Merge tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Don't destroy user event fields when removal fails

   User event fields are destroyed before the event is removed from
   visibility. But that can fail leaving the still visible event with no
   fields. Move the destroying of the fields to after the event is
   successfully removed from visibility.

 - Initialize function graph state is fork before calling
   copy_exec_state()

   For non-CLONE_VM forks, copy_exec_state() allocates a new
   task_exec_state. If that allocation fails, ftrace_graph_exit_task()
   will free the tasks ret_stack pointer. Since that pointer is still
   using the parent's ret_stack, it mistakenly frees the parent's
   pointer too.

   Call ftrace_graph_init() on the task first which will NULL out the
   new tasks's ret_stack and if the copy fails, it will not free
   anything.

 - Remove FGRAPH_MAX_INDEX

   The macro FGRAPH_MAX_INDEX was added but never used. Remove it.

 - Save ent_size in function graph printing of nested functions

   The function graph tracer needs to look at the next event to see if
   the next event is the return of the current function entry. If it is,
   it prints a single line:

	ktime_get();

   Otherwise it prints it like a nested function:

	tick_nohz_irq_exit() {
	    ktime_get();
	    kcpustat_irq_exit();
	}

   In order to look at the next event, it must save the current event so
   that it has the information to print from it. It saves the event in
   the iterator descriptor called "ent". What it doesn't save is the
   ent_size of the event which is now used to know if the function graph
   arguments are to be printed. The peek doesn't save the size so the
   size used happens to be that of the size of the last event that was
   seen.

   Save the entry event size in the iterator descriptor so that the
   correct size is used.

 - Fix several errors with freeing data in the histogram code

   The histogram code had a lot of leaked or or incorrect accounting
   when failures happen. Correct them.

 - Fix histogram regression of .percent and .graph modifiers

   Up until 6.3 histogram values could have "percent" or "graph"
   modifiers that changed how they were printed. But a change that added
   restricting histograms values from being strings, stack traces and
   other modifiers inadvertently prevented them from using the percent
   and graph modifiers, which were legal use cases for values.

   Put back the percent and graph modifiers.

 - Fix various typos in the comments

 - Set the trace_clock before initializing a histogram with clock
   argument

   The histogram API allows the user to specific which trace clock to
   use via a "clock=" string. The histogram is set up first before the
   clock is checked. If the passed in clock is not valid, it exits
   without fully fixing up the histogram leaving it on the list and a
   use-after-free can trigger.

   Update the clock argument first and if it fails then exit gracefully
   before the histogram trigger is placed on any lists.

 - Restore :mod: trailer after parsing in ftrace_set_clr_event

   The function ftrace_set_clr_event() modifies the parse string and
   needs to put it back to what was passed in. It searches for ":mod:"
   via a strsep() but fails to put back the first ':' in the string.

   Add back the ':' in the passed in string.

 - Take trace_array reference when opening a tracer options file

   The options files are dynamically created and some tracers add their
   own options. When a tracer adds their own list of options, the
   trace_array holding them has an array to hold the list of options for
   each tracer. This array increases in size via a krealloc(), and the
   new entry gets a newly allocated array to hold the options of the new
   tracer being added.

   The element in each entry of the tracer's option array holds a
   pointer back to the trace_array, a pointer to the tracer it is
   associated to, a pointer to the flags of the option.

   The issue is that these arrays are freed when the trace_array is
   freed when its instance it represents is removed from the instances
   directory. There's a race that an open of one of these options files
   can happen when the instance is being removed.

   Add a new helper function to be called by the open function of the
   options file to iterate all existing trace_arrays under a lock and
   find the one that has the given option element in one of it's tracer
   arrays. If found, then update the associated trace_array's reference
   counter to keep it from being freed. If not found, have the open call
   return -ENODEV.

 - Disable interrupts when acquiring the lock in rb_wake_up_waiters()

   The function rb_wake_up_waiters() assumes it will be called in
   interrupt context and does not disable irqs when taking
   cpu_buffer->reader_lock, which can be called in hard interrupt
   context. The issue is in PREEMPT_RT, this function is called in
   thread context leaving this lock open to a deadlock.

   Take the lock with interrupts disabled.

 - Use rcu_assign_pointer() for tmp_ops filter hash

   The tmp_ops used in update_ftrace_direct_mod() assigns its
   filter_hash field directly, but that field is annotated as __rcu and
   sparse complains. Assign it with rcu_assign_pointer()

 - Fix use-after-free in enable_trigger_private_data_free()

   The trace_event_call is accessed through the event_trigger_data's
   trace_event_file pointer to put the trace_event_call on freeing. The
   issue is that the trace_event_file data may have been freed already
   causing a use-after-free. Add a field to the event_trigger_data that
   points directly to the trace_event_call so that it can decrement its
   reference directly without needing to go through the
   trace_event_file.

 - Fix accounting of buffer data remote headers

   trace_buffer_desc_size() and trace_remote_alloc_buffer() undercount
   the number of pages is needed for the asked for size as it doesn't
   take into account the meta data on each page. Add a helper function
   to do the calculation properly and use that in these functions.

