/6] PM / devfreq: Don't fail devfreq_dev_release if not in list
From: Leonard Crestez @ 2019-09-23 21:10 UTC (permalink / raw)
  To: MyungJoo Ham, Kyungmin Park, Matthias Kaehlcke
  Cc: Artur Świgoń, Abel Vesa, Saravana Kannan, linux-pm,
	Viresh Kumar, NXP Linux Team, Krzysztof Kozlowski, Lukasz Luba,
	Chanwoo Choi, Alexandre Bailon, Martin Kepplinger, Georgi Djakov,
	linux-arm-kernel, Jacky Bai
In-Reply-To: <cover.1569272883.git.leonard.crestez@nxp.com>

Right now devfreq_dev_release will print a warning and abort the rest of
the cleanup if the devfreq instance is not part of the global
devfreq_list. But this is a valid scenario, for example it can happen if
the governor can't be found or on any other init error that happens
after device_register.

Initialize devfreq->node to an empty list head in devfreq_add_device so
that list_del becomes a safe noop inside devfreq_dev_release and we can
continue the rest of the cleanup.

Signed-off-by: Leonard Crestez <leonard.crestez@nxp.com>
Reviewed-by: Matthias Kaehlcke <mka@chromium.org>
---
 drivers/devfreq/devfreq.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index e9e6c8f1dc4b..f5bea7350f72 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -582,15 +582,10 @@ static int devfreq_notifier_call(struct notifier_block *nb, unsigned long type,
 static void devfreq_dev_release(struct device *dev)
 {
 	struct devfreq *devfreq = to_devfreq(dev);
 
 	mutex_lock(&devfreq_list_lock);
-	if (IS_ERR(find_device_devfreq(devfreq->dev.parent))) {
-		mutex_unlock(&devfreq_list_lock);
-		dev_warn(&devfreq->dev, "releasing devfreq which doesn't exist\n");
-		return;
-	}
 	list_del(&devfreq->node);
 	mutex_unlock(&devfreq_list_lock);
 
 	if (devfreq->profile->exit)
 		devfreq->profile->exit(devfreq->dev.parent);
@@ -641,10 +636,11 @@ struct devfreq *devfreq_add_device(struct device *dev,
 	mutex_init(&devfreq->lock);
 	mutex_lock(&devfreq->lock);
 	devfreq->dev.parent = dev;
 	devfreq->dev.class = devfreq_class;
 	devfreq->dev.release = devfreq_dev_release;
+	INIT_LIST_HEAD(&devfreq->node);
 	devfreq->profile = profile;
 	strncpy(devfreq->governor_name, governor_name, DEVFREQ_NAME_LEN);
 	devfreq->previous_freq = profile->initial_freq;
 	devfreq->last_status.current_frequency = profile->initial_freq;
 	devfreq->data = data;
-- 
2.17.1


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

^ permalink raw reply related

* [PATCH v7 0/6] PM / devfreq: Add dev_pm_qos support
From: Leonard Crestez @ 2019-09-23 21:10 UTC (permalink / raw)
  To: MyungJoo Ham, Kyungmin Park, Matthias Kaehlcke
  Cc: Artur Świgoń, Abel Vesa, Saravana Kannan, linux-pm,
	Viresh Kumar, NXP Linux Team, Krzysztof Kozlowski, Lukasz Luba,
	Chanwoo Choi, Alexandre Bailon, Martin Kepplinger, Georgi Djakov,
	linux-arm-kernel, Jacky Bai

Add dev_pm_qos notifiers to devfreq core in order to support frequency
limits via dev_pm_qos_add_request.

Unlike the rest of devfreq the dev_pm_qos frequency is measured in Khz,
this is consistent with current dev_pm_qos usage for cpufreq and
allows frequencies above 2Ghz (pm_qos expresses limits as s32).

Like with cpufreq the handling of min_freq/max_freq is moved to the
dev_pm_qos mechanism. Constraints from userspace are no longer clamped on
store, instead all values can be written and we only check against OPPs in a
new devfreq_get_freq_range function. This is consistent with the design of
dev_pm_qos.

Notifiers from pm_qos are executed under a single global dev_pm_qos_mtx and
need to take devfreq->lock. Notifier registration takes the same dev_pm_qos_mtx
so in order to prevent lockdep warnings it must be done outside devfreq->lock.
Current devfreq_add_device does all initialization under devfreq->lock and that
needs to be relaxed.

---
Changes since v6:
* Don't return errno from devfreq_qos_notifier_call, return NOTIFY_DONE
and print the error. Message mirrors devfreq_monitor.
* More spelling and punctuation nits
Link to v6: https://patchwork.kernel.org/cover/11157201/

Changes since v5 are mostly cosmetic:
* Drop patches which are not strictly related to PM QoS.
* Add a comment explaining why devfreq_add_device needs two cleanup paths.
* Remove {} for single line.
* Rename {min,max}_freq_req to user_{min,max}_freq_req
* Collect reviews
Link to v5: https://patchwork.kernel.org/cover/11149497/

Sorry for forgetting to properly label v5. I know this is inside the
merge window but review would still be appreciated.

Changes since v4:
* Move more devfreq_add_device init ahead of device_register.
* Make devfreq_dev_release cleanup devices not yet in devfreq_list. This is
simpler than previous attempt to add to devfreq_list sonner.
* Take devfreq->lock in trans_stat_show
* Register dev_pm_opp notifier on devfreq parent dev (which has OPPs)
Link to v4: https://patchwork.kernel.org/cover/11114657/

Changes since v4:
* Move more devfreq_add_device init ahead of device_register.
* Make devfreq_dev_release cleanup devices not yet in devfreq_list. This is
simpler than previous attempt to add to devfreq_list sonner.
* Take devfreq->lock in trans_stat_show
* Register dev_pm_opp notifier on devfreq parent dev (which has OPPs)
Like to v4: https://patchwork.kernel.org/cover/11114657/

Changes since v3:
* Cleanup locking and error-handling in devfreq_add_device
* Register notifiers after device registration but before governor start
* Keep the initialization of min_req/max_req ahead of device_register
because it's used for sysfs handling
* Use HZ_PER_KHZ instead of 1000
* Add kernel-doc comments
* Move OPP notifier to core
Link to v3: https://patchwork.kernel.org/cover/11104061/

Changes since v2:
* Handle sysfs via dev_pm_qos (in separate patch)
* Add locking to {min,max}_freq_show
* Fix checkpatch issues (long lines etc)
Link to v2: https://patchwork.kernel.org/patch/11084279/

Changes since v1:
* Add doxygen comments for min_nb/max_nb
* Remove notifiers on error/cleanup paths. Keep gotos simple by relying on
dev_pm_qos_remove_notifier ignoring notifiers which were not added.
Link to v1: https://patchwork.kernel.org/patch/11078475/

Leonard Crestez (6):
  PM / devfreq: Don't fail devfreq_dev_release if not in list
  PM / devfreq: Move more initialization before registration
  PM / devfreq: Don't take lock in devfreq_add_device
  PM / devfreq: Introduce devfreq_get_freq_range
  PM / devfreq: Add PM QoS support
  PM / devfreq: Use PM QoS for sysfs min/max_freq

 drivers/devfreq/devfreq.c | 269 ++++++++++++++++++++++++++------------
 include/linux/devfreq.h   |  14 +-
 2 files changed, 193 insertions(+), 90 deletions(-)

-- 
2.17.1


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

^ permalink raw reply

* Re: [PATCH 4/5] clk: meson: meson8b: don't register the XTAL clock when provided via OF
From: Martin Blumenstingl @ 2019-09-23 20:57 UTC (permalink / raw)
  To: Jerome Brunet
  Cc: mark.rutland, devicetree, Neil Armstrong, khilman, linux-kernel,
	robh+dt, linux-amlogic, linux-clk, linux-arm-kernel
In-Reply-To: <1jwodzs6ir.fsf@starbuckisacylon.baylibre.com>

On Mon, Sep 23, 2019 at 11:31 AM Jerome Brunet <jbrunet@baylibre.com> wrote:
>
> On Sat 21 Sep 2019 at 17:12, Martin Blumenstingl <martin.blumenstingl@googlemail.com> wrote:
>
> > The XTAL clock is an actual crystal on the PCB. Thus the meson8b clock
> > driver should not register the XTAL clock - instead it should be
> > provided via .dts and then passed to the clock controller.
> >
> > Skip the registration of the XTAL clock if a parent clock is provided
> > via OF. Fall back to registering the XTAL clock if this is not the case
> > to keep support for old .dtbs.
> >
> > Signed-off-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
> > ---
> >  drivers/clk/meson/meson8b.c | 12 +++++++++---
> >  1 file changed, 9 insertions(+), 3 deletions(-)
> >
> > diff --git a/drivers/clk/meson/meson8b.c b/drivers/clk/meson/meson8b.c
> > index b785b67baf2b..15ec14fde2a0 100644
> > --- a/drivers/clk/meson/meson8b.c
> > +++ b/drivers/clk/meson/meson8b.c
> > @@ -3682,10 +3682,16 @@ static void __init meson8b_clkc_init_common(struct device_node *np,
> >               meson8b_clk_regmaps[i]->map = map;
> >
> >       /*
> > -      * register all clks
> > -      * CLKID_UNUSED = 0, so skip it and start with CLKID_XTAL = 1
> > +      * always skip CLKID_UNUSED and also skip XTAL if the .dtb provides the
> > +      * XTAL clock as input.
> >        */
> > -     for (i = CLKID_XTAL; i < CLK_NR_CLKS; i++) {
> > +     if (of_clk_get_parent_count(np))
>
> If we are going for this, I'd prefer if could explicity check for the
> clock named "xtal" instead of just checking if DT has clocks.
OK, I'll wait a few days and then fix this in v2


Martin

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

^ permalink raw reply

* Re: [RFCv4 3/7] dt-bindings: devfreq: imx: Describe interconnect properties
From: Rob Herring @ 2019-09-23 21:03 UTC (permalink / raw)
  To: Leonard Crestez
  Cc: Mark Rutland, Artur Świgoń,
	linux-arm-kernel@lists.infradead.org, Saravana Kannan,
	linux-pm@vger.kernel.org, Stephen Boyd, Viresh Kumar,
	Michael Turquette, Krzysztof Kozlowski, Chanwoo Choi,
	Kyungmin Park, MyungJoo Ham, Alexandre Bailon,
	kernel@pengutronix.de, Aisheng Dong, Fabio Estevam, Shawn Guo,
	Georgi Djakov, devicetree@vger.kernel.org, dl-linux-imx
In-Reply-To: <VI1PR04MB70237046A8DF88936C7A83F8EE850@VI1PR04MB7023.eurprd04.prod.outlook.com>

On Mon, Sep 23, 2019 at 12:42 PM Leonard Crestez
<leonard.crestez@nxp.com> wrote:
>
> On 17.09.2019 23:20, Rob Herring wrote:
> > On Fri, Aug 23, 2019 at 05:36:56PM +0300, Leonard Crestez wrote:
> >> The interconnect-node-id property is parsed by the imx interconnect
> >> driver to find nodes on which frequencies can be adjusted.
> >>
> >> Add #interconnect-cells so that device drivers can request paths from
> >> bus nodes instead of requiring a separate "virtual" node to represent
> >> the interconnect itself.
> >>
> >> Signed-off-by: Leonard Crestez <leonard.crestez@nxp.com>
> >> ---
> >>   Documentation/devicetree/bindings/devfreq/imx-ddrc.yaml | 5 +++++
> >>   Documentation/devicetree/bindings/devfreq/imx.yaml      | 5 +++++
> >>   2 files changed, 10 insertions(+)
> >
> > Please combine this with the other series for devfreq support.
>
> I understand that having two series which add to the same bindings file
> is odd but the devfreq and interconnect parts are independent to a very
> large degree and devfreq can be useful on it's own.

To start with, I'm suspicious of any 'devfreq' binding because that's
a Linux thing. I somewhat expect that the interconnect binding should
replace the devfreq binding, but I haven't been able to investigate.

> The only reason devfreq bindings are updated is to avoid adding a
> "virtual" node for interconnect. Since DT is a big source of confusion
> here can you read https://patchwork.kernel.org/cover/11111865/#22883457
> and maybe offer some advice?

Design something that matches the structure of the h/w not how Linux
drivers happen to be structured. I can't tell what that is without any
context around adding a couple of properties. Nor do I have the time
to dig into each SoC vendor's bus structure if it's even documented
publicly.

I also don't follow why you need 'interconnect-node-id' and if you do,
it should be a common property.

Rob

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

^ permalink raw reply

* Re: [PATCH 0/5] provide the XTAL clock via OF on Meson8/8b/8m2
From: Martin Blumenstingl @ 2019-09-23 20:56 UTC (permalink / raw)
  To: Jerome Brunet
  Cc: mark.rutland, devicetree, Neil Armstrong, khilman, linux-kernel,
	robh+dt, linux-amlogic, linux-clk, linux-arm-kernel
In-Reply-To: <1jzhivs6n6.fsf@starbuckisacylon.baylibre.com>

Hi Jerome,

On Mon, Sep 23, 2019 at 11:29 AM Jerome Brunet <jbrunet@baylibre.com> wrote:
>
> On Sat 21 Sep 2019 at 17:12, Martin Blumenstingl <martin.blumenstingl@googlemail.com> wrote:
>
> > So far the HHI clock controller has been providing the XTAL clock on
> > Amlogic Meson8/Meson8b/Meson8m2 SoCs.
> > This is not correct because the XTAL is actually a crystal on the
> > boards and the SoC has a dedicated input for it.
> >
> > This updates the dt-bindings of the HHI clock controller and defines
> > a fixed-clock in meson.dtsi (along with switching everything over to
> > use this clock).
> > The clock driver needs three updates to use this:
> > - patch #2 uses clk_hw_set_parent in the CPU clock notifier. This drops
> >   the explicit reference to CLKID_XTAL while at the same time making
> >   the code much easier (thanks to Neil for providing this new method
> >   as part of the G12A CPU clock bringup!)
> > - patch #3 ensures that the clock driver doesn't rely on it's internal
> >   XTAL clock while not losing support for older .dtbs that don't have
> >   the XTAL clock input yet
> > - with patch #4 the clock controller's own XTAL clock is not registered
> >   anymore when a clock input is provided via OF
> >
> > This series is a functional no-op. It's main goal is to better represent
> > how the actual hardware looks like.
>
> I'm a bit unsure about this series.
>
> On one hand, I totally agree with you ... having the xtal in DT is the
> right way to do it ... when done from the start
yep

> On the other hand, things have been this way for years, they are working
> and going for xtal in DT does not solve any pending issue. Doing this
> means adding complexity in the driver to support both methods. It is
> also quite a significant change in DT :/
my two main motivations were:
- keeping the 32-bit SoCs as similar as possible to the 64-bit ones in
terms of "how are the [clock] drivers implemented"
- with the DDR clock controller the .dts looked weird: &ddr_clkc took
CLKID_XTAL from &clkc as input and &clkc took DDR_CLKID_DDR_PLL as
input from &ddr_clkc

RE complexity in the driver to support both:
I still have a cleanup of the meson8b.c init code on my TODO-list
because we're still supporting .dtbs without parent syscon
my plan is to drop that code-path along with the newly added fallback
for "skip CLKID_XTAL" (assuming this is accepted) together for v5.6 or
v5.7


Martin

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

^ permalink raw reply

* Re: [PATCH 0/6] add the DDR clock controller on Meson8 and Meson8b
From: Martin Blumenstingl @ 2019-09-23 20:49 UTC (permalink / raw)
  To: Jerome Brunet
  Cc: mark.rutland, devicetree, Neil Armstrong, khilman, linux-kernel,
	robh+dt, linux-amlogic, linux-clk, linux-arm-kernel
In-Reply-To: <1jsgons4wy.fsf@starbuckisacylon.baylibre.com>

Hi Jerome,

On Mon, Sep 23, 2019 at 12:06 PM Jerome Brunet <jbrunet@baylibre.com> wrote:
>
> On Sat 21 Sep 2019 at 17:18, Martin Blumenstingl <martin.blumenstingl@googlemail.com> wrote:
>
> > Meson8 and Meson8b SoCs embed a DDR clock controller in their MMCBUS
> > registers. This series:
> > - adds support for this DDR clock controller (patches 0 and 1)
> > - wires up the DDR PLL as input for two audio clocks (patches 2 and 3)
>
> Have you been able to validate somehow that DDR rate calculated by CCF
> is the actual rate that gets to the audio clocks ?
no, I haven't been able to validate this (yet)