 - Catch nr_page_va overflow in ring_buffer_desc sizing

   The number of pages per remote ring buffer is capped by
   ring_buffer_desc::nr_page_va (32 bits). A buffer_size large enough to
   overflow that field would silently allocate a descriptor smaller than
   what was asked for.

 - Do not resize the subbuf order if any per_cpu buffer is disabled

   The mmapping of ring buffers disables resizing the subbuffers, but it
   is done per-cpu whereas the subbuf size change is done for all the
   per_cpu buffers under the buffer->mutex. It could change the size of
   some while the mapping is happening on others. Have the resize of the
   subbuf order check all the per_cpu buffers under the lock to see if
   any of them is disabled before starting and causing an inconsistency
   between buffers that are being mapped.

* tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: (25 commits)
  ring-buffer: Check resize_disabled before publishing the new subbuf order
  tracing/remotes: Catch nr_page_va overflow in ring_buffer_desc sizing
  tracing/remotes: Account for ring buffer page header in size calculation
  tracing: Don't dereference trace_event_file in deferred trigger free
  ftrace: Use rcu_assign_pointer() for tmp_ops filter hash
  ring-buffer: Acquire the lock with irqsave in rb_wake_up_waiters()
  tracing: Take trace_array reference when opening a tracer options file
  tracing: Fix ring_buffer_read_page_size() kernel-doc
  tracing: Restore :mod: trailer after parsing in ftrace_set_clr_event()
  tracing: Fix memory corruption from a "STACKTRACE" histogram key
  tracing: Fix memory corruption from the histogram stacktrace modifier
  tracing: Undo the registration when enabling the histogram trigger fails
  tracing: Take the reference before publishing the named histogram trigger
  tracing: Set the trace clock before registering the histogram trigger
  tracing: Fix typo "preceeded" in comment
  tracing: Fix typo "availabe" in comment
  tracing: Let histogram values keep the percent and graph modifiers
  tracing: Keep the entry count when the histogram stats allocation fails
  tracing: Free histogram the field rejected for a bad modifier
  tracing: Free histogram the var ref when its initialization fails
  ...

1 files changed, 814 insertions, 0 deletions

diff --git a/drivers/leds/trigger/ledtrig-netdev.c b/drivers/leds/trigger/ledtrig-netdev.c
new file mode 100644
index 000000000..5b4e92c14
--- /dev/null
+++ b/drivers/leds/trigger/ledtrig-netdev.c
@@ -0,0 +1,814 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright 2017 Ben Whitten <ben.whitten@gmail.com>
+// Copyright 2007 Oliver Jowett <oliver@opencloud.com>
+//
+// LED Kernel Netdev Trigger
+//
+// Toggles the LED to reflect the link and traffic state of a named net device
+//
+// Derived from ledtrig-timer.c which is:
+//  Copyright 2005-2006 Openedhand Ltd.
+//  Author: Richard Purdie <rpurdie@openedhand.com>
+
+#include <linux/atomic.h>
+#include <linux/ctype.h>
+#include <linux/device.h>
+#include <linux/ethtool.h>
+#include <linux/init.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/leds.h>
+#include <linux/linkmode.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/mutex.h>
+#include <linux/phy.h>
+#include <linux/rtnetlink.h>
+#include <linux/timer.h>
+#include <net/netdev_lock.h>
+#include "../leds.h"
+
+#define NETDEV_LED_DEFAULT_INTERVAL	50
+
+/*
+ * Configurable sysfs attributes:
+ *
+ * device_name - network device name to monitor
+ * interval - duration of LED blink, in milliseconds
+ * link -  LED's normal state reflects whether the link is up
+ *         (has carrier) or not
+ * tx -  LED blinks on transmitted data
+ * rx -  LED blinks on receive data
+ * tx_err -  LED blinks on transmit error
+ * rx_err -  LED blinks on receive error
+ *
+ * Note: If the user selects a mode that is not supported by hw, default
+ * behavior is to fall back to software control of the LED. However not every
+ * hw supports software control. LED callbacks brightness_set() and
+ * brightness_set_blocking() are NULL in this case. hw_control_is_supported()
+ * should use available means supported by hw to inform the user that selected
+ * mode isn't supported by hw. This could be switching off the LED or any
+ * hw blink mode. If software control fallback isn't possible, we return
+ * -EOPNOTSUPP to the user, but still store the selected mode. This is needed
+ * in case an intermediate unsupported mode is necessary to switch from one
+ * supported mode to another.
+ */
+
+struct led_netdev_data {
+	struct mutex lock;
+
+	struct delayed_work work;
+	struct notifier_block notifier;
+
+	struct led_classdev *led_cdev;
+	struct net_device *net_dev;
+
+	char device_name[IFNAMSIZ];
+	atomic_t interval;
+	unsigned int last_activity;
+
+	unsigned long mode;
+	int link_speed;
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(supported_link_modes);
+	u8 duplex;
+
+	bool carrier_link_up;
+	bool hw_control;
+};
+
+static const struct attribute_group netdev_trig_link_speed_attrs_group;
+
+static void set_baseline_state(struct led_netdev_data *trigger_data)
+{
+	int current_brightness;
+	struct led_classdev *led_cdev = trigger_data->led_cdev;
+
+	/* Already validated, hw control is possible with the requested mode */
+	if (trigger_data->hw_control) {
+		led_cdev->hw_control_set(led_cdev, trigger_data->mode);
+
+		return;
+	}
+
+	current_brightness = led_cdev->brightness;
+	if (current_brightness)
+		led_cdev->blink_brightness = current_brightness;
+	if (!led_cdev->blink_brightness)
+		led_cdev->blink_brightness = led_cdev->max_brightness;
+
+	if (!trigger_data->carrier_link_up) {
+		led_set_brightness(led_cdev, LED_OFF);
+	} else {
+		bool blink_on = false;
+
+		if (test_bit(TRIGGER_NETDEV_LINK, &trigger_data->mode))
+			blink_on = true;
+
+		if (test_bit(TRIGGER_NETDEV_LINK_10, &trigger_data->mode) &&
+		    trigger_data->link_speed == SPEED_10)
+			blink_on = true;
+
+		if (test_bit(TRIGGER_NETDEV_LINK_100, &trigger_data->mode) &&
+		    trigger_data->link_speed == SPEED_100)
+			blink_on = true;
+
+		if (test_bit(TRIGGER_NETDEV_LINK_1000, &trigger_data->mode) &&
+		    trigger_data->link_speed == SPEED_1000)
+			blink_on = true;
+
+		if (test_bit(TRIGGER_NETDEV_LINK_2500, &trigger_data->mode) &&
+		    trigger_data->link_speed == SPEED_2500)
+			blink_on = true;
+
+		if (test_bit(TRIGGER_NETDEV_LINK_5000, &trigger_data->mode) &&