> While I understand the interest for completeness, I suspect the having
> the DDR clock as an audio parent was just for debugging purpose. IOW,
> I'm not sure if adding this parent is useful to an actual audio use
> case. As far as audio would be concerned, I think we are better of
> without this parent.
there at least three other (potential) consumers of the ddr_pll clocks
on the 32-bit SoCs:
- CPU clock mux [0]
- clk81 mux [1]
- USB PHY [2]

I have not validated any of these either

> > - adds the DDR clock controller to meson8.dtsi and meson8b.dtsi
> >
>
> Could you please separate the driver and DT series in the future ? Those
> take different paths and are meant for different maintainers.
sure - so far Kevin has been doing a great job of still tracking these
but I'm happy to split this into two patchsets


Martin


[0] https://github.com/endlessm/u-boot-meson/blob/345ee7eb02903f5ecb1173ffb2cd36666e44ebed/board/amlogic/m8b_m201_v1/firmware/timming.c#L441
[1] https://github.com/endlessm/u-boot-meson/blob/345ee7eb02903f5ecb1173ffb2cd36666e44ebed/board/amlogic/m8b_m201_v1/firmware/timming.c#L452
[2] https://github.com/endlessm/u-boot-meson/blob/f1ee03e3f7547d03e1478cc1fc967a9e5a121d92/arch/arm/cpu/aml_meson/m8/firmware/usb_boot/platform.c#L22

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

^ permalink raw reply

* [PATCH v5 16/17] arm64: kexec: configure trans_pgd page table for kexec
From: Pavel Tatashin @ 2019-09-23 20:34 UTC (permalink / raw)
  To: pasha.tatashin, jmorris, sashal, ebiederm, kexec, linux-kernel,
	corbet, catalin.marinas, will, linux-arm-kernel, marc.zyngier,
	james.morse, vladimir.murzin, matthias.bgg, bhsharma, linux-mm,
	mark.rutland
In-Reply-To: <20190923203427.294286-1-pasha.tatashin@soleen.com>

Configure a page table located in kexec-safe memory that has
the following mappings:

1. identity mapping for text of relocation function with executable
   permission.
2. identity mapping for argument for relocation function.
3. linear mappings for all source ranges
4. linear mappings for all destination ranges.

Also, configure el2_vector, that is used to jump to new kernel from EL2 on
non-VHE kernels.

Signed-off-by: Pavel Tatashin <pasha.tatashin@soleen.com>
---
 arch/arm64/include/asm/kexec.h      |  32 +++++++
 arch/arm64/kernel/asm-offsets.c     |   6 ++
 arch/arm64/kernel/machine_kexec.c   | 125 ++++++++++++++++++++++++++--
 arch/arm64/kernel/relocate_kernel.S |  16 +++-
 4 files changed, 170 insertions(+), 9 deletions(-)

diff --git a/arch/arm64/include/asm/kexec.h b/arch/arm64/include/asm/kexec.h
index d5b79d4c7fae..450d8440f597 100644
--- a/arch/arm64/include/asm/kexec.h
+++ b/arch/arm64/include/asm/kexec.h
@@ -90,6 +90,23 @@ static inline void crash_prepare_suspend(void) {}
 static inline void crash_post_resume(void) {}
 #endif
 
+#if defined(CONFIG_KEXEC_CORE)
+/* Global variables for the arm64_relocate_new_kernel routine. */
+extern const unsigned char arm64_relocate_new_kernel[];
+extern const unsigned long arm64_relocate_new_kernel_size;
+
+/* Body of the vector for escalating to EL2 from relocation routine */
+extern const unsigned char kexec_el1_sync[];
+extern const unsigned long kexec_el1_sync_size;
+
+#define KEXEC_EL2_VECTOR_TABLE_SIZE	2048
+#define KEXEC_EL2_SYNC_OFFSET		(KEXEC_EL2_VECTOR_TABLE_SIZE / 2)
+
+#endif
+
+#define KEXEC_SRC_START	PAGE_OFFSET
+#define KEXEC_DST_START	(PAGE_OFFSET + \
+			((UL(0xffffffffffffffff) - PAGE_OFFSET) >> 1) + 1)
 /*
  * kern_reloc_arg is passed to kernel relocation function as an argument.
  * head		kimage->head, allows to traverse through relocation segments.
@@ -97,6 +114,15 @@ static inline void crash_post_resume(void) {}
  *		kernel, or purgatory entry address).
  * kern_arg0	first argument to kernel is its dtb address. The other
  *		arguments are currently unused, and must be set to 0
+ * trans_ttbr0	idmap for relocation function and its argument
+ * trans_ttbr1	linear map for source/destination addresses.
+ * el2_vector	If present means that relocation routine will go to EL1
+ *		from EL2 to do the copy, and then back to EL2 to do the jump
+ *		to new world. This vector contains only the final jump
+ *		instruction at KEXEC_EL2_SYNC_OFFSET.
+ * src_addr	linear map for source pages.
+ * dst_addr	linear map for destination pages.
+ * copy_len	Number of bytes that need to be copied
  */
 struct kern_reloc_arg {
 	unsigned long	head;
@@ -105,6 +131,12 @@ struct kern_reloc_arg {
 	unsigned long	kern_arg1;
 	unsigned long	kern_arg2;
 	unsigned long	kern_arg3;
+	unsigned long	trans_ttbr0;
+	unsigned long	trans_ttbr1;
+	unsigned long	el2_vector;
+	unsigned long	src_addr;
+	unsigned long	dst_addr;
+	unsigned long	copy_len;
 };
 
 #define ARCH_HAS_KIMAGE_ARCH
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 900394907fd8..7c2ba09a8ceb 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -135,6 +135,12 @@ int main(void)
   DEFINE(KRELOC_KERN_ARG1,	offsetof(struct kern_reloc_arg, kern_arg1));
   DEFINE(KRELOC_KERN_ARG2,	offsetof(struct kern_reloc_arg, kern_arg2));
   DEFINE(KRELOC_KERN_ARG3,	offsetof(struct kern_reloc_arg, kern_arg3));
+  DEFINE(KRELOC_TRANS_TTBR0,	offsetof(struct kern_reloc_arg, trans_ttbr0));
+  DEFINE(KRELOC_TRANS_TTBR1,	offsetof(struct kern_reloc_arg, trans_ttbr1));
+  DEFINE(KRELOC_EL2_VECTOR,	offsetof(struct kern_reloc_arg, el2_vector));
+  DEFINE(KRELOC_SRC_ADDR,	offsetof(struct kern_reloc_arg, src_addr));
+  DEFINE(KRELOC_DST_ADDR,	offsetof(struct kern_reloc_arg, dst_addr));
+  DEFINE(KRELOC_COPY_LEN,	offsetof(struct kern_reloc_arg, copy_len));
 #endif
   return 0;
 }
diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c
index fb6138a1c9ff..71479013dd24 100644
--- a/arch/arm64/kernel/machine_kexec.c
+++ b/arch/arm64/kernel/machine_kexec.c
@@ -20,13 +20,10 @@
 #include <asm/mmu.h>
 #include <asm/mmu_context.h>
 #include <asm/page.h>
+#include <asm/trans_pgd.h>
 
 #include "cpu-reset.h"
 
-/* Global variables for the arm64_relocate_new_kernel routine. */
-extern const unsigned char arm64_relocate_new_kernel[];
-extern const unsigned long arm64_relocate_new_kernel_size;
-
 /**
  * kexec_image_info - For debugging output.
  */
@@ -74,15 +71,124 @@ static void *kexec_page_alloc(void *arg)
 	return page_address(page);
 }
 
+/*
+ * Map source segments starting from KEXEC_SRC_START, and map destination
+ * segments starting from KEXEC_DST_START, and return size of copy in
+ * *copy_len argument.
+ * Relocation function essentially needs to do:
+ * memcpy(KEXEC_DST_START, KEXEC_SRC_START, copy_len);
+ */
+static int map_segments(struct kimage *kimage, pgd_t *pgdp,
+			struct trans_pgd_info *info,
+			unsigned long *copy_len)
+{
+	unsigned long *ptr = 0;
+	unsigned long dest = 0;
+	unsigned long src_va = KEXEC_SRC_START;
+	unsigned long dst_va = KEXEC_DST_START;
+	unsigned long len = 0;
+	unsigned long entry, addr;
+	int rc;
+
+	for (entry = kimage->head; !(entry & IND_DONE); entry = *ptr++) {
+		addr = entry & PAGE_MASK;
+
+		switch (entry & IND_FLAGS) {
+		case IND_DESTINATION:
+			dest = addr;
+			break;
+		case IND_INDIRECTION:
+			ptr = __va(addr);
+			if (rc)
+				return rc;
+			break;
+		case IND_SOURCE:
+			rc = trans_pgd_map_page(info, pgdp, __va(addr),
+						src_va, PAGE_KERNEL);
+			if (rc)
+				return rc;
+			rc = trans_pgd_map_page(info, pgdp, __va(dest),
+						dst_va, PAGE_KERNEL);
+			if (rc)
+				return rc;
+			dest += PAGE_SIZE;
+			src_va += PAGE_SIZE;
+			dst_va += PAGE_SIZE;
+			len += PAGE_SIZE;
+		}
+	}
+	*copy_len = len;
+
+	return 0;
+}
+
+static int mmu_relocate_setup(struct kimage *kimage, unsigned long kern_reloc,
+			      struct kern_reloc_arg *kern_reloc_arg)
+{
+	struct trans_pgd_info info = {
+		.trans_alloc_page	= kexec_page_alloc,
+		.trans_alloc_arg	= kimage,
+	};
+
+	pgd_t *trans_ttbr0 = kexec_page_alloc(kimage);
+	pgd_t *trans_ttbr1 = kexec_page_alloc(kimage);
+	int rc;
+
+	if (!trans_ttbr0 || !trans_ttbr1)
+		return -ENOMEM;
+
+	rc = map_segments(kimage, trans_ttbr1, &info,
+			  &kern_reloc_arg->copy_len);
+	if (rc)
+		return rc;
+
+	/* Map relocation function va == pa */
+	rc = trans_pgd_map_page(&info, trans_ttbr0,  __va(kern_reloc),
+				kern_reloc, PAGE_KERNEL_EXEC);
+	if (rc)
+		return rc;
+
+	/* Map relocation function argument va == pa */
+	rc = trans_pgd_map_page(&info, trans_ttbr0, kern_reloc_arg,
+				__pa(kern_reloc_arg), PAGE_KERNEL);
+	if (rc)
+		return rc;
+
+	kern_reloc_arg->trans_ttbr0 = phys_to_ttbr(__pa(trans_ttbr0));
+	kern_reloc_arg->trans_ttbr1 = phys_to_ttbr(__pa(trans_ttbr1));
+	kern_reloc_arg->src_addr = KEXEC_SRC_START;
+	kern_reloc_arg->dst_addr = KEXEC_DST_START;
+
+	return 0;
+}
+
 int machine_kexec_post_load(struct kimage *kimage)
 {
+	unsigned long el2_vector = 0;
 	unsigned long kern_reloc;
 	struct kern_reloc_arg *kern_reloc_arg;
+	int rc = 0;
+
+	/*
+	 * Sanity check that relocation function + el2_vector fit into one
+	 * page.
+	 */
+	if (arm64_relocate_new_kernel_size > KEXEC_EL2_VECTOR_TABLE_SIZE) {
+		pr_err("can't fit relocation function and el2_vector in one page");
+		return -ENOMEM;
+	}
 
 	kern_reloc = page_to_phys(kimage->control_code_page);
 	memcpy(__va(kern_reloc), arm64_relocate_new_kernel,
 	       arm64_relocate_new_kernel_size);
 
+	/* Setup vector table only when EL2 is available, but no VHE */
+	if (is_hyp_mode_available() && !is_kernel_in_hyp_mode()) {
+		el2_vector = kern_reloc + KEXEC_EL2_VECTOR_TABLE_SIZE;
+		memcpy(__va(el2_vector + KEXEC_EL2_SYNC_OFFSET), kexec_el1_sync,
+		       kexec_el1_sync_size);
+	}
+
 	kern_reloc_arg = kexec_page_alloc(kimage);
 	if (!kern_reloc_arg)
 		return -ENOMEM;
@@ -92,10 +198,19 @@ int machine_kexec_post_load(struct kimage *kimage)
 
 	kern_reloc_arg->head = kimage->head;
 	kern_reloc_arg->entry_addr = kimage->start;
+	kern_reloc_arg->el2_vector = el2_vector;
 	kern_reloc_arg->kern_arg0 = kimage->arch.dtb_mem;
 
+	/*
+	 * If relocation is not needed, we do not need to enable MMU in
+	 * relocation routine, therefore do not create page tables for
+	 * scenarios such as crash kernel
+	 */
+	if (!(kimage->head & IND_DONE))
+		rc = mmu_relocate_setup(kimage, kern_reloc, kern_reloc_arg);
+
 	kexec_image_info(kimage);
-	return 0;
+	return rc;
 }
 
 /**
diff --git a/arch/arm64/kernel/relocate_kernel.S b/arch/arm64/kernel/relocate_kernel.S
index d352faf7cbe6..14243a678277 100644
--- a/arch/arm64/kernel/relocate_kernel.S
+++ b/arch/arm64/kernel/relocate_kernel.S
@@ -83,17 +83,25 @@ ENTRY(arm64_relocate_new_kernel)
 	ldr	x1, [x0, #KRELOC_KERN_ARG1]
 	ldr	x0, [x0, #KRELOC_KERN_ARG0]	/* x0 = dtb address */
 	br	x4
+.ltorg
+.Larm64_relocate_new_kernel_end:
 END(arm64_relocate_new_kernel)
 
-.ltorg
+ENTRY(kexec_el1_sync)
+	br	x4				/* Jump to new world from el2 */
+.Lkexec_el1_sync_end:
+END(kexec_el1_sync)
+
 .align 3	/* To keep the 64-bit values below naturally aligned. */
-.Lcopy_end:
 .org	KEXEC_CONTROL_PAGE_SIZE
-
 /*
  * arm64_relocate_new_kernel_size - Number of bytes to copy to the
  * control_code_page.
  */
 .globl arm64_relocate_new_kernel_size
 arm64_relocate_new_kernel_size:
-	.quad	.Lcopy_end - arm64_relocate_new_kernel
+	.quad	.Larm64_relocate_new_kernel_end - arm64_relocate_new_kernel
+
+.globl kexec_el1_sync_size
+kexec_el1_sync_size:
+	.quad	.Lkexec_el1_sync_end - kexec_el1_sync
-- 
2.23.0


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

^ permalink raw reply related

* [PATCH v5 17/17] arm64: kexec: enable MMU during kexec relocation
From: Pavel Tatashin @ 2019-09-23 20:34 UTC (permalink / raw)
  To: pasha.tatashin, jmorris, sashal, ebiederm, kexec, linux-kernel,
	corbet, catalin.marinas, will, linux-arm-kernel, marc.zyngier,
	james.morse, vladimir.murzin, matthias.bgg, bhsharma, linux-mm,
	mark.rutland
In-Reply-To: <20190923203427.294286-1-pasha.tatashin@soleen.com>

Now, that we have transitional page tables configured, temporarily enable
MMU to allow faster relocation of segments to final destination.

The performance data: for a moderate size kernel + initramfs: 25M the
relocation was taking 0.382s, with enabled MMU it now takes
0.019s only or x20 improvement.

The time is proportional to the size of relocation, therefore if initramfs
is larger, 100M it could take over a second.

Also, remove reloc_arg->head, as it is not needed anymore once MMU is
enabled.