+		    trigger_data->link_speed == SPEED_5000)
+			blink_on = true;
+
+		if (test_bit(TRIGGER_NETDEV_LINK_10000, &trigger_data->mode) &&
+		    trigger_data->link_speed == SPEED_10000)
+			blink_on = true;
+
+		if (test_bit(TRIGGER_NETDEV_LINK_25000, &trigger_data->mode) &&
+		    trigger_data->link_speed == SPEED_25000)
+			blink_on = true;
+
+		if (test_bit(TRIGGER_NETDEV_LINK_40000, &trigger_data->mode) &&
+		    trigger_data->link_speed == SPEED_40000)
+			blink_on = true;
+
+		if (test_bit(TRIGGER_NETDEV_LINK_50000, &trigger_data->mode) &&
+		    trigger_data->link_speed == SPEED_50000)
+			blink_on = true;
+
+		if (test_bit(TRIGGER_NETDEV_LINK_100000, &trigger_data->mode) &&
+		    trigger_data->link_speed == SPEED_100000)
+			blink_on = true;
+
+		if (test_bit(TRIGGER_NETDEV_HALF_DUPLEX, &trigger_data->mode) &&
+		    trigger_data->duplex == DUPLEX_HALF)
+			blink_on = true;
+
+		if (test_bit(TRIGGER_NETDEV_FULL_DUPLEX, &trigger_data->mode) &&
+		    trigger_data->duplex == DUPLEX_FULL)
+			blink_on = true;
+
+		if (blink_on)
+			led_set_brightness(led_cdev,
+					   led_cdev->blink_brightness);
+		else
+			led_set_brightness(led_cdev, LED_OFF);
+
+		/* If we are looking for RX/TX start periodically
+		 * checking stats
+		 */
+		if (test_bit(TRIGGER_NETDEV_TX, &trigger_data->mode) ||
+		    test_bit(TRIGGER_NETDEV_RX, &trigger_data->mode) ||
+		    test_bit(TRIGGER_NETDEV_TX_ERR, &trigger_data->mode) ||
+		    test_bit(TRIGGER_NETDEV_RX_ERR, &trigger_data->mode))
+			schedule_delayed_work(&trigger_data->work, 0);
+	}
+}
+
+static bool supports_hw_control(struct led_classdev *led_cdev)
+{
+	if (!led_cdev->hw_control_get || !led_cdev->hw_control_set ||
+	    !led_cdev->hw_control_is_supported)
+		return false;
+
+	return !strcmp(led_cdev->hw_control_trigger, led_cdev->trigger->name);
+}
+
+/*
+ * Validate the configured netdev is the same as the one associated with
+ * the LED driver in hw control.
+ */
+static bool validate_net_dev(struct led_classdev *led_cdev,
+			     struct net_device *net_dev)
+{
+	struct device *dev = led_cdev->hw_control_get_device(led_cdev);
+	struct net_device *ndev;
+
+	if (!dev)
+		return false;
+
+	ndev = to_net_dev(dev);
+
+	return ndev == net_dev;
+}
+
+static bool can_hw_control(struct led_netdev_data *trigger_data)
+{
+	unsigned long default_interval = msecs_to_jiffies(NETDEV_LED_DEFAULT_INTERVAL);
+	unsigned int interval = atomic_read(&trigger_data->interval);
+	struct led_classdev *led_cdev = trigger_data->led_cdev;
+	int ret;
+
+	if (!supports_hw_control(led_cdev))
+		return false;
+
+	/*
+	 * Interval must be set to the default
+	 * value. Any different value is rejected if in hw
+	 * control.
+	 */
+	if (interval != default_interval)
+		return false;
+
+	/*
+	 * net_dev must be set with hw control, otherwise no
+	 * blinking can be happening and there is nothing to
+	 * offloaded. Additionally, for hw control to be
+	 * valid, the configured netdev must be the same as
+	 * netdev associated to the LED.
+	 */
+	if (!validate_net_dev(led_cdev, trigger_data->net_dev))
+		return false;
+
+	/* Check if the requested mode is supported */
+	ret = led_cdev->hw_control_is_supported(led_cdev, trigger_data->mode);
+	/* Fall back to software blinking if not supported */
+	if (ret == -EOPNOTSUPP)
+		return false;
+	if (ret) {
+		dev_warn(led_cdev->dev,
+			 "Current mode check failed with error %d\n", ret);
+		return false;
+	}
+
+	return true;
+}
+
+static void get_device_state(struct led_netdev_data *trigger_data)
+{
+	struct ethtool_link_ksettings cmd;
+
+	trigger_data->carrier_link_up = netif_carrier_ok(trigger_data->net_dev);
+
+	if (netif_get_link_ksettings(trigger_data->net_dev, &cmd))
+		return;
+
+	if (trigger_data->carrier_link_up) {
+		trigger_data->link_speed = cmd.base.speed;
+		trigger_data->duplex = cmd.base.duplex;
+	}
+
+	/*
+	 * Have a local copy of the link speed supported to avoid rtnl lock every time
+	 * modes are refreshed on any change event
+	 */
+	linkmode_copy(trigger_data->supported_link_modes, cmd.link_modes.supported);
+}
+
+static ssize_t device_name_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct led_netdev_data *trigger_data = led_trigger_get_drvdata(dev);
+	ssize_t len;
+
+	mutex_lock(&trigger_data->lock);
+	len = sprintf(buf, "%s\n", trigger_data->device_name);
+	mutex_unlock(&trigger_data->lock);
+
+	return len;
+}
+
+static int set_device_name(struct led_netdev_data *trigger_data,
+			   const char *name, size_t size)
+{
+	struct net_device *new_dev = NULL;
+	char device_name[IFNAMSIZ];
+
+	if (size >= IFNAMSIZ)
+		return -EINVAL;
+
+	cancel_delayed_work_sync(&trigger_data->work);
+
+	memcpy(device_name, name, size);
+	device_name[size] = 0;
+	if (size > 0 && device_name[size - 1] == '\n')
+		device_name[size - 1] = 0;
+
+	/*
+	 * Lock order: rtnl_lock -> netdev instance lock -> trigger_data lock.
+	 */
+	rtnl_lock();
+	if (device_name[0]) {
+		new_dev = dev_get_by_name(&init_net, device_name);
+		if (new_dev)
+			netdev_lock_ops(new_dev);
+	}
+	mutex_lock(&trigger_data->lock);
+
+	dev_put(trigger_data->net_dev);
+	trigger_data->net_dev = new_dev;
+	strscpy(trigger_data->device_name, device_name);
+
+	trigger_data->carrier_link_up = false;
+	trigger_data->link_speed = SPEED_UNKNOWN;
+	trigger_data->duplex = DUPLEX_UNKNOWN;
+	if (trigger_data->net_dev)
+		get_device_state(trigger_data);
+
+	trigger_data->last_activity = 0;
+
+	/* Skip if we're called from netdev_trig_activate() and hw_control is true */
+	if (!trigger_data->hw_control || led_get_trigger_data(trigger_data->led_cdev))
+		set_baseline_state(trigger_data);
+
+	mutex_unlock(&trigger_data->lock);
+	if (new_dev)
+		netdev_unlock_ops(new_dev);
+	rtnl_unlock();
+
+	return 0;
+}
+
+static ssize_t device_name_store(struct device *dev,
+				 struct device_attribute *attr, const char *buf,
+				 size_t size)
+{
+	struct led_netdev_data *trigger_data = led_trigger_get_drvdata(dev);
+	int ret;
+
+	ret = set_device_name(trigger_data, buf, size);
+
+	if (ret < 0)
+		return ret;
+
+	/* Refresh link_speed visibility */
+	sysfs_update_group(&dev->kobj, &netdev_trig_link_speed_attrs_group);
+
+	return size;
+}
+
+static DEVICE_ATTR_RW(device_name);
+
+static ssize_t netdev_led_attr_show(struct device *dev, char *buf,
+				    enum led_trigger_netdev_modes attr)
+{
+	struct led_netdev_data *trigger_data = led_trigger_get_drvdata(dev);
+	int bit;
+
+	switch (attr) {
+	case TRIGGER_NETDEV_LINK:
+	case TRIGGER_NETDEV_LINK_10:
+	case TRIGGER_NETDEV_LINK_100:
+	case TRIGGER_NETDEV_LINK_1000:
+	case TRIGGER_NETDEV_LINK_2500:
+	case TRIGGER_NETDEV_LINK_5000:
+	case TRIGGER_NETDEV_LINK_10000:
+	case TRIGGER_NETDEV_LINK_25000:
+	case TRIGGER_NETDEV_LINK_40000:
+	case TRIGGER_NETDEV_LINK_50000:
+	case TRIGGER_NETDEV_LINK_100000:
+	case TRIGGER_NETDEV_HALF_DUPLEX:
+	case TRIGGER_NETDEV_FULL_DUPLEX:
+	case TRIGGER_NETDEV_TX:
+	case TRIGGER_NETDEV_RX:
+	case TRIGGER_NETDEV_TX_ERR:
+	case TRIGGER_NETDEV_RX_ERR:
+		bit = attr;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return sprintf(buf, "%u\n", test_bit(bit, &trigger_data->mode));
+}
+
+static ssize_t netdev_led_attr_store(struct device *dev, const char *buf,
+				     size_t size, enum led_trigger_netdev_modes attr)
+{
+	struct led_netdev_data *trigger_data = led_trigger_get_drvdata(dev);
+	struct led_classdev *led_cdev = trigger_data->led_cdev;
+	unsigned long state, mode = trigger_data->mode;
+	int ret;
+	int bit;
+
+	ret = kstrtoul(buf, 0, &state);
+	if (ret)
+		return ret;
+
+	switch (attr) {
+	case TRIGGER_NETDEV_LINK:
+	case TRIGGER_NETDEV_LINK_10:
+	case TRIGGER_NETDEV_LINK_100:
+	case TRIGGER_NETDEV_LINK_1000:
+	case TRIGGER_NETDEV_LINK_2500:
+	case TRIGGER_NETDEV_LINK_5000:
+	case TRIGGER_NETDEV_LINK_10000:
+	case TRIGGER_NETDEV_LINK_25000:
+	case TRIGGER_NETDEV_LINK_40000:
+	case TRIGGER_NETDEV_LINK_50000:
+	case TRIGGER_NETDEV_LINK_100000:
+	case TRIGGER_NETDEV_HALF_DUPLEX:
+	case TRIGGER_NETDEV_FULL_DUPLEX:
+	case TRIGGER_NETDEV_TX:
+	case TRIGGER_NETDEV_RX:
+	case TRIGGER_NETDEV_TX_ERR:
+	case TRIGGER_NETDEV_RX_ERR:
+		bit = attr;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (state)
+		set_bit(bit, &mode);
+	else
+		clear_bit(bit, &mode);
+
+	if (test_bit(TRIGGER_NETDEV_LINK, &mode) &&