Signed-off-by: Pavel Tatashin <pasha.tatashin@soleen.com>
---
 arch/arm64/include/asm/kexec.h      |   2 -
 arch/arm64/kernel/asm-offsets.c     |   1 -
 arch/arm64/kernel/machine_kexec.c   |   1 -
 arch/arm64/kernel/relocate_kernel.S | 136 +++++++++++++++++-----------
 4 files changed, 84 insertions(+), 56 deletions(-)

diff --git a/arch/arm64/include/asm/kexec.h b/arch/arm64/include/asm/kexec.h
index 450d8440f597..ad81ed3e5751 100644
--- a/arch/arm64/include/asm/kexec.h
+++ b/arch/arm64/include/asm/kexec.h
@@ -109,7 +109,6 @@ extern const unsigned long kexec_el1_sync_size;
 			((UL(0xffffffffffffffff) - PAGE_OFFSET) >> 1) + 1)
 /*
  * kern_reloc_arg is passed to kernel relocation function as an argument.
- * head		kimage->head, allows to traverse through relocation segments.
  * entry_addr	kimage->start, where to jump from relocation function (new
  *		kernel, or purgatory entry address).
  * kern_arg0	first argument to kernel is its dtb address. The other
@@ -125,7 +124,6 @@ extern const unsigned long kexec_el1_sync_size;
  * copy_len	Number of bytes that need to be copied
  */
 struct kern_reloc_arg {
-	unsigned long	head;
 	unsigned long	entry_addr;
 	unsigned long	kern_arg0;
 	unsigned long	kern_arg1;
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 7c2ba09a8ceb..13ad00b1b90f 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -129,7 +129,6 @@ int main(void)
   DEFINE(SDEI_EVENT_PRIORITY,	offsetof(struct sdei_registered_event, priority));
 #endif
 #ifdef CONFIG_KEXEC_CORE
-  DEFINE(KRELOC_HEAD,		offsetof(struct kern_reloc_arg, head));
   DEFINE(KRELOC_ENTRY_ADDR,	offsetof(struct kern_reloc_arg, entry_addr));
   DEFINE(KRELOC_KERN_ARG0,	offsetof(struct kern_reloc_arg, kern_arg0));
   DEFINE(KRELOC_KERN_ARG1,	offsetof(struct kern_reloc_arg, kern_arg1));
diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c
index 71479013dd24..970892970bab 100644
--- a/arch/arm64/kernel/machine_kexec.c
+++ b/arch/arm64/kernel/machine_kexec.c
@@ -196,7 +196,6 @@ int machine_kexec_post_load(struct kimage *kimage)
 	kimage->arch.kern_reloc = kern_reloc;
 	kimage->arch.kern_reloc_arg = __pa(kern_reloc_arg);
 
-	kern_reloc_arg->head = kimage->head;
 	kern_reloc_arg->entry_addr = kimage->start;
 	kern_reloc_arg->el2_vector = el2_vector;
 	kern_reloc_arg->kern_arg0 = kimage->arch.dtb_mem;
diff --git a/arch/arm64/kernel/relocate_kernel.S b/arch/arm64/kernel/relocate_kernel.S
index 14243a678277..96ff6760bd9c 100644
--- a/arch/arm64/kernel/relocate_kernel.S
+++ b/arch/arm64/kernel/relocate_kernel.S
@@ -4,6 +4,8 @@
  *
  * Copyright (C) Linaro.
  * Copyright (C) Huawei Futurewei Technologies.
+ * Copyright (c) 2019, Microsoft Corporation.
+ * Pavel Tatashin <patatash@linux.microsoft.com>
  */
 
 #include <linux/kexec.h>
@@ -14,6 +16,49 @@
 #include <asm/page.h>
 #include <asm/sysreg.h>
 
+/* Invalidae TLB */
+.macro tlb_invalidate
+	dsb	sy
+	dsb	ish
+	tlbi	vmalle1
+	dsb	ish
+	isb
+.endm
+
+/* Turn-off mmu at level specified by sctlr */
+.macro turn_off_mmu sctlr, tmp1, tmp2
+	mrs	\tmp1, \sctlr
+	ldr	\tmp2, =SCTLR_ELx_FLAGS
+	bic	\tmp1, \tmp1, \tmp2
+	pre_disable_mmu_workaround
+	msr	\sctlr, \tmp1
+	isb
+.endm
+
+/* Turn-on mmu at level specified by sctlr */
+.macro turn_on_mmu sctlr, tmp1, tmp2
+	mrs	\tmp1, \sctlr
+	ldr	\tmp2, =SCTLR_ELx_FLAGS
+	orr	\tmp1, \tmp1, \tmp2
+	msr	\sctlr, \tmp1
+	ic	iallu
+	dsb	nsh
+	isb
+.endm
+
+/*
+ * Set ttbr0 and ttbr1, called while MMU is disabled, so no need to temporarily
+ * set zero_page table. Invalidate TLB after new tables are set.
+ */
+.macro set_ttbr arg, tmp
+	ldr	\tmp, [\arg, #KRELOC_TRANS_TTBR0]
+	msr	ttbr0_el1, \tmp
+	ldr	\tmp, [\arg, #KRELOC_TRANS_TTBR1]
+	offset_ttbr1 \tmp
+	msr	ttbr1_el1, \tmp
+	isb
+.endm
+
 /*
  * arm64_relocate_new_kernel - Put a 2nd stage image in place and boot it.
  *
@@ -24,65 +69,52 @@
  * symbols arm64_relocate_new_kernel and arm64_relocate_new_kernel_end.  The
  * machine_kexec() routine will copy arm64_relocate_new_kernel to the kexec
  * safe memory that has been set up to be preserved during the copy operation.
+ *
+ * This function temporarily enables MMU if kernel relocation is needed.
+ * Also, if we enter this function at EL2 on non-VHE kernel, we temporarily go
+ * to EL1 to enable MMU, and escalate back to EL2 at the end to do the jump to
+ * the new kernel. This is determined by presence of el2_vector.
  */
 ENTRY(arm64_relocate_new_kernel)
-	/* Clear the sctlr_el2 flags. */
-	mrs	x2, CurrentEL
-	cmp	x2, #CurrentEL_EL2
+	mrs	x1, CurrentEL
+	cmp	x1, #CurrentEL_EL2
 	b.ne	1f
-	mrs	x2, sctlr_el2
-	ldr	x1, =SCTLR_ELx_FLAGS
-	bic	x2, x2, x1
-	pre_disable_mmu_workaround
-	msr	sctlr_el2, x2
-	isb
-1:	/* Check if the new image needs relocation. */
-	ldr	x16, [x0, #KRELOC_HEAD]		/* x16 = kimage_head */
-	tbnz	x16, IND_DONE_BIT, .Ldone
-	raw_dcache_line_size x15, x1		/* x15 = dcache line size */
-.Lloop:
-	and	x12, x16, PAGE_MASK		/* x12 = addr */
-	/* Test the entry flags. */
-.Ltest_source:
-	tbz	x16, IND_SOURCE_BIT, .Ltest_indirection
-
-	/* Invalidate dest page to PoC. */
-	mov     x2, x13
-	add     x20, x2, #PAGE_SIZE
-	sub     x1, x15, #1
-	bic     x2, x2, x1
-2:	dc      ivac, x2
-	add     x2, x2, x15
-	cmp     x2, x20
-	b.lo    2b
-	dsb     sy
-
-	copy_page x13, x12, x1, x2, x3, x4, x5, x6, x7, x8
-	b	.Lnext
-.Ltest_indirection:
-	tbz	x16, IND_INDIRECTION_BIT, .Ltest_destination
-	mov	x14, x12			/* ptr = addr */
-	b	.Lnext
-.Ltest_destination:
-	tbz	x16, IND_DESTINATION_BIT, .Lnext
-	mov	x13, x12			/* dest = addr */
-.Lnext:
-	ldr	x16, [x14], #8			/* entry = *ptr++ */
-	tbz	x16, IND_DONE_BIT, .Lloop	/* while (!(entry & DONE)) */
-.Ldone:
-	/* wait for writes from copy_page to finish */
-	dsb	nsh
-	ic	iallu
-	dsb	nsh
-	isb
-
-	/* Start new image. */
-	ldr	x4, [x0, #KRELOC_ENTRY_ADDR]	/* x4 = kimage_start */
+	turn_off_mmu sctlr_el2, x1, x2		/* Turn off MMU at EL2 */
+1:	mov	x20, xzr			/* x20 will hold vector value */
+	ldr	x11, [x0, #KRELOC_COPY_LEN]
+	cbz	x11, 5f				/* Check if need to relocate */
+	ldr	x20, [x0, #KRELOC_EL2_VECTOR]
+	cbz	x20, 2f				/* need to reduce to EL1? */
+	msr	vbar_el2, x20			/* el2_vector present, means */
+	adr	x1, 2f				/* we will do copy in el1 but */
+	msr	elr_el2, x1			/* do final jump from el2 */
+	eret					/* Reduce to EL1 */
+2:	set_ttbr x0, x1				/* Set our page tables */
+	tlb_invalidate
+	turn_on_mmu sctlr_el1, x1, x2		/* Turn MMU back on */
+	ldr	x1, [x0, #KRELOC_DST_ADDR];
+	ldr	x2, [x0, #KRELOC_SRC_ADDR];
+	mov	x12, x1				/* x12 dst backup */
+3:	copy_page x1, x2, x3, x4, x5, x6, x7, x8, x9, x10
+	sub	x11, x11, #PAGE_SIZE
+	cbnz	x11, 3b				/* page copy loop */
+	raw_dcache_line_size x2, x3		/* x2 = dcache line size */
+	sub	x3, x2, #1			/* x3 = dcache_size - 1 */
+	bic	x12, x12, x3
+4:	dc	cvau, x12			/* Flush D-cache */
+	add	x12, x12, x2
+	cmp	x12, x1				/* Compare to dst + len */
+	b.ne	4b				/* D-cache flush loop */
+	turn_off_mmu sctlr_el1, x1, x2		/* Turn off MMU */
+	tlb_invalidate				/* Invalidate TLB */
+5:	ldr	x4, [x0, #KRELOC_ENTRY_ADDR]	/* x4 = kimage_start */
 	ldr	x3, [x0, #KRELOC_KERN_ARG3]
 	ldr	x2, [x0, #KRELOC_KERN_ARG2]
 	ldr	x1, [x0, #KRELOC_KERN_ARG1]
 	ldr	x0, [x0, #KRELOC_KERN_ARG0]	/* x0 = dtb address */
-	br	x4
+	cbnz	x20, 6f				/* need to escalate to el2? */
+	br	x4				/* Jump to new world */
+6:	hvc	#0				/* enters kexec_el1_sync */
 .ltorg
 .Larm64_relocate_new_kernel_end:
 END(arm64_relocate_new_kernel)
-- 
2.23.0


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

^ permalink raw reply related

* [PATCH v5 15/17] arm64: kexec: add expandable argument to relocation function
From: Pavel Tatashin @ 2019-09-23 20:34 UTC (permalink / raw)
  To: pasha.tatashin, jmorris, sashal, ebiederm, kexec, linux-kernel,
	corbet, catalin.marinas, will, linux-arm-kernel, marc.zyngier,
	james.morse, vladimir.murzin, matthias.bgg, bhsharma, linux-mm,
	mark.rutland
In-Reply-To: <20190923203427.294286-1-pasha.tatashin@soleen.com>

Currently, kexec relocation function (arm64_relocate_new_kernel) accepts
the following arguments:

head:		start of array that contains relocation information.
entry:		entry point for new kernel or purgatory.
dtb_mem:	first and only argument to entry.

The number of arguments cannot be easily expended, because this
function is also called from HVC_SOFT_RESTART, which preserves only
three arguments. And, also arm64_relocate_new_kernel is written in
assembly but called without stack, thus no place to move extra
arguments to free registers.

Soon, we will need to pass more arguments: once we enable MMU we
will need to pass information about page tables.

Another benefit of allowing this function to accept more arguments, is that
kernel can actually accept up to 4 arguments (x0-x3), however currently
only one is used, but if in the future we will need for more (for example,
pass information about when previous kernel exited to have a precise
measurement in time spent in purgatory), we won't be easilty do that
if arm64_relocate_new_kernel can't accept more arguments.

So, add a new struct: kern_reloc_arg, and place it in kexec safe page (i.e
memory that is not overwritten during relocation).
Thus, make arm64_relocate_new_kernel to only take one argument, that
contains all the needed information.

Signed-off-by: Pavel Tatashin <pasha.tatashin@soleen.com>
---
 arch/arm64/include/asm/kexec.h      | 18 ++++++
 arch/arm64/kernel/asm-offsets.c     |  9 +++
 arch/arm64/kernel/cpu-reset.S       |  4 +-
 arch/arm64/kernel/cpu-reset.h       |  8 +--
 arch/arm64/kernel/machine_kexec.c   | 29 +++++++++-
 arch/arm64/kernel/relocate_kernel.S | 88 ++++++++++-------------------
 6 files changed, 87 insertions(+), 69 deletions(-)

diff --git a/arch/arm64/include/asm/kexec.h b/arch/arm64/include/asm/kexec.h
index d15ca1ca1e83..d5b79d4c7fae 100644
--- a/arch/arm64/include/asm/kexec.h
+++ b/arch/arm64/include/asm/kexec.h
@@ -90,12 +90,30 @@ static inline void crash_prepare_suspend(void) {}
 static inline void crash_post_resume(void) {}
 #endif
 
+/*
+ * kern_reloc_arg is passed to kernel relocation function as an argument.
+ * head		kimage->head, allows to traverse through relocation segments.
+ * entry_addr	kimage->start, where to jump from relocation function (new
+ *		kernel, or purgatory entry address).
+ * kern_arg0	first argument to kernel is its dtb address. The other
+ *		arguments are currently unused, and must be set to 0
+ */
+struct kern_reloc_arg {
+	unsigned long	head;
+	unsigned long	entry_addr;
+	unsigned long	kern_arg0;
+	unsigned long	kern_arg1;
+	unsigned long	kern_arg2;
+	unsigned long	kern_arg3;
+};
+
 #define ARCH_HAS_KIMAGE_ARCH
 
 struct kimage_arch {
 	void *dtb;
 	unsigned long dtb_mem;
 	unsigned long kern_reloc;
+	unsigned long kern_reloc_arg;
 };
 
 #ifdef CONFIG_KEXEC_FILE
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 214685760e1c..900394907fd8 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -23,6 +23,7 @@
 #include <asm/suspend.h>
 #include <linux/kbuild.h>
 #include <linux/arm-smccc.h>
+#include <linux/kexec.h>
 
 int main(void)
 {
@@ -126,6 +127,14 @@ int main(void)
 #ifdef CONFIG_ARM_SDE_INTERFACE
   DEFINE(SDEI_EVENT_INTREGS,	offsetof(struct sdei_registered_event, interrupted_regs));
   DEFINE(SDEI_EVENT_PRIORITY,	offsetof(struct sdei_registered_event, priority));
+#endif
+#ifdef CONFIG_KEXEC_CORE
+  DEFINE(KRELOC_HEAD,		offsetof(struct kern_reloc_arg, head));
+  DEFINE(KRELOC_ENTRY_ADDR,	offsetof(struct kern_reloc_arg, entry_addr));
+  DEFINE(KRELOC_KERN_ARG0,	offsetof(struct kern_reloc_arg, kern_arg0));
+  DEFINE(KRELOC_KERN_ARG1,	offsetof(struct kern_reloc_arg, kern_arg1));
+  DEFINE(KRELOC_KERN_ARG2,	offsetof(struct kern_reloc_arg, kern_arg2));
+  DEFINE(KRELOC_KERN_ARG3,	offsetof(struct kern_reloc_arg, kern_arg3));
 #endif
   return 0;
 }
diff --git a/arch/arm64/kernel/cpu-reset.S b/arch/arm64/kernel/cpu-reset.S
index 6ea337d464c4..64c78a42919f 100644
--- a/arch/arm64/kernel/cpu-reset.S
+++ b/arch/arm64/kernel/cpu-reset.S
@@ -43,9 +43,7 @@ ENTRY(__cpu_soft_restart)
 	hvc	#0				// no return
 
 1:	mov	x18, x1				// entry
-	mov	x0, x2				// arg0
-	mov	x1, x3				// arg1
-	mov	x2, x4				// arg2
+	mov	x0, x2				// arg
 	br	x18
 ENDPROC(__cpu_soft_restart)
 
diff --git a/arch/arm64/kernel/cpu-reset.h b/arch/arm64/kernel/cpu-reset.h
index ed50e9587ad8..7a8720ff186f 100644
--- a/arch/arm64/kernel/cpu-reset.h
+++ b/arch/arm64/kernel/cpu-reset.h
@@ -11,12 +11,10 @@
 #include <asm/virt.h>
 
 void __cpu_soft_restart(unsigned long el2_switch, unsigned long entry,
-	unsigned long arg0, unsigned long arg1, unsigned long arg2);
+			unsigned long arg);
 
 static inline void __noreturn cpu_soft_restart(unsigned long entry,
-					       unsigned long arg0,
-					       unsigned long arg1,
-					       unsigned long arg2)
+					       unsigned long arg)
 {
 	typeof(__cpu_soft_restart) *restart;
 
@@ -25,7 +23,7 @@ static inline void __noreturn cpu_soft_restart(unsigned long entry,
 	restart = (void *)__pa_symbol(__cpu_soft_restart);
 
 	cpu_install_idmap();
-	restart(el2_switch, entry, arg0, arg1, arg2);
+	restart(el2_switch, entry, arg);
 	unreachable();
 }
 
diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c
index 9b41da50e6f7..fb6138a1c9ff 100644
--- a/arch/arm64/kernel/machine_kexec.c
+++ b/arch/arm64/kernel/machine_kexec.c
@@ -43,6 +43,7 @@ static void _kexec_image_info(const char *func, int line,
 	pr_debug("    head:        %lx\n", kimage->head);
 	pr_debug("    nr_segments: %lu\n", kimage->nr_segments);
 	pr_debug("    kern_reloc: %pa\n", &kimage->arch.kern_reloc);
+	pr_debug("    kern_reloc_arg: %pa\n", &kimage->arch.kern_reloc_arg);
 
 	for (i = 0; i < kimage->nr_segments; i++) {
 		pr_debug("      segment[%lu]: %016lx - %016lx, 0x%lx bytes, %lu pages\n",
@@ -59,14 +60,39 @@ void machine_kexec_cleanup(struct kimage *kimage)
 	/* Empty routine needed to avoid build errors. */
 }
 
+/* Allocates pages for kexec page table */
+static void *kexec_page_alloc(void *arg)
+{
+	struct kimage *kimage = (struct kimage *)arg;
+	struct page *page = kimage_alloc_control_pages(kimage, 0);
+
+	if (!page)
+		return NULL;
+
+	memset(page_address(page), 0, PAGE_SIZE);
+
+	return page_address(page);
+}
+
 int machine_kexec_post_load(struct kimage *kimage)
 {
 	unsigned long kern_reloc;
+	struct kern_reloc_arg *kern_reloc_arg;
 
 	kern_reloc = page_to_phys(kimage->control_code_page);
 	memcpy(__va(kern_reloc), arm64_relocate_new_kernel,
 	       arm64_relocate_new_kernel_size);
+
+	kern_reloc_arg = kexec_page_alloc(kimage);
+	if (!kern_reloc_arg)
+		return -ENOMEM;
+
 	kimage->arch.kern_reloc = kern_reloc;
+	kimage->arch.kern_reloc_arg = __pa(kern_reloc_arg);
+
+	kern_reloc_arg->head = kimage->head;
+	kern_reloc_arg->entry_addr = kimage->start;
+	kern_reloc_arg->kern_arg0 = kimage->arch.dtb_mem;
 
 	kexec_image_info(kimage);
 	return 0;
@@ -203,8 +229,7 @@ void machine_kexec(struct kimage *kimage)
 	 * userspace (kexec-tools).
 	 * In kexec_file case, the kernel starts directly without purgatory.
 	 */
-	cpu_soft_restart(kimage->arch.kern_reloc, kimage->head, kimage->start,
-			 kimage->arch.dtb_mem);
+	cpu_soft_restart(kimage->arch.kern_reloc, kimage->arch.kern_reloc_arg);
 
 	BUG(); /* Should never get here. */
 }
diff --git a/arch/arm64/kernel/relocate_kernel.S b/arch/arm64/kernel/relocate_kernel.S
index c1d7db71a726..d352faf7cbe6 100644
--- a/arch/arm64/kernel/relocate_kernel.S
+++ b/arch/arm64/kernel/relocate_kernel.S
@@ -8,7 +8,7 @@
 
 #include <linux/kexec.h>
 #include <linux/linkage.h>
-
+#include <asm/asm-offsets.h>
 #include <asm/assembler.h>
 #include <asm/kexec.h>
 #include <asm/page.h>
@@ -17,86 +17,58 @@
 /*
  * arm64_relocate_new_kernel - Put a 2nd stage image in place and boot it.
  *
- * The memory that the old kernel occupies may be overwritten when coping the
+ * The memory that the old kernel occupies may be overwritten when copying the
  * new image to its final location.  To assure that the
  * arm64_relocate_new_kernel routine which does that copy is not overwritten,
  * all code and data needed by arm64_relocate_new_kernel must be between the
  * symbols arm64_relocate_new_kernel and arm64_relocate_new_kernel_end.  The
  * machine_kexec() routine will copy arm64_relocate_new_kernel to the kexec
- * control_code_page, a special page which has been set up to be preserved
- * during the copy operation.
+ * safe memory that has been set up to be preserved during the copy operation.
  */
 ENTRY(arm64_relocate_new_kernel)
-
-	/* Setup the list loop variables. */
-	mov	x18, x2				/* x18 = dtb address */
-	mov	x17, x1				/* x17 = kimage_start */
-	mov	x16, x0				/* x16 = kimage_head */
-	raw_dcache_line_size x15, x0		/* x15 = dcache line size */
-	mov	x14, xzr			/* x14 = entry ptr */
-	mov	x13, xzr			/* x13 = copy dest */
-
 	/* Clear the sctlr_el2 flags. */
-	mrs	x0, CurrentEL
-	cmp	x0, #CurrentEL_EL2
+	mrs	x2, CurrentEL
+	cmp	x2, #CurrentEL_EL2
 	b.ne	1f
-	mrs	x0, sctlr_el2
+	mrs	x2, sctlr_el2
 	ldr	x1, =SCTLR_ELx_FLAGS
-	bic	x0, x0, x1
+	bic	x2, x2, x1
 	pre_disable_mmu_workaround
-	msr	sctlr_el2, x0
+	msr	sctlr_el2, x2
 	isb
-1:
-
-	/* Check if the new image needs relocation. */
+1:	/* Check if the new image needs relocation. */
+	ldr	x16, [x0, #KRELOC_HEAD]		/* x16 = kimage_head */
 	tbnz	x16, IND_DONE_BIT, .Ldone
-
+	raw_dcache_line_size x15, x1		/* x15 = dcache line size */
 .Lloop:
 	and	x12, x16, PAGE_MASK		/* x12 = addr */
-
 	/* Test the entry flags. */
 .Ltest_source:
 	tbz	x16, IND_SOURCE_BIT, .Ltest_indirection
 
 	/* Invalidate dest page to PoC. */
-	mov     x0, x13
-	add     x20, x0, #PAGE_SIZE
+	mov     x2, x13
+	add     x20, x2, #PAGE_SIZE
 	sub     x1, x15, #1
-	bic     x0, x0, x1
-2:	dc      ivac, x0
-	add     x0, x0, x15
-	cmp     x0, x20
+	bic     x2, x2, x1
+2:	dc      ivac, x2
+	add     x2, x2, x15
+	cmp     x2, x20
 	b.lo    2b
 	dsb     sy
 
-	mov x20, x13
-	mov x21, x12
-	copy_page x20, x21, x0, x1, x2, x3, x4, x5, x6, x7
-
-	/* dest += PAGE_SIZE */
-	add	x13, x13, PAGE_SIZE
+	copy_page x13, x12, x1, x2, x3, x4, x5, x6, x7, x8
 	b	.Lnext
-
 .Ltest_indirection:
 	tbz	x16, IND_INDIRECTION_BIT, .Ltest_destination
-
-	/* ptr = addr */
-	mov	x14, x12
+	mov	x14, x12			/* ptr = addr */
 	b	.Lnext
-
 .Ltest_destination:
 	tbz	x16, IND_DESTINATION_BIT, .Lnext
-
-	/* dest = addr */
-	mov	x13, x12
-
+	mov	x13, x12			/* dest = addr */
 .Lnext:
-	/* entry = *ptr++ */
-	ldr	x16, [x14], #8
-
-	/* while (!(entry & DONE)) */
-	tbz	x16, IND_DONE_BIT, .Lloop
-
+	ldr	x16, [x14], #8			/* entry = *ptr++ */
+	tbz	x16, IND_DONE_BIT, .Lloop	/* while (!(entry & DONE)) */
 .Ldone:
 	/* wait for writes from copy_page to finish */
 	dsb	nsh
@@ -105,18 +77,16 @@ ENTRY(arm64_relocate_new_kernel)
 	isb
 
 	/* Start new image. */
-	mov	x0, x18
-	mov	x1, xzr
-	mov	x2, xzr
-	mov	x3, xzr
-	br	x17
-
-ENDPROC(arm64_relocate_new_kernel)
+	ldr	x4, [x0, #KRELOC_ENTRY_ADDR]	/* x4 = kimage_start */
+	ldr	x3, [x0, #KRELOC_KERN_ARG3]
+	ldr	x2, [x0, #KRELOC_KERN_ARG2]
+	ldr	x1, [x0, #KRELOC_KERN_ARG1]
+	ldr	x0, [x0, #KRELOC_KERN_ARG0]	/* x0 = dtb address */
+	br	x4
+END(arm64_relocate_new_kernel)
 
 .ltorg
-
 .align 3	/* To keep the 64-bit values below naturally aligned. */
-
 .Lcopy_end:
 .org	KEXEC_CONTROL_PAGE_SIZE
 
-- 
2.23.0


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

^ permalink raw reply related

* [PATCH v5 14/17] arm64: kexec: move relocation function setup and clean up
From: Pavel Tatashin @ 2019-09-23 20:34 UTC (permalink / raw)
  To: pasha.tatashin, jmorris, sashal, ebiederm, kexec, linux-kernel,
	corbet, catalin.marinas, will, linux-arm-kernel, marc.zyngier,
	james.morse, vladimir.murzin, matthias.bgg, bhsharma, linux-mm,
	mark.rutland
In-Reply-To: <20190923203427.294286-1-pasha.tatashin@soleen.com>

Currently, kernel relocation function is configured in machine_kexec()
at the time of kexec reboot by using control_code_page.

This operation, however, is more logical to be done during kexec_load,
and thus remove from reboot time. Move, setup of this function to
newly added machine_kexec_post_load().

In addition, do some cleanup: add infor about reloction function to
kexec_image_info(), and remove extra messages from machine_kexec().

Make dtb_mem, always available, if CONFIG_KEXEC_FILE is not configured
dtb_mem is set to zero anyway.

Signed-off-by: Pavel Tatashin <pasha.tatashin@soleen.com>
---
 arch/arm64/include/asm/kexec.h    |  3 +-
 arch/arm64/kernel/machine_kexec.c | 49 +++++++++++--------------------
 2 files changed, 19 insertions(+), 33 deletions(-)

diff --git a/arch/arm64/include/asm/kexec.h b/arch/arm64/include/asm/kexec.h
index 12a561a54128..d15ca1ca1e83 100644
--- a/arch/arm64/include/asm/kexec.h
+++ b/arch/arm64/include/asm/kexec.h
@@ -90,14 +90,15 @@ static inline void crash_prepare_suspend(void) {}
 static inline void crash_post_resume(void) {}
 #endif
 
-#ifdef CONFIG_KEXEC_FILE
 #define ARCH_HAS_KIMAGE_ARCH
 
 struct kimage_arch {
 	void *dtb;
 	unsigned long dtb_mem;
+	unsigned long kern_reloc;
 };
 
+#ifdef CONFIG_KEXEC_FILE
 extern const struct kexec_file_ops kexec_image_ops;
 
 struct kimage;
diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c
index 0df8493624e0..9b41da50e6f7 100644
--- a/arch/arm64/kernel/machine_kexec.c
+++ b/arch/arm64/kernel/machine_kexec.c
@@ -42,6 +42,7 @@ static void _kexec_image_info(const char *func, int line,
 	pr_debug("    start:       %lx\n", kimage->start);
 	pr_debug("    head:        %lx\n", kimage->head);
 	pr_debug("    nr_segments: %lu\n", kimage->nr_segments);
+	pr_debug("    kern_reloc: %pa\n", &kimage->arch.kern_reloc);
 
 	for (i = 0; i < kimage->nr_segments; i++) {
 		pr_debug("      segment[%lu]: %016lx - %016lx, 0x%lx bytes, %lu pages\n",
@@ -58,6 +59,19 @@ void machine_kexec_cleanup(struct kimage *kimage)
 	/* Empty routine needed to avoid build errors. */
 }
 
+int machine_kexec_post_load(struct kimage *kimage)
+{
+	unsigned long kern_reloc;
+
+	kern_reloc = page_to_phys(kimage->control_code_page);
+	memcpy(__va(kern_reloc), arm64_relocate_new_kernel,
+	       arm64_relocate_new_kernel_size);
+	kimage->arch.kern_reloc = kern_reloc;
+
+	kexec_image_info(kimage);
+	return 0;
+}
+
 /**
  * machine_kexec_prepare - Prepare for a kexec reboot.
  *
@@ -67,8 +81,6 @@ void machine_kexec_cleanup(struct kimage *kimage)
  */
 int machine_kexec_prepare(struct kimage *kimage)
 {
-	kexec_image_info(kimage);
-
 	if (kimage->type != KEXEC_TYPE_CRASH && cpus_are_stuck_in_kernel()) {
 		pr_err("Can't kexec: CPUs are stuck in the kernel.\n");
 		return -EBUSY;
@@ -143,8 +155,7 @@ static void kexec_segment_flush(const struct kimage *kimage)
  */
 void machine_kexec(struct kimage *kimage)
 {
-	phys_addr_t reboot_code_buffer_phys;
-	void *reboot_code_buffer;
+	void *reboot_code_buffer = phys_to_virt(kimage->arch.kern_reloc);
 	bool in_kexec_crash = (kimage == kexec_crash_image);
 	bool stuck_cpus = cpus_are_stuck_in_kernel();
 
@@ -155,30 +166,8 @@ void machine_kexec(struct kimage *kimage)
 	WARN(in_kexec_crash && (stuck_cpus || smp_crash_stop_failed()),
 		"Some CPUs may be stale, kdump will be unreliable.\n");
 
-	reboot_code_buffer_phys = page_to_phys(kimage->control_code_page);
-	reboot_code_buffer = phys_to_virt(reboot_code_buffer_phys);
-
 	kexec_image_info(kimage);
 
-	pr_debug("%s:%d: control_code_page:        %p\n", __func__, __LINE__,
-		kimage->control_code_page);
-	pr_debug("%s:%d: reboot_code_buffer_phys:  %pa\n", __func__, __LINE__,
-		&reboot_code_buffer_phys);
-	pr_debug("%s:%d: reboot_code_buffer:       %p\n", __func__, __LINE__,
-		reboot_code_buffer);
-	pr_debug("%s:%d: relocate_new_kernel:      %p\n", __func__, __LINE__,
-		arm64_relocate_new_kernel);
-	pr_debug("%s:%d: relocate_new_kernel_size: 0x%lx(%lu) bytes\n",
-		__func__, __LINE__, arm64_relocate_new_kernel_size,
-		arm64_relocate_new_kernel_size);
-
-	/*
-	 * Copy arm64_relocate_new_kernel to the reboot_code_buffer for use
-	 * after the kernel is shut down.
-	 */
-	memcpy(reboot_code_buffer, arm64_relocate_new_kernel,
-		arm64_relocate_new_kernel_size);
-
 	/* Flush the reboot_code_buffer in preparation for its execution. */
 	__flush_dcache_area(reboot_code_buffer, arm64_relocate_new_kernel_size);
 
@@ -214,12 +203,8 @@ void machine_kexec(struct kimage *kimage)
 	 * userspace (kexec-tools).
 	 * In kexec_file case, the kernel starts directly without purgatory.
 	 */
-	cpu_soft_restart(reboot_code_buffer_phys, kimage->head, kimage->start,
-#ifdef CONFIG_KEXEC_FILE
-						kimage->arch.dtb_mem);
-#else
-						0);
-#endif
+	cpu_soft_restart(kimage->arch.kern_reloc, kimage->head, kimage->start,
+			 kimage->arch.dtb_mem);
 
 	BUG(); /* Should never get here. */
 }
-- 
2.23.0


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

^ permalink raw reply related

* [PATCH v5 13/17] kexec: add machine_kexec_post_load()
From: Pavel Tatashin @ 2019-09-23 20:34 UTC (permalink / raw)
  To: pasha.tatashin, jmorris, sashal, ebiederm, kexec, linux-kernel,
	corbet, catalin.marinas, will, linux-arm-kernel, marc.zyngier,
	james.morse, vladimir.murzin, matthias.bgg, bhsharma, linux-mm,
	mark.rutland
In-Reply-To: <20190923203427.294286-1-pasha.tatashin@soleen.com>

It is the same as machine_kexec_prepare(), but is called after segments are
loaded. This way, can do processing work with already loaded relocation
segments. One such example is arm64: it has to have segments loaded in
order to create a page table, but it cannot do it during kexec time,
because at that time allocations won't be possible anymore.