+	    (test_bit(TRIGGER_NETDEV_LINK_10, &mode) ||
+	     test_bit(TRIGGER_NETDEV_LINK_100, &mode) ||
+	     test_bit(TRIGGER_NETDEV_LINK_1000, &mode) ||
+	     test_bit(TRIGGER_NETDEV_LINK_2500, &mode) ||
+	     test_bit(TRIGGER_NETDEV_LINK_5000, &mode) ||
+	     test_bit(TRIGGER_NETDEV_LINK_10000, &mode) ||
+	     test_bit(TRIGGER_NETDEV_LINK_25000, &mode) ||
+	     test_bit(TRIGGER_NETDEV_LINK_40000, &mode) ||
+	     test_bit(TRIGGER_NETDEV_LINK_50000, &mode) ||
+	     test_bit(TRIGGER_NETDEV_LINK_100000, &mode)))
+		return -EINVAL;
+
+	cancel_delayed_work_sync(&trigger_data->work);
+
+	trigger_data->mode = mode;
+	trigger_data->hw_control = can_hw_control(trigger_data);
+
+	if (!led_cdev->brightness_set && !led_cdev->brightness_set_blocking &&
+	    !trigger_data->hw_control)
+		return -EOPNOTSUPP;
+
+	set_baseline_state(trigger_data);
+
+	return size;
+}
+
+#define DEFINE_NETDEV_TRIGGER(trigger_name, trigger) \
+	static ssize_t trigger_name##_show(struct device *dev, \
+		struct device_attribute *attr, char *buf) \
+	{ \
+		return netdev_led_attr_show(dev, buf, trigger); \
+	} \
+	static ssize_t trigger_name##_store(struct device *dev, \
+		struct device_attribute *attr, const char *buf, size_t size) \
+	{ \
+		return netdev_led_attr_store(dev, buf, size, trigger); \
+	} \
+	static DEVICE_ATTR_RW(trigger_name)
+
+DEFINE_NETDEV_TRIGGER(link, TRIGGER_NETDEV_LINK);
+DEFINE_NETDEV_TRIGGER(link_10, TRIGGER_NETDEV_LINK_10);
+DEFINE_NETDEV_TRIGGER(link_100, TRIGGER_NETDEV_LINK_100);
+DEFINE_NETDEV_TRIGGER(link_1000, TRIGGER_NETDEV_LINK_1000);
+DEFINE_NETDEV_TRIGGER(link_2500, TRIGGER_NETDEV_LINK_2500);
+DEFINE_NETDEV_TRIGGER(link_5000, TRIGGER_NETDEV_LINK_5000);
+DEFINE_NETDEV_TRIGGER(link_10000, TRIGGER_NETDEV_LINK_10000);
+DEFINE_NETDEV_TRIGGER(link_25000, TRIGGER_NETDEV_LINK_25000);
+DEFINE_NETDEV_TRIGGER(link_40000, TRIGGER_NETDEV_LINK_40000);
+DEFINE_NETDEV_TRIGGER(link_50000, TRIGGER_NETDEV_LINK_50000);
+DEFINE_NETDEV_TRIGGER(link_100000, TRIGGER_NETDEV_LINK_100000);
+DEFINE_NETDEV_TRIGGER(half_duplex, TRIGGER_NETDEV_HALF_DUPLEX);
+DEFINE_NETDEV_TRIGGER(full_duplex, TRIGGER_NETDEV_FULL_DUPLEX);
+DEFINE_NETDEV_TRIGGER(tx, TRIGGER_NETDEV_TX);
+DEFINE_NETDEV_TRIGGER(rx, TRIGGER_NETDEV_RX);
+DEFINE_NETDEV_TRIGGER(tx_err, TRIGGER_NETDEV_TX_ERR);
+DEFINE_NETDEV_TRIGGER(rx_err, TRIGGER_NETDEV_RX_ERR);
+
+static ssize_t interval_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
+{
+	struct led_netdev_data *trigger_data = led_trigger_get_drvdata(dev);
+
+	return sprintf(buf, "%u\n",
+		       jiffies_to_msecs(atomic_read(&trigger_data->interval)));
+}
+
+static ssize_t interval_store(struct device *dev,
+			      struct device_attribute *attr, const char *buf,
+			      size_t size)
+{
+	struct led_netdev_data *trigger_data = led_trigger_get_drvdata(dev);
+	unsigned long value;
+	int ret;
+
+	if (trigger_data->hw_control)
+		return -EINVAL;
+
+	ret = kstrtoul(buf, 0, &value);
+	if (ret)
+		return ret;
+
+	/* impose some basic bounds on the timer interval */
+	if (value >= 5 && value <= 10000) {
+		cancel_delayed_work_sync(&trigger_data->work);
+
+		atomic_set(&trigger_data->interval, msecs_to_jiffies(value));
+		set_baseline_state(trigger_data);	/* resets timer */
+	}
+
+	return size;
+}
+
+static DEVICE_ATTR_RW(interval);
+
+static ssize_t offloaded_show(struct device *dev,
+			      struct device_attribute *attr, char *buf)
+{
+	struct led_netdev_data *trigger_data = led_trigger_get_drvdata(dev);
+
+	return sprintf(buf, "%d\n", trigger_data->hw_control);
+}
+
+static DEVICE_ATTR_RO(offloaded);
+
+#define CHECK_LINK_MODE_ATTR(link_speed) \
+	do { \
+		if (attr == &dev_attr_link_##link_speed.attr && \
+		    link_ksettings.base.speed == SPEED_##link_speed) \
+			return attr->mode; \
+	} while (0)
+
+static umode_t netdev_trig_link_speed_visible(struct kobject *kobj,
+					      struct attribute *attr, int n)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct led_netdev_data *trigger_data;
+	unsigned long *supported_link_modes;
+	u32 mode;
+
+	trigger_data = led_trigger_get_drvdata(dev);
+	supported_link_modes = trigger_data->supported_link_modes;
+
+	/*