Signed-off-by: Pavel Tatashin <pasha.tatashin@soleen.com>
---
 kernel/kexec.c          | 4 ++++
 kernel/kexec_core.c     | 6 ++++++
 kernel/kexec_file.c     | 4 ++++
 kernel/kexec_internal.h | 2 ++
 4 files changed, 16 insertions(+)

diff --git a/kernel/kexec.c b/kernel/kexec.c
index 1b018f1a6e0d..27b71dc7b35a 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -159,6 +159,10 @@ static int do_kexec_load(unsigned long entry, unsigned long nr_segments,
 
 	kimage_terminate(image);
 
+	ret = machine_kexec_post_load(image);
+	if (ret)
+		goto out;
+
 	/* Install the new kernel and uninstall the old */
 	image = xchg(dest_image, image);
 
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index 2c5b72863b7b..8360645d1bbe 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -587,6 +587,12 @@ static void kimage_free_extra_pages(struct kimage *image)
 	kimage_free_page_list(&image->unusable_pages);
 
 }
+
+int __weak machine_kexec_post_load(struct kimage *image)
+{
+	return 0;
+}
+
 void kimage_terminate(struct kimage *image)
 {
 	if (*image->entry != 0)
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index b8cc032d5620..cb531d768114 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -391,6 +391,10 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd,
 
 	kimage_terminate(image);
 
+	ret = machine_kexec_post_load(image);
+	if (ret)
+		goto out;
+
 	/*
 	 * Free up any temporary buffers allocated which are not needed
 	 * after image has been loaded
diff --git a/kernel/kexec_internal.h b/kernel/kexec_internal.h
index 48aaf2ac0d0d..39d30ccf8d87 100644
--- a/kernel/kexec_internal.h
+++ b/kernel/kexec_internal.h
@@ -13,6 +13,8 @@ void kimage_terminate(struct kimage *image);
 int kimage_is_destination_range(struct kimage *image,
 				unsigned long start, unsigned long end);
 
+int machine_kexec_post_load(struct kimage *image);
+
 extern struct mutex kexec_mutex;
 
 #ifdef CONFIG_KEXEC_FILE
-- 
2.23.0


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

^ permalink raw reply related

* [PATCH v5 12/17] arm64: trans_pgd: pass NULL instead of init_mm to *_populate functions
From: Pavel Tatashin @ 2019-09-23 20:34 UTC (permalink / raw)
  To: pasha.tatashin, jmorris, sashal, ebiederm, kexec, linux-kernel,
	corbet, catalin.marinas, will, linux-arm-kernel, marc.zyngier,
	james.morse, vladimir.murzin, matthias.bgg, bhsharma, linux-mm,
	mark.rutland
In-Reply-To: <20190923203427.294286-1-pasha.tatashin@soleen.com>

trans_pgd_* should be independent from mm context because the tables that
are created by this code are used when there are no mm context around, as
it is between kernels. Simply replace mm_init's with NULL.

Signed-off-by: Pavel Tatashin <pasha.tatashin@soleen.com>
---
 arch/arm64/mm/trans_pgd.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/arch/arm64/mm/trans_pgd.c b/arch/arm64/mm/trans_pgd.c
index df3a10d36f62..2b02a646101f 100644
--- a/arch/arm64/mm/trans_pgd.c
+++ b/arch/arm64/mm/trans_pgd.c
@@ -67,7 +67,7 @@ static int copy_pte(struct trans_pgd_info *info, pmd_t *dst_pmdp,
 	dst_ptep = trans_alloc(info);
 	if (!dst_ptep)
 		return -ENOMEM;
-	pmd_populate_kernel(&init_mm, dst_pmdp, dst_ptep);
+	pmd_populate_kernel(NULL, dst_pmdp, dst_ptep);
 	dst_ptep = pte_offset_kernel(dst_pmdp, start);
 
 	src_ptep = pte_offset_kernel(src_pmdp, start);
@@ -90,7 +90,7 @@ static int copy_pmd(struct trans_pgd_info *info, pud_t *dst_pudp,
 		dst_pmdp = trans_alloc(info);
 		if (!dst_pmdp)
 			return -ENOMEM;
-		pud_populate(&init_mm, dst_pudp, dst_pmdp);
+		pud_populate(NULL, dst_pudp, dst_pmdp);
 	}
 	dst_pmdp = pmd_offset(dst_pudp, start);
 
@@ -126,7 +126,7 @@ static int copy_pud(struct trans_pgd_info *info, pgd_t *dst_pgdp,
 		dst_pudp = trans_alloc(info);
 		if (!dst_pudp)
 			return -ENOMEM;
-		pgd_populate(&init_mm, dst_pgdp, dst_pudp);
+		pgd_populate(NULL, dst_pgdp, dst_pudp);
 	}
 	dst_pudp = pud_offset(dst_pgdp, start);
 
@@ -218,7 +218,7 @@ int trans_pgd_map_page(struct trans_pgd_info *info, pgd_t *trans_pgd,
 		pudp = trans_alloc(info);
 		if (!pudp)
 			return -ENOMEM;
-		pgd_populate(&init_mm, pgdp, pudp);
+		pgd_populate(NULL, pgdp, pudp);
 	}
 
 	pudp = pud_offset(pgdp, dst_addr);
@@ -226,7 +226,7 @@ int trans_pgd_map_page(struct trans_pgd_info *info, pgd_t *trans_pgd,
 		pmdp = trans_alloc(info);
 		if (!pmdp)
 			return -ENOMEM;
-		pud_populate(&init_mm, pudp, pmdp);
+		pud_populate(NULL, pudp, pmdp);
 	}
 
 	pmdp = pmd_offset(pudp, dst_addr);
@@ -234,7 +234,7 @@ int trans_pgd_map_page(struct trans_pgd_info *info, pgd_t *trans_pgd,
 		ptep = trans_alloc(info);
 		if (!ptep)
 			return -ENOMEM;
-		pmd_populate_kernel(&init_mm, pmdp, ptep);
+		pmd_populate_kernel(NULL, pmdp, ptep);
 	}
 
 	ptep = pte_offset_kernel(pmdp, dst_addr);
-- 
2.23.0


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

^ permalink raw reply related

* [PATCH v5 11/17] arm64: trans_pgd: pass allocator trans_pgd_create_copy
From: Pavel Tatashin @ 2019-09-23 20:34 UTC (permalink / raw)
  To: pasha.tatashin, jmorris, sashal, ebiederm, kexec, linux-kernel,
	corbet, catalin.marinas, will, linux-arm-kernel, marc.zyngier,
	james.morse, vladimir.murzin, matthias.bgg, bhsharma, linux-mm,
	mark.rutland
In-Reply-To: <20190923203427.294286-1-pasha.tatashin@soleen.com>

Make trans_pgd_create_copy and its subroutines to use allocator that is
passed as an argument

Signed-off-by: Pavel Tatashin <pasha.tatashin@soleen.com>
---
 arch/arm64/include/asm/trans_pgd.h |  4 +--
 arch/arm64/kernel/hibernate.c      |  7 ++++-
 arch/arm64/mm/trans_pgd.c          | 44 ++++++++++++++++++------------
 3 files changed, 35 insertions(+), 20 deletions(-)

diff --git a/arch/arm64/include/asm/trans_pgd.h b/arch/arm64/include/asm/trans_pgd.h
index bb38f73aa7aa..56613e83aa53 100644
--- a/arch/arm64/include/asm/trans_pgd.h
+++ b/arch/arm64/include/asm/trans_pgd.h
@@ -25,8 +25,8 @@ struct trans_pgd_info {
 	void *trans_alloc_arg;
 };
 
-int trans_pgd_create_copy(pgd_t **dst_pgdp, unsigned long start,
-			  unsigned long end);
+int trans_pgd_create_copy(struct trans_pgd_info *info, pgd_t **trans_pgd,
+			  unsigned long start, unsigned long end);
 
 int trans_pgd_map_page(struct trans_pgd_info *info, pgd_t *trans_pgd,
 		       void *page, unsigned long dst_addr, pgprot_t pgprot);
diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index 7f0a5e152c45..038d8214df8d 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -322,6 +322,10 @@ int swsusp_arch_resume(void)
 	phys_addr_t phys_hibernate_exit;
 	void __noreturn (*hibernate_exit)(phys_addr_t, phys_addr_t, void *,
 					  void *, phys_addr_t, phys_addr_t);
+	struct trans_pgd_info trans_info = {
+		.trans_alloc_page	= hibernate_page_alloc,
+		.trans_alloc_arg	= (void *)GFP_ATOMIC,
+	};
 
 	/*
 	 * Restoring the memory image will overwrite the ttbr1 page tables.
@@ -333,7 +337,8 @@ int swsusp_arch_resume(void)
 		pr_err("Failed to allocate memory for temporary page tables.\n");
 		return -ENOMEM;
 	}
-	rc = trans_pgd_create_copy(&tmp_pg_dir, PAGE_OFFSET, PAGE_END);
+	rc = trans_pgd_create_copy(&trans_info, &tmp_pg_dir, PAGE_OFFSET,
+				   PAGE_END);
 	if (rc)
 		return rc;
 
diff --git a/arch/arm64/mm/trans_pgd.c b/arch/arm64/mm/trans_pgd.c
index 1142dde8c02f..df3a10d36f62 100644
--- a/arch/arm64/mm/trans_pgd.c
+++ b/arch/arm64/mm/trans_pgd.c
@@ -57,14 +57,14 @@ static void _copy_pte(pte_t *dst_ptep, pte_t *src_ptep, unsigned long addr)
 	}
 }
 
-static int copy_pte(pmd_t *dst_pmdp, pmd_t *src_pmdp, unsigned long start,
-		    unsigned long end)
+static int copy_pte(struct trans_pgd_info *info, pmd_t *dst_pmdp,
+		    pmd_t *src_pmdp, unsigned long start, unsigned long end)
 {
 	pte_t *src_ptep;
 	pte_t *dst_ptep;
 	unsigned long addr = start;
 
-	dst_ptep = (pte_t *)get_safe_page(GFP_ATOMIC);
+	dst_ptep = trans_alloc(info);
 	if (!dst_ptep)
 		return -ENOMEM;
 	pmd_populate_kernel(&init_mm, dst_pmdp, dst_ptep);
@@ -78,8 +78,8 @@ static int copy_pte(pmd_t *dst_pmdp, pmd_t *src_pmdp, unsigned long start,
 	return 0;
 }
 
-static int copy_pmd(pud_t *dst_pudp, pud_t *src_pudp, unsigned long start,
-		    unsigned long end)
+static int copy_pmd(struct trans_pgd_info *info, pud_t *dst_pudp,
+		    pud_t *src_pudp, unsigned long start, unsigned long end)
 {
 	pmd_t *src_pmdp;
 	pmd_t *dst_pmdp;
@@ -87,7 +87,7 @@ static int copy_pmd(pud_t *dst_pudp, pud_t *src_pudp, unsigned long start,
 	unsigned long addr = start;
 
 	if (pud_none(READ_ONCE(*dst_pudp))) {
-		dst_pmdp = (pmd_t *)get_safe_page(GFP_ATOMIC);
+		dst_pmdp = trans_alloc(info);
 		if (!dst_pmdp)
 			return -ENOMEM;
 		pud_populate(&init_mm, dst_pudp, dst_pmdp);
@@ -102,7 +102,7 @@ static int copy_pmd(pud_t *dst_pudp, pud_t *src_pudp, unsigned long start,
 		if (pmd_none(pmd))
 			continue;
 		if (pmd_table(pmd)) {
-			if (copy_pte(dst_pmdp, src_pmdp, addr, next))
+			if (copy_pte(info, dst_pmdp, src_pmdp, addr, next))
 				return -ENOMEM;
 		} else {
 			set_pmd(dst_pmdp,
@@ -113,7 +113,8 @@ static int copy_pmd(pud_t *dst_pudp, pud_t *src_pudp, unsigned long start,
 	return 0;
 }
 
-static int copy_pud(pgd_t *dst_pgdp, pgd_t *src_pgdp, unsigned long start,
+static int copy_pud(struct trans_pgd_info *info, pgd_t *dst_pgdp,
+		    pgd_t *src_pgdp, unsigned long start,
 		    unsigned long end)
 {
 	pud_t *dst_pudp;
@@ -122,7 +123,7 @@ static int copy_pud(pgd_t *dst_pgdp, pgd_t *src_pgdp, unsigned long start,
 	unsigned long addr = start;
 
 	if (pgd_none(READ_ONCE(*dst_pgdp))) {
-		dst_pudp = (pud_t *)get_safe_page(GFP_ATOMIC);
+		dst_pudp = trans_alloc(info);
 		if (!dst_pudp)
 			return -ENOMEM;
 		pgd_populate(&init_mm, dst_pgdp, dst_pudp);
@@ -137,7 +138,7 @@ static int copy_pud(pgd_t *dst_pgdp, pgd_t *src_pgdp, unsigned long start,
 		if (pud_none(pud))
 			continue;
 		if (pud_table(pud)) {
-			if (copy_pmd(dst_pudp, src_pudp, addr, next))
+			if (copy_pmd(info, dst_pudp, src_pudp, addr, next))
 				return -ENOMEM;
 		} else {
 			set_pud(dst_pudp,
@@ -148,8 +149,8 @@ static int copy_pud(pgd_t *dst_pgdp, pgd_t *src_pgdp, unsigned long start,
 	return 0;
 }
 
-static int copy_page_tables(pgd_t *dst_pgdp, unsigned long start,
-			    unsigned long end)
+static int copy_page_tables(struct trans_pgd_info *info, pgd_t *dst_pgdp,
+			    unsigned long start, unsigned long end)
 {
 	unsigned long next;
 	unsigned long addr = start;
@@ -160,25 +161,34 @@ static int copy_page_tables(pgd_t *dst_pgdp, unsigned long start,
 		next = pgd_addr_end(addr, end);
 		if (pgd_none(READ_ONCE(*src_pgdp)))
 			continue;
-		if (copy_pud(dst_pgdp, src_pgdp, addr, next))
+		if (copy_pud(info, dst_pgdp, src_pgdp, addr, next))
 			return -ENOMEM;
 	} while (dst_pgdp++, src_pgdp++, addr = next, addr != end);
 
 	return 0;
 }
 
-int trans_pgd_create_copy(pgd_t **dst_pgdp, unsigned long start,
-			  unsigned long end)
+/*
+ * Create trans_pgd and copy linear map.
+ * info:	contains allocator and its argument
+ * dst_pgdp:	new page table that is created, and to which map is copied.
+ * start:	Start of the interval (inclusive).
+ * end:		End of the interval (exclusive).
+ *
+ * Returns 0 on success, and -ENOMEM on failure.
+ */
+int trans_pgd_create_copy(struct trans_pgd_info *info, pgd_t **dst_pgdp,
+			  unsigned long start, unsigned long end)
 {
 	int rc;
-	pgd_t *trans_pgd = (pgd_t *)get_safe_page(GFP_ATOMIC);
+	pgd_t *trans_pgd = trans_alloc(info);
 
 	if (!trans_pgd) {
 		pr_err("Failed to allocate memory for temporary page tables.\n");
 		return -ENOMEM;
 	}
 
-	rc = copy_page_tables(trans_pgd, start, end);
+	rc = copy_page_tables(info, trans_pgd, start, end);
 	if (!rc)
 		*dst_pgdp = trans_pgd;
 
-- 
2.23.0


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

^ permalink raw reply related

* [PATCH v5 10/17] arm64: trans_pgd: make trans_pgd_map_page generic
From: Pavel Tatashin @ 2019-09-23 20:34 UTC (permalink / raw)
  To: pasha.tatashin, jmorris, sashal, ebiederm, kexec, linux-kernel,
	corbet, catalin.marinas, will, linux-arm-kernel, marc.zyngier,
	james.morse, vladimir.murzin, matthias.bgg, bhsharma, linux-mm,
	mark.rutland
In-Reply-To: <20190923203427.294286-1-pasha.tatashin@soleen.com>

kexec is going to use a different allocator, so make
trans_pgd_map_page to accept allocator as an argument, and also
kexec is going to use a different map protection, so also pass
it via argument.

Signed-off-by: Pavel Tatashin <pasha.tatashin@soleen.com>
Reviewed-by: Matthias Brugger <mbrugger@suse.com>
---
 arch/arm64/include/asm/trans_pgd.h | 18 ++++++++++++++++--
 arch/arm64/kernel/hibernate.c      | 12 +++++++++++-
 arch/arm64/mm/trans_pgd.c          | 27 +++++++++++++++++++++------
 3 files changed, 48 insertions(+), 9 deletions(-)

diff --git a/arch/arm64/include/asm/trans_pgd.h b/arch/arm64/include/asm/trans_pgd.h
index c7b5402b7d87..bb38f73aa7aa 100644
--- a/arch/arm64/include/asm/trans_pgd.h
+++ b/arch/arm64/include/asm/trans_pgd.h
@@ -11,10 +11,24 @@
 #include <linux/bits.h>
 #include <asm/pgtable-types.h>
 
+/*
+ * trans_alloc_page
+ *	- Allocator that should return exactly one zeroed page, if this
+ *	 allocator fails, trans_pgd returns -ENOMEM error.
+ *
+ * trans_alloc_arg
+ *	- Passed to trans_alloc_page as an argument
+ */
+
+struct trans_pgd_info {
+	void * (*trans_alloc_page)(void *arg);
+	void *trans_alloc_arg;
+};
+
 int trans_pgd_create_copy(pgd_t **dst_pgdp, unsigned long start,
 			  unsigned long end);
 
-int trans_pgd_map_page(pgd_t *trans_pgd, void *page, unsigned long dst_addr,
-		       pgprot_t pgprot);
+int trans_pgd_map_page(struct trans_pgd_info *info, pgd_t *trans_pgd,
+		       void *page, unsigned long dst_addr, pgprot_t pgprot);
 
 #endif /* _ASM_TRANS_TABLE_H */
diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index d6346ad23f87..7f0a5e152c45 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -179,6 +179,11 @@ int arch_hibernation_header_restore(void *addr)
 }
 EXPORT_SYMBOL(arch_hibernation_header_restore);
 
+static void *hibernate_page_alloc(void *arg)
+{
+	return (void *)get_safe_page((gfp_t)(unsigned long)arg);
+}
+
 /*
  * Copies length bytes, starting at src_start into an new page,
  * perform cache maintenance, then maps it at the specified address low
@@ -195,6 +200,11 @@ static int create_safe_exec_page(void *src_start, size_t length,
 				 unsigned long dst_addr,
 				 phys_addr_t *phys_dst_addr)
 {
+	struct trans_pgd_info trans_info = {
+		.trans_alloc_page	= hibernate_page_alloc,
+		.trans_alloc_arg	= (void *)GFP_ATOMIC,
+	};
+
 	void *page = (void *)get_safe_page(GFP_ATOMIC);
 	pgd_t *trans_pgd;
 	int rc;
@@ -209,7 +219,7 @@ static int create_safe_exec_page(void *src_start, size_t length,
 	if (!trans_pgd)
 		return -ENOMEM;
 
-	rc = trans_pgd_map_page(trans_pgd, page, dst_addr,
+	rc = trans_pgd_map_page(&trans_info, trans_pgd, page, dst_addr,
 				PAGE_KERNEL_EXEC);
 	if (rc)
 		return rc;
diff --git a/arch/arm64/mm/trans_pgd.c b/arch/arm64/mm/trans_pgd.c
index 5ac712b92439..1142dde8c02f 100644
--- a/arch/arm64/mm/trans_pgd.c
+++ b/arch/arm64/mm/trans_pgd.c
@@ -25,6 +25,11 @@
 #include <linux/mm.h>
 #include <linux/mmzone.h>
 
+static void *trans_alloc(struct trans_pgd_info *info)
+{
+	return info->trans_alloc_page(info->trans_alloc_arg);
+}
+
 static void _copy_pte(pte_t *dst_ptep, pte_t *src_ptep, unsigned long addr)
 {
 	pte_t pte = READ_ONCE(*src_ptep);
@@ -180,8 +185,18 @@ int trans_pgd_create_copy(pgd_t **dst_pgdp, unsigned long start,
 	return rc;
 }
 
-int trans_pgd_map_page(pgd_t *trans_pgd, void *page, unsigned long dst_addr,
-		       pgprot_t pgprot)
+/*
+ * Add map entry to trans_pgd for a base-size page at PTE level.
+ * info:	contains allocator and its argument
+ * trans_pgd:	page table in which new map is added.
+ * page:	page to be mapped.
+ * dst_addr:	new VA address for the pages
+ * pgprot:	protection for the page.
+ *
+ * Returns 0 on success, and -ENOMEM on failure.
+ */
+int trans_pgd_map_page(struct trans_pgd_info *info, pgd_t *trans_pgd,
+		       void *page, unsigned long dst_addr, pgprot_t pgprot)
 {
 	pgd_t *pgdp;
 	pud_t *pudp;
@@ -190,7 +205,7 @@ int trans_pgd_map_page(pgd_t *trans_pgd, void *page, unsigned long dst_addr,
 
 	pgdp = pgd_offset_raw(trans_pgd, dst_addr);
 	if (pgd_none(READ_ONCE(*pgdp))) {
-		pudp = (void *)get_safe_page(GFP_ATOMIC);
+		pudp = trans_alloc(info);
 		if (!pudp)
 			return -ENOMEM;
 		pgd_populate(&init_mm, pgdp, pudp);
@@ -198,7 +213,7 @@ int trans_pgd_map_page(pgd_t *trans_pgd, void *page, unsigned long dst_addr,
 
 	pudp = pud_offset(pgdp, dst_addr);
 	if (pud_none(READ_ONCE(*pudp))) {
-		pmdp = (void *)get_safe_page(GFP_ATOMIC);
+		pmdp = trans_alloc(info);
 		if (!pmdp)
 			return -ENOMEM;
 		pud_populate(&init_mm, pudp, pmdp);
@@ -206,14 +221,14 @@ int trans_pgd_map_page(pgd_t *trans_pgd, void *page, unsigned long dst_addr,
 
 	pmdp = pmd_offset(pudp, dst_addr);
 	if (pmd_none(READ_ONCE(*pmdp))) {
-		ptep = (void *)get_safe_page(GFP_ATOMIC);
+		ptep = trans_alloc(info);
 		if (!ptep)
 			return -ENOMEM;
 		pmd_populate_kernel(&init_mm, pmdp, ptep);
 	}
 
 	ptep = pte_offset_kernel(pmdp, dst_addr);
-	set_pte(ptep, pfn_pte(virt_to_pfn(page), PAGE_KERNEL_EXEC));
+	set_pte(ptep, pfn_pte(virt_to_pfn(page), pgprot));
 
 	return 0;
 }
-- 
2.23.0


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

^ permalink raw reply related

* [PATCH v5 09/17] arm64: hibernate: move page handling function to new trans_pgd.c
From: Pavel Tatashin @ 2019-09-23 20:34 UTC (permalink / raw)
  To: pasha.tatashin, jmorris, sashal, ebiederm, kexec, linux-kernel,
	corbet, catalin.marinas, will, linux-arm-kernel, marc.zyngier,
	james.morse, vladimir.murzin, matthias.bgg, bhsharma, linux-mm,
	mark.rutland
In-Reply-To: <20190923203427.294286-1-pasha.tatashin@soleen.com>

Now, that we abstracted the required functions move them to a new home.
Later, we will generalize these function in order to be useful outside
of hibernation.

Signed-off-by: Pavel Tatashin <pasha.tatashin@soleen.com>
---
 arch/arm64/Kconfig                 |   4 +
 arch/arm64/include/asm/trans_pgd.h |  20 +++
 arch/arm64/kernel/hibernate.c      | 199 +-------------------------
 arch/arm64/mm/Makefile             |   1 +
 arch/arm64/mm/trans_pgd.c          | 219 +++++++++++++++++++++++++++++
 5 files changed, 245 insertions(+), 198 deletions(-)
 create mode 100644 arch/arm64/include/asm/trans_pgd.h
 create mode 100644 arch/arm64/mm/trans_pgd.c

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 37c610963eee..789b90b80e48 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1017,6 +1017,10 @@ config CRASH_DUMP
 
 	  For more details see Documentation/admin-guide/kdump/kdump.rst
 
+config TRANS_TABLE
+	def_bool y
+	depends on HIBERNATION || KEXEC_CORE
+
 config XEN_DOM0
 	def_bool y
 	depends on XEN
diff --git a/arch/arm64/include/asm/trans_pgd.h b/arch/arm64/include/asm/trans_pgd.h
new file mode 100644
index 000000000000..c7b5402b7d87
--- /dev/null
+++ b/arch/arm64/include/asm/trans_pgd.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Copyright (c) 2019, Microsoft Corporation.
+ * Pavel Tatashin <patatash@linux.microsoft.com>
+ */
+
+#ifndef _ASM_TRANS_TABLE_H
+#define _ASM_TRANS_TABLE_H
+
+#include <linux/bits.h>
+#include <asm/pgtable-types.h>
+
+int trans_pgd_create_copy(pgd_t **dst_pgdp, unsigned long start,
+			  unsigned long end);
+
+int trans_pgd_map_page(pgd_t *trans_pgd, void *page, unsigned long dst_addr,
+		       pgprot_t pgprot);
+
+#endif /* _ASM_TRANS_TABLE_H */
diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index ded9034b9d39..d6346ad23f87 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -16,7 +16,6 @@
 #define pr_fmt(x) "hibernate: " x
 #include <linux/cpu.h>
 #include <linux/kvm_host.h>
-#include <linux/mm.h>
 #include <linux/pm.h>
 #include <linux/sched.h>
 #include <linux/suspend.h>
@@ -31,14 +30,12 @@
 #include <asm/kexec.h>
 #include <asm/memory.h>
 #include <asm/mmu_context.h>
-#include <asm/pgalloc.h>
-#include <asm/pgtable.h>
-#include <asm/pgtable-hwdef.h>
 #include <asm/sections.h>
 #include <asm/smp.h>
 #include <asm/smp_plat.h>
 #include <asm/suspend.h>
 #include <asm/sysreg.h>
+#include <asm/trans_pgd.h>
 #include <asm/virt.h>
 
 /*
@@ -182,45 +179,6 @@ int arch_hibernation_header_restore(void *addr)
 }
 EXPORT_SYMBOL(arch_hibernation_header_restore);
 
-int trans_pgd_map_page(pgd_t *trans_pgd, void *page,
-		       unsigned long dst_addr,
-		       pgprot_t pgprot)
-{
-	pgd_t *pgdp;
-	pud_t *pudp;
-	pmd_t *pmdp;
-	pte_t *ptep;
-
-	pgdp = pgd_offset_raw(trans_pgd, dst_addr);
-	if (pgd_none(READ_ONCE(*pgdp))) {
-		pudp = (void *)get_safe_page(GFP_ATOMIC);
-		if (!pudp)
-			return -ENOMEM;
-		pgd_populate(&init_mm, pgdp, pudp);
-	}
-
-	pudp = pud_offset(pgdp, dst_addr);
-	if (pud_none(READ_ONCE(*pudp))) {
-		pmdp = (void *)get_safe_page(GFP_ATOMIC);
-		if (!pmdp)
-			return -ENOMEM;
-		pud_populate(&init_mm, pudp, pmdp);
-	}
-
-	pmdp = pmd_offset(pudp, dst_addr);
-	if (pmd_none(READ_ONCE(*pmdp))) {
-		ptep = (void *)get_safe_page(GFP_ATOMIC);
-		if (!ptep)
-			return -ENOMEM;
-		pmd_populate_kernel(&init_mm, pmdp, ptep);
-	}
-
-	ptep = pte_offset_kernel(pmdp, dst_addr);
-	set_pte(ptep, pfn_pte(virt_to_pfn(page), PAGE_KERNEL_EXEC));
-
-	return 0;
-}
-
 /*
  * Copies length bytes, starting at src_start into an new page,
  * perform cache maintenance, then maps it at the specified address low
@@ -339,161 +297,6 @@ int swsusp_arch_suspend(void)
 	return ret;
 }
 