+	 * Search in the supported link mode mask a matching supported mode.
+	 * Stop at the first matching entry as we care only to check if a particular
+	 * speed is supported and not the kind.
+	 */
+	for_each_set_bit(mode, supported_link_modes, __ETHTOOL_LINK_MODE_MASK_NBITS) {
+		struct ethtool_link_ksettings link_ksettings;
+
+		ethtool_params_from_link_mode(&link_ksettings, mode);
+
+		CHECK_LINK_MODE_ATTR(10);
+		CHECK_LINK_MODE_ATTR(100);
+		CHECK_LINK_MODE_ATTR(1000);
+		CHECK_LINK_MODE_ATTR(2500);
+		CHECK_LINK_MODE_ATTR(5000);
+		CHECK_LINK_MODE_ATTR(10000);
+		CHECK_LINK_MODE_ATTR(25000);
+		CHECK_LINK_MODE_ATTR(40000);
+		CHECK_LINK_MODE_ATTR(50000);
+		CHECK_LINK_MODE_ATTR(100000);
+	}
+
+	return 0;
+}
+
+static struct attribute *netdev_trig_link_speed_attrs[] = {
+	&dev_attr_link_10.attr,
+	&dev_attr_link_100.attr,
+	&dev_attr_link_1000.attr,
+	&dev_attr_link_2500.attr,
+	&dev_attr_link_5000.attr,
+	&dev_attr_link_10000.attr,
+	&dev_attr_link_25000.attr,
+	&dev_attr_link_40000.attr,
+	&dev_attr_link_50000.attr,
+	&dev_attr_link_100000.attr,
+	NULL
+};
+
+static const struct attribute_group netdev_trig_link_speed_attrs_group = {
+	.attrs = netdev_trig_link_speed_attrs,
+	.is_visible = netdev_trig_link_speed_visible,
+};
+
+static struct attribute *netdev_trig_attrs[] = {
+	&dev_attr_device_name.attr,
+	&dev_attr_link.attr,
+	&dev_attr_full_duplex.attr,
+	&dev_attr_half_duplex.attr,
+	&dev_attr_rx.attr,
+	&dev_attr_tx.attr,
+	&dev_attr_rx_err.attr,
+	&dev_attr_tx_err.attr,
+	&dev_attr_interval.attr,
+	&dev_attr_offloaded.attr,
+	NULL
+};
+
+static const struct attribute_group netdev_trig_attrs_group = {
+	.attrs = netdev_trig_attrs,
+};
+
+static const struct attribute_group *netdev_trig_groups[] = {
+	&netdev_trig_attrs_group,
+	&netdev_trig_link_speed_attrs_group,
+	NULL,
+};
+
+static int netdev_trig_notify(struct notifier_block *nb,
+			      unsigned long evt, void *dv)
+{
+	struct net_device *dev =
+		netdev_notifier_info_to_dev((struct netdev_notifier_info *)dv);
+	struct led_netdev_data *trigger_data =
+		container_of(nb, struct led_netdev_data, notifier);
+	struct led_classdev *led_cdev = trigger_data->led_cdev;
+
+	if (evt != NETDEV_UP && evt != NETDEV_DOWN && evt != NETDEV_CHANGE
+	    && evt != NETDEV_REGISTER && evt != NETDEV_UNREGISTER
+	    && evt != NETDEV_CHANGENAME)
+		return NOTIFY_DONE;
+
+	if (!(dev == trigger_data->net_dev ||
+	      (evt == NETDEV_CHANGENAME && !strcmp(dev->name, trigger_data->device_name)) ||
+	      (evt == NETDEV_REGISTER && !strcmp(dev->name, trigger_data->device_name))))
+		return NOTIFY_DONE;
+
+	cancel_delayed_work_sync(&trigger_data->work);
+
+	mutex_lock(&trigger_data->lock);
+
+	trigger_data->carrier_link_up = false;
+	trigger_data->link_speed = SPEED_UNKNOWN;
+	trigger_data->duplex = DUPLEX_UNKNOWN;
+	switch (evt) {
+	case NETDEV_CHANGENAME:
+	case NETDEV_REGISTER:
+		dev_put(trigger_data->net_dev);
+		dev_hold(dev);
+		trigger_data->net_dev = dev;
+		if (evt == NETDEV_CHANGENAME)
+			get_device_state(trigger_data);
+		break;
+	case NETDEV_UNREGISTER:
+		dev_put(trigger_data->net_dev);
+		trigger_data->net_dev = NULL;
+		break;
+	case NETDEV_UP:
+		trigger_data->hw_control = can_hw_control(trigger_data);
+		fallthrough;
+	case NETDEV_CHANGE:
+		get_device_state(trigger_data);
+		/* Refresh link_speed visibility */
+		if (evt == NETDEV_CHANGE)
+			sysfs_update_group(&led_cdev->dev->kobj,
+					   &netdev_trig_link_speed_attrs_group);
+		break;
+	}
+
+	set_baseline_state(trigger_data);
+
+	mutex_unlock(&trigger_data->lock);
+
+	return NOTIFY_DONE;
+}
+
+/* here's the real work! */
+static void netdev_trig_work(struct work_struct *work)
+{
+	struct led_netdev_data *trigger_data =
+		container_of(work, struct led_netdev_data, work.work);
+	struct rtnl_link_stats64 *dev_stats;
+	unsigned int new_activity;
+	struct rtnl_link_stats64 temp;
+	unsigned long interval;
+	int invert;
+
+	/* If we dont have a device, insure we are off */
+	if (!trigger_data->net_dev) {
+		led_set_brightness(trigger_data->led_cdev, LED_OFF);
+		return;
+	}
+
+	/* If we are not looking for RX/TX then return  */
+	if (!test_bit(TRIGGER_NETDEV_TX, &trigger_data->mode) &&
+	    !test_bit(TRIGGER_NETDEV_RX, &trigger_data->mode) &&
+	    !test_bit(TRIGGER_NETDEV_TX_ERR, &trigger_data->mode) &&
+	    !test_bit(TRIGGER_NETDEV_RX_ERR, &trigger_data->mode))
+		return;
+
+	dev_stats = dev_get_stats(trigger_data->net_dev, &temp);
+	new_activity =
+	    (test_bit(TRIGGER_NETDEV_TX, &trigger_data->mode) ?
+		dev_stats->tx_packets : 0) +
+	    (test_bit(TRIGGER_NETDEV_RX, &trigger_data->mode) ?
+		dev_stats->rx_packets : 0) +
+	    (test_bit(TRIGGER_NETDEV_TX_ERR, &trigger_data->mode) ?
+		dev_stats->tx_errors : 0) +
+	    (test_bit(TRIGGER_NETDEV_RX_ERR, &trigger_data->mode) ?
+		dev_stats->rx_errors : 0);
+
+	if (trigger_data->last_activity != new_activity) {
+		led_stop_software_blink(trigger_data->led_cdev);
+
+		invert = test_bit(TRIGGER_NETDEV_LINK, &trigger_data->mode) ||
+			 test_bit(TRIGGER_NETDEV_LINK_10, &trigger_data->mode) ||
+			 test_bit(TRIGGER_NETDEV_LINK_100, &trigger_data->mode) ||
+			 test_bit(TRIGGER_NETDEV_LINK_1000, &trigger_data->mode) ||
+			 test_bit(TRIGGER_NETDEV_LINK_2500, &trigger_data->mode) ||
+			 test_bit(TRIGGER_NETDEV_LINK_5000, &trigger_data->mode) ||
+			 test_bit(TRIGGER_NETDEV_LINK_10000, &trigger_data->mode) ||
+			 test_bit(TRIGGER_NETDEV_LINK_25000, &trigger_data->mode) ||
+			 test_bit(TRIGGER_NETDEV_LINK_40000, &trigger_data->mode) ||
+			 test_bit(TRIGGER_NETDEV_LINK_50000, &trigger_data->mode) ||
+			 test_bit(TRIGGER_NETDEV_LINK_100000, &trigger_data->mode) ||
+			 test_bit(TRIGGER_NETDEV_HALF_DUPLEX, &trigger_data->mode) ||
+			 test_bit(TRIGGER_NETDEV_FULL_DUPLEX, &trigger_data->mode);
+		interval = jiffies_to_msecs(
+				atomic_read(&trigger_data->interval));
+		/* base state is ON (link present) */
+		led_blink_set_oneshot(trigger_data->led_cdev,
+				      &interval,
+				      &interval,
+				      invert);
+		trigger_data->last_activity = new_activity;
+	}
+
+	schedule_delayed_work(&trigger_data->work,
+			(atomic_read(&trigger_data->interval)*2));
+}
+
+static int netdev_trig_activate(struct led_classdev *led_cdev)
+{
+	struct led_netdev_data *trigger_data;
+	unsigned long mode = 0;
+	struct device *dev;
+	int rc;
+
+	trigger_data = kzalloc_obj(struct led_netdev_data);
+	if (!trigger_data)
+		return -ENOMEM;
+
+	mutex_init(&trigger_data->lock);
+
+	trigger_data->notifier.notifier_call = netdev_trig_notify;
+	trigger_data->notifier.priority = 10;
+
+	INIT_DELAYED_WORK(&trigger_data->work, netdev_trig_work);
+
+	trigger_data->led_cdev = led_cdev;
+	trigger_data->net_dev = NULL;
+	trigger_data->device_name[0] = 0;
+
+	trigger_data->mode = 0;
+	atomic_set(&trigger_data->interval, msecs_to_jiffies(NETDEV_LED_DEFAULT_INTERVAL));
+	trigger_data->last_activity = 0;
+
+	/* Check if hw control is active by default on the LED.
+	 * Init already enabled mode in hw control.
+	 */
+	if (supports_hw_control(led_cdev)) {
+		dev = led_cdev->hw_control_get_device(led_cdev);
+		if (dev) {
+			const char *name = dev_name(dev);
+
+			trigger_data->hw_control = true;
+			set_device_name(trigger_data, name, strlen(name));
+
+			rc = led_cdev->hw_control_get(led_cdev, &mode);
+			if (!rc)
+				trigger_data->mode = mode;
+		}
+	}
+
+	led_set_trigger_data(led_cdev, trigger_data);
+
+	rc = register_netdevice_notifier(&trigger_data->notifier);
+	if (rc)
+		kfree(trigger_data);
+
+	return rc;
+}
+
+static void netdev_trig_deactivate(struct led_classdev *led_cdev)
+{
+	struct led_netdev_data *trigger_data = led_get_trigger_data(led_cdev);
+
+	unregister_netdevice_notifier(&trigger_data->notifier);
+
+	cancel_delayed_work_sync(&trigger_data->work);
+
+	dev_put(trigger_data->net_dev);
+
+	kfree(trigger_data);
+}
+
+static struct led_trigger netdev_led_trigger = {
+	.name = "netdev",
+	.activate = netdev_trig_activate,
+	.deactivate = netdev_trig_deactivate,
+	.groups = netdev_trig_groups,
+};
+
+module_led_trigger(netdev_led_trigger);
+
+MODULE_AUTHOR("Ben Whitten <ben.whitten@gmail.com>");
+MODULE_AUTHOR("Oliver Jowett <oliver@opencloud.com>");
+MODULE_DESCRIPTION("Netdev LED trigger");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("ledtrig:netdev");