-static void _copy_pte(pte_t *dst_ptep, pte_t *src_ptep, unsigned long addr)
-{
-	pte_t pte = READ_ONCE(*src_ptep);
-
-	if (pte_valid(pte)) {
-		/*
-		 * Resume will overwrite areas that may be marked
-		 * read only (code, rodata). Clear the RDONLY bit from
-		 * the temporary mappings we use during restore.
-		 */
-		set_pte(dst_ptep, pte_mkwrite(pte));
-	} else if (debug_pagealloc_enabled() && !pte_none(pte)) {
-		/*
-		 * debug_pagealloc will removed the PTE_VALID bit if
-		 * the page isn't in use by the resume kernel. It may have
-		 * been in use by the original kernel, in which case we need
-		 * to put it back in our copy to do the restore.
-		 *
-		 * Before marking this entry valid, check the pfn should
-		 * be mapped.
-		 */
-		BUG_ON(!pfn_valid(pte_pfn(pte)));
-
-		set_pte(dst_ptep, pte_mkpresent(pte_mkwrite(pte)));
-	}
-}
-
-static int copy_pte(pmd_t *dst_pmdp, pmd_t *src_pmdp, unsigned long start,
-		    unsigned long end)
-{
-	pte_t *src_ptep;
-	pte_t *dst_ptep;
-	unsigned long addr = start;
-
-	dst_ptep = (pte_t *)get_safe_page(GFP_ATOMIC);
-	if (!dst_ptep)
-		return -ENOMEM;
-	pmd_populate_kernel(&init_mm, dst_pmdp, dst_ptep);
-	dst_ptep = pte_offset_kernel(dst_pmdp, start);
-
-	src_ptep = pte_offset_kernel(src_pmdp, start);
-	do {
-		_copy_pte(dst_ptep, src_ptep, addr);
-	} while (dst_ptep++, src_ptep++, addr += PAGE_SIZE, addr != end);
-
-	return 0;
-}
-
-static int copy_pmd(pud_t *dst_pudp, pud_t *src_pudp, unsigned long start,
-		    unsigned long end)
-{
-	pmd_t *src_pmdp;
-	pmd_t *dst_pmdp;
-	unsigned long next;
-	unsigned long addr = start;
-
-	if (pud_none(READ_ONCE(*dst_pudp))) {
-		dst_pmdp = (pmd_t *)get_safe_page(GFP_ATOMIC);
-		if (!dst_pmdp)
-			return -ENOMEM;
-		pud_populate(&init_mm, dst_pudp, dst_pmdp);
-	}
-	dst_pmdp = pmd_offset(dst_pudp, start);
-
-	src_pmdp = pmd_offset(src_pudp, start);
-	do {
-		pmd_t pmd = READ_ONCE(*src_pmdp);
-
-		next = pmd_addr_end(addr, end);
-		if (pmd_none(pmd))
-			continue;
-		if (pmd_table(pmd)) {
-			if (copy_pte(dst_pmdp, src_pmdp, addr, next))
-				return -ENOMEM;
-		} else {
-			set_pmd(dst_pmdp,
-				__pmd(pmd_val(pmd) & ~PMD_SECT_RDONLY));
-		}
-	} while (dst_pmdp++, src_pmdp++, addr = next, addr != end);
-
-	return 0;
-}
-
-static int copy_pud(pgd_t *dst_pgdp, pgd_t *src_pgdp, unsigned long start,
-		    unsigned long end)
-{
-	pud_t *dst_pudp;
-	pud_t *src_pudp;
-	unsigned long next;
-	unsigned long addr = start;
-
-	if (pgd_none(READ_ONCE(*dst_pgdp))) {
-		dst_pudp = (pud_t *)get_safe_page(GFP_ATOMIC);
-		if (!dst_pudp)
-			return -ENOMEM;
-		pgd_populate(&init_mm, dst_pgdp, dst_pudp);
-	}
-	dst_pudp = pud_offset(dst_pgdp, start);
-
-	src_pudp = pud_offset(src_pgdp, start);
-	do {
-		pud_t pud = READ_ONCE(*src_pudp);
-
-		next = pud_addr_end(addr, end);
-		if (pud_none(pud))
-			continue;
-		if (pud_table(pud)) {
-			if (copy_pmd(dst_pudp, src_pudp, addr, next))
-				return -ENOMEM;
-		} else {
-			set_pud(dst_pudp,
-				__pud(pud_val(pud) & ~PUD_SECT_RDONLY));
-		}
-	} while (dst_pudp++, src_pudp++, addr = next, addr != end);
-
-	return 0;
-}
-
-static int copy_page_tables(pgd_t *dst_pgdp, unsigned long start,
-			    unsigned long end)
-{
-	unsigned long next;
-	unsigned long addr = start;
-	pgd_t *src_pgdp = pgd_offset_k(start);
-
-	dst_pgdp = pgd_offset_raw(dst_pgdp, start);
-	do {
-		next = pgd_addr_end(addr, end);
-		if (pgd_none(READ_ONCE(*src_pgdp)))
-			continue;
-		if (copy_pud(dst_pgdp, src_pgdp, addr, next))
-			return -ENOMEM;
-	} while (dst_pgdp++, src_pgdp++, addr = next, addr != end);
-
-	return 0;
-}
-
-int trans_pgd_create_copy(pgd_t **dst_pgdp, unsigned long start,
-			  unsigned long end)
-{
-	int rc;
-	pgd_t *trans_pgd = (pgd_t *)get_safe_page(GFP_ATOMIC);
-
-	if (!trans_pgd) {
-		pr_err("Failed to allocate memory for temporary page tables.\n");
-		return -ENOMEM;
-	}
-
-	rc = copy_page_tables(trans_pgd, start, end);
-	if (!rc)
-		*dst_pgdp = trans_pgd;
-
-	return rc;
-}
-
 /*
  * Setup then Resume from the hibernate image using swsusp_arch_suspend_exit().
  *
diff --git a/arch/arm64/mm/Makefile b/arch/arm64/mm/Makefile
index 849c1df3d214..f3002f1d0e61 100644
--- a/arch/arm64/mm/Makefile
+++ b/arch/arm64/mm/Makefile
@@ -6,6 +6,7 @@ obj-y				:= dma-mapping.o extable.o fault.o init.o \
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
 obj-$(CONFIG_ARM64_PTDUMP_CORE)	+= dump.o
 obj-$(CONFIG_ARM64_PTDUMP_DEBUGFS)	+= ptdump_debugfs.o
+obj-$(CONFIG_TRANS_TABLE)	+= trans_pgd.o
 obj-$(CONFIG_NUMA)		+= numa.o
 obj-$(CONFIG_DEBUG_VIRTUAL)	+= physaddr.o
 KASAN_SANITIZE_physaddr.o	+= n
diff --git a/arch/arm64/mm/trans_pgd.c b/arch/arm64/mm/trans_pgd.c
new file mode 100644
index 000000000000..5ac712b92439
--- /dev/null
+++ b/arch/arm64/mm/trans_pgd.c
@@ -0,0 +1,219 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Transitional page tables for kexec and hibernate
+ *
+ * This file derived from: arch/arm64/kernel/hibernate.c
+ *
+ * Copyright (c) 2019, Microsoft Corporation.
+ * Pavel Tatashin <patatash@linux.microsoft.com>
+ *
+ */
+
+/*
+ * Transitional tables are used during system transferring from one world to
+ * another: such as during hibernate restore, and kexec reboots. During these
+ * phases one cannot rely on page table not being overwritten. This is because
+ * hibernate and kexec can overwrite the current page tables during transition.
+ */
+
+#include <asm/trans_pgd.h>
+#include <asm/pgalloc.h>
+#include <asm/pgtable.h>
+#include <linux/suspend.h>
+#include <linux/bug.h>
+#include <linux/mm.h>
+#include <linux/mmzone.h>
+
+static void _copy_pte(pte_t *dst_ptep, pte_t *src_ptep, unsigned long addr)
+{
+	pte_t pte = READ_ONCE(*src_ptep);
+
+	if (pte_valid(pte)) {
+		/*
+		 * Resume will overwrite areas that may be marked
+		 * read only (code, rodata). Clear the RDONLY bit from
+		 * the temporary mappings we use during restore.
+		 */
+		set_pte(dst_ptep, pte_mkwrite(pte));
+	} else if (debug_pagealloc_enabled() && !pte_none(pte)) {
+		/*
+		 * debug_pagealloc will removed the PTE_VALID bit if
+		 * the page isn't in use by the resume kernel. It may have
+		 * been in use by the original kernel, in which case we need
+		 * to put it back in our copy to do the restore.
+		 *
+		 * Before marking this entry valid, check the pfn should
+		 * be mapped.
+		 */
+		BUG_ON(!pfn_valid(pte_pfn(pte)));
+
+		set_pte(dst_ptep, pte_mkpresent(pte_mkwrite(pte)));
+	}
+}
+
+static int copy_pte(pmd_t *dst_pmdp, pmd_t *src_pmdp, unsigned long start,
+		    unsigned long end)
+{
+	pte_t *src_ptep;
+	pte_t *dst_ptep;
+	unsigned long addr = start;
+
+	dst_ptep = (pte_t *)get_safe_page(GFP_ATOMIC);
+	if (!dst_ptep)
+		return -ENOMEM;
+	pmd_populate_kernel(&init_mm, dst_pmdp, dst_ptep);
+	dst_ptep = pte_offset_kernel(dst_pmdp, start);
+
+	src_ptep = pte_offset_kernel(src_pmdp, start);
+	do {
+		_copy_pte(dst_ptep, src_ptep, addr);
+	} while (dst_ptep++, src_ptep++, addr += PAGE_SIZE, addr != end);
+
+	return 0;
+}
+
+static int copy_pmd(pud_t *dst_pudp, pud_t *src_pudp, unsigned long start,
+		    unsigned long end)
+{
+	pmd_t *src_pmdp;
+	pmd_t *dst_pmdp;
+	unsigned long next;
+	unsigned long addr = start;
+
+	if (pud_none(READ_ONCE(*dst_pudp))) {
+		dst_pmdp = (pmd_t *)get_safe_page(GFP_ATOMIC);
+		if (!dst_pmdp)
+			return -ENOMEM;
+		pud_populate(&init_mm, dst_pudp, dst_pmdp);
+	}
+	dst_pmdp = pmd_offset(dst_pudp, start);
+
+	src_pmdp = pmd_offset(src_pudp, start);
+	do {
+		pmd_t pmd = READ_ONCE(*src_pmdp);
+
+		next = pmd_addr_end(addr, end);
+		if (pmd_none(pmd))
+			continue;
+		if (pmd_table(pmd)) {
+			if (copy_pte(dst_pmdp, src_pmdp, addr, next))
+				return -ENOMEM;
+		} else {
+			set_pmd(dst_pmdp,
+				__pmd(pmd_val(pmd) & ~PMD_SECT_RDONLY));
+		}
+	} while (dst_pmdp++, src_pmdp++, addr = next, addr != end);
+
+	return 0;
+}
+
+static int copy_pud(pgd_t *dst_pgdp, pgd_t *src_pgdp, unsigned long start,
+		    unsigned long end)
+{
+	pud_t *dst_pudp;
+	pud_t *src_pudp;
+	unsigned long next;
+	unsigned long addr = start;
+
+	if (pgd_none(READ_ONCE(*dst_pgdp))) {
+		dst_pudp = (pud_t *)get_safe_page(GFP_ATOMIC);
+		if (!dst_pudp)
+			return -ENOMEM;
+		pgd_populate(&init_mm, dst_pgdp, dst_pudp);
+	}
+	dst_pudp = pud_offset(dst_pgdp, start);
+
+	src_pudp = pud_offset(src_pgdp, start);
+	do {
+		pud_t pud = READ_ONCE(*src_pudp);
+
+		next = pud_addr_end(addr, end);
+		if (pud_none(pud))
+			continue;
+		if (pud_table(pud)) {
+			if (copy_pmd(dst_pudp, src_pudp, addr, next))
+				return -ENOMEM;
+		} else {
+			set_pud(dst_pudp,
+				__pud(pud_val(pud) & ~PUD_SECT_RDONLY));
+		}
+	} while (dst_pudp++, src_pudp++, addr = next, addr != end);
+
+	return 0;
+}
+
+static int copy_page_tables(pgd_t *dst_pgdp, unsigned long start,
+			    unsigned long end)
+{
+	unsigned long next;
+	unsigned long addr = start;
+	pgd_t *src_pgdp = pgd_offset_k(start);
+
+	dst_pgdp = pgd_offset_raw(dst_pgdp, start);
+	do {
+		next = pgd_addr_end(addr, end);
+		if (pgd_none(READ_ONCE(*src_pgdp)))
+			continue;
+		if (copy_pud(dst_pgdp, src_pgdp, addr, next))
+			return -ENOMEM;
+	} while (dst_pgdp++, src_pgdp++, addr = next, addr != end);
+
+	return 0;
+}
+
+int trans_pgd_create_copy(pgd_t **dst_pgdp, unsigned long start,
+			  unsigned long end)
+{
+	int rc;
+	pgd_t *trans_pgd = (pgd_t *)get_safe_page(GFP_ATOMIC);
+
+	if (!trans_pgd) {
+		pr_err("Failed to allocate memory for temporary page tables.\n");
+		return -ENOMEM;
+	}
+
+	rc = copy_page_tables(trans_pgd, start, end);
+	if (!rc)
+		*dst_pgdp = trans_pgd;
+
+	return rc;
+}
+
+int trans_pgd_map_page(pgd_t *trans_pgd, void *page, unsigned long dst_addr,
+		       pgprot_t pgprot)
+{
+	pgd_t *pgdp;
+	pud_t *pudp;
+	pmd_t *pmdp;
+	pte_t *ptep;
+
+	pgdp = pgd_offset_raw(trans_pgd, dst_addr);
+	if (pgd_none(READ_ONCE(*pgdp))) {
+		pudp = (void *)get_safe_page(GFP_ATOMIC);
+		if (!pudp)
+			return -ENOMEM;
+		pgd_populate(&init_mm, pgdp, pudp);
+	}
+
+	pudp = pud_offset(pgdp, dst_addr);
+	if (pud_none(READ_ONCE(*pudp))) {
+		pmdp = (void *)get_safe_page(GFP_ATOMIC);
+		if (!pmdp)
+			return -ENOMEM;
+		pud_populate(&init_mm, pudp, pmdp);
+	}
+
+	pmdp = pmd_offset(pudp, dst_addr);
+	if (pmd_none(READ_ONCE(*pmdp))) {
+		ptep = (void *)get_safe_page(GFP_ATOMIC);
+		if (!ptep)
+			return -ENOMEM;
+		pmd_populate_kernel(&init_mm, pmdp, ptep);
+	}
+
+	ptep = pte_offset_kernel(pmdp, dst_addr);
+	set_pte(ptep, pfn_pte(virt_to_pfn(page), PAGE_KERNEL_EXEC));
+
+	return 0;
+}
-- 
2.23.0


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

^ permalink raw reply related

* [PATCH v5 08/17] arm64: hibernate: add trans_pgd public functions
From: Pavel Tatashin @ 2019-09-23 20:34 UTC (permalink / raw)
  To: pasha.tatashin, jmorris, sashal, ebiederm, kexec, linux-kernel,
	corbet, catalin.marinas, will, linux-arm-kernel, marc.zyngier,
	james.morse, vladimir.murzin, matthias.bgg, bhsharma, linux-mm,
	mark.rutland
In-Reply-To: <20190923203427.294286-1-pasha.tatashin@soleen.com>

trans_pgd_create_copy() and trans_pgd_map_page() are going to be
the basis for new shared code that handles page tables for cases
which are between kernels: kexec, and hibernate.

Note: Eventually, get_safe_page() will be moved into a function pointer
passed via argument, but for now keep it as is.

Signed-off-by: Pavel Tatashin <pasha.tatashin@soleen.com>
---
 arch/arm64/kernel/hibernate.c | 88 ++++++++++++++++++++++++-----------
 1 file changed, 60 insertions(+), 28 deletions(-)

diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index ce60bceed357..ded9034b9d39 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -182,39 +182,15 @@ int arch_hibernation_header_restore(void *addr)
 }
 EXPORT_SYMBOL(arch_hibernation_header_restore);
 
-/*
- * Copies length bytes, starting at src_start into an new page,
- * perform cache maintentance, then maps it at the specified address low
- * address as executable.
- *
- * This is used by hibernate to copy the code it needs to execute when
- * overwriting the kernel text. This function generates a new set of page
- * tables, which it loads into ttbr0.
- *
- * Length is provided as we probably only want 4K of data, even on a 64K
- * page system.
- */
-static int create_safe_exec_page(void *src_start, size_t length,
-				 unsigned long dst_addr,
-				 phys_addr_t *phys_dst_addr)
+int trans_pgd_map_page(pgd_t *trans_pgd, void *page,
+		       unsigned long dst_addr,
+		       pgprot_t pgprot)
 {
-	void *page = (void *)get_safe_page(GFP_ATOMIC);
-	pgd_t *trans_pgd;
 	pgd_t *pgdp;
 	pud_t *pudp;
 	pmd_t *pmdp;
 	pte_t *ptep;
 
-	if (!page)
-		return -ENOMEM;
-
-	memcpy(page, src_start, length);
-	__flush_icache_range((unsigned long)page, (unsigned long)page + length);
-
-	trans_pgd = (void *)get_safe_page(GFP_ATOMIC);
-	if (!trans_pgd)
-		return -ENOMEM;
-
 	pgdp = pgd_offset_raw(trans_pgd, dst_addr);
 	if (pgd_none(READ_ONCE(*pgdp))) {
 		pudp = (void *)get_safe_page(GFP_ATOMIC);
@@ -242,6 +218,44 @@ static int create_safe_exec_page(void *src_start, size_t length,
 	ptep = pte_offset_kernel(pmdp, dst_addr);
 	set_pte(ptep, pfn_pte(virt_to_pfn(page), PAGE_KERNEL_EXEC));
 
+	return 0;
+}
+
+/*
+ * Copies length bytes, starting at src_start into an new page,
+ * perform cache maintenance, then maps it at the specified address low
+ * address as executable.
+ *
+ * This is used by hibernate to copy the code it needs to execute when
+ * overwriting the kernel text. This function generates a new set of page
+ * tables, which it loads into ttbr0.
+ *
+ * Length is provided as we probably only want 4K of data, even on a 64K
+ * page system.
+ */
+static int create_safe_exec_page(void *src_start, size_t length,
+				 unsigned long dst_addr,
+				 phys_addr_t *phys_dst_addr)
+{
+	void *page = (void *)get_safe_page(GFP_ATOMIC);
+	pgd_t *trans_pgd;
+	int rc;
+
+	if (!page)
+		return -ENOMEM;
+
+	memcpy(page, src_start, length);
+	__flush_icache_range((unsigned long)page, (unsigned long)page + length);
+
+	trans_pgd = (void *)get_safe_page(GFP_ATOMIC);
+	if (!trans_pgd)
+		return -ENOMEM;
+
+	rc = trans_pgd_map_page(trans_pgd, page, dst_addr,
+				PAGE_KERNEL_EXEC);
+	if (rc)
+		return rc;
+
 	/*
 	 * Load our new page tables. A strict BBM approach requires that we
 	 * ensure that TLBs are free of any entries that may overlap with the
@@ -462,6 +476,24 @@ static int copy_page_tables(pgd_t *dst_pgdp, unsigned long start,
 	return 0;
 }
 
+int trans_pgd_create_copy(pgd_t **dst_pgdp, unsigned long start,
+			  unsigned long end)
+{
+	int rc;
+	pgd_t *trans_pgd = (pgd_t *)get_safe_page(GFP_ATOMIC);
+
+	if (!trans_pgd) {
+		pr_err("Failed to allocate memory for temporary page tables.\n");
+		return -ENOMEM;
+	}
+
+	rc = copy_page_tables(trans_pgd, start, end);
+	if (!rc)
+		*dst_pgdp = trans_pgd;
+
+	return rc;
+}
+
 /*
  * Setup then Resume from the hibernate image using swsusp_arch_suspend_exit().
  *
@@ -488,7 +520,7 @@ int swsusp_arch_resume(void)
 		pr_err("Failed to allocate memory for temporary page tables.\n");
 		return -ENOMEM;
 	}
-	rc = copy_page_tables(tmp_pg_dir, PAGE_OFFSET, PAGE_END);
+	rc = trans_pgd_create_copy(&tmp_pg_dir, PAGE_OFFSET, PAGE_END);
 	if (rc)
 		return rc;
 
-- 
2.23.0


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

^ permalink raw reply related

* [PATCH v5 07/17] arm64: hibernate: add PUD_SECT_RDONLY
From: Pavel Tatashin @ 2019-09-23 20:34 UTC (permalink / raw)
  To: pasha.tatashin, jmorris, sashal, ebiederm, kexec, linux-kernel,
	corbet, catalin.marinas, will, linux-arm-kernel, marc.zyngier,
	james.morse, vladimir.murzin, matthias.bgg, bhsharma, linux-mm,
	mark.rutland
In-Reply-To: <20190923203427.294286-1-pasha.tatashin@soleen.com>

There is PMD_SECT_RDONLY that is used in pud_* function which is confusing.

Signed-off-by: Pavel Tatashin <pasha.tatashin@soleen.com>
Acked-by: James Morse <james.morse@arm.com>
---
 arch/arm64/include/asm/pgtable-hwdef.h | 1 +
 arch/arm64/kernel/hibernate.c          | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index 3df60f97da1f..756a1dfb4f55 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -110,6 +110,7 @@
 #define PUD_TABLE_BIT		(_AT(pudval_t, 1) << 1)
 #define PUD_TYPE_MASK		(_AT(pudval_t, 3) << 0)
 #define PUD_TYPE_SECT		(_AT(pudval_t, 1) << 0)
+#define PUD_SECT_RDONLY		(_AT(pudval_t, 1) << 7)		/* AP[2] */
 
 /*
  * Level 2 descriptor (PMD).
diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index 1ca8af685e96..ce60bceed357 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -436,7 +436,7 @@ static int copy_pud(pgd_t *dst_pgdp, pgd_t *src_pgdp, unsigned long start,
 				return -ENOMEM;
 		} else {
 			set_pud(dst_pudp,
-				__pud(pud_val(pud) & ~PMD_SECT_RDONLY));
+				__pud(pud_val(pud) & ~PUD_SECT_RDONLY));
 		}
 	} while (dst_pudp++, src_pudp++, addr = next, addr != end);
 
-- 
2.23.0


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

^ permalink raw reply related

* [PATCH v5 06/17] arm64: hibernate: rename dst to page in create_safe_exec_page
From: Pavel Tatashin @ 2019-09-23 20:34 UTC (permalink / raw)
  To: pasha.tatashin, jmorris, sashal, ebiederm, kexec, linux-kernel,
	corbet, catalin.marinas, will, linux-arm-kernel, marc.zyngier,
	james.morse, vladimir.murzin, matthias.bgg, bhsharma, linux-mm,
	mark.rutland
In-Reply-To: <20190923203427.294286-1-pasha.tatashin@soleen.com>

create_safe_exec_page() allocates a safe page and maps it at a
specific location, also this function returns the physical address
of newly allocated page.

The destination VA, and PA are specified in arguments: dst_addr,
phys_dst_addr

However, within the function it uses "dst" which has unsigned long
type, but is actually a pointers in the current virtual space. This
is confusing to read.

Rename dst to more appropriate page (page that is created), and also
change its time to "void *"

Signed-off-by: Pavel Tatashin <pasha.tatashin@soleen.com>
Reviewed-by: James Morse <james.morse@arm.com>
---
 arch/arm64/kernel/hibernate.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index 83c41a2f8400..1ca8af685e96 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -198,18 +198,18 @@ static int create_safe_exec_page(void *src_start, size_t length,
 				 unsigned long dst_addr,
 				 phys_addr_t *phys_dst_addr)
 {
+	void *page = (void *)get_safe_page(GFP_ATOMIC);
 	pgd_t *trans_pgd;
 	pgd_t *pgdp;
 	pud_t *pudp;
 	pmd_t *pmdp;
 	pte_t *ptep;
-	unsigned long dst = get_safe_page(GFP_ATOMIC);
 
-	if (!dst)
+	if (!page)
 		return -ENOMEM;
 
-	memcpy((void *)dst, src_start, length);
-	__flush_icache_range(dst, dst + length);
+	memcpy(page, src_start, length);
+	__flush_icache_range((unsigned long)page, (unsigned long)page + length);
 
 	trans_pgd = (void *)get_safe_page(GFP_ATOMIC);
 	if (!trans_pgd)
@@ -240,7 +240,7 @@ static int create_safe_exec_page(void *src_start, size_t length,
 	}
 
 	ptep = pte_offset_kernel(pmdp, dst_addr);
-	set_pte(ptep, pfn_pte(virt_to_pfn(dst), PAGE_KERNEL_EXEC));
+	set_pte(ptep, pfn_pte(virt_to_pfn(page), PAGE_KERNEL_EXEC));
 
 	/*
 	 * Load our new page tables. A strict BBM approach requires that we
@@ -259,7 +259,7 @@ static int create_safe_exec_page(void *src_start, size_t length,
 	write_sysreg(phys_to_ttbr(virt_to_phys(trans_pgd)), ttbr0_el1);
 	isb();
 
-	*phys_dst_addr = virt_to_phys((void *)dst);
+	*phys_dst_addr = virt_to_phys(page);
 
 	return 0;
 }
-- 
2.23.0


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

^ permalink raw reply related

* [PATCH v5 05/17] arm64: hibernate: remove gotos as they are not needed
From: Pavel Tatashin @ 2019-09-23 20:34 UTC (permalink / raw)
  To: pasha.tatashin, jmorris, sashal, ebiederm, kexec, linux-kernel,
	corbet, catalin.marinas, will, linux-arm-kernel, marc.zyngier,
	james.morse, vladimir.murzin, matthias.bgg, bhsharma, linux-mm,
	mark.rutland
In-Reply-To: <20190923203427.294286-1-pasha.tatashin@soleen.com>

Usually, gotos are used to handle cleanup after exception, but in case of
create_safe_exec_page and swsusp_arch_resume there are no clean-ups. So,
simply return the errors directly.

Signed-off-by: Pavel Tatashin <pasha.tatashin@soleen.com>
Reviewed-by: James Morse <james.morse@arm.com>
---
 arch/arm64/kernel/hibernate.c | 49 ++++++++++++-----------------------
 1 file changed, 17 insertions(+), 32 deletions(-)

diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index 34297716643f..83c41a2f8400 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -198,7 +198,6 @@ static int create_safe_exec_page(void *src_start, size_t length,
 				 unsigned long dst_addr,
 				 phys_addr_t *phys_dst_addr)
 {
-	int rc = 0;
 	pgd_t *trans_pgd;
 	pgd_t *pgdp;
 	pud_t *pudp;
@@ -206,47 +205,37 @@ static int create_safe_exec_page(void *src_start, size_t length,
 	pte_t *ptep;
 	unsigned long dst = get_safe_page(GFP_ATOMIC);
 
-	if (!dst) {
-		rc = -ENOMEM;
-		goto out;
-	}
+	if (!dst)
+		return -ENOMEM;
 
 	memcpy((void *)dst, src_start, length);
 	__flush_icache_range(dst, dst + length);
 
 	trans_pgd = (void *)get_safe_page(GFP_ATOMIC);
-	if (!trans_pgd) {
-		rc = -ENOMEM;
-		goto out;
-	}
+	if (!trans_pgd)
+		return -ENOMEM;
 
 	pgdp = pgd_offset_raw(trans_pgd, dst_addr);
 	if (pgd_none(READ_ONCE(*pgdp))) {
 		pudp = (void *)get_safe_page(GFP_ATOMIC);
-		if (!pudp) {
-			rc = -ENOMEM;
-			goto out;
-		}
+		if (!pudp)
+			return -ENOMEM;
 		pgd_populate(&init_mm, pgdp, pudp);
 	}
 
 	pudp = pud_offset(pgdp, dst_addr);
 	if (pud_none(READ_ONCE(*pudp))) {
 		pmdp = (void *)get_safe_page(GFP_ATOMIC);
-		if (!pmdp) {
-			rc = -ENOMEM;
-			goto out;
-		}
+		if (!pmdp)
+			return -ENOMEM;
 		pud_populate(&init_mm, pudp, pmdp);
 	}
 
 	pmdp = pmd_offset(pudp, dst_addr);
 	if (pmd_none(READ_ONCE(*pmdp))) {
 		ptep = (void *)get_safe_page(GFP_ATOMIC);
-		if (!ptep) {
-			rc = -ENOMEM;
-			goto out;
-		}
+		if (!ptep)
+			return -ENOMEM;
 		pmd_populate_kernel(&init_mm, pmdp, ptep);
 	}
 
@@ -272,8 +261,7 @@ static int create_safe_exec_page(void *src_start, size_t length,
 
 	*phys_dst_addr = virt_to_phys((void *)dst);
 
-out:
-	return rc;
+	return 0;
 }
 
 #define dcache_clean_range(start, end)	__flush_dcache_area(start, (end - start))
@@ -482,7 +470,7 @@ static int copy_page_tables(pgd_t *dst_pgdp, unsigned long start,
  */
 int swsusp_arch_resume(void)
 {
-	int rc = 0;
+	int rc;
 	void *zero_page;
 	size_t exit_size;
 	pgd_t *tmp_pg_dir;
@@ -498,12 +486,11 @@ int swsusp_arch_resume(void)
 	tmp_pg_dir = (pgd_t *)get_safe_page(GFP_ATOMIC);
 	if (!tmp_pg_dir) {
 		pr_err("Failed to allocate memory for temporary page tables.\n");
-		rc = -ENOMEM;
-		goto out;
+		return -ENOMEM;
 	}
 	rc = copy_page_tables(tmp_pg_dir, PAGE_OFFSET, PAGE_END);
 	if (rc)
-		goto out;
+		return rc;
 
 	/*
 	 * We need a zero page that is zero before & after resume in order to
@@ -512,8 +499,7 @@ int swsusp_arch_resume(void)
 	zero_page = (void *)get_safe_page(GFP_ATOMIC);
 	if (!zero_page) {
 		pr_err("Failed to allocate zero page.\n");
-		rc = -ENOMEM;
-		goto out;
+		return -ENOMEM;
 	}
 
 	/*
@@ -531,7 +517,7 @@ int swsusp_arch_resume(void)
 				   &phys_hibernate_exit);
 	if (rc) {
 		pr_err("Failed to create safe executable page for hibernate_exit code.\n");
-		goto out;
+		return rc;
 	}
 
 	/*
@@ -558,8 +544,7 @@ int swsusp_arch_resume(void)
 		       resume_hdr.reenter_kernel, restore_pblist,
 		       resume_hdr.__hyp_stub_vectors, virt_to_phys(zero_page));
 
-out:
-	return rc;
+	return 0;
 }
 
 int hibernate_resume_nonboot_cpu_disable(void)
-- 
2.23.0


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

^ permalink raw reply related

* [PATCH v5 04/17] arm64: hibernate: use get_safe_page directly
From: Pavel Tatashin @ 2019-09-23 20:34 UTC (permalink / raw)
  To: pasha.tatashin, jmorris, sashal, ebiederm, kexec, linux-kernel,
	corbet, catalin.marinas, will, linux-arm-kernel, marc.zyngier,
	james.morse, vladimir.murzin, matthias.bgg, bhsharma, linux-mm,
	mark.rutland
In-Reply-To: <20190923203427.294286-1-pasha.tatashin@soleen.com>

create_safe_exec_page() uses hibernate's allocator to create a set of page
table to map a single page that will contain the relocation code.

Remove the allocator related arguments, and use get_safe_page directly, as
it is done in other local functions in this file to simplify function
prototype.

Removing this function pointer makes it easier to refactor the code later.

Signed-off-by: Pavel Tatashin <pasha.tatashin@soleen.com>
Reviewed-by: Matthias Brugger <mbrugger@suse.com>
---
 arch/arm64/kernel/hibernate.c | 17 +++++++----------
 1 file changed, 7 insertions(+), 10 deletions(-)

diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index ef46ce66d7e8..34297716643f 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -196,9 +196,7 @@ EXPORT_SYMBOL(arch_hibernation_header_restore);
  */
 static int create_safe_exec_page(void *src_start, size_t length,
 				 unsigned long dst_addr,
-				 phys_addr_t *phys_dst_addr,
-				 void *(*allocator)(gfp_t mask),
-				 gfp_t mask)
+				 phys_addr_t *phys_dst_addr)
 {
 	int rc = 0;
 	pgd_t *trans_pgd;
@@ -206,7 +204,7 @@ static int create_safe_exec_page(void *src_start, size_t length,
 	pud_t *pudp;
 	pmd_t *pmdp;
 	pte_t *ptep;
-	unsigned long dst = (unsigned long)allocator(mask);
+	unsigned long dst = get_safe_page(GFP_ATOMIC);
 
 	if (!dst) {
 		rc = -ENOMEM;
@@ -216,7 +214,7 @@ static int create_safe_exec_page(void *src_start, size_t length,
 	memcpy((void *)dst, src_start, length);
 	__flush_icache_range(dst, dst + length);
 
-	trans_pgd = allocator(mask);
+	trans_pgd = (void *)get_safe_page(GFP_ATOMIC);
 	if (!trans_pgd) {
 		rc = -ENOMEM;
 		goto out;
@@ -224,7 +222,7 @@ static int create_safe_exec_page(void *src_start, size_t length,
 
 	pgdp = pgd_offset_raw(trans_pgd, dst_addr);
 	if (pgd_none(READ_ONCE(*pgdp))) {
-		pudp = allocator(mask);
+		pudp = (void *)get_safe_page(GFP_ATOMIC);
 		if (!pudp) {
 			rc = -ENOMEM;
 			goto out;
@@ -234,7 +232,7 @@ static int create_safe_exec_page(void *src_start, size_t length,
 
 	pudp = pud_offset(pgdp, dst_addr);
 	if (pud_none(READ_ONCE(*pudp))) {
-		pmdp = allocator(mask);
+		pmdp = (void *)get_safe_page(GFP_ATOMIC);
 		if (!pmdp) {
 			rc = -ENOMEM;
 			goto out;
@@ -244,7 +242,7 @@ static int create_safe_exec_page(void *src_start, size_t length,
 
 	pmdp = pmd_offset(pudp, dst_addr);
 	if (pmd_none(READ_ONCE(*pmdp))) {
-		ptep = allocator(mask);
+		ptep = (void *)get_safe_page(GFP_ATOMIC);
 		if (!ptep) {
 			rc = -ENOMEM;
 			goto out;
@@ -530,8 +528,7 @@ int swsusp_arch_resume(void)
 	 */
 	rc = create_safe_exec_page(__hibernate_exit_text_start, exit_size,
 				   (unsigned long)hibernate_exit,
-				   &phys_hibernate_exit,
-				   (void *)get_safe_page, GFP_ATOMIC);
+				   &phys_hibernate_exit);
 	if (rc) {
 		pr_err("Failed to create safe executable page for hibernate_exit code.\n");
 		goto out;
-- 
2.23.0


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

^ permalink raw reply related


This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox